diff options
| author | Dave Airlie <airlied@redhat.com> | 2021-06-23 10:07:48 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2021-06-23 10:07:48 +1000 |
| commit | f45fbbb6d5cff29ddfc708676ec1c2496eed3a07 (patch) | |
| tree | 5496fee9f6b10da368aa49b03612061156e42d2f | |
| parent | d472b36efbf8a27dc8a80519db8b5a8caffe42b6 (diff) | |
| parent | 13311e74253fe64329390df80bed3f07314ddd61 (diff) | |
Backmerge tag 'v5.13-rc7' into drm-next
Backmerge Linux 5.13-rc7 to make some pulls from later bases apply,
and to bake in the conflicts so far.
1141 files changed, 13286 insertions, 5752 deletions
diff --git a/.clang-format b/.clang-format index c24b147cac01..15d4eaabc6b5 100644 --- a/.clang-format +++ b/.clang-format @@ -109,8 +109,8 @@ ForEachMacros: - 'css_for_each_child' - 'css_for_each_descendant_post' - 'css_for_each_descendant_pre' - - 'cxl_for_each_cmd' - 'device_for_each_child_node' + - 'displayid_iter_for_each' - 'dma_fence_chain_for_each' - 'do_for_each_ftrace_op' - 'drm_atomic_crtc_for_each_plane' @@ -136,6 +136,7 @@ ForEachMacros: - 'drm_mm_for_each_node_in_range' - 'drm_mm_for_each_node_safe' - 'flow_action_for_each' + - 'for_each_acpi_dev_match' - 'for_each_active_dev_scope' - 'for_each_active_drhd_unit' - 'for_each_active_iommu' @@ -171,7 +172,6 @@ ForEachMacros: - 'for_each_dapm_widgets' - 'for_each_dev_addr' - 'for_each_dev_scope' - - 'for_each_displayid_db' - 'for_each_dma_cap_mask' - 'for_each_dpcm_be' - 'for_each_dpcm_be_rollback' @@ -179,6 +179,7 @@ ForEachMacros: - 'for_each_dpcm_fe' - 'for_each_drhd_unit' - 'for_each_dss_dev' + - 'for_each_dtpm_table' - 'for_each_efi_memory_desc' - 'for_each_efi_memory_desc_in_map' - 'for_each_element' @@ -215,6 +216,7 @@ ForEachMacros: - 'for_each_migratetype_order' - 'for_each_msi_entry' - 'for_each_msi_entry_safe' + - 'for_each_msi_vector' - 'for_each_net' - 'for_each_net_continue_reverse' - 'for_each_netdev' @@ -270,6 +272,12 @@ ForEachMacros: - 'for_each_prime_number_from' - 'for_each_process' - 'for_each_process_thread' + - 'for_each_prop_codec_conf' + - 'for_each_prop_dai_codec' + - 'for_each_prop_dai_cpu' + - 'for_each_prop_dlc_codecs' + - 'for_each_prop_dlc_cpus' + - 'for_each_prop_dlc_platforms' - 'for_each_property_of_node' - 'for_each_registered_fb' - 'for_each_requested_gpio' @@ -430,6 +438,7 @@ ForEachMacros: - 'queue_for_each_hw_ctx' - 'radix_tree_for_each_slot' - 'radix_tree_for_each_tagged' + - 'rb_for_each' - 'rbtree_postorder_for_each_entry_safe' - 'rdma_for_each_block' - 'rdma_for_each_port' @@ -243,6 +243,9 @@ Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com> Mayuresh Janorkar <mayur@ti.com> Michael Buesch <m@bues.ch> Michel Dänzer <michel@tungstengraphics.com> +Michel Lespinasse <michel@lespinasse.org> +Michel Lespinasse <michel@lespinasse.org> <walken@google.com> +Michel Lespinasse <michel@lespinasse.org> <walken@zoy.org> Miguel Ojeda <ojeda@kernel.org> <miguel.ojeda.sandonis@gmail.com> Mike Rapoport <rppt@kernel.org> <mike@compulab.co.il> Mike Rapoport <rppt@kernel.org> <mike.rapoport@gmail.com> diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 7ca8df5451d4..68b21395a743 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1458,11 +1458,22 @@ unprivileged_bpf_disabled ========================= Writing 1 to this entry will disable unprivileged calls to ``bpf()``; -once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` will return -``-EPERM``. +once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` or ``CAP_BPF`` +will return ``-EPERM``. Once set to 1, this can't be cleared from the +running kernel anymore. -Once set, this can't be cleared. +Writing 2 to this entry will also disable unprivileged calls to ``bpf()``, +however, an admin can still change this setting later on, if needed, by +writing 0 or 1 to this entry. +If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in the kernel config, then this +entry will default to 2 instead of 0. + += ============================================================= +0 Unprivileged calls to ``bpf()`` are enabled +1 Unprivileged calls to ``bpf()`` are disabled without recovery +2 Unprivileged calls to ``bpf()`` are disabled += ============================================================= watchdog ======== diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml index 32509b98142e..92b49bc37939 100644 --- a/Documentation/devicetree/bindings/connector/usb-connector.yaml +++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml @@ -149,6 +149,17 @@ properties: maxItems: 6 $ref: /schemas/types.yaml#/definitions/uint32-array + sink-vdos-v1: + description: An array of u32 with each entry, a Vendor Defined Message Object (VDO), + providing additional information corresponding to the product, the detailed bit + definitions and the order of each VDO can be found in + "USB Power Delivery Specification Revision 2.0, Version 1.3" chapter 6.4.4.3.1 Discover + Identity. User can specify the VDO array via VDO_IDH/_CERT/_PRODUCT/_CABLE/_AMA defined in + dt-bindings/usb/pd.h. + minItems: 3 + maxItems: 6 + $ref: /schemas/types.yaml#/definitions/uint32-array + op-sink-microwatt: description: Sink required operating power in microwatt, if source can't offer the power, Capability Mismatch is set. Required for power sink and @@ -207,6 +218,10 @@ properties: SNK_READY for non-pd link. type: boolean +dependencies: + sink-vdos-v1: [ 'sink-vdos' ] + sink-vdos: [ 'sink-vdos-v1' ] + required: - compatible diff --git a/Documentation/devicetree/bindings/hwmon/ti,ads7828.yaml b/Documentation/devicetree/bindings/hwmon/ti,ads7828.yaml index 33ee575bb09d..926be9a29044 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,ads7828.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,ads7828.yaml @@ -49,7 +49,7 @@ examples: #size-cells = <0>; adc@48 { - comatible = "ti,ads7828"; + compatible = "ti,ads7828"; reg = <0x48>; vref-supply = <&vref>; ti,differential-input; diff --git a/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml b/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml index 7b553d559c83..98c6fcf7bf26 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml @@ -46,6 +46,13 @@ properties: description: | I2C bus timeout in microseconds + fsl,i2c-erratum-a004447: + $ref: /schemas/types.yaml#/definitions/flag + description: | + Indicates the presence of QorIQ erratum A-004447, which + says that the standard i2c recovery scheme mechanism does + not work and an alternate implementation is needed. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/media/renesas,drif.yaml b/Documentation/devicetree/bindings/media/renesas,drif.yaml index ce505a7c006a..9cd56ff2c316 100644 --- a/Documentation/devicetree/bindings/media/renesas,drif.yaml +++ b/Documentation/devicetree/bindings/media/renesas,drif.yaml @@ -67,9 +67,7 @@ properties: maxItems: 1 clock-names: - maxItems: 1 - items: - - const: fck + const: fck resets: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 8ce5ed8a58dd..c101a1ec846e 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -10,7 +10,7 @@ allOf: - $ref: ethernet-controller.yaml# maintainers: - - Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> + - Sergei Shtylyov <sergei.shtylyov@gmail.com> properties: compatible: diff --git a/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml b/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml index db61f0731a20..2e35aeaa8781 100644 --- a/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml +++ b/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml @@ -57,7 +57,7 @@ patternProperties: rate sound-dai: - $ref: /schemas/types.yaml#/definitions/phandle + $ref: /schemas/types.yaml#/definitions/phandle-array description: phandle of the CPU DAI patternProperties: @@ -71,7 +71,7 @@ patternProperties: properties: sound-dai: - $ref: /schemas/types.yaml#/definitions/phandle + $ref: /schemas/types.yaml#/definitions/phandle-array description: phandle of the codec DAI required: diff --git a/Documentation/devicetree/bindings/spi/spi-mux.yaml b/Documentation/devicetree/bindings/spi/spi-mux.yaml index d09c6355e22d..51c7622dc20b 100644 --- a/Documentation/devicetree/bindings/spi/spi-mux.yaml +++ b/Documentation/devicetree/bindings/spi/spi-mux.yaml @@ -72,7 +72,7 @@ examples: mux-controls = <&mux>; - spi-flash@0 { + flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <40000000>; diff --git a/Documentation/driver-api/usb/usb.rst b/Documentation/driver-api/usb/usb.rst index 820e867af45a..2c94ff2f4385 100644 --- a/Documentation/driver-api/usb/usb.rst +++ b/Documentation/driver-api/usb/usb.rst @@ -123,6 +123,8 @@ are in ``drivers/usb/common/common.c``. In addition, some functions useful for creating debugging output are defined in ``drivers/usb/common/debug.c``. +.. _usb_header: + Host-Side Data Types and Macros =============================== diff --git a/Documentation/riscv/vm-layout.rst b/Documentation/riscv/vm-layout.rst index 329d32098af4..b7f98930d38d 100644 --- a/Documentation/riscv/vm-layout.rst +++ b/Documentation/riscv/vm-layout.rst @@ -58,6 +58,6 @@ RISC-V Linux Kernel SV39 | ____________________________________________________________|____________________________________________________________ | | | | - ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | modules - ffffffff80000000 | -2 GB | ffffffffffffffff | 2 GB | kernel, BPF + ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | modules, BPF + ffffffff80000000 | -2 GB | ffffffffffffffff | 2 GB | kernel __________________|____________|__________________|_________|____________________________________________________________ diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index bd9165241b6c..6efb41cc8072 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -250,14 +250,14 @@ Users can read via ``ioctl(SECCOMP_IOCTL_NOTIF_RECV)`` (or ``poll()``) on a seccomp notification fd to receive a ``struct seccomp_notif``, which contains five members: the input length of the structure, a unique-per-filter ``id``, the ``pid`` of the task which triggered this request (which may be 0 if the -task is in a pid ns not visible from the listener's pid namespace), a ``flags`` -member which for now only has ``SECCOMP_NOTIF_FLAG_SIGNALED``, representing -whether or not the notification is a result of a non-fatal signal, and the -``data`` passed to seccomp. Userspace can then make a decision based on this -information about what to do, and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a -response, indicating what should be returned to userspace. The ``id`` member of -``struct seccomp_notif_resp`` should be the same ``id`` as in ``struct -seccomp_notif``. +task is in a pid ns not visible from the listener's pid namespace). The +notification also contains the ``data`` passed to seccomp, and a filters flag. +The structure should be zeroed out prior to calling the ioctl. + +Userspace can then make a decision based on this information about what to do, +and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a response, indicating what should be +returned to userspace. The ``id`` member of ``struct seccomp_notif_resp`` should +be the same ``id`` as in ``struct seccomp_notif``. It is worth noting that ``struct seccomp_data`` contains the values of register arguments to the syscall, but does not contain pointers to memory. The task's diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index 5bfe28b0728e..20d85daed395 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -171,8 +171,8 @@ Shadow pages contain the following information: shadow pages) so role.quadrant takes values in the range 0..3. Each quadrant maps 1GB virtual address space. role.access: - Inherited guest access permissions in the form uwx. Note execute - permission is positive, not negative. + Inherited guest access permissions from the parent ptes in the form uwx. + Note execute permission is positive, not negative. role.invalid: The page is invalid and should not be used. It is a root page that is currently pinned (by a cpu hardware register pointing to it); once it is diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 5feb3706a7ae..af1b37441e0a 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -118,10 +118,12 @@ KVM_REQ_MMU_RELOAD necessary to inform each VCPU to completely refresh the tables. This request is used for that. -KVM_REQ_PENDING_TIMER +KVM_REQ_UNBLOCK - This request may be made from a timer handler run on the host on behalf - of a VCPU. It informs the VCPU thread to inject a timer interrupt. + This request informs the vCPU to exit kvm_vcpu_block. It is used for + example from timer handlers that run on the host on behalf of a vCPU, + or in order to update the interrupt routing and ensure that assigned + devices will wake up the vCPU. KVM_REQ_UNHALT diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst index 03f294a638bd..d3028554b1e9 100644 --- a/Documentation/vm/slub.rst +++ b/Documentation/vm/slub.rst @@ -181,7 +181,7 @@ SLUB Debug output Here is a sample of slub debug output:: ==================================================================== - BUG kmalloc-8: Redzone overwritten + BUG kmalloc-8: Right Redzone overwritten -------------------------------------------------------------------- INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc @@ -189,10 +189,10 @@ Here is a sample of slub debug output:: INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58 INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554 - Bytes b4 0xc90f6d10: 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ - Object 0xc90f6d20: 31 30 31 39 2e 30 30 35 1019.005 - Redzone 0xc90f6d28: 00 cc cc cc . - Padding 0xc90f6d50: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ + Bytes b4 (0xc90f6d10): 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ + Object (0xc90f6d20): 31 30 31 39 2e 30 30 35 1019.005 + Redzone (0xc90f6d28): 00 cc cc cc . + Padding (0xc90f6d50): 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ [<c010523d>] dump_trace+0x63/0x1eb [<c01053df>] show_trace_log_lvl+0x1a/0x2f diff --git a/MAINTAINERS b/MAINTAINERS index bc336961ed52..b2cbb5c49358 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3877,6 +3877,7 @@ L: linux-btrfs@vger.kernel.org S: Maintained W: http://btrfs.wiki.kernel.org/ Q: http://patchwork.kernel.org/project/linux-btrfs/list/ +C: irc://irc.libera.chat/btrfs T: git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git F: Documentation/filesystems/btrfs.rst F: fs/btrfs/ @@ -4138,6 +4139,14 @@ S: Odd Fixes F: Documentation/devicetree/bindings/arm/cavium-thunder2.txt F: arch/arm64/boot/dts/cavium/thunder2-99xx* +CBS/ETF/TAPRIO QDISCS +M: Vinicius Costa Gomes <vinicius.gomes@intel.com> +S: Maintained +L: netdev@vger.kernel.org +F: net/sched/sch_cbs.c +F: net/sched/sch_etf.c +F: net/sched/sch_taprio.c + CC2520 IEEE-802.15.4 RADIO DRIVER M: Varka Bhadram <varkabhadram@gmail.com> L: linux-wpan@vger.kernel.org @@ -5569,7 +5578,6 @@ F: drivers/soc/fsl/dpio DPAA2 ETHERNET DRIVER M: Ioana Ciornei <ioana.ciornei@nxp.com> -M: Ioana Radulescu <ruxandra.radulescu@nxp.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/freescale/dpaa2/ethernet-driver.rst @@ -6953,6 +6961,7 @@ F: net/core/failover.c FANOTIFY M: Jan Kara <jack@suse.cz> R: Amir Goldstein <amir73il@gmail.com> +R: Matthew Bobrowski <repnop@google.com> L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/notify/fanotify/ @@ -12704,9 +12713,9 @@ F: drivers/rtc/rtc-ntxec.c F: include/linux/mfd/ntxec.h NETRONOME ETHERNET DRIVERS -M: Simon Horman <simon.horman@netronome.com> +M: Simon Horman <simon.horman@corigine.com> R: Jakub Kicinski <kuba@kernel.org> -L: oss-drivers@netronome.com +L: oss-drivers@corigine.com S: Maintained F: drivers/net/ethernet/netronome/ @@ -12733,7 +12742,6 @@ M: "David S. Miller" <davem@davemloft.net> M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net Q: https://patchwork.kernel.org/project/netdevbpf/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git @@ -12778,7 +12786,6 @@ M: "David S. Miller" <davem@davemloft.net> M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net Q: https://patchwork.kernel.org/project/netdevbpf/list/ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -12920,8 +12927,10 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM +M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +L: linux-nfc@lists.01.org (subscribers-only) L: netdev@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h @@ -12932,7 +12941,7 @@ F: net/nfc/ NFC VIRTUAL NCI DEVICE DRIVER M: Bongsu Jeon <bongsu.jeon@samsung.com> L: netdev@vger.kernel.org -L: linux-nfc@lists.01.org (moderated for non-subscribers) +L: linux-nfc@lists.01.org (subscribers-only) S: Supported F: drivers/nfc/virtual_ncidev.c F: tools/testing/selftests/nci/ @@ -13229,9 +13238,8 @@ F: Documentation/devicetree/bindings/sound/tfa9879.txt F: sound/soc/codecs/tfa9879* NXP-NCI NFC DRIVER -M: Clément Perrochaud <clement.perrochaud@effinnov.com> R: Charles Gorand <charles.gorand@effinnov.com> -L: linux-nfc@lists.01.org (moderated for non-subscribers) +L: linux-nfc@lists.01.org (subscribers-only) S: Supported F: drivers/nfc/nxp-nci @@ -14134,6 +14142,7 @@ F: drivers/pci/controller/pci-v3-semi.c PCI ENDPOINT SUBSYSTEM M: Kishon Vijay Abraham I <kishon@ti.com> M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> +R: Krzysztof WilczyÅ„ski <kw@linux.com> L: linux-pci@vger.kernel.org S: Supported F: Documentation/PCI/endpoint/* @@ -14182,6 +14191,7 @@ F: drivers/pci/controller/pci-xgene-msi.c PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> R: Rob Herring <robh@kernel.org> +R: Krzysztof WilczyÅ„ski <kw@linux.com> L: linux-pci@vger.kernel.org S: Supported Q: http://patchwork.ozlabs.org/project/linux-pci/list/ @@ -14341,10 +14351,12 @@ PER-CPU MEMORY ALLOCATOR M: Dennis Zhou <dennis@kernel.org> M: Tejun Heo <tj@kernel.org> M: Christoph Lameter <cl@linux.com> +L: linux-mm@kvack.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu.git F: arch/*/include/asm/percpu.h F: include/linux/percpu*.h +F: lib/percpu*.c F: mm/percpu*.c PER-TASK DELAY ACCOUNTING @@ -15969,6 +15981,7 @@ S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/net/*iucv* @@ -15979,6 +15992,7 @@ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/net/ @@ -16157,7 +16171,7 @@ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> M: Krzysztof Opasiak <k.opasiak@samsung.com> -L: linux-nfc@lists.01.org (moderated for non-subscribers) +L: linux-nfc@lists.01.org (subscribers-only) S: Maintained F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml F: drivers/nfc/s3fwrn5 @@ -16570,6 +16584,7 @@ F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS M: Karsten Graul <kgraul@linux.ibm.com> +M: Guvenc Gulce <guvenc@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -17328,6 +17343,12 @@ L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-stm32* +ST STM32 SPI DRIVER +M: Alain Volmat <alain.volmat@foss.st.com> +L: linux-spi@vger.kernel.org +S: Maintained +F: drivers/spi/spi-stm32.c + ST STPDDC60 DRIVER M: Daniel Nilsson <daniel.nilsson@flex.com> L: linux-hwmon@vger.kernel.org @@ -17686,7 +17707,6 @@ R: Mika Westerberg <mika.westerberg@linux.intel.com> L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-designware-* -F: include/linux/platform_data/i2c-designware.h SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER M: Jaehoon Chung <jh80.chung@samsung.com> @@ -18342,7 +18362,7 @@ F: sound/soc/codecs/tas571x* TI TRF7970A NFC DRIVER M: Mark Greer <mgreer@animalcreek.com> L: linux-wireless@vger.kernel.org -L: linux-nfc@lists.01.org (moderated for non-subscribers) +L: linux-nfc@lists.01.org (subscribers-only) S: Supported F: Documentation/devicetree/bindings/net/nfc/trf7970a.txt F: drivers/nfc/trf7970a.c @@ -18878,6 +18898,13 @@ S: Maintained F: drivers/usb/host/isp116x* F: include/linux/usb/isp116x.h +USB ISP1760 DRIVER +M: Rui Miguel Silva <rui.silva@linaro.org> +L: linux-usb@vger.kernel.org +S: Maintained +F: drivers/usb/isp1760/* +F: Documentation/devicetree/bindings/usb/nxp,isp1760.yaml + USB LAN78XX ETHERNET DRIVER M: Woojung Huh <woojung.huh@microchip.com> M: UNGLinuxDriver@microchip.com @@ -20022,6 +20049,7 @@ F: arch/x86/xen/*swiotlb* F: drivers/xen/*swiotlb* XFS FILESYSTEM +C: irc://irc.oftc.net/xfs M: Darrick J. Wong <djwong@kernel.org> M: linux-xfs@vger.kernel.org L: linux-xfs@vger.kernel.org @@ -2,8 +2,8 @@ VERSION = 5 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc3 -NAME = Frozen Wasteland +EXTRAVERSION = -rc7 +NAME = Opossums on Parade # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -928,6 +928,14 @@ CC_FLAGS_LTO += -fvisibility=hidden # Limit inlining across translation units to reduce binary size KBUILD_LDFLAGS += -mllvm -import-instr-limit=5 + +# Check for frame size exceeding threshold during prolog/epilog insertion +# when using lld < 13.0.0. +ifneq ($(CONFIG_FRAME_WARN),0) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 130000; echo $$?),0) +KBUILD_LDFLAGS += -plugin-opt=-warn-stack-size=$(CONFIG_FRAME_WARN) +endif +endif endif ifdef CONFIG_LTO diff --git a/arch/arc/include/uapi/asm/sigcontext.h b/arch/arc/include/uapi/asm/sigcontext.h index 95f8a4380e11..7a5449dfcb29 100644 --- a/arch/arc/include/uapi/asm/sigcontext.h +++ b/arch/arc/include/uapi/asm/sigcontext.h @@ -18,6 +18,7 @@ */ struct sigcontext { struct user_regs_struct regs; + struct user_regs_arcv2 v2abi; }; #endif /* _ASM_ARC_SIGCONTEXT_H */ diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index b3ccb9e5ffe4..cb2f88502baf 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -61,6 +61,41 @@ struct rt_sigframe { unsigned int sigret_magic; }; +static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +{ + int err = 0; +#ifndef CONFIG_ISA_ARCOMPACT + struct user_regs_arcv2 v2abi; + + v2abi.r30 = regs->r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + v2abi.r58 = regs->r58; + v2abi.r59 = regs->r59; +#else + v2abi.r58 = v2abi.r59 = 0; +#endif + err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi)); +#endif + return err; +} + +static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +{ + int err = 0; +#ifndef CONFIG_ISA_ARCOMPACT + struct user_regs_arcv2 v2abi; + + err = __copy_from_user(&v2abi, &mctx->v2abi, sizeof(v2abi)); + + regs->r30 = v2abi.r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + regs->r58 = v2abi.r58; + regs->r59 = v2abi.r59; +#endif +#endif + return err; +} + static int stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) @@ -94,6 +129,10 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), &uregs.scratch, sizeof(sf->uc.uc_mcontext.regs.scratch)); + + if (is_isa_arcv2()) + err |= save_arcv2_regs(&(sf->uc.uc_mcontext), regs); + err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); return err ? -EFAULT : 0; @@ -109,6 +148,10 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) err |= __copy_from_user(&uregs.scratch, &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); + + if (is_isa_arcv2()) + err |= restore_arcv2_regs(&(sf->uc.uc_mcontext), regs); + if (err) return -EFAULT; diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 33ce59d91461..e2146a8da195 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -57,7 +57,6 @@ SECTIONS .init.ramfs : { INIT_RAM_FS } . = ALIGN(PAGE_SIZE); - _stext = .; HEAD_TEXT_SECTION INIT_TEXT_SECTION(L1_CACHE_BYTES) @@ -83,6 +82,7 @@ SECTIONS .text : { _text = .; + _stext = .; TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi index 7d2c72562c73..9148a01ed6d9 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -105,9 +105,13 @@ phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; phy-reset-duration = <20>; phy-supply = <&sw2_reg>; - phy-handle = <ðphy0>; status = "okay"; + fixed-link { + speed = <1000>; + full-duplex; + }; + mdio { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6q-dhcom-som.dtsi b/arch/arm/boot/dts/imx6q-dhcom-som.dtsi index 236fc205c389..d0768ae429fa 100644 --- a/arch/arm/boot/dts/imx6q-dhcom-som.dtsi +++ b/arch/arm/boot/dts/imx6q-dhcom-som.dtsi @@ -406,6 +406,18 @@ vin-supply = <&sw1_reg>; }; +®_pu { + vin-supply = <&sw1_reg>; +}; + +®_vdd1p1 { + vin-supply = <&sw2_reg>; +}; + +®_vdd2p5 { + vin-supply = <&sw2_reg>; +}; + &uart1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart1>; diff --git a/arch/arm/boot/dts/imx6qdl-emcon-avari.dtsi b/arch/arm/boot/dts/imx6qdl-emcon-avari.dtsi index 828cf3e39784..c4e146f3341b 100644 --- a/arch/arm/boot/dts/imx6qdl-emcon-avari.dtsi +++ b/arch/arm/boot/dts/imx6qdl-emcon-avari.dtsi @@ -126,7 +126,7 @@ compatible = "nxp,pca8574"; reg = <0x3a>; gpio-controller; - #gpio-cells = <1>; + #gpio-cells = <2>; }; }; diff --git a/arch/arm/boot/dts/imx7d-meerkat96.dts b/arch/arm/boot/dts/imx7d-meerkat96.dts index 5339210b63d0..dd8003bd1fc0 100644 --- a/arch/arm/boot/dts/imx7d-meerkat96.dts +++ b/arch/arm/boot/dts/imx7d-meerkat96.dts @@ -193,7 +193,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usdhc1>; keep-power-in-suspend; - tuning-step = <2>; + fsl,tuning-step = <2>; vmmc-supply = <®_3p3v>; no-1-8-v; broken-cd; diff --git a/arch/arm/boot/dts/imx7d-pico.dtsi b/arch/arm/boot/dts/imx7d-pico.dtsi index e57da0d32b98..e519897fae08 100644 --- a/arch/arm/boot/dts/imx7d-pico.dtsi +++ b/arch/arm/boot/dts/imx7d-pico.dtsi @@ -351,7 +351,7 @@ pinctrl-2 = <&pinctrl_usdhc1_200mhz>; cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; bus-width = <4>; - tuning-step = <2>; + fsl,tuning-step = <2>; vmmc-supply = <®_3p3v>; wakeup-source; no-1-8-v; diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h index 0d67ed682e07..bc4ffa7ca04c 100644 --- a/arch/arm/include/asm/cpuidle.h +++ b/arch/arm/include/asm/cpuidle.h @@ -7,9 +7,11 @@ #ifdef CONFIG_CPU_IDLE extern int arm_cpuidle_simple_enter(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); +#define __cpuidle_method_section __used __section("__cpuidle_method_of_table") #else static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { return -ENODEV; } +#define __cpuidle_method_section __maybe_unused /* drop silently */ #endif /* Common ARM WFI state */ @@ -42,8 +44,7 @@ struct of_cpuidle_method { #define CPUIDLE_METHOD_OF_DECLARE(name, _method, _ops) \ static const struct of_cpuidle_method __cpuidle_method_of_table_##name \ - __used __section("__cpuidle_method_of_table") \ - = { .method = _method, .ops = _ops } + __cpuidle_method_section = { .method = _method, .ops = _ops } extern int arm_cpuidle_suspend(int index); diff --git a/arch/arm/mach-imx/pm-imx27.c b/arch/arm/mach-imx/pm-imx27.c index 020e6deb67c8..237e8aa9fe83 100644 --- a/arch/arm/mach-imx/pm-imx27.c +++ b/arch/arm/mach-imx/pm-imx27.c @@ -12,6 +12,7 @@ #include <linux/suspend.h> #include <linux/io.h> +#include "common.h" #include "hardware.h" static int mx27_suspend_enter(suspend_state_t state) diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index 2ee527c00284..1026a816dcc0 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -458,20 +458,6 @@ static struct gpiod_lookup_table leds_gpio_table = { #ifdef CONFIG_LEDS_TRIGGERS DEFINE_LED_TRIGGER(ams_delta_camera_led_trigger); - -static int ams_delta_camera_power(struct device *dev, int power) -{ - /* - * turn on camera LED - */ - if (power) - led_trigger_event(ams_delta_camera_led_trigger, LED_FULL); - else - led_trigger_event(ams_delta_camera_led_trigger, LED_OFF); - return 0; -} -#else -#define ams_delta_camera_power NULL #endif static struct platform_device ams_delta_audio_device = { diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c index c40cf5ef8607..977b0b744c22 100644 --- a/arch/arm/mach-omap1/board-h2.c +++ b/arch/arm/mach-omap1/board-h2.c @@ -320,7 +320,7 @@ static int tps_setup(struct i2c_client *client, void *context) { if (!IS_BUILTIN(CONFIG_TPS65010)) return -ENOSYS; - + tps65010_config_vregs1(TPS_LDO2_ENABLE | TPS_VLDO2_3_0V | TPS_LDO1_ENABLE | TPS_VLDO1_3_0V); @@ -394,6 +394,8 @@ static void __init h2_init(void) BUG_ON(gpio_request(H2_NAND_RB_GPIO_PIN, "NAND ready") < 0); gpio_direction_input(H2_NAND_RB_GPIO_PIN); + gpiod_add_lookup_table(&isp1301_gpiod_table); + omap_cfg_reg(L3_1610_FLASH_CS2B_OE); omap_cfg_reg(M8_1610_FLASH_CS2B_WE); diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c index 2c1e2b32b9b3..a745d64d4699 100644 --- a/arch/arm/mach-omap1/pm.c +++ b/arch/arm/mach-omap1/pm.c @@ -655,9 +655,13 @@ static int __init omap_pm_init(void) irq = INT_7XX_WAKE_UP_REQ; else if (cpu_is_omap16xx()) irq = INT_1610_WAKE_UP_REQ; - if (request_irq(irq, omap_wakeup_interrupt, 0, "peripheral wakeup", - NULL)) - pr_err("Failed to request irq %d (peripheral wakeup)\n", irq); + else + irq = -1; + + if (irq >= 0) { + if (request_irq(irq, omap_wakeup_interrupt, 0, "peripheral wakeup", NULL)) + pr_err("Failed to request irq %d (peripheral wakeup)\n", irq); + } /* Program new power ramp-up time * (0 for most boards since we don't lower voltage when in deep sleep) diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index 418a61ecb827..5e86145db0e2 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -322,6 +322,7 @@ static int n8x0_mmc_get_cover_state(struct device *dev, int slot) static void n8x0_mmc_callback(void *data, u8 card_mask) { +#ifdef CONFIG_MMC_OMAP int bit, *openp, index; if (board_is_n800()) { @@ -339,7 +340,6 @@ static void n8x0_mmc_callback(void *data, u8 card_mask) else *openp = 0; -#ifdef CONFIG_MMC_OMAP omap_mmc_notify_cover_event(mmc_device, index, *openp); #else pr_warn("MMC: notify cover event not available\n"); diff --git a/arch/arm64/Kbuild b/arch/arm64/Kbuild index d6465823b281..7b393cfec071 100644 --- a/arch/arm64/Kbuild +++ b/arch/arm64/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += kernel/ mm/ -obj-$(CONFIG_NET) += net/ +obj-y += kernel/ mm/ net/ obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_XEN) += xen/ obj-$(CONFIG_CRYPTO) += crypto/ diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 6409b47b73e4..7336c1fd0dda 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -165,6 +165,7 @@ config ARCH_MEDIATEK config ARCH_MESON bool "Amlogic Platforms" + select COMMON_CLK select MESON_IRQ_GPIO help This enables support for the arm64 based Amlogic SoCs diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts index 6c309b97587d..e8d31279b7a3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts @@ -46,7 +46,8 @@ eee-broken-100tx; qca,clk-out-frequency = <125000000>; qca,clk-out-strength = <AR803X_STRENGTH_FULL>; - vddio-supply = <&vddh>; + qca,keep-pll-enabled; + vddio-supply = <&vddio>; vddio: vddio-regulator { regulator-name = "VDDIO"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var4.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var4.dts index df212ed5bb94..e65d1c477e2c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var4.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var4.dts @@ -31,11 +31,10 @@ reg = <0x4>; eee-broken-1000t; eee-broken-100tx; - qca,clk-out-frequency = <125000000>; qca,clk-out-strength = <AR803X_STRENGTH_FULL>; - - vddio-supply = <&vddh>; + qca,keep-pll-enabled; + vddio-supply = <&vddio>; vddio: vddio-regulator { regulator-name = "VDDIO"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index eca06a0c3cf8..a30249ebffa8 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -197,8 +197,8 @@ ddr: memory-controller@1080000 { compatible = "fsl,qoriq-memory-controller"; reg = <0x0 0x1080000 0x0 0x1000>; - interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>; - big-endian; + interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>; + little-endian; }; dcfg: syscon@1e00000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra-rmb3.dts b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra-rmb3.dts index 631e01c1b9fd..be1e7d6f0ecb 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra-rmb3.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra-rmb3.dts @@ -88,11 +88,11 @@ pinctrl-0 = <&pinctrl_codec2>; reg = <0x18>; #sound-dai-cells = <0>; - HPVDD-supply = <®_3p3v>; - SPRVDD-supply = <®_3p3v>; - SPLVDD-supply = <®_3p3v>; - AVDD-supply = <®_3p3v>; - IOVDD-supply = <®_3p3v>; + HPVDD-supply = <®_gen_3p3>; + SPRVDD-supply = <®_gen_3p3>; + SPLVDD-supply = <®_gen_3p3>; + AVDD-supply = <®_gen_3p3>; + IOVDD-supply = <®_gen_3p3>; DVDD-supply = <&vgen4_reg>; reset-gpios = <&gpio3 4 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi index 4dc8383478ee..a08a568c31d9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi @@ -45,8 +45,8 @@ reg_12p0_main: regulator-12p0-main { compatible = "regulator-fixed"; regulator-name = "12V_MAIN"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; regulator-always-on; }; @@ -77,15 +77,6 @@ regulator-always-on; }; - reg_3p3v: regulator-3p3v { - compatible = "regulator-fixed"; - vin-supply = <®_3p3_main>; - regulator-name = "GEN_3V3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - }; - reg_usdhc2_vmmc: regulator-vsd-3v3 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reg_usdhc2>; @@ -415,11 +406,11 @@ pinctrl-0 = <&pinctrl_codec1>; reg = <0x18>; #sound-dai-cells = <0>; - HPVDD-supply = <®_3p3v>; - SPRVDD-supply = <®_3p3v>; - SPLVDD-supply = <®_3p3v>; - AVDD-supply = <®_3p3v>; - IOVDD-supply = <®_3p3v>; + HPVDD-supply = <®_gen_3p3>; + SPRVDD-supply = <®_gen_3p3>; + SPLVDD-supply = <®_gen_3p3>; + AVDD-supply = <®_gen_3p3>; + IOVDD-supply = <®_gen_3p3>; DVDD-supply = <&vgen4_reg>; reset-gpios = <&gpio3 3 GPIO_ACTIVE_LOW>; }; diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi index b2bcbf23eefd..ca59d1f711f8 100644 --- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi @@ -42,12 +42,12 @@ }; }; - dmss: dmss { + dmss: bus@48000000 { compatible = "simple-mfd"; #address-cells = <2>; #size-cells = <2>; dma-ranges; - ranges; + ranges = <0x00 0x48000000 0x00 0x48000000 0x00 0x06400000>; ti,sci-dev-id = <25>; @@ -134,7 +134,7 @@ }; }; - dmsc: dmsc@44043000 { + dmsc: system-controller@44043000 { compatible = "ti,k2g-sci"; ti,host-id = <12>; mbox-names = "rx", "tx"; @@ -148,7 +148,7 @@ #power-domain-cells = <2>; }; - k3_clks: clocks { + k3_clks: clock-controller { compatible = "ti,k2g-sci-clk"; #clock-cells = <2>; }; @@ -373,8 +373,9 @@ clocks = <&k3_clks 145 0>; }; - main_gpio_intr: interrupt-controller0 { + main_gpio_intr: interrupt-controller@a00000 { compatible = "ti,sci-intr"; + reg = <0x00 0x00a00000 0x00 0x800>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; diff --git a/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi index 99e94dee1bd4..deb19ae5e168 100644 --- a/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi @@ -74,8 +74,9 @@ clocks = <&k3_clks 148 0>; }; - mcu_gpio_intr: interrupt-controller1 { + mcu_gpio_intr: interrupt-controller@4210000 { compatible = "ti,sci-intr"; + reg = <0x00 0x04210000 0x00 0x200>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index cb340d1b401f..6cd3131eb9ff 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -433,8 +433,9 @@ #phy-cells = <0>; }; - intr_main_gpio: interrupt-controller0 { + intr_main_gpio: interrupt-controller@a00000 { compatible = "ti,sci-intr"; + reg = <0x0 0x00a00000 0x0 0x400>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; @@ -444,18 +445,19 @@ ti,interrupt-ranges = <0 392 32>; }; - main-navss { + main_navss: bus@30800000 { compatible = "simple-mfd"; #address-cells = <2>; #size-cells = <2>; - ranges; + ranges = <0x0 0x30800000 0x0 0x30800000 0x0 0xbc00000>; dma-coherent; dma-ranges; ti,sci-dev-id = <118>; - intr_main_navss: interrupt-controller1 { + intr_main_navss: interrupt-controller@310e0000 { compatible = "ti,sci-intr"; + reg = <0x0 0x310e0000 0x0 0x2000>; ti,intr-trigger-type = <4>; interrupt-controller; interrupt-parent = <&gic500>; diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi index 0388c02c2203..f5b8ef2f5f77 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi @@ -116,11 +116,11 @@ }; }; - mcu-navss { + mcu_navss: bus@28380000 { compatible = "simple-mfd"; #address-cells = <2>; #size-cells = <2>; - ranges; + ranges = <0x00 0x28380000 0x00 0x28380000 0x00 0x03880000>; dma-coherent; dma-ranges; diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi index ed42f13e7663..7cb864b4d74a 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi @@ -6,24 +6,24 @@ */ &cbass_wakeup { - dmsc: dmsc { + dmsc: system-controller@44083000 { compatible = "ti,am654-sci"; ti,host-id = <12>; - #address-cells = <1>; - #size-cells = <1>; - ranges; mbox-names = "rx", "tx"; mboxes= <&secure_proxy_main 11>, <&secure_proxy_main 13>; + reg-names = "debug_messages"; + reg = <0x44083000 0x1000>; + k3_pds: power-controller { compatible = "ti,sci-pm-domain"; #power-domain-cells = <2>; }; - k3_clks: clocks { + k3_clks: clock-controller { compatible = "ti,k2g-sci-clk"; #clock-cells = <2>; }; @@ -69,8 +69,9 @@ power-domains = <&k3_pds 115 TI_SCI_PD_EXCLUSIVE>; }; - intr_wkup_gpio: interrupt-controller2 { + intr_wkup_gpio: interrupt-controller@42200000 { compatible = "ti,sci-intr"; + reg = <0x42200000 0x200>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts index 9e87fb313a54..eddb2ffb93ca 100644 --- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts +++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts @@ -85,12 +85,6 @@ gpios = <&wkup_gpio0 27 GPIO_ACTIVE_LOW>; }; }; - - clk_ov5640_fixed: clock { - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <24000000>; - }; }; &wkup_pmx0 { @@ -287,23 +281,6 @@ pinctrl-names = "default"; pinctrl-0 = <&main_i2c1_pins_default>; clock-frequency = <400000>; - - ov5640: camera@3c { - compatible = "ovti,ov5640"; - reg = <0x3c>; - - clocks = <&clk_ov5640_fixed>; - clock-names = "xclk"; - - port { - csi2_cam0: endpoint { - remote-endpoint = <&csi2_phy0>; - clock-lanes = <0>; - data-lanes = <1 2>; - }; - }; - }; - }; &main_i2c2 { @@ -496,14 +473,6 @@ }; }; -&csi2_0 { - csi2_phy0: endpoint { - remote-endpoint = <&csi2_cam0>; - clock-lanes = <0>; - data-lanes = <1 2>; - }; -}; - &mcu_cpsw { pinctrl-names = "default"; pinctrl-0 = <&mcu_cpsw_pins_default &mcu_mdio_pins_default>; diff --git a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi index f86c493a44f1..19fea8adbcff 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi @@ -68,8 +68,9 @@ }; }; - main_gpio_intr: interrupt-controller0 { + main_gpio_intr: interrupt-controller@a00000 { compatible = "ti,sci-intr"; + reg = <0x00 0x00a00000 0x00 0x800>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; @@ -85,9 +86,12 @@ #size-cells = <2>; ranges = <0x00 0x30000000 0x00 0x30000000 0x00 0x0c400000>; ti,sci-dev-id = <199>; + dma-coherent; + dma-ranges; - main_navss_intr: interrupt-controller1 { + main_navss_intr: interrupt-controller@310e0000 { compatible = "ti,sci-intr"; + reg = <0x00 0x310e0000 0x00 0x4000>; ti,intr-trigger-type = <4>; interrupt-controller; interrupt-parent = <&gic500>; diff --git a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi index 5e74e43822c3..5663fe3ea466 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi @@ -6,7 +6,7 @@ */ &cbass_mcu_wakeup { - dmsc: dmsc@44083000 { + dmsc: system-controller@44083000 { compatible = "ti,k2g-sci"; ti,host-id = <12>; @@ -23,7 +23,7 @@ #power-domain-cells = <2>; }; - k3_clks: clocks { + k3_clks: clock-controller { compatible = "ti,k2g-sci-clk"; #clock-cells = <2>; }; @@ -96,8 +96,9 @@ clock-names = "fclk"; }; - wkup_gpio_intr: interrupt-controller2 { + wkup_gpio_intr: interrupt-controller@42200000 { compatible = "ti,sci-intr"; + reg = <0x00 0x42200000 0x00 0x400>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi index c2aa45a3ac79..3bcafe4c1742 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi @@ -76,8 +76,9 @@ }; }; - main_gpio_intr: interrupt-controller0 { + main_gpio_intr: interrupt-controller@a00000 { compatible = "ti,sci-intr"; + reg = <0x00 0x00a00000 0x00 0x800>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; @@ -87,18 +88,19 @@ ti,interrupt-ranges = <8 392 56>; }; - main-navss { + main_navss: bus@30000000 { compatible = "simple-mfd"; #address-cells = <2>; #size-cells = <2>; - ranges; + ranges = <0x00 0x30000000 0x00 0x30000000 0x00 0x0c400000>; dma-coherent; dma-ranges; ti,sci-dev-id = <199>; - main_navss_intr: interrupt-controller1 { + main_navss_intr: interrupt-controller@310e0000 { compatible = "ti,sci-intr"; + reg = <0x0 0x310e0000 0x0 0x4000>; ti,intr-trigger-type = <4>; interrupt-controller; interrupt-parent = <&gic500>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi index d56e3475aee7..5e825e4d0306 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi @@ -6,7 +6,7 @@ */ &cbass_mcu_wakeup { - dmsc: dmsc@44083000 { + dmsc: system-controller@44083000 { compatible = "ti,k2g-sci"; ti,host-id = <12>; @@ -23,7 +23,7 @@ #power-domain-cells = <2>; }; - k3_clks: clocks { + k3_clks: clock-controller { compatible = "ti,k2g-sci-clk"; #clock-cells = <2>; }; @@ -96,8 +96,9 @@ clock-names = "fclk"; }; - wkup_gpio_intr: interrupt-controller2 { + wkup_gpio_intr: interrupt-controller@42200000 { compatible = "ti,sci-intr"; + reg = <0x00 0x42200000 0x00 0x400>; ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; @@ -249,11 +250,11 @@ }; }; - mcu-navss { + mcu_navss: bus@28380000 { compatible = "simple-mfd"; #address-cells = <2>; #size-cells = <2>; - ranges; + ranges = <0x00 0x28380000 0x00 0x28380000 0x00 0x03880000>; dma-coherent; dma-ranges; diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 2175ec0004ed..451e11e5fd23 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -74,7 +74,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx, * This insanity brought to you by speculative system register reads, * out-of-order memory accesses, sequence locks and Thomas Gleixner. * - * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html + * https://lore.kernel.org/r/alpine.DEB.2.21.1902081950260.1662@nanos.tec.linutronix.de/ */ #define arch_counter_enforce_ordering(val) do { \ u64 tmp, _val = (val); \ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index cf8df032b9c3..5e9b33cbac51 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -63,6 +63,7 @@ #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 #define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20 +#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21 #ifndef __ASSEMBLY__ @@ -201,6 +202,8 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); +extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu); + extern u64 __vgic_v3_get_gic_config(void); extern u64 __vgic_v3_read_vmcr(void); extern void __vgic_v3_write_vmcr(u32 vmcr); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f612c090f2e4..01b9857757f2 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -463,4 +463,9 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC; } +static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) +{ + return test_bit(feature, vcpu->arch.features); +} + #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1cb39c0803a4..e720148232a0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -720,11 +720,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) return ret; } - if (run->immediate_exit) - return -EINTR; - vcpu_load(vcpu); + if (run->immediate_exit) { + ret = -EINTR; + goto out; + } + kvm_sigset_activate(vcpu); ret = 1; @@ -897,6 +899,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_sigset_deactivate(vcpu); +out: + /* + * In the unlikely event that we are returning to userspace + * with pending exceptions or PC adjustment, commit these + * adjustments in order to give userspace a consistent view of + * the vcpu state. Note that this relies on __kvm_adjust_pc() + * being preempt-safe on VHE. + */ + if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_INCREMENT_PC))) + kvm_call_hyp(__kvm_adjust_pc, vcpu); + vcpu_put(vcpu); return ret; } diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 73629094f903..11541b94b328 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -296,7 +296,7 @@ static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) *vcpu_pc(vcpu) = vect_offset; } -void kvm_inject_exception(struct kvm_vcpu *vcpu) +static void kvm_inject_exception(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) { switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) { @@ -329,3 +329,19 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu) } } } + +/* + * Adjust the guest PC (and potentially exception state) depending on + * flags provided by the emulation code. + */ +void __kvm_adjust_pc(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { + kvm_inject_exception(vcpu); + vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_EXCEPT_MASK); + } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { + kvm_skip_instr(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; + } +} diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h index 61716359035d..4fdfeabefeb4 100644 --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -13,8 +13,6 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> -void kvm_inject_exception(struct kvm_vcpu *vcpu); - static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { @@ -44,22 +42,6 @@ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) } /* - * Adjust the guest PC on entry, depending on flags provided by EL1 - * for the purpose of emulation (MMIO, sysreg) or exception injection. - */ -static inline void __adjust_pc(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { - kvm_inject_exception(vcpu); - vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | - KVM_ARM64_EXCEPT_MASK); - } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { - kvm_skip_instr(vcpu); - vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; - } -} - -/* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index f36420a80474..1632f001f4ed 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -28,6 +28,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); } +static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __kvm_adjust_pc(kern_hyp_va(vcpu)); +} + static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) { __kvm_flush_vm_context(); @@ -170,6 +177,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *); static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index e342f7f4f4fb..4b60c0056c04 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -23,8 +23,8 @@ extern unsigned long hyp_nr_cpus; struct host_kvm host_kvm; -struct hyp_pool host_s2_mem; -struct hyp_pool host_s2_dev; +static struct hyp_pool host_s2_mem; +static struct hyp_pool host_s2_dev; /* * Copies of the host's CPU features registers holding sanitized values. diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 7488f53b0aa2..a3d3a275344e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -17,7 +17,6 @@ #include <nvhe/trap_handler.h> struct hyp_pool hpool; -struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; unsigned long hyp_nr_cpus; #define hyp_percpu_size ((unsigned long)__per_cpu_end - \ @@ -27,6 +26,7 @@ static void *vmemmap_base; static void *hyp_pgt_base; static void *host_s2_mem_pgt_base; static void *host_s2_dev_pgt_base; +static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; static int divide_memory_pool(void *virt, unsigned long size) { diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index e9f6ea704d07..f7af9688c1f7 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <hyp/sysreg-sr.h> @@ -201,7 +200,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) */ __debug_save_host_buffers_nvhe(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); /* * We must restore the 32-bit state before the sysregs, thanks diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7b8f7db5c1ed..b3229924d243 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <linux/arm-smccc.h> @@ -132,7 +131,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __load_guest_stage2(vcpu->arch.hw_mmu); __activate_traps(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c5d1f3c87dbd..c10207fed2f3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1156,13 +1156,13 @@ out_unlock: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); - return 0; + return false; } bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1170,7 +1170,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) kvm_pfn_t pfn = pte_pfn(range->pte); if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(range->end - range->start != 1); @@ -1190,7 +1190,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) PAGE_SIZE, __pfn_to_phys(pfn), KVM_PGTABLE_PROT_R, NULL); - return 0; + return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1200,7 +1200,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) pte_t pte; if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); @@ -1213,7 +1213,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 956cdc240148..d37ebee085cf 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -166,6 +166,25 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) return 0; } +static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *tmp; + bool is32bit; + int i; + + is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) + return false; + + /* Check that the vcpus are either all 32bit or all 64bit */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit) + return false; + } + + return true; +} + /** * kvm_reset_vcpu - sets core registers and sys_regs to reset value * @vcpu: The VCPU pointer @@ -217,13 +236,14 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } } + if (!vcpu_allowed_register_width(vcpu)) { + ret = -EINVAL; + goto out; + } + switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) { - ret = -EINVAL; - goto out; - } pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 76ea2800c33e..1a7968ad078c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -399,14 +399,14 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -414,7 +414,7 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -424,7 +424,7 @@ static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -434,21 +434,21 @@ static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val; } static bool trap_bcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -456,7 +456,7 @@ static bool trap_bcr(struct kvm_vcpu *vcpu, static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -467,7 +467,7 @@ static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -477,22 +477,22 @@ static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val; } static bool trap_wvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]); + trace_trap_reg(__func__, rd->CRm, p->is_write, + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]); return true; } @@ -500,7 +500,7 @@ static bool trap_wvr(struct kvm_vcpu *vcpu, static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -510,7 +510,7 @@ static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -520,21 +520,21 @@ static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val; } static bool trap_wcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -542,7 +542,7 @@ static bool trap_wcr(struct kvm_vcpu *vcpu, static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -552,7 +552,7 @@ static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -562,7 +562,7 @@ static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val; } static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 6dd9369e3ea0..89b66ef43a0f 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -515,7 +515,8 @@ static void __init map_mem(pgd_t *pgdp) */ BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end)); - if (rodata_full || crash_mem_map || debug_pagealloc_enabled()) + if (rodata_full || crash_mem_map || debug_pagealloc_enabled() || + IS_ENABLED(CONFIG_KFENCE)) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c index b184baa4e56a..f175bce2987f 100644 --- a/arch/mips/alchemy/board-xxs1500.c +++ b/arch/mips/alchemy/board-xxs1500.c @@ -18,6 +18,7 @@ #include <asm/reboot.h> #include <asm/setup.h> #include <asm/mach-au1x00/au1000.h> +#include <asm/mach-au1x00/gpio-au1000.h> #include <prom.h> const char *get_system_type(void) diff --git a/arch/mips/include/asm/mips-boards/launch.h b/arch/mips/include/asm/mips-boards/launch.h index f93aa5ee2e2e..3481ed4c117b 100644 --- a/arch/mips/include/asm/mips-boards/launch.h +++ b/arch/mips/include/asm/mips-boards/launch.h @@ -3,6 +3,9 @@ * */ +#ifndef _ASM_MIPS_BOARDS_LAUNCH_H +#define _ASM_MIPS_BOARDS_LAUNCH_H + #ifndef _ASSEMBLER_ struct cpulaunch { @@ -34,3 +37,5 @@ struct cpulaunch { /* Polling period in count cycles for secondary CPU's */ #define LAUNCHPERIOD 10000 + +#endif /* _ASM_MIPS_BOARDS_LAUNCH_H */ diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c index de03838b343b..a9b72eacfc0b 100644 --- a/arch/mips/lib/mips-atomic.c +++ b/arch/mips/lib/mips-atomic.c @@ -37,7 +37,7 @@ */ notrace void arch_local_irq_disable(void) { - preempt_disable(); + preempt_disable_notrace(); __asm__ __volatile__( " .set push \n" @@ -53,7 +53,7 @@ notrace void arch_local_irq_disable(void) : /* no inputs */ : "memory"); - preempt_enable(); + preempt_enable_notrace(); } EXPORT_SYMBOL(arch_local_irq_disable); @@ -61,7 +61,7 @@ notrace unsigned long arch_local_irq_save(void) { unsigned long flags; - preempt_disable(); + preempt_disable_notrace(); __asm__ __volatile__( " .set push \n" @@ -78,7 +78,7 @@ notrace unsigned long arch_local_irq_save(void) : /* no inputs */ : "memory"); - preempt_enable(); + preempt_enable_notrace(); return flags; } @@ -88,7 +88,7 @@ notrace void arch_local_irq_restore(unsigned long flags) { unsigned long __tmp1; - preempt_disable(); + preempt_disable_notrace(); __asm__ __volatile__( " .set push \n" @@ -106,7 +106,7 @@ notrace void arch_local_irq_restore(unsigned long flags) : "0" (flags) : "memory"); - preempt_enable(); + preempt_enable_notrace(); } EXPORT_SYMBOL(arch_local_irq_restore); diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index a7bf0c80371c..830ab91e574f 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -158,31 +158,29 @@ unsigned long _page_cachable_default; EXPORT_SYMBOL(_page_cachable_default); #define PM(p) __pgprot(_page_cachable_default | (p)) -#define PVA(p) PM(_PAGE_VALID | _PAGE_ACCESSED | (p)) static inline void setup_protection_map(void) { protection_map[0] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[1] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[2] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[3] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[4] = PVA(_PAGE_PRESENT); - protection_map[5] = PVA(_PAGE_PRESENT); - protection_map[6] = PVA(_PAGE_PRESENT); - protection_map[7] = PVA(_PAGE_PRESENT); + protection_map[1] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[2] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); + protection_map[3] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[4] = PM(_PAGE_PRESENT); + protection_map[5] = PM(_PAGE_PRESENT); + protection_map[6] = PM(_PAGE_PRESENT); + protection_map[7] = PM(_PAGE_PRESENT); protection_map[8] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[9] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[10] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | + protection_map[9] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ); - protection_map[11] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); - protection_map[12] = PVA(_PAGE_PRESENT); - protection_map[13] = PVA(_PAGE_PRESENT); - protection_map[14] = PVA(_PAGE_PRESENT); - protection_map[15] = PVA(_PAGE_PRESENT); + protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); + protection_map[12] = PM(_PAGE_PRESENT); + protection_map[13] = PM(_PAGE_PRESENT); + protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE); + protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE); } -#undef _PVA #undef PM void cpu_cache_init(void) diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 0c5de07da097..0135376c5de5 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -8,6 +8,7 @@ #include <linux/io.h> #include <linux/clk.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/sizes.h> #include <linux/of_fdt.h> @@ -25,6 +26,7 @@ __iomem void *rt_sysc_membase; __iomem void *rt_memc_membase; +EXPORT_SYMBOL_GPL(rt_sysc_membase); __iomem void *plat_of_remap_node(const char *node) { diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi index c2717f31925a..ccda0a91abf0 100644 --- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi @@ -122,7 +122,15 @@ }; /include/ "pq3-i2c-0.dtsi" + i2c@3000 { + fsl,i2c-erratum-a004447; + }; + /include/ "pq3-i2c-1.dtsi" + i2c@3100 { + fsl,i2c-erratum-a004447; + }; + /include/ "pq3-duart-0.dtsi" /include/ "pq3-espi-0.dtsi" spi0: spi@7000 { diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi index 872e4485dc3f..ddc018d42252 100644 --- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi @@ -371,7 +371,23 @@ }; /include/ "qoriq-i2c-0.dtsi" + i2c@118000 { + fsl,i2c-erratum-a004447; + }; + + i2c@118100 { + fsl,i2c-erratum-a004447; + }; + /include/ "qoriq-i2c-1.dtsi" + i2c@119000 { + fsl,i2c-erratum-a004447; + }; + + i2c@119100 { + fsl,i2c-erratum-a004447; + }; + /include/ "qoriq-duart-0.dtsi" /include/ "qoriq-duart-1.dtsi" /include/ "qoriq-gpio-0.dtsi" diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 2d5c6bec2b4f..93ce3ec25387 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -50,7 +50,7 @@ l_yes: 1098: nop; \ .pushsection __jump_table, "aw"; \ .long 1098b - ., LABEL - .; \ - FTR_ENTRY_LONG KEY; \ + FTR_ENTRY_LONG KEY - .; \ .popsection #endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1e83359f286b..7f2e90db2050 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -51,6 +51,7 @@ /* PPC-specific vcpu->requests bit members */ #define KVM_REQ_WATCHDOG KVM_ARCH_REQ(0) #define KVM_REQ_EPR_EXIT KVM_ARCH_REQ(1) +#define KVM_REQ_PENDING_TIMER KVM_ARCH_REQ(2) #include <linux/mmu_notifier.h> diff --git a/arch/powerpc/include/asm/pte-walk.h b/arch/powerpc/include/asm/pte-walk.h index 33fa5dd8ee6a..714a35f0d425 100644 --- a/arch/powerpc/include/asm/pte-walk.h +++ b/arch/powerpc/include/asm/pte-walk.h @@ -31,6 +31,35 @@ static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift) pgd_t *pgdir = init_mm.pgd; return __find_linux_pte(pgdir, ea, NULL, hshift); } + +/* + * Convert a kernel vmap virtual address (vmalloc or ioremap space) to a + * physical address, without taking locks. This can be used in real-mode. + */ +static inline phys_addr_t ppc_find_vmap_phys(unsigned long addr) +{ + pte_t *ptep; + phys_addr_t pa; + int hugepage_shift; + + /* + * init_mm does not free page tables, and does not do THP. It may + * have huge pages from huge vmalloc / ioremap etc. + */ + ptep = find_init_mm_pte(addr, &hugepage_shift); + if (WARN_ON(!ptep)) + return 0; + + pa = PFN_PHYS(pte_pfn(*ptep)); + + if (!hugepage_shift) + hugepage_shift = PAGE_SHIFT; + + pa |= addr & ((1ul << hugepage_shift) - 1); + + return pa; +} + /* * This is what we should always use. Any other lockless page table lookup needs * careful audit against THP split. diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f24cd53ff26e..3bbdcc86d01b 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -346,28 +346,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) */ static inline unsigned long eeh_token_to_phys(unsigned long token) { - pte_t *ptep; - unsigned long pa; - int hugepage_shift; - - /* - * We won't find hugepages here(this is iomem). Hence we are not - * worried about _PAGE_SPLITTING/collapse. Also we will not hit - * page table free, because of init_mm. - */ - ptep = find_init_mm_pte(token, &hugepage_shift); - if (!ptep) - return token; - - pa = pte_pfn(*ptep); - - /* On radix we can do hugepage mappings for io, so handle that */ - if (!hugepage_shift) - hugepage_shift = PAGE_SHIFT; - - pa <<= PAGE_SHIFT; - pa |= token & ((1ul << hugepage_shift) - 1); - return pa; + return ppc_find_vmap_phys(token); } /* diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index 51bbaae94ccc..c877f074d174 100644 --- a/arch/powerpc/kernel/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -55,7 +55,6 @@ static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr) #ifdef CONFIG_PPC_INDIRECT_MMIO struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) { - unsigned hugepage_shift; struct iowa_bus *bus; int token; @@ -65,22 +64,13 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) bus = &iowa_busses[token - 1]; else { unsigned long vaddr, paddr; - pte_t *ptep; vaddr = (unsigned long)PCI_FIX_ADDR(addr); if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END) return NULL; - /* - * We won't find huge pages here (iomem). Also can't hit - * a page table free due to init_mm - */ - ptep = find_init_mm_pte(vaddr, &hugepage_shift); - if (ptep == NULL) - paddr = 0; - else { - WARN_ON(hugepage_shift); - paddr = pte_pfn(*ptep) << PAGE_SHIFT; - } + + paddr = ppc_find_vmap_phys(vaddr); + bus = iowa_pci_find(vaddr, paddr); if (bus == NULL) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 57d6b85e9b96..2af89a5e379f 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -898,7 +898,6 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, unsigned int order; unsigned int nio_pages, io_order; struct page *page; - size_t size_io = size; size = PAGE_ALIGN(size); order = get_order(size); @@ -925,9 +924,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - size_io = IOMMU_PAGE_ALIGN(size_io, tbl); - nio_pages = size_io >> tbl->it_page_shift; - io_order = get_iommu_order(size_io, tbl); + nio_pages = size >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); if (mapping == DMA_MAPPING_ERROR) { @@ -942,9 +940,10 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, void *vaddr, dma_addr_t dma_handle) { if (tbl) { - size_t size_io = IOMMU_PAGE_ALIGN(size, tbl); - unsigned int nio_pages = size_io >> tbl->it_page_shift; + unsigned int nio_pages; + size = PAGE_ALIGN(size); + nio_pages = size >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 01ab2163659e..e8c2a6373157 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -108,7 +108,6 @@ int arch_prepare_kprobe(struct kprobe *p) int ret = 0; struct kprobe *prev; struct ppc_inst insn = ppc_inst_read((struct ppc_inst *)p->addr); - struct ppc_inst prefix = ppc_inst_read((struct ppc_inst *)(p->addr - 1)); if ((unsigned long)p->addr & 0x03) { printk("Attempt to register kprobe at an unaligned address\n"); @@ -116,7 +115,8 @@ int arch_prepare_kprobe(struct kprobe *p) } else if (IS_MTMSRD(insn) || IS_RFID(insn) || IS_RFI(insn)) { printk("Cannot register a kprobe on rfi/rfid or mtmsr[d]\n"); ret = -EINVAL; - } else if (ppc_inst_prefixed(prefix)) { + } else if ((unsigned long)p->addr & ~PAGE_MASK && + ppc_inst_prefixed(ppc_inst_read((struct ppc_inst *)(p->addr - 1)))) { printk("Cannot register a kprobe on the second word of prefixed instruction\n"); ret = -EINVAL; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index dca66481d0c2..f9e1f5428b9e 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -902,6 +902,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, unsafe_copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set), badframe_block); user_write_access_end(); + /* Save the siginfo outside of the unsafe block. */ + if (copy_siginfo_to_user(&frame->info, &ksig->info)) + goto badframe; + /* Make sure signal handler doesn't get spurious FP exceptions */ tsk->thread.fp_state.fpscr = 0; @@ -915,11 +919,6 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, regs->nip = (unsigned long) &frame->tramp[0]; } - - /* Save the siginfo outside of the unsafe block. */ - if (copy_siginfo_to_user(&frame->info, &ksig->info)) - goto badframe; - /* Allocate a dummy caller frame for the signal handler. */ newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE; err |= put_user(regs->gpr[1], (unsigned long __user *)newsp); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 28a80d240b76..bc0813644666 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3936,7 +3936,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) break; } cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; @@ -4455,7 +4455,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) mtspr(SPRN_EBBRR, ebb_regs[1]); mtspr(SPRN_BESCR, ebb_regs[2]); mtspr(SPRN_TAR, user_tar); - mtspr(SPRN_FSCR, current->thread.fscr); } mtspr(SPRN_VRSAVE, user_vrsave); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 7af7c70f1468..7a0f12404e0e 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -23,20 +23,9 @@ #include <asm/pte-walk.h> /* Translate address of a vmalloc'd thing to a linear map address */ -static void *real_vmalloc_addr(void *x) +static void *real_vmalloc_addr(void *addr) { - unsigned long addr = (unsigned long) x; - pte_t *p; - /* - * assume we don't have huge pages in vmalloc space... - * So don't worry about THP collapse/split. Called - * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore. - */ - p = find_init_mm_pte(addr, NULL); - if (!p || !pte_present(*p)) - return NULL; - addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK); - return __va(addr); + return __va(ppc_find_vmap_phys((unsigned long)addr)); } /* Return 1 if we need to do a global tlbie, 0 if we can use tlbiel */ diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 5e634db4809b..004f0d4e665f 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -59,6 +59,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) #define STACK_SLOT_UAMOR (SFS-88) #define STACK_SLOT_DAWR1 (SFS-96) #define STACK_SLOT_DAWRX1 (SFS-104) +#define STACK_SLOT_FSCR (SFS-112) /* the following is used by the P9 short path */ #define STACK_SLOT_NVGPRS (SFS-152) /* 18 gprs */ @@ -686,6 +687,8 @@ BEGIN_FTR_SECTION std r6, STACK_SLOT_DAWR0(r1) std r7, STACK_SLOT_DAWRX0(r1) std r8, STACK_SLOT_IAMR(r1) + mfspr r5, SPRN_FSCR + std r5, STACK_SLOT_FSCR(r1) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) BEGIN_FTR_SECTION mfspr r6, SPRN_DAWR1 @@ -1663,6 +1666,10 @@ FTR_SECTION_ELSE ld r7, STACK_SLOT_HFSCR(r1) mtspr SPRN_HFSCR, r7 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) +BEGIN_FTR_SECTION + ld r5, STACK_SLOT_FSCR(r1) + mtspr SPRN_FSCR, r5 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* * Restore various registers to 0, where non-zero values * set by the guest could disrupt the host. diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 043bbeaf407c..a6b36a40897a 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -20,6 +20,7 @@ #include <asm/machdep.h> #include <asm/rtas.h> #include <asm/kasan.h> +#include <asm/sparsemem.h> #include <asm/svm.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 16d4d1b6a1ff..51622411a7cc 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2254,7 +2254,7 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs) bool use_siar = regs_use_siar(regs); unsigned long siar = mfspr(SPRN_SIAR); - if (ppmu->flags & PPMU_P10_DD1) { + if (ppmu && (ppmu->flags & PPMU_P10_DD1)) { if (siar) return siar; else diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a8ad8eb76120..18ec0f9bb8d5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -34,6 +34,7 @@ config RISCV select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_SUPPORTS_HUGETLBFS if MMU + select ARCH_USE_MEMTEST select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if 64BIT @@ -60,11 +61,11 @@ config RISCV select GENERIC_TIME_VSYSCALL if MMU && 64BIT select HANDLE_DOMAIN_IRQ select HAVE_ARCH_AUDITSYSCALL - select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_JUMP_LABEL_RELATIVE + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL + select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL select HAVE_ARCH_KASAN if MMU && 64BIT select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT - select HAVE_ARCH_KGDB + select HAVE_ARCH_KGDB if !XIP_KERNEL select HAVE_ARCH_KGDB_QXFER_PKT select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_SECCOMP_FILTER @@ -79,9 +80,9 @@ config RISCV select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO if MMU && 64BIT select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_KPROBES - select HAVE_KPROBES_ON_FTRACE - select HAVE_KRETPROBES + select HAVE_KPROBES if !XIP_KERNEL + select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL + select HAVE_KRETPROBES if !XIP_KERNEL select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS @@ -230,11 +231,11 @@ config ARCH_RV64I bool "RV64I" select 64BIT select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000 - select HAVE_DYNAMIC_FTRACE if MMU && $(cc-option,-fpatchable-function-entry=8) + select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8) select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE - select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_TRACER if !XIP_KERNEL select SWIOTLB if MMU endchoice diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index ed963761fbd2..30676ebb16eb 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -14,6 +14,7 @@ config SOC_SIFIVE select CLK_SIFIVE select CLK_SIFIVE_PRCI select SIFIVE_PLIC + select RISCV_ERRATA_ALTERNATIVE select ERRATA_SIFIVE help This enables support for SiFive SoC platform hardware. diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 3eb9590a0775..99ecd8bcfd77 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -16,7 +16,7 @@ ifeq ($(CONFIG_DYNAMIC_FTRACE),y) CC_FLAGS_FTRACE := -fpatchable-function-entry=8 endif -ifeq ($(CONFIG_64BIT)$(CONFIG_CMODEL_MEDLOW),yy) +ifeq ($(CONFIG_CMODEL_MEDLOW),y) KBUILD_CFLAGS_MODULE += -mcmodel=medany endif @@ -38,6 +38,15 @@ else KBUILD_LDFLAGS += -melf32lriscv endif +ifeq ($(CONFIG_LD_IS_LLD),y) + KBUILD_CFLAGS += -mno-relax + KBUILD_AFLAGS += -mno-relax +ifneq ($(LLVM_IAS),1) + KBUILD_CFLAGS += -Wa,-mno-relax + KBUILD_AFLAGS += -Wa,-mno-relax +endif +endif + # ISA string setting riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima riscv-march-$(CONFIG_ARCH_RV64I) := rv64ima diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile index 622b12771fd3..855c1502d912 100644 --- a/arch/riscv/boot/dts/microchip/Makefile +++ b/arch/riscv/boot/dts/microchip/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += microchip-mpfs-icicle-kit.dtb +obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/riscv/boot/dts/sifive/Makefile b/arch/riscv/boot/dts/sifive/Makefile index 74c47fe9fc22..d90e4eb0ade8 100644 --- a/arch/riscv/boot/dts/sifive/Makefile +++ b/arch/riscv/boot/dts/sifive/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_SOC_SIFIVE) += hifive-unleashed-a00.dtb \ hifive-unmatched-a00.dtb +obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi index 8eef82e4199f..abbb960f90a0 100644 --- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -273,7 +273,7 @@ cache-size = <2097152>; cache-unified; interrupt-parent = <&plic0>; - interrupts = <19 20 21 22>; + interrupts = <19 21 22 20>; reg = <0x0 0x2010000 0x0 0x1000>; }; gpio: gpio@10060000 { diff --git a/arch/riscv/errata/sifive/Makefile b/arch/riscv/errata/sifive/Makefile index bdd5fc843b8e..2fde48db0619 100644 --- a/arch/riscv/errata/sifive/Makefile +++ b/arch/riscv/errata/sifive/Makefile @@ -1,2 +1,2 @@ -obj-y += errata_cip_453.o +obj-$(CONFIG_ERRATA_SIFIVE_CIP_453) += errata_cip_453.o obj-y += errata.o diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 88c08705f64a..67406c376389 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -51,7 +51,7 @@ REG_ASM " " newlen "\n" \ ".word " errata_id "\n" -#define ALT_NEW_CONSTENT(vendor_id, errata_id, enable, new_c) \ +#define ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c) \ ".if " __stringify(enable) " == 1\n" \ ".pushsection .alternative, \"a\"\n" \ ALT_ENTRY("886b", "888f", __stringify(vendor_id), __stringify(errata_id), "889f - 888f") \ @@ -69,7 +69,7 @@ "886 :\n" \ old_c "\n" \ "887 :\n" \ - ALT_NEW_CONSTENT(vendor_id, errata_id, enable, new_c) + ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c) #define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \ __ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, IS_ENABLED(CONFIG_k)) diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h index 1e954101906a..e4e291d40759 100644 --- a/arch/riscv/include/asm/kexec.h +++ b/arch/riscv/include/asm/kexec.h @@ -42,8 +42,8 @@ struct kimage_arch { unsigned long fdt_addr; }; -const extern unsigned char riscv_kexec_relocate[]; -const extern unsigned int riscv_kexec_relocate_size; +extern const unsigned char riscv_kexec_relocate[]; +extern const unsigned int riscv_kexec_relocate_size; typedef void (*riscv_kexec_method)(unsigned long first_ind_entry, unsigned long jump_addr, diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 9469f464e71a..380cd3a7e548 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -30,9 +30,8 @@ #define BPF_JIT_REGION_SIZE (SZ_128M) #ifdef CONFIG_64BIT -/* KASLR should leave at least 128MB for BPF after the kernel */ -#define BPF_JIT_REGION_START PFN_ALIGN((unsigned long)&_end) -#define BPF_JIT_REGION_END (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE) +#define BPF_JIT_REGION_START (BPF_JIT_REGION_END - BPF_JIT_REGION_SIZE) +#define BPF_JIT_REGION_END (MODULES_END) #else #define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) #define BPF_JIT_REGION_END (VMALLOC_END) diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index cc048143fba5..9e99e1db156b 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -14,8 +14,9 @@ #include <asm/set_memory.h> /* For set_memory_x() */ #include <linux/compiler.h> /* For unreachable() */ #include <linux/cpu.h> /* For cpu_down() */ +#include <linux/reboot.h> -/** +/* * kexec_image_info - Print received image details */ static void @@ -39,7 +40,7 @@ kexec_image_info(const struct kimage *image) } } -/** +/* * machine_kexec_prepare - Initialize kexec * * This function is called from do_kexec_load, when the user has @@ -100,7 +101,7 @@ machine_kexec_prepare(struct kimage *image) } -/** +/* * machine_kexec_cleanup - Cleanup any leftovers from * machine_kexec_prepare * @@ -135,7 +136,7 @@ void machine_shutdown(void) #endif } -/** +/* * machine_crash_shutdown - Prepare to kexec after a kernel crash * * This function is called by crash_kexec just before machine_kexec @@ -151,7 +152,7 @@ machine_crash_shutdown(struct pt_regs *regs) pr_info("Starting crashdump kernel...\n"); } -/** +/* * machine_kexec - Jump to the loaded kimage * * This function is called by kernel_kexec which is called by the diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 10b965c34536..15cc65ac7ca6 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -84,6 +84,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return 0; } +#ifdef CONFIG_MMU void *alloc_insn_page(void) { return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, @@ -91,6 +92,7 @@ void *alloc_insn_page(void) VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } +#endif /* install breakpoint in text */ void __kprobes arch_arm_kprobe(struct kprobe *p) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 03901d3a8b02..9a1b7a0603b2 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -231,13 +231,13 @@ static void __init init_resources(void) /* Clean-up any unused pre-allocated resources */ mem_res_sz = (num_resources - res_idx + 1) * sizeof(*mem_res); - memblock_free((phys_addr_t) mem_res, mem_res_sz); + memblock_free(__pa(mem_res), mem_res_sz); return; error: /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); - memblock_free((phys_addr_t) mem_res, mem_res_sz); + memblock_free(__pa(mem_res), mem_res_sz); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 2b3e0cb90d78..bde85fc53357 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -27,10 +27,10 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame_pointer(regs); sp = user_stack_pointer(regs); pc = instruction_pointer(regs); - } else if (task == NULL || task == current) { - fp = (unsigned long)__builtin_frame_address(0); - sp = sp_in_global; - pc = (unsigned long)walk_stackframe; + } else if (task == current) { + fp = (unsigned long)__builtin_frame_address(1); + sp = (unsigned long)__builtin_frame_address(0); + pc = (unsigned long)__builtin_return_address(0); } else { /* task blocked in __switch_to */ fp = task->thread.s[0]; @@ -106,15 +106,15 @@ static bool print_trace_address(void *arg, unsigned long pc) return true; } -void dump_backtrace(struct pt_regs *regs, struct task_struct *task, +noinline void dump_backtrace(struct pt_regs *regs, struct task_struct *task, const char *loglvl) { - pr_cont("%sCall Trace:\n", loglvl); walk_stackframe(task, regs, print_trace_address, (void *)loglvl); } void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) { + pr_cont("%sCall Trace:\n", loglvl); dump_backtrace(NULL, task, loglvl); } @@ -139,7 +139,7 @@ unsigned long get_wchan(struct task_struct *task) #ifdef CONFIG_STACKTRACE -void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, +noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { walk_stackframe(task, regs, consume_entry, cookie); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 0721b9798595..7bc88d8aab97 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -86,8 +86,13 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, } } +#if defined (CONFIG_XIP_KERNEL) && defined (CONFIG_RISCV_ERRATA_ALTERNATIVE) +#define __trap_section __section(".xip.traps") +#else +#define __trap_section +#endif #define DO_ERROR_INFO(name, signo, code, str) \ -asmlinkage __visible void name(struct pt_regs *regs) \ +asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ { \ do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ } @@ -111,7 +116,7 @@ DO_ERROR_INFO(do_trap_store_misaligned, int handle_misaligned_load(struct pt_regs *regs); int handle_misaligned_store(struct pt_regs *regs); -asmlinkage void do_trap_load_misaligned(struct pt_regs *regs) +asmlinkage void __trap_section do_trap_load_misaligned(struct pt_regs *regs) { if (!handle_misaligned_load(regs)) return; @@ -119,7 +124,7 @@ asmlinkage void do_trap_load_misaligned(struct pt_regs *regs) "Oops - load address misaligned"); } -asmlinkage void do_trap_store_misaligned(struct pt_regs *regs) +asmlinkage void __trap_section do_trap_store_misaligned(struct pt_regs *regs) { if (!handle_misaligned_store(regs)) return; @@ -146,7 +151,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc) return GET_INSN_LENGTH(insn); } -asmlinkage __visible void do_trap_break(struct pt_regs *regs) +asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) { #ifdef CONFIG_KPROBES if (kprobe_single_step_handler(regs)) diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S index 4b29b9917f99..a3ff09c4c3f9 100644 --- a/arch/riscv/kernel/vmlinux-xip.lds.S +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -99,9 +99,22 @@ SECTIONS } PERCPU_SECTION(L1_CACHE_BYTES) - . = ALIGN(PAGE_SIZE); + . = ALIGN(8); + .alternative : { + __alt_start = .; + *(.alternative) + __alt_end = .; + } __init_end = .; + . = ALIGN(16); + .xip.traps : { + __xip_traps_start = .; + *(.xip.traps) + __xip_traps_end = .; + } + + . = ALIGN(PAGE_SIZE); .sdata : { __global_pointer$ = . + 0x800; *(.sdata*) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 4faf8bd157ea..4c4c92ce0bb8 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -746,14 +746,18 @@ void __init protect_kernel_text_data(void) unsigned long init_data_start = (unsigned long)__init_data_begin; unsigned long rodata_start = (unsigned long)__start_rodata; unsigned long data_start = (unsigned long)_data; - unsigned long max_low = (unsigned long)(__va(PFN_PHYS(max_low_pfn))); +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) + unsigned long end_va = kernel_virt_addr + load_sz; +#else + unsigned long end_va = (unsigned long)(__va(PFN_PHYS(max_low_pfn))); +#endif set_memory_ro(text_start, (init_text_start - text_start) >> PAGE_SHIFT); set_memory_ro(init_text_start, (init_data_start - init_text_start) >> PAGE_SHIFT); set_memory_nx(init_data_start, (rodata_start - init_data_start) >> PAGE_SHIFT); /* rodata section is marked readonly in mark_rodata_ro */ set_memory_nx(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT); - set_memory_nx(data_start, (max_low - data_start) >> PAGE_SHIFT); + set_memory_nx(data_start, (end_va - data_start) >> PAGE_SHIFT); } void mark_rodata_ro(void) diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 9daacae93e33..d7189c8714a9 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -169,7 +169,7 @@ static void __init kasan_shallow_populate(void *start, void *end) void __init kasan_init(void) { - phys_addr_t _start, _end; + phys_addr_t p_start, p_end; u64 i; /* @@ -189,9 +189,9 @@ void __init kasan_init(void) (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); /* Populate the linear mapping */ - for_each_mem_range(i, &_start, &_end) { - void *start = (void *)__va(_start); - void *end = (void *)__va(_end); + for_each_mem_range(i, &p_start, &p_end) { + void *start = (void *)__va(p_start); + void *end = (void *)__va(p_end); if (start >= end) break; @@ -201,7 +201,7 @@ void __init kasan_init(void) /* Populate kernel, BPF, modules mapping */ kasan_populate(kasan_mem_to_shadow((const void *)MODULES_VADDR), - kasan_mem_to_shadow((const void *)BPF_JIT_REGION_END)); + kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G)); for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_early_shadow_pte[i], diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 12de7a9c85b3..9cc71ca9a88f 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -651,9 +651,9 @@ ENDPROC(stack_overflow) .Lcleanup_sie_mcck: larl %r13,.Lsie_entry slgr %r9,%r13 - larl %r13,.Lsie_skip + lghi %r13,.Lsie_skip - .Lsie_entry clgr %r9,%r13 - jh .Lcleanup_sie_int + jhe .Lcleanup_sie_int oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST .Lcleanup_sie_int: BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 307529417021..cb5e8d39cac1 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -200,8 +200,9 @@ endif KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE) ifdef CONFIG_LTO_CLANG -KBUILD_LDFLAGS += -plugin-opt=-code-model=kernel \ - -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 130000; echo $$?),0) +KBUILD_LDFLAGS += -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8) +endif endif ifdef CONFIG_X86_NEED_RELOCS diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 63f097289a84..3a75a2c601c2 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1406,6 +1406,8 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool die_id = i; else die_id = topology_phys_to_logical_pkg(i); + if (die_id < 0) + die_id = -ENODEV; map->pbus_to_dieid[bus] = die_id; break; } @@ -1452,14 +1454,14 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool i = -1; if (reverse) { for (bus = 255; bus >= 0; bus--) { - if (map->pbus_to_dieid[bus] >= 0) + if (map->pbus_to_dieid[bus] != -1) i = map->pbus_to_dieid[bus]; else map->pbus_to_dieid[bus] = i; } } else { for (bus = 0; bus <= 255; bus++) { - if (map->pbus_to_dieid[bus] >= 0) + if (map->pbus_to_dieid[bus] != -1) i = map->pbus_to_dieid[bus]; else map->pbus_to_dieid[bus] = i; @@ -5097,9 +5099,10 @@ static struct intel_uncore_type icx_uncore_m2m = { .perf_ctr = SNR_M2M_PCI_PMON_CTR0, .event_ctl = SNR_M2M_PCI_PMON_CTL0, .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SNR_M2M_PCI_PMON_UMASK_EXT, .box_ctl = SNR_M2M_PCI_PMON_BOX_CTL, .ops = &snr_m2m_uncore_pci_ops, - .format_group = &skx_uncore_format_group, + .format_group = &snr_m2m_uncore_format_group, }; static struct attribute *icx_upi_uncore_formats_attr[] = { diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 412b51e059c8..48067af94678 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -174,6 +174,7 @@ static inline int apic_is_clustered_box(void) extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); extern void lapic_assign_system_vectors(void); extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace); +extern void lapic_update_legacy_vectors(void); extern void lapic_online(void); extern void lapic_offline(void); extern bool apic_needs_pit(void); diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index b7dd944dc867..8f28fafa98b3 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -56,11 +56,8 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_IOMMU_SUPPORT -# define DISABLE_ENQCMD 0 -#else -# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) -#endif +/* Force disable because it's broken beyond repair */ +#define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) #ifdef CONFIG_X86_SGX # define DISABLE_SGX 0 diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index ed33a14188f6..23bef08a8388 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -106,10 +106,6 @@ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); */ #define PASID_DISABLED 0 -#ifdef CONFIG_IOMMU_SUPPORT -/* Update current's PASID MSR/state by mm's PASID. */ -void update_pasid(void); -#else static inline void update_pasid(void) { } -#endif + #endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 8d33ad80704f..fdee23ea4e17 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -578,19 +578,19 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * PKRU state is switched eagerly because it needs to be valid before we * return to userland e.g. for a copy_to_user() operation. */ - if (current->mm) { + if (!(current->flags & PF_KTHREAD)) { + /* + * If the PKRU bit in xsave.header.xfeatures is not set, + * then the PKRU component was in init state, which means + * XRSTOR will set PKRU to 0. If the bit is not set then + * get_xsave_addr() will return NULL because the PKRU value + * in memory is not valid. This means pkru_val has to be + * set to 0 and not to init_pkru_value. + */ pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU); - if (pk) - pkru_val = pk->pkru; + pkru_val = pk ? pk->pkru : 0; } __write_pkru(pkru_val); - - /* - * Expensive PASID MSR write will be avoided in update_pasid() because - * TIF_NEED_FPU_LOAD was set. And the PASID state won't be updated - * unless it's different from mm->pasid to reduce overhead. - */ - update_pasid(); } #endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 323641097f63..e7bef91cee04 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -99,6 +99,7 @@ KVM_X86_OP_NULL(post_block) KVM_X86_OP_NULL(vcpu_blocking) KVM_X86_OP_NULL(vcpu_unblocking) KVM_X86_OP_NULL(update_pi_irte) +KVM_X86_OP_NULL(start_assignment) KVM_X86_OP_NULL(apicv_post_state_restore) KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt) KVM_X86_OP_NULL(set_hv_timer) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 55efbacfc244..9c7ced0e3171 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1352,6 +1352,7 @@ struct kvm_x86_ops { int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); + void (*start_assignment)(struct kvm *kvm); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/thermal.h b/arch/x86/include/asm/thermal.h index ddbdefd5b94f..91a7b6687c3b 100644 --- a/arch/x86/include/asm/thermal.h +++ b/arch/x86/include/asm/thermal.h @@ -3,11 +3,13 @@ #define _ASM_X86_THERMAL_H #ifdef CONFIG_X86_THERMAL_VECTOR +void therm_lvt_init(void); void intel_init_thermal(struct cpuinfo_x86 *c); bool x86_thermal_enabled(void); void intel_thermal_interrupt(void); #else -static inline void intel_init_thermal(struct cpuinfo_x86 *c) { } +static inline void therm_lvt_init(void) { } +static inline void intel_init_thermal(struct cpuinfo_x86 *c) { } #endif #endif /* _ASM_X86_THERMAL_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 6974b5174495..6fe5b44fcbc9 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -183,41 +183,69 @@ done: } /* + * optimize_nops_range() - Optimize a sequence of single byte NOPs (0x90) + * + * @instr: instruction byte stream + * @instrlen: length of the above + * @off: offset within @instr where the first NOP has been detected + * + * Return: number of NOPs found (and replaced). + */ +static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off) +{ + unsigned long flags; + int i = off, nnops; + + while (i < instrlen) { + if (instr[i] != 0x90) + break; + + i++; + } + + nnops = i - off; + + if (nnops <= 1) + return nnops; + + local_irq_save(flags); + add_nops(instr + off, nnops); + local_irq_restore(flags); + + DUMP_BYTES(instr, instrlen, "%px: [%d:%d) optimized NOPs: ", instr, off, i); + + return nnops; +} + +/* * "noinline" to cause control flow change and thus invalidate I$ and * cause refetch after modification. */ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr) { - unsigned long flags; struct insn insn; - int nop, i = 0; + int i = 0; /* - * Jump over the non-NOP insns, the remaining bytes must be single-byte - * NOPs, optimize them. + * Jump over the non-NOP insns and optimize single-byte NOPs into bigger + * ones. */ for (;;) { if (insn_decode_kernel(&insn, &instr[i])) return; + /* + * See if this and any potentially following NOPs can be + * optimized. + */ if (insn.length == 1 && insn.opcode.bytes[0] == 0x90) - break; - - if ((i += insn.length) >= a->instrlen) - return; - } + i += optimize_nops_range(instr, a->instrlen, i); + else + i += insn.length; - for (nop = i; i < a->instrlen; i++) { - if (WARN_ONCE(instr[i] != 0x90, "Not a NOP at 0x%px\n", &instr[i])) + if (i >= a->instrlen) return; } - - local_irq_save(flags); - add_nops(instr + nop, i - nop); - local_irq_restore(flags); - - DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", - instr, nop, a->instrlen); } /* diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4a39fb429f15..d262811ce14b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2604,6 +2604,7 @@ static void __init apic_bsp_setup(bool upmode) end_local_APIC_setup(); irq_remap_enable_fault_handling(); setup_IO_APIC(); + lapic_update_legacy_vectors(); } #ifdef CONFIG_UP_LATE_INIT diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 6dbdc7c22bb7..fb67ed5e7e6a 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -738,6 +738,26 @@ void lapic_assign_legacy_vector(unsigned int irq, bool replace) irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace); } +void __init lapic_update_legacy_vectors(void) +{ + unsigned int i; + + if (IS_ENABLED(CONFIG_X86_IO_APIC) && nr_ioapics > 0) + return; + + /* + * If the IO/APIC is disabled via config, kernel command line or + * lack of enumeration then all legacy interrupts are routed + * through the PIC. Make sure that they are marked as legacy + * vectors. PIC_CASCADE_IRQ has already been marked in + * lapic_assign_system_vectors(). + */ + for (i = 0; i < nr_legacy_irqs(); i++) { + if (i != PIC_CASCADE_IR) + lapic_assign_legacy_vector(i, true); + } +} + void __init lapic_assign_system_vectors(void) { unsigned int i, vector = 0; diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 3ef5868ac588..7aecb2fc3186 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -63,7 +63,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) case 15: return msr - MSR_P4_BPU_PERFCTR0; } - fallthrough; + break; case X86_VENDOR_ZHAOXIN: case X86_VENDOR_CENTAUR: return msr - MSR_ARCH_PERFMON_PERFCTR0; @@ -96,7 +96,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) case 15: return msr - MSR_P4_BSU_ESCR0; } - fallthrough; + break; case X86_VENDOR_ZHAOXIN: case X86_VENDOR_CENTAUR: return msr - MSR_ARCH_PERFMON_EVENTSEL0; diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c index 6ad165a5c0cc..64511c4a5200 100644 --- a/arch/x86/kernel/cpu/sgx/virt.c +++ b/arch/x86/kernel/cpu/sgx/virt.c @@ -212,6 +212,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file) list_splice_tail(&secs_pages, &zombie_secs_pages); mutex_unlock(&zombie_secs_pages_lock); + xa_destroy(&vepc->page_array); kfree(vepc); return 0; diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a4ec65317a7f..ec3ae3054792 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -307,13 +307,17 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) return 0; } - if (!access_ok(buf, size)) - return -EACCES; + if (!access_ok(buf, size)) { + ret = -EACCES; + goto out; + } - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; + if (!static_cpu_has(X86_FEATURE_FPU)) { + ret = fpregs_soft_set(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), + NULL, buf); + goto out; + } if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; @@ -369,6 +373,25 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); return 0; } + + /* + * The above did an FPU restore operation, restricted to + * the user portion of the registers, and failed, but the + * microcode might have modified the FPU registers + * nevertheless. + * + * If the FPU registers do not belong to current, then + * invalidate the FPU register state otherwise the task might + * preempt current and return to user space with corrupted + * FPU registers. + * + * In case current owns the FPU registers then no further + * action is required. The fixup below will handle it + * correctly. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + __cpu_invalidate_fpregs_state(); + fpregs_unlock(); } else { /* @@ -377,7 +400,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) */ ret = __copy_from_user(&env, buf, sizeof(env)); if (ret) - goto err_out; + goto out; envp = &env; } @@ -405,16 +428,9 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (use_xsave() && !fx_only) { u64 init_bv = xfeatures_mask_user() & ~user_xfeatures; - if (using_compacted_format()) { - ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); - } else { - ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); - - if (!ret && state_size > offsetof(struct xregs_state, header)) - ret = validate_user_xstate_header(&fpu->state.xsave.header); - } + ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) - goto err_out; + goto out; sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, fx_only); @@ -434,7 +450,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); if (ret) { ret = -EFAULT; - goto err_out; + goto out; } sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, @@ -452,7 +468,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } else { ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size); if (ret) - goto err_out; + goto out; fpregs_lock(); ret = copy_kernel_to_fregs_err(&fpu->state.fsave); @@ -463,7 +479,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_deactivate(fpu); fpregs_unlock(); -err_out: +out: if (ret) fpu__clear_user_states(fpu); return ret; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index a85c64000218..d0eef963aad1 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1402,60 +1402,3 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ - -#ifdef CONFIG_IOMMU_SUPPORT -void update_pasid(void) -{ - u64 pasid_state; - u32 pasid; - - if (!cpu_feature_enabled(X86_FEATURE_ENQCMD)) - return; - - if (!current->mm) - return; - - pasid = READ_ONCE(current->mm->pasid); - /* Set the valid bit in the PASID MSR/state only for valid pasid. */ - pasid_state = pasid == PASID_DISABLED ? - pasid : pasid | MSR_IA32_PASID_VALID; - - /* - * No need to hold fregs_lock() since the task's fpstate won't - * be changed by others (e.g. ptrace) while the task is being - * switched to or is in IPI. - */ - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { - /* The MSR is active and can be directly updated. */ - wrmsrl(MSR_IA32_PASID, pasid_state); - } else { - struct fpu *fpu = ¤t->thread.fpu; - struct ia32_pasid_state *ppasid_state; - struct xregs_state *xsave; - - /* - * The CPU's xstate registers are not currently active. Just - * update the PASID state in the memory buffer here. The - * PASID MSR will be loaded when returning to user mode. - */ - xsave = &fpu->state.xsave; - xsave->header.xfeatures |= XFEATURE_MASK_PASID; - ppasid_state = get_xsave_addr(xsave, XFEATURE_PASID); - /* - * Since XFEATURE_MASK_PASID is set in xfeatures, ppasid_state - * won't be NULL and no need to check its value. - * - * Only update the task's PASID state when it's different - * from the mm's pasid. - */ - if (ppasid_state->pasid != pasid_state) { - /* - * Invalid fpregs so that state restoring will pick up - * the PASID state. - */ - __fpu_invalidate_fpregs_state(fpu); - ppasid_state->pasid = pasid_state; - } - } -} -#endif /* CONFIG_IOMMU_SUPPORT */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 72920af0b3c0..1e720626069a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -44,6 +44,7 @@ #include <asm/pci-direct.h> #include <asm/prom.h> #include <asm/proto.h> +#include <asm/thermal.h> #include <asm/unwind.h> #include <asm/vsyscall.h> #include <linux/vmalloc.h> @@ -637,11 +638,11 @@ static void __init trim_snb_memory(void) * them from accessing certain memory ranges, namely anything below * 1M and in the pages listed in bad_pages[] above. * - * To avoid these pages being ever accessed by SNB gfx devices - * reserve all memory below the 1 MB mark and bad_pages that have - * not already been reserved at boot time. + * To avoid these pages being ever accessed by SNB gfx devices reserve + * bad_pages that have not already been reserved at boot time. + * All memory below the 1 MB mark is anyway reserved later during + * setup_arch(), so there is no need to reserve it here. */ - memblock_reserve(0, 1<<20); for (i = 0; i < ARRAY_SIZE(bad_pages); i++) { if (memblock_reserve(bad_pages[i], PAGE_SIZE)) @@ -733,14 +734,14 @@ static void __init early_reserve_memory(void) * The first 4Kb of memory is a BIOS owned area, but generally it is * not listed as such in the E820 table. * - * Reserve the first memory page and typically some additional - * memory (64KiB by default) since some BIOSes are known to corrupt - * low memory. See the Kconfig help text for X86_RESERVE_LOW. + * Reserve the first 64K of memory since some BIOSes are known to + * corrupt low memory. After the real mode trampoline is allocated the + * rest of the memory below 640k is reserved. * * In addition, make sure page 0 is always reserved because on * systems with L1TF its contents can be leaked to user processes. */ - memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); + memblock_reserve(0, SZ_64K); early_reserve_initrd(); @@ -751,6 +752,7 @@ static void __init early_reserve_memory(void) reserve_ibft_region(); reserve_bios_regions(); + trim_snb_memory(); } /* @@ -1081,14 +1083,20 @@ void __init setup_arch(char **cmdline_p) (max_pfn_mapped<<PAGE_SHIFT) - 1); #endif - reserve_real_mode(); - /* - * Reserving memory causing GPU hangs on Sandy Bridge integrated - * graphics devices should be done after we allocated memory under - * 1M for the real mode trampoline. + * Find free memory for the real mode trampoline and place it + * there. + * If there is not enough free memory under 1M, on EFI-enabled + * systems there will be additional attempt to reclaim the memory + * for the real mode trampoline at efi_free_boot_services(). + * + * Unconditionally reserve the entire first 1M of RAM because + * BIOSes are know to corrupt low memory and several + * hundred kilobytes are not worth complex detection what memory gets + * clobbered. Moreover, on machines with SandyBridge graphics or in + * setups that use crashkernel the entire 1M is reserved anyway. */ - trim_snb_memory(); + reserve_real_mode(); init_mem_mapping(); @@ -1226,6 +1234,14 @@ void __init setup_arch(char **cmdline_p) x86_init.timers.wallclock_init(); + /* + * This needs to run before setup_local_APIC() which soft-disables the + * local APIC temporarily and that masks the thermal LVT interrupt, + * leading to softlockups on machines which have configured SMI + * interrupt delivery. + */ + therm_lvt_init(); + mcheck_init(); register_refined_jiffies(CLOCK_TICK_RATE); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9a48f138832d..b4da665bb892 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -655,6 +655,7 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) entry->ecx = F(RDPID); ++array->nent; + break; default: break; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8a0ccdb56076..5e5de05a8fbf 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5111,7 +5111,7 @@ done: return rc; } -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type) { int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; @@ -5322,7 +5322,8 @@ done_prefixes: ctxt->execute = opcode.u.execute; - if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD))) + if (unlikely(emulation_type & EMULTYPE_TRAP_UD) && + likely(!(ctxt->d & EmulateOnUD))) return EMULATION_FAILED; if (unlikely(ctxt->d & diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index f98370a39936..f00830e5202f 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1172,6 +1172,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); u64 gfn; + int idx; if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || @@ -1190,9 +1191,16 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; hv->tsc_ref.tsc_sequence = 0; + + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&kvm->srcu); if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; + srcu_read_unlock(&kvm->srcu, idx); out_unlock: mutex_unlock(&hv->hv_lock); diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index f016838faedd..3e870bf9ca4d 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -314,7 +314,6 @@ struct x86_emulate_ctxt { int interruptibility; bool perm_ok; /* do not check permissions if true */ - bool ud; /* inject an #UD if host doesn't support insn */ bool tf; /* TF value before instruction (after for syscall/sysret) */ bool have_exception; @@ -491,7 +490,7 @@ enum x86_intercept { #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64 #endif -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len); +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type); bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt); #define EMULATION_FAILED -1 #define EMULATION_OK 0 diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c0ebef560bd1..17fa4ab1b834 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1410,6 +1410,9 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, if (!apic_x2apic_mode(apic)) valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI); + if (alignment + len > 4) + return 1; + if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) return 1; @@ -1494,6 +1497,15 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic) static void cancel_hv_timer(struct kvm_lapic *apic); +static void cancel_apic_timer(struct kvm_lapic *apic) +{ + hrtimer_cancel(&apic->lapic_timer.timer); + preempt_disable(); + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_timer(apic); + preempt_enable(); +} + static void apic_update_lvtt(struct kvm_lapic *apic) { u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) & @@ -1502,11 +1514,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic) if (apic->lapic_timer.timer_mode != timer_mode) { if (apic_lvtt_tscdeadline(apic) != (timer_mode == APIC_LVT_TIMER_TSCDEADLINE)) { - hrtimer_cancel(&apic->lapic_timer.timer); - preempt_disable(); - if (apic->lapic_timer.hv_timer_in_use) - cancel_hv_timer(apic); - preempt_enable(); + cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, 0); apic->lapic_timer.period = 0; apic->lapic_timer.tscdeadline = 0; @@ -1598,11 +1606,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline; + if (lapic_timer_advance_dynamic) { + adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); + /* + * If the timer fired early, reread the TSC to account for the + * overhead of the above adjustment to avoid waiting longer + * than is necessary. + */ + if (guest_tsc < tsc_deadline) + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + } + if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - - if (lapic_timer_advance_dynamic) - adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); } void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) @@ -1661,7 +1677,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) } atomic_inc(&apic->lapic_timer.pending); - kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_make_request(KVM_REQ_UNBLOCK, vcpu); if (from_timer_fn) kvm_vcpu_kick(vcpu); } @@ -2084,7 +2100,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) if (apic_lvtt_tscdeadline(apic)) break; - hrtimer_cancel(&apic->lapic_timer.timer); + cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); break; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 0144c40d09c7..8d5876dfc6b7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4739,9 +4739,33 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) context->inject_page_fault = kvm_inject_page_fault; } +static union kvm_mmu_role kvm_calc_nested_mmu_role(struct kvm_vcpu *vcpu) +{ + union kvm_mmu_role role = kvm_calc_shadow_root_page_role_common(vcpu, false); + + /* + * Nested MMUs are used only for walking L2's gva->gpa, they never have + * shadow pages of their own and so "direct" has no meaning. Set it + * to "true" to try to detect bogus usage of the nested MMU. + */ + role.base.direct = true; + + if (!is_paging(vcpu)) + role.base.level = 0; + else if (is_long_mode(vcpu)) + role.base.level = is_la57_mode(vcpu) ? PT64_ROOT_5LEVEL : + PT64_ROOT_4LEVEL; + else if (is_pae(vcpu)) + role.base.level = PT32E_ROOT_LEVEL; + else + role.base.level = PT32_ROOT_LEVEL; + + return role; +} + static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) { - union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false); + union kvm_mmu_role new_role = kvm_calc_nested_mmu_role(vcpu); struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; if (new_role.as_u64 == g_context->mmu_role.as_u64) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 70b7e44e3035..823a5919f9fa 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -90,8 +90,8 @@ struct guest_walker { gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS]; bool pte_writable[PT_MAX_FULL_LEVELS]; - unsigned pt_access; - unsigned pte_access; + unsigned int pt_access[PT_MAX_FULL_LEVELS]; + unsigned int pte_access; gfn_t gfn; struct x86_exception fault; }; @@ -418,13 +418,15 @@ retry_walk: } walker->ptes[walker->level - 1] = pte; + + /* Convert to ACC_*_MASK flags for struct guest_walker. */ + walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask); } while (!is_last_gpte(mmu, walker->level, pte)); pte_pkey = FNAME(gpte_pkeys)(vcpu, pte); accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; /* Convert to ACC_*_MASK flags for struct guest_walker. */ - walker->pt_access = FNAME(gpte_access)(pt_access ^ walk_nx_mask); walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask); errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) @@ -463,7 +465,8 @@ retry_walk: } pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, walker->pte_access, walker->pt_access); + __func__, (u64)pte, walker->pte_access, + walker->pt_access[walker->level - 1]); return 1; error: @@ -643,7 +646,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled; struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; - unsigned direct_access, access = gw->pt_access; + unsigned int direct_access, access; int top_level, level, req_level, ret; gfn_t base_gfn = gw->gfn; @@ -675,6 +678,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, sp = NULL; if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; + access = gw->pt_access[it.level - 2]; sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, false, access); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 95eeb5ac6a8a..237317b1eddd 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1192,9 +1192,9 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) } /* - * Remove write access from all the SPTEs mapping GFNs [start, end). If - * skip_4k is set, SPTEs that map 4k pages, will not be write-protected. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. + * Remove write access from all SPTEs at or above min_level that map GFNs + * [start, end). Returns true if an SPTE has been changed and the TLBs need to + * be flushed. */ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, int min_level) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 712b4e0de481..5e7e920113f3 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -28,10 +28,8 @@ #include "svm.h" /* enable / disable AVIC */ -int avic; -#ifdef CONFIG_X86_LOCAL_APIC -module_param(avic, int, S_IRUGO); -#endif +bool avic; +module_param(avic, bool, S_IRUGO); #define SVM_AVIC_DOORBELL 0xc001011b @@ -223,7 +221,7 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, return &avic_physical_id_table[index]; } -/** +/* * Note: * AVIC hardware walks the nested page table to check permissions, * but does not use the SPA address specified in the leaf page @@ -766,7 +764,7 @@ out: return ret; } -/** +/* * Note: * The HW cannot support posting multicast/broadcast * interrupts to a vCPU. So, we still use legacy interrupt @@ -1007,7 +1005,7 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } -/** +/* * This function is called during VCPU halt/unhalt. */ static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 5bc887e9a986..8d36f0c73071 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -199,9 +199,19 @@ static void sev_asid_free(struct kvm_sev_info *sev) sev->misc_cg = NULL; } -static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +static void sev_decommission(unsigned int handle) { struct sev_data_decommission decommission; + + if (!handle) + return; + + decommission.handle = handle; + sev_guest_decommission(&decommission, NULL); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ struct sev_data_deactivate deactivate; if (!handle) @@ -214,9 +224,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_guest_deactivate(&deactivate, NULL); up_read(&sev_deactivate_lock); - /* decommission handle */ - decommission.handle = handle; - sev_guest_decommission(&decommission, NULL); + sev_decommission(handle); } static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) @@ -341,8 +349,10 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start.handle, error); - if (ret) + if (ret) { + sev_decommission(start.handle); goto e_free_session; + } /* return handle to userspace */ params.handle = start.handle; @@ -1103,10 +1113,9 @@ __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp, struct sev_data_send_start data; int ret; + memset(&data, 0, sizeof(data)); data.handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); - if (ret < 0) - return ret; params->session_len = data.session_len; if (copy_to_user((void __user *)(uintptr_t)argp->data, params, @@ -1215,10 +1224,9 @@ __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp, struct sev_data_send_update_data data; int ret; + memset(&data, 0, sizeof(data)); data.handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error); - if (ret < 0) - return ret; params->hdr_len = data.hdr_len; params->trans_len = data.trans_len; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 05eca131eaf2..e088086f3de6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1010,9 +1010,7 @@ static __init int svm_hardware_setup(void) } if (avic) { - if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_AVIC) || - !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { + if (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)) { avic = false; } else { pr_info("AVIC enabled\n"); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 2c9ece618b29..2908c6ab5bb4 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -480,7 +480,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops; #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL -extern int avic; +extern bool avic; static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) { diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a61c015870e3..4f839148948b 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1550,16 +1550,16 @@ TRACE_EVENT(kvm_nested_vmenter_failed, TP_ARGS(msg, err), TP_STRUCT__entry( - __field(const char *, msg) + __string(msg, msg) __field(u32, err) ), TP_fast_assign( - __entry->msg = msg; + __assign_str(msg, msg); __entry->err = err; ), - TP_printk("%s%s", __entry->msg, !__entry->err ? "" : + TP_printk("%s%s", __get_str(msg), !__entry->err ? "" : __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS)) ); diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 8dee8a5fbc17..aa0e7872fcc9 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -90,8 +90,7 @@ static inline bool cpu_has_vmx_preemption_timer(void) static inline bool cpu_has_vmx_posted_intr(void) { - return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && - vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; } static inline bool cpu_has_load_ia32_efer(void) diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 459748680daf..5f81ef092bd4 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -238,6 +238,20 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) /* + * Bail out of the block loop if the VM has an assigned + * device, but the blocking vCPU didn't reconfigure the + * PI.NV to the wakeup vector, i.e. the assigned device + * came along after the initial check in pi_pre_block(). + */ +void vmx_pi_start_assignment(struct kvm *kvm) +{ + if (!irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); +} + +/* * pi_update_irte - set IRTE for Posted-Interrupts * * @kvm: kvm diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 0bdc41391c5b..7f7b2326caf5 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -95,5 +95,6 @@ void __init pi_init_cpu(int cpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); +void vmx_pi_start_assignment(struct kvm *kvm); #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4bceb5ca3a89..c2a779b688e6 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4843,7 +4843,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; - unsigned long cr2, rip, dr6; + unsigned long cr2, dr6; u32 vect_info; vect_info = vmx->idt_vectoring_info; @@ -4933,8 +4933,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vmx->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_run->exit_reason = KVM_EXIT_DEBUG; - rip = kvm_rip_read(vcpu); - kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; + kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = ex_no; break; case AC_VECTOR: @@ -6248,6 +6247,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) switch (kvm_get_apic_mode(vcpu)) { case LAPIC_MODE_INVALID: WARN_ONCE(true, "Invalid local APIC state"); + break; case LAPIC_MODE_DISABLED: break; case LAPIC_MODE_XAPIC: @@ -7721,6 +7721,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .nested_ops = &vmx_nested_ops, .update_pi_irte = pi_update_irte, + .start_assignment = vmx_pi_start_assignment, #ifdef CONFIG_X86_64 .set_hv_timer = vmx_set_hv_timer, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bbc4e04e67ad..e0f4a46649d7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3072,6 +3072,19 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; + + if (!tdp_enabled) { + /* + * A TLB flush on behalf of the guest is equivalent to + * INVPCID(all), toggling CR4.PGE, etc., which requires + * a forced sync of the shadow page tables. Unload the + * entire MMU here and the subsequent load will sync the + * shadow page tables, and also flush the TLB. + */ + kvm_mmu_unload(vcpu); + return; + } + static_call(kvm_x86_tlb_flush_guest)(vcpu); } @@ -3101,10 +3114,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu) * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { + u8 st_preempted = xchg(&st->preempted, 0); + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, - st->preempted & KVM_VCPU_FLUSH_TLB); - if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) + st_preempted & KVM_VCPU_FLUSH_TLB); + if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + } else { + st->preempted = 0; } vcpu->arch.st.preempted = 0; @@ -7089,7 +7106,10 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) { - emul_to_vcpu(ctxt)->arch.hflags = emul_flags; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + vcpu->arch.hflags = emul_flags; + kvm_mmu_reset_context(vcpu); } static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, @@ -7226,6 +7246,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } @@ -7561,14 +7586,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, kvm_vcpu_check_breakpoint(vcpu, &r)) return r; - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; - - r = x86_decode_insn(ctxt, insn, insn_len); + r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; @@ -8243,6 +8261,7 @@ void kvm_arch_exit(void) kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(user_return_msrs); + kmem_cache_destroy(x86_emulator_cache); kmem_cache_destroy(x86_fpu_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); @@ -8360,6 +8379,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) vcpu->stat.directed_yield_attempted++; + if (single_task_running()) + goto no_yield; + rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); @@ -9496,7 +9518,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (r <= 0) break; - kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); @@ -10115,8 +10137,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + - get_segment_base(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace @@ -11499,7 +11520,8 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) void kvm_arch_start_assignment(struct kvm *kvm) { - atomic_inc(&kvm->arch.assigned_device_count); + if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) + static_call_cond(kvm_x86_start_assignment)(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 1c548ad00752..6bda7f67d737 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -836,8 +836,8 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, if (si_code == SEGV_PKUERR) force_sig_pkuerr((void __user *)address, pkey); - - force_sig_fault(SIGSEGV, si_code, (void __user *)address); + else + force_sig_fault(SIGSEGV, si_code, (void __user *)address); local_irq_disable(); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 12c686c65ea9..60ade7dd71bd 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -118,7 +118,9 @@ static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *des if (!IS_ENABLED(CONFIG_EFI)) return; - if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA) + if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA || + (efi_mem_type(addr) == EFI_BOOT_SERVICES_DATA && + efi_mem_attributes(addr) & EFI_MEMORY_RUNTIME)) desc->flags |= IORES_MAP_ENCRYPTED; } diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index a9639f663d25..470b20208430 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -504,10 +504,6 @@ void __init sme_enable(struct boot_params *bp) #define AMD_SME_BIT BIT(0) #define AMD_SEV_BIT BIT(1) - /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; - /* * Check for the SME/SEV feature: * CPUID Fn8000_001F[EAX] @@ -519,11 +515,16 @@ void __init sme_enable(struct boot_params *bp) eax = 0x8000001f; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); - if (!(eax & feature_mask)) + /* Check whether SEV or SME is supported */ + if (!(eax & (AMD_SEV_BIT | AMD_SME_BIT))) return; me_mask = 1UL << (ebx & 0x3f); + /* Check the SEV MSR whether SEV or SME is enabled */ + sev_status = __rdmsr(MSR_AMD64_SEV); + feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { /* diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 5eb4dc2b97da..e94da744386f 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -254,7 +254,13 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) /* make sure all non-reserved blocks are inside the limits */ bi->start = max(bi->start, low); - bi->end = min(bi->end, high); + + /* preserve info for non-RAM areas above 'max_pfn': */ + if (bi->end > high) { + numa_add_memblk_to(bi->nid, high, bi->end, + &numa_reserved_meminfo); + bi->end = high; + } /* and there's no empty block */ if (bi->start >= bi->end) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 02dc64625e64..2edd86649468 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -779,4 +779,48 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); +#define RS690_LOWER_TOP_OF_DRAM2 0x30 +#define RS690_LOWER_TOP_OF_DRAM2_VALID 0x1 +#define RS690_UPPER_TOP_OF_DRAM2 0x31 +#define RS690_HTIU_NB_INDEX 0xA8 +#define RS690_HTIU_NB_INDEX_WR_ENABLE 0x100 +#define RS690_HTIU_NB_DATA 0xAC + +/* + * Some BIOS implementations support RAM above 4GB, but do not configure the + * PCI host to respond to bus master accesses for these addresses. These + * implementations set the TOP_OF_DRAM_SLOT1 register correctly, so PCI DMA + * works as expected for addresses below 4GB. + * + * Reference: "AMD RS690 ASIC Family Register Reference Guide" (pg. 2-57) + * https://www.amd.com/system/files/TechDocs/43372_rs690_rrg_3.00o.pdf + */ +static void rs690_fix_64bit_dma(struct pci_dev *pdev) +{ + u32 val = 0; + phys_addr_t top_of_dram = __pa(high_memory - 1) + 1; + + if (top_of_dram <= (1ULL << 32)) + return; + + pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, + RS690_LOWER_TOP_OF_DRAM2); + pci_read_config_dword(pdev, RS690_HTIU_NB_DATA, &val); + + if (val) + return; + + pci_info(pdev, "Adjusting top of DRAM to %pa for 64-bit DMA support\n", &top_of_dram); + + pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, + RS690_UPPER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE); + pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, top_of_dram >> 32); + + pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, + RS690_LOWER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE); + pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, + top_of_dram | RS690_LOWER_TOP_OF_DRAM2_VALID); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); + #endif diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 7850111008a8..b15ebfe40a73 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -450,6 +450,18 @@ void __init efi_free_boot_services(void) size -= rm_size; } + /* + * Don't free memory under 1M for two reasons: + * - BIOS might clobber it + * - Crash kernel needs it to be reserved + */ + if (start + size < SZ_1M) + continue; + if (start < SZ_1M) { + size -= (SZ_1M - start); + start = SZ_1M; + } + memblock_free_late(start, size); } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 2e1c1bec0f9e..6534c92d0f83 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -29,14 +29,16 @@ void __init reserve_real_mode(void) /* Has to be under 1M so we can execute real-mode AP code. */ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); - if (!mem) { + if (!mem) pr_info("No sub-1M memory is available for the trampoline\n"); - return; - } + else + set_real_mode_mem(mem); - memblock_reserve(mem, size); - set_real_mode_mem(mem); - crash_reserve_low_1M(); + /* + * Unconditionally reserve the entire fisrt 1M, see comment in + * setup_arch(). + */ + memblock_reserve(0, SZ_1M); } static void sme_sev_setup_real_mode(struct trampoline_header *th) diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 6cd7f7025df4..d8a91521144e 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -233,7 +233,8 @@ async_xor_offs(struct page *dest, unsigned int offset, if (submit->flags & ASYNC_TX_XOR_DROP_DST) { src_cnt--; src_list++; - src_offs++; + if (src_offs) + src_offs++; } /* wait for any prerequisite operations */ diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index 0ec5b3f69112..6e02448d15d9 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -226,6 +226,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = { { "AMDI0010", APD_ADDR(wt_i2c_desc) }, { "AMD0020", APD_ADDR(cz_uart_desc) }, { "AMDI0020", APD_ADDR(cz_uart_desc) }, + { "AMDI0022", APD_ADDR(cz_uart_desc) }, { "AMD0030", }, { "AMD0040", APD_ADDR(fch_misc_desc)}, { "HYGO0010", APD_ADDR(wt_i2c_desc) }, diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c index 624a26794d55..e5ba9795ec69 100644 --- a/drivers/acpi/acpica/utdelete.c +++ b/drivers/acpi/acpica/utdelete.c @@ -285,6 +285,14 @@ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object) } break; + case ACPI_TYPE_LOCAL_ADDRESS_HANDLER: + + ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, + "***** Address handler %p\n", object)); + + acpi_os_delete_mutex(object->address_space.context_mutex); + break; + default: break; diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index be7da23fad76..a4bd673934c0 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -330,32 +330,21 @@ static void acpi_bus_osc_negotiate_platform_control(void) if (ACPI_FAILURE(acpi_run_osc(handle, &context))) return; - capbuf_ret = context.ret.pointer; - if (context.ret.length <= OSC_SUPPORT_DWORD) { - kfree(context.ret.pointer); - return; - } + kfree(context.ret.pointer); - /* - * Now run _OSC again with query flag clear and with the caps - * supported by both the OS and the platform. - */ + /* Now run _OSC again with query flag clear */ capbuf[OSC_QUERY_DWORD] = 0; - capbuf[OSC_SUPPORT_DWORD] = capbuf_ret[OSC_SUPPORT_DWORD]; - kfree(context.ret.pointer); if (ACPI_FAILURE(acpi_run_osc(handle, &context))) return; capbuf_ret = context.ret.pointer; - if (context.ret.length > OSC_SUPPORT_DWORD) { - osc_sb_apei_support_acked = - capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_APEI_SUPPORT; - osc_pc_lpi_support_confirmed = - capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_PCLPI_SUPPORT; - osc_sb_native_usb4_support_confirmed = - capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_NATIVE_USB4_SUPPORT; - } + osc_sb_apei_support_acked = + capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_APEI_SUPPORT; + osc_pc_lpi_support_confirmed = + capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_PCLPI_SUPPORT; + osc_sb_native_usb4_support_confirmed = + capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_NATIVE_USB4_SUPPORT; kfree(context.ret.pointer); } diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index f973bbe90e5e..e21611c9a170 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -134,7 +134,7 @@ int acpi_power_init(void); void acpi_power_resources_list_free(struct list_head *list); int acpi_extract_power_resources(union acpi_object *package, unsigned int start, struct list_head *list); -int acpi_add_power_resource(acpi_handle handle); +struct acpi_device *acpi_add_power_resource(acpi_handle handle); void acpi_power_add_remove_device(struct acpi_device *adev, bool add); int acpi_power_wakeup_list_init(struct list_head *list, int *system_level); int acpi_device_sleep_wake(struct acpi_device *dev, @@ -142,7 +142,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); -void acpi_turn_off_unused_power_resources(void); +void acpi_turn_off_unused_power_resources(bool init); /* -------------------------------------------------------------------------- Device Power Management diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 56102eaaa2da..97c9a94a1a30 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -52,6 +52,7 @@ struct acpi_power_resource { u32 system_level; u32 order; unsigned int ref_count; + unsigned int users; bool wakeup_enabled; struct mutex resource_lock; struct list_head dependents; @@ -147,6 +148,7 @@ int acpi_extract_power_resources(union acpi_object *package, unsigned int start, for (i = start; i < package->package.count; i++) { union acpi_object *element = &package->package.elements[i]; + struct acpi_device *rdev; acpi_handle rhandle; if (element->type != ACPI_TYPE_LOCAL_REFERENCE) { @@ -163,13 +165,16 @@ int acpi_extract_power_resources(union acpi_object *package, unsigned int start, if (acpi_power_resource_is_dup(package, start, i)) continue; - err = acpi_add_power_resource(rhandle); - if (err) + rdev = acpi_add_power_resource(rhandle); + if (!rdev) { + err = -ENODEV; break; - + } err = acpi_power_resources_list_add(rhandle, list); if (err) break; + + to_power_resource(rdev)->users++; } if (err) acpi_power_resources_list_free(list); @@ -907,7 +912,7 @@ static void acpi_power_add_resource_to_list(struct acpi_power_resource *resource mutex_unlock(&power_resource_list_lock); } -int acpi_add_power_resource(acpi_handle handle) +struct acpi_device *acpi_add_power_resource(acpi_handle handle) { struct acpi_power_resource *resource; struct acpi_device *device = NULL; @@ -918,11 +923,11 @@ int acpi_add_power_resource(acpi_handle handle) acpi_bus_get_device(handle, &device); if (device) - return 0; + return device; resource = kzalloc(sizeof(*resource), GFP_KERNEL); if (!resource) - return -ENOMEM; + return NULL; device = &resource->device; acpi_init_device_object(device, handle, ACPI_BUS_TYPE_POWER); @@ -959,11 +964,11 @@ int acpi_add_power_resource(acpi_handle handle) acpi_power_add_resource_to_list(resource); acpi_device_add_finalize(device); - return 0; + return device; err: acpi_release_power_resource(&device->dev); - return result; + return NULL; } #ifdef CONFIG_ACPI_SLEEP @@ -997,7 +1002,38 @@ void acpi_resume_power_resources(void) } #endif -void acpi_turn_off_unused_power_resources(void) +static void acpi_power_turn_off_if_unused(struct acpi_power_resource *resource, + bool init) +{ + if (resource->ref_count > 0) + return; + + if (init) { + if (resource->users > 0) + return; + } else { + int result, state; + + result = acpi_power_get_state(resource->device.handle, &state); + if (result || state == ACPI_POWER_RESOURCE_STATE_OFF) + return; + } + + dev_info(&resource->device.dev, "Turning OFF\n"); + __acpi_power_off(resource); +} + +/** + * acpi_turn_off_unused_power_resources - Turn off power resources not in use. + * @init: Control switch. + * + * If @ainit is set, unconditionally turn off all of the ACPI power resources + * without any users. + * + * Otherwise, turn off all ACPI power resources without active references (that + * is, the ones that should be "off" at the moment) that are "on". + */ +void acpi_turn_off_unused_power_resources(bool init) { struct acpi_power_resource *resource; @@ -1006,10 +1042,7 @@ void acpi_turn_off_unused_power_resources(void) list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) { mutex_lock(&resource->resource_lock); - if (!resource->ref_count) { - dev_info(&resource->device.dev, "Turning OFF\n"); - __acpi_power_off(resource); - } + acpi_power_turn_off_if_unused(resource, init); mutex_unlock(&resource->resource_lock); } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 453eff8ec8c3..e10d38ac7cf2 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2360,7 +2360,7 @@ int __init acpi_scan_init(void) } } - acpi_turn_off_unused_power_resources(); + acpi_turn_off_unused_power_resources(true); acpi_scan_initialized = true; diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 09fd13757b65..3bb2adef8490 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -504,7 +504,7 @@ static void acpi_pm_start(u32 acpi_state) */ static void acpi_pm_end(void) { - acpi_turn_off_unused_power_resources(); + acpi_turn_off_unused_power_resources(false); acpi_scan_lock_release(); /* * This is necessary in case acpi_pm_finish() is not called during a @@ -1009,10 +1009,8 @@ static void acpi_sleep_hibernate_setup(void) return; acpi_get_table(ACPI_SIG_FACS, 1, (struct acpi_table_header **)&facs); - if (facs) { + if (facs) s4_hardware_signature = facs->hardware_signature; - acpi_put_table((struct acpi_table_header *)facs); - } } #else /* !CONFIG_HIBERNATION */ static inline void acpi_sleep_hibernate_setup(void) {} diff --git a/drivers/base/core.c b/drivers/base/core.c index 628e33939aca..54ba506e5a89 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -194,6 +194,17 @@ int device_links_read_lock_held(void) { return srcu_read_lock_held(&device_links_srcu); } + +static void device_link_synchronize_removal(void) +{ + synchronize_srcu(&device_links_srcu); +} + +static void device_link_remove_from_lists(struct device_link *link) +{ + list_del_rcu(&link->s_node); + list_del_rcu(&link->c_node); +} #else /* !CONFIG_SRCU */ static DECLARE_RWSEM(device_links_lock); @@ -224,6 +235,16 @@ int device_links_read_lock_held(void) return lockdep_is_held(&device_links_lock); } #endif + +static inline void device_link_synchronize_removal(void) +{ +} + +static void device_link_remove_from_lists(struct device_link *link) +{ + list_del(&link->s_node); + list_del(&link->c_node); +} #endif /* !CONFIG_SRCU */ static bool device_is_ancestor(struct device *dev, struct device *target) @@ -445,8 +466,13 @@ static struct attribute *devlink_attrs[] = { }; ATTRIBUTE_GROUPS(devlink); -static void device_link_free(struct device_link *link) +static void device_link_release_fn(struct work_struct *work) { + struct device_link *link = container_of(work, struct device_link, rm_work); + + /* Ensure that all references to the link object have been dropped. */ + device_link_synchronize_removal(); + while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put(link->supplier); @@ -455,24 +481,19 @@ static void device_link_free(struct device_link *link) kfree(link); } -#ifdef CONFIG_SRCU -static void __device_link_free_srcu(struct rcu_head *rhead) -{ - device_link_free(container_of(rhead, struct device_link, rcu_head)); -} - static void devlink_dev_release(struct device *dev) { struct device_link *link = to_devlink(dev); - call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu); -} -#else -static void devlink_dev_release(struct device *dev) -{ - device_link_free(to_devlink(dev)); + INIT_WORK(&link->rm_work, device_link_release_fn); + /* + * It may take a while to complete this work because of the SRCU + * synchronization in device_link_release_fn() and if the consumer or + * supplier devices get deleted when it runs, so put it into the "long" + * workqueue. + */ + queue_work(system_long_wq, &link->rm_work); } -#endif static struct class devlink_class = { .name = "devlink", @@ -846,7 +867,6 @@ out: } EXPORT_SYMBOL_GPL(device_link_add); -#ifdef CONFIG_SRCU static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); @@ -856,25 +876,9 @@ static void __device_link_del(struct kref *kref) pm_runtime_drop_link(link); - list_del_rcu(&link->s_node); - list_del_rcu(&link->c_node); - device_unregister(&link->link_dev); -} -#else /* !CONFIG_SRCU */ -static void __device_link_del(struct kref *kref) -{ - struct device_link *link = container_of(kref, struct device_link, kref); - - dev_info(link->consumer, "Dropping the link to %s\n", - dev_name(link->supplier)); - - pm_runtime_drop_link(link); - - list_del(&link->s_node); - list_del(&link->c_node); + device_link_remove_from_lists(link); device_unregister(&link->link_dev); } -#endif /* !CONFIG_SRCU */ static void device_link_put_kref(struct device_link *link) { diff --git a/drivers/base/memory.c b/drivers/base/memory.c index b31b3af5c490..d5ffaab3cb61 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -218,14 +218,14 @@ static int memory_block_offline(struct memory_block *mem) struct zone *zone; int ret; - zone = page_zone(pfn_to_page(start_pfn)); - /* * Unaccount before offlining, such that unpopulated zone and kthreads * can properly be torn down in offline_pages(). */ - if (nr_vmemmap_pages) + if (nr_vmemmap_pages) { + zone = page_zone(pfn_to_page(start_pfn)); adjust_present_page_count(zone, -nr_vmemmap_pages); + } ret = offline_pages(start_pfn + nr_vmemmap_pages, nr_pages - nr_vmemmap_pages); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d58d68f3c7cd..76e12f3482a9 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1879,29 +1879,18 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, static int lo_open(struct block_device *bdev, fmode_t mode) { - struct loop_device *lo; + struct loop_device *lo = bdev->bd_disk->private_data; int err; - /* - * take loop_ctl_mutex to protect lo pointer from race with - * loop_control_ioctl(LOOP_CTL_REMOVE), however, to reduce contention - * release it prior to updating lo->lo_refcnt. - */ - err = mutex_lock_killable(&loop_ctl_mutex); - if (err) - return err; - lo = bdev->bd_disk->private_data; - if (!lo) { - mutex_unlock(&loop_ctl_mutex); - return -ENXIO; - } err = mutex_lock_killable(&lo->lo_mutex); - mutex_unlock(&loop_ctl_mutex); if (err) return err; - atomic_inc(&lo->lo_refcnt); + if (lo->lo_state == Lo_deleting) + err = -ENXIO; + else + atomic_inc(&lo->lo_refcnt); mutex_unlock(&lo->lo_mutex); - return 0; + return err; } static void lo_release(struct gendisk *disk, fmode_t mode) @@ -2285,7 +2274,7 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, mutex_unlock(&lo->lo_mutex); break; } - lo->lo_disk->private_data = NULL; + lo->lo_state = Lo_deleting; mutex_unlock(&lo->lo_mutex); idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); diff --git a/drivers/block/loop.h b/drivers/block/loop.h index a3c04f310672..5beb959b94d3 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -22,6 +22,7 @@ enum { Lo_unbound, Lo_bound, Lo_rundown, + Lo_deleting, }; struct loop_func_table; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 5d603ef39bad..7f6ba2c975ed 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -388,6 +388,8 @@ static const struct usb_device_id blacklist_table[] = { /* Realtek 8822CE Bluetooth devices */ { USB_DEVICE(0x0bda, 0xb00c), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0xc822), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek 8852AE Bluetooth devices */ { USB_DEVICE(0x0bda, 0xc852), .driver_info = BTUSB_REALTEK | @@ -2527,10 +2529,17 @@ static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev, } btusb_setup_intel_newgen_get_fw_name(ver, fwname, sizeof(fwname), "sfi"); - err = request_firmware(&fw, fwname, &hdev->dev); + err = firmware_request_nowarn(&fw, fwname, &hdev->dev); if (err < 0) { + if (!test_bit(BTUSB_BOOTLOADER, &data->flags)) { + /* Firmware has already been loaded */ + set_bit(BTUSB_FIRMWARE_LOADED, &data->flags); + return 0; + } + bt_dev_err(hdev, "Failed to load Intel firmware file %s (%d)", fwname, err); + return err; } @@ -2680,12 +2689,24 @@ download: err = btusb_setup_intel_new_get_fw_name(ver, params, fwname, sizeof(fwname), "sfi"); if (err < 0) { + if (!test_bit(BTUSB_BOOTLOADER, &data->flags)) { + /* Firmware has already been loaded */ + set_bit(BTUSB_FIRMWARE_LOADED, &data->flags); + return 0; + } + bt_dev_err(hdev, "Unsupported Intel firmware naming"); return -EINVAL; } - err = request_firmware(&fw, fwname, &hdev->dev); + err = firmware_request_nowarn(&fw, fwname, &hdev->dev); if (err < 0) { + if (!test_bit(BTUSB_BOOTLOADER, &data->flags)) { + /* Firmware has already been loaded */ + set_bit(BTUSB_FIRMWARE_LOADED, &data->flags); + return 0; + } + bt_dev_err(hdev, "Failed to load Intel firmware file %s (%d)", fwname, err); return err; diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c index 7c810f02a2ef..b3357a8a2fdb 100644 --- a/drivers/bus/mhi/pci_generic.c +++ b/drivers/bus/mhi/pci_generic.c @@ -311,8 +311,8 @@ static const struct mhi_channel_config mhi_foxconn_sdx55_channels[] = { MHI_CHANNEL_CONFIG_DL(5, "DIAG", 32, 1), MHI_CHANNEL_CONFIG_UL(12, "MBIM", 32, 0), MHI_CHANNEL_CONFIG_DL(13, "MBIM", 32, 0), - MHI_CHANNEL_CONFIG_UL(32, "AT", 32, 0), - MHI_CHANNEL_CONFIG_DL(33, "AT", 32, 0), + MHI_CHANNEL_CONFIG_UL(32, "DUN", 32, 0), + MHI_CHANNEL_CONFIG_DL(33, "DUN", 32, 0), MHI_CHANNEL_CONFIG_HW_UL(100, "IP_HW0_MBIM", 128, 2), MHI_CHANNEL_CONFIG_HW_DL(101, "IP_HW0_MBIM", 128, 3), }; @@ -708,7 +708,7 @@ static void mhi_pci_remove(struct pci_dev *pdev) struct mhi_pci_device *mhi_pdev = pci_get_drvdata(pdev); struct mhi_controller *mhi_cntrl = &mhi_pdev->mhi_cntrl; - del_timer(&mhi_pdev->health_check_timer); + del_timer_sync(&mhi_pdev->health_check_timer); cancel_work_sync(&mhi_pdev->recovery_work); if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) { @@ -935,9 +935,43 @@ static int __maybe_unused mhi_pci_resume(struct device *dev) return ret; } +static int __maybe_unused mhi_pci_freeze(struct device *dev) +{ + struct mhi_pci_device *mhi_pdev = dev_get_drvdata(dev); + struct mhi_controller *mhi_cntrl = &mhi_pdev->mhi_cntrl; + + /* We want to stop all operations, hibernation does not guarantee that + * device will be in the same state as before freezing, especially if + * the intermediate restore kernel reinitializes MHI device with new + * context. + */ + if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) { + mhi_power_down(mhi_cntrl, false); + mhi_unprepare_after_power_down(mhi_cntrl); + } + + return 0; +} + +static int __maybe_unused mhi_pci_restore(struct device *dev) +{ + struct mhi_pci_device *mhi_pdev = dev_get_drvdata(dev); + + /* Reinitialize the device */ + queue_work(system_long_wq, &mhi_pdev->recovery_work); + + return 0; +} + static const struct dev_pm_ops mhi_pci_pm_ops = { SET_RUNTIME_PM_OPS(mhi_pci_runtime_suspend, mhi_pci_runtime_resume, NULL) - SET_SYSTEM_SLEEP_PM_OPS(mhi_pci_suspend, mhi_pci_resume) +#ifdef CONFIG_PM_SLEEP + .suspend = mhi_pci_suspend, + .resume = mhi_pci_resume, + .freeze = mhi_pci_freeze, + .thaw = mhi_pci_restore, + .restore = mhi_pci_restore, +#endif }; static struct pci_driver mhi_pci_driver = { diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 5fae60f8c135..38cb116ed433 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1334,6 +1334,34 @@ err_allow_idle: return error; } +static int sysc_reinit_module(struct sysc *ddata, bool leave_enabled) +{ + struct device *dev = ddata->dev; + int error; + + /* Disable target module if it is enabled */ + if (ddata->enabled) { + error = sysc_runtime_suspend(dev); + if (error) + dev_warn(dev, "reinit suspend failed: %i\n", error); + } + + /* Enable target module */ + error = sysc_runtime_resume(dev); + if (error) + dev_warn(dev, "reinit resume failed: %i\n", error); + + if (leave_enabled) + return error; + + /* Disable target module if no leave_enabled was set */ + error = sysc_runtime_suspend(dev); + if (error) + dev_warn(dev, "reinit suspend failed: %i\n", error); + + return error; +} + static int __maybe_unused sysc_noirq_suspend(struct device *dev) { struct sysc *ddata; @@ -1344,12 +1372,18 @@ static int __maybe_unused sysc_noirq_suspend(struct device *dev) (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE)) return 0; - return pm_runtime_force_suspend(dev); + if (!ddata->enabled) + return 0; + + ddata->needs_resume = 1; + + return sysc_runtime_suspend(dev); } static int __maybe_unused sysc_noirq_resume(struct device *dev) { struct sysc *ddata; + int error = 0; ddata = dev_get_drvdata(dev); @@ -1357,7 +1391,19 @@ static int __maybe_unused sysc_noirq_resume(struct device *dev) (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE)) return 0; - return pm_runtime_force_resume(dev); + if (ddata->cfg.quirks & SYSC_QUIRK_REINIT_ON_RESUME) { + error = sysc_reinit_module(ddata, ddata->needs_resume); + if (error) + dev_warn(dev, "noirq_resume failed: %i\n", error); + } else if (ddata->needs_resume) { + error = sysc_runtime_resume(dev); + if (error) + dev_warn(dev, "noirq_resume failed: %i\n", error); + } + + ddata->needs_resume = 0; + + return error; } static const struct dev_pm_ops sysc_pm_ops = { @@ -1408,9 +1454,9 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), /* Uarts on omap4 and later */ SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x50411e03, 0xffff00ff, - SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47422e03, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), /* Quirks that need to be set based on the module address */ SYSC_QUIRK("mcpdm", 0x40132000, 0, 0x10, -ENODEV, 0x50000800, 0xffffffff, @@ -1459,6 +1505,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), SYSC_QUIRK("tptc", 0, 0, -ENODEV, -ENODEV, 0x40007c00, 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), + SYSC_QUIRK("sata", 0, 0xfc, 0x1100, -ENODEV, 0x5e412000, 0xffffffff, + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, 0x14, 0x50700100, 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, -ENODEV, 0x50700101, 0xffffffff, @@ -1466,7 +1514,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("usb_otg_hs", 0, 0x400, 0x404, 0x408, 0x00000050, 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), SYSC_QUIRK("usb_otg_hs", 0, 0, 0x10, -ENODEV, 0x4ea2080d, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY | + SYSC_QUIRK_REINIT_ON_RESUME), SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0, SYSC_MODULE_QUIRK_WDT), /* PRUSS on am3, am4 and am5 */ @@ -1524,7 +1573,6 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("prcm", 0, 0, -ENODEV, -ENODEV, 0x40000400, 0xffffffff, 0), SYSC_QUIRK("rfbi", 0x4832a800, 0, 0x10, 0x14, 0x00000010, 0xffffffff, 0), SYSC_QUIRK("rfbi", 0x58002000, 0, 0x10, 0x14, 0x00000010, 0xffffffff, 0), - SYSC_QUIRK("sata", 0, 0xfc, 0x1100, -ENODEV, 0x5e412000, 0xffffffff, 0), SYSC_QUIRK("scm", 0, 0, 0x10, -ENODEV, 0x40000900, 0xffffffff, 0), SYSC_QUIRK("scm", 0, 0, -ENODEV, -ENODEV, 0x4e8b0100, 0xffffffff, 0), SYSC_QUIRK("scm", 0, 0, -ENODEV, -ENODEV, 0x4f000100, 0xffffffff, 0), diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index a5c5f70acfc9..e65e0a43be64 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -19,16 +19,6 @@ config ACPI_CPPC_CPUFREQ If in doubt, say N. -config ACPI_CPPC_CPUFREQ_FIE - bool "Frequency Invariance support for CPPC cpufreq driver" - depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY - default y - help - This extends frequency invariance support in the CPPC cpufreq driver, - by using CPPC delivered and reference performance counters. - - If in doubt, say N. - config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM tristate "Allwinner nvmem based SUN50I CPUFreq driver" depends on ARCH_SUNXI diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 3848b4c222e1..2f769b1630c5 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -10,18 +10,14 @@ #define pr_fmt(fmt) "CPPC Cpufreq:" fmt -#include <linux/arch_topology.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/dmi.h> -#include <linux/irq_work.h> -#include <linux/kthread.h> #include <linux/time.h> #include <linux/vmalloc.h> -#include <uapi/linux/sched/types.h> #include <asm/unaligned.h> @@ -61,204 +57,6 @@ static struct cppc_workaround_oem_info wa_info[] = { } }; -#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE - -/* Frequency invariance support */ -struct cppc_freq_invariance { - int cpu; - struct irq_work irq_work; - struct kthread_work work; - struct cppc_perf_fb_ctrs prev_perf_fb_ctrs; - struct cppc_cpudata *cpu_data; -}; - -static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv); -static struct kthread_worker *kworker_fie; -static bool fie_disabled; - -static struct cpufreq_driver cppc_cpufreq_driver; -static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu); -static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data, - struct cppc_perf_fb_ctrs fb_ctrs_t0, - struct cppc_perf_fb_ctrs fb_ctrs_t1); - -/** - * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance - * @work: The work item. - * - * The CPPC driver register itself with the topology core to provide its own - * implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which - * gets called by the scheduler on every tick. - * - * Note that the arch specific counters have higher priority than CPPC counters, - * if available, though the CPPC driver doesn't need to have any special - * handling for that. - * - * On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we - * reach here from hard-irq context), which then schedules a normal work item - * and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable - * based on the counter updates since the last tick. - */ -static void cppc_scale_freq_workfn(struct kthread_work *work) -{ - struct cppc_freq_invariance *cppc_fi; - struct cppc_perf_fb_ctrs fb_ctrs = {0}; - struct cppc_cpudata *cpu_data; - unsigned long local_freq_scale; - u64 perf; - - cppc_fi = container_of(work, struct cppc_freq_invariance, work); - cpu_data = cppc_fi->cpu_data; - - if (cppc_get_perf_ctrs(cppc_fi->cpu, &fb_ctrs)) { - pr_warn("%s: failed to read perf counters\n", __func__); - return; - } - - cppc_fi->prev_perf_fb_ctrs = fb_ctrs; - perf = cppc_perf_from_fbctrs(cpu_data, cppc_fi->prev_perf_fb_ctrs, - fb_ctrs); - - perf <<= SCHED_CAPACITY_SHIFT; - local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf); - if (WARN_ON(local_freq_scale > 1024)) - local_freq_scale = 1024; - - per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale; -} - -static void cppc_irq_work(struct irq_work *irq_work) -{ - struct cppc_freq_invariance *cppc_fi; - - cppc_fi = container_of(irq_work, struct cppc_freq_invariance, irq_work); - kthread_queue_work(kworker_fie, &cppc_fi->work); -} - -static void cppc_scale_freq_tick(void) -{ - struct cppc_freq_invariance *cppc_fi = &per_cpu(cppc_freq_inv, smp_processor_id()); - - /* - * cppc_get_perf_ctrs() can potentially sleep, call that from the right - * context. - */ - irq_work_queue(&cppc_fi->irq_work); -} - -static struct scale_freq_data cppc_sftd = { - .source = SCALE_FREQ_SOURCE_CPPC, - .set_freq_scale = cppc_scale_freq_tick, -}; - -static void cppc_freq_invariance_policy_init(struct cpufreq_policy *policy, - struct cppc_cpudata *cpu_data) -{ - struct cppc_perf_fb_ctrs fb_ctrs = {0}; - struct cppc_freq_invariance *cppc_fi; - int i, ret; - - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) - return; - - if (fie_disabled) - return; - - for_each_cpu(i, policy->cpus) { - cppc_fi = &per_cpu(cppc_freq_inv, i); - cppc_fi->cpu = i; - cppc_fi->cpu_data = cpu_data; - kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn); - init_irq_work(&cppc_fi->irq_work, cppc_irq_work); - - ret = cppc_get_perf_ctrs(i, &fb_ctrs); - if (ret) { - pr_warn("%s: failed to read perf counters: %d\n", - __func__, ret); - fie_disabled = true; - } else { - cppc_fi->prev_perf_fb_ctrs = fb_ctrs; - } - } -} - -static void __init cppc_freq_invariance_init(void) -{ - struct sched_attr attr = { - .size = sizeof(struct sched_attr), - .sched_policy = SCHED_DEADLINE, - .sched_nice = 0, - .sched_priority = 0, - /* - * Fake (unused) bandwidth; workaround to "fix" - * priority inheritance. - */ - .sched_runtime = 1000000, - .sched_deadline = 10000000, - .sched_period = 10000000, - }; - int ret; - - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) - return; - - if (fie_disabled) - return; - - kworker_fie = kthread_create_worker(0, "cppc_fie"); - if (IS_ERR(kworker_fie)) - return; - - ret = sched_setattr_nocheck(kworker_fie->task, &attr); - if (ret) { - pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__, - ret); - kthread_destroy_worker(kworker_fie); - return; - } - - /* Register for freq-invariance */ - topology_set_scale_freq_source(&cppc_sftd, cpu_present_mask); -} - -static void cppc_freq_invariance_exit(void) -{ - struct cppc_freq_invariance *cppc_fi; - int i; - - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) - return; - - if (fie_disabled) - return; - - topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, cpu_present_mask); - - for_each_possible_cpu(i) { - cppc_fi = &per_cpu(cppc_freq_inv, i); - irq_work_sync(&cppc_fi->irq_work); - } - - kthread_destroy_worker(kworker_fie); - kworker_fie = NULL; -} - -#else -static inline void -cppc_freq_invariance_policy_init(struct cpufreq_policy *policy, - struct cppc_cpudata *cpu_data) -{ -} - -static inline void cppc_freq_invariance_init(void) -{ -} - -static inline void cppc_freq_invariance_exit(void) -{ -} -#endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */ - /* Callback function used to retrieve the max frequency from DMI */ static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private) { @@ -547,12 +345,9 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) cpu_data->perf_ctrls.desired_perf = caps->highest_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); - if (ret) { + if (ret) pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n", caps->highest_perf, cpu, ret); - } else { - cppc_freq_invariance_policy_init(policy, cpu_data); - } return ret; } @@ -565,12 +360,12 @@ static inline u64 get_delta(u64 t1, u64 t0) return (u32)t1 - (u32)t0; } -static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data, - struct cppc_perf_fb_ctrs fb_ctrs_t0, - struct cppc_perf_fb_ctrs fb_ctrs_t1) +static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data, + struct cppc_perf_fb_ctrs fb_ctrs_t0, + struct cppc_perf_fb_ctrs fb_ctrs_t1) { u64 delta_reference, delta_delivered; - u64 reference_perf; + u64 reference_perf, delivered_perf; reference_perf = fb_ctrs_t0.reference_perf; @@ -579,21 +374,12 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data, delta_delivered = get_delta(fb_ctrs_t1.delivered, fb_ctrs_t0.delivered); - /* Check to avoid divide-by zero and invalid delivered_perf */ - if (!delta_reference || !delta_delivered) - return cpu_data->perf_ctrls.desired_perf; - - return (reference_perf * delta_delivered) / delta_reference; -} - -static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data, - struct cppc_perf_fb_ctrs fb_ctrs_t0, - struct cppc_perf_fb_ctrs fb_ctrs_t1) -{ - u64 delivered_perf; - - delivered_perf = cppc_perf_from_fbctrs(cpu_data, fb_ctrs_t0, - fb_ctrs_t1); + /* Check to avoid divide-by zero */ + if (delta_reference || delta_delivered) + delivered_perf = (reference_perf * delta_delivered) / + delta_reference; + else + delivered_perf = cpu_data->perf_ctrls.desired_perf; return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf); } @@ -718,8 +504,6 @@ static void cppc_check_hisi_workaround(void) static int __init cppc_cpufreq_init(void) { - int ret; - if ((acpi_disabled) || !acpi_cpc_valid()) return -ENODEV; @@ -727,11 +511,7 @@ static int __init cppc_cpufreq_init(void) cppc_check_hisi_workaround(); - ret = cpufreq_register_driver(&cppc_cpufreq_driver); - if (!ret) - cppc_freq_invariance_init(); - - return ret; + return cpufreq_register_driver(&cppc_cpufreq_driver); } static inline void free_cpu_data(void) @@ -748,7 +528,6 @@ static inline void free_cpu_data(void) static void __exit cppc_cpufreq_exit(void) { - cppc_freq_invariance_exit(); cpufreq_unregister_driver(&cppc_cpufreq_driver); free_cpu_data(); diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 6ab9d9a488a6..39b5b46e880f 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -59,6 +59,7 @@ config DMA_OF #devices config ALTERA_MSGDMA tristate "Altera / Intel mSGDMA Engine" + depends on HAS_IOMEM select DMA_ENGINE help Enable support for Altera / Intel mSGDMA controller. @@ -701,6 +702,7 @@ config XILINX_ZYNQMP_DMA config XILINX_ZYNQMP_DPDMA tristate "Xilinx DPDMA Engine" + depends on HAS_IOMEM && OF select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c index 4ec909e0b810..4ae057922ef1 100644 --- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c +++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c @@ -332,6 +332,7 @@ static int __cold dpaa2_qdma_setup(struct fsl_mc_device *ls_dev) } if (priv->dpdmai_attr.version.major > DPDMAI_VER_MAJOR) { + err = -EINVAL; dev_err(dev, "DPDMAI major version mismatch\n" "Found %u.%u, supported version is %u.%u\n", priv->dpdmai_attr.version.major, @@ -341,6 +342,7 @@ static int __cold dpaa2_qdma_setup(struct fsl_mc_device *ls_dev) } if (priv->dpdmai_attr.version.minor > DPDMAI_VER_MINOR) { + err = -EINVAL; dev_err(dev, "DPDMAI minor version mismatch\n" "Found %u.%u, supported version is %u.%u\n", priv->dpdmai_attr.version.major, @@ -475,6 +477,7 @@ static int __cold dpaa2_qdma_dpio_setup(struct dpaa2_qdma_priv *priv) ppriv->store = dpaa2_io_store_create(DPAA2_QDMA_STORE_SIZE, dev); if (!ppriv->store) { + err = -ENOMEM; dev_err(dev, "dpaa2_io_store_create() failed\n"); goto err_store; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 302cba5ff779..d4419bf1fede 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -110,6 +110,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) pasid = iommu_sva_get_pasid(sva); if (pasid == IOMMU_PASID_INVALID) { iommu_sva_unbind_device(sva); + rc = -EINVAL; goto failed; } diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 2a926bef87f2..442d55c11a5f 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -168,6 +168,32 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) return rc; } +static void idxd_cleanup_interrupts(struct idxd_device *idxd) +{ + struct pci_dev *pdev = idxd->pdev; + struct idxd_irq_entry *irq_entry; + int i, msixcnt; + + msixcnt = pci_msix_vec_count(pdev); + if (msixcnt <= 0) + return; + + irq_entry = &idxd->irq_entries[0]; + free_irq(irq_entry->vector, irq_entry); + + for (i = 1; i < msixcnt; i++) { + + irq_entry = &idxd->irq_entries[i]; + if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)) + idxd_device_release_int_handle(idxd, idxd->int_handles[i], + IDXD_IRQ_MSIX); + free_irq(irq_entry->vector, irq_entry); + } + + idxd_mask_error_interrupts(idxd); + pci_free_irq_vectors(pdev); +} + static int idxd_setup_wqs(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; @@ -242,6 +268,7 @@ static int idxd_setup_engines(struct idxd_device *idxd) engine->idxd = idxd; device_initialize(&engine->conf_dev); engine->conf_dev.parent = &idxd->conf_dev; + engine->conf_dev.bus = &dsa_bus_type; engine->conf_dev.type = &idxd_engine_device_type; rc = dev_set_name(&engine->conf_dev, "engine%d.%d", idxd->id, engine->id); if (rc < 0) { @@ -303,6 +330,19 @@ static int idxd_setup_groups(struct idxd_device *idxd) return rc; } +static void idxd_cleanup_internals(struct idxd_device *idxd) +{ + int i; + + for (i = 0; i < idxd->max_groups; i++) + put_device(&idxd->groups[i]->conf_dev); + for (i = 0; i < idxd->max_engines; i++) + put_device(&idxd->engines[i]->conf_dev); + for (i = 0; i < idxd->max_wqs; i++) + put_device(&idxd->wqs[i]->conf_dev); + destroy_workqueue(idxd->wq); +} + static int idxd_setup_internals(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; @@ -531,12 +571,12 @@ static int idxd_probe(struct idxd_device *idxd) dev_dbg(dev, "Loading RO device config\n"); rc = idxd_device_load_config(idxd); if (rc < 0) - goto err; + goto err_config; } rc = idxd_setup_interrupts(idxd); if (rc) - goto err; + goto err_config; dev_dbg(dev, "IDXD interrupt setup complete.\n"); @@ -549,6 +589,8 @@ static int idxd_probe(struct idxd_device *idxd) dev_dbg(dev, "IDXD device %d probed successfully\n", idxd->id); return 0; + err_config: + idxd_cleanup_internals(idxd); err: if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); @@ -556,6 +598,18 @@ static int idxd_probe(struct idxd_device *idxd) return rc; } +static void idxd_cleanup(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + + perfmon_pmu_remove(idxd); + idxd_cleanup_interrupts(idxd); + idxd_cleanup_internals(idxd); + if (device_pasid_enabled(idxd)) + idxd_disable_system_pasid(idxd); + iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA); +} + static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; @@ -608,7 +662,7 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) rc = idxd_register_devices(idxd); if (rc) { dev_err(dev, "IDXD sysfs setup failed\n"); - goto err; + goto err_dev_register; } idxd->state = IDXD_DEV_CONF_READY; @@ -618,6 +672,8 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; + err_dev_register: + idxd_cleanup(idxd); err: pci_iounmap(pdev, idxd->reg_base); err_iomap: @@ -745,12 +801,12 @@ static int __init idxd_init_module(void) * If the CPU does not support MOVDIR64B or ENQCMDS, there's no point in * enumerating the device. We can not utilize it. */ - if (!boot_cpu_has(X86_FEATURE_MOVDIR64B)) { + if (!cpu_feature_enabled(X86_FEATURE_MOVDIR64B)) { pr_warn("idxd driver failed to load without MOVDIR64B.\n"); return -ENODEV; } - if (!boot_cpu_has(X86_FEATURE_ENQCMD)) + if (!cpu_feature_enabled(X86_FEATURE_ENQCMD)) pr_warn("Platform does not have ENQCMD(S) support.\n"); else support_enqcmd = true; @@ -787,6 +843,7 @@ module_init(idxd_init_module); static void __exit idxd_exit_module(void) { + idxd_unregister_driver(); pci_unregister_driver(&idxd_pci_driver); idxd_cdev_remove(); idxd_unregister_bus_type(); diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c index 0d5c42f7bfa4..97d9a6f04f2a 100644 --- a/drivers/dma/ipu/ipu_irq.c +++ b/drivers/dma/ipu/ipu_irq.c @@ -230,7 +230,7 @@ out: } /** - * ipu_irq_map() - map an IPU interrupt source to an IRQ number + * ipu_irq_unmap() - unmap an IPU interrupt source * @source: interrupt source bit position (see ipu_irq_map()) * @return: 0 or negative error code */ diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index 27c07350971d..375e7e647df6 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -131,10 +131,7 @@ static unsigned int mtk_uart_apdma_read(struct mtk_chan *c, unsigned int reg) static void mtk_uart_apdma_desc_free(struct virt_dma_desc *vd) { - struct dma_chan *chan = vd->tx.chan; - struct mtk_chan *c = to_mtk_uart_apdma_chan(chan); - - kfree(c->desc); + kfree(container_of(vd, struct mtk_uart_apdma_desc, vd)); } static void mtk_uart_apdma_start_tx(struct mtk_chan *c) @@ -207,14 +204,9 @@ static void mtk_uart_apdma_start_rx(struct mtk_chan *c) static void mtk_uart_apdma_tx_handler(struct mtk_chan *c) { - struct mtk_uart_apdma_desc *d = c->desc; - mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B); mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B); mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B); - - list_del(&d->vd.node); - vchan_cookie_complete(&d->vd); } static void mtk_uart_apdma_rx_handler(struct mtk_chan *c) @@ -245,9 +237,17 @@ static void mtk_uart_apdma_rx_handler(struct mtk_chan *c) c->rx_status = d->avail_len - cnt; mtk_uart_apdma_write(c, VFF_RPT, wg); +} - list_del(&d->vd.node); - vchan_cookie_complete(&d->vd); +static void mtk_uart_apdma_chan_complete_handler(struct mtk_chan *c) +{ + struct mtk_uart_apdma_desc *d = c->desc; + + if (d) { + list_del(&d->vd.node); + vchan_cookie_complete(&d->vd); + c->desc = NULL; + } } static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) @@ -261,6 +261,7 @@ static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) mtk_uart_apdma_rx_handler(c); else if (c->dir == DMA_MEM_TO_DEV) mtk_uart_apdma_tx_handler(c); + mtk_uart_apdma_chan_complete_handler(c); spin_unlock_irqrestore(&c->vc.lock, flags); return IRQ_HANDLED; @@ -348,7 +349,7 @@ static struct dma_async_tx_descriptor *mtk_uart_apdma_prep_slave_sg return NULL; /* Now allocate and setup the descriptor */ - d = kzalloc(sizeof(*d), GFP_ATOMIC); + d = kzalloc(sizeof(*d), GFP_NOWAIT); if (!d) return NULL; @@ -366,7 +367,7 @@ static void mtk_uart_apdma_issue_pending(struct dma_chan *chan) unsigned long flags; spin_lock_irqsave(&c->vc.lock, flags); - if (vchan_issue_pending(&c->vc)) { + if (vchan_issue_pending(&c->vc) && !c->desc) { vd = vchan_next_desc(&c->vc); c->desc = to_mtk_uart_apdma_desc(&vd->tx); diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index fd8d2bc3be9f..110de8a60058 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2694,13 +2694,15 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( for (i = 0; i < len / period_len; i++) { desc = pl330_get_desc(pch); if (!desc) { + unsigned long iflags; + dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n", __func__, __LINE__); if (!first) return NULL; - spin_lock_irqsave(&pl330->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, iflags); while (!list_empty(&first->node)) { desc = list_entry(first->node.next, @@ -2710,7 +2712,7 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( list_move_tail(&first->node, &pl330->desc_pool); - spin_unlock_irqrestore(&pl330->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, iflags); return NULL; } diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig index 365f94eb3b08..3f926a653bd8 100644 --- a/drivers/dma/qcom/Kconfig +++ b/drivers/dma/qcom/Kconfig @@ -33,6 +33,7 @@ config QCOM_GPI_DMA config QCOM_HIDMA_MGMT tristate "Qualcomm Technologies HIDMA Management support" + depends on HAS_IOMEM select DMA_ENGINE help Enable support for the Qualcomm Technologies HIDMA Management. diff --git a/drivers/dma/sf-pdma/Kconfig b/drivers/dma/sf-pdma/Kconfig index f8ffa02e279f..ba46a0a15a93 100644 --- a/drivers/dma/sf-pdma/Kconfig +++ b/drivers/dma/sf-pdma/Kconfig @@ -1,5 +1,6 @@ config SF_PDMA tristate "Sifive PDMA controller driver" + depends on HAS_IOMEM select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index d530c1bf11d9..6885b3dcd7a9 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1913,7 +1913,7 @@ static int rcar_dmac_probe(struct platform_device *pdev) /* Enable runtime PM and initialize the device. */ pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret); return ret; diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 265d7c07b348..e1827393143f 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -3675,6 +3675,9 @@ static int __init d40_probe(struct platform_device *pdev) kfree(base->lcla_pool.base_unaligned); + if (base->lcpa_base) + iounmap(base->lcpa_base); + if (base->phy_lcpa) release_mem_region(base->phy_lcpa, base->lcpa_size); diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 36ba8b43e78d..18cbd1e43c2e 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1452,7 +1452,7 @@ static int stm32_mdma_alloc_chan_resources(struct dma_chan *c) return -ENOMEM; } - ret = pm_runtime_get_sync(dmadev->ddev.dev); + ret = pm_runtime_resume_and_get(dmadev->ddev.dev); if (ret < 0) return ret; @@ -1718,7 +1718,7 @@ static int stm32_mdma_pm_suspend(struct device *dev) u32 ccr, id; int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index 70b29bd079c9..6c709803203a 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -113,6 +113,7 @@ #define XILINX_DPDMA_CH_VDO 0x020 #define XILINX_DPDMA_CH_PYLD_SZ 0x024 #define XILINX_DPDMA_CH_DESC_ID 0x028 +#define XILINX_DPDMA_CH_DESC_ID_MASK GENMASK(15, 0) /* DPDMA descriptor fields */ #define XILINX_DPDMA_DESC_CONTROL_PREEMBLE 0xa5 @@ -866,7 +867,8 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan) * will be used, but it should be enough. */ list_for_each_entry(sw_desc, &desc->descriptors, node) - sw_desc->hw.desc_id = desc->vdesc.tx.cookie; + sw_desc->hw.desc_id = desc->vdesc.tx.cookie + & XILINX_DPDMA_CH_DESC_ID_MASK; sw_desc = list_first_entry(&desc->descriptors, struct xilinx_dpdma_sw_desc, node); @@ -1086,7 +1088,8 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) if (!chan->running || !pending) goto out; - desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID); + desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID) + & XILINX_DPDMA_CH_DESC_ID_MASK; /* If the retrigger raced with vsync, retry at the next frame. */ sw_desc = list_first_entry(&pending->descriptors, @@ -1459,7 +1462,7 @@ static void xilinx_dpdma_enable_irq(struct xilinx_dpdma_device *xdev) */ static void xilinx_dpdma_disable_irq(struct xilinx_dpdma_device *xdev) { - dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ERR_ALL); + dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ALL); dpdma_write(xdev->reg, XILINX_DPDMA_EIDS, XILINX_DPDMA_EINTR_ALL); } @@ -1596,6 +1599,26 @@ static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec, return dma_get_slave_channel(&xdev->chan[chan_id]->vchan.chan); } +static void dpdma_hw_init(struct xilinx_dpdma_device *xdev) +{ + unsigned int i; + void __iomem *reg; + + /* Disable all interrupts */ + xilinx_dpdma_disable_irq(xdev); + + /* Stop all channels */ + for (i = 0; i < ARRAY_SIZE(xdev->chan); i++) { + reg = xdev->reg + XILINX_DPDMA_CH_BASE + + XILINX_DPDMA_CH_OFFSET * i; + dpdma_clr(reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_ENABLE); + } + + /* Clear the interrupt status registers */ + dpdma_write(xdev->reg, XILINX_DPDMA_ISR, XILINX_DPDMA_INTR_ALL); + dpdma_write(xdev->reg, XILINX_DPDMA_EISR, XILINX_DPDMA_EINTR_ALL); +} + static int xilinx_dpdma_probe(struct platform_device *pdev) { struct xilinx_dpdma_device *xdev; @@ -1622,6 +1645,8 @@ static int xilinx_dpdma_probe(struct platform_device *pdev) if (IS_ERR(xdev->reg)) return PTR_ERR(xdev->reg); + dpdma_hw_init(xdev); + xdev->irq = platform_get_irq(pdev, 0); if (xdev->irq < 0) { dev_err(xdev->dev, "failed to get platform irq\n"); diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index d8419565b92c..5fecf5aa6e85 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -468,7 +468,7 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan) struct zynqmp_dma_desc_sw *desc; int i, ret; - ret = pm_runtime_get_sync(chan->dev); + ret = pm_runtime_resume_and_get(chan->dev); if (ret < 0) return ret; diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index e15d484b6a5a..ea7ca74fc173 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -276,8 +276,7 @@ static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) if (!msg || !(mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE)) return 0; - n = 0; - len = CPER_REC_LEN - 1; + len = CPER_REC_LEN; dmi_memdev_name(mem->mem_dev_handle, &bank, &device); if (bank && device) n = snprintf(msg, len, "DIMM location: %s %s ", bank, device); @@ -286,7 +285,6 @@ static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) "DIMM location: not present. DMI handle: 0x%.4x ", mem->mem_dev_handle); - msg[n] = '\0'; return n; } diff --git a/drivers/firmware/efi/fdtparams.c b/drivers/firmware/efi/fdtparams.c index bb042ab7c2be..e901f8564ca0 100644 --- a/drivers/firmware/efi/fdtparams.c +++ b/drivers/firmware/efi/fdtparams.c @@ -98,6 +98,9 @@ u64 __init efi_get_fdt_params(struct efi_memory_map_data *mm) BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(name)); BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(dt_params[0].params)); + if (!fdt) + return 0; + for (i = 0; i < ARRAY_SIZE(dt_params); i++) { node = fdt_path_offset(fdt, dt_params[i].path); if (node < 0) diff --git a/drivers/firmware/efi/libstub/file.c b/drivers/firmware/efi/libstub/file.c index 4e81c6077188..dd95f330fe6e 100644 --- a/drivers/firmware/efi/libstub/file.c +++ b/drivers/firmware/efi/libstub/file.c @@ -103,7 +103,7 @@ static int find_file_option(const efi_char16_t *cmdline, int cmdline_len, return 0; /* Skip any leading slashes */ - while (cmdline[i] == L'/' || cmdline[i] == L'\\') + while (i < cmdline_len && (cmdline[i] == L'/' || cmdline[i] == L'\\')) i++; while (--result_len > 0 && i < cmdline_len) { diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 5737cb0fcd44..0a9aba5f9cef 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -67,11 +67,6 @@ static bool entry_is_valid(const efi_memory_desc_t *in, efi_memory_desc_t *out) return false; } - if (!(in->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP))) { - pr_warn("Entry attributes invalid: RO and XP bits both cleared\n"); - return false; - } - if (PAGE_SIZE > EFI_PAGE_SIZE && (!PAGE_ALIGNED(in->phys_addr) || !PAGE_ALIGNED(in->num_pages << EFI_PAGE_SHIFT))) { diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c index 1cbce5990855..97e6caedf1f3 100644 --- a/drivers/gpio/gpio-wcd934x.c +++ b/drivers/gpio/gpio-wcd934x.c @@ -7,7 +7,7 @@ #include <linux/slab.h> #include <linux/of_device.h> -#define WCD_PIN_MASK(p) BIT(p - 1) +#define WCD_PIN_MASK(p) BIT(p) #define WCD_REG_DIR_CTL_OFFSET 0x42 #define WCD_REG_VAL_CTL_OFFSET 0x43 #define WCD934X_NPINS 5 diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index f00e5abdbbf4..b59b26a71ad5 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -315,9 +315,10 @@ int drm_master_open(struct drm_file *file_priv) void drm_master_release(struct drm_file *file_priv) { struct drm_device *dev = file_priv->minor->dev; - struct drm_master *master = file_priv->master; + struct drm_master *master; mutex_lock(&dev->master_mutex); + master = file_priv->master; if (file_priv->magic) idr_remove(&file_priv->master->magic_map, file_priv->magic); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 53d314103a37..98ae00661656 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -117,17 +117,18 @@ int drm_getunique(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_unique *u = data; - struct drm_master *master = file_priv->master; + struct drm_master *master; - mutex_lock(&master->dev->master_mutex); + mutex_lock(&dev->master_mutex); + master = file_priv->master; if (u->unique_len >= master->unique_len) { if (copy_to_user(u->unique, master->unique, master->unique_len)) { - mutex_unlock(&master->dev->master_mutex); + mutex_unlock(&dev->master_mutex); return -EFAULT; } } u->unique_len = master->unique_len; - mutex_unlock(&master->dev->master_mutex); + mutex_unlock(&dev->master_mutex); return 0; } diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c index 5aade1d13961..34a00d7e9c38 100644 --- a/drivers/gpu/drm/mcde/mcde_dsi.c +++ b/drivers/gpu/drm/mcde/mcde_dsi.c @@ -577,7 +577,7 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d, * porches and sync. */ /* (ps/s) / (pixels/s) = ps/pixels */ - pclk = DIV_ROUND_UP_ULL(1000000000000, mode->clock); + pclk = DIV_ROUND_UP_ULL(1000000000000, (mode->clock * 1000)); dev_dbg(d->dev, "picoseconds between two pixels: %llu\n", pclk); diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 66de3f4f7222..a7388bf7c838 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -474,11 +474,12 @@ static int meson_probe_remote(struct platform_device *pdev, static void meson_drv_shutdown(struct platform_device *pdev) { struct meson_drm *priv = dev_get_drvdata(&pdev->dev); - struct drm_device *drm = priv->drm; - DRM_DEBUG_DRIVER("\n"); - drm_kms_helper_poll_fini(drm); - drm_atomic_helper_shutdown(drm); + if (!priv) + return; + + drm_kms_helper_poll_fini(priv->drm); + drm_atomic_helper_shutdown(priv->drm); } static int meson_drv_probe(struct platform_device *pdev) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index b4d8e1b01ee4..f6c1b62b901e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -157,7 +157,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) * GPU registers so we need to add 0x1a800 to the register value on A630 * to get the right value from PM4. */ - get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800, + get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, rbmemptr_stats(ring, index, alwayson_start)); /* Invalidate CCU depth and color */ @@ -187,7 +187,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO, rbmemptr_stats(ring, index, cpcycles_end)); - get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800, + get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, rbmemptr_stats(ring, index, alwayson_end)); /* Write the fence to the scratch register */ @@ -206,8 +206,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, submit->seqno); trace_msm_gpu_submit_flush(submit, - gmu_read64(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L, - REG_A6XX_GMU_ALWAYS_ON_COUNTER_H)); + gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, + REG_A6XX_CP_ALWAYS_ON_COUNTER_HI)); a6xx_flush(gpu, ring); } @@ -462,6 +462,113 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state) gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0); } +/* For a615, a616, a618, A619, a630, a640 and a680 */ +static const u32 a6xx_protect[] = { + A6XX_PROTECT_RDONLY(0x00000, 0x04ff), + A6XX_PROTECT_RDONLY(0x00501, 0x0005), + A6XX_PROTECT_RDONLY(0x0050b, 0x02f4), + A6XX_PROTECT_NORDWR(0x0050e, 0x0000), + A6XX_PROTECT_NORDWR(0x00510, 0x0000), + A6XX_PROTECT_NORDWR(0x00534, 0x0000), + A6XX_PROTECT_NORDWR(0x00800, 0x0082), + A6XX_PROTECT_NORDWR(0x008a0, 0x0008), + A6XX_PROTECT_NORDWR(0x008ab, 0x0024), + A6XX_PROTECT_RDONLY(0x008de, 0x00ae), + A6XX_PROTECT_NORDWR(0x00900, 0x004d), + A6XX_PROTECT_NORDWR(0x0098d, 0x0272), + A6XX_PROTECT_NORDWR(0x00e00, 0x0001), + A6XX_PROTECT_NORDWR(0x00e03, 0x000c), + A6XX_PROTECT_NORDWR(0x03c00, 0x00c3), + A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff), + A6XX_PROTECT_NORDWR(0x08630, 0x01cf), + A6XX_PROTECT_NORDWR(0x08e00, 0x0000), + A6XX_PROTECT_NORDWR(0x08e08, 0x0000), + A6XX_PROTECT_NORDWR(0x08e50, 0x001f), + A6XX_PROTECT_NORDWR(0x09624, 0x01db), + A6XX_PROTECT_NORDWR(0x09e70, 0x0001), + A6XX_PROTECT_NORDWR(0x09e78, 0x0187), + A6XX_PROTECT_NORDWR(0x0a630, 0x01cf), + A6XX_PROTECT_NORDWR(0x0ae02, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae50, 0x032f), + A6XX_PROTECT_NORDWR(0x0b604, 0x0000), + A6XX_PROTECT_NORDWR(0x0be02, 0x0001), + A6XX_PROTECT_NORDWR(0x0be20, 0x17df), + A6XX_PROTECT_NORDWR(0x0f000, 0x0bff), + A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff), + A6XX_PROTECT_NORDWR(0x11c00, 0x0000), /* note: infinite range */ +}; + +/* These are for a620 and a650 */ +static const u32 a650_protect[] = { + A6XX_PROTECT_RDONLY(0x00000, 0x04ff), + A6XX_PROTECT_RDONLY(0x00501, 0x0005), + A6XX_PROTECT_RDONLY(0x0050b, 0x02f4), + A6XX_PROTECT_NORDWR(0x0050e, 0x0000), + A6XX_PROTECT_NORDWR(0x00510, 0x0000), + A6XX_PROTECT_NORDWR(0x00534, 0x0000), + A6XX_PROTECT_NORDWR(0x00800, 0x0082), + A6XX_PROTECT_NORDWR(0x008a0, 0x0008), + A6XX_PROTECT_NORDWR(0x008ab, 0x0024), + A6XX_PROTECT_RDONLY(0x008de, 0x00ae), + A6XX_PROTECT_NORDWR(0x00900, 0x004d), + A6XX_PROTECT_NORDWR(0x0098d, 0x0272), + A6XX_PROTECT_NORDWR(0x00e00, 0x0001), + A6XX_PROTECT_NORDWR(0x00e03, 0x000c), + A6XX_PROTECT_NORDWR(0x03c00, 0x00c3), + A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff), + A6XX_PROTECT_NORDWR(0x08630, 0x01cf), + A6XX_PROTECT_NORDWR(0x08e00, 0x0000), + A6XX_PROTECT_NORDWR(0x08e08, 0x0000), + A6XX_PROTECT_NORDWR(0x08e50, 0x001f), + A6XX_PROTECT_NORDWR(0x08e80, 0x027f), + A6XX_PROTECT_NORDWR(0x09624, 0x01db), + A6XX_PROTECT_NORDWR(0x09e60, 0x0011), + A6XX_PROTECT_NORDWR(0x09e78, 0x0187), + A6XX_PROTECT_NORDWR(0x0a630, 0x01cf), + A6XX_PROTECT_NORDWR(0x0ae02, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae50, 0x032f), + A6XX_PROTECT_NORDWR(0x0b604, 0x0000), + A6XX_PROTECT_NORDWR(0x0b608, 0x0007), + A6XX_PROTECT_NORDWR(0x0be02, 0x0001), + A6XX_PROTECT_NORDWR(0x0be20, 0x17df), + A6XX_PROTECT_NORDWR(0x0f000, 0x0bff), + A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff), + A6XX_PROTECT_NORDWR(0x18400, 0x1fff), + A6XX_PROTECT_NORDWR(0x1a800, 0x1fff), + A6XX_PROTECT_NORDWR(0x1f400, 0x0443), + A6XX_PROTECT_RDONLY(0x1f844, 0x007b), + A6XX_PROTECT_NORDWR(0x1f887, 0x001b), + A6XX_PROTECT_NORDWR(0x1f8c0, 0x0000), /* note: infinite range */ +}; + +static void a6xx_set_cp_protect(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const u32 *regs = a6xx_protect; + unsigned i, count = ARRAY_SIZE(a6xx_protect), count_max = 32; + + BUILD_BUG_ON(ARRAY_SIZE(a6xx_protect) > 32); + BUILD_BUG_ON(ARRAY_SIZE(a650_protect) > 48); + + if (adreno_is_a650(adreno_gpu)) { + regs = a650_protect; + count = ARRAY_SIZE(a650_protect); + count_max = 48; + } + + /* + * Enable access protection to privileged registers, fault on an access + * protect violation and select the last span to protect from the start + * address all the way to the end of the register address space + */ + gpu_write(gpu, REG_A6XX_CP_PROTECT_CNTL, BIT(0) | BIT(1) | BIT(3)); + + for (i = 0; i < count - 1; i++) + gpu_write(gpu, REG_A6XX_CP_PROTECT(i), regs[i]); + /* last CP_PROTECT to have "infinite" length on the last entry */ + gpu_write(gpu, REG_A6XX_CP_PROTECT(count_max - 1), regs[i]); +} + static void a6xx_set_ubwc_config(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -489,7 +596,7 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu) rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1); gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1); gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, - uavflagprd_inv >> 4 | lower_bit << 1); + uavflagprd_inv << 4 | lower_bit << 1); gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, lower_bit << 21); } @@ -776,41 +883,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu) } /* Protect registers from the CP */ - gpu_write(gpu, REG_A6XX_CP_PROTECT_CNTL, 0x00000003); - - gpu_write(gpu, REG_A6XX_CP_PROTECT(0), - A6XX_PROTECT_RDONLY(0x600, 0x51)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(1), A6XX_PROTECT_RW(0xae50, 0x2)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(2), A6XX_PROTECT_RW(0x9624, 0x13)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(3), A6XX_PROTECT_RW(0x8630, 0x8)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(4), A6XX_PROTECT_RW(0x9e70, 0x1)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(5), A6XX_PROTECT_RW(0x9e78, 0x187)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(6), A6XX_PROTECT_RW(0xf000, 0x810)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(7), - A6XX_PROTECT_RDONLY(0xfc00, 0x3)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(8), A6XX_PROTECT_RW(0x50e, 0x0)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(9), A6XX_PROTECT_RDONLY(0x50f, 0x0)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(10), A6XX_PROTECT_RW(0x510, 0x0)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(11), - A6XX_PROTECT_RDONLY(0x0, 0x4f9)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(12), - A6XX_PROTECT_RDONLY(0x501, 0xa)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(13), - A6XX_PROTECT_RDONLY(0x511, 0x44)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(14), A6XX_PROTECT_RW(0xe00, 0xe)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(15), A6XX_PROTECT_RW(0x8e00, 0x0)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(16), A6XX_PROTECT_RW(0x8e50, 0xf)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(17), A6XX_PROTECT_RW(0xbe02, 0x0)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(18), - A6XX_PROTECT_RW(0xbe20, 0x11f3)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(19), A6XX_PROTECT_RW(0x800, 0x82)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(20), A6XX_PROTECT_RW(0x8a0, 0x8)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(21), A6XX_PROTECT_RW(0x8ab, 0x19)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(22), A6XX_PROTECT_RW(0x900, 0x4d)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(23), A6XX_PROTECT_RW(0x98d, 0x76)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(24), - A6XX_PROTECT_RDONLY(0x980, 0x4)); - gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0)); + a6xx_set_cp_protect(gpu); /* Enable expanded apriv for targets that support it */ if (gpu->hw_apriv) { @@ -1211,7 +1284,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) if (ret) return ret; - if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) + if (a6xx_gpu->shadow_bo) for (i = 0; i < gpu->nr_rings; i++) a6xx_gpu->shadow[i] = 0; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index ce0610c5256f..bb544dfe5737 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -44,7 +44,7 @@ struct a6xx_gpu { * REG_CP_PROTECT_REG(n) - this will block both reads and writes for _len * registers starting at _reg. */ -#define A6XX_PROTECT_RW(_reg, _len) \ +#define A6XX_PROTECT_NORDWR(_reg, _len) \ ((1 << 31) | \ (((_len) & 0x3FFF) << 18) | ((_reg) & 0x3FFFF)) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index 34bc93548fcf..657778889d35 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -432,6 +432,7 @@ static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw, pll_freq += div_u64(tmp64, multiplier); vco_rate = pll_freq; + pll_10nm->vco_current_rate = vco_rate; DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", pll_10nm->phy->id, (unsigned long)vco_rate, dec, frac); diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index e76ce40a12ab..6f96fbac8282 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -460,6 +460,7 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, pll_freq += div_u64(tmp64, multiplier); vco_rate = pll_freq; + pll_7nm->vco_current_rate = vco_rate; DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", pll_7nm->phy->id, (unsigned long)vco_rate, dec, frac); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index a94a43de95ef..b61f5466e522 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1240,6 +1240,13 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev, to_msm_bo(obj)->vram_node = &vma->node; + /* Call chain get_pages() -> update_inactive() tries to + * access msm_obj->mm_list, but it is not initialized yet. + * To avoid NULL pointer dereference error, initialize + * mm_list to be empty. + */ + INIT_LIST_HEAD(&msm_obj->mm_list); + msm_gem_lock(obj); pages = get_pages(obj); msm_gem_unlock(obj); diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c index bbdfd5e26ec8..f75fb157f2ff 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -209,7 +209,7 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, goto err_disable_clk_tmds; } - ret = sun8i_hdmi_phy_probe(hdmi, phy_node); + ret = sun8i_hdmi_phy_get(hdmi, phy_node); of_node_put(phy_node); if (ret) { dev_err(dev, "Couldn't get the HDMI PHY\n"); @@ -242,7 +242,6 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, cleanup_encoder: drm_encoder_cleanup(encoder); - sun8i_hdmi_phy_remove(hdmi); err_disable_clk_tmds: clk_disable_unprepare(hdmi->clk_tmds); err_assert_ctrl_reset: @@ -263,7 +262,6 @@ static void sun8i_dw_hdmi_unbind(struct device *dev, struct device *master, struct sun8i_dw_hdmi *hdmi = dev_get_drvdata(dev); dw_hdmi_unbind(hdmi->hdmi); - sun8i_hdmi_phy_remove(hdmi); clk_disable_unprepare(hdmi->clk_tmds); reset_control_assert(hdmi->rst_ctrl); gpiod_set_value(hdmi->ddc_en, 0); @@ -320,7 +318,32 @@ static struct platform_driver sun8i_dw_hdmi_pltfm_driver = { .of_match_table = sun8i_dw_hdmi_dt_ids, }, }; -module_platform_driver(sun8i_dw_hdmi_pltfm_driver); + +static int __init sun8i_dw_hdmi_init(void) +{ + int ret; + + ret = platform_driver_register(&sun8i_dw_hdmi_pltfm_driver); + if (ret) + return ret; + + ret = platform_driver_register(&sun8i_hdmi_phy_driver); + if (ret) { + platform_driver_unregister(&sun8i_dw_hdmi_pltfm_driver); + return ret; + } + + return ret; +} + +static void __exit sun8i_dw_hdmi_exit(void) +{ + platform_driver_unregister(&sun8i_dw_hdmi_pltfm_driver); + platform_driver_unregister(&sun8i_hdmi_phy_driver); +} + +module_init(sun8i_dw_hdmi_init); +module_exit(sun8i_dw_hdmi_exit); MODULE_AUTHOR("Jernej Skrabec <jernej.skrabec@siol.net>"); MODULE_DESCRIPTION("Allwinner DW HDMI bridge"); diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h index d4b55af0592f..74f6ed0e2570 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h @@ -195,14 +195,15 @@ struct sun8i_dw_hdmi { struct gpio_desc *ddc_en; }; +extern struct platform_driver sun8i_hdmi_phy_driver; + static inline struct sun8i_dw_hdmi * encoder_to_sun8i_dw_hdmi(struct drm_encoder *encoder) { return container_of(encoder, struct sun8i_dw_hdmi, encoder); } -int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node); -void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi); +int sun8i_hdmi_phy_get(struct sun8i_dw_hdmi *hdmi, struct device_node *node); void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy); void sun8i_hdmi_phy_set_ops(struct sun8i_hdmi_phy *phy, diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c index 9994edf67509..c9239708d398 100644 --- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c +++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c @@ -5,6 +5,7 @@ #include <linux/delay.h> #include <linux/of_address.h> +#include <linux/of_platform.h> #include "sun8i_dw_hdmi.h" @@ -597,10 +598,30 @@ static const struct of_device_id sun8i_hdmi_phy_of_table[] = { { /* sentinel */ } }; -int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node) +int sun8i_hdmi_phy_get(struct sun8i_dw_hdmi *hdmi, struct device_node *node) +{ + struct platform_device *pdev = of_find_device_by_node(node); + struct sun8i_hdmi_phy *phy; + + if (!pdev) + return -EPROBE_DEFER; + + phy = platform_get_drvdata(pdev); + if (!phy) + return -EPROBE_DEFER; + + hdmi->phy = phy; + + put_device(&pdev->dev); + + return 0; +} + +static int sun8i_hdmi_phy_probe(struct platform_device *pdev) { const struct of_device_id *match; - struct device *dev = hdmi->dev; + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; struct sun8i_hdmi_phy *phy; struct resource res; void __iomem *regs; @@ -704,7 +725,7 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node) clk_prepare_enable(phy->clk_phy); } - hdmi->phy = phy; + platform_set_drvdata(pdev, phy); return 0; @@ -728,9 +749,9 @@ err_put_clk_bus: return ret; } -void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi) +static int sun8i_hdmi_phy_remove(struct platform_device *pdev) { - struct sun8i_hdmi_phy *phy = hdmi->phy; + struct sun8i_hdmi_phy *phy = platform_get_drvdata(pdev); clk_disable_unprepare(phy->clk_mod); clk_disable_unprepare(phy->clk_bus); @@ -744,4 +765,14 @@ void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi) clk_put(phy->clk_pll1); clk_put(phy->clk_mod); clk_put(phy->clk_bus); + return 0; } + +struct platform_driver sun8i_hdmi_phy_driver = { + .probe = sun8i_hdmi_phy_probe, + .remove = sun8i_hdmi_phy_remove, + .driver = { + .name = "sun8i-hdmi-phy", + .of_match_table = sun8i_hdmi_phy_of_table, + }, +}; diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index 87df251c1fcf..0cb868065348 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -25,7 +25,7 @@ #include "trace.h" /* XXX move to include/uapi/drm/drm_fourcc.h? */ -#define DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT BIT(22) +#define DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT BIT_ULL(22) struct reset_control; diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index 79bff8b48271..bfae8a02f55b 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -510,7 +510,7 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, * dGPU sector layout. */ if (tegra_plane_state->tiling.sector_layout == TEGRA_BO_SECTOR_LAYOUT_GPU) - base |= BIT(39); + base |= BIT_ULL(39); #endif tegra_plane_writel(p, tegra_plane_state->format, DC_WIN_COLOR_DEPTH); diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 7b88261f57bb..0ea320c1092b 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3125,21 +3125,21 @@ static int tegra_sor_init(struct host1x_client *client) if (err < 0) { dev_err(sor->dev, "failed to acquire SOR reset: %d\n", err); - return err; + goto rpm_put; } err = reset_control_assert(sor->rst); if (err < 0) { dev_err(sor->dev, "failed to assert SOR reset: %d\n", err); - return err; + goto rpm_put; } } err = clk_prepare_enable(sor->clk); if (err < 0) { dev_err(sor->dev, "failed to enable clock: %d\n", err); - return err; + goto rpm_put; } usleep_range(1000, 3000); @@ -3150,7 +3150,7 @@ static int tegra_sor_init(struct host1x_client *client) dev_err(sor->dev, "failed to deassert SOR reset: %d\n", err); clk_disable_unprepare(sor->clk); - return err; + goto rpm_put; } reset_control_release(sor->rst); @@ -3171,6 +3171,12 @@ static int tegra_sor_init(struct host1x_client *client) } return 0; + +rpm_put: + if (sor->rst) + pm_runtime_put(sor->dev); + + return err; } static int tegra_sor_exit(struct host1x_client *client) @@ -3739,12 +3745,8 @@ static int tegra_sor_probe(struct platform_device *pdev) if (!sor->aux) return -EPROBE_DEFER; - if (get_device(&sor->aux->ddc.dev)) { - if (try_module_get(sor->aux->ddc.owner)) - sor->output.ddc = &sor->aux->ddc; - else - put_device(&sor->aux->ddc.dev); - } + if (get_device(sor->aux->dev)) + sor->output.ddc = &sor->aux->ddc; } if (!sor->aux) { @@ -3772,12 +3774,13 @@ static int tegra_sor_probe(struct platform_device *pdev) err = tegra_sor_parse_dt(sor); if (err < 0) - return err; + goto put_aux; err = tegra_output_probe(&sor->output); - if (err < 0) - return dev_err_probe(&pdev->dev, err, - "failed to probe output\n"); + if (err < 0) { + dev_err_probe(&pdev->dev, err, "failed to probe output\n"); + goto put_aux; + } if (sor->ops && sor->ops->probe) { err = sor->ops->probe(sor); @@ -3916,17 +3919,10 @@ static int tegra_sor_probe(struct platform_device *pdev) platform_set_drvdata(pdev, sor); pm_runtime_enable(&pdev->dev); - INIT_LIST_HEAD(&sor->client.list); + host1x_client_init(&sor->client); sor->client.ops = &sor_client_ops; sor->client.dev = &pdev->dev; - err = host1x_client_register(&sor->client); - if (err < 0) { - dev_err(&pdev->dev, "failed to register host1x client: %d\n", - err); - goto rpm_disable; - } - /* * On Tegra210 and earlier, provide our own implementation for the * pad output clock. @@ -3938,13 +3934,13 @@ static int tegra_sor_probe(struct platform_device *pdev) sor->index); if (!name) { err = -ENOMEM; - goto unregister; + goto uninit; } err = host1x_client_resume(&sor->client); if (err < 0) { dev_err(sor->dev, "failed to resume: %d\n", err); - goto unregister; + goto uninit; } sor->clk_pad = tegra_clk_sor_pad_register(sor, name); @@ -3955,17 +3951,30 @@ static int tegra_sor_probe(struct platform_device *pdev) err = PTR_ERR(sor->clk_pad); dev_err(sor->dev, "failed to register SOR pad clock: %d\n", err); - goto unregister; + goto uninit; + } + + err = __host1x_client_register(&sor->client); + if (err < 0) { + dev_err(&pdev->dev, "failed to register host1x client: %d\n", + err); + goto uninit; } return 0; -unregister: - host1x_client_unregister(&sor->client); -rpm_disable: +uninit: + host1x_client_exit(&sor->client); pm_runtime_disable(&pdev->dev); remove: + if (sor->aux) + sor->output.ddc = NULL; + tegra_output_remove(&sor->output); +put_aux: + if (sor->aux) + put_device(sor->aux->dev); + return err; } @@ -3983,6 +3992,11 @@ static int tegra_sor_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); + if (sor->aux) { + put_device(sor->aux->dev); + sor->output.ddc = NULL; + } + tegra_output_remove(&sor->output); return 0; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index db53fecca696..1b950b45cf4b 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1139,7 +1139,10 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL)) return -EBUSY; - if (!ttm_bo_get_unless_zero(bo)) { + if (!bo->ttm || !ttm_tt_is_populated(bo->ttm) || + bo->ttm->page_flags & TTM_PAGE_FLAG_SG || + bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED || + !ttm_bo_get_unless_zero(bo)) { if (locked) dma_resv_unlock(bo->base.resv); return -EBUSY; diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 460953dcad11..5f31acec3ad7 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -143,14 +143,8 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) { list_for_each_entry(bo, &man->lru[j], lru) { - uint32_t num_pages; + uint32_t num_pages = PFN_UP(bo->base.size); - if (!bo->ttm || - bo->ttm->page_flags & TTM_PAGE_FLAG_SG || - bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) - continue; - - num_pages = bo->ttm->num_pages; ret = ttm_bo_swapout(bo, ctx, gfp_flags); /* ttm_bo_swapout has dropped the lru_lock */ if (!ret) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index f29ac64a5aa5..6a1a9e1d72ce 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -372,7 +372,7 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) if (!old_hvs_state->fifo_state[channel].in_use) continue; - ret = drm_crtc_commit_wait(old_hvs_state->fifo_state[i].pending_commit); + ret = drm_crtc_commit_wait(old_hvs_state->fifo_state[channel].pending_commit); if (ret) drm_err(dev, "Timed out waiting for commit\n"); } diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 46f69c532b6b..218e3718fd68 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -736,6 +736,29 @@ void host1x_driver_unregister(struct host1x_driver *driver) EXPORT_SYMBOL(host1x_driver_unregister); /** + * __host1x_client_init() - initialize a host1x client + * @client: host1x client + * @key: lock class key for the client-specific mutex + */ +void __host1x_client_init(struct host1x_client *client, struct lock_class_key *key) +{ + INIT_LIST_HEAD(&client->list); + __mutex_init(&client->lock, "host1x client lock", key); + client->usecount = 0; +} +EXPORT_SYMBOL(__host1x_client_init); + +/** + * host1x_client_exit() - uninitialize a host1x client + * @client: host1x client + */ +void host1x_client_exit(struct host1x_client *client) +{ + mutex_destroy(&client->lock); +} +EXPORT_SYMBOL(host1x_client_exit); + +/** * __host1x_client_register() - register a host1x client * @client: host1x client * @key: lock class key for the client-specific mutex @@ -747,16 +770,11 @@ EXPORT_SYMBOL(host1x_driver_unregister); * device and call host1x_device_init(), which will in turn call each client's * &host1x_client_ops.init implementation. */ -int __host1x_client_register(struct host1x_client *client, - struct lock_class_key *key) +int __host1x_client_register(struct host1x_client *client) { struct host1x *host1x; int err; - INIT_LIST_HEAD(&client->list); - __mutex_init(&client->lock, "host1x client lock", key); - client->usecount = 0; - mutex_lock(&devices_lock); list_for_each_entry(host1x, &devices, list) { diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 4bf263c2d61a..160554903ef9 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -93,11 +93,11 @@ menu "Special HID drivers" depends on HID config HID_A4TECH - tristate "A4 tech mice" + tristate "A4TECH mice" depends on HID default !EXPERT help - Support for A4 tech X5 and WOP-35 / Trust 450L mice. + Support for some A4TECH mice with two scroll wheels. config HID_ACCUTOUCH tristate "Accutouch touch device" @@ -922,6 +922,21 @@ config HID_SAMSUNG help Support for Samsung InfraRed remote control or keyboards. +config HID_SEMITEK + tristate "Semitek USB keyboards" + depends on HID + help + Support for Semitek USB keyboards that are not fully compliant + with the HID standard. + + There are many variants, including: + - GK61, GK64, GK68, GK84, GK96, etc. + - SK61, SK64, SK68, SK84, SK96, etc. + - Dierya DK61/DK66 + - Tronsmart TK09R + - Woo-dy + - X-Bows Nature/Knight + config HID_SONY tristate "Sony PS2/3/4 accessories" depends on USB_HID diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index 193431ec4db8..1ea1a7c0b20f 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -106,6 +106,7 @@ obj-$(CONFIG_HID_ROCCAT) += hid-roccat.o hid-roccat-common.o \ obj-$(CONFIG_HID_RMI) += hid-rmi.o obj-$(CONFIG_HID_SAITEK) += hid-saitek.o obj-$(CONFIG_HID_SAMSUNG) += hid-samsung.o +obj-$(CONFIG_HID_SEMITEK) += hid-semitek.o obj-$(CONFIG_HID_SMARTJOYPLUS) += hid-sjoy.o obj-$(CONFIG_HID_SONY) += hid-sony.o obj-$(CONFIG_HID_SPEEDLINK) += hid-speedlink.o diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index 2ab38b715347..3589d9945da1 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -88,6 +88,7 @@ static void amd_sfh_work(struct work_struct *work) sensor_index = req_node->sensor_idx; report_id = req_node->report_id; node_type = req_node->report_type; + kfree(req_node); if (node_type == HID_FEATURE_REPORT) { report_size = get_feature_report(sensor_index, report_id, @@ -142,7 +143,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) int rc, i; dev = &privdata->pdev->dev; - cl_data = kzalloc(sizeof(*cl_data), GFP_KERNEL); + cl_data = devm_kzalloc(dev, sizeof(*cl_data), GFP_KERNEL); if (!cl_data) return -ENOMEM; @@ -175,12 +176,12 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) rc = -EINVAL; goto cleanup; } - cl_data->feature_report[i] = kzalloc(feature_report_size, GFP_KERNEL); + cl_data->feature_report[i] = devm_kzalloc(dev, feature_report_size, GFP_KERNEL); if (!cl_data->feature_report[i]) { rc = -ENOMEM; goto cleanup; } - cl_data->input_report[i] = kzalloc(input_report_size, GFP_KERNEL); + cl_data->input_report[i] = devm_kzalloc(dev, input_report_size, GFP_KERNEL); if (!cl_data->input_report[i]) { rc = -ENOMEM; goto cleanup; @@ -189,7 +190,8 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) info.sensor_idx = cl_idx; info.dma_address = cl_data->sensor_dma_addr[i]; - cl_data->report_descr[i] = kzalloc(cl_data->report_descr_sz[i], GFP_KERNEL); + cl_data->report_descr[i] = + devm_kzalloc(dev, cl_data->report_descr_sz[i], GFP_KERNEL); if (!cl_data->report_descr[i]) { rc = -ENOMEM; goto cleanup; @@ -214,11 +216,11 @@ cleanup: cl_data->sensor_virt_addr[i], cl_data->sensor_dma_addr[i]); } - kfree(cl_data->feature_report[i]); - kfree(cl_data->input_report[i]); - kfree(cl_data->report_descr[i]); + devm_kfree(dev, cl_data->feature_report[i]); + devm_kfree(dev, cl_data->input_report[i]); + devm_kfree(dev, cl_data->report_descr[i]); } - kfree(cl_data); + devm_kfree(dev, cl_data); return rc; } @@ -241,6 +243,5 @@ int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata) cl_data->sensor_dma_addr[i]); } } - kfree(cl_data); return 0; } diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c index 4f989483aa03..5ad1e7acd294 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c @@ -162,9 +162,6 @@ void amdtp_hid_remove(struct amdtp_cl_data *cli_data) int i; for (i = 0; i < cli_data->num_hid_devices; ++i) { - kfree(cli_data->feature_report[i]); - kfree(cli_data->input_report[i]); - kfree(cli_data->report_descr[i]); if (cli_data->hid_sensor_hubs[i]) { kfree(cli_data->hid_sensor_hubs[i]->driver_data); hid_destroy_device(cli_data->hid_sensor_hubs[i]); diff --git a/drivers/hid/hid-a4tech.c b/drivers/hid/hid-a4tech.c index 3a8c4a5971f7..2cbc32dda7f7 100644 --- a/drivers/hid/hid-a4tech.c +++ b/drivers/hid/hid-a4tech.c @@ -147,6 +147,8 @@ static const struct hid_device_id a4_devices[] = { .driver_data = A4_2WHEEL_MOUSE_HACK_B8 }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_RP_649), .driver_data = A4_2WHEEL_MOUSE_HACK_B8 }, + { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_NB_95), + .driver_data = A4_2WHEEL_MOUSE_HACK_B8 }, { } }; MODULE_DEVICE_TABLE(hid, a4_devices); diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 2ab22b925941..fca8fc78a78a 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -79,10 +79,9 @@ MODULE_DESCRIPTION("Asus HID Keyboard and TouchPad"); #define QUIRK_T100_KEYBOARD BIT(6) #define QUIRK_T100CHI BIT(7) #define QUIRK_G752_KEYBOARD BIT(8) -#define QUIRK_T101HA_DOCK BIT(9) -#define QUIRK_T90CHI BIT(10) -#define QUIRK_MEDION_E1239T BIT(11) -#define QUIRK_ROG_NKEY_KEYBOARD BIT(12) +#define QUIRK_T90CHI BIT(9) +#define QUIRK_MEDION_E1239T BIT(10) +#define QUIRK_ROG_NKEY_KEYBOARD BIT(11) #define I2C_KEYBOARD_QUIRKS (QUIRK_FIX_NOTEBOOK_REPORT | \ QUIRK_NO_INIT_REPORTS | \ @@ -335,7 +334,7 @@ static int asus_raw_event(struct hid_device *hdev, if (drvdata->quirks & QUIRK_MEDION_E1239T) return asus_e1239t_event(drvdata, data, size); - if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD) { + if (drvdata->quirks & QUIRK_USE_KBD_BACKLIGHT) { /* * Skip these report ID, the device emits a continuous stream associated * with the AURA mode it is in which looks like an 'echo'. @@ -355,6 +354,16 @@ static int asus_raw_event(struct hid_device *hdev, return -1; } } + if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD) { + /* + * G713 and G733 send these codes on some keypresses, depending on + * the key pressed it can trigger a shutdown event if not caught. + */ + if(data[0] == 0x02 && data[1] == 0x30) { + return -1; + } + } + } return 0; @@ -1072,11 +1081,6 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; } - /* use hid-multitouch for T101HA touchpad */ - if (id->driver_data & QUIRK_T101HA_DOCK && - hdev->collection->usage == HID_GD_MOUSE) - return -ENODEV; - ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "Asus hw start failed: %d\n", ret); @@ -1230,8 +1234,6 @@ static const struct hid_device_id asus_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100TAF_KEYBOARD), QUIRK_T100_KEYBOARD | QUIRK_NO_CONSUMER_USAGES }, - { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, - USB_DEVICE_ID_ASUSTEK_T101HA_KEYBOARD), QUIRK_T101HA_DOCK }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_ASUS_AK1D) }, { HID_USB_DEVICE(USB_VENDOR_ID_TURBOX, USB_DEVICE_ID_ASUS_MD_5110) }, { HID_USB_DEVICE(USB_VENDOR_ID_JESS, USB_DEVICE_ID_ASUS_MD_5112) }, @@ -1239,6 +1241,12 @@ static const struct hid_device_id asus_devices[] = { USB_DEVICE_ID_ASUSTEK_T100CHI_KEYBOARD), QUIRK_T100CHI }, { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE_MEDION_E1239T), QUIRK_MEDION_E1239T }, + /* + * Note bind to the HID_GROUP_GENERIC group, so that we only bind to the keyboard + * part, while letting hid-multitouch.c handle the touchpad. + */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T101HA_KEYBOARD) }, { } }; MODULE_DEVICE_TABLE(hid, asus_devices); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 0ae9f6df59d1..0de2788b9814 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2005,6 +2005,9 @@ int hid_connect(struct hid_device *hdev, unsigned int connect_mask) case BUS_I2C: bus = "I2C"; break; + case BUS_VIRTUAL: + bus = "VIRTUAL"; + break; default: bus = "<UNKNOWN>"; } @@ -2588,7 +2591,6 @@ int hid_check_keys_pressed(struct hid_device *hid) return 0; } - EXPORT_SYMBOL_GPL(hid_check_keys_pressed); static int __init hid_init(void) diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 59f8d716d78f..a311fb87b02a 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -930,6 +930,9 @@ static const char *keys[KEY_MAX + 1] = { [KEY_APPSELECT] = "AppSelect", [KEY_SCREENSAVER] = "ScreenSaver", [KEY_VOICECOMMAND] = "VoiceCommand", + [KEY_ASSISTANT] = "Assistant", + [KEY_KBD_LAYOUT_NEXT] = "KbdLayoutNext", + [KEY_EMOJI_PICKER] = "EmojiPicker", [KEY_BRIGHTNESS_MIN] = "BrightnessMin", [KEY_BRIGHTNESS_MAX] = "BrightnessMax", [KEY_BRIGHTNESS_AUTO] = "BrightnessAuto", diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index a5751607ce24..f43a8406cb9a 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -201,7 +201,7 @@ struct ft260_i2c_write_request_report { u8 address; /* 7-bit I2C address */ u8 flag; /* I2C transaction condition */ u8 length; /* data payload length */ - u8 data[60]; /* data payload */ + u8 data[FT260_WR_DATA_MAX]; /* data payload */ } __packed; struct ft260_i2c_read_request_report { @@ -249,7 +249,10 @@ static int ft260_hid_feature_report_get(struct hid_device *hdev, ret = hid_hw_raw_request(hdev, report_id, buf, len, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); - memcpy(data, buf, len); + if (likely(ret == len)) + memcpy(data, buf, len); + else if (ret >= 0) + ret = -EIO; kfree(buf); return ret; } @@ -298,7 +301,7 @@ static int ft260_xfer_status(struct ft260_device *dev) ret = ft260_hid_feature_report_get(hdev, FT260_I2C_STATUS, (u8 *)&report, sizeof(report)); - if (ret < 0) { + if (unlikely(ret < 0)) { hid_err(hdev, "failed to retrieve status: %d\n", ret); return ret; } @@ -429,6 +432,9 @@ static int ft260_smbus_write(struct ft260_device *dev, u8 addr, u8 cmd, struct ft260_i2c_write_request_report *rep = (struct ft260_i2c_write_request_report *)dev->write_buf; + if (data_len >= sizeof(rep->data)) + return -EINVAL; + rep->address = addr; rep->data[0] = cmd; rep->length = data_len + 1; @@ -721,10 +727,9 @@ static int ft260_get_system_config(struct hid_device *hdev, ret = ft260_hid_feature_report_get(hdev, FT260_SYSTEM_SETTINGS, (u8 *)cfg, len); - if (ret != len) { + if (ret < 0) { hid_err(hdev, "failed to retrieve system status\n"); - if (ret >= 0) - return -EIO; + return ret; } return 0; } @@ -777,8 +782,8 @@ static int ft260_byte_show(struct hid_device *hdev, int id, u8 *cfg, int len, int ret; ret = ft260_hid_feature_report_get(hdev, id, cfg, len); - if (ret != len && ret >= 0) - return -EIO; + if (ret < 0) + return ret; return scnprintf(buf, PAGE_SIZE, "%hi\n", *field); } @@ -789,8 +794,8 @@ static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len, int ret; ret = ft260_hid_feature_report_get(hdev, id, cfg, len); - if (ret != len && ret >= 0) - return -EIO; + if (ret < 0) + return ret; return scnprintf(buf, PAGE_SIZE, "%hi\n", le16_to_cpu(*field)); } @@ -941,10 +946,8 @@ static int ft260_probe(struct hid_device *hdev, const struct hid_device_id *id) ret = ft260_hid_feature_report_get(hdev, FT260_CHIP_VERSION, (u8 *)&version, sizeof(version)); - if (ret != sizeof(version)) { + if (ret < 0) { hid_err(hdev, "failed to retrieve chip version\n"); - if (ret >= 0) - ret = -EIO; goto err_hid_close; } diff --git a/drivers/hid/hid-gt683r.c b/drivers/hid/hid-gt683r.c index 898871c8c768..29ccb0accfba 100644 --- a/drivers/hid/hid-gt683r.c +++ b/drivers/hid/hid-gt683r.c @@ -54,6 +54,7 @@ static const struct hid_device_id gt683r_led_id[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL) }, { } }; +MODULE_DEVICE_TABLE(hid, gt683r_led_id); static void gt683r_brightness_set(struct led_classdev *led_cdev, enum led_brightness brightness) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 84b8da3e7d09..b84a0a11e05b 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -26,6 +26,7 @@ #define USB_DEVICE_ID_A4TECH_WCP32PU 0x0006 #define USB_DEVICE_ID_A4TECH_X5_005D 0x000a #define USB_DEVICE_ID_A4TECH_RP_649 0x001a +#define USB_DEVICE_ID_A4TECH_NB_95 0x022b #define USB_VENDOR_ID_AASHIMA 0x06d6 #define USB_DEVICE_ID_AASHIMA_GAMEPAD 0x0025 @@ -299,8 +300,6 @@ #define USB_VENDOR_ID_CORSAIR 0x1b1c #define USB_DEVICE_ID_CORSAIR_K90 0x1b02 - -#define USB_VENDOR_ID_CORSAIR 0x1b1c #define USB_DEVICE_ID_CORSAIR_K70R 0x1b09 #define USB_DEVICE_ID_CORSAIR_K95RGB 0x1b11 #define USB_DEVICE_ID_CORSAIR_M65RGB 0x1b12 @@ -751,6 +750,7 @@ #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 #define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5 +#define USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E 0x600e #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D 0x608d #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019 0x6019 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E 0x602e @@ -1051,6 +1051,7 @@ #define USB_DEVICE_ID_SAITEK_X52 0x075c #define USB_DEVICE_ID_SAITEK_X52_2 0x0255 #define USB_DEVICE_ID_SAITEK_X52_PRO 0x0762 +#define USB_DEVICE_ID_SAITEK_X65 0x0b6a #define USB_VENDOR_ID_SAMSUNG 0x0419 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 @@ -1060,6 +1061,9 @@ #define USB_DEVICE_ID_SEMICO_USB_KEYKOARD 0x0023 #define USB_DEVICE_ID_SEMICO_USB_KEYKOARD2 0x0027 +#define USB_VENDOR_ID_SEMITEK 0x1ea7 +#define USB_DEVICE_ID_SEMITEK_KEYBOARD 0x0907 + #define USB_VENDOR_ID_SENNHEISER 0x1395 #define USB_DEVICE_ID_SENNHEISER_BTD500USB 0x002c @@ -1161,6 +1165,7 @@ #define USB_DEVICE_ID_SYNAPTICS_DELL_K12A 0x2819 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 +#define USB_DEVICE_ID_SYNAPTICS_DELL_K15A 0x6e21 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002 0x73f4 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003 0x73f5 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 18f5e28d475c..abbfa91e73e4 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -964,6 +964,9 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x0cd: map_key_clear(KEY_PLAYPAUSE); break; case 0x0cf: map_key_clear(KEY_VOICECOMMAND); break; + + case 0x0d9: map_key_clear(KEY_EMOJI_PICKER); break; + case 0x0e0: map_abs_clear(ABS_VOLUME); break; case 0x0e2: map_key_clear(KEY_MUTE); break; case 0x0e5: map_key_clear(KEY_BASSBOOST); break; diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index d598094dadd0..fee4e54a3ce0 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -1263,6 +1263,7 @@ static int hidpp20_battery_map_status_voltage(u8 data[3], int *voltage, int status; long flags = (long) data[2]; + *level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN; if (flags & 0x80) switch (flags & 0x07) { diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 2bb473d8c424..8bcaee4ccae0 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -693,7 +693,7 @@ static int magicmouse_probe(struct hid_device *hdev, if (id->vendor == USB_VENDOR_ID_APPLE && id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 && hdev->type != HID_TYPE_USBMOUSE) - return 0; + return -ENODEV; msc = devm_kzalloc(&hdev->dev, sizeof(*msc), GFP_KERNEL); if (msc == NULL) { @@ -779,7 +779,10 @@ err_stop_hw: static void magicmouse_remove(struct hid_device *hdev) { struct magicmouse_sc *msc = hid_get_drvdata(hdev); - cancel_delayed_work_sync(&msc->work); + + if (msc) + cancel_delayed_work_sync(&msc->work); + hid_hw_stop(hdev); } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 9d9f3e1bd5f4..2e4fb76c45f3 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -70,6 +70,7 @@ MODULE_LICENSE("GPL"); #define MT_QUIRK_WIN8_PTP_BUTTONS BIT(18) #define MT_QUIRK_SEPARATE_APP_REPORT BIT(19) #define MT_QUIRK_FORCE_MULTI_INPUT BIT(20) +#define MT_QUIRK_DISABLE_WAKEUP BIT(21) #define MT_INPUTMODE_TOUCHSCREEN 0x02 #define MT_INPUTMODE_TOUCHPAD 0x03 @@ -191,6 +192,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app); #define MT_CLS_EXPORT_ALL_INPUTS 0x0013 /* reserved 0x0014 */ #define MT_CLS_WIN_8_FORCE_MULTI_INPUT 0x0015 +#define MT_CLS_WIN_8_DISABLE_WAKEUP 0x0016 /* vendor specific classes */ #define MT_CLS_3M 0x0101 @@ -283,6 +285,15 @@ static const struct mt_class mt_classes[] = { MT_QUIRK_WIN8_PTP_BUTTONS | MT_QUIRK_FORCE_MULTI_INPUT, .export_all_inputs = true }, + { .name = MT_CLS_WIN_8_DISABLE_WAKEUP, + .quirks = MT_QUIRK_ALWAYS_VALID | + MT_QUIRK_IGNORE_DUPLICATES | + MT_QUIRK_HOVERING | + MT_QUIRK_CONTACT_CNT_ACCURATE | + MT_QUIRK_STICKY_FINGERS | + MT_QUIRK_WIN8_PTP_BUTTONS | + MT_QUIRK_DISABLE_WAKEUP, + .export_all_inputs = true }, /* * vendor specific classes @@ -604,9 +615,13 @@ static struct mt_report_data *mt_allocate_report_data(struct mt_device *td, if (!(HID_MAIN_ITEM_VARIABLE & field->flags)) continue; - for (n = 0; n < field->report_count; n++) { - if (field->usage[n].hid == HID_DG_CONTACTID) - rdata->is_mt_collection = true; + if (field->logical == HID_DG_FINGER || td->hdev->group != HID_GROUP_MULTITOUCH_WIN_8) { + for (n = 0; n < field->report_count; n++) { + if (field->usage[n].hid == HID_DG_CONTACTID) { + rdata->is_mt_collection = true; + break; + } + } } } @@ -759,7 +774,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 1; case HID_DG_CONFIDENCE: if ((cls->name == MT_CLS_WIN_8 || - cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT) && + cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT || + cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP) && (field->application == HID_DG_TOUCHPAD || field->application == HID_DG_TOUCHSCREEN)) app->quirks |= MT_QUIRK_CONFIDENCE; @@ -1576,13 +1592,13 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi) /* we do not set suffix = "Touchscreen" */ hi->input->name = hdev->name; break; - case HID_DG_STYLUS: - /* force BTN_STYLUS to allow tablet matching in udev */ - __set_bit(BTN_STYLUS, hi->input->keybit); - break; case HID_VD_ASUS_CUSTOM_MEDIA_KEYS: suffix = "Custom Media Keys"; break; + case HID_DG_STYLUS: + /* force BTN_STYLUS to allow tablet matching in udev */ + __set_bit(BTN_STYLUS, hi->input->keybit); + fallthrough; case HID_DG_PEN: suffix = "Stylus"; break; @@ -1749,8 +1765,14 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) #ifdef CONFIG_PM static int mt_suspend(struct hid_device *hdev, pm_message_t state) { + struct mt_device *td = hid_get_drvdata(hdev); + /* High latency is desirable for power savings during S3/S0ix */ - mt_set_modes(hdev, HID_LATENCY_HIGH, true, true); + if (td->mtclass.quirks & MT_QUIRK_DISABLE_WAKEUP) + mt_set_modes(hdev, HID_LATENCY_HIGH, false, false); + else + mt_set_modes(hdev, HID_LATENCY_HIGH, true, true); + return 0; } @@ -1809,6 +1831,12 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_ANTON, USB_DEVICE_ID_ANTON_TOUCH_PAD) }, + /* Asus T101HA */ + { .driver_data = MT_CLS_WIN_8_DISABLE_WAKEUP, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_ASUSTEK, + USB_DEVICE_ID_ASUSTEK_T101HA_KEYBOARD) }, + /* Asus T304UA */ { .driver_data = MT_CLS_ASUS, HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 3dd6f15f2a67..51b39bda9a9d 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -110,6 +110,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_M912), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE_ID2), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E), HID_QUIRK_ALWAYS_POLL }, @@ -158,6 +159,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_2), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_PRO), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X65), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET }, @@ -176,6 +178,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DELL_K12A), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DELL_K15A), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPMAX, USB_DEVICE_ID_TOPMAX_COBRAPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8882), HID_QUIRK_NOGET }, @@ -211,6 +214,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_WCP32PU) }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_X5_005D) }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_RP_649) }, + { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_NB_95) }, #endif #if IS_ENABLED(CONFIG_HID_ACCUTOUCH) { HID_USB_DEVICE(USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_ACCUTOUCH_2216) }, diff --git a/drivers/hid/hid-semitek.c b/drivers/hid/hid-semitek.c new file mode 100644 index 000000000000..ba6607d5e051 --- /dev/null +++ b/drivers/hid/hid-semitek.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * HID driver for Semitek keyboards + * + * Copyright (c) 2021 Benjamin Moody + */ + +#include <linux/device.h> +#include <linux/hid.h> +#include <linux/module.h> + +#include "hid-ids.h" + +static __u8 *semitek_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + /* In the report descriptor for interface 2, fix the incorrect + description of report ID 0x04 (the report contains a + bitmask, not an array of keycodes.) */ + if (*rsize == 0xcb && rdesc[0x83] == 0x81 && rdesc[0x84] == 0x00) { + hid_info(hdev, "fixing up Semitek report descriptor\n"); + rdesc[0x84] = 0x02; + } + return rdesc; +} + +static const struct hid_device_id semitek_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_SEMITEK, USB_DEVICE_ID_SEMITEK_KEYBOARD) }, + { } +}; +MODULE_DEVICE_TABLE(hid, semitek_devices); + +static struct hid_driver semitek_driver = { + .name = "semitek", + .id_table = semitek_devices, + .report_fixup = semitek_report_fixup, +}; +module_hid_driver(semitek_driver); + +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index 2e6662173a79..32c2306e240d 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -387,7 +387,7 @@ static ssize_t store_value(struct device *dev, struct device_attribute *attr, struct hid_sensor_custom *sensor_inst = dev_get_drvdata(dev); int index, field_index, usage; char name[HID_CUSTOM_NAME_LENGTH]; - int value; + int value, ret; if (sscanf(attr->attr.name, "feature-%x-%x-%s", &index, &usage, name) == 3) { @@ -403,8 +403,10 @@ static ssize_t store_value(struct device *dev, struct device_attribute *attr, report_id = sensor_inst->fields[field_index].attribute. report_id; - sensor_hub_set_feature(sensor_inst->hsdev, report_id, - index, sizeof(value), &value); + ret = sensor_hub_set_feature(sensor_inst->hsdev, report_id, + index, sizeof(value), &value); + if (ret) + return ret; } else return -EINVAL; diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 95cf88f3bafb..6abd3e2a9094 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -209,16 +209,21 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, buffer_size = buffer_size / sizeof(__s32); if (buffer_size) { for (i = 0; i < buffer_size; ++i) { - hid_set_field(report->field[field_index], i, - (__force __s32)cpu_to_le32(*buf32)); + ret = hid_set_field(report->field[field_index], i, + (__force __s32)cpu_to_le32(*buf32)); + if (ret) + goto done_proc; + ++buf32; } } if (remaining_bytes) { value = 0; memcpy(&value, (u8 *)buf32, remaining_bytes); - hid_set_field(report->field[field_index], i, - (__force __s32)cpu_to_le32(value)); + ret = hid_set_field(report->field[field_index], i, + (__force __s32)cpu_to_le32(value)); + if (ret) + goto done_proc; } hid_hw_request(hsdev->hdev, report, HID_REQ_SET_REPORT); hid_hw_wait(hsdev->hdev); diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index 2e452c6e8ef4..f643b1cb112d 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -312,7 +312,7 @@ static int thrustmaster_probe(struct hid_device *hdev, const struct hid_device_i } tm_wheel->change_request = kzalloc(sizeof(struct usb_ctrlrequest), GFP_KERNEL); - if (!tm_wheel->model_request) { + if (!tm_wheel->change_request) { ret = -ENOMEM; goto error5; } diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 9993133989a5..46474612e73c 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -45,6 +45,7 @@ #define I2C_HID_QUIRK_BOGUS_IRQ BIT(4) #define I2C_HID_QUIRK_RESET_ON_RESUME BIT(5) #define I2C_HID_QUIRK_BAD_INPUT_SIZE BIT(6) +#define I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET BIT(7) /* flags */ @@ -178,6 +179,11 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_RESET_ON_RESUME }, { USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720, I2C_HID_QUIRK_BAD_INPUT_SIZE }, + /* + * Sending the wakeup after reset actually break ELAN touchscreen controller + */ + { USB_VENDOR_ID_ELAN, HID_ANY_ID, + I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET }, { 0, 0 } }; @@ -461,7 +467,8 @@ static int i2c_hid_hwreset(struct i2c_client *client) } /* At least some SIS devices need this after reset */ - ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); + if (!(ihid->quirks & I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET)) + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); out_unlock: mutex_unlock(&ihid->reset_lock); @@ -990,8 +997,8 @@ int i2c_hid_core_probe(struct i2c_client *client, struct i2chid_ops *ops, hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID); hid->product = le16_to_cpu(ihid->hdesc.wProductID); - snprintf(hid->name, sizeof(hid->name), "%s %04hX:%04hX", - client->name, hid->vendor, hid->product); + snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", + client->name, (u16)hid->vendor, (u16)hid->product); strlcpy(hid->phys, dev_name(&client->dev), sizeof(hid->phys)); ihid->quirks = i2c_hid_lookup_quirk(hid->vendor, hid->product); diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index 21b87e4003af..07e3cbc86bef 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -28,6 +28,8 @@ #define EHL_Ax_DEVICE_ID 0x4BB3 #define TGL_LP_DEVICE_ID 0xA0FC #define TGL_H_DEVICE_ID 0x43FC +#define ADL_S_DEVICE_ID 0x7AF8 +#define ADL_P_DEVICE_ID 0x51FC #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 06081cf9b85a..a6d5173ac003 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -39,6 +39,8 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, EHL_Ax_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, TGL_LP_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, TGL_H_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_S_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_P_DEVICE_ID)}, {0, } }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hid/surface-hid/surface_hid_core.c b/drivers/hid/surface-hid/surface_hid_core.c index 7b27ec392232..5571e74abe91 100644 --- a/drivers/hid/surface-hid/surface_hid_core.c +++ b/drivers/hid/surface-hid/surface_hid_core.c @@ -168,9 +168,9 @@ int surface_hid_device_add(struct surface_hid_device *shid) shid->hid->dev.parent = shid->dev; shid->hid->bus = BUS_HOST; - shid->hid->vendor = cpu_to_le16(shid->attrs.vendor); - shid->hid->product = cpu_to_le16(shid->attrs.product); - shid->hid->version = cpu_to_le16(shid->hid_desc.hid_version); + shid->hid->vendor = get_unaligned_le16(&shid->attrs.vendor); + shid->hid->product = get_unaligned_le16(&shid->attrs.product); + shid->hid->version = get_unaligned_le16(&shid->hid_desc.hid_version); shid->hid->country = shid->hid_desc.country_code; snprintf(shid->hid->name, sizeof(shid->hid->name), "Microsoft Surface %04X:%04X", diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 86257ce6d619..4e9077363c96 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -374,7 +374,7 @@ static int hid_submit_ctrl(struct hid_device *hid) raw_report = usbhid->ctrl[usbhid->ctrltail].raw_report; dir = usbhid->ctrl[usbhid->ctrltail].dir; - len = ((report->size - 1) >> 3) + 1 + (report->id > 0); + len = hid_report_len(report); if (dir == USB_DIR_OUT) { usbhid->urbctrl->pipe = usb_sndctrlpipe(hid_to_usb_dev(hid), 0); usbhid->urbctrl->transfer_buffer_length = len; diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index ea126c50acc3..3b4ee21cd811 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -1292,6 +1292,7 @@ int hid_pidff_init(struct hid_device *hid) if (pidff->pool[PID_DEVICE_MANAGED_POOL].value && pidff->pool[PID_DEVICE_MANAGED_POOL].value[0] == 0) { + error = -EPERM; hid_notice(hid, "device does not support device managed pool\n"); goto fail; diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index 02298b86b57b..731d5117f9f1 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -771,6 +771,16 @@ static int corsairpsu_raw_event(struct hid_device *hdev, struct hid_report *repo return 0; } +#ifdef CONFIG_PM +static int corsairpsu_resume(struct hid_device *hdev) +{ + struct corsairpsu_data *priv = hid_get_drvdata(hdev); + + /* some PSUs turn off the microcontroller during standby, so a reinit is required */ + return corsairpsu_init(priv); +} +#endif + static const struct hid_device_id corsairpsu_idtable[] = { { HID_USB_DEVICE(0x1b1c, 0x1c03) }, /* Corsair HX550i */ { HID_USB_DEVICE(0x1b1c, 0x1c04) }, /* Corsair HX650i */ @@ -793,6 +803,10 @@ static struct hid_driver corsairpsu_driver = { .probe = corsairpsu_probe, .remove = corsairpsu_remove, .raw_event = corsairpsu_raw_event, +#ifdef CONFIG_PM + .resume = corsairpsu_resume, + .reset_resume = corsairpsu_resume, +#endif }; module_hid_driver(corsairpsu_driver); diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index 2970892bed82..f2221ca0aa7b 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -838,10 +838,10 @@ static struct attribute *i8k_attrs[] = { static umode_t i8k_is_visible(struct kobject *kobj, struct attribute *attr, int index) { - if (disallow_fan_support && index >= 8) + if (disallow_fan_support && index >= 20) return 0; if (disallow_fan_type_call && - (index == 9 || index == 12 || index == 15)) + (index == 21 || index == 25 || index == 28)) return 0; if (index >= 0 && index <= 1 && !(i8k_hwmon_flags & I8K_HWMON_HAVE_TEMP1)) diff --git a/drivers/hwmon/pmbus/fsp-3y.c b/drivers/hwmon/pmbus/fsp-3y.c index e24842475254..aec294cc72d1 100644 --- a/drivers/hwmon/pmbus/fsp-3y.c +++ b/drivers/hwmon/pmbus/fsp-3y.c @@ -37,6 +37,8 @@ struct fsp3y_data { struct pmbus_driver_info info; int chip; int page; + + bool vout_linear_11; }; #define to_fsp3y_data(x) container_of(x, struct fsp3y_data, info) @@ -108,11 +110,9 @@ static int fsp3y_read_byte_data(struct i2c_client *client, int page, int reg) int rv; /* - * YH5151-E outputs vout in linear11. The conversion is done when - * reading. Here, we have to inject pmbus_core with the correct - * exponent (it is -6). + * Inject an exponent for non-compliant YH5151-E. */ - if (data->chip == yh5151e && reg == PMBUS_VOUT_MODE) + if (data->vout_linear_11 && reg == PMBUS_VOUT_MODE) return 0x1A; rv = set_page(client, page); @@ -161,10 +161,9 @@ static int fsp3y_read_word_data(struct i2c_client *client, int page, int phase, return rv; /* - * YH-5151E is non-compliant and outputs output voltages in linear11 - * instead of linear16. + * Handle YH-5151E non-compliant linear11 vout voltage. */ - if (data->chip == yh5151e && reg == PMBUS_READ_VOUT) + if (data->vout_linear_11 && reg == PMBUS_READ_VOUT) rv = sign_extend32(rv, 10) & 0xffff; return rv; @@ -256,6 +255,25 @@ static int fsp3y_probe(struct i2c_client *client) data->info = fsp3y_info[data->chip]; + /* + * YH-5151E sometimes reports vout in linear11 and sometimes in + * linear16. This depends on the exact individual piece of hardware. One + * YH-5151E can use linear16 and another might use linear11 instead. + * + * The format can be recognized by reading VOUT_MODE - if it doesn't + * report a valid exponent, then vout uses linear11. Otherwise, the + * device is compliant and uses linear16. + */ + data->vout_linear_11 = false; + if (data->chip == yh5151e) { + rv = i2c_smbus_read_byte_data(client, PMBUS_VOUT_MODE); + if (rv < 0) + return rv; + + if (rv == 0xFF) + data->vout_linear_11 = true; + } + return pmbus_do_probe(client, &data->info); } diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c index 40597a9e799f..1a8caff1ac5f 100644 --- a/drivers/hwmon/pmbus/isl68137.c +++ b/drivers/hwmon/pmbus/isl68137.c @@ -244,8 +244,8 @@ static int isl68137_probe(struct i2c_client *client) info->read_word_data = raa_dmpvr2_read_word_data; break; case raa_dmpvr2_2rail_nontc: - info->func[0] &= ~PMBUS_HAVE_TEMP; - info->func[1] &= ~PMBUS_HAVE_TEMP; + info->func[0] &= ~PMBUS_HAVE_TEMP3; + info->func[1] &= ~PMBUS_HAVE_TEMP3; fallthrough; case raa_dmpvr2_2rail: info->pages = 2; diff --git a/drivers/hwmon/pmbus/q54sj108a2.c b/drivers/hwmon/pmbus/q54sj108a2.c index b6e8b20466f1..fa298b4265a1 100644 --- a/drivers/hwmon/pmbus/q54sj108a2.c +++ b/drivers/hwmon/pmbus/q54sj108a2.c @@ -299,7 +299,7 @@ static int q54sj108a2_probe(struct i2c_client *client) dev_err(&client->dev, "Failed to read Manufacturer ID\n"); return ret; } - if (ret != 5 || strncmp(buf, "DELTA", 5)) { + if (ret != 6 || strncmp(buf, "DELTA", 5)) { buf[ret] = '\0'; dev_err(dev, "Unsupported Manufacturer ID '%s'\n", buf); return -ENODEV; diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c index 25aac40f2764..919877970ae3 100644 --- a/drivers/hwmon/scpi-hwmon.c +++ b/drivers/hwmon/scpi-hwmon.c @@ -99,6 +99,15 @@ scpi_show_sensor(struct device *dev, struct device_attribute *attr, char *buf) scpi_scale_reading(&value, sensor); + /* + * Temperature sensor values are treated as signed values based on + * observation even though that is not explicitly specified, and + * because an unsigned u64 temperature does not really make practical + * sense especially when the temperature is below zero degrees Celsius. + */ + if (sensor->info.class == TEMPERATURE) + return sprintf(buf, "%lld\n", (s64)value); + return sprintf(buf, "%llu\n", value); } diff --git a/drivers/hwmon/tps23861.c b/drivers/hwmon/tps23861.c index c2484f15298b..8bd6435c13e8 100644 --- a/drivers/hwmon/tps23861.c +++ b/drivers/hwmon/tps23861.c @@ -99,11 +99,14 @@ #define POWER_ENABLE 0x19 #define TPS23861_NUM_PORTS 4 +#define TPS23861_GENERAL_MASK_1 0x17 +#define TPS23861_CURRENT_SHUNT_MASK BIT(0) + #define TEMPERATURE_LSB 652 /* 0.652 degrees Celsius */ #define VOLTAGE_LSB 3662 /* 3.662 mV */ #define SHUNT_RESISTOR_DEFAULT 255000 /* 255 mOhm */ -#define CURRENT_LSB_255 62260 /* 62.260 uA */ -#define CURRENT_LSB_250 61039 /* 61.039 uA */ +#define CURRENT_LSB_250 62260 /* 62.260 uA */ +#define CURRENT_LSB_255 61039 /* 61.039 uA */ #define RESISTANCE_LSB 110966 /* 11.0966 Ohm*/ #define RESISTANCE_LSB_LOW 157216 /* 15.7216 Ohm*/ @@ -117,6 +120,7 @@ struct tps23861_data { static struct regmap_config tps23861_regmap_config = { .reg_bits = 8, .val_bits = 8, + .max_register = 0x6f, }; static int tps23861_read_temp(struct tps23861_data *data, long *val) @@ -560,6 +564,15 @@ static int tps23861_probe(struct i2c_client *client) else data->shunt_resistor = SHUNT_RESISTOR_DEFAULT; + if (data->shunt_resistor == SHUNT_RESISTOR_DEFAULT) + regmap_clear_bits(data->regmap, + TPS23861_GENERAL_MASK_1, + TPS23861_CURRENT_SHUNT_MASK); + else + regmap_set_bits(data->regmap, + TPS23861_GENERAL_MASK_1, + TPS23861_CURRENT_SHUNT_MASK); + hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data, &tps23861_chip_info, NULL); diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 281a65d9b44b..10acece9d7b9 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -647,7 +647,7 @@ config I2C_HIGHLANDER config I2C_HISI tristate "HiSilicon I2C controller" - depends on ARM64 || COMPILE_TEST + depends on (ARM64 && ACPI) || COMPILE_TEST help Say Y here if you want to have Hisilicon I2C controller support available on the Kunpeng Server. diff --git a/drivers/i2c/busses/i2c-ali1563.c b/drivers/i2c/busses/i2c-ali1563.c index 4d12e3da12f0..55a9e93fbfeb 100644 --- a/drivers/i2c/busses/i2c-ali1563.c +++ b/drivers/i2c/busses/i2c-ali1563.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * i2c-ali1563.c - i2c driver for the ALi 1563 Southbridge * * Copyright (C) 2004 Patrick Mochel diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c index 7d62cbda6e06..354cf7e45c4a 100644 --- a/drivers/i2c/busses/i2c-altera.c +++ b/drivers/i2c/busses/i2c-altera.c @@ -55,7 +55,7 @@ #define ALTR_I2C_XFER_TIMEOUT (msecs_to_jiffies(250)) /** - * altr_i2c_dev - I2C device context + * struct altr_i2c_dev - I2C device context * @base: pointer to register struct * @msg: pointer to current message * @msg_len: number of bytes transferred in msg @@ -172,7 +172,7 @@ static void altr_i2c_init(struct altr_i2c_dev *idev) altr_i2c_int_enable(idev, ALTR_I2C_ALL_IRQ, false); } -/** +/* * altr_i2c_transfer - On the last byte to be transmitted, send * a Stop bit on the last byte. */ @@ -185,7 +185,7 @@ static void altr_i2c_transfer(struct altr_i2c_dev *idev, u32 data) writel(data, idev->base + ALTR_I2C_TFR_CMD); } -/** +/* * altr_i2c_empty_rx_fifo - Fetch data from RX FIFO until end of * transfer. Send a Stop bit on the last byte. */ @@ -201,9 +201,8 @@ static void altr_i2c_empty_rx_fifo(struct altr_i2c_dev *idev) } } -/** +/* * altr_i2c_fill_tx_fifo - Fill TX FIFO from current message buffer. - * @return: Number of bytes left to transfer. */ static int altr_i2c_fill_tx_fifo(struct altr_i2c_dev *idev) { diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index c1bbc4caeb5c..66aafa7d1123 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -144,7 +144,7 @@ enum cdns_i2c_mode { }; /** - * enum cdns_i2c_slave_mode - Slave state when I2C is operating in slave mode + * enum cdns_i2c_slave_state - Slave state when I2C is operating in slave mode * * @CDNS_I2C_SLAVE_STATE_IDLE: I2C slave idle * @CDNS_I2C_SLAVE_STATE_SEND: I2C slave sending data to master diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index 13be1d678c39..9b08bb5df38d 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -165,7 +165,7 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev) } /** - * i2c_dw_init() - Initialize the designware I2C master hardware + * i2c_dw_init_master() - Initialize the designware I2C master hardware * @dev: device private data * * This functions configures and enables the I2C master. diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index 843b31a0f752..321b2770feab 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -148,7 +148,7 @@ struct i2c_algo_pch_data { /** * struct adapter_info - This structure holds the adapter information for the - PCH i2c controller + * PCH i2c controller * @pch_data: stores a list of i2c_algo_pch_data * @pch_i2c_suspended: specifies whether the system is suspended or not * perhaps with more lines and words. @@ -358,6 +358,7 @@ static void pch_i2c_repstart(struct i2c_algo_pch_data *adap) /** * pch_i2c_writebytes() - write data to I2C bus in normal mode * @i2c_adap: Pointer to the struct i2c_adapter. + * @msgs: Pointer to the i2c message structure. * @last: specifies whether last message or not. * In the case of compound mode it will be 1 for last message, * otherwise 0. diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 99d446763530..f9e1c2ceaac0 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -395,11 +395,9 @@ static int i801_check_post(struct i801_priv *priv, int status) dev_err(&priv->pci_dev->dev, "Transaction timeout\n"); /* try to stop the current command */ dev_dbg(&priv->pci_dev->dev, "Terminating the current operation\n"); - outb_p(inb_p(SMBHSTCNT(priv)) | SMBHSTCNT_KILL, - SMBHSTCNT(priv)); + outb_p(SMBHSTCNT_KILL, SMBHSTCNT(priv)); usleep_range(1000, 2000); - outb_p(inb_p(SMBHSTCNT(priv)) & (~SMBHSTCNT_KILL), - SMBHSTCNT(priv)); + outb_p(0, SMBHSTCNT(priv)); /* Check if it worked */ status = inb_p(SMBHSTSTS(priv)); diff --git a/drivers/i2c/busses/i2c-icy.c b/drivers/i2c/busses/i2c-icy.c index c8c422e9dda4..5dae7cab7260 100644 --- a/drivers/i2c/busses/i2c-icy.c +++ b/drivers/i2c/busses/i2c-icy.c @@ -123,7 +123,6 @@ static int icy_probe(struct zorro_dev *z, { struct icy_i2c *i2c; struct i2c_algo_pcf_data *algo_data; - struct fwnode_handle *new_fwnode; struct i2c_board_info ltc2990_info = { .type = "ltc2990", .swnode = &icy_ltc2990_node, diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c index 30d9e89a3db2..dcca9c2396db 100644 --- a/drivers/i2c/busses/i2c-mpc.c +++ b/drivers/i2c/busses/i2c-mpc.c @@ -19,6 +19,7 @@ #include <linux/clk.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/fsl_devices.h> #include <linux/i2c.h> #include <linux/interrupt.h> @@ -45,6 +46,7 @@ #define CCR_MTX 0x10 #define CCR_TXAK 0x08 #define CCR_RSTA 0x04 +#define CCR_RSVD 0x02 #define CSR_MCF 0x80 #define CSR_MAAS 0x40 @@ -97,7 +99,7 @@ struct mpc_i2c { u32 block; int rc; int expect_rxack; - + bool has_errata_A004447; }; struct mpc_i2c_divider { @@ -136,6 +138,75 @@ static void mpc_i2c_fixup(struct mpc_i2c *i2c) } } +static int i2c_mpc_wait_sr(struct mpc_i2c *i2c, int mask) +{ + void __iomem *addr = i2c->base + MPC_I2C_SR; + u8 val; + + return readb_poll_timeout(addr, val, val & mask, 0, 100); +} + +/* + * Workaround for Erratum A004447. From the P2040CE Rev Q + * + * 1. Set up the frequency divider and sampling rate. + * 2. I2CCR - a0h + * 3. Poll for I2CSR[MBB] to get set. + * 4. If I2CSR[MAL] is set (an indication that SDA is stuck low), then go to + * step 5. If MAL is not set, then go to step 13. + * 5. I2CCR - 00h + * 6. I2CCR - 22h + * 7. I2CCR - a2h + * 8. Poll for I2CSR[MBB] to get set. + * 9. Issue read to I2CDR. + * 10. Poll for I2CSR[MIF] to be set. + * 11. I2CCR - 82h + * 12. Workaround complete. Skip the next steps. + * 13. Issue read to I2CDR. + * 14. Poll for I2CSR[MIF] to be set. + * 15. I2CCR - 80h + */ +static void mpc_i2c_fixup_A004447(struct mpc_i2c *i2c) +{ + int ret; + u32 val; + + writeccr(i2c, CCR_MEN | CCR_MSTA); + ret = i2c_mpc_wait_sr(i2c, CSR_MBB); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MBB\n"); + return; + } + + val = readb(i2c->base + MPC_I2C_SR); + + if (val & CSR_MAL) { + writeccr(i2c, 0x00); + writeccr(i2c, CCR_MSTA | CCR_RSVD); + writeccr(i2c, CCR_MEN | CCR_MSTA | CCR_RSVD); + ret = i2c_mpc_wait_sr(i2c, CSR_MBB); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MBB\n"); + return; + } + val = readb(i2c->base + MPC_I2C_DR); + ret = i2c_mpc_wait_sr(i2c, CSR_MIF); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MIF\n"); + return; + } + writeccr(i2c, CCR_MEN | CCR_RSVD); + } else { + val = readb(i2c->base + MPC_I2C_DR); + ret = i2c_mpc_wait_sr(i2c, CSR_MIF); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MIF\n"); + return; + } + writeccr(i2c, CCR_MEN); + } +} + #if defined(CONFIG_PPC_MPC52xx) || defined(CONFIG_PPC_MPC512x) static const struct mpc_i2c_divider mpc_i2c_dividers_52xx[] = { {20, 0x20}, {22, 0x21}, {24, 0x22}, {26, 0x23}, @@ -670,7 +741,10 @@ static int fsl_i2c_bus_recovery(struct i2c_adapter *adap) { struct mpc_i2c *i2c = i2c_get_adapdata(adap); - mpc_i2c_fixup(i2c); + if (i2c->has_errata_A004447) + mpc_i2c_fixup_A004447(i2c); + else + mpc_i2c_fixup(i2c); return 0; } @@ -767,6 +841,9 @@ static int fsl_i2c_probe(struct platform_device *op) } dev_info(i2c->dev, "timeout %u us\n", mpc_ops.timeout * 1000000 / HZ); + if (of_property_read_bool(op->dev.of_node, "fsl,i2c-erratum-a004447")) + i2c->has_errata_A004447 = true; + i2c->adap = mpc_ops; scnprintf(i2c->adap.name, sizeof(i2c->adap.name), "MPC adapter (%s)", of_node_full_name(op->dev.of_node)); diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 5ddfa4e56ee2..4e9fb6b44436 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -479,6 +479,11 @@ static void mtk_i2c_clock_disable(struct mtk_i2c *i2c) static void mtk_i2c_init_hw(struct mtk_i2c *i2c) { u16 control_reg; + u16 intr_stat_reg; + + mtk_i2c_writew(i2c, I2C_CHN_CLR_FLAG, OFFSET_START); + intr_stat_reg = mtk_i2c_readw(i2c, OFFSET_INTR_STAT); + mtk_i2c_writew(i2c, intr_stat_reg, OFFSET_INTR_STAT); if (i2c->dev_comp->apdma_sync) { writel(I2C_DMA_WARM_RST, i2c->pdmabase + OFFSET_RST); diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c index dc77e1c4e80f..a2d12a5b1c34 100644 --- a/drivers/i2c/busses/i2c-nomadik.c +++ b/drivers/i2c/busses/i2c-nomadik.c @@ -159,7 +159,7 @@ struct i2c_nmk_client { * @clk_freq: clock frequency for the operation mode * @tft: Tx FIFO Threshold in bytes * @rft: Rx FIFO Threshold in bytes - * @timeout Slave response timeout (ms) + * @timeout: Slave response timeout (ms) * @sm: speed mode * @stop: stop condition. * @xfer_complete: acknowledge completion for a I2C message. diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index 273222e38056..a0af027db04c 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -250,7 +250,7 @@ static irqreturn_t ocores_isr(int irq, void *dev_id) } /** - * Process timeout event + * ocores_process_timeout() - Process timeout event * @i2c: ocores I2C device instance */ static void ocores_process_timeout(struct ocores_i2c *i2c) @@ -264,7 +264,7 @@ static void ocores_process_timeout(struct ocores_i2c *i2c) } /** - * Wait until something change in a given register + * ocores_wait() - Wait until something change in a given register * @i2c: ocores I2C device instance * @reg: register to query * @mask: bitmask to apply on register value @@ -296,7 +296,7 @@ static int ocores_wait(struct ocores_i2c *i2c, } /** - * Wait until is possible to process some data + * ocores_poll_wait() - Wait until is possible to process some data * @i2c: ocores I2C device instance * * Used when the device is in polling mode (interrupts disabled). @@ -334,7 +334,7 @@ static int ocores_poll_wait(struct ocores_i2c *i2c) } /** - * It handles an IRQ-less transfer + * ocores_process_polling() - It handles an IRQ-less transfer * @i2c: ocores I2C device instance * * Even if IRQ are disabled, the I2C OpenCore IP behavior is exactly the same diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index 8c4ec7f13f5a..50f21cdbe90d 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -138,7 +138,7 @@ static inline void i2c_pnx_arm_timer(struct i2c_pnx_algo_data *alg_data) /** * i2c_pnx_start - start a device * @slave_addr: slave address - * @adap: pointer to adapter structure + * @alg_data: pointer to local driver data structure * * Generate a START signal in the desired mode. */ @@ -194,7 +194,7 @@ static int i2c_pnx_start(unsigned char slave_addr, /** * i2c_pnx_stop - stop a device - * @adap: pointer to I2C adapter structure + * @alg_data: pointer to local driver data structure * * Generate a STOP signal to terminate the master transaction. */ @@ -223,7 +223,7 @@ static void i2c_pnx_stop(struct i2c_pnx_algo_data *alg_data) /** * i2c_pnx_master_xmit - transmit data to slave - * @adap: pointer to I2C adapter structure + * @alg_data: pointer to local driver data structure * * Sends one byte of data to the slave */ @@ -293,7 +293,7 @@ static int i2c_pnx_master_xmit(struct i2c_pnx_algo_data *alg_data) /** * i2c_pnx_master_rcv - receive data from slave - * @adap: pointer to I2C adapter structure + * @alg_data: pointer to local driver data structure * * Reads one byte data from the slave */ diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 214b4c913a13..6d635a7c104c 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -100,7 +100,7 @@ static const struct geni_i2c_err_log gi2c_log[] = { [GP_IRQ0] = {-EIO, "Unknown I2C err GP_IRQ0"}, [NACK] = {-ENXIO, "NACK: slv unresponsive, check its power/reset-ln"}, [GP_IRQ2] = {-EIO, "Unknown I2C err GP IRQ2"}, - [BUS_PROTO] = {-EPROTO, "Bus proto err, noisy/unepxected start/stop"}, + [BUS_PROTO] = {-EPROTO, "Bus proto err, noisy/unexpected start/stop"}, [ARB_LOST] = {-EAGAIN, "Bus arbitration lost, clock line undriveable"}, [GP_IRQ5] = {-EIO, "Unknown I2C err GP IRQ5"}, [GENI_OVERRUN] = {-EIO, "Cmd overrun, check GENI cmd-state machine"}, @@ -650,6 +650,14 @@ static int geni_i2c_remove(struct platform_device *pdev) return 0; } +static void geni_i2c_shutdown(struct platform_device *pdev) +{ + struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev); + + /* Make client i2c transfers start failing */ + i2c_mark_adapter_suspended(&gi2c->adap); +} + static int __maybe_unused geni_i2c_runtime_suspend(struct device *dev) { int ret; @@ -690,6 +698,8 @@ static int __maybe_unused geni_i2c_suspend_noirq(struct device *dev) { struct geni_i2c_dev *gi2c = dev_get_drvdata(dev); + i2c_mark_adapter_suspended(&gi2c->adap); + if (!gi2c->suspended) { geni_i2c_runtime_suspend(dev); pm_runtime_disable(dev); @@ -699,8 +709,16 @@ static int __maybe_unused geni_i2c_suspend_noirq(struct device *dev) return 0; } +static int __maybe_unused geni_i2c_resume_noirq(struct device *dev) +{ + struct geni_i2c_dev *gi2c = dev_get_drvdata(dev); + + i2c_mark_adapter_resumed(&gi2c->adap); + return 0; +} + static const struct dev_pm_ops geni_i2c_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(geni_i2c_suspend_noirq, NULL) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(geni_i2c_suspend_noirq, geni_i2c_resume_noirq) SET_RUNTIME_PM_OPS(geni_i2c_runtime_suspend, geni_i2c_runtime_resume, NULL) }; @@ -714,6 +732,7 @@ MODULE_DEVICE_TABLE(of, geni_i2c_dt_match); static struct platform_driver geni_i2c_driver = { .probe = geni_i2c_probe, .remove = geni_i2c_remove, + .shutdown = geni_i2c_shutdown, .driver = { .name = "geni_i2c", .pm = &geni_i2c_pm_ops, diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index ab928613afba..4d82761e1585 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -480,7 +480,10 @@ static int i2c_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat) * forces us to send a new START * when we change direction */ + dev_dbg(i2c->dev, + "missing START before write->read\n"); s3c24xx_i2c_stop(i2c, -EINVAL); + break; } goto retry_write; diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c index 3ae6ca21a02c..2d2e630fd438 100644 --- a/drivers/i2c/busses/i2c-sh_mobile.c +++ b/drivers/i2c/busses/i2c-sh_mobile.c @@ -807,7 +807,7 @@ static const struct sh_mobile_dt_config r8a7740_dt_config = { static const struct of_device_id sh_mobile_i2c_dt_ids[] = { { .compatible = "renesas,iic-r8a73a4", .data = &fast_clock_dt_config }, { .compatible = "renesas,iic-r8a7740", .data = &r8a7740_dt_config }, - { .compatible = "renesas,iic-r8a774c0", .data = &fast_clock_dt_config }, + { .compatible = "renesas,iic-r8a774c0", .data = &v2_freq_calc_dt_config }, { .compatible = "renesas,iic-r8a7790", .data = &v2_freq_calc_dt_config }, { .compatible = "renesas,iic-r8a7791", .data = &v2_freq_calc_dt_config }, { .compatible = "renesas,iic-r8a7792", .data = &v2_freq_calc_dt_config }, diff --git a/drivers/i2c/busses/i2c-st.c b/drivers/i2c/busses/i2c-st.c index faa81a95551f..88482316d22a 100644 --- a/drivers/i2c/busses/i2c-st.c +++ b/drivers/i2c/busses/i2c-st.c @@ -524,7 +524,7 @@ static void st_i2c_handle_write(struct st_i2c_dev *i2c_dev) } /** - * st_i2c_handle_write() - Handle FIFO enmpty interrupt in case of read + * st_i2c_handle_read() - Handle FIFO empty interrupt in case of read * @i2c_dev: Controller's private data */ static void st_i2c_handle_read(struct st_i2c_dev *i2c_dev) @@ -558,7 +558,7 @@ static void st_i2c_handle_read(struct st_i2c_dev *i2c_dev) } /** - * st_i2c_isr() - Interrupt routine + * st_i2c_isr_thread() - Interrupt routine * @irq: interrupt number * @data: Controller's private data */ diff --git a/drivers/i2c/busses/i2c-stm32f4.c b/drivers/i2c/busses/i2c-stm32f4.c index 4933fc8ce3fd..eebce7ecef25 100644 --- a/drivers/i2c/busses/i2c-stm32f4.c +++ b/drivers/i2c/busses/i2c-stm32f4.c @@ -313,7 +313,7 @@ static int stm32f4_i2c_wait_free_bus(struct stm32f4_i2c_dev *i2c_dev) } /** - * stm32f4_i2c_write_ byte() - Write a byte in the data register + * stm32f4_i2c_write_byte() - Write a byte in the data register * @i2c_dev: Controller's private data * @byte: Data to write in the register */ diff --git a/drivers/i2c/busses/i2c-tegra-bpmp.c b/drivers/i2c/busses/i2c-tegra-bpmp.c index 3680d608698b..ec0c7cad4240 100644 --- a/drivers/i2c/busses/i2c-tegra-bpmp.c +++ b/drivers/i2c/busses/i2c-tegra-bpmp.c @@ -65,7 +65,7 @@ static void tegra_bpmp_xlate_flags(u16 flags, u16 *out) *out |= SERIALI2C_RECV_LEN; } -/** +/* * The serialized I2C format is simply the following: * [addr little-endian][flags little-endian][len little-endian][data if write] * [addr little-endian][flags little-endian][len little-endian][data if write] @@ -109,7 +109,7 @@ static void tegra_bpmp_serialize_i2c_msg(struct tegra_bpmp_i2c *i2c, request->xfer.data_size = pos; } -/** +/* * The data in the BPMP -> CPU direction is composed of sequential blocks for * those messages that have I2C_M_RD. So, for example, if you have: * diff --git a/drivers/i2c/muxes/i2c-arb-gpio-challenge.c b/drivers/i2c/muxes/i2c-arb-gpio-challenge.c index 6dc88902c189..1c78657631f4 100644 --- a/drivers/i2c/muxes/i2c-arb-gpio-challenge.c +++ b/drivers/i2c/muxes/i2c-arb-gpio-challenge.c @@ -34,7 +34,7 @@ struct i2c_arbitrator_data { }; -/** +/* * i2c_arbitrator_select - claim the I2C bus * * Use the GPIO-based signalling protocol; return -EBUSY if we fail. @@ -77,7 +77,7 @@ static int i2c_arbitrator_select(struct i2c_mux_core *muxc, u32 chan) return -EBUSY; } -/** +/* * i2c_arbitrator_deselect - release the I2C bus * * Release the I2C bus using the GPIO-based signalling protocol. diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 9d3952b4674f..a27db78ea13e 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -771,6 +771,13 @@ static int ad7124_of_parse_channel_config(struct iio_dev *indio_dev, if (ret) goto err; + if (channel >= indio_dev->num_channels) { + dev_err(indio_dev->dev.parent, + "Channel index >= number of channels\n"); + ret = -EINVAL; + goto err; + } + ret = of_property_read_u32_array(child, "diff-channels", ain, 2); if (ret) @@ -850,6 +857,11 @@ static int ad7124_setup(struct ad7124_state *st) return ret; } +static void ad7124_reg_disable(void *r) +{ + regulator_disable(r); +} + static int ad7124_probe(struct spi_device *spi) { const struct ad7124_chip_info *info; @@ -895,17 +907,20 @@ static int ad7124_probe(struct spi_device *spi) ret = regulator_enable(st->vref[i]); if (ret) return ret; + + ret = devm_add_action_or_reset(&spi->dev, ad7124_reg_disable, + st->vref[i]); + if (ret) + return ret; } st->mclk = devm_clk_get(&spi->dev, "mclk"); - if (IS_ERR(st->mclk)) { - ret = PTR_ERR(st->mclk); - goto error_regulator_disable; - } + if (IS_ERR(st->mclk)) + return PTR_ERR(st->mclk); ret = clk_prepare_enable(st->mclk); if (ret < 0) - goto error_regulator_disable; + return ret; ret = ad7124_soft_reset(st); if (ret < 0) @@ -935,11 +950,6 @@ error_remove_trigger: ad_sd_cleanup_buffer_and_trigger(indio_dev); error_clk_disable_unprepare: clk_disable_unprepare(st->mclk); -error_regulator_disable: - for (i = ARRAY_SIZE(st->vref) - 1; i >= 0; i--) { - if (!IS_ERR_OR_NULL(st->vref[i])) - regulator_disable(st->vref[i]); - } return ret; } @@ -948,17 +958,11 @@ static int ad7124_remove(struct spi_device *spi) { struct iio_dev *indio_dev = spi_get_drvdata(spi); struct ad7124_state *st = iio_priv(indio_dev); - int i; iio_device_unregister(indio_dev); ad_sd_cleanup_buffer_and_trigger(indio_dev); clk_disable_unprepare(st->mclk); - for (i = ARRAY_SIZE(st->vref) - 1; i >= 0; i--) { - if (!IS_ERR_OR_NULL(st->vref[i])) - regulator_disable(st->vref[i]); - } - return 0; } diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 2ed580521d81..1141cc13a124 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -912,7 +912,7 @@ static int ad7192_probe(struct spi_device *spi) { struct ad7192_state *st; struct iio_dev *indio_dev; - int ret, voltage_uv = 0; + int ret; if (!spi->irq) { dev_err(&spi->dev, "no IRQ?\n"); @@ -949,15 +949,12 @@ static int ad7192_probe(struct spi_device *spi) goto error_disable_avdd; } - voltage_uv = regulator_get_voltage(st->avdd); - - if (voltage_uv > 0) { - st->int_vref_mv = voltage_uv / 1000; - } else { - ret = voltage_uv; + ret = regulator_get_voltage(st->avdd); + if (ret < 0) { dev_err(&spi->dev, "Device tree error, reference voltage undefined\n"); goto error_disable_avdd; } + st->int_vref_mv = ret / 1000; spi_set_drvdata(spi, indio_dev); st->chip_info = of_device_get_match_data(&spi->dev); @@ -1014,7 +1011,9 @@ static int ad7192_probe(struct spi_device *spi) return 0; error_disable_clk: - clk_disable_unprepare(st->mclk); + if (st->clock_sel == AD7192_CLK_EXT_MCLK1_2 || + st->clock_sel == AD7192_CLK_EXT_MCLK2) + clk_disable_unprepare(st->mclk); error_remove_trigger: ad_sd_cleanup_buffer_and_trigger(indio_dev); error_disable_dvdd: @@ -1031,7 +1030,9 @@ static int ad7192_remove(struct spi_device *spi) struct ad7192_state *st = iio_priv(indio_dev); iio_device_unregister(indio_dev); - clk_disable_unprepare(st->mclk); + if (st->clock_sel == AD7192_CLK_EXT_MCLK1_2 || + st->clock_sel == AD7192_CLK_EXT_MCLK2) + clk_disable_unprepare(st->mclk); ad_sd_cleanup_buffer_and_trigger(indio_dev); regulator_disable(st->dvdd); diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index c945f1349623..60f21fed6dcb 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -167,6 +167,10 @@ struct ad7768_state { * transfer buffers to live in their own cache lines. */ union { + struct { + __be32 chan; + s64 timestamp; + } scan; __be32 d32; u8 d8[2]; } data ____cacheline_aligned; @@ -469,11 +473,11 @@ static irqreturn_t ad7768_trigger_handler(int irq, void *p) mutex_lock(&st->lock); - ret = spi_read(st->spi, &st->data.d32, 3); + ret = spi_read(st->spi, &st->data.scan.chan, 3); if (ret < 0) goto err_unlock; - iio_push_to_buffers_with_timestamp(indio_dev, &st->data.d32, + iio_push_to_buffers_with_timestamp(indio_dev, &st->data.scan, iio_get_time_ns(indio_dev)); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c index 5e980a06258e..440ef4c7be07 100644 --- a/drivers/iio/adc/ad7793.c +++ b/drivers/iio/adc/ad7793.c @@ -279,6 +279,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, id &= AD7793_ID_MASK; if (id != st->chip_info->id) { + ret = -ENODEV; dev_err(&st->sd.spi->dev, "device ID query failed\n"); goto out; } diff --git a/drivers/iio/adc/ad7923.c b/drivers/iio/adc/ad7923.c index 9a649745cd0a..069b561ee768 100644 --- a/drivers/iio/adc/ad7923.c +++ b/drivers/iio/adc/ad7923.c @@ -59,8 +59,10 @@ struct ad7923_state { /* * DMA (thus cache coherency maintenance) requires the * transfer buffers to live in their own cache lines. + * Ensure rx_buf can be directly used in iio_push_to_buffers_with_timetamp + * Length = 8 channels + 4 extra for 8 byte timestamp */ - __be16 rx_buf[4] ____cacheline_aligned; + __be16 rx_buf[12] ____cacheline_aligned; __be16 tx_buf[4]; }; diff --git a/drivers/iio/dac/ad5770r.c b/drivers/iio/dac/ad5770r.c index 7ab2ccf90863..8107f7bbbe3c 100644 --- a/drivers/iio/dac/ad5770r.c +++ b/drivers/iio/dac/ad5770r.c @@ -524,23 +524,29 @@ static int ad5770r_channel_config(struct ad5770r_state *st) device_for_each_child_node(&st->spi->dev, child) { ret = fwnode_property_read_u32(child, "num", &num); if (ret) - return ret; - if (num >= AD5770R_MAX_CHANNELS) - return -EINVAL; + goto err_child_out; + if (num >= AD5770R_MAX_CHANNELS) { + ret = -EINVAL; + goto err_child_out; + } ret = fwnode_property_read_u32_array(child, "adi,range-microamp", tmp, 2); if (ret) - return ret; + goto err_child_out; min = tmp[0] / 1000; max = tmp[1] / 1000; ret = ad5770r_store_output_range(st, min, max, num); if (ret) - return ret; + goto err_child_out; } + return 0; + +err_child_out: + fwnode_handle_put(child); return ret; } diff --git a/drivers/iio/gyro/fxas21002c_core.c b/drivers/iio/gyro/fxas21002c_core.c index 1a20c6b88e7d..645461c70454 100644 --- a/drivers/iio/gyro/fxas21002c_core.c +++ b/drivers/iio/gyro/fxas21002c_core.c @@ -399,6 +399,7 @@ static int fxas21002c_temp_get(struct fxas21002c_data *data, int *val) ret = regmap_field_read(data->regmap_fields[F_TEMP], &temp); if (ret < 0) { dev_err(dev, "failed to read temp: %d\n", ret); + fxas21002c_pm_put(data); goto data_unlock; } @@ -432,6 +433,7 @@ static int fxas21002c_axis_get(struct fxas21002c_data *data, &axis_be, sizeof(axis_be)); if (ret < 0) { dev_err(dev, "failed to read axis: %d: %d\n", index, ret); + fxas21002c_pm_put(data); goto data_unlock; } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index d5e15a8c870d..64e4be1cbec7 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3248,6 +3248,11 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs) goto err_free_attr; } + if (!rdma_is_port_valid(uobj->context->device, cmd.flow_attr.port)) { + err = -EINVAL; + goto err_uobj; + } + qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs); if (!qp) { err = -EINVAL; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 22898d97ecbd..230a6ae0ab5a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -581,12 +581,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT; props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD; - if (!mlx4_is_slave(dev->dev)) - err = mlx4_get_internal_clock_params(dev->dev, &clock_params); - if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) { resp.response_length += sizeof(resp.hca_core_clock_offset); - if (!err && !mlx4_is_slave(dev->dev)) { + if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) { resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET; resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE; } @@ -1702,9 +1699,6 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct mlx4_dev *dev = (to_mdev(qp->device))->dev; int is_bonded = mlx4_is_bonded(dev); - if (!rdma_is_port_valid(qp->device, flow_attr->port)) - return ERR_PTR(-EINVAL); - if (flow_attr->flags & ~IB_FLOW_ATTR_FLAGS_DONT_TRAP) return ERR_PTR(-EOPNOTSUPP); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index eb92cefffd77..9ce01f729673 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -849,15 +849,14 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_udata *udata) ib_umem_release(cq->buf.umem); } -static void init_cq_frag_buf(struct mlx5_ib_cq *cq, - struct mlx5_ib_cq_buf *buf) +static void init_cq_frag_buf(struct mlx5_ib_cq_buf *buf) { int i; void *cqe; struct mlx5_cqe64 *cqe64; for (i = 0; i < buf->nent; i++) { - cqe = get_cqe(cq, i); + cqe = mlx5_frag_buf_get_wqe(&buf->fbc, i); cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64; cqe64->op_own = MLX5_CQE_INVALID << 4; } @@ -883,7 +882,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (err) goto err_db; - init_cq_frag_buf(cq, &cq->buf); + init_cq_frag_buf(&cq->buf); *inlen = MLX5_ST_SZ_BYTES(create_cq_in) + MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * @@ -1184,7 +1183,7 @@ static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (err) goto ex; - init_cq_frag_buf(cq, cq->resize_buf); + init_cq_frag_buf(cq->resize_buf); return 0; diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 61475b571531..7af4df7a6823 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page { struct ib_umem *umem; unsigned long user_virt; int refcnt; + struct mm_struct *mm; }; int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, @@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, mutex_lock(&context->db_page_mutex); list_for_each_entry(page, &context->db_page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if ((current->mm == page->mm) && + (page->user_virt == (virt & PAGE_MASK))) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, kfree(page); goto out; } + mmgrab(current->mm); + page->mm = current->mm; list_add(&page->list, &context->db_page_list); @@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) if (!--db->u.user_page->refcnt) { list_del(&db->u.user_page->list); + mmdrop(db->u.user_page->mm); ib_umem_release(db->u.user_page->umem); kfree(db->u.user_page); } diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index 2fc6a60c4e77..18ee2f293825 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -1194,9 +1194,8 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp, goto free_ucmd; } - if (flow_attr->port > dev->num_ports || - (flow_attr->flags & - ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP | IB_FLOW_ATTR_FLAGS_EGRESS))) { + if (flow_attr->flags & + ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP | IB_FLOW_ATTR_FLAGS_EGRESS)) { err = -EINVAL; goto free_ucmd; } @@ -2134,6 +2133,12 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)( if (err) goto end; + if (obj->ns_type == MLX5_FLOW_NAMESPACE_FDB && + mlx5_eswitch_mode(dev->mdev) != MLX5_ESWITCH_OFFLOADS) { + err = -EINVAL; + goto end; + } + uobj->object = obj; obj->mdev = dev->mdev; atomic_set(&obj->usecnt, 0); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 4388afeff251..425423dfac72 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -743,10 +743,10 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) / MLX5_IB_UMR_OCTOWORD; ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT; - if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) && + if ((dev->mdev->profile.mask & MLX5_PROF_MASK_MR_CACHE) && !dev->is_rep && mlx5_core_is_pf(dev->mdev) && mlx5_ib_can_load_pas_with_umr(dev, 0)) - ent->limit = dev->mdev->profile->mr_cache[i].limit; + ent->limit = dev->mdev->profile.mr_cache[i].limit; else ent->limit = 0; spin_lock_irq(&ent->lock); @@ -1940,8 +1940,8 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) mlx5r_deref_wait_odp_mkey(&mr->mmkey); if (ibmr->type == IB_MR_TYPE_INTEGRITY) { - xa_cmpxchg(&dev->sig_mrs, mlx5_base_mkey(mr->mmkey.key), ibmr, - NULL, GFP_KERNEL); + xa_cmpxchg(&dev->sig_mrs, mlx5_base_mkey(mr->mmkey.key), + mr->sig, NULL, GFP_KERNEL); if (mr->mtt_mr) { rc = mlx5_ib_dereg_mr(&mr->mtt_mr->ibmr, NULL); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index d5a90a66b45c..5b05cf3837da 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -163,6 +163,7 @@ static size_t ipoib_get_size(const struct net_device *dev) static struct rtnl_link_ops ipoib_link_ops __read_mostly = { .kind = "ipoib", + .netns_refund = true, .maxtype = IFLA_IPOIB_MAX, .policy = ipoib_policy, .priv_size = sizeof(struct ipoib_dev_priv), diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index d1591a28b743..8f385f9c2dd3 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2020-2021, The Linux Foundation. All rights reserved. */ #include <asm/div64.h> @@ -205,6 +205,7 @@ struct bcm_voter *of_bcm_voter_get(struct device *dev, const char *name) } mutex_unlock(&bcm_voter_lock); + of_node_put(node); return voter; } EXPORT_SYMBOL_GPL(of_bcm_voter_get); @@ -362,6 +363,7 @@ static const struct of_device_id bcm_voter_of_match[] = { { .compatible = "qcom,bcm-voter" }, { } }; +MODULE_DEVICE_TABLE(of, bcm_voter_of_match); static struct platform_driver qcom_icc_bcm_voter_driver = { .probe = qcom_icc_bcm_voter_probe, diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 80e8e1916dd1..3ac42bbdefc6 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -884,7 +884,7 @@ static inline u64 build_inv_address(u64 address, size_t size) * The msb-bit must be clear on the address. Just set all the * lower bits. */ - address |= 1ull << (msb_diff - 1); + address |= (1ull << msb_diff) - 1; } /* Clear bits 11:0 */ @@ -1714,6 +1714,8 @@ static void amd_iommu_probe_finalize(struct device *dev) domain = iommu_get_domain_for_dev(dev); if (domain->type == IOMMU_DOMAIN_DMA) iommu_setup_dma_ops(dev, IOVA_START_PFN << PAGE_SHIFT, 0); + else + set_dma_ops(dev, NULL); } static void amd_iommu_release_device(struct device *dev) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 1757ac1e1623..84057cb9596c 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1142,7 +1142,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) err = iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL); if (err) - goto err_unmap; + goto err_sysfs; } drhd->iommu = iommu; @@ -1150,6 +1150,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) return 0; +err_sysfs: + iommu_device_sysfs_remove(&iommu->iommu); err_unmap: unmap_iommu(iommu); error_free_seq_id: diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 708f430af1c4..be35284a2016 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2525,9 +2525,9 @@ static int domain_setup_first_level(struct intel_iommu *iommu, struct device *dev, u32 pasid) { - int flags = PASID_FLAG_SUPERVISOR_MODE; struct dma_pte *pgd = domain->pgd; int agaw, level; + int flags = 0; /* * Skip top levels of page tables for iommu which has @@ -2543,7 +2543,10 @@ static int domain_setup_first_level(struct intel_iommu *iommu, if (level != 4 && level != 5) return -EINVAL; - flags |= (level == 5) ? PASID_FLAG_FL5LP : 0; + if (pasid != PASID_RID2PASID) + flags |= PASID_FLAG_SUPERVISOR_MODE; + if (level == 5) + flags |= PASID_FLAG_FL5LP; if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED) flags |= PASID_FLAG_PAGE_SNOOP; @@ -4606,6 +4609,8 @@ static int auxiliary_link_device(struct dmar_domain *domain, if (!sinfo) { sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC); + if (!sinfo) + return -ENOMEM; sinfo->domain = domain; sinfo->pdev = dev; list_add(&sinfo->link_phys, &info->subdevices); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 72646bafc52f..72dc84821dad 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -699,7 +699,8 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, * Since it is a second level only translation setup, we should * set SRE bit as well (addresses are expected to be GPAs). */ - pasid_set_sre(pte); + if (pasid != PASID_RID2PASID) + pasid_set_sre(pte); pasid_set_present(pte); pasid_flush_caches(iommu, pte, pasid, did); diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 7c02481a81b4..c6e5ee4d9cef 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1136,6 +1136,7 @@ static struct virtio_device_id id_table[] = { { VIRTIO_ID_IOMMU, VIRTIO_DEV_ANY_ID }, { 0 }, }; +MODULE_DEVICE_TABLE(virtio, id_table); static struct virtio_driver virtio_iommu_drv = { .driver.name = KBUILD_MODNAME, diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 37a23aa6de37..66d623f91678 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -642,11 +642,45 @@ static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs) nmi_exit(); } +static u32 do_read_iar(struct pt_regs *regs) +{ + u32 iar; + + if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) { + u64 pmr; + + /* + * We were in a context with IRQs disabled. However, the + * entry code has set PMR to a value that allows any + * interrupt to be acknowledged, and not just NMIs. This can + * lead to surprising effects if the NMI has been retired in + * the meantime, and that there is an IRQ pending. The IRQ + * would then be taken in NMI context, something that nobody + * wants to debug twice. + * + * Until we sort this, drop PMR again to a level that will + * actually only allow NMIs before reading IAR, and then + * restore it to what it was. + */ + pmr = gic_read_pmr(); + gic_pmr_mask_irqs(); + isb(); + + iar = gic_read_iar(); + + gic_write_pmr(pmr); + } else { + iar = gic_read_iar(); + } + + return iar; +} + static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) { u32 irqnr; - irqnr = gic_read_iar(); + irqnr = do_read_iar(regs); /* Check for special IDs first */ if ((irqnr >= 1020 && irqnr <= 1023)) diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index ee925b58bbce..2a1ddd47a096 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -1100,7 +1100,6 @@ nj_probe(struct pci_dev *pdev, const struct pci_device_id *ent) card->typ = NETJET_S_TJ300; card->base = pci_resource_start(pdev, 0); - card->irq = pdev->irq; pci_set_drvdata(pdev, card); err = setup_instance(card); if (err) diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 0a4551e165ab..5fc989a6d452 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -364,7 +364,6 @@ struct cached_dev { /* The rest of this all shows up in sysfs */ unsigned int sequential_cutoff; - unsigned int readahead; unsigned int io_disable:1; unsigned int verify:1; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 29c231758293..6d1de889baeb 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -880,9 +880,9 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, struct bio *bio, unsigned int sectors) { int ret = MAP_CONTINUE; - unsigned int reada = 0; struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); struct bio *miss, *cache_bio; + unsigned int size_limit; s->cache_missed = 1; @@ -892,14 +892,10 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, goto out_submit; } - if (!(bio->bi_opf & REQ_RAHEAD) && - !(bio->bi_opf & (REQ_META|REQ_PRIO)) && - s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA) - reada = min_t(sector_t, dc->readahead >> 9, - get_capacity(bio->bi_bdev->bd_disk) - - bio_end_sector(bio)); - - s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada); + /* Limitation for valid replace key size and cache_bio bvecs number */ + size_limit = min_t(unsigned int, BIO_MAX_VECS * PAGE_SECTORS, + (1 << KEY_SIZE_BITS) - 1); + s->insert_bio_sectors = min3(size_limit, sectors, bio_sectors(bio)); s->iop.replace_key = KEY(s->iop.inode, bio->bi_iter.bi_sector + s->insert_bio_sectors, @@ -911,7 +907,8 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, s->iop.replace = true; - miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split); + miss = bio_next_split(bio, s->insert_bio_sectors, GFP_NOIO, + &s->d->bio_split); /* btree_search_recurse()'s btree iterator is no good anymore */ ret = miss == bio ? MAP_DONE : -EINTR; @@ -933,9 +930,6 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, if (bch_bio_alloc_pages(cache_bio, __GFP_NOWARN|GFP_NOIO)) goto out_put; - if (reada) - bch_mark_cache_readahead(s->iop.c, s->d); - s->cache_miss = miss; s->iop.bio = cache_bio; bio_get(cache_bio); diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c index 503aafe188dc..4c7ee5fedb9d 100644 --- a/drivers/md/bcache/stats.c +++ b/drivers/md/bcache/stats.c @@ -46,7 +46,6 @@ read_attribute(cache_misses); read_attribute(cache_bypass_hits); read_attribute(cache_bypass_misses); read_attribute(cache_hit_ratio); -read_attribute(cache_readaheads); read_attribute(cache_miss_collisions); read_attribute(bypassed); @@ -64,7 +63,6 @@ SHOW(bch_stats) DIV_SAFE(var(cache_hits) * 100, var(cache_hits) + var(cache_misses))); - var_print(cache_readaheads); var_print(cache_miss_collisions); sysfs_hprint(bypassed, var(sectors_bypassed) << 9); #undef var @@ -86,7 +84,6 @@ static struct attribute *bch_stats_files[] = { &sysfs_cache_bypass_hits, &sysfs_cache_bypass_misses, &sysfs_cache_hit_ratio, - &sysfs_cache_readaheads, &sysfs_cache_miss_collisions, &sysfs_bypassed, NULL @@ -113,7 +110,6 @@ void bch_cache_accounting_clear(struct cache_accounting *acc) acc->total.cache_misses = 0; acc->total.cache_bypass_hits = 0; acc->total.cache_bypass_misses = 0; - acc->total.cache_readaheads = 0; acc->total.cache_miss_collisions = 0; acc->total.sectors_bypassed = 0; } @@ -145,7 +141,6 @@ static void scale_stats(struct cache_stats *stats, unsigned long rescale_at) scale_stat(&stats->cache_misses); scale_stat(&stats->cache_bypass_hits); scale_stat(&stats->cache_bypass_misses); - scale_stat(&stats->cache_readaheads); scale_stat(&stats->cache_miss_collisions); scale_stat(&stats->sectors_bypassed); } @@ -168,7 +163,6 @@ static void scale_accounting(struct timer_list *t) move_stat(cache_misses); move_stat(cache_bypass_hits); move_stat(cache_bypass_misses); - move_stat(cache_readaheads); move_stat(cache_miss_collisions); move_stat(sectors_bypassed); @@ -209,14 +203,6 @@ void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d, mark_cache_stats(&c->accounting.collector, hit, bypass); } -void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d) -{ - struct cached_dev *dc = container_of(d, struct cached_dev, disk); - - atomic_inc(&dc->accounting.collector.cache_readaheads); - atomic_inc(&c->accounting.collector.cache_readaheads); -} - void bch_mark_cache_miss_collision(struct cache_set *c, struct bcache_device *d) { struct cached_dev *dc = container_of(d, struct cached_dev, disk); diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h index abfaabf7e7fc..ca4f435f7216 100644 --- a/drivers/md/bcache/stats.h +++ b/drivers/md/bcache/stats.h @@ -7,7 +7,6 @@ struct cache_stat_collector { atomic_t cache_misses; atomic_t cache_bypass_hits; atomic_t cache_bypass_misses; - atomic_t cache_readaheads; atomic_t cache_miss_collisions; atomic_t sectors_bypassed; }; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index cc89f3156d1a..05ac1d6fbbf3 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -137,7 +137,6 @@ rw_attribute(io_disable); rw_attribute(discard); rw_attribute(running); rw_attribute(label); -rw_attribute(readahead); rw_attribute(errors); rw_attribute(io_error_limit); rw_attribute(io_error_halflife); @@ -260,7 +259,6 @@ SHOW(__bch_cached_dev) var_printf(partial_stripes_expensive, "%u"); var_hprint(sequential_cutoff); - var_hprint(readahead); sysfs_print(running, atomic_read(&dc->running)); sysfs_print(state, states[BDEV_STATE(&dc->sb)]); @@ -365,7 +363,6 @@ STORE(__cached_dev) sysfs_strtoul_clamp(sequential_cutoff, dc->sequential_cutoff, 0, UINT_MAX); - d_strtoi_h(readahead); if (attr == &sysfs_clear_stats) bch_cache_accounting_clear(&dc->accounting); @@ -538,7 +535,6 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_running, &sysfs_state, &sysfs_label, - &sysfs_readahead, #ifdef CONFIG_BCACHE_DEBUG &sysfs_verify, &sysfs_bypass_torture_test, diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index b8e4d31124ea..751ec5ea1dbb 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -859,7 +859,8 @@ static uint32_t __minimum_chunk_size(struct origin *o) if (o) list_for_each_entry(snap, &o->snapshots, list) - chunk_size = min(chunk_size, snap->store->chunk_size); + chunk_size = min_not_zero(chunk_size, + snap->store->chunk_size); return (uint32_t) chunk_size; } diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c index 29385dc470d5..db61a1f43ae9 100644 --- a/drivers/md/dm-verity-verify-sig.c +++ b/drivers/md/dm-verity-verify-sig.c @@ -15,7 +15,7 @@ #define DM_VERITY_VERIFY_ERR(s) DM_VERITY_ROOT_HASH_VERIFICATION " " s static bool require_signatures; -module_param(require_signatures, bool, false); +module_param(require_signatures, bool, 0444); MODULE_PARM_DESC(require_signatures, "Verify the roothash of dm-verity hash tree"); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 841e1c1aa5e6..7d4ff8a5c55e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5311,8 +5311,6 @@ static int in_chunk_boundary(struct mddev *mddev, struct bio *bio) unsigned int chunk_sectors; unsigned int bio_sectors = bio_sectors(bio); - WARN_ON_ONCE(bio->bi_bdev->bd_partno); - chunk_sectors = min(conf->chunk_sectors, conf->prev_chunk_sectors); return chunk_sectors >= ((sector & (chunk_sectors - 1)) + bio_sectors); diff --git a/drivers/misc/cardreader/rtl8411.c b/drivers/misc/cardreader/rtl8411.c index a07674ed0596..4c5621b17a6f 100644 --- a/drivers/misc/cardreader/rtl8411.c +++ b/drivers/misc/cardreader/rtl8411.c @@ -468,6 +468,7 @@ static void rtl8411_init_common_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = DRIVER_TYPE_D; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_CFG; pcr->tx_initial_phase = SET_CLOCK_PHASE(23, 7, 14); pcr->rx_initial_phase = SET_CLOCK_PHASE(4, 3, 10); pcr->ic_version = rtl8411_get_ic_version(pcr); diff --git a/drivers/misc/cardreader/rts5209.c b/drivers/misc/cardreader/rts5209.c index 39a6a7ecc32e..29f5414072bf 100644 --- a/drivers/misc/cardreader/rts5209.c +++ b/drivers/misc/cardreader/rts5209.c @@ -255,6 +255,7 @@ void rts5209_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = DRIVER_TYPE_D; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_CFG; pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 16); pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index 8200af22b529..4bcfbc9afbac 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -358,6 +358,7 @@ void rts5227_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_CFG; pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 15); pcr->rx_initial_phase = SET_CLOCK_PHASE(30, 7, 7); @@ -483,6 +484,7 @@ void rts522a_init_params(struct rtsx_pcr *pcr) rts5227_init_params(pcr); pcr->ops = &rts522a_pcr_ops; + pcr->aspm_mode = ASPM_MODE_REG; pcr->tx_initial_phase = SET_CLOCK_PHASE(20, 20, 11); pcr->reg_pm_ctrl3 = RTS522A_PM_CTRL3; diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c index 781a86def59a..ffc128278613 100644 --- a/drivers/misc/cardreader/rts5228.c +++ b/drivers/misc/cardreader/rts5228.c @@ -718,6 +718,7 @@ void rts5228_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_REG; pcr->tx_initial_phase = SET_CLOCK_PHASE(28, 27, 11); pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); diff --git a/drivers/misc/cardreader/rts5229.c b/drivers/misc/cardreader/rts5229.c index 89e6f124ca5c..c748eaf1ec1f 100644 --- a/drivers/misc/cardreader/rts5229.c +++ b/drivers/misc/cardreader/rts5229.c @@ -246,6 +246,7 @@ void rts5229_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = DRIVER_TYPE_D; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_CFG; pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 15); pcr->rx_initial_phase = SET_CLOCK_PHASE(30, 6, 6); diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index b2676e7f5027..53f3a1f45c4a 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -566,6 +566,7 @@ void rts5249_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_CFG; pcr->tx_initial_phase = SET_CLOCK_PHASE(1, 29, 16); pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); @@ -729,6 +730,7 @@ static const struct pcr_ops rts524a_pcr_ops = { void rts524a_init_params(struct rtsx_pcr *pcr) { rts5249_init_params(pcr); + pcr->aspm_mode = ASPM_MODE_REG; pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 29, 11); pcr->option.ltr_l1off_sspwrgate = LTR_L1OFF_SSPWRGATE_5250_DEF; pcr->option.ltr_l1off_snooze_sspwrgate = @@ -845,6 +847,7 @@ static const struct pcr_ops rts525a_pcr_ops = { void rts525a_init_params(struct rtsx_pcr *pcr) { rts5249_init_params(pcr); + pcr->aspm_mode = ASPM_MODE_REG; pcr->tx_initial_phase = SET_CLOCK_PHASE(25, 29, 11); pcr->option.ltr_l1off_sspwrgate = LTR_L1OFF_SSPWRGATE_5250_DEF; pcr->option.ltr_l1off_snooze_sspwrgate = diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index 080a7d67a8e1..9b42b20a3e5a 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -628,6 +628,7 @@ void rts5260_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_REG; pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 29, 11); pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c index 6c64dade8e1a..1fd4e0e50730 100644 --- a/drivers/misc/cardreader/rts5261.c +++ b/drivers/misc/cardreader/rts5261.c @@ -783,6 +783,7 @@ void rts5261_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = 0x00; pcr->sd30_drive_sel_3v3 = 0x00; pcr->aspm_en = ASPM_L1_EN; + pcr->aspm_mode = ASPM_MODE_REG; pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 11); pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 273311184669..baf83594a01d 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -85,12 +85,18 @@ static void rtsx_comm_set_aspm(struct rtsx_pcr *pcr, bool enable) if (pcr->aspm_enabled == enable) return; - if (pcr->aspm_en & 0x02) - rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 | - FORCE_ASPM_CTL1, enable ? 0 : FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1); - else - rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 | - FORCE_ASPM_CTL1, FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1); + if (pcr->aspm_mode == ASPM_MODE_CFG) { + pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPMC, + enable ? pcr->aspm_en : 0); + } else if (pcr->aspm_mode == ASPM_MODE_REG) { + if (pcr->aspm_en & 0x02) + rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 | + FORCE_ASPM_CTL1, enable ? 0 : FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1); + else + rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 | + FORCE_ASPM_CTL1, FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1); + } if (!enable && (pcr->aspm_en & 0x02)) mdelay(10); @@ -1394,7 +1400,8 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) return err; } - rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30); + if (pcr->aspm_mode == ASPM_MODE_REG) + rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30); /* No CD interrupt if probing driver with card inserted. * So we need to initialize pcr->card_exist here. @@ -1410,6 +1417,8 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) static int rtsx_pci_init_chip(struct rtsx_pcr *pcr) { int err; + u16 cfg_val; + u8 val; spin_lock_init(&pcr->lock); mutex_init(&pcr->pcr_mutex); @@ -1477,6 +1486,21 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr) if (!pcr->slots) return -ENOMEM; + if (pcr->aspm_mode == ASPM_MODE_CFG) { + pcie_capability_read_word(pcr->pci, PCI_EXP_LNKCTL, &cfg_val); + if (cfg_val & PCI_EXP_LNKCTL_ASPM_L1) + pcr->aspm_enabled = true; + else + pcr->aspm_enabled = false; + + } else if (pcr->aspm_mode == ASPM_MODE_REG) { + rtsx_pci_read_register(pcr, ASPM_FORCE_CTL, &val); + if (val & FORCE_ASPM_CTL0 && val & FORCE_ASPM_CTL1) + pcr->aspm_enabled = false; + else + pcr->aspm_enabled = true; + } + if (pcr->ops->fetch_vendor_settings) pcr->ops->fetch_vendor_settings(pcr); @@ -1506,7 +1530,6 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, struct pcr_handle *handle; u32 base, len; int ret, i, bar = 0; - u8 val; dev_dbg(&(pcidev->dev), ": Realtek PCI-E Card Reader found at %s [%04x:%04x] (rev %x)\n", @@ -1572,11 +1595,6 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, pcr->host_cmds_addr = pcr->rtsx_resv_buf_addr; pcr->host_sg_tbl_ptr = pcr->rtsx_resv_buf + HOST_CMDS_BUF_LEN; pcr->host_sg_tbl_addr = pcr->rtsx_resv_buf_addr + HOST_CMDS_BUF_LEN; - rtsx_pci_read_register(pcr, ASPM_FORCE_CTL, &val); - if (val & FORCE_ASPM_CTL0 && val & FORCE_ASPM_CTL1) - pcr->aspm_enabled = false; - else - pcr->aspm_enabled = true; pcr->card_inserted = 0; pcr->card_removed = 0; INIT_DELAYED_WORK(&pcr->carddet_work, rtsx_pci_card_detect); diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index 64d33e368509..67c5b452dd35 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -101,8 +101,9 @@ printk(KERN_INFO a); \ } while (0) #define v2printk(a...) do { \ - if (verbose > 1) \ + if (verbose > 1) { \ printk(KERN_INFO a); \ + } \ touch_nmi_watchdog(); \ } while (0) #define eprintk(a...) do { \ diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index a98f6b895af7..aab3ebfa9fc4 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -277,6 +277,9 @@ static int mei_cl_irq_read(struct mei_cl *cl, struct mei_cl_cb *cb, return ret; } + pm_runtime_mark_last_busy(dev->dev); + pm_request_autosuspend(dev->dev); + list_move_tail(&cb->list, &cl->rd_pending); return 0; diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 635bf31a6735..baab4c2e1b53 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -692,14 +692,19 @@ static int renesas_sdhi_execute_tuning(struct mmc_host *mmc, u32 opcode) /* Issue CMD19 twice for each tap */ for (i = 0; i < 2 * priv->tap_num; i++) { + int cmd_error; + /* Set sampling clock position */ sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_TAPSET, i % priv->tap_num); - if (mmc_send_tuning(mmc, opcode, NULL) == 0) + if (mmc_send_tuning(mmc, opcode, &cmd_error) == 0) set_bit(i, priv->taps); if (sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_SMPCMP) == 0) set_bit(i, priv->smpcmp); + + if (cmd_error) + mmc_abort_tuning(mmc, opcode); } ret = renesas_sdhi_select_tuning(host); @@ -939,7 +944,7 @@ static const struct soc_device_attribute sdhi_quirks_match[] = { { .soc_id = "r8a7795", .revision = "ES3.*", .data = &sdhi_quirks_bad_taps2367 }, { .soc_id = "r8a7796", .revision = "ES1.[012]", .data = &sdhi_quirks_4tap_nohs400 }, { .soc_id = "r8a7796", .revision = "ES1.*", .data = &sdhi_quirks_r8a7796_es13 }, - { .soc_id = "r8a7796", .revision = "ES3.*", .data = &sdhi_quirks_bad_taps1357 }, + { .soc_id = "r8a77961", .data = &sdhi_quirks_bad_taps1357 }, { .soc_id = "r8a77965", .data = &sdhi_quirks_r8a77965 }, { .soc_id = "r8a77980", .data = &sdhi_quirks_nohs400 }, { .soc_id = "r8a77990", .data = &sdhi_quirks_r8a77990 }, diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c index 6edf78c16fc8..df40927e5678 100644 --- a/drivers/mtd/nand/raw/cs553x_nand.c +++ b/drivers/mtd/nand/raw/cs553x_nand.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/iopoll.h> @@ -240,6 +241,15 @@ static int cs_calculate_ecc(struct nand_chip *this, const u_char *dat, return 0; } +static int cs553x_ecc_correct(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + static struct cs553x_nand_controller *controllers[4]; static int cs553x_attach_chip(struct nand_chip *chip) @@ -251,7 +261,7 @@ static int cs553x_attach_chip(struct nand_chip *chip) chip->ecc.bytes = 3; chip->ecc.hwctl = cs_enable_hwecc; chip->ecc.calculate = cs_calculate_ecc; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = cs553x_ecc_correct; chip->ecc.strength = 1; return 0; diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index bf695255b43a..a3e66155ae40 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -25,6 +25,7 @@ #include <linux/sched.h> #include <linux/types.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/platform_device.h> #include <linux/of.h> @@ -432,6 +433,15 @@ static int fsmc_read_hwecc_ecc1(struct nand_chip *chip, const u8 *data, return 0; } +static int fsmc_correct_ecc1(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + /* Count the number of 0's in buff upto a max of max_bits */ static int count_written_bits(u8 *buff, int size, int max_bits) { @@ -917,7 +927,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) case NAND_ECC_ENGINE_TYPE_ON_HOST: dev_info(host->dev, "Using 1-bit HW ECC scheme\n"); nand->ecc.calculate = fsmc_read_hwecc_ecc1; - nand->ecc.correct = rawnand_sw_hamming_correct; + nand->ecc.correct = fsmc_correct_ecc1; nand->ecc.hwctl = fsmc_enable_hwecc; nand->ecc.bytes = 3; nand->ecc.strength = 1; diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index 6b7269cfb7d8..d7dfc6fd85ca 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -27,6 +27,7 @@ #include <linux/of.h> #include <linux/of_gpio.h> #include <linux/mtd/lpc32xx_slc.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #define LPC32XX_MODNAME "lpc32xx-nand" @@ -345,6 +346,18 @@ static int lpc32xx_nand_ecc_calculate(struct nand_chip *chip, } /* + * Corrects the data + */ +static int lpc32xx_nand_ecc_correct(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + +/* * Read a single byte from NAND device */ static uint8_t lpc32xx_nand_read_byte(struct nand_chip *chip) @@ -802,7 +815,7 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome; chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome; chip->ecc.calculate = lpc32xx_nand_ecc_calculate; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = lpc32xx_nand_ecc_correct; chip->ecc.hwctl = lpc32xx_nand_ecc_enable; /* diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index 338d6b1a189e..98d5a94c3a24 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -22,6 +22,7 @@ #include <linux/mtd/ndfc.h> #include <linux/slab.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/of_address.h> #include <linux/of_platform.h> #include <asm/io.h> @@ -100,6 +101,15 @@ static int ndfc_calculate_ecc(struct nand_chip *chip, return 0; } +static int ndfc_correct_ecc(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + /* * Speedups for buffer read/write/verify * @@ -145,7 +155,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc, chip->controller = &ndfc->ndfc_control; chip->legacy.read_buf = ndfc_read_buf; chip->legacy.write_buf = ndfc_write_buf; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = ndfc_correct_ecc; chip->ecc.hwctl = ndfc_enable_hwecc; chip->ecc.calculate = ndfc_calculate_ecc; chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c index 5612ee628425..2f1fe464e663 100644 --- a/drivers/mtd/nand/raw/sharpsl.c +++ b/drivers/mtd/nand/raw/sharpsl.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/mtd/sharpsl.h> @@ -96,6 +97,15 @@ static int sharpsl_nand_calculate_ecc(struct nand_chip *chip, return readb(sharpsl->io + ECCCNTR) != 0; } +static int sharpsl_nand_correct_ecc(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + static int sharpsl_attach_chip(struct nand_chip *chip) { if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) @@ -106,7 +116,7 @@ static int sharpsl_attach_chip(struct nand_chip *chip) chip->ecc.strength = 1; chip->ecc.hwctl = sharpsl_nand_enable_hwecc; chip->ecc.calculate = sharpsl_nand_calculate_ecc; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = sharpsl_nand_correct_ecc; return 0; } diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c index de8e919d0ebe..6d93dd31969b 100644 --- a/drivers/mtd/nand/raw/tmio_nand.c +++ b/drivers/mtd/nand/raw/tmio_nand.c @@ -34,6 +34,7 @@ #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/slab.h> @@ -292,11 +293,12 @@ static int tmio_nand_correct_data(struct nand_chip *chip, unsigned char *buf, int r0, r1; /* assume ecc.size = 512 and ecc.bytes = 6 */ - r0 = rawnand_sw_hamming_correct(chip, buf, read_ecc, calc_ecc); + r0 = ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); if (r0 < 0) return r0; - r1 = rawnand_sw_hamming_correct(chip, buf + 256, read_ecc + 3, - calc_ecc + 3); + r1 = ecc_sw_hamming_correct(buf + 256, read_ecc + 3, calc_ecc + 3, + chip->ecc.size, false); if (r1 < 0) return r1; return r0 + r1; diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index 1a9449e53bf9..b8894ac27073 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -13,6 +13,7 @@ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/io.h> @@ -193,8 +194,8 @@ static int txx9ndfmc_correct_data(struct nand_chip *chip, unsigned char *buf, int stat; for (eccsize = chip->ecc.size; eccsize > 0; eccsize -= 256) { - stat = rawnand_sw_hamming_correct(chip, buf, read_ecc, - calc_ecc); + stat = ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); if (stat < 0) return stat; corrected += stat; diff --git a/drivers/mtd/parsers/ofpart_core.c b/drivers/mtd/parsers/ofpart_core.c index 0fd8d2a0db97..192190c42fc8 100644 --- a/drivers/mtd/parsers/ofpart_core.c +++ b/drivers/mtd/parsers/ofpart_core.c @@ -57,20 +57,22 @@ static int parse_fixed_partitions(struct mtd_info *master, if (!mtd_node) return 0; - ofpart_node = of_get_child_by_name(mtd_node, "partitions"); - if (!ofpart_node && !master->parent) { - /* - * We might get here even when ofpart isn't used at all (e.g., - * when using another parser), so don't be louder than - * KERN_DEBUG - */ - pr_debug("%s: 'partitions' subnode not found on %pOF. Trying to parse direct subnodes as partitions.\n", - master->name, mtd_node); + if (!master->parent) { /* Master */ + ofpart_node = of_get_child_by_name(mtd_node, "partitions"); + if (!ofpart_node) { + /* + * We might get here even when ofpart isn't used at all (e.g., + * when using another parser), so don't be louder than + * KERN_DEBUG + */ + pr_debug("%s: 'partitions' subnode not found on %pOF. Trying to parse direct subnodes as partitions.\n", + master->name, mtd_node); + ofpart_node = mtd_node; + dedicated = false; + } + } else { /* Partition */ ofpart_node = mtd_node; - dedicated = false; } - if (!ofpart_node) - return 0; of_id = of_match_node(parse_ofpart_match_table, ofpart_node); if (dedicated && !of_id) { diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index ba8e70a8e312..6b12ce822e51 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -327,6 +327,8 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) break; } + dev->base_addr = ioaddr; + /* Reserve any actual interrupt. */ if (dev->irq) { retval = request_irq(dev->irq, cops_interrupt, 0, dev->name, dev); @@ -334,8 +336,6 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) goto err_out; } - dev->base_addr = ioaddr; - lp = netdev_priv(dev); spin_lock_init(&lp->lock); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 20bbda1b36e1..c5a646d06102 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1526,6 +1526,7 @@ static struct slave *bond_alloc_slave(struct bonding *bond, slave->bond = bond; slave->dev = slave_dev; + INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); if (bond_kobj_init(slave)) return NULL; @@ -1538,7 +1539,6 @@ static struct slave *bond_alloc_slave(struct bonding *bond, return NULL; } } - INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); return slave; } diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index d17482395a4d..4ffbfd534f18 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -350,6 +350,7 @@ static int ldisc_open(struct tty_struct *tty) rtnl_lock(); result = register_netdevice(dev); if (result) { + tty_kref_put(tty); rtnl_unlock(); free_netdev(dev); return -ENODEV; diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 029e77dfa773..a45865bd7254 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -82,6 +82,8 @@ struct mcba_priv { bool can_ka_first_pass; bool can_speed_check; atomic_t free_ctx_cnt; + void *rxbuf[MCBA_MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MCBA_MAX_RX_URBS]; }; /* CAN frame */ @@ -633,6 +635,7 @@ static int mcba_usb_start(struct mcba_priv *priv) for (i = 0; i < MCBA_MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -642,7 +645,7 @@ static int mcba_usb_start(struct mcba_priv *priv) } buf = usb_alloc_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, - GFP_KERNEL, &urb->transfer_dma); + GFP_KERNEL, &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -661,11 +664,14 @@ static int mcba_usb_start(struct mcba_priv *priv) if (err) { usb_unanchor_urb(urb); usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, - buf, urb->transfer_dma); + buf, buf_dma); usb_free_urb(urb); break; } + priv->rxbuf[i] = buf; + priv->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -708,7 +714,14 @@ static int mcba_usb_open(struct net_device *netdev) static void mcba_urb_unlink(struct mcba_priv *priv) { + int i; + usb_kill_anchored_urbs(&priv->rx_submitted); + + for (i = 0; i < MCBA_MAX_RX_URBS; ++i) + usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, + priv->rxbuf[i], priv->rxbuf_dma[i]); + usb_kill_anchored_urbs(&priv->tx_submitted); } diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 9150038b60cb..3b018fcf4412 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -821,11 +821,9 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, bcm_sf2_sw_mac_link_set(ds, port, interface, true); if (port != core_readl(priv, CORE_IMP0_PRT_ID)) { - u32 reg_rgmii_ctrl; + u32 reg_rgmii_ctrl = 0; u32 reg, offset; - reg_rgmii_ctrl = bcm_sf2_reg_rgmii_cntrl(priv, port); - if (priv->type == BCM4908_DEVICE_ID || priv->type == BCM7445_DEVICE_ID) offset = CORE_STS_OVERRIDE_GMIIP_PORT(port); @@ -836,6 +834,7 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, interface == PHY_INTERFACE_MODE_RGMII_TXID || interface == PHY_INTERFACE_MODE_MII || interface == PHY_INTERFACE_MODE_REVMII) { + reg_rgmii_ctrl = bcm_sf2_reg_rgmii_cntrl(priv, port); reg = reg_readl(priv, reg_rgmii_ctrl); reg &= ~(RX_PAUSE_EN | TX_PAUSE_EN); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 55e5d479acce..854e25f43fa7 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1530,6 +1530,7 @@ static const struct ksz_chip_data ksz9477_switch_chips[] = { .num_statics = 16, .cpu_ports = 0x7F, /* can be configured as cpu port */ .port_cnt = 7, /* total physical port count */ + .phy_errata_9477 = true, }, }; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 96f7c9eede35..9b90f3d3a8f5 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1262,14 +1262,6 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) { struct mt7530_priv *priv = ds->priv; - /* The real fabric path would be decided on the membership in the - * entry of VLAN table. PCR_MATRIX set up here with ALL_MEMBERS - * means potential VLAN can be consisting of certain subset of all - * ports. - */ - mt7530_rmw(priv, MT7530_PCR_P(port), - PCR_MATRIX_MASK, PCR_MATRIX(MT7530_ALL_MEMBERS)); - /* Trapped into security mode allows packet forwarding through VLAN * table lookup. CPU port is set to fallback mode to let untagged * frames pass through. diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 2473bebe48e6..f966a253d1c7 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1227,12 +1227,17 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, if (taprio->num_entries > VSC9959_TAS_GCL_ENTRY_MAX) return -ERANGE; - /* Set port num and disable ALWAYS_GUARD_BAND_SCH_Q, which means set - * guard band to be implemented for nonschedule queues to schedule - * queues transition. + /* Enable guard band. The switch will schedule frames without taking + * their length into account. Thus we'll always need to enable the + * guard band which reserves the time of a maximum sized frame at the + * end of the time window. + * + * Although the ALWAYS_GUARD_BAND_SCH_Q bit is global for all ports, we + * need to set PORT_NUM, because subsequent writes to PARAM_CFG_REG_n + * operate on the port number. */ - ocelot_rmw(ocelot, - QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM(port), + ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM(port) | + QSYS_TAS_PARAM_CFG_CTRL_ALWAYS_GUARD_BAND_SCH_Q, QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM_M | QSYS_TAS_PARAM_CFG_CTRL_ALWAYS_GUARD_BAND_SCH_Q, QSYS_TAS_PARAM_CFG_CTRL); diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index b777d3f37573..12cd04b56803 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -167,9 +167,10 @@ enum sja1105_hostcmd { SJA1105_HOSTCMD_INVALIDATE = 4, }; +/* Command and entry overlap */ static void -sja1105_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, - enum packing_op op) +sja1105et_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) { const int size = SJA1105_SIZE_DYN_CMD; @@ -179,6 +180,20 @@ sja1105_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(buf, &cmd->index, 9, 0, size, op); } +/* Command and entry are separate */ +static void +sja1105pqrs_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_VL_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->errors, 30, 30, size, op); + sja1105_packing(p, &cmd->rdwrset, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 9, 0, size, op); +} + static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -641,7 +656,7 @@ static size_t sja1105pqrs_cbs_entry_packing(void *buf, void *entry_ptr, const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_VL_LOOKUP] = { .entry_packing = sja1105et_vl_lookup_entry_packing, - .cmd_packing = sja1105_vl_lookup_cmd_packing, + .cmd_packing = sja1105et_vl_lookup_cmd_packing, .access = OP_WRITE, .max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT, .packed_size = SJA1105ET_SIZE_VL_LOOKUP_DYN_CMD, @@ -725,7 +740,7 @@ const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_VL_LOOKUP] = { .entry_packing = sja1105_vl_lookup_entry_packing, - .cmd_packing = sja1105_vl_lookup_cmd_packing, + .cmd_packing = sja1105pqrs_vl_lookup_cmd_packing, .access = (OP_READ | OP_WRITE), .max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT, .packed_size = SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD, diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 405024b637d6..b88d9ef45a1f 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -26,6 +26,7 @@ #include "sja1105_tas.h" #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull +#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) static const struct dsa_switch_ops sja1105_switch_ops; @@ -207,6 +208,7 @@ static int sja1105_init_mii_settings(struct sja1105_private *priv, default: dev_err(dev, "Unsupported PHY mode %s!\n", phy_modes(ports[i].phy_mode)); + return -EINVAL; } /* Even though the SerDes port is able to drive SGMII autoneg @@ -321,6 +323,13 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) return 0; } +/* Set up a default VLAN for untagged traffic injected from the CPU + * using management routes (e.g. STP, PTP) as opposed to tag_8021q. + * All DT-defined ports are members of this VLAN, and there are no + * restrictions on forwarding (since the CPU selects the destination). + * Frames from this VLAN will always be transmitted as untagged, and + * neither the bridge nor the 8021q module cannot create this VLAN ID. + */ static int sja1105_init_static_vlan(struct sja1105_private *priv) { struct sja1105_table *table; @@ -330,17 +339,13 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) .vmemb_port = 0, .vlan_bc = 0, .tag_port = 0, - .vlanid = 1, + .vlanid = SJA1105_DEFAULT_VLAN, }; struct dsa_switch *ds = priv->ds; int port; table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; - /* The static VLAN table will only contain the initial pvid of 1. - * All other VLANs are to be configured through dynamic entries, - * and kept in the static configuration table as backing memory. - */ if (table->entry_count) { kfree(table->entries); table->entry_count = 0; @@ -353,9 +358,6 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) table->entry_count = 1; - /* VLAN 1: all DT-defined ports are members; no restrictions on - * forwarding; always transmit as untagged. - */ for (port = 0; port < ds->num_ports; port++) { struct sja1105_bridge_vlan *v; @@ -366,15 +368,12 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) pvid.vlan_bc |= BIT(port); pvid.tag_port &= ~BIT(port); - /* Let traffic that don't need dsa_8021q (e.g. STP, PTP) be - * transmitted as untagged. - */ v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) return -ENOMEM; v->port = port; - v->vid = 1; + v->vid = SJA1105_DEFAULT_VLAN; v->untagged = true; if (dsa_is_cpu_port(ds, port)) v->pvid = true; @@ -2817,11 +2816,22 @@ static int sja1105_vlan_add_one(struct dsa_switch *ds, int port, u16 vid, bool pvid = flags & BRIDGE_VLAN_INFO_PVID; struct sja1105_bridge_vlan *v; - list_for_each_entry(v, vlan_list, list) - if (v->port == port && v->vid == vid && - v->untagged == untagged && v->pvid == pvid) + list_for_each_entry(v, vlan_list, list) { + if (v->port == port && v->vid == vid) { /* Already added */ - return 0; + if (v->untagged == untagged && v->pvid == pvid) + /* Nothing changed */ + return 0; + + /* It's the same VLAN, but some of the flags changed + * and the user did not bother to delete it first. + * Update it and trigger sja1105_build_vlan_table. + */ + v->untagged = untagged; + v->pvid = pvid; + return 1; + } + } v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { @@ -2976,13 +2986,13 @@ static int sja1105_setup(struct dsa_switch *ds) rc = sja1105_static_config_load(priv, ports); if (rc < 0) { dev_err(ds->dev, "Failed to load static config: %d\n", rc); - return rc; + goto out_ptp_clock_unregister; } /* Configure the CGU (PHY link modes and speeds) */ rc = sja1105_clocking_setup(priv); if (rc < 0) { dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc); - return rc; + goto out_static_config_free; } /* On SJA1105, VLAN filtering per se is always enabled in hardware. * The only thing we can do to disable it is lie about what the 802.1Q @@ -3003,7 +3013,7 @@ static int sja1105_setup(struct dsa_switch *ds) rc = sja1105_devlink_setup(ds); if (rc < 0) - return rc; + goto out_static_config_free; /* The DSA/switchdev model brings up switch ports in standalone mode by * default, and that means vlan_filtering is 0 since they're not under @@ -3012,6 +3022,17 @@ static int sja1105_setup(struct dsa_switch *ds) rtnl_lock(); rc = sja1105_setup_8021q_tagging(ds, true); rtnl_unlock(); + if (rc) + goto out_devlink_teardown; + + return 0; + +out_devlink_teardown: + sja1105_devlink_teardown(ds); +out_ptp_clock_unregister: + sja1105_ptp_clock_unregister(ds); +out_static_config_free: + sja1105_static_config_free(&priv->static_config); return rc; } @@ -3646,8 +3667,10 @@ static int sja1105_probe(struct spi_device *spi) priv->cbs = devm_kcalloc(dev, priv->info->num_cbs_shapers, sizeof(struct sja1105_cbs_entry), GFP_KERNEL); - if (!priv->cbs) - return -ENOMEM; + if (!priv->cbs) { + rc = -ENOMEM; + goto out_unregister_switch; + } } /* Connections between dsa_port and sja1105_port */ @@ -3672,7 +3695,7 @@ static int sja1105_probe(struct spi_device *spi) dev_err(ds->dev, "failed to create deferred xmit thread: %d\n", rc); - goto out; + goto out_destroy_workers; } skb_queue_head_init(&sp->xmit_queue); sp->xmit_tpid = ETH_P_SJA1105; @@ -3682,7 +3705,8 @@ static int sja1105_probe(struct spi_device *spi) } return 0; -out: + +out_destroy_workers: while (port-- > 0) { struct sja1105_port *sp = &priv->ports[port]; @@ -3691,6 +3715,10 @@ out: kthread_destroy_worker(sp->xmit_worker); } + +out_unregister_switch: + dsa_unregister_switch(ds); + return rc; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 881f88754bf6..52571486705e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -236,36 +236,48 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget) static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring, struct ena_tx_buffer *tx_info, struct xdp_frame *xdpf, - void **push_hdr, - u32 *push_len) + struct ena_com_tx_ctx *ena_tx_ctx) { struct ena_adapter *adapter = xdp_ring->adapter; struct ena_com_buf *ena_buf; - dma_addr_t dma = 0; + int push_len = 0; + dma_addr_t dma; + void *data; u32 size; tx_info->xdpf = xdpf; + data = tx_info->xdpf->data; size = tx_info->xdpf->len; - ena_buf = tx_info->bufs; - /* llq push buffer */ - *push_len = min_t(u32, size, xdp_ring->tx_max_header_size); - *push_hdr = tx_info->xdpf->data; + if (xdp_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) { + /* Designate part of the packet for LLQ */ + push_len = min_t(u32, size, xdp_ring->tx_max_header_size); + + ena_tx_ctx->push_header = data; + + size -= push_len; + data += push_len; + } + + ena_tx_ctx->header_len = push_len; - if (size - *push_len > 0) { + if (size > 0) { dma = dma_map_single(xdp_ring->dev, - *push_hdr + *push_len, - size - *push_len, + data, + size, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(xdp_ring->dev, dma))) goto error_report_dma_error; - tx_info->map_linear_data = 1; - tx_info->num_of_bufs = 1; - } + tx_info->map_linear_data = 0; - ena_buf->paddr = dma; - ena_buf->len = size; + ena_buf = tx_info->bufs; + ena_buf->paddr = dma; + ena_buf->len = size; + + ena_tx_ctx->ena_bufs = ena_buf; + ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1; + } return 0; @@ -274,10 +286,6 @@ error_report_dma_error: &xdp_ring->syncp); netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n"); - xdp_return_frame_rx_napi(tx_info->xdpf); - tx_info->xdpf = NULL; - tx_info->num_of_bufs = 0; - return -EINVAL; } @@ -289,8 +297,6 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, struct ena_com_tx_ctx ena_tx_ctx = {}; struct ena_tx_buffer *tx_info; u16 next_to_use, req_id; - void *push_hdr; - u32 push_len; int rc; next_to_use = xdp_ring->next_to_use; @@ -298,15 +304,11 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, tx_info = &xdp_ring->tx_buffer_info[req_id]; tx_info->num_of_bufs = 0; - rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &push_hdr, &push_len); + rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &ena_tx_ctx); if (unlikely(rc)) return rc; - ena_tx_ctx.ena_bufs = tx_info->bufs; - ena_tx_ctx.push_header = push_hdr; - ena_tx_ctx.num_bufs = tx_info->num_of_bufs; ena_tx_ctx.req_id = req_id; - ena_tx_ctx.header_len = push_len; rc = ena_xmit_common(dev, xdp_ring, diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index b3d74332ed33..7748b276e5fd 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1849,6 +1849,7 @@ out_free_netdev: free_netdev(netdev); out_pci_release: pci_release_mem_regions(pdev); + pci_disable_pcie_error_reporting(pdev); out_pci_disable: pci_disable_device(pdev); return err; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index c0986096c701..5bace8a93d73 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8247,9 +8247,9 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) BNX2_WR(bp, PCI_COMMAND, reg); } else if ((BNX2_CHIP_ID(bp) == BNX2_CHIP_ID_5706_A1) && !(bp->flags & BNX2_FLAG_PCIX)) { - dev_err(&pdev->dev, "5706 A1 can only be used in a PCIX bus, aborting\n"); + rc = -EPERM; goto err_out_unmap; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index d21f085044cd..27943b0446c2 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1223,8 +1223,10 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, goto failed; /* SR-IOV capability was enabled but there are no VFs*/ - if (iov->total == 0) + if (iov->total == 0) { + err = -EINVAL; goto failed; + } iov->nr_virtfn = min_t(u16, iov->total, num_vfs_param); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 2985844634c8..aef3fccc27a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -282,7 +282,8 @@ static bool bnxt_vf_pciid(enum board_idx idx) { return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF || idx == NETXTREME_S_VF || idx == NETXTREME_C_VF_HV || - idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF); + idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF || + idx == NETXTREME_E_P5_VF_HV); } #define DB_CP_REARM_FLAGS (DB_KEY_CP | DB_IDX_VALID) @@ -6932,17 +6933,10 @@ ctx_err: static void bnxt_hwrm_set_pg_attr(struct bnxt_ring_mem_info *rmem, u8 *pg_attr, __le64 *pg_dir) { - u8 pg_size = 0; - if (!rmem->nr_pages) return; - if (BNXT_PAGE_SHIFT == 13) - pg_size = 1 << 4; - else if (BNXT_PAGE_SIZE == 16) - pg_size = 2 << 4; - - *pg_attr = pg_size; + BNXT_SET_CTX_PAGE_ATTR(*pg_attr); if (rmem->depth >= 1) { if (rmem->depth == 2) *pg_attr |= 2; @@ -7314,7 +7308,7 @@ skip_rdma: entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries) + min; entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple); - entries = ctx->qp_max_l2_entries + extra_qps + ctx->qp_min_qp1_entries; + entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries); entries = roundup(entries, ctx->tqm_entries_multiple); entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring); for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) { @@ -10785,37 +10779,125 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) return rc; } +static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off, + u8 **nextp) +{ + struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + nw_off); + int hdr_count = 0; + u8 *nexthdr; + int start; + + /* Check that there are at most 2 IPv6 extension headers, no + * fragment header, and each is <= 64 bytes. + */ + start = nw_off + sizeof(*ip6h); + nexthdr = &ip6h->nexthdr; + while (ipv6_ext_hdr(*nexthdr)) { + struct ipv6_opt_hdr *hp; + int hdrlen; + + if (hdr_count >= 3 || *nexthdr == NEXTHDR_NONE || + *nexthdr == NEXTHDR_FRAGMENT) + return false; + hp = __skb_header_pointer(NULL, start, sizeof(*hp), skb->data, + skb_headlen(skb), NULL); + if (!hp) + return false; + if (*nexthdr == NEXTHDR_AUTH) + hdrlen = ipv6_authlen(hp); + else + hdrlen = ipv6_optlen(hp); + + if (hdrlen > 64) + return false; + nexthdr = &hp->nexthdr; + start += hdrlen; + hdr_count++; + } + if (nextp) { + /* Caller will check inner protocol */ + if (skb->encapsulation) { + *nextp = nexthdr; + return true; + } + *nextp = NULL; + } + /* Only support TCP/UDP for non-tunneled ipv6 and inner ipv6 */ + return *nexthdr == IPPROTO_TCP || *nexthdr == IPPROTO_UDP; +} + +/* For UDP, we can only handle 1 Vxlan port and 1 Geneve port. */ +static bool bnxt_udp_tunl_check(struct bnxt *bp, struct sk_buff *skb) +{ + struct udphdr *uh = udp_hdr(skb); + __be16 udp_port = uh->dest; + + if (udp_port != bp->vxlan_port && udp_port != bp->nge_port) + return false; + if (skb->inner_protocol_type == ENCAP_TYPE_ETHER) { + struct ethhdr *eh = inner_eth_hdr(skb); + + switch (eh->h_proto) { + case htons(ETH_P_IP): + return true; + case htons(ETH_P_IPV6): + return bnxt_exthdr_check(bp, skb, + skb_inner_network_offset(skb), + NULL); + } + } + return false; +} + +static bool bnxt_tunl_check(struct bnxt *bp, struct sk_buff *skb, u8 l4_proto) +{ + switch (l4_proto) { + case IPPROTO_UDP: + return bnxt_udp_tunl_check(bp, skb); + case IPPROTO_IPIP: + return true; + case IPPROTO_GRE: { + switch (skb->inner_protocol) { + default: + return false; + case htons(ETH_P_IP): + return true; + case htons(ETH_P_IPV6): + fallthrough; + } + } + case IPPROTO_IPV6: + /* Check ext headers of inner ipv6 */ + return bnxt_exthdr_check(bp, skb, skb_inner_network_offset(skb), + NULL); + } + return false; +} + static netdev_features_t bnxt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { - struct bnxt *bp; - __be16 udp_port; - u8 l4_proto = 0; + struct bnxt *bp = netdev_priv(dev); + u8 *l4_proto; features = vlan_features_check(skb, features); - if (!skb->encapsulation) - return features; - switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): - l4_proto = ip_hdr(skb)->protocol; + if (!skb->encapsulation) + return features; + l4_proto = &ip_hdr(skb)->protocol; + if (bnxt_tunl_check(bp, skb, *l4_proto)) + return features; break; case htons(ETH_P_IPV6): - l4_proto = ipv6_hdr(skb)->nexthdr; + if (!bnxt_exthdr_check(bp, skb, skb_network_offset(skb), + &l4_proto)) + break; + if (!l4_proto || bnxt_tunl_check(bp, skb, *l4_proto)) + return features; break; - default: - return features; } - - if (l4_proto != IPPROTO_UDP) - return features; - - bp = netdev_priv(dev); - /* For UDP, we can only handle 1 Vxlan port and 1 Geneve port. */ - udp_port = udp_hdr(skb)->dest; - if (udp_port == bp->vxlan_port || udp_port == bp->nge_port) - return features; return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } @@ -11668,6 +11750,8 @@ static void bnxt_fw_init_one_p3(struct bnxt *bp) bnxt_hwrm_coal_params_qcaps(bp); } +static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt); + static int bnxt_fw_init_one(struct bnxt *bp) { int rc; @@ -11682,6 +11766,9 @@ static int bnxt_fw_init_one(struct bnxt *bp) netdev_err(bp->dev, "Firmware init phase 2 failed\n"); return rc; } + rc = bnxt_probe_phy(bp, false); + if (rc) + return rc; rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false); if (rc) return rc; @@ -13073,6 +13160,7 @@ init_err_pci_clean: bnxt_hwrm_func_drv_unrgtr(bp); bnxt_free_hwrm_short_cmd_req(bp); bnxt_free_hwrm_resources(bp); + bnxt_ethtool_free(bp); kfree(bp->fw_health); bp->fw_health = NULL; bnxt_cleanup_pci(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 98e0cef4532c..30e47ea343f9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1457,6 +1457,16 @@ struct bnxt_ctx_pg_info { #define BNXT_BACKING_STORE_CFG_LEGACY_LEN 256 +#define BNXT_SET_CTX_PAGE_ATTR(attr) \ +do { \ + if (BNXT_PAGE_SIZE == 0x2000) \ + attr = FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K; \ + else if (BNXT_PAGE_SIZE == 0x10000) \ + attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K; \ + else \ + attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K; \ +} while (0) + struct bnxt_ctx_mem_info { u32 qp_max_entries; u16 qp_min_qp1_entries; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 6bc7d41d519b..a0c7b1167dbb 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2867,6 +2867,9 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) struct gem_stats *hwstat = &bp->hw_stats.gem; struct net_device_stats *nstat = &bp->dev->stats; + if (!netif_running(bp->dev)) + return nstat; + gem_update_stats(bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors + diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 314f8d806723..9058f09f921e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -2177,8 +2177,6 @@ int cxgb4_update_mac_filt(struct port_info *pi, unsigned int viid, bool persistent, u8 *smt_idx); int cxgb4_get_msix_idx_from_bmap(struct adapter *adap); void cxgb4_free_msix_idx_in_bmap(struct adapter *adap, u32 msix_idx); -int cxgb_open(struct net_device *dev); -int cxgb_close(struct net_device *dev); void cxgb4_enable_rx(struct adapter *adap, struct sge_rspq *q); void cxgb4_quiesce_rx(struct sge_rspq *q); int cxgb4_port_mirror_alloc(struct net_device *dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 61ea3ec5c3fc..83ed10ac8660 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1337,13 +1337,27 @@ static int cxgb4_ethtool_flash_phy(struct net_device *netdev, return ret; } - spin_lock_bh(&adap->win0_lock); + /* We have to RESET the chip/firmware because we need the + * chip in uninitialized state for loading new PHY image. + * Otherwise, the running firmware will only store the PHY + * image in local RAM which will be lost after next reset. + */ + ret = t4_fw_reset(adap, adap->mbox, PIORSTMODE_F | PIORST_F); + if (ret < 0) { + dev_err(adap->pdev_dev, + "Set FW to RESET for flashing PHY FW failed. ret: %d\n", + ret); + return ret; + } + ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size); - spin_unlock_bh(&adap->win0_lock); - if (ret) - dev_err(adap->pdev_dev, "Failed to load PHY FW\n"); + if (ret < 0) { + dev_err(adap->pdev_dev, "Failed to load PHY FW. ret: %d\n", + ret); + return ret; + } - return ret; + return 0; } static int cxgb4_ethtool_flash_fw(struct net_device *netdev, @@ -1610,16 +1624,14 @@ static struct filter_entry *cxgb4_get_filter_entry(struct adapter *adap, u32 ftid) { struct tid_info *t = &adap->tids; - struct filter_entry *f; - if (ftid < t->nhpftids) - f = &adap->tids.hpftid_tab[ftid]; - else if (ftid < t->nftids) - f = &adap->tids.ftid_tab[ftid - t->nhpftids]; - else - f = lookup_tid(&adap->tids, ftid); + if (ftid >= t->hpftid_base && ftid < t->hpftid_base + t->nhpftids) + return &t->hpftid_tab[ftid - t->hpftid_base]; - return f; + if (ftid >= t->ftid_base && ftid < t->ftid_base + t->nftids) + return &t->ftid_tab[ftid - t->ftid_base]; + + return lookup_tid(t, ftid); } static void cxgb4_fill_filter_rule(struct ethtool_rx_flow_spec *fs, @@ -1826,6 +1838,11 @@ static int cxgb4_ntuple_del_filter(struct net_device *dev, filter_id = filter_info->loc_array[cmd->fs.location]; f = cxgb4_get_filter_entry(adapter, filter_id); + if (f->fs.prio) + filter_id -= adapter->tids.hpftid_base; + else if (!f->fs.hash) + filter_id -= (adapter->tids.ftid_base - adapter->tids.nhpftids); + ret = cxgb4_flow_rule_destroy(dev, f->fs.tc_prio, &f->fs, filter_id); if (ret) goto err; @@ -1885,6 +1902,11 @@ static int cxgb4_ntuple_set_filter(struct net_device *netdev, filter_info = &adapter->ethtool_filters->port[pi->port_id]; + if (fs.prio) + tid += adapter->tids.hpftid_base; + else if (!fs.hash) + tid += (adapter->tids.ftid_base - adapter->tids.nhpftids); + filter_info->loc_array[cmd->fs.location] = tid; set_bit(cmd->fs.location, filter_info->bmap); filter_info->in_use++; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index bc581b149b11..6260b3bebd2b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -198,7 +198,7 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f, WORD_MASK, f->fs.nat_lip[3] | f->fs.nat_lip[2] << 8 | f->fs.nat_lip[1] << 16 | - (u64)f->fs.nat_lip[0] << 25, 1); + (u64)f->fs.nat_lip[0] << 24, 1); } } @@ -1042,7 +1042,7 @@ void clear_all_filters(struct adapter *adapter) cxgb4_del_filter(dev, f->tid, &f->fs); } - sb = t4_read_reg(adapter, LE_DB_SRVR_START_INDEX_A); + sb = adapter->tids.stid_base; for (i = 0; i < sb; i++) { f = (struct filter_entry *)adapter->tids.tid_tab[i]; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 6264bc66a4fc..762113a04dde 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2834,7 +2834,7 @@ static void cxgb_down(struct adapter *adapter) /* * net_device operations */ -int cxgb_open(struct net_device *dev) +static int cxgb_open(struct net_device *dev) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; @@ -2882,7 +2882,7 @@ out_unlock: return err; } -int cxgb_close(struct net_device *dev) +static int cxgb_close(struct net_device *dev) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; @@ -4424,10 +4424,8 @@ static int adap_init0_phy(struct adapter *adap) /* Load PHY Firmware onto adapter. */ - spin_lock_bh(&adap->win0_lock); ret = t4_load_phy_fw(adap, MEMWIN_NIC, phy_info->phy_fw_version, (u8 *)phyf->data, phyf->size); - spin_unlock_bh(&adap->win0_lock); if (ret < 0) dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n", -ret); @@ -6480,9 +6478,9 @@ static void cxgb4_ktls_dev_del(struct net_device *netdev, adap->uld[CXGB4_ULD_KTLS].tlsdev_ops->tls_dev_del(netdev, tls_ctx, direction); - cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); out_unlock: + cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); mutex_unlock(&uld_mutex); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 1b88bd1c2dbe..dd9be229819a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -997,20 +997,16 @@ int cxgb4_tc_flower_destroy(struct net_device *dev, if (!ch_flower) return -ENOENT; + rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node, + adap->flower_ht_params); + ret = cxgb4_flow_rule_destroy(dev, ch_flower->fs.tc_prio, &ch_flower->fs, ch_flower->filter_id); if (ret) - goto err; + netdev_err(dev, "Flow rule destroy failed for tid: %u, ret: %d", + ch_flower->filter_id, ret); - ret = rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node, - adap->flower_ht_params); - if (ret) { - netdev_err(dev, "Flow remove from rhashtable failed"); - goto err; - } kfree_rcu(ch_flower, rcu); - -err: return ret; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c index 6c259de96f96..338b04f339b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c @@ -589,7 +589,8 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev, * down before configuring tc params. */ if (netif_running(dev)) { - cxgb_close(dev); + netif_tx_stop_all_queues(dev); + netif_carrier_off(dev); needs_bring_up = true; } @@ -615,8 +616,10 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev, } out: - if (needs_bring_up) - cxgb_open(dev); + if (needs_bring_up) { + netif_tx_start_all_queues(dev); + netif_carrier_on(dev); + } mutex_unlock(&adap->tc_mqprio->mqprio_mutex); return ret; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 1e5f2edb70cf..6a099cb34b12 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2556,6 +2556,12 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc) if (!eosw_txq) return -ENOMEM; + if (!(adap->flags & CXGB4_FW_OK)) { + /* Don't stall caller when access to FW is lost */ + complete(&eosw_txq->completion); + return -EIO; + } + skb = alloc_skb(len, GFP_KERNEL); if (!skb) return -ENOMEM; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 9428ef1f04a8..a0555f4d76fc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3060,16 +3060,19 @@ int t4_read_flash(struct adapter *adapter, unsigned int addr, * @addr: the start address to write * @n: length of data to write in bytes * @data: the data to write + * @byte_oriented: whether to store data as bytes or as words * * Writes up to a page of data (256 bytes) to the serial flash starting * at the given address. All the data must be written to the same page. + * If @byte_oriented is set the write data is stored as byte stream + * (i.e. matches what on disk), otherwise in big-endian. */ static int t4_write_flash(struct adapter *adapter, unsigned int addr, - unsigned int n, const u8 *data) + unsigned int n, const u8 *data, bool byte_oriented) { - int ret; - u32 buf[64]; unsigned int i, c, left, val, offset = addr & 0xff; + u32 buf[64]; + int ret; if (addr >= adapter->params.sf_size || offset + n > SF_PAGE_SIZE) return -EINVAL; @@ -3080,10 +3083,14 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, (ret = sf1_write(adapter, 4, 1, 1, val)) != 0) goto unlock; - for (left = n; left; left -= c) { + for (left = n; left; left -= c, data += c) { c = min(left, 4U); - for (val = 0, i = 0; i < c; ++i) - val = (val << 8) + *data++; + for (val = 0, i = 0; i < c; ++i) { + if (byte_oriented) + val = (val << 8) + data[i]; + else + val = (val << 8) + data[c - i - 1]; + } ret = sf1_write(adapter, c, c != left, 1, val); if (ret) @@ -3096,7 +3103,8 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, t4_write_reg(adapter, SF_OP_A, 0); /* unlock SF */ /* Read the page to verify the write succeeded */ - ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, 1); + ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, + byte_oriented); if (ret) return ret; @@ -3692,7 +3700,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) */ memcpy(first_page, fw_data, SF_PAGE_SIZE); ((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff); - ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page); + ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page, true); if (ret) goto out; @@ -3700,14 +3708,14 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; fw_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data, true); if (ret) goto out; } - ret = t4_write_flash(adap, - fw_start + offsetof(struct fw_hdr, fw_ver), - sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver); + ret = t4_write_flash(adap, fw_start + offsetof(struct fw_hdr, fw_ver), + sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver, + true); out: if (ret) dev_err(adap->pdev_dev, "firmware download failed, error %d\n", @@ -3812,9 +3820,11 @@ int t4_load_phy_fw(struct adapter *adap, int win, /* Copy the supplied PHY Firmware image to the adapter memory location * allocated by the adapter firmware. */ + spin_lock_bh(&adap->win0_lock); ret = t4_memory_rw(adap, win, mtype, maddr, phy_fw_size, (__be32 *)phy_fw_data, T4_MEMORY_WRITE); + spin_unlock_bh(&adap->win0_lock); if (ret) return ret; @@ -10208,7 +10218,7 @@ int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) n = size - i; else n = SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, true); if (ret) goto out; @@ -10677,13 +10687,14 @@ int t4_load_boot(struct adapter *adap, u8 *boot_data, for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; boot_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data, + false); if (ret) goto out; } ret = t4_write_flash(adap, boot_sector, SF_PAGE_SIZE, - (const u8 *)header); + (const u8 *)header, false); out: if (ret) @@ -10758,7 +10769,7 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < size; i += SF_PAGE_SIZE) { n = min_t(u32, size - i, SF_PAGE_SIZE); - ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, false); if (ret) goto out; @@ -10770,7 +10781,8 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < npad; i++) { u8 data = 0; - ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data); + ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data, + false); if (ret) goto out; } diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index ef3f1e92632f..59683f79959c 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -59,6 +59,7 @@ static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len) } static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info); +static void clear_conn_resources(struct chcr_ktls_info *tx_info); /* * chcr_ktls_save_keys: calculate and save crypto keys. * @tx_info - driver specific tls info. @@ -364,10 +365,14 @@ static void chcr_ktls_dev_del(struct net_device *netdev, chcr_get_ktls_tx_context(tls_ctx); struct chcr_ktls_info *tx_info = tx_ctx->chcr_info; struct ch_ktls_port_stats_debug *port_stats; + struct chcr_ktls_uld_ctx *u_ctx; if (!tx_info) return; + u_ctx = tx_info->adap->uld[CXGB4_ULD_KTLS].handle; + if (u_ctx && u_ctx->detach) + return; /* clear l2t entry */ if (tx_info->l2te) cxgb4_l2t_release(tx_info->l2te); @@ -384,6 +389,8 @@ static void chcr_ktls_dev_del(struct net_device *netdev, if (tx_info->tid != -1) { cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tx_info->tid, tx_info->ip_family); + + xa_erase(&u_ctx->tid_list, tx_info->tid); } port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; @@ -411,6 +418,7 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct ch_ktls_port_stats_debug *port_stats; struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_uld_ctx *u_ctx; struct chcr_ktls_info *tx_info; struct dst_entry *dst; struct adapter *adap; @@ -425,6 +433,7 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, adap = pi->adapter; port_stats = &adap->ch_ktls_stats.ktls_port[pi->port_id]; atomic64_inc(&port_stats->ktls_tx_connection_open); + u_ctx = adap->uld[CXGB4_ULD_KTLS].handle; if (direction == TLS_OFFLOAD_CTX_DIR_RX) { pr_err("not expecting for RX direction\n"); @@ -434,6 +443,9 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, if (tx_ctx->chcr_info) goto out; + if (u_ctx && u_ctx->detach) + goto out; + tx_info = kvzalloc(sizeof(*tx_info), GFP_KERNEL); if (!tx_info) goto out; @@ -569,6 +581,8 @@ free_tid: cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tx_info->tid, tx_info->ip_family); + xa_erase(&u_ctx->tid_list, tx_info->tid); + put_module: /* release module refcount */ module_put(THIS_MODULE); @@ -633,8 +647,12 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, { const struct cpl_act_open_rpl *p = (void *)input; struct chcr_ktls_info *tx_info = NULL; + struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_uld_ctx *u_ctx; unsigned int atid, tid, status; + struct tls_context *tls_ctx; struct tid_info *t; + int ret = 0; tid = GET_TID(p); status = AOPEN_STATUS_G(ntohl(p->atid_status)); @@ -666,14 +684,29 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, if (!status) { tx_info->tid = tid; cxgb4_insert_tid(t, tx_info, tx_info->tid, tx_info->ip_family); + /* Adding tid */ + tls_ctx = tls_get_ctx(tx_info->sk); + tx_ctx = chcr_get_ktls_tx_context(tls_ctx); + u_ctx = adap->uld[CXGB4_ULD_KTLS].handle; + if (u_ctx) { + ret = xa_insert_bh(&u_ctx->tid_list, tid, tx_ctx, + GFP_NOWAIT); + if (ret < 0) { + pr_err("%s: Failed to allocate tid XA entry = %d\n", + __func__, tx_info->tid); + tx_info->open_state = CH_KTLS_OPEN_FAILURE; + goto out; + } + } tx_info->open_state = CH_KTLS_OPEN_SUCCESS; } else { tx_info->open_state = CH_KTLS_OPEN_FAILURE; } +out: spin_unlock(&tx_info->lock); complete(&tx_info->completion); - return 0; + return ret; } /* @@ -2090,6 +2123,8 @@ static void *chcr_ktls_uld_add(const struct cxgb4_lld_info *lldi) goto out; } u_ctx->lldi = *lldi; + u_ctx->detach = false; + xa_init_flags(&u_ctx->tid_list, XA_FLAGS_LOCK_BH); out: return u_ctx; } @@ -2123,6 +2158,45 @@ static int chcr_ktls_uld_rx_handler(void *handle, const __be64 *rsp, return 0; } +static void clear_conn_resources(struct chcr_ktls_info *tx_info) +{ + /* clear l2t entry */ + if (tx_info->l2te) + cxgb4_l2t_release(tx_info->l2te); + +#if IS_ENABLED(CONFIG_IPV6) + /* clear clip entry */ + if (tx_info->ip_family == AF_INET6) + cxgb4_clip_release(tx_info->netdev, (const u32 *) + &tx_info->sk->sk_v6_rcv_saddr, + 1); +#endif + + /* clear tid */ + if (tx_info->tid != -1) + cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, + tx_info->tid, tx_info->ip_family); +} + +static void ch_ktls_reset_all_conn(struct chcr_ktls_uld_ctx *u_ctx) +{ + struct ch_ktls_port_stats_debug *port_stats; + struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_info *tx_info; + unsigned long index; + + xa_for_each(&u_ctx->tid_list, index, tx_ctx) { + tx_info = tx_ctx->chcr_info; + clear_conn_resources(tx_info); + port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; + atomic64_inc(&port_stats->ktls_tx_connection_close); + kvfree(tx_info); + tx_ctx->chcr_info = NULL; + /* release module refcount */ + module_put(THIS_MODULE); + } +} + static int chcr_ktls_uld_state_change(void *handle, enum cxgb4_state new_state) { struct chcr_ktls_uld_ctx *u_ctx = handle; @@ -2139,7 +2213,10 @@ static int chcr_ktls_uld_state_change(void *handle, enum cxgb4_state new_state) case CXGB4_STATE_DETACH: pr_info("%s: Down\n", pci_name(u_ctx->lldi.pdev)); mutex_lock(&dev_mutex); + u_ctx->detach = true; list_del(&u_ctx->entry); + ch_ktls_reset_all_conn(u_ctx); + xa_destroy(&u_ctx->tid_list); mutex_unlock(&dev_mutex); break; default: @@ -2178,6 +2255,7 @@ static void __exit chcr_ktls_exit(void) adap = pci_get_drvdata(u_ctx->lldi.pdev); memset(&adap->ch_ktls_stats, 0, sizeof(adap->ch_ktls_stats)); list_del(&u_ctx->entry); + xa_destroy(&u_ctx->tid_list); kfree(u_ctx); } mutex_unlock(&dev_mutex); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h index 18b3b1f02415..10572dc55365 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h @@ -75,6 +75,8 @@ struct chcr_ktls_ofld_ctx_tx { struct chcr_ktls_uld_ctx { struct list_head entry; struct cxgb4_lld_info lldi; + struct xarray tid_list; + bool detach; }; static inline struct chcr_ktls_ofld_ctx_tx * diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 188d871f6b8c..c320cc8ca68d 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -1564,8 +1564,10 @@ found_ok_skb: cerr = put_cmsg(msg, SOL_TLS, TLS_GET_RECORD_TYPE, sizeof(thdr->type), &thdr->type); - if (cerr && thdr->type != TLS_RECORD_TYPE_DATA) - return -EIO; + if (cerr && thdr->type != TLS_RECORD_TYPE_DATA) { + copied = -EIO; + break; + } /* don't send tls header, skip copy */ goto skip_copy; } diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index 46b0dbab8aad..7c992172933b 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -576,10 +576,12 @@ static void ec_bhf_remove(struct pci_dev *dev) struct ec_bhf_priv *priv = netdev_priv(net_dev); unregister_netdev(net_dev); - free_netdev(net_dev); pci_iounmap(dev, priv->dma_io); pci_iounmap(dev, priv->io); + + free_netdev(net_dev); + pci_release_regions(dev); pci_clear_master(dev); pci_disable_device(dev); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b6eba29d8e99..7968568bbe21 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5897,6 +5897,7 @@ drv_cleanup: unmap_bars: be_unmap_pci_bars(adapter); free_netdev: + pci_disable_pcie_error_reporting(pdev); free_netdev(netdev); rel_reg: pci_release_regions(pdev); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f2065f9d02e6..ad82cffc6f3f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1662,7 +1662,7 @@ static int fec_enet_rx_napi(struct napi_struct *napi, int budget) } /* ------------------------------------------------------------------------- */ -static void fec_get_mac(struct net_device *ndev) +static int fec_get_mac(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); unsigned char *iap, tmpaddr[ETH_ALEN]; @@ -1685,6 +1685,8 @@ static void fec_get_mac(struct net_device *ndev) ret = of_get_mac_address(np, tmpaddr); if (!ret) iap = tmpaddr; + else if (ret == -EPROBE_DEFER) + return ret; } } @@ -1723,7 +1725,7 @@ static void fec_get_mac(struct net_device *ndev) eth_hw_addr_random(ndev); dev_info(&fep->pdev->dev, "Using random MAC address: %pM\n", ndev->dev_addr); - return; + return 0; } memcpy(ndev->dev_addr, iap, ETH_ALEN); @@ -1731,6 +1733,8 @@ static void fec_get_mac(struct net_device *ndev) /* Adjust MAC if using macaddr */ if (iap == macaddr) ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id; + + return 0; } /* ------------------------------------------------------------------------- */ @@ -3290,7 +3294,9 @@ static int fec_enet_init(struct net_device *ndev) return ret; } - fec_enet_alloc_queue(ndev); + ret = fec_enet_alloc_queue(ndev); + if (ret) + return ret; bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize; @@ -3298,11 +3304,15 @@ static int fec_enet_init(struct net_device *ndev) cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma, GFP_KERNEL); if (!cbd_base) { - return -ENOMEM; + ret = -ENOMEM; + goto free_queue_mem; } /* Get the Ethernet address */ - fec_get_mac(ndev); + ret = fec_get_mac(ndev); + if (ret) + goto free_queue_mem; + /* make sure MAC we just acquired is programmed into the hw */ fec_set_mac_address(ndev, NULL); @@ -3376,6 +3386,10 @@ static int fec_enet_init(struct net_device *ndev) fec_enet_update_ethtool_stats(ndev); return 0; + +free_queue_mem: + fec_enet_free_queue(ndev); + return ret; } #ifdef CONFIG_OF diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 1753807cbf97..d71eac7e1924 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -215,15 +215,13 @@ static u64 fec_ptp_read(const struct cyclecounter *cc) { struct fec_enet_private *fep = container_of(cc, struct fec_enet_private, cc); - const struct platform_device_id *id_entry = - platform_get_device_id(fep->pdev); u32 tempval; tempval = readl(fep->hwp + FEC_ATIME_CTRL); tempval |= FEC_T_CTRL_CAPTURE; writel(tempval, fep->hwp + FEC_ATIME_CTRL); - if (id_entry->driver_data & FEC_QUIRK_BUG_CAPTURE) + if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) udelay(1); return readl(fep->hwp + FEC_ATIME); @@ -604,6 +602,10 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) fep->ptp_caps.enable = fec_ptp_enable; fep->cycle_speed = clk_get_rate(fep->clk_ptp); + if (!fep->cycle_speed) { + fep->cycle_speed = NSEC_PER_SEC; + dev_err(&fep->pdev->dev, "clk_ptp clock rate is zero\n"); + } fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed; spin_lock_init(&fep->tmreg_lock); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 7302498c6df3..bbc423e93122 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -180,7 +180,7 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) /* Double check we have no extra work. * Ensure unmask synchronizes with checking for work. */ - dma_rmb(); + mb(); if (block->tx) reschedule |= gve_tx_poll(block, -1); if (block->rx) @@ -220,6 +220,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) int vecs_left = new_num_ntfy_blks % 2; priv->num_ntfy_blks = new_num_ntfy_blks; + priv->mgmt_msix_idx = priv->num_ntfy_blks; priv->tx_cfg.max_queues = min_t(int, priv->tx_cfg.max_queues, vecs_per_type); priv->rx_cfg.max_queues = min_t(int, priv->rx_cfg.max_queues, @@ -300,20 +301,22 @@ static void gve_free_notify_blocks(struct gve_priv *priv) { int i; - /* Free the irqs */ - for (i = 0; i < priv->num_ntfy_blks; i++) { - struct gve_notify_block *block = &priv->ntfy_blocks[i]; - int msix_idx = i; + if (priv->msix_vectors) { + /* Free the irqs */ + for (i = 0; i < priv->num_ntfy_blks; i++) { + struct gve_notify_block *block = &priv->ntfy_blocks[i]; + int msix_idx = i; - irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, - NULL); - free_irq(priv->msix_vectors[msix_idx].vector, block); + irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, + NULL); + free_irq(priv->msix_vectors[msix_idx].vector, block); + } + free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); } dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks), priv->ntfy_blocks, priv->ntfy_block_bus); priv->ntfy_blocks = NULL; - free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); pci_disable_msix(priv->pdev); kvfree(priv->msix_vectors); priv->msix_vectors = NULL; diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 6938f3a939d6..3e04a3973d68 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -212,10 +212,11 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) tx->dev = &priv->pdev->dev; if (!tx->raw_addressing) { tx->tx_fifo.qpl = gve_assign_tx_qpl(priv); - + if (!tx->tx_fifo.qpl) + goto abort_with_desc; /* map Tx FIFO */ if (gve_tx_fifo_init(priv, &tx->tx_fifo)) - goto abort_with_desc; + goto abort_with_qpl; } tx->q_resources = @@ -236,6 +237,9 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) abort_with_fifo: if (!tx->raw_addressing) gve_tx_fifo_release(priv, &tx->tx_fifo); +abort_with_qpl: + if (!tx->raw_addressing) + gve_unassign_qpl(priv, tx->tx_fifo.qpl->id); abort_with_desc: dma_free_coherent(hdev, bytes, tx->desc, tx->bus); tx->desc = NULL; @@ -589,7 +593,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) struct gve_tx_ring *tx; int nsegs; - WARN(skb_get_queue_mapping(skb) > priv->tx_cfg.num_queues, + WARN(skb_get_queue_mapping(skb) >= priv->tx_cfg.num_queues, "skb queue index out of range"); tx = &priv->tx[skb_get_queue_mapping(skb)]; if (unlikely(gve_maybe_stop_tx(tx, skb))) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index da48c05435ea..7e62dcff2426 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -192,7 +192,7 @@ static int hns_nic_get_link_ksettings(struct net_device *net_dev, } /** - *hns_nic_set_link_settings - implement ethtool set link ksettings + *hns_nic_set_link_ksettings - implement ethtool set link ksettings *@net_dev: net_device *@cmd: ethtool_link_ksettings *retuen 0 - success , negative --fail @@ -827,7 +827,7 @@ hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) } /** - * get_ethtool_stats - get detail statistics. + * hns_get_ethtool_stats - get detail statistics. * @netdev: net device * @stats: statistics info. * @data: statistics data. @@ -885,7 +885,7 @@ static void hns_get_ethtool_stats(struct net_device *netdev, } /** - * get_strings: Return a set of strings that describe the requested objects + * hns_get_strings: Return a set of strings that describe the requested objects * @netdev: net device * @stringset: string set ID. * @data: objects data. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 783fdaf8f8d6..026558f8e04b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -264,22 +264,17 @@ static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector, struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev); struct hns3_enet_coalesce *tx_coal = &tqp_vector->tx_group.coal; struct hns3_enet_coalesce *rx_coal = &tqp_vector->rx_group.coal; + struct hns3_enet_coalesce *ptx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *prx_coal = &priv->rx_coal; - /* initialize the configuration for interrupt coalescing. - * 1. GL (Interrupt Gap Limiter) - * 2. RL (Interrupt Rate Limiter) - * 3. QL (Interrupt Quantity Limiter) - * - * Default: enable interrupt coalescing self-adaptive and GL - */ - tx_coal->adapt_enable = 1; - rx_coal->adapt_enable = 1; + tx_coal->adapt_enable = ptx_coal->adapt_enable; + rx_coal->adapt_enable = prx_coal->adapt_enable; - tx_coal->int_gl = HNS3_INT_GL_50K; - rx_coal->int_gl = HNS3_INT_GL_50K; + tx_coal->int_gl = ptx_coal->int_gl; + rx_coal->int_gl = prx_coal->int_gl; - rx_coal->flow_level = HNS3_FLOW_LOW; - tx_coal->flow_level = HNS3_FLOW_LOW; + rx_coal->flow_level = prx_coal->flow_level; + tx_coal->flow_level = ptx_coal->flow_level; /* device version above V3(include V3), GL can configure 1us * unit, so uses 1us unit. @@ -294,8 +289,8 @@ static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector, rx_coal->ql_enable = 1; tx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max; rx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max; - tx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; - rx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + tx_coal->int_ql = ptx_coal->int_ql; + rx_coal->int_ql = prx_coal->int_ql; } } @@ -846,8 +841,6 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) l4.udp->dest == htons(4790)))) return false; - skb_checksum_help(skb); - return true; } @@ -924,8 +917,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, /* the stack computes the IP header already, * driver calculate l4 checksum when not TSO. */ - skb_checksum_help(skb); - return 0; + return skb_checksum_help(skb); } hns3_set_outer_l2l3l4(skb, ol4_proto, ol_type_vlan_len_msec); @@ -970,7 +962,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, break; case IPPROTO_UDP: if (hns3_tunnel_csum_bug(skb)) - break; + return skb_checksum_help(skb); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S, @@ -995,8 +987,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, /* the stack computes the IP header already, * driver calculate l4 checksum when not TSO. */ - skb_checksum_help(skb); - return 0; + return skb_checksum_help(skb); } return 0; @@ -3844,6 +3835,34 @@ map_ring_fail: return ret; } +static void hns3_nic_init_coal_cfg(struct hns3_nic_priv *priv) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; + + /* initialize the configuration for interrupt coalescing. + * 1. GL (Interrupt Gap Limiter) + * 2. RL (Interrupt Rate Limiter) + * 3. QL (Interrupt Quantity Limiter) + * + * Default: enable interrupt coalescing self-adaptive and GL + */ + tx_coal->adapt_enable = 1; + rx_coal->adapt_enable = 1; + + tx_coal->int_gl = HNS3_INT_GL_50K; + rx_coal->int_gl = HNS3_INT_GL_50K; + + rx_coal->flow_level = HNS3_FLOW_LOW; + tx_coal->flow_level = HNS3_FLOW_LOW; + + if (ae_dev->dev_specs.int_ql_max) { + tx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + rx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + } +} + static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; @@ -4295,6 +4314,8 @@ static int hns3_client_init(struct hnae3_handle *handle) goto out_get_ring_cfg; } + hns3_nic_init_coal_cfg(priv); + ret = hns3_nic_alloc_vector_data(priv); if (ret) { ret = -ENOMEM; @@ -4317,12 +4338,6 @@ static int hns3_client_init(struct hnae3_handle *handle) if (ret) goto out_init_phy; - ret = register_netdev(netdev); - if (ret) { - dev_err(priv->dev, "probe register netdev fail!\n"); - goto out_reg_netdev_fail; - } - /* the device can work without cpu rmap, only aRFS needs it */ ret = hns3_set_rx_cpu_rmap(netdev); if (ret) @@ -4355,17 +4370,23 @@ static int hns3_client_init(struct hnae3_handle *handle) if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags); + ret = register_netdev(netdev); + if (ret) { + dev_err(priv->dev, "probe register netdev fail!\n"); + goto out_reg_netdev_fail; + } + if (netif_msg_drv(handle)) hns3_info_show(priv); return ret; +out_reg_netdev_fail: + hns3_dbg_uninit(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv); out_init_irq_fail: - unregister_netdev(netdev); -out_reg_netdev_fail: hns3_uninit_phy(netdev); out_init_phy: hns3_uninit_all_ring(priv); @@ -4571,31 +4592,6 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h) return 0; } -static void hns3_store_coal(struct hns3_nic_priv *priv) -{ - /* ethtool only support setting and querying one coal - * configuration for now, so save the vector 0' coal - * configuration here in order to restore it. - */ - memcpy(&priv->tx_coal, &priv->tqp_vector[0].tx_group.coal, - sizeof(struct hns3_enet_coalesce)); - memcpy(&priv->rx_coal, &priv->tqp_vector[0].rx_group.coal, - sizeof(struct hns3_enet_coalesce)); -} - -static void hns3_restore_coal(struct hns3_nic_priv *priv) -{ - u16 vector_num = priv->vector_num; - int i; - - for (i = 0; i < vector_num; i++) { - memcpy(&priv->tqp_vector[i].tx_group.coal, &priv->tx_coal, - sizeof(struct hns3_enet_coalesce)); - memcpy(&priv->tqp_vector[i].rx_group.coal, &priv->rx_coal, - sizeof(struct hns3_enet_coalesce)); - } -} - static int hns3_reset_notify_down_enet(struct hnae3_handle *handle) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; @@ -4654,8 +4650,6 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) if (ret) goto err_put_ring; - hns3_restore_coal(priv); - ret = hns3_nic_init_vector_data(priv); if (ret) goto err_dealloc_vector; @@ -4721,8 +4715,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) hns3_nic_uninit_vector_data(priv); - hns3_store_coal(priv); - hns3_nic_dealloc_vector_data(priv); hns3_uninit_all_ring(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index b48faf769b1c..c1ea403d2b56 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1134,50 +1134,32 @@ static void hns3_get_channels(struct net_device *netdev, h->ae_algo->ops->get_channels(h, ch); } -static int hns3_get_coalesce_per_queue(struct net_device *netdev, u32 queue, - struct ethtool_coalesce *cmd) +static int hns3_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *cmd) { - struct hns3_enet_tqp_vector *tx_vector, *rx_vector; struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; struct hnae3_handle *h = priv->ae_handle; - u16 queue_num = h->kinfo.num_tqps; if (hns3_nic_resetting(netdev)) return -EBUSY; - if (queue >= queue_num) { - netdev_err(netdev, - "Invalid queue value %u! Queue max id=%u\n", - queue, queue_num - 1); - return -EINVAL; - } - - tx_vector = priv->ring[queue].tqp_vector; - rx_vector = priv->ring[queue_num + queue].tqp_vector; + cmd->use_adaptive_tx_coalesce = tx_coal->adapt_enable; + cmd->use_adaptive_rx_coalesce = rx_coal->adapt_enable; - cmd->use_adaptive_tx_coalesce = - tx_vector->tx_group.coal.adapt_enable; - cmd->use_adaptive_rx_coalesce = - rx_vector->rx_group.coal.adapt_enable; - - cmd->tx_coalesce_usecs = tx_vector->tx_group.coal.int_gl; - cmd->rx_coalesce_usecs = rx_vector->rx_group.coal.int_gl; + cmd->tx_coalesce_usecs = tx_coal->int_gl; + cmd->rx_coalesce_usecs = rx_coal->int_gl; cmd->tx_coalesce_usecs_high = h->kinfo.int_rl_setting; cmd->rx_coalesce_usecs_high = h->kinfo.int_rl_setting; - cmd->tx_max_coalesced_frames = tx_vector->tx_group.coal.int_ql; - cmd->rx_max_coalesced_frames = rx_vector->rx_group.coal.int_ql; + cmd->tx_max_coalesced_frames = tx_coal->int_ql; + cmd->rx_max_coalesced_frames = rx_coal->int_ql; return 0; } -static int hns3_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *cmd) -{ - return hns3_get_coalesce_per_queue(netdev, 0, cmd); -} - static int hns3_check_gl_coalesce_para(struct net_device *netdev, struct ethtool_coalesce *cmd) { @@ -1292,19 +1274,7 @@ static int hns3_check_coalesce_para(struct net_device *netdev, return ret; } - ret = hns3_check_ql_coalesce_param(netdev, cmd); - if (ret) - return ret; - - if (cmd->use_adaptive_tx_coalesce == 1 || - cmd->use_adaptive_rx_coalesce == 1) { - netdev_info(netdev, - "adaptive-tx=%u and adaptive-rx=%u, tx_usecs or rx_usecs will changed dynamically.\n", - cmd->use_adaptive_tx_coalesce, - cmd->use_adaptive_rx_coalesce); - } - - return 0; + return hns3_check_ql_coalesce_param(netdev, cmd); } static void hns3_set_coalesce_per_queue(struct net_device *netdev, @@ -1350,6 +1320,9 @@ static int hns3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *cmd) { struct hnae3_handle *h = hns3_get_handle(netdev); + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; u16 queue_num = h->kinfo.num_tqps; int ret; int i; @@ -1364,6 +1337,15 @@ static int hns3_set_coalesce(struct net_device *netdev, h->kinfo.int_rl_setting = hns3_rl_round_down(cmd->rx_coalesce_usecs_high); + tx_coal->adapt_enable = cmd->use_adaptive_tx_coalesce; + rx_coal->adapt_enable = cmd->use_adaptive_rx_coalesce; + + tx_coal->int_gl = cmd->tx_coalesce_usecs; + rx_coal->int_gl = cmd->rx_coalesce_usecs; + + tx_coal->int_ql = cmd->tx_max_coalesced_frames; + rx_coal->int_ql = cmd->rx_max_coalesced_frames; + for (i = 0; i < queue_num; i++) hns3_set_coalesce_per_queue(netdev, cmd, i); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 8e5f9dc8791d..f1c9f4ada348 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -710,7 +710,6 @@ void hclge_mbx_handler(struct hclge_dev *hdev) unsigned int flag; int ret = 0; - memset(&resp_msg, 0, sizeof(resp_msg)); /* handle all the mailbox requests in the queue */ while (!hclge_cmd_crq_empty(&hdev->hw)) { if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) { @@ -738,6 +737,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) trace_hclge_pf_mbx_get(hdev, req); + /* clear the resp_msg before processing every mailbox message */ + memset(&resp_msg, 0, sizeof(resp_msg)); + switch (req->msg.code) { case HCLGE_MBX_MAP_RING_TO_VECTOR: ret = hclge_map_unmap_ring_to_vf_vector(vport, true, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index de70c16ef619..b883ab809df3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2313,15 +2313,20 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + if (result == I40E_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + if (err) + goto out_failure; + result = I40E_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 46d884417c63..68f177a86403 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -162,9 +162,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return I40E_XDP_REDIR; } switch (act) { @@ -173,11 +174,14 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + if (result == I40E_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index e35db3ff583b..2924c67567b8 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -335,6 +335,7 @@ struct ice_vsi { struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_ring **xdp_rings; /* XDP ring array */ + unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ @@ -547,15 +548,16 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring) */ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring) { + struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; if (ice_ring_is_xdp(ring)) - qid -= ring->vsi->num_xdp_txq; + qid -= vsi->num_xdp_txq; - if (!ice_is_xdp_ena_vsi(ring->vsi)) + if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) return NULL; - return xsk_get_pool_from_qid(ring->vsi->netdev, qid); + return xsk_get_pool_from_qid(vsi->netdev, qid); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index d9ddd0bcf65f..99301ad95290 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1773,49 +1773,6 @@ ice_phy_type_to_ethtool(struct net_device *netdev, ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, 100000baseKR4_Full); } - - /* Autoneg PHY types */ - if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || - phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX || - phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX || - phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR || - phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 || - phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || - phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { - ethtool_link_ksettings_add_link_mode(ks, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - Autoneg); - } - if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 || - phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 || - phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP || - phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) { - ethtool_link_ksettings_add_link_mode(ks, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - Autoneg); - } - if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 || - phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 || - phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 || - phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) { - ethtool_link_ksettings_add_link_mode(ks, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - Autoneg); - } } #define TEST_SET_BITS_TIMEOUT 50 @@ -1972,9 +1929,7 @@ ice_get_link_ksettings(struct net_device *netdev, ks->base.port = PORT_TP; break; case ICE_MEDIA_BACKPLANE: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); ethtool_link_ksettings_add_link_mode(ks, supported, Backplane); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); ethtool_link_ksettings_add_link_mode(ks, advertising, Backplane); ks->base.port = PORT_NONE; @@ -2049,6 +2004,12 @@ ice_get_link_ksettings(struct net_device *netdev, if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN) ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + /* Set supported and advertised autoneg */ + if (ice_is_phy_caps_an_enabled(caps)) { + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + } + done: kfree(caps); return err; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index de38a0fc9665..9b8300d4a267 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -31,6 +31,7 @@ #define PF_FW_ATQLEN_ATQOVFL_M BIT(29) #define PF_FW_ATQLEN_ATQCRIT_M BIT(30) #define VF_MBX_ARQLEN(_VF) (0x0022BC00 + ((_VF) * 4)) +#define VF_MBX_ATQLEN(_VF) (0x0022A800 + ((_VF) * 4)) #define PF_FW_ATQLEN_ATQENABLE_M BIT(31) #define PF_FW_ATQT 0x00080400 #define PF_MBX_ARQBAH 0x0022E400 diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 82e2ce23df3d..27f9dac8719c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -105,8 +105,14 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->q_vectors) goto err_vectors; + vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); + if (!vsi->af_xdp_zc_qps) + goto err_zc_qps; + return 0; +err_zc_qps: + devm_kfree(dev, vsi->q_vectors); err_vectors: devm_kfree(dev, vsi->rxq_map); err_rxq_map: @@ -194,6 +200,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) break; case ICE_VSI_VF: vf = &pf->vf[vsi->vf_id]; + if (vf->num_req_qs) + vf->num_vf_qs = vf->num_req_qs; vsi->alloc_txq = vf->num_vf_qs; vsi->alloc_rxq = vf->num_vf_qs; /* pf->num_msix_per_vf includes (VF miscellaneous vector + @@ -288,6 +296,10 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); + if (vsi->af_xdp_zc_qps) { + bitmap_free(vsi->af_xdp_zc_qps); + vsi->af_xdp_zc_qps = NULL; + } /* free the ring and vector containers */ if (vsi->q_vectors) { devm_kfree(dev, vsi->q_vectors); @@ -1705,12 +1717,13 @@ setup_rings: * ice_vsi_cfg_txqs - Configure the VSI for Tx * @vsi: the VSI being configured * @rings: Tx ring array to be configured + * @count: number of Tx ring array elements * * Return 0 on success and a negative value on error * Configure the Tx VSI for operation. */ static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count) { struct ice_aqc_add_tx_qgrp *qg_buf; u16 q_idx = 0; @@ -1722,7 +1735,7 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) qg_buf->num_txqs = 1; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); if (err) goto err_cfg_txqs; @@ -1742,7 +1755,7 @@ err_cfg_txqs: */ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) { - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings); + return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); } /** @@ -1757,7 +1770,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) int ret; int i; - ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings); + ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); if (ret) return ret; @@ -1997,17 +2010,18 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) * @rst_src: reset source * @rel_vmvf_num: Relative ID of VF/VM * @rings: Tx ring array to be stopped + * @count: number of Tx ring array elements */ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings) + u16 rel_vmvf_num, struct ice_ring **rings, u16 count) { u16 q_idx; if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) return -EINVAL; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { struct ice_txq_meta txq_meta = { }; int status; @@ -2035,7 +2049,7 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num) { - return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings); + return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, vsi->num_txq); } /** @@ -2044,7 +2058,7 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, */ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) { - return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings); + return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings, vsi->num_xdp_txq); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4ee85a217c6f..0eb2307325d3 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2556,6 +2556,20 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } /** + * ice_xdp_safe_mode - XDP handler for safe mode + * @dev: netdevice + * @xdp: XDP command + */ +static int ice_xdp_safe_mode(struct net_device __always_unused *dev, + struct netdev_bpf *xdp) +{ + NL_SET_ERR_MSG_MOD(xdp->extack, + "Please provide working DDP firmware package in order to use XDP\n" + "Refer to Documentation/networking/device_drivers/ethernet/intel/ice.rst"); + return -EOPNOTSUPP; +} + +/** * ice_xdp - implements XDP handler * @dev: netdevice * @xdp: XDP command @@ -6937,6 +6951,7 @@ static const struct net_device_ops ice_netdev_safe_mode_ops = { .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, .ndo_tx_timeout = ice_tx_timeout, + .ndo_bpf = ice_xdp_safe_mode, }; static const struct net_device_ops ice_netdev_ops = { diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index e2b4b29ea207..04748aa4c7c8 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -523,7 +523,7 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct ice_ring *xdp_ring; - int err; + int err, result; u32 act; act = bpf_prog_run_xdp(xdp_prog, xdp); @@ -532,14 +532,20 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, return ICE_XDP_PASS; case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()]; - return ice_xmit_xdp_buff(xdp, xdp_ring); + result = ice_xmit_xdp_buff(xdp, xdp_ring); + if (result == ICE_XDP_CONSUMED) + goto out_failure; + return result; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; + if (err) + goto out_failure; + return ICE_XDP_REDIR; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: @@ -2143,6 +2149,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) struct ice_tx_offload_params offload = { 0 }; struct ice_vsi *vsi = tx_ring->vsi; struct ice_tx_buf *first; + struct ethhdr *eth; unsigned int count; int tso, csum; @@ -2189,7 +2196,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) goto out_drop; /* allow CONTROL frames egress from main VSI if FW LLDP disabled */ - if (unlikely(skb->priority == TC_PRIO_CONTROL && + eth = (struct ethhdr *)skb_mac_header(skb); + if (unlikely((skb->priority == TC_PRIO_CONTROL || + eth->h_proto == htons(ETH_P_LLDP)) && vsi->type == ICE_VSI_PF && vsi->port_info->qos_cfg.is_sw_lldp)) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index a1d22d2aa0bd..97a46c616aca 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -713,13 +713,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) */ clear_bit(ICE_VF_STATE_INIT, vf->vf_states); - /* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it - * in the case of VFR. If this is done for PFR, it can mess up VF - * resets because the VF driver may already have started cleanup - * by the time we get here. + /* VF_MBX_ARQLEN and VF_MBX_ATQLEN are cleared by PFR, so the driver + * needs to clear them in the case of VFR/VFLR. If this is done for + * PFR, it can mess up VF resets because the VF driver may already + * have started cleanup by the time we get here. */ - if (!is_pfr) + if (!is_pfr) { wr32(hw, VF_MBX_ARQLEN(vf->vf_id), 0); + wr32(hw, VF_MBX_ATQLEN(vf->vf_id), 0); + } /* In the case of a VFLR, the HW has already reset the VF and we * just need to clean up, so don't hit the VFRTRIG register. @@ -1698,7 +1700,12 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) ice_vf_ctrl_vsi_release(vf); ice_vf_pre_vsi_rebuild(vf); - ice_vf_rebuild_vsi_with_release(vf); + + if (ice_vf_rebuild_vsi_with_release(vf)) { + dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id); + return false; + } + ice_vf_post_vsi_rebuild(vf); /* if the VF has been reset allow it to come up again */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index faa7b8d96adb..a1f89ea3c2bd 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -270,6 +270,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) if (!pool) return -EINVAL; + clear_bit(qid, vsi->af_xdp_zc_qps); xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR); return 0; @@ -300,6 +301,8 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) if (err) return err; + set_bit(qid, vsi->af_xdp_zc_qps); + return 0; } @@ -473,9 +476,10 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return ICE_XDP_REDIR; } switch (act) { @@ -484,11 +488,14 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index]; result = ice_xmit_xdp_buff(xdp, xdp_ring); + if (result == ICE_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 7bda8c5edea5..2d3daf022651 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -749,7 +749,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_tx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb); + ktime_t *timestamp); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); void igb_set_flag_queue_pairs(struct igb_adapter *, const u32); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 038a9fd1af44..b2a042f825ff 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8280,7 +8280,7 @@ static void igb_add_rx_frag(struct igb_ring *rx_ring, static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, struct xdp_buff *xdp, - union e1000_adv_rx_desc *rx_desc) + ktime_t timestamp) { #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; @@ -8300,12 +8300,8 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, if (unlikely(!skb)) return NULL; - if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { - if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) { - xdp->data += IGB_TS_HDR_LEN; - size -= IGB_TS_HDR_LEN; - } - } + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; /* Determine available headroom for copy */ headlen = size; @@ -8336,7 +8332,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, struct xdp_buff *xdp, - union e1000_adv_rx_desc *rx_desc) + ktime_t timestamp) { #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; @@ -8363,11 +8359,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, if (metasize) skb_metadata_set(skb, metasize); - /* pull timestamp out of packet data */ - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb)) - __skb_pull(skb, IGB_TS_HDR_LEN); - } + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; /* update buffer offset */ #if (PAGE_SIZE < 8192) @@ -8401,18 +8394,20 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, break; case XDP_TX: result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); - if (!err) - result = IGB_XDP_REDIR; - else - result = IGB_XDP_CONSUMED; + if (err) + goto out_failure; + result = IGB_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: @@ -8682,7 +8677,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; struct igb_rx_buffer *rx_buffer; + ktime_t timestamp = 0; + int pkt_offset = 0; unsigned int size; + void *pktbuf; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { @@ -8702,14 +8700,24 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) dma_rmb(); rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt); + pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset; + + /* pull rx packet timestamp if available and valid */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + int ts_hdr_len; + + ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector, + pktbuf, ×tamp); + + pkt_offset += ts_hdr_len; + size -= ts_hdr_len; + } /* retrieve a buffer from the ring */ if (!skb) { - unsigned int offset = igb_rx_offset(rx_ring); - unsigned char *hard_start; + unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring); + unsigned int offset = pkt_offset + igb_rx_offset(rx_ring); - hard_start = page_address(rx_buffer->page) + - rx_buffer->page_offset - offset; xdp_prepare_buff(&xdp, hard_start, offset, size, true); #if (PAGE_SIZE > 4096) /* At larger PAGE_SIZE, frame_sz depend on len size */ @@ -8732,10 +8740,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) } else if (skb) igb_add_rx_frag(rx_ring, rx_buffer, skb, size); else if (ring_uses_build_skb(rx_ring)) - skb = igb_build_skb(rx_ring, rx_buffer, &xdp, rx_desc); + skb = igb_build_skb(rx_ring, rx_buffer, &xdp, + timestamp); else skb = igb_construct_skb(rx_ring, rx_buffer, - &xdp, rx_desc); + &xdp, timestamp); /* exit if we failed to retrieve a buffer */ if (!skb) { diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index ba61fe9bfaf4..d68cd4466a54 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -856,30 +856,28 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) dev_kfree_skb_any(skb); } -#define IGB_RET_PTP_DISABLED 1 -#define IGB_RET_PTP_INVALID 2 - /** * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp * @q_vector: Pointer to interrupt specific structure * @va: Pointer to address containing Rx buffer - * @skb: Buffer containing timestamp and packet + * @timestamp: Pointer where timestamp will be stored * * This function is meant to retrieve a timestamp from the first buffer of an * incoming frame. The value is stored in little endian format starting on * byte 8 * - * Returns: 0 if success, nonzero if failure + * Returns: The timestamp header length or 0 if not available **/ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb) + ktime_t *timestamp) { struct igb_adapter *adapter = q_vector->adapter; + struct skb_shared_hwtstamps ts; __le64 *regval = (__le64 *)va; int adjust = 0; if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) - return IGB_RET_PTP_DISABLED; + return 0; /* The timestamp is recorded in little endian format. * DWORD: 0 1 2 3 @@ -888,10 +886,9 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, /* check reserved dwords are zero, be/le doesn't matter for zero */ if (regval[0]) - return IGB_RET_PTP_INVALID; + return 0; - igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), - le64_to_cpu(regval[1])); + igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1])); /* adjust timestamp for the RX latency based on link speed */ if (adapter->hw.mac.type == e1000_i210) { @@ -907,10 +904,10 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, break; } } - skb_hwtstamps(skb)->hwtstamp = - ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); - return 0; + *timestamp = ktime_sub_ns(ts.hwtstamp, adjust); + + return IGB_TS_HDR_LEN; } /** diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 069471b7ffb0..f1adf154ec4a 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2047,20 +2047,19 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, break; case XDP_TX: if (igc_xdp_xmit_back(adapter, xdp) < 0) - res = IGC_XDP_CONSUMED; - else - res = IGC_XDP_TX; + goto out_failure; + res = IGC_XDP_TX; break; case XDP_REDIRECT: if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0) - res = IGC_XDP_CONSUMED; - else - res = IGC_XDP_REDIRECT; + goto out_failure; + res = IGC_XDP_REDIRECT; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(adapter->netdev, prog, act); fallthrough; case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index c5ec17d19c59..2ac5b82676f3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2213,23 +2213,23 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, break; case XDP_TX: xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) { - result = IXGBE_XDP_CONSUMED; - break; - } + if (unlikely(!xdpf)) + goto out_failure; result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); - if (!err) - result = IXGBE_XDP_REDIR; - else - result = IXGBE_XDP_CONSUMED; + if (err) + goto out_failure; + result = IXGBE_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 988db46bff0e..214a38de3f41 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -467,12 +467,16 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, return err; } -static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int max_frame = msgbuf[1]; u32 max_frs; + if (max_frame < ETH_MIN_MTU || max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return -EINVAL; + } + /* * For 82599EB we have to keep all PFs and VFs operating with * the same max_frame value in order to avoid sending an oversize @@ -533,12 +537,6 @@ static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) } } - /* MTU < 68 is an error and causes problems on some kernels */ - if (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { - e_err(drv, "VF max_frame %d out of range\n", max_frame); - return -EINVAL; - } - /* pull current max frame size from hardware */ max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); max_frs &= IXGBE_MHADD_MFS_MASK; @@ -1249,7 +1247,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf); break; case IXGBE_VF_SET_LPE: - retval = ixgbe_set_vf_lpe(adapter, msgbuf, vf); + retval = ixgbe_set_vf_lpe(adapter, msgbuf[1], vf); break; case IXGBE_VF_SET_MACVLAN: retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 91ad5b902673..f72d2978263b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -106,9 +106,10 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return IXGBE_XDP_REDIR; } switch (act) { @@ -116,16 +117,17 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, break; case XDP_TX: xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) { - result = IXGBE_XDP_CONSUMED; - break; - } + if (unlikely(!xdpf)) + goto out_failure; result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index ba2ed8a43d2d..0e733cc15c58 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1067,11 +1067,14 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, case XDP_TX: xdp_ring = adapter->xdp_ring[rx_ring->queue_index]; result = ixgbevf_xmit_xdp_ring(xdp_ring, xdp); + if (result == IXGBEVF_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 6f987a7ffcb3..b30a45725374 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1315,23 +1315,23 @@ static int korina_probe(struct platform_device *pdev) lp->tx_irq = platform_get_irq_byname(pdev, "tx"); p = devm_platform_ioremap_resource_byname(pdev, "emac"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->eth_regs = p; p = devm_platform_ioremap_resource_byname(pdev, "dma_rx"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap Rx DMA registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->rx_dma_regs = p; p = devm_platform_ioremap_resource_byname(pdev, "dma_tx"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap Tx DMA registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->tx_dma_regs = p; diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 41c2ad210bc9..21ef2f128070 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -154,6 +154,8 @@ static int xrx200_close(struct net_device *net_dev) static int xrx200_alloc_skb(struct xrx200_chan *ch) { + struct sk_buff *skb = ch->skb[ch->dma.desc]; + dma_addr_t mapping; int ret = 0; ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev, @@ -163,16 +165,18 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch) goto skip; } - ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(ch->priv->dev, - ch->skb[ch->dma.desc]->data, XRX200_DMA_DATA_LEN, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(ch->priv->dev, - ch->dma.desc_base[ch->dma.desc].addr))) { + mapping = dma_map_single(ch->priv->dev, ch->skb[ch->dma.desc]->data, + XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) { dev_kfree_skb_any(ch->skb[ch->dma.desc]); + ch->skb[ch->dma.desc] = skb; ret = -ENOMEM; goto skip; } + ch->dma.desc_base[ch->dma.desc].addr = mapping; + /* Make sure the address is written before we give it to HW */ + wmb(); skip: ch->dma.desc_base[ch->dma.desc].ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | @@ -196,6 +200,7 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) ch->dma.desc %= LTQ_DESC_NUM; if (ret) { + net_dev->stats.rx_dropped++; netdev_err(net_dev, "failed to allocate new rx buffer\n"); return ret; } @@ -348,8 +353,8 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr) struct xrx200_chan *ch = ptr; if (napi_schedule_prep(&ch->napi)) { - __napi_schedule(&ch->napi); ltq_dma_disable_irq(&ch->dma); + __napi_schedule(&ch->napi); } ltq_dma_ack_irq(&ch->dma); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 8edba5ea90f0..4a61c90003b5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -993,6 +993,14 @@ enum mvpp22_ptp_packet_format { #define MVPP2_DESC_DMA_MASK DMA_BIT_MASK(40) +/* Buffer header info bits */ +#define MVPP2_B_HDR_INFO_MC_ID_MASK 0xfff +#define MVPP2_B_HDR_INFO_MC_ID(info) ((info) & MVPP2_B_HDR_INFO_MC_ID_MASK) +#define MVPP2_B_HDR_INFO_LAST_OFFS 12 +#define MVPP2_B_HDR_INFO_LAST_MASK BIT(12) +#define MVPP2_B_HDR_INFO_IS_LAST(info) \ + (((info) & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS) + struct mvpp2_tai; /* Definitions */ @@ -1002,6 +1010,20 @@ struct mvpp2_rss_table { u32 indir[MVPP22_RSS_TABLE_ENTRIES]; }; +struct mvpp2_buff_hdr { + __le32 next_phys_addr; + __le32 next_dma_addr; + __le16 byte_count; + __le16 info; + __le16 reserved1; /* bm_qset (for future use, BM) */ + u8 next_phys_addr_high; + u8 next_dma_addr_high; + __le16 reserved2; + __le16 reserved3; + __le16 reserved4; + __le16 reserved5; +}; + /* Shared Packet Processor resources */ struct mvpp2 { /* Shared registers' base addresses */ diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ec706d614cac..d39c7639cdba 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3839,6 +3839,35 @@ mvpp2_run_xdp(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq, return ret; } +static void mvpp2_buff_hdr_pool_put(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc, + int pool, u32 rx_status) +{ + phys_addr_t phys_addr, phys_addr_next; + dma_addr_t dma_addr, dma_addr_next; + struct mvpp2_buff_hdr *buff_hdr; + + phys_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc); + dma_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); + + do { + buff_hdr = (struct mvpp2_buff_hdr *)phys_to_virt(phys_addr); + + phys_addr_next = le32_to_cpu(buff_hdr->next_phys_addr); + dma_addr_next = le32_to_cpu(buff_hdr->next_dma_addr); + + if (port->priv->hw_version >= MVPP22) { + phys_addr_next |= ((u64)buff_hdr->next_phys_addr_high << 32); + dma_addr_next |= ((u64)buff_hdr->next_dma_addr_high << 32); + } + + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); + + phys_addr = phys_addr_next; + dma_addr = dma_addr_next; + + } while (!MVPP2_B_HDR_INFO_IS_LAST(le16_to_cpu(buff_hdr->info))); +} + /* Main rx processing */ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, int rx_todo, struct mvpp2_rx_queue *rxq) @@ -3885,14 +3914,6 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, MVPP2_RXD_BM_POOL_ID_OFFS; bm_pool = &port->priv->bm_pools[pool]; - /* In case of an error, release the requested buffer pointer - * to the Buffer Manager. This request process is controlled - * by the hardware, and the information about the buffer is - * comprised by the RX descriptor. - */ - if (rx_status & MVPP2_RXD_ERR_SUMMARY) - goto err_drop_frame; - if (port->priv->percpu_pools) { pp = port->priv->page_pool[pool]; dma_dir = page_pool_get_dma_dir(pp); @@ -3904,6 +3925,18 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, rx_bytes + MVPP2_MH_SIZE, dma_dir); + /* Buffer header not supported */ + if (rx_status & MVPP2_RXD_BUF_HDR) + goto err_drop_frame; + + /* In case of an error, release the requested buffer pointer + * to the Buffer Manager. This request process is controlled + * by the hardware, and the information about the buffer is + * comprised by the RX descriptor. + */ + if (rx_status & MVPP2_RXD_ERR_SUMMARY) + goto err_drop_frame; + /* Prefetch header */ prefetch(data); @@ -3985,7 +4018,10 @@ err_drop_frame: dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ - mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); + if (rx_status & MVPP2_RXD_BUF_HDR) + mvpp2_buff_hdr_pool_put(port, rx_desc, pool, rx_status); + else + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); } rcu_read_unlock(); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index f4962a97a075..9d9a2e438acf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -786,6 +786,10 @@ static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + if (*rss_context != ETH_RXFH_CONTEXT_ALLOC && + *rss_context >= MAX_RSS_GROUPS) + return -EINVAL; + rss = &pfvf->hw.rss_info; if (!rss->enable) { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index ed4eacef17ce..64adfd24e134 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -681,32 +681,53 @@ static int mtk_set_mac_address(struct net_device *dev, void *p) void mtk_stats_update_mac(struct mtk_mac *mac) { struct mtk_hw_stats *hw_stats = mac->hw_stats; - unsigned int base = MTK_GDM1_TX_GBCNT; - u64 stats; - - base += hw_stats->reg_offset; + struct mtk_eth *eth = mac->hw; u64_stats_update_begin(&hw_stats->syncp); - hw_stats->rx_bytes += mtk_r32(mac->hw, base); - stats = mtk_r32(mac->hw, base + 0x04); - if (stats) - hw_stats->rx_bytes += (stats << 32); - hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x08); - hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x10); - hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x14); - hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x18); - hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x1c); - hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x20); - hw_stats->rx_flow_control_packets += - mtk_r32(mac->hw, base + 0x24); - hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x28); - hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x2c); - hw_stats->tx_bytes += mtk_r32(mac->hw, base + 0x30); - stats = mtk_r32(mac->hw, base + 0x34); - if (stats) - hw_stats->tx_bytes += (stats << 32); - hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x38); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + hw_stats->tx_packets += mtk_r32(mac->hw, MT7628_SDM_TPCNT); + hw_stats->tx_bytes += mtk_r32(mac->hw, MT7628_SDM_TBCNT); + hw_stats->rx_packets += mtk_r32(mac->hw, MT7628_SDM_RPCNT); + hw_stats->rx_bytes += mtk_r32(mac->hw, MT7628_SDM_RBCNT); + hw_stats->rx_checksum_errors += + mtk_r32(mac->hw, MT7628_SDM_CS_ERR); + } else { + unsigned int offs = hw_stats->reg_offset; + u64 stats; + + hw_stats->rx_bytes += mtk_r32(mac->hw, + MTK_GDM1_RX_GBCNT_L + offs); + stats = mtk_r32(mac->hw, MTK_GDM1_RX_GBCNT_H + offs); + if (stats) + hw_stats->rx_bytes += (stats << 32); + hw_stats->rx_packets += + mtk_r32(mac->hw, MTK_GDM1_RX_GPCNT + offs); + hw_stats->rx_overflow += + mtk_r32(mac->hw, MTK_GDM1_RX_OERCNT + offs); + hw_stats->rx_fcs_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_FERCNT + offs); + hw_stats->rx_short_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_SERCNT + offs); + hw_stats->rx_long_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_LENCNT + offs); + hw_stats->rx_checksum_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_CERCNT + offs); + hw_stats->rx_flow_control_packets += + mtk_r32(mac->hw, MTK_GDM1_RX_FCCNT + offs); + hw_stats->tx_skip += + mtk_r32(mac->hw, MTK_GDM1_TX_SKIPCNT + offs); + hw_stats->tx_collisions += + mtk_r32(mac->hw, MTK_GDM1_TX_COLCNT + offs); + hw_stats->tx_bytes += + mtk_r32(mac->hw, MTK_GDM1_TX_GBCNT_L + offs); + stats = mtk_r32(mac->hw, MTK_GDM1_TX_GBCNT_H + offs); + if (stats) + hw_stats->tx_bytes += (stats << 32); + hw_stats->tx_packets += + mtk_r32(mac->hw, MTK_GDM1_TX_GPCNT + offs); + } + u64_stats_update_end(&hw_stats->syncp); } @@ -2423,7 +2444,8 @@ static void mtk_dim_rx(struct work_struct *work) val |= cur << MTK_PDMA_DELAY_RX_PINT_SHIFT; mtk_w32(eth, val, MTK_PDMA_DELAY_INT); - mtk_w32(eth, val, MTK_QDMA_DELAY_INT); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_w32(eth, val, MTK_QDMA_DELAY_INT); spin_unlock_bh(ð->dim_lock); @@ -2452,7 +2474,8 @@ static void mtk_dim_tx(struct work_struct *work) val |= cur << MTK_PDMA_DELAY_TX_PINT_SHIFT; mtk_w32(eth, val, MTK_PDMA_DELAY_INT); - mtk_w32(eth, val, MTK_QDMA_DELAY_INT); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_w32(eth, val, MTK_QDMA_DELAY_INT); spin_unlock_bh(ð->dim_lock); @@ -2480,6 +2503,10 @@ static int mtk_hw_init(struct mtk_eth *eth) goto err_disable_pm; } + /* set interrupt delays based on current Net DIM sample */ + mtk_dim_rx(ð->rx_dim.work); + mtk_dim_tx(ð->tx_dim.work); + /* disable delay and normal interrupt */ mtk_tx_irq_disable(eth, ~0); mtk_rx_irq_disable(eth, ~0); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 11331b44ba07..5ef70dd8b49c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -278,8 +278,21 @@ /* QDMA FQ Free Page Buffer Length Register */ #define MTK_QDMA_FQ_BLEN 0x1B2C -/* GMA1 Received Good Byte Count Register */ -#define MTK_GDM1_TX_GBCNT 0x2400 +/* GMA1 counter / statics register */ +#define MTK_GDM1_RX_GBCNT_L 0x2400 +#define MTK_GDM1_RX_GBCNT_H 0x2404 +#define MTK_GDM1_RX_GPCNT 0x2408 +#define MTK_GDM1_RX_OERCNT 0x2410 +#define MTK_GDM1_RX_FERCNT 0x2414 +#define MTK_GDM1_RX_SERCNT 0x2418 +#define MTK_GDM1_RX_LENCNT 0x241c +#define MTK_GDM1_RX_CERCNT 0x2420 +#define MTK_GDM1_RX_FCCNT 0x2424 +#define MTK_GDM1_TX_SKIPCNT 0x2428 +#define MTK_GDM1_TX_COLCNT 0x242c +#define MTK_GDM1_TX_GBCNT_L 0x2430 +#define MTK_GDM1_TX_GBCNT_H 0x2434 +#define MTK_GDM1_TX_GPCNT 0x2438 #define MTK_STAT_OFFSET 0x40 /* QDMA descriptor txd4 */ @@ -502,6 +515,13 @@ #define MT7628_SDM_MAC_ADRL (MT7628_SDM_OFFSET + 0x0c) #define MT7628_SDM_MAC_ADRH (MT7628_SDM_OFFSET + 0x10) +/* Counter / stat register */ +#define MT7628_SDM_TPCNT (MT7628_SDM_OFFSET + 0x100) +#define MT7628_SDM_TBCNT (MT7628_SDM_OFFSET + 0x104) +#define MT7628_SDM_RPCNT (MT7628_SDM_OFFSET + 0x108) +#define MT7628_SDM_RBCNT (MT7628_SDM_OFFSET + 0x10c) +#define MT7628_SDM_CS_ERR (MT7628_SDM_OFFSET + 0x110) + struct mtk_rx_dma { unsigned int rxd1; unsigned int rxd2; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 1434df66fcf2..3616b77caa0a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -2027,8 +2027,6 @@ static int mlx4_en_set_tunable(struct net_device *dev, return ret; } -#define MLX4_EEPROM_PAGE_LEN 256 - static int mlx4_en_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { @@ -2063,7 +2061,7 @@ static int mlx4_en_get_module_info(struct net_device *dev, break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; break; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index f6cfec81ccc3..dc4ac1a2b6b6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET 0xb0 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET 0xa8 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET 0xac +#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2 @@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) if (mlx4_is_mfunc(dev)) disable_unsupported_roce_caps(outbox); + MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER); + dev_cap->map_clock_to_user = field & 0x80; MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET); dev_cap->reserved_qps = 1 << (field & 0xf); MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 8f020f26ebf5..cf64e54eecb0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -131,6 +131,7 @@ struct mlx4_dev_cap { u32 health_buffer_addrs; struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; bool wol_port[MLX4_MAX_PORTS + 1]; + bool map_clock_to_user; }; struct mlx4_func_cap { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index c326b434734e..00c84656b2e7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) } } + dev->caps.map_clock_to_user = dev_cap->map_clock_to_user; dev->caps.uar_page_size = PAGE_SIZE; dev->caps.num_uars = dev_cap->uar_size / PAGE_SIZE; dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay; @@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev, if (mlx4_is_slave(dev)) return -EOPNOTSUPP; + if (!dev->caps.map_clock_to_user) { + mlx4_dbg(dev, "Map clock to user is not supported.\n"); + return -EOPNOTSUPP; + } + if (!params) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index ba6ac31a339d..256a06b3c096 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -1973,6 +1973,7 @@ EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave); #define I2C_ADDR_LOW 0x50 #define I2C_ADDR_HIGH 0x51 #define I2C_PAGE_SIZE 256 +#define I2C_HIGH_PAGE_SIZE 128 /* Module Info Data */ struct mlx4_cable_info { @@ -2026,6 +2027,88 @@ static inline const char *cable_info_mad_err_str(u16 mad_status) return "Unknown Error"; } +static int mlx4_get_module_id(struct mlx4_dev *dev, u8 port, u8 *module_id) +{ + struct mlx4_cmd_mailbox *inbox, *outbox; + struct mlx4_mad_ifc *inmad, *outmad; + struct mlx4_cable_info *cable_info; + int ret; + + inbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(inbox)) + return PTR_ERR(inbox); + + outbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(outbox)) { + mlx4_free_cmd_mailbox(dev, inbox); + return PTR_ERR(outbox); + } + + inmad = (struct mlx4_mad_ifc *)(inbox->buf); + outmad = (struct mlx4_mad_ifc *)(outbox->buf); + + inmad->method = 0x1; /* Get */ + inmad->class_version = 0x1; + inmad->mgmt_class = 0x1; + inmad->base_version = 0x1; + inmad->attr_id = cpu_to_be16(0xFF60); /* Module Info */ + + cable_info = (struct mlx4_cable_info *)inmad->data; + cable_info->dev_mem_address = 0; + cable_info->page_num = 0; + cable_info->i2c_addr = I2C_ADDR_LOW; + cable_info->size = cpu_to_be16(1); + + ret = mlx4_cmd_box(dev, inbox->dma, outbox->dma, port, 3, + MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + if (ret) + goto out; + + if (be16_to_cpu(outmad->status)) { + /* Mad returned with bad status */ + ret = be16_to_cpu(outmad->status); + mlx4_warn(dev, + "MLX4_CMD_MAD_IFC Get Module ID attr(%x) port(%d) i2c_addr(%x) offset(%d) size(%d): Response Mad Status(%x) - %s\n", + 0xFF60, port, I2C_ADDR_LOW, 0, 1, ret, + cable_info_mad_err_str(ret)); + ret = -ret; + goto out; + } + cable_info = (struct mlx4_cable_info *)outmad->data; + *module_id = cable_info->data[0]; +out: + mlx4_free_cmd_mailbox(dev, inbox); + mlx4_free_cmd_mailbox(dev, outbox); + return ret; +} + +static void mlx4_sfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + *i2c_addr = I2C_ADDR_LOW; + *page_num = 0; + + if (*offset < I2C_PAGE_SIZE) + return; + + *i2c_addr = I2C_ADDR_HIGH; + *offset -= I2C_PAGE_SIZE; +} + +static void mlx4_qsfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + /* Offsets 0-255 belong to page 0. + * Offsets 256-639 belong to pages 01, 02, 03. + * For example, offset 400 is page 02: 1 + (400 - 256) / 128 = 2 + */ + if (*offset < I2C_PAGE_SIZE) + *page_num = 0; + else + *page_num = 1 + (*offset - I2C_PAGE_SIZE) / I2C_HIGH_PAGE_SIZE; + *i2c_addr = I2C_ADDR_LOW; + *offset -= *page_num * I2C_HIGH_PAGE_SIZE; +} + /** * mlx4_get_module_info - Read cable module eeprom data * @dev: mlx4_dev. @@ -2045,12 +2128,30 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, struct mlx4_cmd_mailbox *inbox, *outbox; struct mlx4_mad_ifc *inmad, *outmad; struct mlx4_cable_info *cable_info; - u16 i2c_addr; + u8 module_id, i2c_addr, page_num; int ret; if (size > MODULE_INFO_MAX_READ) size = MODULE_INFO_MAX_READ; + ret = mlx4_get_module_id(dev, port, &module_id); + if (ret) + return ret; + + switch (module_id) { + case MLX4_MODULE_ID_SFP: + mlx4_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + case MLX4_MODULE_ID_QSFP: + case MLX4_MODULE_ID_QSFP_PLUS: + case MLX4_MODULE_ID_QSFP28: + mlx4_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + default: + mlx4_err(dev, "Module ID not recognized: %#x\n", module_id); + return -EINVAL; + } + inbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(inbox)) return PTR_ERR(inbox); @@ -2076,11 +2177,9 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, */ size -= offset + size - I2C_PAGE_SIZE; - i2c_addr = I2C_ADDR_LOW; - cable_info = (struct mlx4_cable_info *)inmad->data; cable_info->dev_mem_address = cpu_to_be16(offset); - cable_info->page_num = 0; + cable_info->page_num = page_num; cable_info->i2c_addr = i2c_addr; cable_info->size = cpu_to_be16(size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index a9166cd85013..ceebfc20f65e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -303,6 +303,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) int ret = 0, i; mutex_lock(&mlx5_intf_mutex); + priv->flags &= ~MLX5_PRIV_FLAGS_DETACH; for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { if (!priv->adev[i]) { bool is_supported = false; @@ -320,6 +321,16 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) } } else { adev = &priv->adev[i]->adev; + + /* Pay attention that this is not PCI driver that + * mlx5_core_dev is connected, but auxiliary driver. + * + * Here we can race of module unload with devlink + * reload, but we don't need to take extra lock because + * we are holding global mlx5_intf_mutex. + */ + if (!adev->dev.driver) + continue; adrv = to_auxiliary_drv(adev->dev.driver); if (adrv->resume) @@ -350,6 +361,10 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue; adev = &priv->adev[i]->adev; + /* Auxiliary driver was unbind manually through sysfs */ + if (!adev->dev.driver) + goto skip_suspend; + adrv = to_auxiliary_drv(adev->dev.driver); if (adrv->suspend) { @@ -357,9 +372,11 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue; } +skip_suspend: del_adev(&priv->adev[i]->adev); priv->adev[i] = NULL; } + priv->flags |= MLX5_PRIV_FLAGS_DETACH; mutex_unlock(&mlx5_intf_mutex); } @@ -448,6 +465,8 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) struct mlx5_priv *priv = &dev->priv; lockdep_assert_held(&mlx5_intf_mutex); + if (priv->flags & MLX5_PRIV_FLAGS_DETACH) + return 0; delete_drivers(dev); if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 0dd7615e5931..bc33eaada3b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -64,6 +64,8 @@ struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) struct mlx5e_priv *priv = netdev_priv(dev); struct devlink_port *port; + if (!netif_device_present(dev)) + return NULL; port = mlx5e_devlink_get_dl_port(priv); if (port->registered) return port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index d907c1acd4d5..778e229310a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2020 Mellanox Technologies -#include <linux/ptp_classify.h> #include "en/ptp.h" #include "en/txrx.h" #include "en/params.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index ab935cce952b..c96668bd701c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -6,6 +6,7 @@ #include "en.h" #include "en_stats.h" +#include <linux/ptp_classify.h> struct mlx5e_ptpsq { struct mlx5e_txqsq txqsq; @@ -43,6 +44,27 @@ struct mlx5e_ptp { DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES); }; +static inline bool mlx5e_use_ptpsq(struct sk_buff *skb) +{ + struct flow_keys fk; + + if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) + return false; + + if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) + return false; + + if (fk.basic.n_proto == htons(ETH_P_1588)) + return true; + + if (fk.basic.n_proto != htons(ETH_P_IP) && + fk.basic.n_proto != htons(ETH_P_IPV6)) + return false; + + return (fk.basic.ip_proto == IPPROTO_UDP && + fk.ports.dst == htons(PTP_EV_PORT)); +} + int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, u8 lag_port, struct mlx5e_ptp **cp); void mlx5e_ptp_close(struct mlx5e_ptp *c); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 95f2b26a3ee3..9c076aa20306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -223,6 +223,8 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt rpriv = priv->ppriv; fwd_vport_num = rpriv->rep->vport; lag_dev = netdev_master_upper_dev_get(netdev); + if (!lag_dev) + return; netdev_dbg(netdev, "lag_dev(%s)'s slave vport(%d) is txable(%d)\n", lag_dev->name, fwd_vport_num, net_lag_port_dev_txable(netdev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index be0ee03de721..2e9bee4e5209 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -129,10 +129,9 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) work); struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; struct neighbour *n = update_work->n; + struct mlx5e_encap_entry *e = NULL; bool neigh_connected, same_dev; - struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; - struct mlx5e_priv *priv; u8 nud_state, dead; rtnl_lock(); @@ -156,14 +155,12 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) if (!same_dev) goto out; - list_for_each_entry(e, &nhe->encap_list, encap_list) { - if (!mlx5e_encap_take(e)) - continue; + /* mlx5e_get_next_init_encap() releases previous encap before returning + * the next one. + */ + while ((e = mlx5e_get_next_init_encap(nhe, e)) != NULL) + mlx5e_rep_update_flows(netdev_priv(e->out_dev), e, neigh_connected, ha); - priv = netdev_priv(e->out_dev); - mlx5e_rep_update_flows(priv, e, neigh_connected, ha); - mlx5e_encap_put(priv, e); - } out: rtnl_unlock(); mlx5e_release_neigh_update_work(update_work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 6cdc52d50a48..85eaadc989df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -94,13 +94,9 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv, ASSERT_RTNL(); - /* wait for encap to be fully initialized */ - wait_for_completion(&e->res_ready); - mutex_lock(&esw->offloads.encap_tbl_lock); encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); - if (e->compl_result < 0 || (encap_connected == neigh_connected && - ether_addr_equal(e->h_dest, ha))) + if (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha)) goto unlock; mlx5e_take_all_encap_flows(e, &flow_list); @@ -626,7 +622,7 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1, struct mlx5_eswitch *esw; u32 zone_restore_id; - tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + tc_skb_ext = tc_skb_ext_alloc(skb); if (!tc_skb_ext) { WARN_ON(1); return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 593503bc4d07..490131e06efb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -251,9 +251,12 @@ static void mlx5e_take_all_route_decap_flows(struct mlx5e_route_entry *r, mlx5e_take_tmp_flow(flow, flow_list, 0); } +typedef bool (match_cb)(struct mlx5e_encap_entry *); + static struct mlx5e_encap_entry * -mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, - struct mlx5e_encap_entry *e) +mlx5e_get_next_matching_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e, + match_cb match) { struct mlx5e_encap_entry *next = NULL; @@ -288,7 +291,7 @@ retry: /* wait for encap to be fully initialized */ wait_for_completion(&next->res_ready); /* continue searching if encap entry is not in valid state after completion */ - if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) { + if (!match(next)) { e = next; goto retry; } @@ -296,6 +299,30 @@ retry: return next; } +static bool mlx5e_encap_valid(struct mlx5e_encap_entry *e) +{ + return e->flags & MLX5_ENCAP_ENTRY_VALID; +} + +static struct mlx5e_encap_entry * +mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_valid); +} + +static bool mlx5e_encap_initialized(struct mlx5e_encap_entry *e) +{ + return e->compl_result >= 0; +} + +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_initialized); +} + void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; @@ -1505,7 +1532,7 @@ mlx5e_init_fib_work_ipv4(struct mlx5e_priv *priv, fen_info = container_of(info, struct fib_entry_notifier_info, info); fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; - if (fib_dev->netdev_ops != &mlx5e_netdev_ops || + if (!fib_dev || fib_dev->netdev_ops != &mlx5e_netdev_ops || fen_info->dst_len != 32) return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 3d45341e2216..26f7fab109d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -532,9 +532,6 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; struct net_device *netdev = priv->netdev; - if (!priv->ipsec) - return; - if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) || !MLX5_CAP_ETH(mdev, swp)) { mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 5cd466ec6492..25403af32859 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -356,7 +356,7 @@ err: int mlx5e_arfs_create_tables(struct mlx5e_priv *priv) { - int err = 0; + int err = -ENOMEM; int i; if (!(priv->netdev->hw_features & NETIF_F_NTUPLE)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8360289813f0..d6513aef5cd4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1624,12 +1624,13 @@ static int mlx5e_set_fecparam(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + unsigned long fec_bitmap; u16 fec_policy = 0; int mode; int err; - if (bitmap_weight((unsigned long *)&fecparam->fec, - ETHTOOL_FEC_LLRS_BIT + 1) > 1) + bitmap_from_arr32(&fec_bitmap, &fecparam->fec, sizeof(fecparam->fec) * BITS_PER_BYTE); + if (bitmap_weight(&fec_bitmap, ETHTOOL_FEC_LLRS_BIT + 1) > 1) return -EOPNOTSUPP; for (mode = 0; mode < ARRAY_SIZE(pplm_fec_2_ethtool); mode++) { @@ -1893,6 +1894,13 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val if (curr_val == new_val) return 0; + if (new_val && !priv->profile->rx_ptp_support && + priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) { + netdev_err(priv->netdev, + "Profile doesn't support enabling of CQE compression while hardware time-stamping is enabled.\n"); + return -EINVAL; + } + new_params = priv->channels.params; MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val); if (priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 0d571a0c76d9..0b75fab41ae8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -35,6 +35,7 @@ #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/mlx5/fs.h> +#include <linux/mlx5/mpfs.h> #include "en.h" #include "en_rep.h" #include "lib/mpfs.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bca832cdc4cb..d26b8ed51195 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -889,10 +889,13 @@ err_free_rq: void mlx5e_activate_rq(struct mlx5e_rq *rq) { set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - if (rq->icosq) + if (rq->icosq) { mlx5e_trigger_irq(rq->icosq); - else + } else { + local_bh_disable(); napi_schedule(rq->cq.napi); + local_bh_enable(); + } } void mlx5e_deactivate_rq(struct mlx5e_rq *rq) @@ -2697,13 +2700,11 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) int err; old_num_txqs = netdev->real_num_tx_queues; - old_ntc = netdev->num_tc; + old_ntc = netdev->num_tc ? : 1; nch = priv->channels.params.num_channels; ntc = priv->channels.params.num_tc; num_rxqs = nch * priv->profile->rq_groups; - if (priv->channels.params.ptp_rx) - num_rxqs++; mlx5e_netdev_set_tcs(netdev, nch, ntc); @@ -3855,6 +3856,16 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n"); } + if (mlx5e_is_uplink_rep(priv)) { + features &= ~NETIF_F_HW_TLS_RX; + if (netdev->features & NETIF_F_HW_TLS_RX) + netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n"); + + features &= ~NETIF_F_HW_TLS_TX; + if (netdev->features & NETIF_F_HW_TLS_TX) + netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n"); + } + mutex_unlock(&priv->state_lock); return features; @@ -3971,11 +3982,45 @@ int mlx5e_ptp_rx_manage_fs_ctx(struct mlx5e_priv *priv, void *ctx) return mlx5e_ptp_rx_manage_fs(priv, set); } -int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) +static int mlx5e_hwstamp_config_no_ptp_rx(struct mlx5e_priv *priv, bool rx_filter) +{ + bool rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def; + int err; + + if (!rx_filter) + /* Reset CQE compression to Admin default */ + return mlx5e_modify_rx_cqe_compression_locked(priv, rx_cqe_compress_def); + + if (!MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS)) + return 0; + + /* Disable CQE compression */ + netdev_warn(priv->netdev, "Disabling RX cqe compression\n"); + err = mlx5e_modify_rx_cqe_compression_locked(priv, false); + if (err) + netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); + + return err; +} + +static int mlx5e_hwstamp_config_ptp_rx(struct mlx5e_priv *priv, bool ptp_rx) { struct mlx5e_params new_params; + + if (ptp_rx == priv->channels.params.ptp_rx) + return 0; + + new_params = priv->channels.params; + new_params.ptp_rx = ptp_rx; + return mlx5e_safe_switch_params(priv, &new_params, mlx5e_ptp_rx_manage_fs_ctx, + &new_params.ptp_rx, true); +} + +int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) +{ struct hwtstamp_config config; bool rx_cqe_compress_def; + bool ptp_rx; int err; if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) || @@ -3995,13 +4040,12 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) } mutex_lock(&priv->state_lock); - new_params = priv->channels.params; rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def; /* RX HW timestamp */ switch (config.rx_filter) { case HWTSTAMP_FILTER_NONE: - new_params.ptp_rx = false; + ptp_rx = false; break; case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_SOME: @@ -4018,24 +4062,25 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: - new_params.ptp_rx = rx_cqe_compress_def; config.rx_filter = HWTSTAMP_FILTER_ALL; + /* ptp_rx is set if both HW TS is set and CQE + * compression is set + */ + ptp_rx = rx_cqe_compress_def; break; default: - mutex_unlock(&priv->state_lock); - return -ERANGE; + err = -ERANGE; + goto err_unlock; } - if (new_params.ptp_rx == priv->channels.params.ptp_rx) - goto out; + if (!priv->profile->rx_ptp_support) + err = mlx5e_hwstamp_config_no_ptp_rx(priv, + config.rx_filter != HWTSTAMP_FILTER_NONE); + else + err = mlx5e_hwstamp_config_ptp_rx(priv, ptp_rx); + if (err) + goto err_unlock; - err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_ptp_rx_manage_fs_ctx, - &new_params.ptp_rx, true); - if (err) { - mutex_unlock(&priv->state_lock); - return err; - } -out: memcpy(&priv->tstamp, &config, sizeof(config)); mutex_unlock(&priv->state_lock); @@ -4044,6 +4089,9 @@ out: return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; +err_unlock: + mutex_unlock(&priv->state_lock); + return err; } int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) @@ -4774,22 +4822,15 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) } if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) { - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) { - netdev->hw_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->gso_partial_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; + netdev->hw_features |= NETIF_F_GSO_GRE; + netdev->hw_enc_features |= NETIF_F_GSO_GRE; + netdev->gso_partial_features |= NETIF_F_GSO_GRE; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_IPIP)) { @@ -5229,6 +5270,11 @@ static void mlx5e_update_features(struct net_device *netdev) rtnl_unlock(); } +static void mlx5e_reset_channels(struct net_device *netdev) +{ + netdev_reset_tc(netdev); +} + int mlx5e_attach_netdev(struct mlx5e_priv *priv) { const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED; @@ -5283,6 +5329,7 @@ err_cleanup_tx: profile->cleanup_tx(priv); out: + mlx5e_reset_channels(priv->netdev); set_bit(MLX5E_STATE_DESTROYING, &priv->state); cancel_work_sync(&priv->update_stats_work); return err; @@ -5300,6 +5347,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) profile->cleanup_rx(priv); profile->cleanup_tx(priv); + mlx5e_reset_channels(priv->netdev); cancel_work_sync(&priv->update_stats_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 47a9c49b25fd..d4b0f270b6bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1322,10 +1322,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *out_dev, *encap_dev = NULL; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; bool vf_tun = false, encap_valid = true; + struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; @@ -1371,16 +1371,22 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr = attr->esw_attr; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; int mirred_ifindex; if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) continue; mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = __dev_get_by_index(dev_net(priv->netdev), - mirred_ifindex); + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto err_out; + } err = mlx5e_attach_encap(priv, flow, out_dev, out_index, extack, &encap_dev, &encap_valid); + dev_put(out_dev); if (err) goto err_out; @@ -1393,6 +1399,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->dests[out_index].mdev = out_priv->mdev; } + if (vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto err_out; + } + err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) goto err_out; @@ -2003,11 +2015,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, misc_parameters_3); struct flow_rule *rule = flow_cls_offload_flow_rule(f); struct flow_dissector *dissector = rule->match.dissector; + enum fs_flow_table_type fs_type; u16 addr_type = 0; u8 ip_proto = 0; u8 *match_level; int err; + fs_type = mlx5e_is_eswitch_flow(flow) ? FS_FT_FDB : FS_FT_NIC_RX; match_level = outer_match_level; if (dissector->used_keys & @@ -2133,6 +2147,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, if (match.mask->vlan_id || match.mask->vlan_priority || match.mask->vlan_tpid) { + if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ft_field_support.outer_second_vid, + fs_type)) { + NL_SET_ERR_MSG_MOD(extack, + "Matching on CVLAN is not supported"); + return -EOPNOTSUPP; + } + if (match.key->vlan_tpid == htons(ETH_P_8021AD)) { MLX5_SET(fte_match_set_misc, misc_c, outer_second_svlan_tag, 1); @@ -3526,8 +3547,12 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, if (err) return err; - *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), - dev_get_iflink(vlan_dev)); + rcu_read_lock(); + *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev)); + rcu_read_unlock(); + if (!*out_dev) + return -ENODEV; + if (is_vlan_dev(*out_dev)) err = add_vlan_push_action(priv, attr, out_dev, action); @@ -4740,7 +4765,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { wait_for_completion(&hpe->res_ready); if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) - hpe->hp->pair->peer_gone = true; + mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair); mlx5e_hairpin_put(priv, hpe); } @@ -5074,7 +5099,7 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) { chain = mapped_obj.chain; - tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + tc_skb_ext = tc_skb_ext_alloc(skb); if (WARN_ON(!tc_skb_ext)) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 25c091795bcd..17027536efba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -178,6 +178,9 @@ void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *f void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list); struct mlx5e_neigh_hash_entry; +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e); void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); void mlx5e_tc_reoffload_flows_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 8ba62671f5f1..320fe0cda917 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -32,7 +32,6 @@ #include <linux/tcp.h> #include <linux/if_vlan.h> -#include <linux/ptp_classify.h> #include <net/geneve.h> #include <net/dsfield.h> #include "en.h" @@ -67,24 +66,6 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb } #endif -static bool mlx5e_use_ptpsq(struct sk_buff *skb) -{ - struct flow_keys fk; - - if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) - return false; - - if (fk.basic.n_proto == htons(ETH_P_1588)) - return true; - - if (fk.basic.n_proto != htons(ETH_P_IP) && - fk.basic.n_proto != htons(ETH_P_IPV6)) - return false; - - return (fk.basic.ip_proto == IPPROTO_UDP && - fk.ports.dst == htons(PTP_EV_PORT)); -} - static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -145,9 +126,9 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, } ptp_channel = READ_ONCE(priv->channels.ptp); - if (unlikely(ptp_channel) && - test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) && - mlx5e_use_ptpsq(skb)) + if (unlikely(ptp_channel && + test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) && + mlx5e_use_ptpsq(skb))) return mlx5e_select_ptpsq(dev, skb); txq_ix = netdev_pick_tx(dev, skb, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 77c0ca655975..940333410267 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -136,7 +136,7 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, eqe = next_eqe_sw(eq); if (!eqe) - return 0; + goto out; do { struct mlx5_core_cq *cq; @@ -161,6 +161,8 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); + +out: eq_update_ci(eq, 1); if (cqn != -1) @@ -248,9 +250,9 @@ static int mlx5_eq_async_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); - eq_update_ci(eq, 1); out: + eq_update_ci(eq, 1); mlx5_eq_async_int_unlock(eq_async, recovery, &flags); return unlikely(recovery) ? num_eqes : 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 570f2280823c..97e6cb6f13c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -35,6 +35,7 @@ #include <linux/mlx5/mlx5_ifc.h> #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> +#include <linux/mlx5/mpfs.h> #include "esw/acl/lgcy.h" #include "esw/legacy.h" #include "mlx5_core.h" @@ -1053,6 +1054,12 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num, goto err_vhca_mapping; } + /* External controller host PF has factory programmed MAC. + * Read it from the device. + */ + if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) + mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac); + esw_vport_change_handle_locked(vport); esw->enabled_vports++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index db1e74280e57..d18a28a6e9a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -219,7 +219,8 @@ esw_setup_slow_path_dest(struct mlx5_flow_destination *dest, struct mlx5_fs_chains *chains, int i) { - flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; + if (mlx5_chains_ignore_flow_level_supported(chains)) + flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[i].ft = mlx5_chains_get_tc_end_ft(chains); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index a81ece94f599..b45954905845 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -65,7 +65,7 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev, { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_namespace *root_ns; - int err; + int err, err2; root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { @@ -76,33 +76,34 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev, /* As this is the terminating action then the termination table is the * same prio as the slow path */ - ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | + ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | MLX5_FLOW_TABLE_UNMANAGED | MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; - ft_attr.prio = FDB_SLOW_PATH; + ft_attr.prio = FDB_TC_OFFLOAD; ft_attr.max_fte = 1; + ft_attr.level = 1; ft_attr.autogroup.max_num_groups = 1; tt->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr); if (IS_ERR(tt->termtbl)) { - esw_warn(dev, "Failed to create termination table (error %d)\n", - IS_ERR(tt->termtbl)); - return -EOPNOTSUPP; + err = PTR_ERR(tt->termtbl); + esw_warn(dev, "Failed to create termination table, err %pe\n", tt->termtbl); + return err; } tt->rule = mlx5_add_flow_rules(tt->termtbl, NULL, flow_act, &tt->dest, 1); if (IS_ERR(tt->rule)) { - esw_warn(dev, "Failed to create termination table rule (error %d)\n", - IS_ERR(tt->rule)); + err = PTR_ERR(tt->rule); + esw_warn(dev, "Failed to create termination table rule, err %pe\n", tt->rule); goto add_flow_err; } return 0; add_flow_err: - err = mlx5_destroy_flow_table(tt->termtbl); - if (err) - esw_warn(dev, "Failed to destroy termination table\n"); + err2 = mlx5_destroy_flow_table(tt->termtbl); + if (err2) + esw_warn(dev, "Failed to destroy termination table, err %d\n", err2); - return -EOPNOTSUPP; + return err; } static struct mlx5_termtbl_handle * @@ -172,19 +173,6 @@ mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw, } } -static bool mlx5_eswitch_termtbl_is_encap_reformat(struct mlx5_pkt_reformat *rt) -{ - switch (rt->reformat_type) { - case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: - case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: - case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: - case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: - return true; - default: - return false; - } -} - static void mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, struct mlx5_flow_act *dst) @@ -202,14 +190,6 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, memset(&src->vlan[1], 0, sizeof(src->vlan[1])); } } - - if (src->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT && - mlx5_eswitch_termtbl_is_encap_reformat(src->pkt_reformat)) { - src->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - dst->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - dst->pkt_reformat = src->pkt_reformat; - src->pkt_reformat = NULL; - } } static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, @@ -238,6 +218,7 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, int i; if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) || + !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) || attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH || !mlx5_eswitch_offload_is_uplink_port(esw, spec)) return false; @@ -279,12 +260,19 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, if (dest[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) continue; + if (attr->dests[num_vport_dests].flags & MLX5_ESW_DEST_ENCAP) { + term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + term_tbl_act.pkt_reformat = attr->dests[num_vport_dests].pkt_reformat; + } else { + term_tbl_act.action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + term_tbl_act.pkt_reformat = NULL; + } + /* get the terminating table for the action list */ tt = mlx5_eswitch_termtbl_get_create(esw, &term_tbl_act, &dest[i], attr); if (IS_ERR(tt)) { - esw_warn(esw->dev, "Failed to get termination table (error %d)\n", - IS_ERR(tt)); + esw_warn(esw->dev, "Failed to get termination table, err %pe\n", tt); goto revert_changes; } attr->dests[num_vport_dests].termtbl = tt; @@ -301,6 +289,9 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, goto revert_changes; /* create the FTE */ + flow_act->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act->pkt_reformat = NULL; + flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; rule = mlx5_add_flow_rules(fdb, spec, flow_act, dest, num_dest); if (IS_ERR(rule)) goto revert_changes; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index d5d57630015f..106b50e42b46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -349,6 +349,9 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work) reset_abort_work); struct mlx5_core_dev *dev = fw_reset->dev; + if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) + return; + mlx5_sync_reset_clear_reset_requested(dev, true); mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 2c41a6920264..fd6196b5e163 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -307,6 +307,11 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) struct lag_mp *mp = &ldev->lag_mp; int err; + /* always clear mfi, as it might become stale when a route delete event + * has been missed + */ + mp->mfi = NULL; + if (mp->fib_nb.notifier_call) return 0; @@ -335,4 +340,5 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) unregister_fib_notifier(&init_net, &mp->fib_nb); destroy_workqueue(mp->wq); mp->fib_nb.notifier_call = NULL; + mp->mfi = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index 00ef10a1a9f8..20a4047f2737 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -107,7 +107,7 @@ bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains) return chains->flags & MLX5_CHAINS_AND_PRIOS_SUPPORTED; } -static bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains) +bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains) { return chains->flags & MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h index e96f345e7dae..d50bdb226cef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h @@ -28,6 +28,7 @@ struct mlx5_chains_attr { bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains); +bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains); bool mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains); u32 @@ -70,6 +71,10 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains, #else /* CONFIG_MLX5_CLS_ACT */ +static inline bool +mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains) +{ return false; } + static inline struct mlx5_flow_table * mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio, u32 level) { return ERR_PTR(-EOPNOTSUPP); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index fd8449ff9e17..839a01da110f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -33,6 +33,7 @@ #include <linux/etherdevice.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/mpfs.h> #include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "lib/mpfs.h" @@ -175,6 +176,7 @@ out: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_add_mac); int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { @@ -206,3 +208,4 @@ unlock: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_del_mac); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h index 4a7b2c3203a7..4a293542a7aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h @@ -84,12 +84,9 @@ struct l2addr_node { #ifdef CONFIG_MLX5_MPFS int mlx5_mpfs_init(struct mlx5_core_dev *dev); void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev); -int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); -int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); #else /* #ifndef CONFIG_MLX5_MPFS */ static inline int mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {} -static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } -static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } #endif + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c114365eb126..0d0f63a27aba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -503,7 +503,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) { - struct mlx5_profile *prof = dev->profile; + struct mlx5_profile *prof = &dev->profile; void *set_hca_cap; int err; @@ -524,11 +524,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) to_fw_pkey_sz(dev, 128)); /* Check log_max_qp from HCA caps to set in current profile */ - if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) { + if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", - profile[prof_sel].log_max_qp, + prof->log_max_qp, MLX5_CAP_GEN_MAX(dev, log_max_qp)); - profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); + prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); } if (prof->mask & MLX5_PROF_MASK_QP_SIZE) MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp, @@ -1161,7 +1161,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) err = mlx5_core_set_hca_defaults(dev); if (err) { mlx5_core_err(dev, "Failed to set hca defaults\n"); - goto err_sriov; + goto err_set_hca; } mlx5_vhca_event_start(dev); @@ -1194,6 +1194,7 @@ err_ec: mlx5_sf_hw_table_destroy(dev); err_vhca: mlx5_vhca_event_stop(dev); +err_set_hca: mlx5_cleanup_fs(dev); err_fs: mlx5_accel_tls_cleanup(dev); @@ -1381,8 +1382,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) struct mlx5_priv *priv = &dev->priv; int err; - dev->profile = &profile[profile_idx]; - + memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile)); INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); mutex_init(&dev->intf_state_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 50af84e76fb6..174f71ed5280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -54,7 +54,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); mkey->iova = MLX5_GET64(mkc, mkc, start_addr); mkey->size = MLX5_GET64(mkc, mkc, len); - mkey->key |= mlx5_idx_to_mkey(mkey_index); + mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); init_waitqueue_head(&mkey->wait); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 1f907df5b3a2..c3373fb1cd7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -95,9 +95,10 @@ int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs) int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, int msix_vec_count) { - int sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); + int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + void *hca_cap = NULL, *query_cap = NULL, *cap; int num_vf_msix, min_msix, max_msix; - void *hca_cap, *cap; int ret; num_vf_msix = MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix); @@ -116,11 +117,20 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, if (msix_vec_count > max_msix) return -EOVERFLOW; - hca_cap = kzalloc(sz, GFP_KERNEL); - if (!hca_cap) - return -ENOMEM; + query_cap = kzalloc(query_sz, GFP_KERNEL); + hca_cap = kzalloc(set_sz, GFP_KERNEL); + if (!hca_cap || !query_cap) { + ret = -ENOMEM; + goto out; + } + + ret = mlx5_vport_get_other_func_cap(dev, function_id, query_cap); + if (ret) + goto out; cap = MLX5_ADDR_OF(set_hca_cap_in, hca_cap, capability); + memcpy(cap, MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability), + MLX5_UN_SZ_BYTES(hca_cap_union)); MLX5_SET(cmd_hca_cap, cap, dynamic_msix_table_size, msix_vec_count); MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP); @@ -130,7 +140,9 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, MLX5_SET(set_hca_cap_in, hca_cap, op_mod, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1); ret = mlx5_cmd_exec_in(dev, set_hca_cap, hca_cap); +out: kfree(hca_cap); + kfree(query_cap); return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 441b5453acae..540cf05f6373 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -156,6 +156,9 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { int err; + if (!MLX5_CAP_GEN(dev, roce)) + return; + err = mlx5_nic_vport_enable_roce(dev); if (err) { mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 6a0c6f965ad1..fa0288afc0dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -163,6 +163,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ sf_index = event->function_id - base_id; sf_dev = xa_load(&table->devices, sf_index); switch (event->new_vhca_state) { + case MLX5_VHCA_STATE_INVALID: case MLX5_VHCA_STATE_ALLOCATED: if (sf_dev) mlx5_sf_dev_del(table->dev, sf_dev, sf_index); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index a8e73c9ed1ea..1be048769309 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -136,10 +136,10 @@ static enum devlink_port_fn_state mlx5_sf_to_devlink_state(u8 hw_state) switch (hw_state) { case MLX5_VHCA_STATE_ACTIVE: case MLX5_VHCA_STATE_IN_USE: - case MLX5_VHCA_STATE_TEARDOWN_REQUEST: return DEVLINK_PORT_FN_STATE_ACTIVE; case MLX5_VHCA_STATE_INVALID: case MLX5_VHCA_STATE_ALLOCATED: + case MLX5_VHCA_STATE_TEARDOWN_REQUEST: default: return DEVLINK_PORT_FN_STATE_INACTIVE; } @@ -192,14 +192,17 @@ sf_err: return err; } -static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) +static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf, + struct netlink_ext_ack *extack) { int err; if (mlx5_sf_is_active(sf)) return 0; - if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) - return -EINVAL; + if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) { + NL_SET_ERR_MSG_MOD(extack, "SF is inactivated but it is still attached"); + return -EBUSY; + } err = mlx5_cmd_sf_enable_hca(dev, sf->hw_fn_id); if (err) @@ -226,7 +229,8 @@ static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, struct mlx5_sf *sf, - enum devlink_port_fn_state state) + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack) { int err = 0; @@ -234,7 +238,7 @@ static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *ta if (state == mlx5_sf_to_devlink_state(sf->hw_state)) goto out; if (state == DEVLINK_PORT_FN_STATE_ACTIVE) - err = mlx5_sf_activate(dev, sf); + err = mlx5_sf_activate(dev, sf, extack); else if (state == DEVLINK_PORT_FN_STATE_INACTIVE) err = mlx5_sf_deactivate(dev, sf); else @@ -265,7 +269,7 @@ int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_po goto out; } - err = mlx5_sf_state_set(dev, table, sf, state); + err = mlx5_sf_state_set(dev, table, sf, state, extack); out: mlx5_sf_table_put(table); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c index 1fbcd012bb85..7ccfd40586ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -112,7 +112,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, int ret; ft_attr.table_type = MLX5_FLOW_TABLE_TYPE_FDB; - ft_attr.level = dmn->info.caps.max_ft_level - 2; + ft_attr.level = min_t(int, dmn->info.caps.max_ft_level - 2, + MLX5_FT_MAX_MULTIPATH_LEVEL); ft_attr.reformat_en = reformat_req; ft_attr.decap_en = reformat_req; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 054c2e2b6554..7466f016375c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -694,7 +694,11 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM) return -EINVAL; - memcpy(padded_data, data, data_sz); + inline_data_sz = + MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + + /* Add an alignment padding */ + memcpy(padded_data + data_sz % inline_data_sz, data, data_sz); /* Remove L2L3 outer headers */ MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id, @@ -706,32 +710,34 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, hw_action += DR_STE_ACTION_DOUBLE_SZ; used_actions++; /* Remove and NOP are a single double action */ - inline_data_sz = - MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + /* Point to the last dword of the header */ + data_ptr += (data_sz / inline_data_sz) * inline_data_sz; - /* Add the new header inline + 2 extra bytes */ + /* Add the new header using inline action 4Byte at a time, the header + * is added in reversed order to the beginning of the packet to avoid + * incorrect parsing by the HW. Since header is 14B or 18B an extra + * two bytes are padded and later removed. + */ for (i = 0; i < data_sz / inline_data_sz + 1; i++) { void *addr_inline; MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE); /* The hardware expects here offset to words (2 bytes) */ - MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, - i * 2); + MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, 0); /* Copy bytes one by one to avoid endianness problem */ addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1, hw_action, inline_data); - memcpy(addr_inline, data_ptr, inline_data_sz); + memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz); hw_action += DR_STE_ACTION_DOUBLE_SZ; - data_ptr += inline_data_sz; used_actions++; } - /* Remove 2 extra bytes */ + /* Remove first 2 extra bytes */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); - MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2); + MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, 0); /* The hardware expects here size in words (2 bytes) */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1); used_actions++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 612b0ac31db2..9737565cd8d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -124,10 +124,11 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action); static inline bool mlx5dr_is_supported(struct mlx5_core_dev *dev) { - return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || - (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && - (MLX5_CAP_GEN(dev, steering_format_version) <= - MLX5_STEERING_FORMAT_CONNECTX_6DX)); + return MLX5_CAP_GEN(dev, roce) && + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && + (MLX5_CAP_GEN(dev, steering_format_version) <= + MLX5_STEERING_FORMAT_CONNECTX_6DX))); } /* buddy functions & structure */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index 01cc00ad8acf..b6931bbe52d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -424,6 +424,15 @@ err_modify_sq: return err; } +static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp) +{ + int i; + + for (i = 0; i < hp->num_channels; i++) + mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, + MLX5_SQC_STATE_RST, 0, 0); +} + static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) { int i; @@ -432,13 +441,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_RST, 0, 0); - /* unset peer SQs */ - if (hp->peer_gone) - return; - for (i = 0; i < hp->num_channels; i++) - mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_RST, 0, 0); + if (!hp->peer_gone) + mlx5_hairpin_unpair_peer_sq(hp); } struct mlx5_hairpin * @@ -485,3 +490,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp) mlx5_hairpin_destroy_queues(hp); kfree(hp); } + +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp) +{ + int i; + + mlx5_hairpin_unpair_peer_sq(hp); + + /* destroy peer SQ */ + for (i = 0; i < hp->num_channels; i++) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + + hp->peer_gone = true; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 457ad42eaa2a..4c1440a95ad7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -465,8 +465,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, void *in; int err; - if (!vport) - return -EINVAL; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return -EACCES; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index dfea14399607..85f0ce285146 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -693,7 +693,8 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz) MLXSW_THERMAL_TRIP_MASK, module_tz, &mlxsw_thermal_module_ops, - NULL, 0, 0); + NULL, 0, + module_tz->parent->polling_delay); if (IS_ERR(module_tz->tzdev)) { err = PTR_ERR(module_tz->tzdev); return err; @@ -815,7 +816,8 @@ mlxsw_thermal_gearbox_tz_init(struct mlxsw_thermal_module *gearbox_tz) MLXSW_THERMAL_TRIP_MASK, gearbox_tz, &mlxsw_thermal_gearbox_ops, - NULL, 0, 0); + NULL, 0, + gearbox_tz->parent->polling_delay); if (IS_ERR(gearbox_tz->tzdev)) return PTR_ERR(gearbox_tz->tzdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 900b4bf5bb5b..2bc5a9003c6d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3907,7 +3907,7 @@ MLXSW_ITEM32(reg, qeec, max_shaper_bs, 0x1C, 0, 6); #define MLXSW_REG_QEEC_HIGHEST_SHAPER_BS 25 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1 5 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2 11 -#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 5 +#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 11 static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port, enum mlxsw_reg_qeec_hr hr, u8 index, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 04672eb5c7f3..9958d503bf0e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -1332,6 +1332,7 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, u8 band, u32 child_handle) { struct mlxsw_sp_qdisc *old_qdisc; + u32 parent; if (band < mlxsw_sp_qdisc->num_classes && mlxsw_sp_qdisc->qdiscs[band].handle == child_handle) @@ -1352,7 +1353,9 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, if (old_qdisc) mlxsw_sp_qdisc_destroy(mlxsw_sp_port, old_qdisc); - mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc, band); + parent = TC_H_MAKE(mlxsw_sp_qdisc->handle, band + 1); + mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc, + parent); if (!WARN_ON(!mlxsw_sp_qdisc)) mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc); diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 3658c4ae3c37..ee921a99e439 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * Microchip ENCX24J600 ethernet driver * * Copyright (C) 2015 Gridpoint diff --git a/drivers/net/ethernet/microchip/encx24j600_hw.h b/drivers/net/ethernet/microchip/encx24j600_hw.h index f604a260ede7..fac61a8fbd02 100644 --- a/drivers/net/ethernet/microchip/encx24j600_hw.h +++ b/drivers/net/ethernet/microchip/encx24j600_hw.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/** +/* * encx24j600_hw.h: Register definitions * */ diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 0c4283319d7f..adfb9781799e 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -379,6 +379,7 @@ static u32 ocelot_read_eq_avail(struct ocelot *ocelot, int port) int ocelot_port_flush(struct ocelot *ocelot, int port) { + unsigned int pause_ena; int err, val; /* Disable dequeuing from the egress queues */ @@ -387,6 +388,7 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) QSYS_PORT_MODE, port); /* Disable flow control */ + ocelot_fields_read(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, &pause_ena); ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0); /* Disable priority flow control */ @@ -422,6 +424,9 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) /* Clear flushing again. */ ocelot_rmw_gix(ocelot, 0, REW_PORT_CFG_FLUSH_ENA, REW_PORT_CFG, port); + /* Re-enable flow control */ + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, pause_ena); + return err; } EXPORT_SYMBOL(ocelot_port_flush); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index c84c8bf2bc20..fc99ad8e4a38 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -3815,6 +3815,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(&pdev->dev, "invalid sram_size %dB or board span %ldB\n", mgp->sram_size, mgp->board_span); + status = -EINVAL; goto abort_with_ioremap; } memcpy_fromio(mgp->eeprom_strings, diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig index 5f8b0bb3af6e..202973a82712 100644 --- a/drivers/net/ethernet/pensando/Kconfig +++ b/drivers/net/ethernet/pensando/Kconfig @@ -20,6 +20,7 @@ if NET_VENDOR_PENSANDO config IONIC tristate "Pensando Ethernet IONIC Support" depends on 64BIT && PCI + depends on PTP_1588_CLOCK || !PTP_1588_CLOCK select NET_DEVLINK select DIMLIB help diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 7e6bac85495d..344ea1143454 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1602,6 +1602,8 @@ err_out_free_netdev: free_netdev(netdev); err_out_free_res: + if (NX_IS_REVISION_P3(pdev->revision)) + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_out_disable_pdev: diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 17d5b649eb36..e81dd34a3cac 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -1266,9 +1266,11 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn, p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_STATIC; p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled; + BUILD_BUG_ON(sizeof(dcbx_info->operational.params) != + sizeof(p_hwfn->p_dcbx_info->set.config.params)); memcpy(&p_hwfn->p_dcbx_info->set.config.params, &dcbx_info->operational.params, - sizeof(struct qed_dcbx_admin_params)); + sizeof(p_hwfn->p_dcbx_info->set.config.params)); p_hwfn->p_dcbx_info->set.config.valid = true; memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set)); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 214e347097a7..2376b2729633 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -114,7 +114,7 @@ static int ql_sem_spinlock(struct ql3_adapter *qdev, value = readl(&port_regs->CommonRegs.semaphoreReg); if ((value & (sem_mask >> 16)) == sem_bits) return 0; - ssleep(1); + mdelay(1000); } while (--seconds); return -1; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 96b947fde646..3beafc60747e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -2690,6 +2690,7 @@ err_out_free_hw_res: kfree(ahw); err_out_free_res: + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_out_disable_pdev: diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 41fbd2ceeede..ab1e0fcccabb 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -126,24 +126,24 @@ static void rmnet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct rmnet_priv *priv = netdev_priv(dev); - struct rmnet_vnd_stats total_stats; + struct rmnet_vnd_stats total_stats = { }; struct rmnet_pcpu_stats *pcpu_ptr; + struct rmnet_vnd_stats snapshot; unsigned int cpu, start; - memset(&total_stats, 0, sizeof(struct rmnet_vnd_stats)); - for_each_possible_cpu(cpu) { pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu); do { start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp); - total_stats.rx_pkts += pcpu_ptr->stats.rx_pkts; - total_stats.rx_bytes += pcpu_ptr->stats.rx_bytes; - total_stats.tx_pkts += pcpu_ptr->stats.tx_pkts; - total_stats.tx_bytes += pcpu_ptr->stats.tx_bytes; + snapshot = pcpu_ptr->stats; /* struct assignment */ } while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start)); - total_stats.tx_drops += pcpu_ptr->stats.tx_drops; + total_stats.rx_pkts += snapshot.rx_pkts; + total_stats.rx_bytes += snapshot.rx_bytes; + total_stats.tx_pkts += snapshot.tx_pkts; + total_stats.tx_bytes += snapshot.tx_bytes; + total_stats.tx_drops += snapshot.tx_drops; } s->rx_packets = total_stats.rx_pkts; @@ -354,4 +354,4 @@ int rmnet_vnd_update_dev_mtu(struct rmnet_port *port, } return 0; -}
\ No newline at end of file +} diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 2c89cde7da1e..2ee72dc431cd 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1671,7 +1671,7 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data) { switch(stringset) { case ETH_SS_STATS: - memcpy(data, *rtl8169_gstrings, sizeof(rtl8169_gstrings)); + memcpy(data, rtl8169_gstrings, sizeof(rtl8169_gstrings)); break; } } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index c5b154868c1f..713d3629b4c1 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2287,7 +2287,7 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data) { switch (stringset) { case ETH_SS_STATS: - memcpy(data, *sh_eth_gstrings_stats, + memcpy(data, sh_eth_gstrings_stats, sizeof(sh_eth_gstrings_stats)); break; } diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index d1e908846f5d..22fbb0ae77fb 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -90,6 +90,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx) efx->pci_dev->irq); goto fail1; } + efx->irqs_hooked = true; return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index b70d44ac0990..3c73453725f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -76,10 +76,10 @@ enum power_event { #define LPI_CTRL_STATUS_TLPIEN 0x00000001 /* Transmit LPI Entry */ /* GMAC HW ADDR regs */ -#define GMAC_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \ - (reg * 8)) -#define GMAC_ADDR_LOW(reg) (((reg > 15) ? 0x00000804 : 0x00000044) + \ - (reg * 8)) +#define GMAC_ADDR_HIGH(reg) ((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \ + 0x00000040 + (reg * 8)) +#define GMAC_ADDR_LOW(reg) ((reg > 15) ? 0x00000804 + (reg - 16) * 8 : \ + 0x00000044 + (reg * 8)) #define GMAC_MAX_PERFECT_ADDRESSES 1 #define GMAC_PCS_BASE 0x000000c0 /* PCS register base */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 345b4c6d1fd4..c87202cbd3d6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1196,7 +1196,6 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) */ static int stmmac_init_phy(struct net_device *dev) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct stmmac_priv *priv = netdev_priv(dev); struct device_node *node; int ret; @@ -1222,8 +1221,12 @@ static int stmmac_init_phy(struct net_device *dev) ret = phylink_connect_phy(priv->phylink, phydev); } - phylink_ethtool_get_wol(priv->phylink, &wol); - device_set_wakeup_capable(priv->device, !!wol.supported); + if (!priv->plat->pmt) { + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phylink_ethtool_get_wol(priv->phylink, &wol); + device_set_wakeup_capable(priv->device, !!wol.supported); + } return ret; } @@ -1237,8 +1240,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) priv->phylink_config.dev = &priv->dev->dev; priv->phylink_config.type = PHYLINK_NETDEV; priv->phylink_config.pcs_poll = true; - priv->phylink_config.ovr_an_inband = - priv->plat->mdio_bus_data->xpcs_an_inband; + if (priv->plat->mdio_bus_data) + priv->phylink_config.ovr_an_inband = + priv->plat->mdio_bus_data->xpcs_an_inband; if (!fwnode) fwnode = dev_fwnode(priv->device); @@ -5888,12 +5892,21 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr) struct stmmac_priv *priv = netdev_priv(ndev); int ret = 0; + ret = pm_runtime_get_sync(priv->device); + if (ret < 0) { + pm_runtime_put_noidle(priv->device); + return ret; + } + ret = eth_mac_addr(ndev, addr); if (ret) - return ret; + goto set_mac_error; stmmac_set_umac_addr(priv, priv->hw, ndev->dev_addr, 0); +set_mac_error: + pm_runtime_put(priv->device); + return ret; } @@ -6188,12 +6201,6 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid bool is_double = false; int ret; - ret = pm_runtime_get_sync(priv->device); - if (ret < 0) { - pm_runtime_put_noidle(priv->device); - return ret; - } - if (be16_to_cpu(proto) == ETH_P_8021AD) is_double = true; @@ -6219,6 +6226,12 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi bool is_double = false; int ret; + ret = pm_runtime_get_sync(priv->device); + if (ret < 0) { + pm_runtime_put_noidle(priv->device); + return ret; + } + if (be16_to_cpu(proto) == ETH_P_8021AD) is_double = true; @@ -7036,7 +7049,6 @@ error_mdio_register: stmmac_napi_del(ndev); error_hw_init: destroy_workqueue(priv->wq); - stmmac_bus_clks_config(priv, false); bitmap_free(priv->af_xdp_zc_qps); return ret; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 1e17a23d9118..a696ada013eb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -622,6 +622,8 @@ error_pclk_get: void stmmac_remove_config_dt(struct platform_device *pdev, struct plat_stmmacenet_data *plat) { + clk_disable_unprepare(plat->stmmac_clk); + clk_disable_unprepare(plat->pclk); of_node_put(plat->phy_node); of_node_put(plat->mdio_node); } diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 9030e619e543..97942b0e3897 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1350,8 +1350,8 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) tx_pipe->dma_queue = knav_queue_open(name, tx_pipe->dma_queue_id, KNAV_QUEUE_SHARED); if (IS_ERR(tx_pipe->dma_queue)) { - dev_err(dev, "Could not open DMA queue for channel \"%s\": %d\n", - name, ret); + dev_err(dev, "Could not open DMA queue for channel \"%s\": %pe\n", + name, tx_pipe->dma_queue); ret = PTR_ERR(tx_pipe->dma_queue); goto err; } diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index a1f5f07f4ca9..9a13953ea70f 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -774,12 +774,15 @@ static void temac_start_xmit_done(struct net_device *ndev) stat = be32_to_cpu(cur_p->app0); while (stat & STS_CTRL_APP0_CMPLT) { + /* Make sure that the other fields are read after bd is + * released by dma + */ + rmb(); dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys), be32_to_cpu(cur_p->len), DMA_TO_DEVICE); skb = (struct sk_buff *)ptr_from_txbd(cur_p); if (skb) dev_consume_skb_irq(skb); - cur_p->app0 = 0; cur_p->app1 = 0; cur_p->app2 = 0; cur_p->app3 = 0; @@ -788,6 +791,12 @@ static void temac_start_xmit_done(struct net_device *ndev) ndev->stats.tx_packets++; ndev->stats.tx_bytes += be32_to_cpu(cur_p->len); + /* app0 must be visible last, as it is used to flag + * availability of the bd + */ + smp_mb(); + cur_p->app0 = 0; + lp->tx_bd_ci++; if (lp->tx_bd_ci >= lp->tx_bd_num) lp->tx_bd_ci = 0; @@ -814,6 +823,9 @@ static inline int temac_check_tx_bd_space(struct temac_local *lp, int num_frag) if (cur_p->app0) return NETDEV_TX_BUSY; + /* Make sure to read next bd app0 after this one */ + rmb(); + tail++; if (tail >= lp->tx_bd_num) tail = 0; @@ -849,7 +861,7 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) smp_mb(); /* Space might have just been freed - check again */ - if (temac_check_tx_bd_space(lp, num_frag)) + if (temac_check_tx_bd_space(lp, num_frag + 1)) return NETDEV_TX_BUSY; netif_wake_queue(ndev); @@ -876,7 +888,6 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } cur_p->phys = cpu_to_be32(skb_dma_addr); - ptr_to_txbd((void *)skb, cur_p); for (ii = 0; ii < num_frag; ii++) { if (++lp->tx_bd_tail >= lp->tx_bd_num) @@ -915,6 +926,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) } cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_EOP); + /* Mark last fragment with skb address, so it can be consumed + * in temac_start_xmit_done() + */ + ptr_to_txbd((void *)skb, cur_p); + tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail; lp->tx_bd_tail++; if (lp->tx_bd_tail >= lp->tx_bd_num) @@ -926,6 +942,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) wmb(); lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */ + if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) { + netdev_info(ndev, "%s -> netif_stop_queue\n", __func__); + netif_stop_queue(ndev); + } + return NETDEV_TX_OK; } diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 65154224d5b8..7685a1721597 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -799,6 +799,7 @@ static void mkiss_close(struct tty_struct *tty) ax->tty = NULL; unregister_netdev(ax->dev); + free_netdev(ax->dev); } /* Perform I/O control on an active ax25 channel. */ diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c index b9be530b285f..ff83e00b77af 100644 --- a/drivers/net/ieee802154/mrf24j40.c +++ b/drivers/net/ieee802154/mrf24j40.c @@ -8,8 +8,8 @@ #include <linux/spi/spi.h> #include <linux/interrupt.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> -#include <linux/of.h> #include <linux/regmap.h> #include <linux/ieee802154.h> #include <linux/irq.h> @@ -1388,7 +1388,7 @@ MODULE_DEVICE_TABLE(spi, mrf24j40_ids); static struct spi_driver mrf24j40_driver = { .driver = { - .of_match_table = of_match_ptr(mrf24j40_of_match), + .of_match_table = mrf24j40_of_match, .name = "mrf24j40", }, .id_table = mrf24j40_ids, diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index e7ff376cb5b7..744406832a77 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -58,6 +58,7 @@ enum ipa_flag { * @mem_virt: Virtual address of IPA-local memory space * @mem_offset: Offset from @mem_virt used for access to IPA memory * @mem_size: Total size (bytes) of memory at @mem_virt + * @mem_count: Number of entries in the mem array * @mem: Array of IPA-local memory region descriptors * @imem_iova: I/O virtual address of IPA region in IMEM * @imem_size: Size of IMEM region @@ -103,6 +104,7 @@ struct ipa { void *mem_virt; u32 mem_offset; u32 mem_size; + u32 mem_count; const struct ipa_mem *mem; unsigned long imem_iova; diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index c5c3b1b7e67d..1624125e7459 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -180,7 +180,7 @@ int ipa_mem_config(struct ipa *ipa) * for the region, write "canary" values in the space prior to * the region's base address. */ - for (mem_id = 0; mem_id < IPA_MEM_COUNT; mem_id++) { + for (mem_id = 0; mem_id < ipa->mem_count; mem_id++) { const struct ipa_mem *mem = &ipa->mem[mem_id]; u16 canary_count; __le32 *canary; @@ -487,6 +487,7 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data) ipa->mem_size = resource_size(res); /* The ipa->mem[] array is indexed by enum ipa_mem_id values */ + ipa->mem_count = mem_data->local_count; ipa->mem = mem_data->local; ret = ipa_imem_init(ipa, mem_data->imem_addr, mem_data->imem_size); diff --git a/drivers/net/mdio/mdio-octeon.c b/drivers/net/mdio/mdio-octeon.c index 8ce99c4888e1..e096e68ac667 100644 --- a/drivers/net/mdio/mdio-octeon.c +++ b/drivers/net/mdio/mdio-octeon.c @@ -71,7 +71,6 @@ static int octeon_mdiobus_probe(struct platform_device *pdev) return 0; fail_register: - mdiobus_free(bus->mii_bus); smi_en.u64 = 0; oct_mdio_writeq(smi_en.u64, bus->register_base + SMI_EN); return err; @@ -85,7 +84,6 @@ static int octeon_mdiobus_remove(struct platform_device *pdev) bus = platform_get_drvdata(pdev); mdiobus_unregister(bus->mii_bus); - mdiobus_free(bus->mii_bus); smi_en.u64 = 0; oct_mdio_writeq(smi_en.u64, bus->register_base + SMI_EN); return 0; diff --git a/drivers/net/mdio/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c index cb1761693b69..822d2cdd2f35 100644 --- a/drivers/net/mdio/mdio-thunder.c +++ b/drivers/net/mdio/mdio-thunder.c @@ -126,7 +126,6 @@ static void thunder_mdiobus_pci_remove(struct pci_dev *pdev) continue; mdiobus_unregister(bus->mii_bus); - mdiobus_free(bus->mii_bus); oct_mdio_writeq(0, bus->register_base + SMI_EN); } pci_release_regions(pdev); diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index 0d8293a47a56..b806f2f8f859 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -49,7 +49,7 @@ static int mhi_ndo_stop(struct net_device *ndev) return 0; } -static int mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev) { struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); const struct mhi_net_proto *proto = mhi_netdev->proto; diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 9bd9a5c0b1db..6bbc81ad295f 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -826,16 +826,12 @@ static int dp83867_phy_reset(struct phy_device *phydev) { int err; - err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET); + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); if (err < 0) return err; usleep_range(10, 20); - /* After reset FORCE_LINK_GOOD bit is set. Although the - * default value should be unset. Disable FORCE_LINK_GOOD - * for the phy to work properly. - */ return phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index dadf75ff3ab9..6045ad3def12 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -607,7 +607,8 @@ void mdiobus_unregister(struct mii_bus *bus) struct mdio_device *mdiodev; int i; - BUG_ON(bus->state != MDIOBUS_REGISTERED); + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) + return; bus->state = MDIOBUS_UNREGISTERED; for (i = 0; i < PHY_MAX_ADDR; i++) { diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c index 0eeec80bec31..359ea0d10e59 100644 --- a/drivers/net/usb/cdc_eem.c +++ b/drivers/net/usb/cdc_eem.c @@ -26,7 +26,7 @@ * for transport over USB using a simpler USB device model than the * previous CDC "Ethernet Control Model" (ECM, or "CDC Ethernet"). * - * For details, see www.usb.org/developers/devclass_docs/CDC_EEM10.pdf + * For details, see https://usb.org/sites/default/files/CDC_EEM10.pdf * * This version has been tested with GIGAntIC WuaoW SIM Smart Card on 2.6.24, * 2.6.27 and 2.6.30rc2 kernel. @@ -123,10 +123,10 @@ static struct sk_buff *eem_tx_fixup(struct usbnet *dev, struct sk_buff *skb, } skb2 = skb_copy_expand(skb, EEM_HEAD, ETH_FCS_LEN + padlen, flags); + dev_kfree_skb_any(skb); if (!skb2) return NULL; - dev_kfree_skb_any(skb); skb = skb2; done: diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index b04055fd1b79..df0d1837e4ed 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1880,7 +1880,7 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) static const struct driver_info cdc_ncm_info = { .description = "CDC NCM", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_LINK_INTR, + | FLAG_LINK_INTR | FLAG_ETHER, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 3ef4b2841402..5c779cc0ea11 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1689,7 +1689,7 @@ static int hso_serial_tiocmset(struct tty_struct *tty, spin_unlock_irqrestore(&serial->serial_lock, flags); return usb_control_msg(serial->parent->usb, - usb_rcvctrlpipe(serial->parent->usb, 0), 0x22, + usb_sndctrlpipe(serial->parent->usb, 0), 0x22, 0x21, val, if_num, NULL, 0, USB_CTRL_SET_TIMEOUT); } @@ -2436,7 +2436,7 @@ static int hso_rfkill_set_block(void *data, bool blocked) if (hso_dev->usb_gone) rv = 0; else - rv = usb_control_msg(hso_dev->usb, usb_rcvctrlpipe(hso_dev->usb, 0), + rv = usb_control_msg(hso_dev->usb, usb_sndctrlpipe(hso_dev->usb, 0), enabled ? 0x82 : 0x81, 0x40, 0, 0, NULL, 0, USB_CTRL_SET_TIMEOUT); mutex_unlock(&hso_dev->mutex); @@ -2618,32 +2618,31 @@ static struct hso_device *hso_create_bulk_serial_device( num_urbs = 2; serial->tiocmget = kzalloc(sizeof(struct hso_tiocmget), GFP_KERNEL); + if (!serial->tiocmget) + goto exit; serial->tiocmget->serial_state_notification = kzalloc(sizeof(struct hso_serial_state_notification), GFP_KERNEL); - /* it isn't going to break our heart if serial->tiocmget - * allocation fails don't bother checking this. - */ - if (serial->tiocmget && serial->tiocmget->serial_state_notification) { - tiocmget = serial->tiocmget; - tiocmget->endp = hso_get_ep(interface, - USB_ENDPOINT_XFER_INT, - USB_DIR_IN); - if (!tiocmget->endp) { - dev_err(&interface->dev, "Failed to find INT IN ep\n"); - goto exit; - } - - tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); - if (tiocmget->urb) { - mutex_init(&tiocmget->mutex); - init_waitqueue_head(&tiocmget->waitq); - } else - hso_free_tiomget(serial); + if (!serial->tiocmget->serial_state_notification) + goto exit; + tiocmget = serial->tiocmget; + tiocmget->endp = hso_get_ep(interface, + USB_ENDPOINT_XFER_INT, + USB_DIR_IN); + if (!tiocmget->endp) { + dev_err(&interface->dev, "Failed to find INT IN ep\n"); + goto exit; } - } - else + + tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); + if (!tiocmget->urb) + goto exit; + + mutex_init(&tiocmget->mutex); + init_waitqueue_head(&tiocmget->waitq); + } else { num_urbs = 1; + } if (hso_serial_common_create(serial, num_urbs, BULK_URB_RX_SIZE, BULK_URB_TX_SIZE)) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 6acc5e904518..02bce40a67e5 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1645,6 +1645,7 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { .get_strings = lan78xx_get_strings, .get_wol = lan78xx_get_wol, .set_wol = lan78xx_set_wol, + .get_ts_info = ethtool_op_get_ts_info, .get_eee = lan78xx_get_eee, .set_eee = lan78xx_set_eee, .get_pauseparam = lan78xx_get_pause, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6700f1970b24..bc55ec739af9 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -575,7 +575,7 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (info->flags & QMI_WWAN_FLAG_PASS_THROUGH) { skb->protocol = htons(ETH_P_MAP); - return (netif_rx(skb) == NET_RX_SUCCESS); + return 1; } switch (skb->data[0] & 0xf0) { diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 136ea06540ff..e25bfb7021ed 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8107,6 +8107,37 @@ static void r8156b_init(struct r8152 *tp) tp->coalesce = 15000; /* 15 us */ } +static bool rtl_check_vendor_ok(struct usb_interface *intf) +{ + struct usb_host_interface *alt = intf->cur_altsetting; + struct usb_endpoint_descriptor *in, *out, *intr; + + if (usb_find_common_endpoints(alt, &in, &out, &intr, NULL) < 0) { + dev_err(&intf->dev, "Expected endpoints are not found\n"); + return false; + } + + /* Check Rx endpoint address */ + if (usb_endpoint_num(in) != 1) { + dev_err(&intf->dev, "Invalid Rx endpoint address\n"); + return false; + } + + /* Check Tx endpoint address */ + if (usb_endpoint_num(out) != 2) { + dev_err(&intf->dev, "Invalid Tx endpoint address\n"); + return false; + } + + /* Check interrupt endpoint address */ + if (usb_endpoint_num(intr) != 3) { + dev_err(&intf->dev, "Invalid interrupt endpoint address\n"); + return false; + } + + return true; +} + static bool rtl_vendor_mode(struct usb_interface *intf) { struct usb_host_interface *alt = intf->cur_altsetting; @@ -8115,12 +8146,15 @@ static bool rtl_vendor_mode(struct usb_interface *intf) int i, num_configs; if (alt->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) - return true; + return rtl_check_vendor_ok(intf); /* The vendor mode is not always config #1, so to find it out. */ udev = interface_to_usbdev(intf); c = udev->config; num_configs = udev->descriptor.bNumConfigurations; + if (num_configs < 2) + return false; + for (i = 0; i < num_configs; (i++, c++)) { struct usb_interface_descriptor *desc = NULL; @@ -8135,7 +8169,8 @@ static bool rtl_vendor_mode(struct usb_interface *intf) } } - WARN_ON_ONCE(i == num_configs); + if (i == num_configs) + dev_err(&intf->dev, "Unexpected Device\n"); return false; } @@ -8643,7 +8678,7 @@ static void rtl8152_get_strings(struct net_device *dev, u32 stringset, u8 *data) { switch (stringset) { case ETH_SS_STATS: - memcpy(data, *rtl8152_gstrings, sizeof(rtl8152_gstrings)); + memcpy(data, rtl8152_gstrings, sizeof(rtl8152_gstrings)); break; } } @@ -9381,9 +9416,6 @@ static int rtl8152_probe(struct usb_interface *intf, if (!rtl_vendor_mode(intf)) return -ENODEV; - if (intf->cur_altsetting->desc.bNumEndpoints < 3) - return -ENODEV; - usb_reset_device(udev); netdev = alloc_etherdev(sizeof(struct r8152)); if (!netdev) { diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index f8cdabb9ef5a..13141dbfa3a8 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1483,7 +1483,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_wait_ready(dev, 0); if (ret < 0) { netdev_warn(dev->net, "device not ready in smsc75xx_bind\n"); - return ret; + goto free_pdata; } smsc75xx_init_mac_address(dev); @@ -1492,7 +1492,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_reset(dev); if (ret < 0) { netdev_warn(dev->net, "smsc75xx_reset error %d\n", ret); - return ret; + goto cancel_work; } dev->net->netdev_ops = &smsc75xx_netdev_ops; @@ -1502,6 +1502,13 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; dev->net->max_mtu = MAX_SINGLE_PACKET_SIZE; return 0; + +cancel_work: + cancel_work_sync(&pdata->set_multicast); +free_pdata: + kfree(pdata); + dev->data[0] = 0; + return ret; } static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) @@ -1511,7 +1518,6 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) cancel_work_sync(&pdata->set_multicast); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); - pdata = NULL; dev->data[0] = 0; } } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 9b6a4a875c55..78a01c71a17c 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -401,18 +401,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, /* If headroom is not 0, there is an offset between the beginning of the * data and the allocated space, otherwise the data and the allocated * space are aligned. + * + * Buffers with headroom use PAGE_SIZE as alloc size, see + * add_recvbuf_mergeable() + get_mergeable_buf_len() */ - if (headroom) { - /* Buffers with headroom use PAGE_SIZE as alloc size, - * see add_recvbuf_mergeable() + get_mergeable_buf_len() - */ - truesize = PAGE_SIZE; - tailroom = truesize - len - offset; - buf = page_address(page); - } else { - tailroom = truesize - len; - buf = p; - } + truesize = headroom ? PAGE_SIZE : truesize; + tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len); + buf = p - headroom; len -= hdr_len; offset += hdr_padded_len; @@ -958,7 +953,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(page); head_skb = page_to_skb(vi, rq, xdp_page, offset, len, PAGE_SIZE, false, - metasize, headroom); + metasize, + VIRTIO_XDP_HEADROOM); return head_skb; } break; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 503e2fd7ce51..28a6c4cfe9b8 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1183,9 +1183,6 @@ static int vrf_dev_init(struct net_device *dev) dev->flags = IFF_MASTER | IFF_NOARP; - /* MTU is irrelevant for VRF device; set to 64k similar to lo */ - dev->mtu = 64 * 1024; - /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); @@ -1685,7 +1682,8 @@ static void vrf_setup(struct net_device *dev) * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; - dev->max_mtu = ETH_MAX_MTU; + dev->max_mtu = IP6_MAX_MTU; + dev->mtu = dev->max_mtu; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/wireguard/Makefile b/drivers/net/wireguard/Makefile index fc52b2cb500b..dbe1f8514efc 100644 --- a/drivers/net/wireguard/Makefile +++ b/drivers/net/wireguard/Makefile @@ -1,5 +1,4 @@ -ccflags-y := -O3 -ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt' +ccflags-y := -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt' ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG wireguard-y := main.o wireguard-y += noise.o diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 3725e9cd85f4..b7197e80f226 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -6,6 +6,8 @@ #include "allowedips.h" #include "peer.h" +static struct kmem_cache *node_cache; + static void swap_endian(u8 *dst, const u8 *src, u8 bits) { if (bits == 32) { @@ -28,8 +30,11 @@ static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src, node->bitlen = bits; memcpy(node->bits, src, bits / 8U); } -#define CHOOSE_NODE(parent, key) \ - parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1] + +static inline u8 choose(struct allowedips_node *node, const u8 *key) +{ + return (key[node->bit_at_a] >> node->bit_at_b) & 1; +} static void push_rcu(struct allowedips_node **stack, struct allowedips_node __rcu *p, unsigned int *len) @@ -40,6 +45,11 @@ static void push_rcu(struct allowedips_node **stack, } } +static void node_free_rcu(struct rcu_head *rcu) +{ + kmem_cache_free(node_cache, container_of(rcu, struct allowedips_node, rcu)); +} + static void root_free_rcu(struct rcu_head *rcu) { struct allowedips_node *node, *stack[128] = { @@ -49,7 +59,7 @@ static void root_free_rcu(struct rcu_head *rcu) while (len > 0 && (node = stack[--len])) { push_rcu(stack, node->bit[0], &len); push_rcu(stack, node->bit[1], &len); - kfree(node); + kmem_cache_free(node_cache, node); } } @@ -66,60 +76,6 @@ static void root_remove_peer_lists(struct allowedips_node *root) } } -static void walk_remove_by_peer(struct allowedips_node __rcu **top, - struct wg_peer *peer, struct mutex *lock) -{ -#define REF(p) rcu_access_pointer(p) -#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock)) -#define PUSH(p) ({ \ - WARN_ON(IS_ENABLED(DEBUG) && len >= 128); \ - stack[len++] = p; \ - }) - - struct allowedips_node __rcu **stack[128], **nptr; - struct allowedips_node *node, *prev; - unsigned int len; - - if (unlikely(!peer || !REF(*top))) - return; - - for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) { - nptr = stack[len - 1]; - node = DEREF(nptr); - if (!node) { - --len; - continue; - } - if (!prev || REF(prev->bit[0]) == node || - REF(prev->bit[1]) == node) { - if (REF(node->bit[0])) - PUSH(&node->bit[0]); - else if (REF(node->bit[1])) - PUSH(&node->bit[1]); - } else if (REF(node->bit[0]) == prev) { - if (REF(node->bit[1])) - PUSH(&node->bit[1]); - } else { - if (rcu_dereference_protected(node->peer, - lockdep_is_held(lock)) == peer) { - RCU_INIT_POINTER(node->peer, NULL); - list_del_init(&node->peer_list); - if (!node->bit[0] || !node->bit[1]) { - rcu_assign_pointer(*nptr, DEREF( - &node->bit[!REF(node->bit[0])])); - kfree_rcu(node, rcu); - node = DEREF(nptr); - } - } - --len; - } - } - -#undef REF -#undef DEREF -#undef PUSH -} - static unsigned int fls128(u64 a, u64 b) { return a ? fls64(a) + 64U : fls64(b); @@ -159,7 +115,7 @@ static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits, found = node; if (node->cidr == bits) break; - node = rcu_dereference_bh(CHOOSE_NODE(node, key)); + node = rcu_dereference_bh(node->bit[choose(node, key)]); } return found; } @@ -191,8 +147,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key, u8 cidr, u8 bits, struct allowedips_node **rnode, struct mutex *lock) { - struct allowedips_node *node = rcu_dereference_protected(trie, - lockdep_is_held(lock)); + struct allowedips_node *node = rcu_dereference_protected(trie, lockdep_is_held(lock)); struct allowedips_node *parent = NULL; bool exact = false; @@ -202,13 +157,24 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key, exact = true; break; } - node = rcu_dereference_protected(CHOOSE_NODE(parent, key), - lockdep_is_held(lock)); + node = rcu_dereference_protected(parent->bit[choose(parent, key)], lockdep_is_held(lock)); } *rnode = parent; return exact; } +static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node) +{ + node->parent_bit_packed = (unsigned long)parent | bit; + rcu_assign_pointer(*parent, node); +} + +static inline void choose_and_connect_node(struct allowedips_node *parent, struct allowedips_node *node) +{ + u8 bit = choose(parent, node->bits); + connect_node(&parent->bit[bit], bit, node); +} + static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, u8 cidr, struct wg_peer *peer, struct mutex *lock) { @@ -218,13 +184,13 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, return -EINVAL; if (!rcu_access_pointer(*trie)) { - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kmem_cache_zalloc(node_cache, GFP_KERNEL); if (unlikely(!node)) return -ENOMEM; RCU_INIT_POINTER(node->peer, peer); list_add_tail(&node->peer_list, &peer->allowedips_list); copy_and_assign_cidr(node, key, cidr, bits); - rcu_assign_pointer(*trie, node); + connect_node(trie, 2, node); return 0; } if (node_placement(*trie, key, cidr, bits, &node, lock)) { @@ -233,7 +199,7 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, return 0; } - newnode = kzalloc(sizeof(*newnode), GFP_KERNEL); + newnode = kmem_cache_zalloc(node_cache, GFP_KERNEL); if (unlikely(!newnode)) return -ENOMEM; RCU_INIT_POINTER(newnode->peer, peer); @@ -243,10 +209,10 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, if (!node) { down = rcu_dereference_protected(*trie, lockdep_is_held(lock)); } else { - down = rcu_dereference_protected(CHOOSE_NODE(node, key), - lockdep_is_held(lock)); + const u8 bit = choose(node, key); + down = rcu_dereference_protected(node->bit[bit], lockdep_is_held(lock)); if (!down) { - rcu_assign_pointer(CHOOSE_NODE(node, key), newnode); + connect_node(&node->bit[bit], bit, newnode); return 0; } } @@ -254,30 +220,29 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, parent = node; if (newnode->cidr == cidr) { - rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down); + choose_and_connect_node(newnode, down); if (!parent) - rcu_assign_pointer(*trie, newnode); + connect_node(trie, 2, newnode); else - rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits), - newnode); - } else { - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (unlikely(!node)) { - list_del(&newnode->peer_list); - kfree(newnode); - return -ENOMEM; - } - INIT_LIST_HEAD(&node->peer_list); - copy_and_assign_cidr(node, newnode->bits, cidr, bits); + choose_and_connect_node(parent, newnode); + return 0; + } - rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down); - rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode); - if (!parent) - rcu_assign_pointer(*trie, node); - else - rcu_assign_pointer(CHOOSE_NODE(parent, node->bits), - node); + node = kmem_cache_zalloc(node_cache, GFP_KERNEL); + if (unlikely(!node)) { + list_del(&newnode->peer_list); + kmem_cache_free(node_cache, newnode); + return -ENOMEM; } + INIT_LIST_HEAD(&node->peer_list); + copy_and_assign_cidr(node, newnode->bits, cidr, bits); + + choose_and_connect_node(node, down); + choose_and_connect_node(node, newnode); + if (!parent) + connect_node(trie, 2, node); + else + choose_and_connect_node(parent, node); return 0; } @@ -335,9 +300,41 @@ int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock) { + struct allowedips_node *node, *child, **parent_bit, *parent, *tmp; + bool free_parent; + + if (list_empty(&peer->allowedips_list)) + return; ++table->seq; - walk_remove_by_peer(&table->root4, peer, lock); - walk_remove_by_peer(&table->root6, peer, lock); + list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) { + list_del_init(&node->peer_list); + RCU_INIT_POINTER(node->peer, NULL); + if (node->bit[0] && node->bit[1]) + continue; + child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])], + lockdep_is_held(lock)); + if (child) + child->parent_bit_packed = node->parent_bit_packed; + parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL); + *parent_bit = child; + parent = (void *)parent_bit - + offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]); + free_parent = !rcu_access_pointer(node->bit[0]) && + !rcu_access_pointer(node->bit[1]) && + (node->parent_bit_packed & 3) <= 1 && + !rcu_access_pointer(parent->peer); + if (free_parent) + child = rcu_dereference_protected( + parent->bit[!(node->parent_bit_packed & 1)], + lockdep_is_held(lock)); + call_rcu(&node->rcu, node_free_rcu); + if (!free_parent) + continue; + if (child) + child->parent_bit_packed = parent->parent_bit_packed; + *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child; + call_rcu(&parent->rcu, node_free_rcu); + } } int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr) @@ -374,4 +371,16 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table, return NULL; } +int __init wg_allowedips_slab_init(void) +{ + node_cache = KMEM_CACHE(allowedips_node, 0); + return node_cache ? 0 : -ENOMEM; +} + +void wg_allowedips_slab_uninit(void) +{ + rcu_barrier(); + kmem_cache_destroy(node_cache); +} + #include "selftest/allowedips.c" diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h index e5c83cafcef4..2346c797eb4d 100644 --- a/drivers/net/wireguard/allowedips.h +++ b/drivers/net/wireguard/allowedips.h @@ -15,14 +15,11 @@ struct wg_peer; struct allowedips_node { struct wg_peer __rcu *peer; struct allowedips_node __rcu *bit[2]; - /* While it may seem scandalous that we waste space for v4, - * we're alloc'ing to the nearest power of 2 anyway, so this - * doesn't actually make a difference. - */ - u8 bits[16] __aligned(__alignof(u64)); u8 cidr, bit_at_a, bit_at_b, bitlen; + u8 bits[16] __aligned(__alignof(u64)); - /* Keep rarely used list at bottom to be beyond cache line. */ + /* Keep rarely used members at bottom to be beyond cache line. */ + unsigned long parent_bit_packed; union { struct list_head peer_list; struct rcu_head rcu; @@ -33,7 +30,7 @@ struct allowedips { struct allowedips_node __rcu *root4; struct allowedips_node __rcu *root6; u64 seq; -}; +} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */ void wg_allowedips_init(struct allowedips *table); void wg_allowedips_free(struct allowedips *table, struct mutex *mutex); @@ -56,4 +53,7 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table, bool wg_allowedips_selftest(void); #endif +int wg_allowedips_slab_init(void); +void wg_allowedips_slab_uninit(void); + #endif /* _WG_ALLOWEDIPS_H */ diff --git a/drivers/net/wireguard/main.c b/drivers/net/wireguard/main.c index 7a7d5f1a80fc..75dbe77b0b4b 100644 --- a/drivers/net/wireguard/main.c +++ b/drivers/net/wireguard/main.c @@ -21,13 +21,22 @@ static int __init mod_init(void) { int ret; + ret = wg_allowedips_slab_init(); + if (ret < 0) + goto err_allowedips; + #ifdef DEBUG + ret = -ENOTRECOVERABLE; if (!wg_allowedips_selftest() || !wg_packet_counter_selftest() || !wg_ratelimiter_selftest()) - return -ENOTRECOVERABLE; + goto err_peer; #endif wg_noise_init(); + ret = wg_peer_init(); + if (ret < 0) + goto err_peer; + ret = wg_device_init(); if (ret < 0) goto err_device; @@ -44,6 +53,10 @@ static int __init mod_init(void) err_netlink: wg_device_uninit(); err_device: + wg_peer_uninit(); +err_peer: + wg_allowedips_slab_uninit(); +err_allowedips: return ret; } @@ -51,6 +64,8 @@ static void __exit mod_exit(void) { wg_genetlink_uninit(); wg_device_uninit(); + wg_peer_uninit(); + wg_allowedips_slab_uninit(); } module_init(mod_init); diff --git a/drivers/net/wireguard/peer.c b/drivers/net/wireguard/peer.c index cd5cb0292cb6..1acd00ab2fbc 100644 --- a/drivers/net/wireguard/peer.c +++ b/drivers/net/wireguard/peer.c @@ -15,6 +15,7 @@ #include <linux/rcupdate.h> #include <linux/list.h> +static struct kmem_cache *peer_cache; static atomic64_t peer_counter = ATOMIC64_INIT(0); struct wg_peer *wg_peer_create(struct wg_device *wg, @@ -29,10 +30,10 @@ struct wg_peer *wg_peer_create(struct wg_device *wg, if (wg->num_peers >= MAX_PEERS_PER_DEVICE) return ERR_PTR(ret); - peer = kzalloc(sizeof(*peer), GFP_KERNEL); + peer = kmem_cache_zalloc(peer_cache, GFP_KERNEL); if (unlikely(!peer)) return ERR_PTR(ret); - if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) + if (unlikely(dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))) goto err; peer->device = wg; @@ -64,7 +65,7 @@ struct wg_peer *wg_peer_create(struct wg_device *wg, return peer; err: - kfree(peer); + kmem_cache_free(peer_cache, peer); return ERR_PTR(ret); } @@ -88,7 +89,7 @@ static void peer_make_dead(struct wg_peer *peer) /* Mark as dead, so that we don't allow jumping contexts after. */ WRITE_ONCE(peer->is_dead, true); - /* The caller must now synchronize_rcu() for this to take effect. */ + /* The caller must now synchronize_net() for this to take effect. */ } static void peer_remove_after_dead(struct wg_peer *peer) @@ -160,7 +161,7 @@ void wg_peer_remove(struct wg_peer *peer) lockdep_assert_held(&peer->device->device_update_lock); peer_make_dead(peer); - synchronize_rcu(); + synchronize_net(); peer_remove_after_dead(peer); } @@ -178,7 +179,7 @@ void wg_peer_remove_all(struct wg_device *wg) peer_make_dead(peer); list_add_tail(&peer->peer_list, &dead_peers); } - synchronize_rcu(); + synchronize_net(); list_for_each_entry_safe(peer, temp, &dead_peers, peer_list) peer_remove_after_dead(peer); } @@ -193,7 +194,8 @@ static void rcu_release(struct rcu_head *rcu) /* The final zeroing takes care of clearing any remaining handshake key * material and other potentially sensitive information. */ - kfree_sensitive(peer); + memzero_explicit(peer, sizeof(*peer)); + kmem_cache_free(peer_cache, peer); } static void kref_release(struct kref *refcount) @@ -225,3 +227,14 @@ void wg_peer_put(struct wg_peer *peer) return; kref_put(&peer->refcount, kref_release); } + +int __init wg_peer_init(void) +{ + peer_cache = KMEM_CACHE(wg_peer, 0); + return peer_cache ? 0 : -ENOMEM; +} + +void wg_peer_uninit(void) +{ + kmem_cache_destroy(peer_cache); +} diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h index 8d53b687a1d1..76e4d3128ad4 100644 --- a/drivers/net/wireguard/peer.h +++ b/drivers/net/wireguard/peer.h @@ -80,4 +80,7 @@ void wg_peer_put(struct wg_peer *peer); void wg_peer_remove(struct wg_peer *peer); void wg_peer_remove_all(struct wg_device *wg); +int wg_peer_init(void); +void wg_peer_uninit(void); + #endif /* _WG_PEER_H */ diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 846db14cb046..e173204ae7d7 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -19,32 +19,22 @@ #include <linux/siphash.h> -static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits, - u8 cidr) -{ - swap_endian(dst, src, bits); - memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8); - if (cidr) - dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8); -} - static __init void print_node(struct allowedips_node *node, u8 bits) { char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n"; - char *fmt_declaration = KERN_DEBUG - "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n"; + char *fmt_declaration = KERN_DEBUG "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n"; + u8 ip1[16], ip2[16], cidr1, cidr2; char *style = "dotted"; - u8 ip1[16], ip2[16]; u32 color = 0; + if (node == NULL) + return; if (bits == 32) { fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n"; - fmt_declaration = KERN_DEBUG - "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n"; + fmt_declaration = KERN_DEBUG "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n"; } else if (bits == 128) { fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n"; - fmt_declaration = KERN_DEBUG - "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n"; + fmt_declaration = KERN_DEBUG "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n"; } if (node->peer) { hsiphash_key_t key = { { 0 } }; @@ -55,24 +45,20 @@ static __init void print_node(struct allowedips_node *node, u8 bits) hsiphash_1u32(0xabad1dea, &key) % 200; style = "bold"; } - swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr); - printk(fmt_declaration, ip1, node->cidr, style, color); + wg_allowedips_read_node(node, ip1, &cidr1); + printk(fmt_declaration, ip1, cidr1, style, color); if (node->bit[0]) { - swap_endian_and_apply_cidr(ip2, - rcu_dereference_raw(node->bit[0])->bits, bits, - node->cidr); - printk(fmt_connection, ip1, node->cidr, ip2, - rcu_dereference_raw(node->bit[0])->cidr); - print_node(rcu_dereference_raw(node->bit[0]), bits); + wg_allowedips_read_node(rcu_dereference_raw(node->bit[0]), ip2, &cidr2); + printk(fmt_connection, ip1, cidr1, ip2, cidr2); } if (node->bit[1]) { - swap_endian_and_apply_cidr(ip2, - rcu_dereference_raw(node->bit[1])->bits, - bits, node->cidr); - printk(fmt_connection, ip1, node->cidr, ip2, - rcu_dereference_raw(node->bit[1])->cidr); - print_node(rcu_dereference_raw(node->bit[1]), bits); + wg_allowedips_read_node(rcu_dereference_raw(node->bit[1]), ip2, &cidr2); + printk(fmt_connection, ip1, cidr1, ip2, cidr2); } + if (node->bit[0]) + print_node(rcu_dereference_raw(node->bit[0]), bits); + if (node->bit[1]) + print_node(rcu_dereference_raw(node->bit[1]), bits); } static __init void print_tree(struct allowedips_node __rcu *top, u8 bits) @@ -121,8 +107,8 @@ static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr) { union nf_inet_addr mask; - memset(&mask, 0x00, 128 / 8); - memset(&mask, 0xff, cidr / 8); + memset(&mask, 0, sizeof(mask)); + memset(&mask.all, 0xff, cidr / 8); if (cidr % 32) mask.all[cidr / 32] = (__force u32)htonl( (0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL); @@ -149,42 +135,36 @@ horrible_mask_self(struct horrible_allowedips_node *node) } static __init inline bool -horrible_match_v4(const struct horrible_allowedips_node *node, - struct in_addr *ip) +horrible_match_v4(const struct horrible_allowedips_node *node, struct in_addr *ip) { return (ip->s_addr & node->mask.ip) == node->ip.ip; } static __init inline bool -horrible_match_v6(const struct horrible_allowedips_node *node, - struct in6_addr *ip) +horrible_match_v6(const struct horrible_allowedips_node *node, struct in6_addr *ip) { - return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == - node->ip.ip6[0] && - (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == - node->ip.ip6[1] && - (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == - node->ip.ip6[2] && + return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == node->ip.ip6[0] && + (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == node->ip.ip6[1] && + (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == node->ip.ip6[2] && (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3]; } static __init void -horrible_insert_ordered(struct horrible_allowedips *table, - struct horrible_allowedips_node *node) +horrible_insert_ordered(struct horrible_allowedips *table, struct horrible_allowedips_node *node) { struct horrible_allowedips_node *other = NULL, *where = NULL; u8 my_cidr = horrible_mask_to_cidr(node->mask); hlist_for_each_entry(other, &table->head, table) { - if (!memcmp(&other->mask, &node->mask, - sizeof(union nf_inet_addr)) && - !memcmp(&other->ip, &node->ip, - sizeof(union nf_inet_addr)) && - other->ip_version == node->ip_version) { + if (other->ip_version == node->ip_version && + !memcmp(&other->mask, &node->mask, sizeof(union nf_inet_addr)) && + !memcmp(&other->ip, &node->ip, sizeof(union nf_inet_addr))) { other->value = node->value; kfree(node); return; } + } + hlist_for_each_entry(other, &table->head, table) { where = other; if (horrible_mask_to_cidr(other->mask) <= my_cidr) break; @@ -201,8 +181,7 @@ static __init int horrible_allowedips_insert_v4(struct horrible_allowedips *table, struct in_addr *ip, u8 cidr, void *value) { - struct horrible_allowedips_node *node = kzalloc(sizeof(*node), - GFP_KERNEL); + struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (unlikely(!node)) return -ENOMEM; @@ -219,8 +198,7 @@ static __init int horrible_allowedips_insert_v6(struct horrible_allowedips *table, struct in6_addr *ip, u8 cidr, void *value) { - struct horrible_allowedips_node *node = kzalloc(sizeof(*node), - GFP_KERNEL); + struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (unlikely(!node)) return -ENOMEM; @@ -234,39 +212,43 @@ horrible_allowedips_insert_v6(struct horrible_allowedips *table, } static __init void * -horrible_allowedips_lookup_v4(struct horrible_allowedips *table, - struct in_addr *ip) +horrible_allowedips_lookup_v4(struct horrible_allowedips *table, struct in_addr *ip) { struct horrible_allowedips_node *node; - void *ret = NULL; hlist_for_each_entry(node, &table->head, table) { - if (node->ip_version != 4) - continue; - if (horrible_match_v4(node, ip)) { - ret = node->value; - break; - } + if (node->ip_version == 4 && horrible_match_v4(node, ip)) + return node->value; } - return ret; + return NULL; } static __init void * -horrible_allowedips_lookup_v6(struct horrible_allowedips *table, - struct in6_addr *ip) +horrible_allowedips_lookup_v6(struct horrible_allowedips *table, struct in6_addr *ip) { struct horrible_allowedips_node *node; - void *ret = NULL; hlist_for_each_entry(node, &table->head, table) { - if (node->ip_version != 6) + if (node->ip_version == 6 && horrible_match_v6(node, ip)) + return node->value; + } + return NULL; +} + + +static __init void +horrible_allowedips_remove_by_value(struct horrible_allowedips *table, void *value) +{ + struct horrible_allowedips_node *node; + struct hlist_node *h; + + hlist_for_each_entry_safe(node, h, &table->head, table) { + if (node->value != value) continue; - if (horrible_match_v6(node, ip)) { - ret = node->value; - break; - } + hlist_del(&node->table); + kfree(node); } - return ret; + } static __init bool randomized_test(void) @@ -296,6 +278,7 @@ static __init bool randomized_test(void) goto free; } kref_init(&peers[i]->refcount); + INIT_LIST_HEAD(&peers[i]->allowedips_list); } mutex_lock(&mutex); @@ -333,7 +316,7 @@ static __init bool randomized_test(void) if (wg_allowedips_insert_v4(&t, (struct in_addr *)mutated, cidr, peer, &mutex) < 0) { - pr_err("allowedips random malloc: FAIL\n"); + pr_err("allowedips random self-test malloc: FAIL\n"); goto free_locked; } if (horrible_allowedips_insert_v4(&h, @@ -396,23 +379,33 @@ static __init bool randomized_test(void) print_tree(t.root6, 128); } - for (i = 0; i < NUM_QUERIES; ++i) { - prandom_bytes(ip, 4); - if (lookup(t.root4, 32, ip) != - horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { - pr_err("allowedips random self-test: FAIL\n"); - goto free; + for (j = 0;; ++j) { + for (i = 0; i < NUM_QUERIES; ++i) { + prandom_bytes(ip, 4); + if (lookup(t.root4, 32, ip) != horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { + horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip); + pr_err("allowedips random v4 self-test: FAIL\n"); + goto free; + } + prandom_bytes(ip, 16); + if (lookup(t.root6, 128, ip) != horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { + pr_err("allowedips random v6 self-test: FAIL\n"); + goto free; + } } + if (j >= NUM_PEERS) + break; + mutex_lock(&mutex); + wg_allowedips_remove_by_peer(&t, peers[j], &mutex); + mutex_unlock(&mutex); + horrible_allowedips_remove_by_value(&h, peers[j]); } - for (i = 0; i < NUM_QUERIES; ++i) { - prandom_bytes(ip, 16); - if (lookup(t.root6, 128, ip) != - horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { - pr_err("allowedips random self-test: FAIL\n"); - goto free; - } + if (t.root4 || t.root6) { + pr_err("allowedips random self-test removal: FAIL\n"); + goto free; } + ret = true; free: diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index d9ad850daa79..8c496b747108 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -430,7 +430,7 @@ void wg_socket_reinit(struct wg_device *wg, struct sock *new4, if (new4) wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); mutex_unlock(&wg->socket_update_lock); - synchronize_rcu(); + synchronize_net(); sock_free(old4); sock_free(old6); } diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index 956157946106..dbc8aef82a65 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -845,6 +845,7 @@ enum htt_security_types { #define ATH10K_HTT_TXRX_PEER_SECURITY_MAX 2 #define ATH10K_TXRX_NUM_EXT_TIDS 19 +#define ATH10K_TXRX_NON_QOS_TID 16 enum htt_security_flags { #define HTT_SECURITY_TYPE_MASK 0x7F diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index 1a08156d5011..7ffb5d5b2a70 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -1746,16 +1746,97 @@ static void ath10k_htt_rx_h_csum_offload(struct sk_buff *msdu) msdu->ip_summed = ath10k_htt_rx_get_csum_state(msdu); } +static u64 ath10k_htt_rx_h_get_pn(struct ath10k *ar, struct sk_buff *skb, + u16 offset, + enum htt_rx_mpdu_encrypt_type enctype) +{ + struct ieee80211_hdr *hdr; + u64 pn = 0; + u8 *ehdr; + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + ehdr = skb->data + offset + ieee80211_hdrlen(hdr->frame_control); + + if (enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) { + pn = ehdr[0]; + pn |= (u64)ehdr[1] << 8; + pn |= (u64)ehdr[4] << 16; + pn |= (u64)ehdr[5] << 24; + pn |= (u64)ehdr[6] << 32; + pn |= (u64)ehdr[7] << 40; + } + return pn; +} + +static bool ath10k_htt_rx_h_frag_multicast_check(struct ath10k *ar, + struct sk_buff *skb, + u16 offset) +{ + struct ieee80211_hdr *hdr; + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + return !is_multicast_ether_addr(hdr->addr1); +} + +static bool ath10k_htt_rx_h_frag_pn_check(struct ath10k *ar, + struct sk_buff *skb, + u16 peer_id, + u16 offset, + enum htt_rx_mpdu_encrypt_type enctype) +{ + struct ath10k_peer *peer; + union htt_rx_pn_t *last_pn, new_pn = {0}; + struct ieee80211_hdr *hdr; + bool more_frags; + u8 tid, frag_number; + u32 seq; + + peer = ath10k_peer_find_by_id(ar, peer_id); + if (!peer) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "invalid peer for frag pn check\n"); + return false; + } + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + if (ieee80211_is_data_qos(hdr->frame_control)) + tid = ieee80211_get_tid(hdr); + else + tid = ATH10K_TXRX_NON_QOS_TID; + + last_pn = &peer->frag_tids_last_pn[tid]; + new_pn.pn48 = ath10k_htt_rx_h_get_pn(ar, skb, offset, enctype); + more_frags = ieee80211_has_morefrags(hdr->frame_control); + frag_number = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG; + seq = (__le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4; + + if (frag_number == 0) { + last_pn->pn48 = new_pn.pn48; + peer->frag_tids_seq[tid] = seq; + } else { + if (seq != peer->frag_tids_seq[tid]) + return false; + + if (new_pn.pn48 != last_pn->pn48 + 1) + return false; + + last_pn->pn48 = new_pn.pn48; + } + + return true; +} + static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, struct sk_buff_head *amsdu, struct ieee80211_rx_status *status, bool fill_crypt_header, u8 *rx_hdr, - enum ath10k_pkt_rx_err *err) + enum ath10k_pkt_rx_err *err, + u16 peer_id, + bool frag) { struct sk_buff *first; struct sk_buff *last; - struct sk_buff *msdu; + struct sk_buff *msdu, *temp; struct htt_rx_desc *rxd; struct ieee80211_hdr *hdr; enum htt_rx_mpdu_encrypt_type enctype; @@ -1768,6 +1849,7 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, bool is_decrypted; bool is_mgmt; u32 attention; + bool frag_pn_check = true, multicast_check = true; if (skb_queue_empty(amsdu)) return; @@ -1866,7 +1948,37 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, } skb_queue_walk(amsdu, msdu) { + if (frag && !fill_crypt_header && is_decrypted && + enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) + frag_pn_check = ath10k_htt_rx_h_frag_pn_check(ar, + msdu, + peer_id, + 0, + enctype); + + if (frag) + multicast_check = ath10k_htt_rx_h_frag_multicast_check(ar, + msdu, + 0); + + if (!frag_pn_check || !multicast_check) { + /* Discard the fragment with invalid PN or multicast DA + */ + temp = msdu->prev; + __skb_unlink(msdu, amsdu); + dev_kfree_skb_any(msdu); + msdu = temp; + frag_pn_check = true; + multicast_check = true; + continue; + } + ath10k_htt_rx_h_csum_offload(msdu); + + if (frag && !fill_crypt_header && + enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA) + status->flag &= ~RX_FLAG_MMIC_STRIPPED; + ath10k_htt_rx_h_undecap(ar, msdu, status, first_hdr, enctype, is_decrypted); @@ -1884,6 +1996,11 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, hdr = (void *)msdu->data; hdr->frame_control &= ~__cpu_to_le16(IEEE80211_FCTL_PROTECTED); + + if (frag && !fill_crypt_header && + enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA) + status->flag &= ~RX_FLAG_IV_STRIPPED & + ~RX_FLAG_MMIC_STRIPPED; } } @@ -1991,14 +2108,62 @@ static void ath10k_htt_rx_h_unchain(struct ath10k *ar, ath10k_unchain_msdu(amsdu, unchain_cnt); } +static bool ath10k_htt_rx_validate_amsdu(struct ath10k *ar, + struct sk_buff_head *amsdu) +{ + u8 *subframe_hdr; + struct sk_buff *first; + bool is_first, is_last; + struct htt_rx_desc *rxd; + struct ieee80211_hdr *hdr; + size_t hdr_len, crypto_len; + enum htt_rx_mpdu_encrypt_type enctype; + int bytes_aligned = ar->hw_params.decap_align_bytes; + + first = skb_peek(amsdu); + + rxd = (void *)first->data - sizeof(*rxd); + hdr = (void *)rxd->rx_hdr_status; + + is_first = !!(rxd->msdu_end.common.info0 & + __cpu_to_le32(RX_MSDU_END_INFO0_FIRST_MSDU)); + is_last = !!(rxd->msdu_end.common.info0 & + __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU)); + + /* Return in case of non-aggregated msdu */ + if (is_first && is_last) + return true; + + /* First msdu flag is not set for the first msdu of the list */ + if (!is_first) + return false; + + enctype = MS(__le32_to_cpu(rxd->mpdu_start.info0), + RX_MPDU_START_INFO0_ENCRYPT_TYPE); + + hdr_len = ieee80211_hdrlen(hdr->frame_control); + crypto_len = ath10k_htt_rx_crypto_param_len(ar, enctype); + + subframe_hdr = (u8 *)hdr + round_up(hdr_len, bytes_aligned) + + crypto_len; + + /* Validate if the amsdu has a proper first subframe. + * There are chances a single msdu can be received as amsdu when + * the unauthenticated amsdu flag of a QoS header + * gets flipped in non-SPP AMSDU's, in such cases the first + * subframe has llc/snap header in place of a valid da. + * return false if the da matches rfc1042 pattern + */ + if (ether_addr_equal(subframe_hdr, rfc1042_header)) + return false; + + return true; +} + static bool ath10k_htt_rx_amsdu_allowed(struct ath10k *ar, struct sk_buff_head *amsdu, struct ieee80211_rx_status *rx_status) { - /* FIXME: It might be a good idea to do some fuzzy-testing to drop - * invalid/dangerous frames. - */ - if (!rx_status->freq) { ath10k_dbg(ar, ATH10K_DBG_HTT, "no channel configured; ignoring frame(s)!\n"); return false; @@ -2009,6 +2174,11 @@ static bool ath10k_htt_rx_amsdu_allowed(struct ath10k *ar, return false; } + if (!ath10k_htt_rx_validate_amsdu(ar, amsdu)) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "invalid amsdu received\n"); + return false; + } + return true; } @@ -2071,7 +2241,8 @@ static int ath10k_htt_rx_handle_amsdu(struct ath10k_htt *htt) ath10k_htt_rx_h_unchain(ar, &amsdu, &drop_cnt, &unchain_cnt); ath10k_htt_rx_h_filter(ar, &amsdu, rx_status, &drop_cnt_filter); - ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true, first_hdr, &err); + ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true, first_hdr, &err, 0, + false); msdus_to_queue = skb_queue_len(&amsdu); ath10k_htt_rx_h_enqueue(ar, &amsdu, rx_status); @@ -2204,6 +2375,11 @@ static bool ath10k_htt_rx_proc_rx_ind_hl(struct ath10k_htt *htt, fw_desc = &rx->fw_desc; rx_desc_len = fw_desc->len; + if (fw_desc->u.bits.discard) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "htt discard mpdu\n"); + goto err; + } + /* I have not yet seen any case where num_mpdu_ranges > 1. * qcacld does not seem handle that case either, so we introduce the * same limitiation here as well. @@ -2509,6 +2685,13 @@ static bool ath10k_htt_rx_proc_rx_frag_ind_hl(struct ath10k_htt *htt, rx_desc = (struct htt_hl_rx_desc *)(skb->data + tot_hdr_len); rx_desc_info = __le32_to_cpu(rx_desc->info); + hdr = (struct ieee80211_hdr *)((u8 *)rx_desc + rx_hl->fw_desc.len); + + if (is_multicast_ether_addr(hdr->addr1)) { + /* Discard the fragment with multicast DA */ + goto err; + } + if (!MS(rx_desc_info, HTT_RX_DESC_HL_INFO_ENCRYPTED)) { spin_unlock_bh(&ar->data_lock); return ath10k_htt_rx_proc_rx_ind_hl(htt, &resp->rx_ind_hl, skb, @@ -2516,8 +2699,6 @@ static bool ath10k_htt_rx_proc_rx_frag_ind_hl(struct ath10k_htt *htt, HTT_RX_NON_TKIP_MIC); } - hdr = (struct ieee80211_hdr *)((u8 *)rx_desc + rx_hl->fw_desc.len); - if (ieee80211_has_retry(hdr->frame_control)) goto err; @@ -3027,7 +3208,7 @@ static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb) ath10k_htt_rx_h_ppdu(ar, &amsdu, status, vdev_id); ath10k_htt_rx_h_filter(ar, &amsdu, status, NULL); ath10k_htt_rx_h_mpdu(ar, &amsdu, status, false, NULL, - NULL); + NULL, peer_id, frag); ath10k_htt_rx_h_enqueue(ar, &amsdu, status); break; case -EAGAIN: diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h index f2b6bf8f0d60..705b6295e466 100644 --- a/drivers/net/wireless/ath/ath10k/rx_desc.h +++ b/drivers/net/wireless/ath/ath10k/rx_desc.h @@ -1282,7 +1282,19 @@ struct fw_rx_desc_base { #define FW_RX_DESC_UDP (1 << 6) struct fw_rx_desc_hl { - u8 info0; + union { + struct { + u8 discard:1, + forward:1, + any_err:1, + dup_err:1, + reserved:1, + inspect:1, + extension:2; + } bits; + u8 info0; + } u; + u8 version; u8 len; u8 flags; diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 1d9aa1bb6b6e..603d2f93ac18 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -260,6 +260,16 @@ static void ath11k_dp_rxdesc_set_msdu_len(struct ath11k_base *ab, ab->hw_params.hw_ops->rx_desc_set_msdu_len(desc, len); } +static bool ath11k_dp_rx_h_attn_is_mcbc(struct ath11k_base *ab, + struct hal_rx_desc *desc) +{ + struct rx_attention *attn = ath11k_dp_rx_get_attention(ab, desc); + + return ath11k_dp_rx_h_msdu_end_first_msdu(ab, desc) && + (!!FIELD_GET(RX_ATTENTION_INFO1_MCAST_BCAST, + __le32_to_cpu(attn->info1))); +} + static void ath11k_dp_service_mon_ring(struct timer_list *t) { struct ath11k_base *ab = from_timer(ab, t, mon_reap_timer); @@ -852,6 +862,24 @@ static void ath11k_dp_rx_frags_cleanup(struct dp_rx_tid *rx_tid, bool rel_link_d __skb_queue_purge(&rx_tid->rx_frags); } +void ath11k_peer_frags_flush(struct ath11k *ar, struct ath11k_peer *peer) +{ + struct dp_rx_tid *rx_tid; + int i; + + lockdep_assert_held(&ar->ab->base_lock); + + for (i = 0; i <= IEEE80211_NUM_TIDS; i++) { + rx_tid = &peer->rx_tid[i]; + + spin_unlock_bh(&ar->ab->base_lock); + del_timer_sync(&rx_tid->frag_timer); + spin_lock_bh(&ar->ab->base_lock); + + ath11k_dp_rx_frags_cleanup(rx_tid, true); + } +} + void ath11k_peer_rx_tid_cleanup(struct ath11k *ar, struct ath11k_peer *peer) { struct dp_rx_tid *rx_tid; @@ -3450,6 +3478,7 @@ static int ath11k_dp_rx_frag_h_mpdu(struct ath11k *ar, u8 tid; int ret = 0; bool more_frags; + bool is_mcbc; rx_desc = (struct hal_rx_desc *)msdu->data; peer_id = ath11k_dp_rx_h_mpdu_start_peer_id(ar->ab, rx_desc); @@ -3457,6 +3486,11 @@ static int ath11k_dp_rx_frag_h_mpdu(struct ath11k *ar, seqno = ath11k_dp_rx_h_mpdu_start_seq_no(ar->ab, rx_desc); frag_no = ath11k_dp_rx_h_mpdu_start_frag_no(ar->ab, msdu); more_frags = ath11k_dp_rx_h_mpdu_start_more_frags(ar->ab, msdu); + is_mcbc = ath11k_dp_rx_h_attn_is_mcbc(ar->ab, rx_desc); + + /* Multicast/Broadcast fragments are not expected */ + if (is_mcbc) + return -EINVAL; if (!ath11k_dp_rx_h_mpdu_start_seq_ctrl_valid(ar->ab, rx_desc) || !ath11k_dp_rx_h_mpdu_start_fc_valid(ar->ab, rx_desc) || diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.h b/drivers/net/wireless/ath/ath11k/dp_rx.h index bf399312b5ff..623da3bf9dc8 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.h +++ b/drivers/net/wireless/ath/ath11k/dp_rx.h @@ -49,6 +49,7 @@ int ath11k_dp_peer_rx_pn_replay_config(struct ath11k_vif *arvif, const u8 *peer_addr, enum set_key_cmd key_cmd, struct ieee80211_key_conf *key); +void ath11k_peer_frags_flush(struct ath11k *ar, struct ath11k_peer *peer); void ath11k_peer_rx_tid_cleanup(struct ath11k *ar, struct ath11k_peer *peer); void ath11k_peer_rx_tid_delete(struct ath11k *ar, struct ath11k_peer *peer, u8 tid); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 4df425dd31a2..9d0ff150ec30 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2779,6 +2779,12 @@ static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, */ spin_lock_bh(&ab->base_lock); peer = ath11k_peer_find(ab, arvif->vdev_id, peer_addr); + + /* flush the fragments cache during key (re)install to + * ensure all frags in the new frag list belong to the same key. + */ + if (peer && cmd == SET_KEY) + ath11k_peer_frags_flush(ar, peer); spin_unlock_bh(&ab->base_lock); if (!peer) { diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 51ce767eaf88..7a6fd46d0c6e 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1693,8 +1693,13 @@ static int mac80211_hwsim_start(struct ieee80211_hw *hw) static void mac80211_hwsim_stop(struct ieee80211_hw *hw) { struct mac80211_hwsim_data *data = hw->priv; + data->started = false; hrtimer_cancel(&data->beacon_timer); + + while (!skb_queue_empty(&data->pending)) + ieee80211_free_txskb(hw, skb_dequeue(&data->pending)); + wiphy_dbg(hw->wiphy, "%s\n", __func__); } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 977acab0360a..03fe62837557 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -514,10 +514,36 @@ EXPORT_SYMBOL_GPL(mt76_free_device); static void mt76_rx_release_amsdu(struct mt76_phy *phy, enum mt76_rxq_id q) { struct sk_buff *skb = phy->rx_amsdu[q].head; + struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb; struct mt76_dev *dev = phy->dev; phy->rx_amsdu[q].head = NULL; phy->rx_amsdu[q].tail = NULL; + + /* + * Validate if the amsdu has a proper first subframe. + * A single MSDU can be parsed as A-MSDU when the unauthenticated A-MSDU + * flag of the QoS header gets flipped. In such cases, the first + * subframe has a LLC/SNAP header in the location of the destination + * address. + */ + if (skb_shinfo(skb)->frag_list) { + int offset = 0; + + if (!(status->flag & RX_FLAG_8023)) { + offset = ieee80211_get_hdrlen_from_skb(skb); + + if ((status->flag & + (RX_FLAG_DECRYPTED | RX_FLAG_IV_STRIPPED)) == + RX_FLAG_DECRYPTED) + offset += 8; + } + + if (ether_addr_equal(skb->data + offset, rfc1042_header)) { + dev_kfree_skb(skb); + return; + } + } __skb_queue_tail(&dev->rx_skb[q], skb); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c index 86341d1f82f3..d20f05a7717d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c @@ -510,7 +510,6 @@ void mt7615_init_device(struct mt7615_dev *dev) mutex_init(&dev->pm.mutex); init_waitqueue_head(&dev->pm.wait); spin_lock_init(&dev->pm.txq_lock); - set_bit(MT76_STATE_PM, &dev->mphy.state); INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7615_mac_work); INIT_DELAYED_WORK(&dev->phy.scan_work, mt7615_scan_work); INIT_DELAYED_WORK(&dev->coredump.work, mt7615_coredump_work); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index f81a17d56008..e2dcfee6be81 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -1912,8 +1912,9 @@ void mt7615_pm_wake_work(struct work_struct *work) napi_schedule(&dev->mt76.napi[i]); mt76_connac_pm_dequeue_skbs(mphy, &dev->pm); mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_WM], false); - ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, - MT7615_WATCHDOG_TIME); + if (test_bit(MT76_STATE_RUNNING, &mphy->state)) + ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, + MT7615_WATCHDOG_TIME); } ieee80211_wake_queues(mphy->hw); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c index 17fe4187d1de..d1be78b0711c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c @@ -51,16 +51,13 @@ mt7663s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb, return ret; } -static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev) +static int __mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev) { struct sdio_func *func = dev->mt76.sdio.func; struct mt76_phy *mphy = &dev->mt76.phy; u32 status; int ret; - if (!test_and_clear_bit(MT76_STATE_PM, &mphy->state)) - goto out; - sdio_claim_host(func); sdio_writel(func, WHLPCR_FW_OWN_REQ_CLR, MCR_WHLPCR, NULL); @@ -76,13 +73,21 @@ static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev) } sdio_release_host(func); - -out: dev->pm.last_activity = jiffies; return 0; } +static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev) +{ + struct mt76_phy *mphy = &dev->mt76.phy; + + if (test_and_clear_bit(MT76_STATE_PM, &mphy->state)) + return __mt7663s_mcu_drv_pmctrl(dev); + + return 0; +} + static int mt7663s_mcu_fw_pmctrl(struct mt7615_dev *dev) { struct sdio_func *func = dev->mt76.sdio.func; @@ -123,7 +128,7 @@ int mt7663s_mcu_init(struct mt7615_dev *dev) struct mt7615_mcu_ops *mcu_ops; int ret; - ret = mt7663s_mcu_drv_pmctrl(dev); + ret = __mt7663s_mcu_drv_pmctrl(dev); if (ret) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c index c55698f9c49a..028ff432d811 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c @@ -55,10 +55,7 @@ int mt7663u_mcu_init(struct mt7615_dev *dev) dev->mt76.mcu_ops = &mt7663u_mcu_ops, - /* usb does not support runtime-pm */ - clear_bit(MT76_STATE_PM, &dev->mphy.state); mt76_set(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN); - if (test_and_clear_bit(MT76_STATE_POWER_OFF, &dev->mphy.state)) { mt7615_mcu_restart(&dev->mt76); if (!mt76_poll_msec(dev, MT_CONN_ON_MISC, diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index fe0ab5e5ff81..619561606f96 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -721,6 +721,10 @@ void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb, phy->phy_type = mt76_connac_get_phy_mode_v2(mphy, vif, band, sta); phy->basic_rate = cpu_to_le16((u16)vif->bss_conf.basic_rates); phy->rcpi = rcpi; + phy->ampdu = FIELD_PREP(IEEE80211_HT_AMPDU_PARM_FACTOR, + sta->ht_cap.ampdu_factor) | + FIELD_PREP(IEEE80211_HT_AMPDU_PARM_DENSITY, + sta->ht_cap.ampdu_density); tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra_info)); ra_info = (struct sta_rec_ra_info *)tlv; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c index 5847f943e8da..b795e7245c07 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c @@ -87,7 +87,7 @@ static const struct ieee80211_ops mt76x0e_ops = { .reconfig_complete = mt76x02_reconfig_complete, }; -static int mt76x0e_register_device(struct mt76x02_dev *dev) +static int mt76x0e_init_hardware(struct mt76x02_dev *dev, bool resume) { int err; @@ -100,9 +100,11 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) if (err < 0) return err; - err = mt76x02_dma_init(dev); - if (err < 0) - return err; + if (!resume) { + err = mt76x02_dma_init(dev); + if (err < 0) + return err; + } err = mt76x0_init_hardware(dev); if (err < 0) @@ -123,6 +125,17 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) mt76_clear(dev, 0x110, BIT(9)); mt76_set(dev, MT_MAX_LEN_CFG, BIT(13)); + return 0; +} + +static int mt76x0e_register_device(struct mt76x02_dev *dev) +{ + int err; + + err = mt76x0e_init_hardware(dev, false); + if (err < 0) + return err; + err = mt76x0_register_device(dev); if (err < 0) return err; @@ -167,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return ret; + mt76_pci_disable_aspm(pdev); + mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt76x0e_ops, &drv_ops); if (!mdev) @@ -220,6 +235,60 @@ mt76x0e_remove(struct pci_dev *pdev) mt76_free_device(mdev); } +#ifdef CONFIG_PM +static int mt76x0e_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int i; + + mt76_worker_disable(&mdev->tx_worker); + for (i = 0; i < ARRAY_SIZE(mdev->phy.q_tx); i++) + mt76_queue_tx_cleanup(dev, mdev->phy.q_tx[i], true); + for (i = 0; i < ARRAY_SIZE(mdev->q_mcu); i++) + mt76_queue_tx_cleanup(dev, mdev->q_mcu[i], true); + napi_disable(&mdev->tx_napi); + + mt76_for_each_q_rx(mdev, i) + napi_disable(&mdev->napi[i]); + + mt76x02_dma_disable(dev); + mt76x02_mcu_cleanup(dev); + mt76x0_chip_onoff(dev, false, false); + + pci_enable_wake(pdev, pci_choose_state(pdev, state), true); + pci_save_state(pdev); + + return pci_set_power_state(pdev, pci_choose_state(pdev, state)); +} + +static int mt76x0e_resume(struct pci_dev *pdev) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int err, i; + + err = pci_set_power_state(pdev, PCI_D0); + if (err) + return err; + + pci_restore_state(pdev); + + mt76_worker_enable(&mdev->tx_worker); + + mt76_for_each_q_rx(mdev, i) { + mt76_queue_rx_reset(dev, i); + napi_enable(&mdev->napi[i]); + napi_schedule(&mdev->napi[i]); + } + + napi_enable(&mdev->tx_napi); + napi_schedule(&mdev->tx_napi); + + return mt76x0e_init_hardware(dev, true); +} +#endif /* CONFIG_PM */ + static const struct pci_device_id mt76x0e_device_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7610) }, { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7630) }, @@ -237,6 +306,10 @@ static struct pci_driver mt76x0e_driver = { .id_table = mt76x0e_device_table, .probe = mt76x0e_probe, .remove = mt76x0e_remove, +#ifdef CONFIG_PM + .suspend = mt76x0e_suspend, + .resume = mt76x0e_resume, +#endif /* CONFIG_PM */ }; module_pci_driver(mt76x0e_driver); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c index fe28bf4050c4..1763ea0614ce 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c @@ -76,8 +76,8 @@ mt7921_init_wiphy(struct ieee80211_hw *hw) struct wiphy *wiphy = hw->wiphy; hw->queues = 4; - hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; - hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; + hw->max_rx_aggregation_subframes = 64; + hw->max_tx_aggregation_subframes = 128; hw->radiotap_timestamp.units_pos = IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index 214bd1859792..decf2d5f0ce3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -1404,8 +1404,9 @@ void mt7921_pm_wake_work(struct work_struct *work) napi_schedule(&dev->mt76.napi[i]); mt76_connac_pm_dequeue_skbs(mphy, &dev->pm); mt7921_tx_cleanup(dev); - ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, - MT7921_WATCHDOG_TIME); + if (test_bit(MT76_STATE_RUNNING, &mphy->state)) + ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, + MT7921_WATCHDOG_TIME); } ieee80211_wake_queues(mphy->hw); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index f4c27aa41048..97a0ef331ac3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -74,8 +74,7 @@ mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band, IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G; else if (band == NL80211_BAND_5GHZ) he_cap_elem->phy_cap_info[0] = - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G; he_cap_elem->phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index 5f3d56d570a5..67dc4b4cc094 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -402,20 +402,22 @@ static void mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb, u16 wlan_idx) { - struct mt7921_mcu_wlan_info_event *wtbl_info = - (struct mt7921_mcu_wlan_info_event *)(skb->data); - struct rate_info rate = {}; - u8 curr_idx = wtbl_info->rate_info.rate_idx; - u16 curr = le16_to_cpu(wtbl_info->rate_info.rate[curr_idx]); - struct mt7921_mcu_peer_cap peer = wtbl_info->peer_cap; + struct mt7921_mcu_wlan_info_event *wtbl_info; struct mt76_phy *mphy = &dev->mphy; struct mt7921_sta_stats *stats; + struct rate_info rate = {}; struct mt7921_sta *msta; struct mt76_wcid *wcid; + u8 idx; if (wlan_idx >= MT76_N_WCIDS) return; + wtbl_info = (struct mt7921_mcu_wlan_info_event *)skb->data; + idx = wtbl_info->rate_info.rate_idx; + if (idx >= ARRAY_SIZE(wtbl_info->rate_info.rate)) + return; + rcu_read_lock(); wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]); @@ -426,7 +428,8 @@ mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb, stats = &msta->stats; /* current rate */ - mt7921_mcu_tx_rate_parse(mphy, &peer, &rate, curr); + mt7921_mcu_tx_rate_parse(mphy, &wtbl_info->peer_cap, &rate, + le16_to_cpu(wtbl_info->rate_info.rate[idx])); stats->tx_rate = rate; out: rcu_read_unlock(); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 193b723fe3bd..c58996c1e230 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -684,6 +684,7 @@ static void xenvif_disconnect_queue(struct xenvif_queue *queue) { if (queue->task) { kthread_stop(queue->task); + put_task_struct(queue->task); queue->task = NULL; } @@ -745,6 +746,11 @@ int xenvif_connect_data(struct xenvif_queue *queue, if (IS_ERR(task)) goto kthread_err; queue->task = task; + /* + * Take a reference to the task in order to prevent it from being freed + * if the thread function returns before kthread_stop is called. + */ + get_task_struct(task); task = kthread_run(xenvif_dealloc_kthread, queue, "%s-dealloc", queue->name); diff --git a/drivers/nfc/nfcmrvl/fw_dnld.h b/drivers/nfc/nfcmrvl/fw_dnld.h index ee4a339c05fd..058ce77b3cbc 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.h +++ b/drivers/nfc/nfcmrvl/fw_dnld.h @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC driver: Firmware downloader * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 18cd96284b77..c5420616b7bc 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-I2C driver: I2C interface related functions * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/nfcmrvl.h b/drivers/nfc/nfcmrvl/nfcmrvl.h index de68ff45e49a..e84ee18c73ae 100644 --- a/drivers/nfc/nfcmrvl/nfcmrvl.h +++ b/drivers/nfc/nfcmrvl/nfcmrvl.h @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC driver * * Copyright (C) 2014-2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c index 8e0ddb434770..dec0d3eb3648 100644 --- a/drivers/nfc/nfcmrvl/spi.c +++ b/drivers/nfc/nfcmrvl/spi.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-SPI driver: SPI interface related functions * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index e5a622ce4b95..7194dd7ef0f1 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-UART driver * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c index 888e298f610b..bcd563cb556c 100644 --- a/drivers/nfc/nfcmrvl/usb.c +++ b/drivers/nfc/nfcmrvl/usb.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-USB driver: USB interface related functions * * Copyright (C) 2014, Marvell International Ltd. diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index a44d49d63968..494675aeaaad 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -71,7 +71,8 @@ config NVME_FC config NVME_TCP tristate "NVM Express over Fabrics TCP host driver" depends on INET - depends on BLK_DEV_NVME + depends on BLOCK + select NVME_CORE select NVME_FABRICS select CRYPTO select CRYPTO_CRC32C diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 762125f2905f..66973bb56305 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3485,8 +3485,10 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, cdev_init(cdev, fops); cdev->owner = owner; ret = cdev_device_add(cdev, cdev_device); - if (ret) + if (ret) { + put_device(cdev_device); ida_simple_remove(&nvme_ns_chr_minor_ida, minor); + } return ret; } diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index a2bb7fc63a73..34a84d2086c7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -336,6 +336,11 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, cmd->connect.recfmt); break; + case NVME_SC_HOST_PATH_ERROR: + dev_err(ctrl->device, + "Connect command failed: host path error\n"); + break; + default: dev_err(ctrl->device, "Connect command failed, error wo/DNR bit: %d\n", diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 256e87721a01..f183f9fa03d0 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3107,6 +3107,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (ctrl->ctrl.icdoff) { dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n", ctrl->ctrl.icdoff); + ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR; goto out_disconnect_admin_queue; } @@ -3114,6 +3115,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) { dev_err(ctrl->ctrl.device, "Mandatory sgls are not supported!\n"); + ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR; goto out_disconnect_admin_queue; } @@ -3280,11 +3282,13 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) return; - if (portptr->port_state == FC_OBJSTATE_ONLINE) + if (portptr->port_state == FC_OBJSTATE_ONLINE) { dev_info(ctrl->ctrl.device, "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", ctrl->cnum, status); - else if (time_after_eq(jiffies, rport->dev_loss_end)) + if (status > 0 && (status & NVME_SC_DNR)) + recon = false; + } else if (time_after_eq(jiffies, rport->dev_loss_end)) recon = false; if (recon && nvmf_should_reconnect(&ctrl->ctrl)) { @@ -3298,12 +3302,17 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay); } else { - if (portptr->port_state == FC_OBJSTATE_ONLINE) - dev_warn(ctrl->ctrl.device, - "NVME-FC{%d}: Max reconnect attempts (%d) " - "reached.\n", - ctrl->cnum, ctrl->ctrl.nr_reconnects); - else + if (portptr->port_state == FC_OBJSTATE_ONLINE) { + if (status > 0 && (status & NVME_SC_DNR)) + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: reconnect failure\n", + ctrl->cnum); + else + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: Max reconnect attempts " + "(%d) reached.\n", + ctrl->cnum, ctrl->ctrl.nr_reconnects); + } else dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: dev_loss_tmo (%d) expired " "while waiting for remoteport connectivity.\n", diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 37943dc4c2c1..4697a94c0945 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1320,16 +1320,17 @@ static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue, int count) { struct nvme_sgl_desc *sg = &c->common.dptr.sgl; - struct scatterlist *sgl = req->data_sgl.sg_table.sgl; struct ib_sge *sge = &req->sge[1]; + struct scatterlist *sgl; u32 len = 0; int i; - for (i = 0; i < count; i++, sgl++, sge++) { + for_each_sg(req->data_sgl.sg_table.sgl, sgl, count, i) { sge->addr = sg_dma_address(sgl); sge->length = sg_dma_len(sgl); sge->lkey = queue->device->pd->local_dma_lkey; len += sge->length; + sge++; } sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 1853db38b682..b20b8d0a1144 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -388,10 +388,10 @@ static void nvmet_keep_alive_timer(struct work_struct *work) { struct nvmet_ctrl *ctrl = container_of(to_delayed_work(work), struct nvmet_ctrl, ka_work); - bool cmd_seen = ctrl->cmd_seen; + bool reset_tbkas = ctrl->reset_tbkas; - ctrl->cmd_seen = false; - if (cmd_seen) { + ctrl->reset_tbkas = false; + if (reset_tbkas) { pr_debug("ctrl %d reschedule traffic based keep-alive timer\n", ctrl->cntlid); schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); @@ -804,6 +804,13 @@ void nvmet_sq_destroy(struct nvmet_sq *sq) percpu_ref_exit(&sq->ref); if (ctrl) { + /* + * The teardown flow may take some time, and the host may not + * send us keep-alive during this period, hence reset the + * traffic based keep-alive timer so we don't trigger a + * controller teardown as a result of a keep-alive expiration. + */ + ctrl->reset_tbkas = true; nvmet_ctrl_put(ctrl); sq->ctrl = NULL; /* allows reusing the queue later */ } @@ -952,7 +959,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, } if (sq->ctrl) - sq->ctrl->cmd_seen = true; + sq->ctrl->reset_tbkas = true; return true; @@ -998,19 +1005,23 @@ static unsigned int nvmet_data_transfer_len(struct nvmet_req *req) return req->transfer_len - req->metadata_len; } -static int nvmet_req_alloc_p2pmem_sgls(struct nvmet_req *req) +static int nvmet_req_alloc_p2pmem_sgls(struct pci_dev *p2p_dev, + struct nvmet_req *req) { - req->sg = pci_p2pmem_alloc_sgl(req->p2p_dev, &req->sg_cnt, + req->sg = pci_p2pmem_alloc_sgl(p2p_dev, &req->sg_cnt, nvmet_data_transfer_len(req)); if (!req->sg) goto out_err; if (req->metadata_len) { - req->metadata_sg = pci_p2pmem_alloc_sgl(req->p2p_dev, + req->metadata_sg = pci_p2pmem_alloc_sgl(p2p_dev, &req->metadata_sg_cnt, req->metadata_len); if (!req->metadata_sg) goto out_free_sg; } + + req->p2p_dev = p2p_dev; + return 0; out_free_sg: pci_p2pmem_free_sgl(req->p2p_dev, req->sg); @@ -1018,25 +1029,19 @@ out_err: return -ENOMEM; } -static bool nvmet_req_find_p2p_dev(struct nvmet_req *req) +static struct pci_dev *nvmet_req_find_p2p_dev(struct nvmet_req *req) { - if (!IS_ENABLED(CONFIG_PCI_P2PDMA)) - return false; - - if (req->sq->ctrl && req->sq->qid && req->ns) { - req->p2p_dev = radix_tree_lookup(&req->sq->ctrl->p2p_ns_map, - req->ns->nsid); - if (req->p2p_dev) - return true; - } - - req->p2p_dev = NULL; - return false; + if (!IS_ENABLED(CONFIG_PCI_P2PDMA) || + !req->sq->ctrl || !req->sq->qid || !req->ns) + return NULL; + return radix_tree_lookup(&req->sq->ctrl->p2p_ns_map, req->ns->nsid); } int nvmet_req_alloc_sgls(struct nvmet_req *req) { - if (nvmet_req_find_p2p_dev(req) && !nvmet_req_alloc_p2pmem_sgls(req)) + struct pci_dev *p2p_dev = nvmet_req_find_p2p_dev(req); + + if (p2p_dev && !nvmet_req_alloc_p2pmem_sgls(p2p_dev, req)) return 0; req->sg = sgl_alloc(nvmet_data_transfer_len(req), GFP_KERNEL, @@ -1065,6 +1070,7 @@ void nvmet_req_free_sgls(struct nvmet_req *req) pci_p2pmem_free_sgl(req->p2p_dev, req->sg); if (req->metadata_sg) pci_p2pmem_free_sgl(req->p2p_dev, req->metadata_sg); + req->p2p_dev = NULL; } else { sgl_free(req->sg); if (req->metadata_sg) diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index cb30cb942e1d..a5c4a1865026 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -263,7 +263,8 @@ static const struct blk_mq_ops nvme_loop_admin_mq_ops = { static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl) { - clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags); + if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags)) + return; nvmet_sq_destroy(&ctrl->queues[0].nvme_sq); blk_cleanup_queue(ctrl->ctrl.admin_q); blk_cleanup_queue(ctrl->ctrl.fabrics_q); @@ -299,6 +300,7 @@ static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl) clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags); nvmet_sq_destroy(&ctrl->queues[i].nvme_sq); } + ctrl->ctrl.queue_count = 1; } static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl) @@ -405,6 +407,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) return 0; out_cleanup_queue: + clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags); blk_cleanup_queue(ctrl->ctrl.admin_q); out_cleanup_fabrics_q: blk_cleanup_queue(ctrl->ctrl.fabrics_q); @@ -462,8 +465,10 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work) nvme_loop_shutdown_ctrl(ctrl); if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { - /* state change failure should never happen */ - WARN_ON_ONCE(1); + if (ctrl->ctrl.state != NVME_CTRL_DELETING && + ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO) + /* state change failure for non-deleted ctrl? */ + WARN_ON_ONCE(1); return; } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index d69a409515d6..53aea9a8056e 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -167,7 +167,7 @@ struct nvmet_ctrl { struct nvmet_subsys *subsys; struct nvmet_sq **sqs; - bool cmd_seen; + bool reset_tbkas; struct mutex lock; u64 cap; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index f9f34f6caf5e..d8aceef83284 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -550,7 +550,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req) * nvmet_req_init is completed. */ if (queue->rcv_state == NVMET_TCP_RECV_PDU && - len && len < cmd->req.port->inline_data_size && + len && len <= cmd->req.port->inline_data_size && nvme_is_write(cmd->req.cmd)) return; } diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile index eca805c1a023..9e6ce0dc2f53 100644 --- a/drivers/pci/controller/dwc/Makefile +++ b/drivers/pci/controller/dwc/Makefile @@ -18,6 +18,7 @@ obj-$(CONFIG_PCIE_INTEL_GW) += pcie-intel-gw.o obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o obj-$(CONFIG_PCI_MESON) += pci-meson.o +obj-$(CONFIG_PCIE_TEGRA194) += pcie-tegra194.o obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o obj-$(CONFIG_PCIE_UNIPHIER_EP) += pcie-uniphier-ep.o @@ -38,6 +39,6 @@ ifdef CONFIG_ACPI ifdef CONFIG_PCI_QUIRKS obj-$(CONFIG_ARM64) += pcie-al.o obj-$(CONFIG_ARM64) += pcie-hisi.o -obj-$(CONFIG_ARM64) += pcie-tegra194.o +obj-$(CONFIG_ARM64) += pcie-tegra194-acpi.o endif endif diff --git a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c new file mode 100644 index 000000000000..c2de6ed4d86f --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * ACPI quirks for Tegra194 PCIe host controller + * + * Copyright (C) 2021 NVIDIA Corporation. + * + * Author: Vidya Sagar <vidyas@nvidia.com> + */ + +#include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> + +#include "pcie-designware.h" + +struct tegra194_pcie_ecam { + void __iomem *config_base; + void __iomem *iatu_base; + void __iomem *dbi_base; +}; + +static int tegra194_acpi_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct tegra194_pcie_ecam *pcie_ecam; + + pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL); + if (!pcie_ecam) + return -ENOMEM; + + pcie_ecam->config_base = cfg->win; + pcie_ecam->iatu_base = cfg->win + SZ_256K; + pcie_ecam->dbi_base = cfg->win + SZ_512K; + cfg->priv = pcie_ecam; + + return 0; +} + +static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index, + u32 val, u32 reg) +{ + u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index); + + writel(val, pcie_ecam->iatu_base + offset + reg); +} + +static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam, + int index, int type, u64 cpu_addr, + u64 pci_addr, u64 size) +{ + atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr), + PCIE_ATU_LOWER_BASE); + atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr), + PCIE_ATU_UPPER_BASE); + atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr), + PCIE_ATU_LOWER_TARGET); + atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1), + PCIE_ATU_LIMIT); + atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr), + PCIE_ATU_UPPER_TARGET); + atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1); + atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2); +} + +static void __iomem *tegra194_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct tegra194_pcie_ecam *pcie_ecam = cfg->priv; + u32 busdev; + int type; + + if (bus->number < cfg->busr.start || bus->number > cfg->busr.end) + return NULL; + + if (bus->number == cfg->busr.start) { + if (PCI_SLOT(devfn) == 0) + return pcie_ecam->dbi_base + where; + else + return NULL; + } + + busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) | + PCIE_ATU_FUNC(PCI_FUNC(devfn)); + + if (bus->parent->number == cfg->busr.start) { + if (PCI_SLOT(devfn) == 0) + type = PCIE_ATU_TYPE_CFG0; + else + return NULL; + } else { + type = PCIE_ATU_TYPE_CFG1; + } + + program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev, + SZ_256K); + + return pcie_ecam->config_base + where; +} + +const struct pci_ecam_ops tegra194_pcie_ops = { + .init = tegra194_acpi_init, + .pci_ops = { + .map_bus = tegra194_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index bafd2c6ab3c2..504669e3afe0 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -22,8 +22,6 @@ #include <linux/of_irq.h> #include <linux/of_pci.h> #include <linux/pci.h> -#include <linux/pci-acpi.h> -#include <linux/pci-ecam.h> #include <linux/phy/phy.h> #include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> @@ -247,24 +245,6 @@ static const unsigned int pcie_gen_freq[] = { GEN4_CORE_CLK_FREQ }; -static const u32 event_cntr_ctrl_offset[] = { - 0x1d8, - 0x1a8, - 0x1a8, - 0x1a8, - 0x1c4, - 0x1d8 -}; - -static const u32 event_cntr_data_offset[] = { - 0x1dc, - 0x1ac, - 0x1ac, - 0x1ac, - 0x1c8, - 0x1dc -}; - struct tegra_pcie_dw { struct device *dev; struct resource *appl_res; @@ -313,104 +293,6 @@ struct tegra_pcie_dw_of_data { enum dw_pcie_device_mode mode; }; -#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) -struct tegra194_pcie_ecam { - void __iomem *config_base; - void __iomem *iatu_base; - void __iomem *dbi_base; -}; - -static int tegra194_acpi_init(struct pci_config_window *cfg) -{ - struct device *dev = cfg->parent; - struct tegra194_pcie_ecam *pcie_ecam; - - pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL); - if (!pcie_ecam) - return -ENOMEM; - - pcie_ecam->config_base = cfg->win; - pcie_ecam->iatu_base = cfg->win + SZ_256K; - pcie_ecam->dbi_base = cfg->win + SZ_512K; - cfg->priv = pcie_ecam; - - return 0; -} - -static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index, - u32 val, u32 reg) -{ - u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index); - - writel(val, pcie_ecam->iatu_base + offset + reg); -} - -static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam, - int index, int type, u64 cpu_addr, - u64 pci_addr, u64 size) -{ - atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr), - PCIE_ATU_LOWER_BASE); - atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr), - PCIE_ATU_UPPER_BASE); - atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr), - PCIE_ATU_LOWER_TARGET); - atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1), - PCIE_ATU_LIMIT); - atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr), - PCIE_ATU_UPPER_TARGET); - atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1); - atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2); -} - -static void __iomem *tegra194_map_bus(struct pci_bus *bus, - unsigned int devfn, int where) -{ - struct pci_config_window *cfg = bus->sysdata; - struct tegra194_pcie_ecam *pcie_ecam = cfg->priv; - u32 busdev; - int type; - - if (bus->number < cfg->busr.start || bus->number > cfg->busr.end) - return NULL; - - if (bus->number == cfg->busr.start) { - if (PCI_SLOT(devfn) == 0) - return pcie_ecam->dbi_base + where; - else - return NULL; - } - - busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) | - PCIE_ATU_FUNC(PCI_FUNC(devfn)); - - if (bus->parent->number == cfg->busr.start) { - if (PCI_SLOT(devfn) == 0) - type = PCIE_ATU_TYPE_CFG0; - else - return NULL; - } else { - type = PCIE_ATU_TYPE_CFG1; - } - - program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev, - SZ_256K); - - return pcie_ecam->config_base + where; -} - -const struct pci_ecam_ops tegra194_pcie_ops = { - .init = tegra194_acpi_init, - .pci_ops = { - .map_bus = tegra194_map_bus, - .read = pci_generic_config_read, - .write = pci_generic_config_write, - } -}; -#endif /* defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) */ - -#ifdef CONFIG_PCIE_TEGRA194 - static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci) { return container_of(pci, struct tegra_pcie_dw, pci); @@ -694,6 +576,24 @@ static struct pci_ops tegra_pci_ops = { }; #if defined(CONFIG_PCIEASPM) +static const u32 event_cntr_ctrl_offset[] = { + 0x1d8, + 0x1a8, + 0x1a8, + 0x1a8, + 0x1c4, + 0x1d8 +}; + +static const u32 event_cntr_data_offset[] = { + 0x1dc, + 0x1ac, + 0x1ac, + 0x1ac, + 0x1c8, + 0x1dc +}; + static void disable_aspm_l11(struct tegra_pcie_dw *pcie) { u32 val; @@ -2411,5 +2311,3 @@ MODULE_DEVICE_TABLE(of, tegra_pcie_dw_of_match); MODULE_AUTHOR("Vidya Sagar <vidyas@nvidia.com>"); MODULE_DESCRIPTION("NVIDIA PCIe host controller driver"); MODULE_LICENSE("GPL v2"); - -#endif /* CONFIG_PCIE_TEGRA194 */ diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 051b48bd7985..e3f5e7ab7606 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -514,7 +514,7 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie) udelay(PIO_RETRY_DELAY); } - dev_err(dev, "config read/write timed out\n"); + dev_err(dev, "PIO read/write transfer time out\n"); return -ETIMEDOUT; } @@ -657,6 +657,35 @@ static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, return true; } +static bool advk_pcie_pio_is_running(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + + /* + * Trying to start a new PIO transfer when previous has not completed + * cause External Abort on CPU which results in kernel panic: + * + * SError Interrupt on CPU0, code 0xbf000002 -- SError + * Kernel panic - not syncing: Asynchronous SError Interrupt + * + * Functions advk_pcie_rd_conf() and advk_pcie_wr_conf() are protected + * by raw_spin_lock_irqsave() at pci_lock_config() level to prevent + * concurrent calls at the same time. But because PIO transfer may take + * about 1.5s when link is down or card is disconnected, it means that + * advk_pcie_wait_pio() does not always have to wait for completion. + * + * Some versions of ARM Trusted Firmware handles this External Abort at + * EL3 level and mask it to prevent kernel panic. Relevant TF-A commit: + * https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/commit/?id=3c7dcdac5c50 + */ + if (advk_readl(pcie, PIO_START)) { + dev_err(dev, "Previous PIO read/write transfer is still running\n"); + return true; + } + + return false; +} + static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { @@ -673,9 +702,10 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, return pci_bridge_emul_conf_read(&pcie->bridge, where, size, val); - /* Start PIO */ - advk_writel(pcie, 0, PIO_START); - advk_writel(pcie, 1, PIO_ISR); + if (advk_pcie_pio_is_running(pcie)) { + *val = 0xffffffff; + return PCIBIOS_SET_FAILED; + } /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); @@ -694,7 +724,8 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, /* Program the data strobe */ advk_writel(pcie, 0xf, PIO_WR_DATA_STRB); - /* Start the transfer */ + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); advk_writel(pcie, 1, PIO_START); ret = advk_pcie_wait_pio(pcie); @@ -734,9 +765,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, if (where % size) return PCIBIOS_SET_FAILED; - /* Start PIO */ - advk_writel(pcie, 0, PIO_START); - advk_writel(pcie, 1, PIO_ISR); + if (advk_pcie_pio_is_running(pcie)) + return PCIBIOS_SET_FAILED; /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); @@ -763,7 +793,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, /* Program the data strobe */ advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB); - /* Start the transfer */ + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); advk_writel(pcie, 1, PIO_START); ret = advk_pcie_wait_pio(pcie); diff --git a/drivers/pci/of.c b/drivers/pci/of.c index da5b414d585a..a143b02b2dcd 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -103,6 +103,13 @@ struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus) #endif } +bool pci_host_of_has_msi_map(struct device *dev) +{ + if (dev && dev->of_node) + return of_get_property(dev->of_node, "msi-map", NULL); + return false; +} + static inline int __of_pci_pci_compare(struct device_node *node, unsigned int data) { @@ -346,6 +353,8 @@ static int devm_of_pci_get_host_bridge_resources(struct device *dev, dev_warn(dev, "More than one I/O resource converted for %pOF. CPU base address for old range lost!\n", dev_node); *io_base = range.cpu_addr; + } else if (resource_type(res) == IORESOURCE_MEM) { + res->flags &= ~IORESOURCE_MEM_64; } pci_add_resource_offset(resources, res, res->start - range.pci_addr); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 3a62d09b8869..275204646c68 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -925,7 +925,8 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) device_enable_async_suspend(bus->bridge); pci_set_bus_of_node(bus); pci_set_bus_msi_domain(bus); - if (bridge->msi_domain && !dev_get_msi_domain(&bus->dev)) + if (bridge->msi_domain && !dev_get_msi_domain(&bus->dev) && + !pci_host_of_has_msi_map(parent)) bus->bus_flags |= PCI_BUS_FLAGS_NO_MSI; if (!parent) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index dcb229de1acb..22b2bb1109c9 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3547,6 +3547,18 @@ static void quirk_no_bus_reset(struct pci_dev *dev) } /* + * Some NVIDIA GPU devices do not work with bus reset, SBR needs to be + * prevented for those affected devices. + */ +static void quirk_nvidia_no_bus_reset(struct pci_dev *dev) +{ + if ((dev->device & 0xffc0) == 0x2340) + quirk_no_bus_reset(dev); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, + quirk_nvidia_no_bus_reset); + +/* * Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset. * The device will throw a Link Down error on AER-capable systems and * regardless of AER, config space of the device is never accessible again @@ -3566,6 +3578,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0034, quirk_no_bus_reset); */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset); +/* + * Some TI KeyStone C667X devices do not support bus/hot reset. The PCIESS + * automatically disables LTSSM when Secondary Bus Reset is received and + * the device stops working. Prevent bus reset for these devices. With + * this change, the device can be assigned to VMs with VFIO, but it will + * leak state between VMs. Reference + * https://e2e.ti.com/support/processors/f/791/t/954382 + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0xb005, quirk_no_bus_reset); + static void quirk_no_pm_reset(struct pci_dev *dev) { /* @@ -3901,6 +3923,69 @@ static int delay_250ms_after_flr(struct pci_dev *dev, int probe) return 0; } +#define PCI_DEVICE_ID_HINIC_VF 0x375E +#define HINIC_VF_FLR_TYPE 0x1000 +#define HINIC_VF_FLR_CAP_BIT (1UL << 30) +#define HINIC_VF_OP 0xE80 +#define HINIC_VF_FLR_PROC_BIT (1UL << 18) +#define HINIC_OPERATION_TIMEOUT 15000 /* 15 seconds */ + +/* Device-specific reset method for Huawei Intelligent NIC virtual functions */ +static int reset_hinic_vf_dev(struct pci_dev *pdev, int probe) +{ + unsigned long timeout; + void __iomem *bar; + u32 val; + + if (probe) + return 0; + + bar = pci_iomap(pdev, 0, 0); + if (!bar) + return -ENOTTY; + + /* Get and check firmware capabilities */ + val = ioread32be(bar + HINIC_VF_FLR_TYPE); + if (!(val & HINIC_VF_FLR_CAP_BIT)) { + pci_iounmap(pdev, bar); + return -ENOTTY; + } + + /* Set HINIC_VF_FLR_PROC_BIT for the start of FLR */ + val = ioread32be(bar + HINIC_VF_OP); + val = val | HINIC_VF_FLR_PROC_BIT; + iowrite32be(val, bar + HINIC_VF_OP); + + pcie_flr(pdev); + + /* + * The device must recapture its Bus and Device Numbers after FLR + * in order generate Completions. Issue a config write to let the + * device capture this information. + */ + pci_write_config_word(pdev, PCI_VENDOR_ID, 0); + + /* Firmware clears HINIC_VF_FLR_PROC_BIT when reset is complete */ + timeout = jiffies + msecs_to_jiffies(HINIC_OPERATION_TIMEOUT); + do { + val = ioread32be(bar + HINIC_VF_OP); + if (!(val & HINIC_VF_FLR_PROC_BIT)) + goto reset_complete; + msleep(20); + } while (time_before(jiffies, timeout)); + + val = ioread32be(bar + HINIC_VF_OP); + if (!(val & HINIC_VF_FLR_PROC_BIT)) + goto reset_complete; + + pci_warn(pdev, "Reset dev timeout, FLR ack reg: %#010x\n", val); + +reset_complete: + pci_iounmap(pdev, bar); + + return 0; +} + static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF, reset_intel_82599_sfp_virtfn }, @@ -3913,6 +3998,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { PCI_VENDOR_ID_INTEL, 0x0a54, delay_250ms_after_flr }, { PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, reset_chelsio_generic_dev }, + { PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HINIC_VF, + reset_hinic_vf_dev }, { 0 } }; @@ -4753,6 +4840,8 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs }, + /* Broadcom multi-function device */ + { PCI_VENDOR_ID_BROADCOM, 0x16D7, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs }, /* Amazon Annapurna Labs */ { PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs }, @@ -5154,7 +5243,8 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { if ((pdev->device == 0x7312 && pdev->revision != 0x00) || - (pdev->device == 0x7340 && pdev->revision != 0xc5)) + (pdev->device == 0x7340 && pdev->revision != 0xc5) || + (pdev->device == 0x7341 && pdev->revision != 0x00)) return; if (pdev->device == 0x15d8) { @@ -5181,6 +5271,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats); /* AMD Navi14 dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats); /* AMD Raven platform iGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.h b/drivers/phy/broadcom/phy-brcm-usb-init.h index 899b9eb43fad..a39f30fa2e99 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init.h +++ b/drivers/phy/broadcom/phy-brcm-usb-init.h @@ -78,7 +78,7 @@ static inline u32 brcm_usb_readl(void __iomem *addr) * Other architectures (e.g., ARM) either do not support big endian, or * else leave I/O in little endian mode. */ - if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN)) + if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) return __raw_readl(addr); else return readl_relaxed(addr); @@ -87,7 +87,7 @@ static inline u32 brcm_usb_readl(void __iomem *addr) static inline void brcm_usb_writel(u32 val, void __iomem *addr) { /* See brcmnand_readl() comments */ - if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN)) + if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) __raw_writel(val, addr); else writel_relaxed(val, addr); diff --git a/drivers/phy/cadence/phy-cadence-sierra.c b/drivers/phy/cadence/phy-cadence-sierra.c index 5c68e31c5939..e93818e3991f 100644 --- a/drivers/phy/cadence/phy-cadence-sierra.c +++ b/drivers/phy/cadence/phy-cadence-sierra.c @@ -940,6 +940,7 @@ static int cdns_sierra_phy_probe(struct platform_device *pdev) sp->nsubnodes = node; if (sp->num_lanes > SIERRA_MAX_LANES) { + ret = -EINVAL; dev_err(dev, "Invalid lane configuration\n"); goto put_child2; } diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c index cdbcc49f7115..731c483a04de 100644 --- a/drivers/phy/mediatek/phy-mtk-tphy.c +++ b/drivers/phy/mediatek/phy-mtk-tphy.c @@ -949,6 +949,8 @@ static int mtk_phy_init(struct phy *phy) break; default: dev_err(tphy->dev, "incompatible PHY type\n"); + clk_disable_unprepare(instance->ref_clk); + clk_disable_unprepare(instance->da_ref_clk); return -EINVAL; } diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c index c8a7d0927ced..4076580fc2cd 100644 --- a/drivers/phy/microchip/sparx5_serdes.c +++ b/drivers/phy/microchip/sparx5_serdes.c @@ -2470,6 +2470,10 @@ static int sparx5_serdes_probe(struct platform_device *pdev) priv->coreclock = clock; iores = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!iores) { + dev_err(priv->dev, "Invalid resource\n"); + return -EINVAL; + } iomem = devm_ioremap(priv->dev, iores->start, resource_size(iores)); if (IS_ERR(iomem)) { dev_err(priv->dev, "Unable to get serdes registers: %s\n", diff --git a/drivers/phy/ralink/phy-mt7621-pci.c b/drivers/phy/ralink/phy-mt7621-pci.c index 753cb5bab930..2a9465f4bb3a 100644 --- a/drivers/phy/ralink/phy-mt7621-pci.c +++ b/drivers/phy/ralink/phy-mt7621-pci.c @@ -341,7 +341,7 @@ static struct platform_driver mt7621_pci_phy_driver = { .probe = mt7621_pci_phy_probe, .driver = { .name = "mt7621-pci-phy", - .of_match_table = of_match_ptr(mt7621_pci_phy_ids), + .of_match_table = mt7621_pci_phy_ids, }, }; diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index 9eb6d37c907e..126f5b8735cc 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -1212,6 +1212,7 @@ static int wiz_probe(struct platform_device *pdev) if (wiz->typec_dir_delay < WIZ_TYPEC_DIR_DEBOUNCE_MIN || wiz->typec_dir_delay > WIZ_TYPEC_DIR_DEBOUNCE_MAX) { + ret = -EINVAL; dev_err(dev, "Invalid typec-dir-debounce property\n"); goto err_addr_to_resource; } diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c index 996ebcba4d38..4c0d26606b6c 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c @@ -2702,8 +2702,8 @@ static int aspeed_g5_sig_expr_eval(struct aspeed_pinmux_data *ctx, } /** - * Configure a pin's signal by applying an expression's descriptor state for - * all descriptors in the expression. + * aspeed_g5_sig_expr_set() - Configure a pin's signal by applying an + * expression's descriptor state for all descriptors in the expression. * * @ctx: The pinmux context * @expr: The expression associated with the function whose signal is to be diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index 5c1a109842a7..eeab093a7815 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -2611,8 +2611,8 @@ static struct aspeed_pin_config aspeed_g6_configs[] = { }; /** - * Configure a pin's signal by applying an expression's descriptor state for - * all descriptors in the expression. + * aspeed_g6_sig_expr_set() - Configure a pin's signal by applying an + * expression's descriptor state for all descriptors in the expression. * * @ctx: The pinmux context * @expr: The expression associated with the function whose signal is to be diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index 9c65d560d48f..9bbfe5c14b36 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -108,7 +108,8 @@ static int aspeed_sig_expr_disable(struct aspeed_pinmux_data *ctx, } /** - * Disable a signal on a pin by disabling all provided signal expressions. + * aspeed_disable_sig() - Disable a signal on a pin by disabling all provided + * signal expressions. * * @ctx: The pinmux context * @exprs: The list of signal expressions (from a priority level on a pin) diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.c b/drivers/pinctrl/aspeed/pinmux-aspeed.c index 57305ca838a7..894e2efd3be7 100644 --- a/drivers/pinctrl/aspeed/pinmux-aspeed.c +++ b/drivers/pinctrl/aspeed/pinmux-aspeed.c @@ -21,7 +21,8 @@ static inline void aspeed_sig_desc_print_val( } /** - * Query the enabled or disabled state of a signal descriptor + * aspeed_sig_desc_eval() - Query the enabled or disabled state of a signal + * descriptor. * * @desc: The signal descriptor of interest * @enabled: True to query the enabled state, false to query disabled state diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index 25d2f7f7f3b6..11e967dbb44b 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -223,7 +223,7 @@ config PINCTRL_SC7280 config PINCTRL_SC8180X tristate "Qualcomm Technologies Inc SC8180x pin controller driver" depends on GPIOLIB && (OF || ACPI) - select PINCTRL_MSM + depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the Qualcomm Technologies Inc TLMM block found on the Qualcomm diff --git a/drivers/pinctrl/qcom/pinctrl-sdx55.c b/drivers/pinctrl/qcom/pinctrl-sdx55.c index 5aaf57b40407..0bb4931cec59 100644 --- a/drivers/pinctrl/qcom/pinctrl-sdx55.c +++ b/drivers/pinctrl/qcom/pinctrl-sdx55.c @@ -410,15 +410,15 @@ static const char * const gpio_groups[] = { "gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35", "gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42", "gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49", - "gpio50", "gpio51", "gpio52", "gpio52", "gpio53", "gpio53", "gpio54", - "gpio55", "gpio56", "gpio57", "gpio58", "gpio59", "gpio60", "gpio61", - "gpio62", "gpio63", "gpio64", "gpio65", "gpio66", "gpio67", "gpio68", - "gpio69", "gpio70", "gpio71", "gpio72", "gpio73", "gpio74", "gpio75", - "gpio76", "gpio77", "gpio78", "gpio79", "gpio80", "gpio81", "gpio82", - "gpio83", "gpio84", "gpio85", "gpio86", "gpio87", "gpio88", "gpio89", - "gpio90", "gpio91", "gpio92", "gpio93", "gpio94", "gpio95", "gpio96", - "gpio97", "gpio98", "gpio99", "gpio100", "gpio101", "gpio102", - "gpio103", "gpio104", "gpio105", "gpio106", "gpio107", + "gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56", + "gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63", + "gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70", + "gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77", + "gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84", + "gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91", + "gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98", + "gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104", + "gpio105", "gpio106", "gpio107", }; static const char * const qdss_stm_groups[] = { diff --git a/drivers/pinctrl/ralink/pinctrl-rt2880.c b/drivers/pinctrl/ralink/pinctrl-rt2880.c index 1f4bca854add..a9b511c7e850 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt2880.c +++ b/drivers/pinctrl/ralink/pinctrl-rt2880.c @@ -127,7 +127,7 @@ static int rt2880_pmx_group_enable(struct pinctrl_dev *pctrldev, if (p->groups[group].enabled) { dev_err(p->dev, "%s is already enabled\n", p->groups[group].name); - return -EBUSY; + return 0; } p->groups[group].enabled = 1; diff --git a/drivers/platform/mellanox/mlxreg-hotplug.c b/drivers/platform/mellanox/mlxreg-hotplug.c index a9db2f32658f..b013445147dd 100644 --- a/drivers/platform/mellanox/mlxreg-hotplug.c +++ b/drivers/platform/mellanox/mlxreg-hotplug.c @@ -683,13 +683,13 @@ static int mlxreg_hotplug_probe(struct platform_device *pdev) err = devm_request_irq(&pdev->dev, priv->irq, mlxreg_hotplug_irq_handler, IRQF_TRIGGER_FALLING - | IRQF_SHARED | IRQF_NO_AUTOEN, - "mlxreg-hotplug", priv); + | IRQF_SHARED, "mlxreg-hotplug", priv); if (err) { dev_err(&pdev->dev, "Failed to request irq: %d\n", err); return err; } + disable_irq(priv->irq); spin_lock_init(&priv->lock); INIT_DELAYED_WORK(&priv->dwork_irq, mlxreg_hotplug_work_handler); dev_set_drvdata(&pdev->dev, priv); diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c index 8a70df60142c..a06964aa96e7 100644 --- a/drivers/platform/surface/aggregator/controller.c +++ b/drivers/platform/surface/aggregator/controller.c @@ -1907,7 +1907,7 @@ static int ssam_ssh_event_disable(struct ssam_controller *ctrl, { int status; - status = __ssam_ssh_event_request(ctrl, reg, reg.cid_enable, id, flags); + status = __ssam_ssh_event_request(ctrl, reg, reg.cid_disable, id, flags); if (status < 0 && status != -EINVAL) { ssam_err(ctrl, diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index 685d37a7add1..ef83461fa536 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -156,7 +156,7 @@ static const struct software_node *ssam_node_group_sl2[] = { NULL, }; -/* Devices for Surface Laptop 3. */ +/* Devices for Surface Laptop 3 and 4. */ static const struct software_node *ssam_node_group_sl3[] = { &ssam_node_root, &ssam_node_bat_ac, @@ -521,9 +521,12 @@ static const struct acpi_device_id ssam_platform_hub_match[] = { /* Surface Laptop 3 (13", Intel) */ { "MSHW0114", (unsigned long)ssam_node_group_sl3 }, - /* Surface Laptop 3 (15", AMD) */ + /* Surface Laptop 3 (15", AMD) and 4 (15", AMD) */ { "MSHW0110", (unsigned long)ssam_node_group_sl3 }, + /* Surface Laptop 4 (13", Intel) */ + { "MSHW0250", (unsigned long)ssam_node_group_sl3 }, + /* Surface Laptop Go 1 */ { "MSHW0118", (unsigned long)ssam_node_group_slg1 }, diff --git a/drivers/platform/surface/surface_dtx.c b/drivers/platform/surface/surface_dtx.c index 5d9b758a99bb..1203b9a82993 100644 --- a/drivers/platform/surface/surface_dtx.c +++ b/drivers/platform/surface/surface_dtx.c @@ -427,6 +427,7 @@ static int surface_dtx_open(struct inode *inode, struct file *file) */ if (test_bit(SDTX_DEVICE_SHUTDOWN_BIT, &ddev->flags)) { up_write(&ddev->client_lock); + mutex_destroy(&client->read_lock); sdtx_device_put(client->ddev); kfree(client); return -ENODEV; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index dd60c9397d35..edd71e744d27 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8853,6 +8853,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ + TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */ }; static int __init fan_init(struct ibm_init_struct *iibm) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 03a246e60fd9..21c4c34c52d8 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -63,7 +63,7 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, spin_unlock_irqrestore(&queue->lock, flags); } -s32 scaled_ppm_to_ppb(long ppm) +long scaled_ppm_to_ppb(long ppm) { /* * The 'freq' field in the 'struct timex' is in parts per @@ -80,7 +80,7 @@ s32 scaled_ppm_to_ppb(long ppm) s64 ppb = 1 + ppm; ppb *= 125; ppb >>= 13; - return (s32) ppb; + return (long) ppb; } EXPORT_SYMBOL(scaled_ppm_to_ppb); @@ -138,7 +138,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) delta = ktime_to_ns(kt); err = ops->adjtime(ops, delta); } else if (tx->modes & ADJ_FREQUENCY) { - s32 ppb = scaled_ppm_to_ppb(tx->freq); + long ppb = scaled_ppm_to_ppb(tx->freq); if (ppb > ops->max_adj || ppb < -ops->max_adj) return -ERANGE; if (ops->adjfine) diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 530e5f90095e..0d1034e3ed0f 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -324,7 +324,7 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!bp->base) { dev_err(&pdev->dev, "io_remap bar0\n"); err = -ENOMEM; - goto out; + goto out_release_regions; } bp->reg = bp->base + OCP_REGISTER_OFFSET; bp->tod = bp->base + TOD_REGISTER_OFFSET; @@ -347,6 +347,8 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; out: + pci_iounmap(pdev, bp->base); +out_release_regions: pci_release_regions(pdev); out_disable: pci_disable_device(pdev); diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 9d84d9245490..3e7a38525cb3 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -1031,7 +1031,7 @@ config REGULATOR_RT5033 current source, LDO and Buck. config REGULATOR_RTMV20 - tristate "RTMV20 Laser Diode Regulator" + tristate "Richtek RTMV20 Laser Diode Regulator" depends on I2C select REGMAP_I2C help diff --git a/drivers/regulator/atc260x-regulator.c b/drivers/regulator/atc260x-regulator.c index d8b429955d33..05147d2c3842 100644 --- a/drivers/regulator/atc260x-regulator.c +++ b/drivers/regulator/atc260x-regulator.c @@ -28,16 +28,16 @@ static const struct linear_range atc2609a_dcdc_voltage_ranges[] = { static const struct linear_range atc2609a_ldo_voltage_ranges0[] = { REGULATOR_LINEAR_RANGE(700000, 0, 15, 100000), - REGULATOR_LINEAR_RANGE(2100000, 16, 28, 100000), + REGULATOR_LINEAR_RANGE(2100000, 0, 12, 100000), }; static const struct linear_range atc2609a_ldo_voltage_ranges1[] = { REGULATOR_LINEAR_RANGE(850000, 0, 15, 100000), - REGULATOR_LINEAR_RANGE(2100000, 16, 27, 100000), + REGULATOR_LINEAR_RANGE(2100000, 0, 11, 100000), }; static const unsigned int atc260x_ldo_voltage_range_sel[] = { - 0x0, 0x1, + 0x0, 0x20, }; static int atc260x_dcdc_set_voltage_time_sel(struct regulator_dev *rdev, @@ -411,7 +411,7 @@ enum atc2609a_reg_ids { .owner = THIS_MODULE, \ } -#define atc2609a_reg_desc_ldo_range_pick(num, n_range) { \ +#define atc2609a_reg_desc_ldo_range_pick(num, n_range, n_volt) { \ .name = "LDO"#num, \ .supply_name = "ldo"#num, \ .of_match = of_match_ptr("ldo"#num), \ @@ -421,6 +421,7 @@ enum atc2609a_reg_ids { .type = REGULATOR_VOLTAGE, \ .linear_ranges = atc2609a_ldo_voltage_ranges##n_range, \ .n_linear_ranges = ARRAY_SIZE(atc2609a_ldo_voltage_ranges##n_range), \ + .n_voltages = n_volt, \ .vsel_reg = ATC2609A_PMU_LDO##num##_CTL0, \ .vsel_mask = GENMASK(4, 1), \ .vsel_range_reg = ATC2609A_PMU_LDO##num##_CTL0, \ @@ -458,12 +459,12 @@ static const struct regulator_desc atc2609a_reg[] = { atc2609a_reg_desc_ldo_bypass(0), atc2609a_reg_desc_ldo_bypass(1), atc2609a_reg_desc_ldo_bypass(2), - atc2609a_reg_desc_ldo_range_pick(3, 0), - atc2609a_reg_desc_ldo_range_pick(4, 0), + atc2609a_reg_desc_ldo_range_pick(3, 0, 29), + atc2609a_reg_desc_ldo_range_pick(4, 0, 29), atc2609a_reg_desc_ldo(5), - atc2609a_reg_desc_ldo_range_pick(6, 1), - atc2609a_reg_desc_ldo_range_pick(7, 0), - atc2609a_reg_desc_ldo_range_pick(8, 0), + atc2609a_reg_desc_ldo_range_pick(6, 1, 28), + atc2609a_reg_desc_ldo_range_pick(7, 0, 29), + atc2609a_reg_desc_ldo_range_pick(8, 0, 29), atc2609a_reg_desc_ldo_fixed(9), }; diff --git a/drivers/regulator/bd718x7-regulator.c b/drivers/regulator/bd718x7-regulator.c index e61295b30503..b1eb46961993 100644 --- a/drivers/regulator/bd718x7-regulator.c +++ b/drivers/regulator/bd718x7-regulator.c @@ -334,7 +334,7 @@ BD718XX_OPS(bd71837_buck_regulator_ops, regulator_list_voltage_linear_range, NULL); BD718XX_OPS(bd71837_buck_regulator_nolinear_ops, regulator_list_voltage_table, - regulator_map_voltage_ascend, bd718xx_set_voltage_sel_restricted, + regulator_map_voltage_ascend, bd71837_set_voltage_sel_restricted, regulator_get_voltage_sel_regmap, regulator_set_voltage_time_sel, NULL); /* diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index f192bf19492e..e20e77e4c159 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1425,6 +1425,12 @@ static int set_machine_constraints(struct regulator_dev *rdev) * and we have control then make sure it is enabled. */ if (rdev->constraints->always_on || rdev->constraints->boot_on) { + /* If we want to enable this regulator, make sure that we know + * the supplying regulator. + */ + if (rdev->supply_name && !rdev->supply) + return -EPROBE_DEFER; + if (rdev->supply) { ret = regulator_enable(rdev->supply); if (ret < 0) { diff --git a/drivers/regulator/cros-ec-regulator.c b/drivers/regulator/cros-ec-regulator.c index eb3fc1db4edc..c4754f3cf233 100644 --- a/drivers/regulator/cros-ec-regulator.c +++ b/drivers/regulator/cros-ec-regulator.c @@ -225,8 +225,9 @@ static int cros_ec_regulator_probe(struct platform_device *pdev) drvdata->dev = devm_regulator_register(dev, &drvdata->desc, &cfg); if (IS_ERR(drvdata->dev)) { + ret = PTR_ERR(drvdata->dev); dev_err(&pdev->dev, "Failed to register regulator: %d\n", ret); - return PTR_ERR(drvdata->dev); + return ret; } platform_set_drvdata(pdev, drvdata); diff --git a/drivers/regulator/da9121-regulator.c b/drivers/regulator/da9121-regulator.c index 08cbf688e14d..e66925090258 100644 --- a/drivers/regulator/da9121-regulator.c +++ b/drivers/regulator/da9121-regulator.c @@ -280,7 +280,7 @@ static unsigned int da9121_map_mode(unsigned int mode) case DA9121_BUCK_MODE_FORCE_PFM: return REGULATOR_MODE_STANDBY; default: - return -EINVAL; + return REGULATOR_MODE_INVALID; } } @@ -317,7 +317,7 @@ static unsigned int da9121_buck_get_mode(struct regulator_dev *rdev) { struct da9121 *chip = rdev_get_drvdata(rdev); int id = rdev_get_id(rdev); - unsigned int val; + unsigned int val, mode; int ret = 0; ret = regmap_read(chip->regmap, da9121_mode_field[id].reg, &val); @@ -326,7 +326,11 @@ static unsigned int da9121_buck_get_mode(struct regulator_dev *rdev) return -EINVAL; } - return da9121_map_mode(val & da9121_mode_field[id].msk); + mode = da9121_map_mode(val & da9121_mode_field[id].msk); + if (mode == REGULATOR_MODE_INVALID) + return -EINVAL; + + return mode; } static const struct regulator_ops da9121_buck_ops = { diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c index f3918f03aaf3..26f06f685b1b 100644 --- a/drivers/regulator/fan53555.c +++ b/drivers/regulator/fan53555.c @@ -55,7 +55,6 @@ #define FAN53555_NVOLTAGES 64 /* Numbers of voltages */ #define FAN53526_NVOLTAGES 128 -#define TCS4525_NVOLTAGES 127 /* Numbers of voltages */ #define TCS_VSEL_NSEL_MASK 0x7f #define TCS_VSEL0_MODE (1 << 7) @@ -376,7 +375,7 @@ static int fan53555_voltages_setup_tcs(struct fan53555_device_info *di) /* Init voltage range and step */ di->vsel_min = 600000; di->vsel_step = 6250; - di->vsel_count = TCS4525_NVOLTAGES; + di->vsel_count = FAN53526_NVOLTAGES; return 0; } diff --git a/drivers/regulator/fan53880.c b/drivers/regulator/fan53880.c index e83eb4fb1876..1684faf82ed2 100644 --- a/drivers/regulator/fan53880.c +++ b/drivers/regulator/fan53880.c @@ -51,6 +51,7 @@ static const struct regulator_ops fan53880_ops = { REGULATOR_LINEAR_RANGE(800000, 0xf, 0x73, 25000), \ }, \ .n_linear_ranges = 2, \ + .n_voltages = 0x74, \ .vsel_reg = FAN53880_LDO ## _num ## VOUT, \ .vsel_mask = 0x7f, \ .enable_reg = FAN53880_ENABLE, \ @@ -76,6 +77,7 @@ static const struct regulator_desc fan53880_regulators[] = { REGULATOR_LINEAR_RANGE(600000, 0x1f, 0xf7, 12500), }, .n_linear_ranges = 2, + .n_voltages = 0xf8, .vsel_reg = FAN53880_BUCKVOUT, .vsel_mask = 0x7f, .enable_reg = FAN53880_ENABLE, @@ -95,6 +97,7 @@ static const struct regulator_desc fan53880_regulators[] = { REGULATOR_LINEAR_RANGE(3000000, 0x4, 0x70, 25000), }, .n_linear_ranges = 2, + .n_voltages = 0x71, .vsel_reg = FAN53880_BOOSTVOUT, .vsel_mask = 0x7f, .enable_reg = FAN53880_ENABLE_BOOST, diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index 02ad83153e19..34e255c235d4 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -88,10 +88,15 @@ static int reg_domain_disable(struct regulator_dev *rdev) { struct fixed_voltage_data *priv = rdev_get_drvdata(rdev); struct device *dev = rdev->dev.parent; + int ret; + + ret = dev_pm_genpd_set_performance_state(dev, 0); + if (ret) + return ret; priv->enable_counter--; - return dev_pm_genpd_set_performance_state(dev, 0); + return 0; } static int reg_is_enabled(struct regulator_dev *rdev) diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c index 0e16e31c968f..ad2237a95572 100644 --- a/drivers/regulator/helpers.c +++ b/drivers/regulator/helpers.c @@ -948,7 +948,7 @@ int regulator_set_ramp_delay_regmap(struct regulator_dev *rdev, int ramp_delay) int ret; unsigned int sel; - if (!rdev->desc->n_ramp_values) + if (WARN_ON(!rdev->desc->n_ramp_values || !rdev->desc->ramp_delay_table)) return -EINVAL; ret = find_closest_bigger(ramp_delay, rdev->desc->ramp_delay_table, diff --git a/drivers/regulator/hi6421v600-regulator.c b/drivers/regulator/hi6421v600-regulator.c index f6a14e9c3cbf..d6340bb49296 100644 --- a/drivers/regulator/hi6421v600-regulator.c +++ b/drivers/regulator/hi6421v600-regulator.c @@ -3,7 +3,7 @@ // Device driver for regulators in Hisi IC // // Copyright (c) 2013 Linaro Ltd. -// Copyright (c) 2011 Hisilicon. +// Copyright (c) 2011 HiSilicon Ltd. // Copyright (c) 2020-2021 Huawei Technologies Co., Ltd // // Guodong Xu <guodong.xu@linaro.org> @@ -83,7 +83,7 @@ static const unsigned int ldo34_voltages[] = { .owner = THIS_MODULE, \ .volt_table = vtable, \ .n_voltages = ARRAY_SIZE(vtable), \ - .vsel_mask = (1 << (ARRAY_SIZE(vtable) - 1)) - 1, \ + .vsel_mask = ARRAY_SIZE(vtable) - 1, \ .vsel_reg = vreg, \ .enable_reg = ereg, \ .enable_mask = emask, \ diff --git a/drivers/regulator/hi655x-regulator.c b/drivers/regulator/hi655x-regulator.c index ac2ee2030211..68cdb173196d 100644 --- a/drivers/regulator/hi655x-regulator.c +++ b/drivers/regulator/hi655x-regulator.c @@ -2,7 +2,7 @@ // // Device driver for regulators in Hi655x IC // -// Copyright (c) 2016 Hisilicon. +// Copyright (c) 2016 HiSilicon Ltd. // // Authors: // Chen Feng <puck.chen@hisilicon.com> diff --git a/drivers/regulator/max77620-regulator.c b/drivers/regulator/max77620-regulator.c index 8d9731e4052b..3cf8f085170a 100644 --- a/drivers/regulator/max77620-regulator.c +++ b/drivers/regulator/max77620-regulator.c @@ -814,6 +814,13 @@ static int max77620_regulator_probe(struct platform_device *pdev) config.dev = dev; config.driver_data = pmic; + /* + * Set of_node_reuse flag to prevent driver core from attempting to + * claim any pinmux resources already claimed by the parent device. + * Otherwise PMIC driver will fail to re-probe. + */ + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); + for (id = 0; id < MAX77620_NUM_REGS; id++) { struct regulator_dev *rdev; struct regulator_desc *rdesc; @@ -839,12 +846,10 @@ static int max77620_regulator_probe(struct platform_device *pdev) return ret; rdev = devm_regulator_register(dev, rdesc, &config); - if (IS_ERR(rdev)) { - ret = PTR_ERR(rdev); - dev_err(dev, "Regulator registration %s failed: %d\n", - rdesc->name, ret); - return ret; - } + if (IS_ERR(rdev)) + return dev_err_probe(dev, PTR_ERR(rdev), + "Regulator registration %s failed\n", + rdesc->name); } return 0; diff --git a/drivers/regulator/mt6315-regulator.c b/drivers/regulator/mt6315-regulator.c index 9edc34981ee0..6b8be52c3772 100644 --- a/drivers/regulator/mt6315-regulator.c +++ b/drivers/regulator/mt6315-regulator.c @@ -59,7 +59,7 @@ static const struct linear_range mt_volt_range1[] = { REGULATOR_LINEAR_RANGE(0, 0, 0xbf, 6250), }; -static unsigned int mt6315_map_mode(u32 mode) +static unsigned int mt6315_map_mode(unsigned int mode) { switch (mode) { case MT6315_BUCK_MODE_AUTO: diff --git a/drivers/regulator/rt4801-regulator.c b/drivers/regulator/rt4801-regulator.c index 2055a9cb13ba..7a87788d3f09 100644 --- a/drivers/regulator/rt4801-regulator.c +++ b/drivers/regulator/rt4801-regulator.c @@ -66,7 +66,7 @@ static int rt4801_enable(struct regulator_dev *rdev) struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev), ret; - if (gpios->ndescs <= id) { + if (!gpios || gpios->ndescs <= id) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; } @@ -88,7 +88,7 @@ static int rt4801_disable(struct regulator_dev *rdev) struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev); - if (gpios->ndescs <= id) { + if (!gpios || gpios->ndescs <= id) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; } diff --git a/drivers/regulator/rtmv20-regulator.c b/drivers/regulator/rtmv20-regulator.c index 852fb2596ffd..4bca64de0f67 100644 --- a/drivers/regulator/rtmv20-regulator.c +++ b/drivers/regulator/rtmv20-regulator.c @@ -27,6 +27,7 @@ #define RTMV20_REG_LDIRQ 0x30 #define RTMV20_REG_LDSTAT 0x40 #define RTMV20_REG_LDMASK 0x50 +#define RTMV20_MAX_REGS (RTMV20_REG_LDMASK + 1) #define RTMV20_VID_MASK GENMASK(7, 4) #define RICHTEK_VID 0x80 @@ -103,9 +104,47 @@ static int rtmv20_lsw_disable(struct regulator_dev *rdev) return 0; } +static int rtmv20_lsw_set_current_limit(struct regulator_dev *rdev, int min_uA, + int max_uA) +{ + int sel; + + if (min_uA > RTMV20_LSW_MAXUA || max_uA < RTMV20_LSW_MINUA) + return -EINVAL; + + if (max_uA > RTMV20_LSW_MAXUA) + max_uA = RTMV20_LSW_MAXUA; + + sel = (max_uA - RTMV20_LSW_MINUA) / RTMV20_LSW_STEPUA; + + /* Ensure the selected setting is still in range */ + if ((sel * RTMV20_LSW_STEPUA + RTMV20_LSW_MINUA) < min_uA) + return -EINVAL; + + sel <<= ffs(rdev->desc->csel_mask) - 1; + + return regmap_update_bits(rdev->regmap, rdev->desc->csel_reg, + rdev->desc->csel_mask, sel); +} + +static int rtmv20_lsw_get_current_limit(struct regulator_dev *rdev) +{ + unsigned int val; + int ret; + + ret = regmap_read(rdev->regmap, rdev->desc->csel_reg, &val); + if (ret) + return ret; + + val &= rdev->desc->csel_mask; + val >>= ffs(rdev->desc->csel_mask) - 1; + + return val * RTMV20_LSW_STEPUA + RTMV20_LSW_MINUA; +} + static const struct regulator_ops rtmv20_regulator_ops = { - .set_current_limit = regulator_set_current_limit_regmap, - .get_current_limit = regulator_get_current_limit_regmap, + .set_current_limit = rtmv20_lsw_set_current_limit, + .get_current_limit = rtmv20_lsw_get_current_limit, .enable = rtmv20_lsw_enable, .disable = rtmv20_lsw_disable, .is_enabled = regulator_is_enabled_regmap, @@ -275,6 +314,7 @@ static const struct regmap_config rtmv20_regmap_config = { .val_bits = 8, .cache_type = REGCACHE_RBTREE, .max_register = RTMV20_REG_LDMASK, + .num_reg_defaults_raw = RTMV20_MAX_REGS, .writeable_reg = rtmv20_is_accessible_reg, .readable_reg = rtmv20_is_accessible_reg, diff --git a/drivers/regulator/scmi-regulator.c b/drivers/regulator/scmi-regulator.c index bbadf72b94e8..1f02f60ad136 100644 --- a/drivers/regulator/scmi-regulator.c +++ b/drivers/regulator/scmi-regulator.c @@ -173,7 +173,7 @@ scmi_config_linear_regulator_mappings(struct scmi_regulator *sreg, sreg->desc.uV_step = vinfo->levels_uv[SCMI_VOLTAGE_SEGMENT_STEP]; sreg->desc.linear_min_sel = 0; - sreg->desc.n_voltages = delta_uV / sreg->desc.uV_step; + sreg->desc.n_voltages = (delta_uV / sreg->desc.uV_step) + 1; sreg->desc.ops = &scmi_reg_linear_ops; } diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index 1b9e1442e6a5..fd42a5fffaed 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -642,12 +642,18 @@ static void dasd_diag_setup_blk_queue(struct dasd_block *block) blk_queue_segment_boundary(q, PAGE_SIZE - 1); } +static int dasd_diag_pe_handler(struct dasd_device *device, + __u8 tbvpm, __u8 fcsecpm) +{ + return dasd_generic_verify_path(device, tbvpm); +} + static struct dasd_discipline dasd_diag_discipline = { .owner = THIS_MODULE, .name = "DIAG", .ebcname = "DIAG", .check_device = dasd_diag_check_device, - .verify_path = dasd_generic_verify_path, + .pe_handler = dasd_diag_pe_handler, .fill_geometry = dasd_diag_fill_geometry, .setup_blk_queue = dasd_diag_setup_blk_queue, .start_IO = dasd_start_diag, diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index 4789410885e4..3ad319aee51e 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -794,13 +794,19 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block) blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } +static int dasd_fba_pe_handler(struct dasd_device *device, + __u8 tbvpm, __u8 fcsecpm) +{ + return dasd_generic_verify_path(device, tbvpm); +} + static struct dasd_discipline dasd_fba_discipline = { .owner = THIS_MODULE, .name = "FBA ", .ebcname = "FBA ", .check_device = dasd_fba_check_characteristics, .do_analysis = dasd_fba_do_analysis, - .verify_path = dasd_generic_verify_path, + .pe_handler = dasd_fba_pe_handler, .setup_blk_queue = dasd_fba_setup_blk_queue, .fill_geometry = dasd_fba_fill_geometry, .start_IO = dasd_start_IO, diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 1c59b0e86a9f..155428bfed8a 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -297,7 +297,6 @@ struct dasd_discipline { * e.g. verify that new path is compatible with the current * configuration. */ - int (*verify_path)(struct dasd_device *, __u8); int (*pe_handler)(struct dasd_device *, __u8, __u8); /* diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index b9febc581b1f..8d1b2771c1aa 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -638,6 +638,10 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 1); int ret; + /* this is an error in the caller */ + if (cp->initialized) + return -EBUSY; + /* * We only support prefetching the channel program. We assume all channel * programs executed by supported guests likewise support prefetching. diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 8c625b530035..9b61e9b131ad 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -86,6 +86,7 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) struct vfio_ccw_private *private; struct irb *irb; bool is_final; + bool cp_is_finished = false; private = container_of(work, struct vfio_ccw_private, io_work); irb = &private->irb; @@ -94,14 +95,21 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT)); if (scsw_is_solicited(&irb->scsw)) { cp_update_scsw(&private->cp, &irb->scsw); - if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) + if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) { cp_free(&private->cp); + cp_is_finished = true; + } } mutex_lock(&private->io_mutex); memcpy(private->io_region->irb_area, irb, sizeof(*irb)); mutex_unlock(&private->io_mutex); - if (private->mdev && is_final) + /* + * Reset to IDLE only if processing of a channel program + * has finished. Do not overwrite a possible processing + * state if the final interrupt was for HSCH or CSCH. + */ + if (private->mdev && cp_is_finished) private->state = VFIO_CCW_STATE_IDLE; if (private->io_trigger) diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index 23e61aa638e4..e435a9cd92da 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -318,6 +318,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, } err_out: + private->state = VFIO_CCW_STATE_IDLE; trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid, io_region->ret_code, errstr); } diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index 491a64c61fff..c57d2a7f0919 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -279,8 +279,6 @@ static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private, } vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ); - if (region->ret_code != 0) - private->state = VFIO_CCW_STATE_IDLE; ret = (region->ret_code != 0) ? region->ret_code : count; out_unlock: diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index ecefc25eff0c..337353c9655e 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -135,12 +135,13 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) { struct ap_queue_status status; struct ap_message *ap_msg; + bool found = false; status = ap_dqap(aq->qid, &aq->reply->psmid, aq->reply->msg, aq->reply->len); switch (status.response_code) { case AP_RESPONSE_NORMAL: - aq->queue_count--; + aq->queue_count = max_t(int, 0, aq->queue_count - 1); if (aq->queue_count > 0) mod_timer(&aq->timeout, jiffies + aq->request_timeout); @@ -150,8 +151,14 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) list_del_init(&ap_msg->list); aq->pendingq_count--; ap_msg->receive(aq, ap_msg, aq->reply); + found = true; break; } + if (!found) { + AP_DBF_WARN("%s unassociated reply psmid=0x%016llx on 0x%02x.%04x\n", + __func__, aq->reply->psmid, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + } fallthrough; case AP_RESPONSE_NO_PENDING_REPLY: if (!status.queue_empty || aq->queue_count <= 0) @@ -232,7 +239,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) ap_msg->flags & AP_MSG_FLAG_SPECIAL); switch (status.response_code) { case AP_RESPONSE_NORMAL: - aq->queue_count++; + aq->queue_count = max_t(int, 1, aq->queue_count + 1); if (aq->queue_count == 1) mod_timer(&aq->timeout, jiffies + aq->request_timeout); list_move_tail(&ap_msg->list, &aq->pendingq); diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y index 924d55a8acbf..65182ad9cdf8 100644 --- a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y +++ b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y @@ -58,7 +58,6 @@ #include "aicasm_symbol.h" #include "aicasm_insformat.h" -int yylineno; char *yyfilename; char stock_prefix[] = "aic_"; char *prefix = stock_prefix; diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h b/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h index 7bf7fd5953ac..ed3bdd43c297 100644 --- a/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h +++ b/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h @@ -108,7 +108,7 @@ struct macro_arg { regex_t arg_regex; char *replacement_text; }; -STAILQ_HEAD(macro_arg_list, macro_arg) args; +STAILQ_HEAD(macro_arg_list, macro_arg); struct macro_info { struct macro_arg_list args; diff --git a/drivers/scsi/aic7xxx/scsi_message.h b/drivers/scsi/aic7xxx/scsi_message.h index a7515c3039ed..53343a6d8ae1 100644 --- a/drivers/scsi/aic7xxx/scsi_message.h +++ b/drivers/scsi/aic7xxx/scsi_message.h @@ -3,6 +3,17 @@ * $FreeBSD: src/sys/cam/scsi/scsi_message.h,v 1.2 2000/05/01 20:21:29 peter Exp $ */ +/* Messages (1 byte) */ /* I/T (M)andatory or (O)ptional */ +#define MSG_SAVEDATAPOINTER 0x02 /* O/O */ +#define MSG_RESTOREPOINTERS 0x03 /* O/O */ +#define MSG_DISCONNECT 0x04 /* O/O */ +#define MSG_MESSAGE_REJECT 0x07 /* M/M */ +#define MSG_NOOP 0x08 /* M/M */ + +/* Messages (2 byte) */ +#define MSG_SIMPLE_Q_TAG 0x20 /* O/O */ +#define MSG_IGN_WIDE_RESIDUE 0x23 /* O/O */ + /* Identify message */ /* M/M */ #define MSG_IDENTIFYFLAG 0x80 #define MSG_IDENTIFY_DISCFLAG 0x40 diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index 1a0dc18d6915..ed300a279a38 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -1220,6 +1220,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd) was a result from the ABTS request rather than the CLEANUP request */ set_bit(BNX2FC_FLAG_IO_CLEANUP, &io_req->req_flags); + rc = FAILED; goto done; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 499c770d405c..e95408314078 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -4811,14 +4811,14 @@ hisi_sas_v3_destroy_irqs(struct pci_dev *pdev, struct hisi_hba *hisi_hba) { int i; - free_irq(pci_irq_vector(pdev, 1), hisi_hba); - free_irq(pci_irq_vector(pdev, 2), hisi_hba); - free_irq(pci_irq_vector(pdev, 11), hisi_hba); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 1), hisi_hba); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 2), hisi_hba); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 11), hisi_hba); for (i = 0; i < hisi_hba->cq_nvecs; i++) { struct hisi_sas_cq *cq = &hisi_hba->cq[i]; int nr = hisi_sas_intr_conv ? 16 : 16 + i; - free_irq(pci_irq_vector(pdev, nr), cq); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, nr), cq); } pci_free_irq_vectors(pdev); } diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 697c09ef259b..cd52664920e1 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -254,12 +254,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, device_enable_async_suspend(&shost->shost_dev); + get_device(&shost->shost_gendev); error = device_add(&shost->shost_dev); if (error) goto out_del_gendev; - get_device(&shost->shost_gendev); - if (shost->transportt->host_size) { shost->shost_data = kzalloc(shost->transportt->host_size, GFP_KERNEL); @@ -278,33 +277,36 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, if (!shost->work_q) { error = -EINVAL; - goto out_free_shost_data; + goto out_del_dev; } } error = scsi_sysfs_add_host(shost); if (error) - goto out_destroy_host; + goto out_del_dev; scsi_proc_host_add(shost); scsi_autopm_put_host(shost); return error; - out_destroy_host: - if (shost->work_q) - destroy_workqueue(shost->work_q); - out_free_shost_data: - kfree(shost->shost_data); + /* + * Any host allocation in this function will be freed in + * scsi_host_dev_release(). + */ out_del_dev: device_del(&shost->shost_dev); out_del_gendev: + /* + * Host state is SHOST_RUNNING so we have to explicitly release + * ->shost_dev. + */ + put_device(&shost->shost_dev); device_del(&shost->shost_gendev); out_disable_runtime_pm: device_disable_async_suspend(&shost->shost_gendev); pm_runtime_disable(&shost->shost_gendev); pm_runtime_set_suspended(&shost->shost_gendev); pm_runtime_put_noidle(&shost->shost_gendev); - scsi_mq_destroy_tags(shost); fail: return error; } @@ -345,7 +347,7 @@ static void scsi_host_dev_release(struct device *dev) ida_simple_remove(&host_index_ida, shost->host_no); - if (parent) + if (shost->shost_state != SHOST_CREATED) put_device(parent); kfree(shost); } @@ -388,8 +390,10 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) mutex_init(&shost->scan_mutex); index = ida_simple_get(&host_index_ida, 0, 0, GFP_KERNEL); - if (index < 0) - goto fail_kfree; + if (index < 0) { + kfree(shost); + return NULL; + } shost->host_no = index; shost->dma_channel = 0xff; @@ -481,7 +485,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost_printk(KERN_WARNING, shost, "error handler thread failed to spawn, error = %ld\n", PTR_ERR(shost->ehandler)); - goto fail_index_remove; + goto fail; } shost->tmf_work_q = alloc_workqueue("scsi_tmf_%d", @@ -490,17 +494,18 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) if (!shost->tmf_work_q) { shost_printk(KERN_WARNING, shost, "failed to create tmf workq\n"); - goto fail_kthread; + goto fail; } scsi_proc_hostdir_add(shost->hostt); return shost; + fail: + /* + * Host state is still SHOST_CREATED and that is enough to release + * ->shost_gendev. scsi_host_dev_release() will free + * dev_name(&shost->shost_dev). + */ + put_device(&shost->shost_gendev); - fail_kthread: - kthread_stop(shost->ehandler); - fail_index_remove: - ida_simple_remove(&host_index_ida, shost->host_no); - fail_kfree: - kfree(shost); return NULL; } EXPORT_SYMBOL(scsi_host_alloc); diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c index 19cf418928fa..e3d03d744713 100644 --- a/drivers/scsi/libsas/sas_port.c +++ b/drivers/scsi/libsas/sas_port.c @@ -25,7 +25,7 @@ static bool phy_is_wideport_member(struct asd_sas_port *port, struct asd_sas_phy static void sas_resume_port(struct asd_sas_phy *phy) { - struct domain_device *dev; + struct domain_device *dev, *n; struct asd_sas_port *port = phy->port; struct sas_ha_struct *sas_ha = phy->ha; struct sas_internal *si = to_sas_internal(sas_ha->core.shost->transportt); @@ -44,7 +44,7 @@ static void sas_resume_port(struct asd_sas_phy *phy) * 1/ presume every device came back * 2/ force the next revalidation to check all expander phys */ - list_for_each_entry(dev, &port->dev_list, dev_list_node) { + list_for_each_entry_safe(dev, n, &port->dev_list, dev_list_node) { int i, rc; rc = sas_notify_lldd_dev_found(dev); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 573c8599d71c..fc3682f15f50 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -20589,10 +20589,8 @@ lpfc_sli4_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, abtswqe = &abtsiocb->wqe; memset(abtswqe, 0, sizeof(*abtswqe)); - if (lpfc_is_link_up(phba)) + if (!lpfc_is_link_up(phba)) bf_set(abort_cmd_ia, &abtswqe->abort_cmd, 1); - else - bf_set(abort_cmd_ia, &abtswqe->abort_cmd, 0); bf_set(abort_cmd_criteria, &abtswqe->abort_cmd, T_XRI_TAG); abtswqe->abort_cmd.rsrvd5 = 0; abtswqe->abort_cmd.wqe_com.abort_tag = xritag; diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 756231151882..b92570a7c309 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -1827,22 +1827,20 @@ static int qedf_vport_create(struct fc_vport *vport, bool disabled) fcoe_wwn_to_str(vport->port_name, buf, sizeof(buf)); QEDF_WARN(&(base_qedf->dbg_ctx), "Failed to create vport, " "WWPN (0x%s) already exists.\n", buf); - goto err1; + return rc; } if (atomic_read(&base_qedf->link_state) != QEDF_LINK_UP) { QEDF_WARN(&(base_qedf->dbg_ctx), "Cannot create vport " "because link is not up.\n"); - rc = -EIO; - goto err1; + return -EIO; } vn_port = libfc_vport_create(vport, sizeof(struct qedf_ctx)); if (!vn_port) { QEDF_WARN(&(base_qedf->dbg_ctx), "Could not create lport " "for vport.\n"); - rc = -ENOMEM; - goto err1; + return -ENOMEM; } fcoe_wwn_to_str(vport->port_name, buf, sizeof(buf)); @@ -1866,7 +1864,7 @@ static int qedf_vport_create(struct fc_vport *vport, bool disabled) if (rc) { QEDF_ERR(&(base_qedf->dbg_ctx), "Could not allocate memory " "for lport stats.\n"); - goto err2; + goto err; } fc_set_wwnn(vn_port, vport->node_name); @@ -1884,7 +1882,7 @@ static int qedf_vport_create(struct fc_vport *vport, bool disabled) if (rc) { QEDF_WARN(&base_qedf->dbg_ctx, "Error adding Scsi_Host rc=0x%x.\n", rc); - goto err2; + goto err; } /* Set default dev_loss_tmo based on module parameter */ @@ -1925,9 +1923,10 @@ static int qedf_vport_create(struct fc_vport *vport, bool disabled) vport_qedf->dbg_ctx.host_no = vn_port->host->host_no; vport_qedf->dbg_ctx.pdev = base_qedf->pdev; -err2: + return 0; + +err: scsi_host_put(vn_port->host); -err1: return rc; } @@ -1968,8 +1967,7 @@ static int qedf_vport_destroy(struct fc_vport *vport) fc_lport_free_stats(vn_port); /* Release Scsi_Host */ - if (vn_port->host) - scsi_host_put(vn_port->host); + scsi_host_put(vn_port->host); out: return 0; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index b2008fb1dd38..12a6848ade43 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1563,10 +1563,12 @@ void qlt_stop_phase2(struct qla_tgt *tgt) return; } + mutex_lock(&tgt->ha->optrom_mutex); mutex_lock(&vha->vha_tgt.tgt_mutex); tgt->tgt_stop = 0; tgt->tgt_stopped = 1; mutex_unlock(&vha->vha_tgt.tgt_mutex); + mutex_unlock(&tgt->ha->optrom_mutex); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00c, "Stop of tgt %p finished\n", tgt); diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index d92cec12454c..d33355ab6e14 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -184,6 +184,7 @@ static struct { {"HP", "C3323-300", "4269", BLIST_NOTQ}, {"HP", "C5713A", NULL, BLIST_NOREPORTLUN}, {"HP", "DISK-SUBSYSTEM", "*", BLIST_REPORTLUN2}, + {"HPE", "OPEN-", "*", BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES}, {"IBM", "AuSaV1S2", NULL, BLIST_FORCELUN}, {"IBM", "ProFibre 4000R", "*", BLIST_SPARSELUN | BLIST_LARGELUN}, {"IBM", "2105", NULL, BLIST_RETRY_HWERROR}, diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index aee3cfc7142a..0a84ec9e7cea 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -603,11 +603,23 @@ static void ufs_mtk_get_controller_version(struct ufs_hba *hba) ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_LOCALVERINFO), &ver); if (!ret) { - if (ver >= UFS_UNIPRO_VER_1_8) + if (ver >= UFS_UNIPRO_VER_1_8) { host->hw_ver.major = 3; + /* + * Fix HCI version for some platforms with + * incorrect version + */ + if (hba->ufs_version < ufshci_version(3, 0)) + hba->ufs_version = ufshci_version(3, 0); + } } } +static u32 ufs_mtk_get_ufs_hci_version(struct ufs_hba *hba) +{ + return hba->ufs_version; +} + /** * ufs_mtk_init - find other essential mmio bases * @hba: host controller instance @@ -1048,6 +1060,7 @@ static void ufs_mtk_event_notify(struct ufs_hba *hba, static const struct ufs_hba_variant_ops ufs_hba_mtk_vops = { .name = "mediatek.ufshci", .init = ufs_mtk_init, + .get_ufs_hci_version = ufs_mtk_get_ufs_hci_version, .setup_clocks = ufs_mtk_setup_clocks, .hce_enable_notify = ufs_mtk_hce_enable_notify, .link_startup_notify = ufs_mtk_link_startup_notify, diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index 8a79605d9652..b9969fce6b4d 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -585,7 +585,13 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter, case BTSTAT_SUCCESS: case BTSTAT_LINKED_COMMAND_COMPLETED: case BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG: - /* If everything went fine, let's move on.. */ + /* + * Commands like INQUIRY may transfer less data than + * requested by the initiator via bufflen. Set residual + * count to make upper layer aware of the actual amount + * of data returned. + */ + scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen); cmd->result = (DID_OK << 16); break; diff --git a/drivers/soc/amlogic/meson-clk-measure.c b/drivers/soc/amlogic/meson-clk-measure.c index e1957476a006..6dd190270123 100644 --- a/drivers/soc/amlogic/meson-clk-measure.c +++ b/drivers/soc/amlogic/meson-clk-measure.c @@ -626,10 +626,8 @@ static int meson_msr_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(base)) { - dev_err(&pdev->dev, "io resource mapping failed\n"); + if (IS_ERR(base)) return PTR_ERR(base); - } priv->regmap = devm_regmap_init_mmio(&pdev->dev, base, &meson_clk_msr_regmap_config); diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 2827085a323b..0ef79d60e88e 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1150,8 +1150,16 @@ static int qcom_swrm_get_port_config(struct qcom_swrm_ctrl *ctrl) ret = of_property_read_u8_array(np, "qcom,ports-block-pack-mode", bp_mode, nports); - if (ret) - return ret; + if (ret) { + u32 version; + + ctrl->reg_read(ctrl, SWRM_COMP_HW_VERSION, &version); + + if (version <= 0x01030000) + memset(bp_mode, SWR_INVALID_PARAM, QCOM_SDW_MAX_PORTS); + else + return ret; + } memset(hstart, SWR_INVALID_PARAM, QCOM_SDW_MAX_PORTS); of_property_read_u8_array(np, "qcom,ports-hstart", hstart, nports); diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 8b161ec4943b..f4481fe48bf0 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -65,7 +65,7 @@ config SPI_ALTERA This is the driver for the Altera SPI Controller. config SPI_ALTERA_CORE - tristate "Altera SPI Controller core code" + tristate "Altera SPI Controller core code" if COMPILE_TEST select REGMAP help "The core code for the Altera SPI Controller" diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 8965fe61c8b4..fe40626e45aa 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -68,7 +68,7 @@ #define BCM2835_SPI_FIFO_SIZE 64 #define BCM2835_SPI_FIFO_SIZE_3_4 48 #define BCM2835_SPI_DMA_MIN_LENGTH 96 -#define BCM2835_SPI_NUM_CS 4 /* raise as necessary */ +#define BCM2835_SPI_NUM_CS 24 /* raise as necessary */ #define BCM2835_SPI_MODE_BITS (SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \ | SPI_NO_CS | SPI_3WIRE) @@ -1195,6 +1195,12 @@ static int bcm2835_spi_setup(struct spi_device *spi) struct gpio_chip *chip; u32 cs; + if (spi->chip_select >= BCM2835_SPI_NUM_CS) { + dev_err(&spi->dev, "only %d chip-selects supported\n", + BCM2835_SPI_NUM_CS - 1); + return -EINVAL; + } + /* * Precalculate SPI slave's CS register value for ->prepare_message(): * The driver always uses software-controlled GPIO chip select, hence @@ -1288,7 +1294,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev) ctlr->use_gpio_descriptors = true; ctlr->mode_bits = BCM2835_SPI_MODE_BITS; ctlr->bits_per_word_mask = SPI_BPW_MASK(8); - ctlr->num_chipselect = BCM2835_SPI_NUM_CS; + ctlr->num_chipselect = 3; ctlr->setup = bcm2835_spi_setup; ctlr->transfer_one = bcm2835_spi_transfer_one; ctlr->handle_err = bcm2835_spi_handle_err; diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index 6a6af85aebfd..27d0087f8688 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -184,6 +184,8 @@ int spi_bitbang_setup(struct spi_device *spi) { struct spi_bitbang_cs *cs = spi->controller_state; struct spi_bitbang *bitbang; + bool initial_setup = false; + int retval; bitbang = spi_master_get_devdata(spi->master); @@ -192,22 +194,30 @@ int spi_bitbang_setup(struct spi_device *spi) if (!cs) return -ENOMEM; spi->controller_state = cs; + initial_setup = true; } /* per-word shift register access, in hardware or bitbanging */ cs->txrx_word = bitbang->txrx_word[spi->mode & (SPI_CPOL|SPI_CPHA)]; - if (!cs->txrx_word) - return -EINVAL; + if (!cs->txrx_word) { + retval = -EINVAL; + goto err_free; + } if (bitbang->setup_transfer) { - int retval = bitbang->setup_transfer(spi, NULL); + retval = bitbang->setup_transfer(spi, NULL); if (retval < 0) - return retval; + goto err_free; } dev_dbg(&spi->dev, "%s, %u nsec/bit\n", __func__, 2 * cs->nsecs); return 0; + +err_free: + if (initial_setup) + kfree(cs); + return retval; } EXPORT_SYMBOL_GPL(spi_bitbang_setup); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 028736687488..fb45e6af6638 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1375,11 +1375,13 @@ poll_mode: ret = spi_register_controller(ctlr); if (ret != 0) { dev_err(&pdev->dev, "Problem registering DSPI ctlr\n"); - goto out_free_irq; + goto out_release_dma; } return ret; +out_release_dma: + dspi_release_dma(dspi); out_free_irq: if (dspi->irq) free_irq(dspi->irq, dspi); diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index d0e5aa18b7ba..bdf94cc7be1a 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -440,6 +440,7 @@ static int fsl_spi_setup(struct spi_device *spi) { struct mpc8xxx_spi *mpc8xxx_spi; struct fsl_spi_reg __iomem *reg_base; + bool initial_setup = false; int retval; u32 hw_mode; struct spi_mpc8xxx_cs *cs = spi_get_ctldata(spi); @@ -452,6 +453,7 @@ static int fsl_spi_setup(struct spi_device *spi) if (!cs) return -ENOMEM; spi_set_ctldata(spi, cs); + initial_setup = true; } mpc8xxx_spi = spi_master_get_devdata(spi->master); @@ -475,6 +477,8 @@ static int fsl_spi_setup(struct spi_device *spi) retval = fsl_spi_setup_transfer(spi, NULL); if (retval < 0) { cs->hw_mode = hw_mode; /* Restore settings */ + if (initial_setup) + kfree(cs); return retval; } diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c index 71402f71ddd8..df28c6664aba 100644 --- a/drivers/spi/spi-omap-uwire.c +++ b/drivers/spi/spi-omap-uwire.c @@ -424,15 +424,22 @@ done: static int uwire_setup(struct spi_device *spi) { struct uwire_state *ust = spi->controller_state; + bool initial_setup = false; + int status; if (ust == NULL) { ust = kzalloc(sizeof(*ust), GFP_KERNEL); if (ust == NULL) return -ENOMEM; spi->controller_state = ust; + initial_setup = true; } - return uwire_setup_transfer(spi, NULL); + status = uwire_setup_transfer(spi, NULL); + if (status && initial_setup) + kfree(ust); + + return status; } static void uwire_cleanup(struct spi_device *spi) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 999c22736416..ede7f05e5ced 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -1032,8 +1032,22 @@ static void omap2_mcspi_release_dma(struct spi_master *master) } } +static void omap2_mcspi_cleanup(struct spi_device *spi) +{ + struct omap2_mcspi_cs *cs; + + if (spi->controller_state) { + /* Unlink controller state from context save list */ + cs = spi->controller_state; + list_del(&cs->node); + + kfree(cs); + } +} + static int omap2_mcspi_setup(struct spi_device *spi) { + bool initial_setup = false; int ret; struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master); struct omap2_mcspi_regs *ctx = &mcspi->ctx; @@ -1051,35 +1065,28 @@ static int omap2_mcspi_setup(struct spi_device *spi) spi->controller_state = cs; /* Link this to context save list */ list_add_tail(&cs->node, &ctx->cs); + initial_setup = true; } ret = pm_runtime_get_sync(mcspi->dev); if (ret < 0) { pm_runtime_put_noidle(mcspi->dev); + if (initial_setup) + omap2_mcspi_cleanup(spi); return ret; } ret = omap2_mcspi_setup_transfer(spi, NULL); + if (ret && initial_setup) + omap2_mcspi_cleanup(spi); + pm_runtime_mark_last_busy(mcspi->dev); pm_runtime_put_autosuspend(mcspi->dev); return ret; } -static void omap2_mcspi_cleanup(struct spi_device *spi) -{ - struct omap2_mcspi_cs *cs; - - if (spi->controller_state) { - /* Unlink controller state from context save list */ - cs = spi->controller_state; - list_del(&cs->node); - - kfree(cs); - } -} - static irqreturn_t omap2_mcspi_irq_handler(int irq, void *data) { struct omap2_mcspi *mcspi = data; diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 5e59ba075bc7..8ee0cc071777 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1254,6 +1254,8 @@ static int setup_cs(struct spi_device *spi, struct chip_data *chip, chip->gpio_cs_inverted = spi->mode & SPI_CS_HIGH; err = gpiod_direction_output(gpiod, !chip->gpio_cs_inverted); + if (err) + gpiod_put(chip->gpiod_cs); } return err; @@ -1267,6 +1269,7 @@ static int setup(struct spi_device *spi) struct driver_data *drv_data = spi_controller_get_devdata(spi->controller); uint tx_thres, tx_hi_thres, rx_thres; + int err; switch (drv_data->ssp_type) { case QUARK_X1000_SSP: @@ -1413,7 +1416,11 @@ static int setup(struct spi_device *spi) if (drv_data->ssp_type == CE4100_SSP) return 0; - return setup_cs(spi, chip, chip_info); + err = setup_cs(spi, chip, chip_info); + if (err) + kfree(chip); + + return err; } static void cleanup(struct spi_device *spi) diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c index 297c512069a5..5d27ee482237 100644 --- a/drivers/spi/spi-sc18is602.c +++ b/drivers/spi/spi-sc18is602.c @@ -174,7 +174,7 @@ static int sc18is602_setup_transfer(struct sc18is602 *hw, u32 hz, u8 mode) static int sc18is602_check_transfer(struct spi_device *spi, struct spi_transfer *t, int tlen) { - if (t && t->len + tlen > SC18IS602_BUFSIZ) + if (t && t->len + tlen > SC18IS602_BUFSIZ + 1) return -EINVAL; return 0; @@ -219,6 +219,11 @@ static int sc18is602_transfer_one(struct spi_master *master, return status; } +static size_t sc18is602_max_transfer_size(struct spi_device *spi) +{ + return SC18IS602_BUFSIZ; +} + static int sc18is602_setup(struct spi_device *spi) { struct sc18is602 *hw = spi_master_get_devdata(spi->master); @@ -293,6 +298,8 @@ static int sc18is602_probe(struct i2c_client *client, master->bits_per_word_mask = SPI_BPW_MASK(8); master->setup = sc18is602_setup; master->transfer_one_message = sc18is602_transfer_one; + master->max_transfer_size = sc18is602_max_transfer_size; + master->max_message_size = sc18is602_max_transfer_size; master->dev.of_node = np; master->min_speed_hz = hw->freq / 128; master->max_speed_hz = hw->freq / 4; diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index b41a75749b49..28e70db9bbba 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -1068,6 +1068,7 @@ static const struct of_device_id sprd_spi_of_match[] = { { .compatible = "sprd,sc9860-spi", }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, sprd_spi_of_match); static struct platform_driver sprd_spi_driver = { .driver = { diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index 7e640ccc7e77..594f64136208 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -294,7 +294,7 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi, int err = 0; if (!op->data.nbytes) - return stm32_qspi_wait_nobusy(qspi); + goto wait_nobusy; if (readl_relaxed(qspi->io_base + QSPI_SR) & SR_TCF) goto out; @@ -315,6 +315,9 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi, out: /* clear flags */ writel_relaxed(FCR_CTCF | FCR_CTEF, qspi->io_base + QSPI_FCR); +wait_nobusy: + if (!err) + err = stm32_qspi_wait_nobusy(qspi); return err; } diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index 5d8a5ee62fa2..9262c6418463 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -367,7 +367,7 @@ static int zynq_qspi_config_op(struct zynq_qspi *xqspi, struct spi_device *spi) } /** - * zynq_qspi_setup - Configure the QSPI controller + * zynq_qspi_setup_op - Configure the QSPI controller * @spi: Pointer to the spi_device structure * * Sets the operational mode of QSPI controller for the next QSPI transfer, baud @@ -528,18 +528,17 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem, struct zynq_qspi *xqspi = spi_controller_get_devdata(mem->spi->master); int err = 0, i; u8 *tmpbuf; - u8 opcode = op->cmd.opcode; dev_dbg(xqspi->dev, "cmd:%#x mode:%d.%d.%d.%d\n", - opcode, op->cmd.buswidth, op->addr.buswidth, + op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth, op->dummy.buswidth, op->data.buswidth); zynq_qspi_chipselect(mem->spi, true); zynq_qspi_config_op(xqspi, mem->spi); - if (op->cmd.nbytes) { + if (op->cmd.opcode) { reinit_completion(&xqspi->data_completion); - xqspi->txbuf = &opcode; + xqspi->txbuf = (u8 *)&op->cmd.opcode; xqspi->rxbuf = NULL; xqspi->tx_bytes = op->cmd.nbytes; xqspi->rx_bytes = op->cmd.nbytes; @@ -679,14 +678,14 @@ static int zynq_qspi_probe(struct platform_device *pdev) xqspi->irq = platform_get_irq(pdev, 0); if (xqspi->irq <= 0) { ret = -ENXIO; - goto remove_master; + goto clk_dis_all; } ret = devm_request_irq(&pdev->dev, xqspi->irq, zynq_qspi_irq, 0, pdev->name, xqspi); if (ret != 0) { ret = -ENXIO; dev_err(&pdev->dev, "request_irq failed\n"); - goto remove_master; + goto clk_dis_all; } ret = of_property_read_u32(np, "num-cs", @@ -694,8 +693,9 @@ static int zynq_qspi_probe(struct platform_device *pdev) if (ret < 0) { ctlr->num_chipselect = 1; } else if (num_cs > ZYNQ_QSPI_MAX_NUM_CS) { + ret = -EINVAL; dev_err(&pdev->dev, "only 2 chip selects are available\n"); - goto remove_master; + goto clk_dis_all; } else { ctlr->num_chipselect = num_cs; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ba425b9c7700..e353b7a9e54e 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -47,10 +47,6 @@ static void spidev_release(struct device *dev) { struct spi_device *spi = to_spi_device(dev); - /* spi controllers may cleanup for released devices */ - if (spi->controller->cleanup) - spi->controller->cleanup(spi); - spi_controller_put(spi->controller); kfree(spi->driver_override); kfree(spi); @@ -558,6 +554,12 @@ static int spi_dev_check(struct device *dev, void *data) return 0; } +static void spi_cleanup(struct spi_device *spi) +{ + if (spi->controller->cleanup) + spi->controller->cleanup(spi); +} + /** * spi_add_device - Add spi_device allocated with spi_alloc_device * @spi: spi_device to register @@ -622,11 +624,13 @@ int spi_add_device(struct spi_device *spi) /* Device may be bound to an active driver when this returns */ status = device_add(&spi->dev); - if (status < 0) + if (status < 0) { dev_err(dev, "can't add %s, status %d\n", dev_name(&spi->dev), status); - else + spi_cleanup(spi); + } else { dev_dbg(dev, "registered child %s\n", dev_name(&spi->dev)); + } done: mutex_unlock(&spi_add_lock); @@ -717,7 +721,9 @@ void spi_unregister_device(struct spi_device *spi) if (ACPI_COMPANION(&spi->dev)) acpi_device_clear_enumerated(ACPI_COMPANION(&spi->dev)); device_remove_software_node(&spi->dev); - device_unregister(&spi->dev); + device_del(&spi->dev); + spi_cleanup(spi); + put_device(&spi->dev); } EXPORT_SYMBOL_GPL(spi_unregister_device); @@ -814,15 +820,29 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) { if (!(spi->mode & SPI_NO_CS)) { - if (spi->cs_gpiod) - /* polarity handled by gpiolib */ - gpiod_set_value_cansleep(spi->cs_gpiod, activate); - else + if (spi->cs_gpiod) { + /* + * Historically ACPI has no means of the GPIO polarity and + * thus the SPISerialBus() resource defines it on the per-chip + * basis. In order to avoid a chain of negations, the GPIO + * polarity is considered being Active High. Even for the cases + * when _DSD() is involved (in the updated versions of ACPI) + * the GPIO CS polarity must be defined Active High to avoid + * ambiguity. That's why we use enable, that takes SPI_CS_HIGH + * into account. + */ + if (has_acpi_companion(&spi->dev)) + gpiod_set_value_cansleep(spi->cs_gpiod, !enable); + else + /* Polarity handled by GPIO library */ + gpiod_set_value_cansleep(spi->cs_gpiod, activate); + } else { /* * invert the enable line, as active low is * default for SPI. */ gpio_set_value_cansleep(spi->cs_gpio, !enable); + } } /* Some SPI masters need both GPIO CS & slave_select */ if ((spi->controller->flags & SPI_MASTER_GPIO_SS) && @@ -3451,9 +3471,12 @@ int spi_set_cs_timing(struct spi_device *spi, struct spi_delay *setup, if (spi->controller->set_cs_timing && !(spi->cs_gpiod || gpio_is_valid(spi->cs_gpio))) { + mutex_lock(&spi->controller->io_mutex); + if (spi->controller->auto_runtime_pm) { status = pm_runtime_get_sync(parent); if (status < 0) { + mutex_unlock(&spi->controller->io_mutex); pm_runtime_put_noidle(parent); dev_err(&spi->controller->dev, "Failed to power device: %d\n", status); @@ -3464,11 +3487,13 @@ int spi_set_cs_timing(struct spi_device *spi, struct spi_delay *setup, hold, inactive); pm_runtime_mark_last_busy(parent); pm_runtime_put_autosuspend(parent); - return status; } else { - return spi->controller->set_cs_timing(spi, setup, hold, + status = spi->controller->set_cs_timing(spi, setup, hold, inactive); } + + mutex_unlock(&spi->controller->io_mutex); + return status; } if ((setup && setup->unit == SPI_DELAY_UNIT_SCK) || diff --git a/drivers/staging/emxx_udc/emxx_udc.c b/drivers/staging/emxx_udc/emxx_udc.c index 741147a4f0fe..ecc5c9da9027 100644 --- a/drivers/staging/emxx_udc/emxx_udc.c +++ b/drivers/staging/emxx_udc/emxx_udc.c @@ -2064,7 +2064,7 @@ static int _nbu2ss_nuke(struct nbu2ss_udc *udc, struct nbu2ss_ep *ep, int status) { - struct nbu2ss_req *req; + struct nbu2ss_req *req, *n; /* Endpoint Disable */ _nbu2ss_epn_exit(udc, ep); @@ -2076,7 +2076,7 @@ static int _nbu2ss_nuke(struct nbu2ss_udc *udc, return 0; /* called with irqs blocked */ - list_for_each_entry(req, &ep->queue, queue) { + list_for_each_entry_safe(req, n, &ep->queue, queue) { _nbu2ss_ep_done(ep, req, status); } diff --git a/drivers/staging/iio/cdc/ad7746.c b/drivers/staging/iio/cdc/ad7746.c index dfd71e99e872..eab534dc4bcc 100644 --- a/drivers/staging/iio/cdc/ad7746.c +++ b/drivers/staging/iio/cdc/ad7746.c @@ -700,7 +700,6 @@ static int ad7746_probe(struct i2c_client *client, indio_dev->num_channels = ARRAY_SIZE(ad7746_channels); else indio_dev->num_channels = ARRAY_SIZE(ad7746_channels) - 2; - indio_dev->num_channels = ARRAY_SIZE(ad7746_channels); indio_dev->modes = INDIO_DIRECT_MODE; if (pdata) { diff --git a/drivers/staging/ralink-gdma/ralink-gdma.c b/drivers/staging/ralink-gdma/ralink-gdma.c index 33e28ccf4d85..b5229bc6eae5 100644 --- a/drivers/staging/ralink-gdma/ralink-gdma.c +++ b/drivers/staging/ralink-gdma/ralink-gdma.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Copyright (C) 2013, Lars-Peter Clausen <lars@metafoo.de> * GDMA4740 DMAC support */ @@ -914,6 +913,5 @@ static struct platform_driver gdma_dma_driver = { }; module_platform_driver(gdma_dma_driver); -MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>"); MODULE_DESCRIPTION("Ralink/MTK DMA driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index a6d731e959a2..437859228371 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -2091,7 +2091,7 @@ void rtw_cfg80211_indicate_sta_assoc(struct adapter *padapter, u8 *pmgmt_frame, struct net_device *ndev = padapter->pnetdev; { - struct station_info sinfo; + struct station_info sinfo = {}; u8 ie_offset; if (GetFrameSubType(pmgmt_frame) == WIFI_ASSOCREQ) ie_offset = _ASOCREQ_IE_OFFSET_; @@ -2284,7 +2284,7 @@ static int rtw_cfg80211_add_monitor_if(struct adapter *padapter, char *name, str mon_wdev->iftype = NL80211_IFTYPE_MONITOR; mon_ndev->ieee80211_ptr = mon_wdev; - ret = register_netdevice(mon_ndev); + ret = cfg80211_register_netdevice(mon_ndev); if (ret) { goto out; } @@ -2360,7 +2360,7 @@ static int cfg80211_rtw_del_virtual_intf(struct wiphy *wiphy, adapter = rtw_netdev_priv(ndev); pwdev_priv = adapter_wdev_data(adapter); - unregister_netdevice(ndev); + cfg80211_unregister_netdevice(ndev); if (ndev == pwdev_priv->pmon_ndev) { pwdev_priv->pmon_ndev = NULL; diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index d6fdd1c61f90..a526f9678c34 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -204,11 +204,11 @@ static struct se_dev_plug *iblock_plug_device(struct se_device *se_dev) struct iblock_dev_plug *ib_dev_plug; /* - * Each se_device has a per cpu work this can be run from. Wwe + * Each se_device has a per cpu work this can be run from. We * shouldn't have multiple threads on the same cpu calling this * at the same time. */ - ib_dev_plug = &ib_dev->ibd_plug[smp_processor_id()]; + ib_dev_plug = &ib_dev->ibd_plug[raw_smp_processor_id()]; if (test_and_set_bit(IBD_PLUGF_PLUGGED, &ib_dev_plug->flags)) return NULL; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 8fbfe75c5744..7e35eddd9eb7 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1416,7 +1416,7 @@ void __target_init_cmd( cmd->orig_fe_lun = unpacked_lun; if (!(cmd->se_cmd_flags & SCF_USE_CPUID)) - cmd->cpuid = smp_processor_id(); + cmd->cpuid = raw_smp_processor_id(); cmd->state_active = false; } @@ -3121,9 +3121,7 @@ __transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop, __releases(&cmd->t_state_lock) __acquires(&cmd->t_state_lock) { - - assert_spin_locked(&cmd->t_state_lock); - WARN_ON_ONCE(!irqs_disabled()); + lockdep_assert_held(&cmd->t_state_lock); if (fabric_stop) cmd->transport_state |= CMD_T_FABRIC_STOP; diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 198d25ae482a..4bba10e7755a 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -516,8 +516,10 @@ static inline int tcmu_get_empty_block(struct tcmu_dev *udev, dpi = dbi * udev->data_pages_per_blk; /* Count the number of already allocated pages */ xas_set(&xas, dpi); + rcu_read_lock(); for (cnt = 0; xas_next(&xas) && cnt < page_cnt;) cnt++; + rcu_read_unlock(); for (i = cnt; i < page_cnt; i++) { /* try to get new page from the mm */ @@ -699,11 +701,10 @@ static inline void tcmu_copy_data(struct tcmu_dev *udev, struct scatterlist *sg, unsigned int sg_nents, struct iovec **iov, size_t data_len) { - XA_STATE(xas, &udev->data_pages, 0); /* start value of dbi + 1 must not be a valid dbi */ int dbi = -2; size_t page_remaining, cp_len; - int page_cnt, page_inx; + int page_cnt, page_inx, dpi; struct sg_mapping_iter sg_iter; unsigned int sg_flags; struct page *page; @@ -726,9 +727,10 @@ static inline void tcmu_copy_data(struct tcmu_dev *udev, if (page_cnt > udev->data_pages_per_blk) page_cnt = udev->data_pages_per_blk; - xas_set(&xas, dbi * udev->data_pages_per_blk); - for (page_inx = 0; page_inx < page_cnt && data_len; page_inx++) { - page = xas_next(&xas); + dpi = dbi * udev->data_pages_per_blk; + for (page_inx = 0; page_inx < page_cnt && data_len; + page_inx++, dpi++) { + page = xa_load(&udev->data_pages, dpi); if (direction == TCMU_DATA_AREA_TO_SG) flush_dcache_page(page); diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 6132cc8d014c..6e6eb836e9b6 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -220,6 +220,7 @@ int optee_open_session(struct tee_context *ctx, struct optee_msg_arg *msg_arg; phys_addr_t msg_parg; struct optee_session *sess = NULL; + uuid_t client_uuid; /* +2 for the meta parameters added below */ shm = get_msg_arg(ctx, arg->num_params + 2, &msg_arg, &msg_parg); @@ -240,10 +241,11 @@ int optee_open_session(struct tee_context *ctx, memcpy(&msg_arg->params[0].u.value, arg->uuid, sizeof(arg->uuid)); msg_arg->params[1].u.value.c = arg->clnt_login; - rc = tee_session_calc_client_uuid((uuid_t *)&msg_arg->params[1].u.value, - arg->clnt_login, arg->clnt_uuid); + rc = tee_session_calc_client_uuid(&client_uuid, arg->clnt_login, + arg->clnt_uuid); if (rc) goto out; + export_uuid(msg_arg->params[1].u.octets, &client_uuid); rc = optee_to_msg_param(msg_arg->params + 2, arg->num_params, param); if (rc) diff --git a/drivers/tee/optee/optee_msg.h b/drivers/tee/optee/optee_msg.h index 81ff593ac4ec..e3d72d09c484 100644 --- a/drivers/tee/optee/optee_msg.h +++ b/drivers/tee/optee/optee_msg.h @@ -9,7 +9,7 @@ #include <linux/types.h> /* - * This file defines the OP-TEE message protocol used to communicate + * This file defines the OP-TEE message protocol (ABI) used to communicate * with an instance of OP-TEE running in secure world. * * This file is divided into two sections. @@ -144,9 +144,10 @@ struct optee_msg_param_value { * @tmem: parameter by temporary memory reference * @rmem: parameter by registered memory reference * @value: parameter by opaque value + * @octets: parameter by octet string * * @attr & OPTEE_MSG_ATTR_TYPE_MASK indicates if tmem, rmem or value is used in - * the union. OPTEE_MSG_ATTR_TYPE_VALUE_* indicates value, + * the union. OPTEE_MSG_ATTR_TYPE_VALUE_* indicates value or octets, * OPTEE_MSG_ATTR_TYPE_TMEM_* indicates @tmem and * OPTEE_MSG_ATTR_TYPE_RMEM_* indicates @rmem, * OPTEE_MSG_ATTR_TYPE_NONE indicates that none of the members are used. @@ -157,6 +158,7 @@ struct optee_msg_param { struct optee_msg_param_tmem tmem; struct optee_msg_param_rmem rmem; struct optee_msg_param_value value; + u8 octets[24]; } u; }; diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index d1248ba943a4..62c0aa5d0783 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -237,6 +237,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, if (ACPI_FAILURE(status)) trip_cnt = 0; else { + int i; + int34x_thermal_zone->aux_trips = kcalloc(trip_cnt, sizeof(*int34x_thermal_zone->aux_trips), @@ -247,6 +249,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, } trip_mask = BIT(trip_cnt) - 1; int34x_thermal_zone->aux_trip_nr = trip_cnt; + for (i = 0; i < trip_cnt; ++i) + int34x_thermal_zone->aux_trips[i] = THERMAL_TEMP_INVALID; } trip_cnt = int340x_thermal_read_trips(int34x_thermal_zone); diff --git a/drivers/thermal/intel/therm_throt.c b/drivers/thermal/intel/therm_throt.c index f8e882592ba5..99abdc03c44c 100644 --- a/drivers/thermal/intel/therm_throt.c +++ b/drivers/thermal/intel/therm_throt.c @@ -621,6 +621,17 @@ bool x86_thermal_enabled(void) return atomic_read(&therm_throt_en); } +void __init therm_lvt_init(void) +{ + /* + * This function is only called on boot CPU. Save the init thermal + * LVT value on BSP and use that value to restore APs' thermal LVT + * entry BIOS programmed later + */ + if (intel_thermal_supported(&boot_cpu_data)) + lvtthmr_init = apic_read(APIC_LVTTHMR); +} + void intel_init_thermal(struct cpuinfo_x86 *c) { unsigned int cpu = smp_processor_id(); @@ -630,10 +641,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if (!intel_thermal_supported(c)) return; - /* On the BSP? */ - if (c == &boot_cpu_data) - lvtthmr_init = apic_read(APIC_LVTTHMR); - /* * First check if its enabled already, in which case there might * be some SMM goo which handles it, so we can't even put a handler diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c index 295742e83960..4d8edc61a78b 100644 --- a/drivers/thermal/intel/x86_pkg_temp_thermal.c +++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c @@ -166,7 +166,7 @@ static int sys_get_trip_temp(struct thermal_zone_device *tzd, if (thres_reg_value) *temp = zonedev->tj_max - thres_reg_value * 1000; else - *temp = 0; + *temp = THERMAL_TEMP_INVALID; pr_debug("sys_get_trip_temp %d\n", *temp); return 0; diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c index b460b56e981c..232fd0b33325 100644 --- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c +++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c @@ -441,7 +441,7 @@ static int adc_tm5_get_dt_channel_data(struct adc_tm5_chip *adc_tm, if (args.args_count != 1 || args.args[0] >= ADC5_MAX_CHANNEL) { dev_err(dev, "%s: invalid ADC channel number %d\n", name, chan); - return ret; + return -EINVAL; } channel->adc_channel = args.args[0]; diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c index ebe7cb70bfb6..ea0603b59309 100644 --- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c +++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c @@ -770,7 +770,7 @@ static int ti_bandgap_tshut_init(struct ti_bandgap *bgp, } /** - * ti_bandgap_alert_init() - setup and initialize talert handling + * ti_bandgap_talert_init() - setup and initialize talert handling * @bgp: pointer to struct ti_bandgap * @pdev: pointer to device struct platform_device * diff --git a/drivers/thunderbolt/dma_port.c b/drivers/thunderbolt/dma_port.c index 7288aaf01ae6..5631319f7b20 100644 --- a/drivers/thunderbolt/dma_port.c +++ b/drivers/thunderbolt/dma_port.c @@ -366,15 +366,15 @@ int dma_port_flash_read(struct tb_dma_port *dma, unsigned int address, void *buf, size_t size) { unsigned int retries = DMA_PORT_RETRIES; - unsigned int offset; - - offset = address & 3; - address = address & ~3; do { - u32 nbytes = min_t(u32, size, MAIL_DATA_DWORDS * 4); + unsigned int offset; + size_t nbytes; int ret; + offset = address & 3; + nbytes = min_t(size_t, size + offset, MAIL_DATA_DWORDS * 4); + ret = dma_port_flash_read_block(dma, address, dma->buf, ALIGN(nbytes, 4)); if (ret) { @@ -386,6 +386,7 @@ int dma_port_flash_read(struct tb_dma_port *dma, unsigned int address, return ret; } + nbytes -= offset; memcpy(buf, dma->buf + offset, nbytes); size -= nbytes; diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 680bc738dd66..671d72af8ba1 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -68,15 +68,15 @@ static int usb4_do_read_data(u16 address, void *buf, size_t size, unsigned int retries = USB4_DATA_RETRIES; unsigned int offset; - offset = address & 3; - address = address & ~3; - do { - size_t nbytes = min_t(size_t, size, USB4_DATA_DWORDS * 4); unsigned int dwaddress, dwords; u8 data[USB4_DATA_DWORDS * 4]; + size_t nbytes; int ret; + offset = address & 3; + nbytes = min_t(size_t, size + offset, USB4_DATA_DWORDS * 4); + dwaddress = address / 4; dwords = ALIGN(nbytes, 4) / 4; @@ -87,6 +87,7 @@ static int usb4_do_read_data(u16 address, void *buf, size_t size, return ret; } + nbytes -= offset; memcpy(buf, data + offset, nbytes); size -= nbytes; diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 52bb21205bb6..6473361525d1 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -7,6 +7,7 @@ * Copyright (C) 2001 Russell King. */ +#include <linux/bits.h> #include <linux/serial_8250.h> #include <linux/serial_reg.h> #include <linux/dmaengine.h> @@ -70,24 +71,25 @@ struct serial8250_config { unsigned int flags; }; -#define UART_CAP_FIFO (1 << 8) /* UART has FIFO */ -#define UART_CAP_EFR (1 << 9) /* UART has EFR */ -#define UART_CAP_SLEEP (1 << 10) /* UART has IER sleep */ -#define UART_CAP_AFE (1 << 11) /* MCR-based hw flow control */ -#define UART_CAP_UUE (1 << 12) /* UART needs IER bit 6 set (Xscale) */ -#define UART_CAP_RTOIE (1 << 13) /* UART needs IER bit 4 set (Xscale, Tegra) */ -#define UART_CAP_HFIFO (1 << 14) /* UART has a "hidden" FIFO */ -#define UART_CAP_RPM (1 << 15) /* Runtime PM is active while idle */ -#define UART_CAP_IRDA (1 << 16) /* UART supports IrDA line discipline */ -#define UART_CAP_MINI (1 << 17) /* Mini UART on BCM283X family lacks: +#define UART_CAP_FIFO BIT(8) /* UART has FIFO */ +#define UART_CAP_EFR BIT(9) /* UART has EFR */ +#define UART_CAP_SLEEP BIT(10) /* UART has IER sleep */ +#define UART_CAP_AFE BIT(11) /* MCR-based hw flow control */ +#define UART_CAP_UUE BIT(12) /* UART needs IER bit 6 set (Xscale) */ +#define UART_CAP_RTOIE BIT(13) /* UART needs IER bit 4 set (Xscale, Tegra) */ +#define UART_CAP_HFIFO BIT(14) /* UART has a "hidden" FIFO */ +#define UART_CAP_RPM BIT(15) /* Runtime PM is active while idle */ +#define UART_CAP_IRDA BIT(16) /* UART supports IrDA line discipline */ +#define UART_CAP_MINI BIT(17) /* Mini UART on BCM283X family lacks: * STOP PARITY EPAR SPAR WLEN5 WLEN6 */ -#define UART_BUG_QUOT (1 << 0) /* UART has buggy quot LSB */ -#define UART_BUG_TXEN (1 << 1) /* UART has buggy TX IIR status */ -#define UART_BUG_NOMSR (1 << 2) /* UART has buggy MSR status bits (Au1x00) */ -#define UART_BUG_THRE (1 << 3) /* UART has buggy THRE reassertion */ -#define UART_BUG_PARITY (1 << 4) /* UART mishandles parity if FIFO enabled */ +#define UART_BUG_QUOT BIT(0) /* UART has buggy quot LSB */ +#define UART_BUG_TXEN BIT(1) /* UART has buggy TX IIR status */ +#define UART_BUG_NOMSR BIT(2) /* UART has buggy MSR status bits (Au1x00) */ +#define UART_BUG_THRE BIT(3) /* UART has buggy THRE reassertion */ +#define UART_BUG_PARITY BIT(4) /* UART mishandles parity if FIFO enabled */ +#define UART_BUG_TXRACE BIT(5) /* UART Tx fails to set remote DR */ #ifdef CONFIG_SERIAL_8250_SHARE_IRQ diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c index 61550f24a2d3..d035d08cb987 100644 --- a/drivers/tty/serial/8250/8250_aspeed_vuart.c +++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c @@ -437,6 +437,7 @@ static int aspeed_vuart_probe(struct platform_device *pdev) port.port.status = UPSTAT_SYNC_FIFO; port.port.dev = &pdev->dev; port.port.has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); + port.bugs |= UART_BUG_TXRACE; rc = sysfs_create_group(&vuart->dev->kobj, &aspeed_vuart_attr_group); if (rc < 0) diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 9e204f9b799a..a3a0154da567 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -714,6 +714,7 @@ static const struct acpi_device_id dw8250_acpi_match[] = { { "APMC0D08", 0}, { "AMD0020", 0 }, { "AMDI0020", 0 }, + { "AMDI0022", 0 }, { "BRCM2032", 0 }, { "HISI0031", 0 }, { }, diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 2f49c580139b..bd4e9f6ac29c 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -553,7 +553,11 @@ static void pci_xr17v35x_exit(struct pci_dev *pcidev) { struct exar8250 *priv = pci_get_drvdata(pcidev); struct uart_8250_port *port = serial8250_get_port(priv->line[0]); - struct platform_device *pdev = port->port.private_data; + struct platform_device *pdev; + + pdev = port->port.private_data; + if (!pdev) + return; device_remove_software_node(&pdev->dev); platform_device_unregister(pdev); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 689d8227f95f..780cc99732b6 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -56,6 +56,8 @@ struct serial_private { int line[]; }; +#define PCI_DEVICE_ID_HPE_PCI_SERIAL 0x37e + static const struct pci_device_id pci_use_msi[] = { { PCI_DEVICE_SUB(PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9900, 0xA000, 0x1000) }, @@ -63,6 +65,8 @@ static const struct pci_device_id pci_use_msi[] = { 0xA000, 0x1000) }, { PCI_DEVICE_SUB(PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9922, 0xA000, 0x1000) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_HP_3PAR, PCI_DEVICE_ID_HPE_PCI_SERIAL, + PCI_ANY_ID, PCI_ANY_ID) }, { } }; @@ -1998,6 +2002,16 @@ static struct pci_serial_quirk pci_serial_quirks[] = { .setup = pci_hp_diva_setup, }, /* + * HPE PCI serial device + */ + { + .vendor = PCI_VENDOR_ID_HP_3PAR, + .device = PCI_DEVICE_ID_HPE_PCI_SERIAL, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_hp_diva_setup, + }, + /* * Intel */ { @@ -3944,21 +3958,26 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board) uart.port.flags = UPF_SKIP_TEST | UPF_BOOT_AUTOCONF | UPF_SHARE_IRQ; uart.port.uartclk = board->base_baud * 16; - if (pci_match_id(pci_use_msi, dev)) { - dev_dbg(&dev->dev, "Using MSI(-X) interrupts\n"); - pci_set_master(dev); - rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES); + if (board->flags & FL_NOIRQ) { + uart.port.irq = 0; } else { - dev_dbg(&dev->dev, "Using legacy interrupts\n"); - rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_LEGACY); - } - if (rc < 0) { - kfree(priv); - priv = ERR_PTR(rc); - goto err_deinit; + if (pci_match_id(pci_use_msi, dev)) { + dev_dbg(&dev->dev, "Using MSI(-X) interrupts\n"); + pci_set_master(dev); + rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES); + } else { + dev_dbg(&dev->dev, "Using legacy interrupts\n"); + rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_LEGACY); + } + if (rc < 0) { + kfree(priv); + priv = ERR_PTR(rc); + goto err_deinit; + } + + uart.port.irq = pci_irq_vector(dev, 0); } - uart.port.irq = pci_irq_vector(dev, 0); uart.port.dev = &dev->dev; for (i = 0; i < nr_ports; i++) { @@ -4973,6 +4992,10 @@ static const struct pci_device_id serial_pci_tbl[] = { { PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_DIVA_AUX, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b2_1_115200 }, + /* HPE PCI serial device */ + { PCI_VENDOR_ID_HP_3PAR, PCI_DEVICE_ID_HPE_PCI_SERIAL, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_b1_1_115200 }, { PCI_VENDOR_ID_DCI, PCI_DEVICE_ID_DCI_PCCOM2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index d45dab1ab316..fc5ab2032282 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1809,6 +1809,18 @@ void serial8250_tx_chars(struct uart_8250_port *up) count = up->tx_loadsz; do { serial_out(up, UART_TX, xmit->buf[xmit->tail]); + if (up->bugs & UART_BUG_TXRACE) { + /* + * The Aspeed BMC virtual UARTs have a bug where data + * may get stuck in the BMC's Tx FIFO from bursts of + * writes on the APB interface. + * + * Delay back-to-back writes by a read cycle to avoid + * stalling the VUART. Read a register that won't have + * side-effects and discard the result. + */ + serial_in(up, UART_SCR); + } xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); port->icount.tx++; if (uart_circ_empty(xmit)) diff --git a/drivers/tty/serial/rp2.c b/drivers/tty/serial/rp2.c index d60abffab70e..6689d8add8f7 100644 --- a/drivers/tty/serial/rp2.c +++ b/drivers/tty/serial/rp2.c @@ -195,7 +195,6 @@ struct rp2_card { void __iomem *bar0; void __iomem *bar1; spinlock_t card_lock; - struct completion fw_loaded; }; #define RP_ID(prod) PCI_VDEVICE(RP, (prod)) @@ -662,17 +661,10 @@ static void rp2_remove_ports(struct rp2_card *card) card->initialized_ports = 0; } -static void rp2_fw_cb(const struct firmware *fw, void *context) +static int rp2_load_firmware(struct rp2_card *card, const struct firmware *fw) { - struct rp2_card *card = context; resource_size_t phys_base; - int i, rc = -ENOENT; - - if (!fw) { - dev_err(&card->pdev->dev, "cannot find '%s' firmware image\n", - RP2_FW_NAME); - goto no_fw; - } + int i, rc = 0; phys_base = pci_resource_start(card->pdev, 1); @@ -718,23 +710,13 @@ static void rp2_fw_cb(const struct firmware *fw, void *context) card->initialized_ports++; } - release_firmware(fw); -no_fw: - /* - * rp2_fw_cb() is called from a workqueue long after rp2_probe() - * has already returned success. So if something failed here, - * we'll just leave the now-dormant device in place until somebody - * unbinds it. - */ - if (rc) - dev_warn(&card->pdev->dev, "driver initialization failed\n"); - - complete(&card->fw_loaded); + return rc; } static int rp2_probe(struct pci_dev *pdev, const struct pci_device_id *id) { + const struct firmware *fw; struct rp2_card *card; struct rp2_uart_port *ports; void __iomem * const *bars; @@ -745,7 +727,6 @@ static int rp2_probe(struct pci_dev *pdev, return -ENOMEM; pci_set_drvdata(pdev, card); spin_lock_init(&card->card_lock); - init_completion(&card->fw_loaded); rc = pcim_enable_device(pdev); if (rc) @@ -778,21 +759,23 @@ static int rp2_probe(struct pci_dev *pdev, return -ENOMEM; card->ports = ports; - rc = devm_request_irq(&pdev->dev, pdev->irq, rp2_uart_interrupt, - IRQF_SHARED, DRV_NAME, card); - if (rc) + rc = request_firmware(&fw, RP2_FW_NAME, &pdev->dev); + if (rc < 0) { + dev_err(&pdev->dev, "cannot find '%s' firmware image\n", + RP2_FW_NAME); return rc; + } - /* - * Only catastrophic errors (e.g. ENOMEM) are reported here. - * If the FW image is missing, we'll find out in rp2_fw_cb() - * and print an error message. - */ - rc = request_firmware_nowait(THIS_MODULE, 1, RP2_FW_NAME, &pdev->dev, - GFP_KERNEL, card, rp2_fw_cb); + rc = rp2_load_firmware(card, fw); + + release_firmware(fw); + if (rc < 0) + return rc; + + rc = devm_request_irq(&pdev->dev, pdev->irq, rp2_uart_interrupt, + IRQF_SHARED, DRV_NAME, card); if (rc) return rc; - dev_dbg(&pdev->dev, "waiting for firmware blob...\n"); return 0; } @@ -801,7 +784,6 @@ static void rp2_remove(struct pci_dev *pdev) { struct rp2_card *card = pci_get_drvdata(pdev); - wait_for_completion(&card->fw_loaded); rp2_remove_ports(card); } diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index bbae072a125d..222032792d6c 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -338,7 +338,7 @@ static void tegra_uart_fifo_reset(struct tegra_uart_port *tup, u8 fcr_bits) do { lsr = tegra_uart_read(tup, UART_LSR); - if ((lsr | UART_LSR_TEMT) && !(lsr & UART_LSR_DR)) + if ((lsr & UART_LSR_TEMT) && !(lsr & UART_LSR_DR)) break; udelay(1); } while (--tmout); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 87f7127b57e6..18ff85a83f80 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -863,9 +863,11 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, goto check_and_exit; } - retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); - if (retval && (change_irq || change_port)) - goto exit; + if (change_irq || change_port) { + retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); + if (retval) + goto exit; + } /* * Ask the low level driver to verify the settings. diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ef37fdf37612..4baf1316ea72 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1023,10 +1023,10 @@ static int scif_set_rtrg(struct uart_port *port, int rx_trig) { unsigned int bits; + if (rx_trig >= port->fifosize) + rx_trig = port->fifosize - 1; if (rx_trig < 1) rx_trig = 1; - if (rx_trig >= port->fifosize) - rx_trig = port->fifosize; /* HSCIF can be set to an arbitrary level. */ if (sci_getreg(port, HSRTRGR)->size) { diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index 9b1bd417cec0..5281f8d3fb3d 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -2007,7 +2007,7 @@ static void cdns3_configure_dmult(struct cdns3_device *priv_dev, else mask = BIT(priv_ep->num); - if (priv_ep->type != USB_ENDPOINT_XFER_ISOC) { + if (priv_ep->type != USB_ENDPOINT_XFER_ISOC && !priv_ep->dir) { cdns3_set_register_bit(®s->tdl_from_trb, mask); cdns3_set_register_bit(®s->tdl_beh, mask); cdns3_set_register_bit(®s->tdl_beh2, mask); @@ -2046,15 +2046,13 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) case USB_ENDPOINT_XFER_INT: ep_cfg = EP_CFG_EPTYPE(USB_ENDPOINT_XFER_INT); - if ((priv_dev->dev_ver == DEV_VER_V2 && !priv_ep->dir) || - priv_dev->dev_ver > DEV_VER_V2) + if (priv_dev->dev_ver >= DEV_VER_V2 && !priv_ep->dir) ep_cfg |= EP_CFG_TDL_CHK; break; case USB_ENDPOINT_XFER_BULK: ep_cfg = EP_CFG_EPTYPE(USB_ENDPOINT_XFER_BULK); - if ((priv_dev->dev_ver == DEV_VER_V2 && !priv_ep->dir) || - priv_dev->dev_ver > DEV_VER_V2) + if (priv_dev->dev_ver >= DEV_VER_V2 && !priv_ep->dir) ep_cfg |= EP_CFG_TDL_CHK; break; default: @@ -3268,8 +3266,10 @@ static int __cdns3_gadget_init(struct cdns *cdns) pm_runtime_get_sync(cdns->dev); ret = cdns3_gadget_start(cdns); - if (ret) + if (ret) { + pm_runtime_put_sync(cdns->dev); return ret; + } /* * Because interrupt line can be shared with other components in diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 56707b6b0f57..c083985e387b 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -422,17 +422,17 @@ unmap: int cdnsp_ep_dequeue(struct cdnsp_ep *pep, struct cdnsp_request *preq) { struct cdnsp_device *pdev = pep->pdev; - int ret; + int ret_stop = 0; + int ret_rem; trace_cdnsp_request_dequeue(preq); - if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_RUNNING) { - ret = cdnsp_cmd_stop_ep(pdev, pep); - if (ret) - return ret; - } + if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_RUNNING) + ret_stop = cdnsp_cmd_stop_ep(pdev, pep); + + ret_rem = cdnsp_remove_request(pdev, preq, pep); - return cdnsp_remove_request(pdev, preq, pep); + return ret_rem ? ret_rem : ret_stop; } static void cdnsp_zero_in_ctx(struct cdnsp_device *pdev) diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 5f0513c96c04..68972746e363 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -1517,13 +1517,14 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data) { struct cdnsp_device *pdev = (struct cdnsp_device *)data; union cdnsp_trb *event_ring_deq; + unsigned long flags; int counter = 0; - spin_lock(&pdev->lock); + spin_lock_irqsave(&pdev->lock, flags); if (pdev->cdnsp_state & (CDNSP_STATE_HALTED | CDNSP_STATE_DYING)) { cdnsp_died(pdev); - spin_unlock(&pdev->lock); + spin_unlock_irqrestore(&pdev->lock, flags); return IRQ_HANDLED; } @@ -1539,7 +1540,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data) cdnsp_update_erst_dequeue(pdev, event_ring_deq, 1); - spin_unlock(&pdev->lock); + spin_unlock_irqrestore(&pdev->lock, flags); return IRQ_HANDLED; } diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index c16d900cdaee..393f216b9161 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -2061,6 +2061,7 @@ static int udc_start(struct ci_hdrc *ci) ci->gadget.name = ci->platdata->name; ci->gadget.otg_caps = otg_caps; ci->gadget.sg_supported = 1; + ci->gadget.irq = ci->irq; if (ci->platdata->flags & CI_HDRC_REQUIRES_ALIGNED_DMA) ci->gadget.quirk_avoids_skb_reserve = 1; diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c index 4545b23bda3f..bac0f5458cab 100644 --- a/drivers/usb/chipidea/usbmisc_imx.c +++ b/drivers/usb/chipidea/usbmisc_imx.c @@ -686,6 +686,16 @@ static int imx7d_charger_secondary_detection(struct imx_usbmisc_data *data) int val; unsigned long flags; + /* Clear VDATSRCENB0 to disable VDP_SRC and IDM_SNK required by BC 1.2 spec */ + spin_lock_irqsave(&usbmisc->lock, flags); + val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2); + val &= ~MX7D_USB_OTG_PHY_CFG2_CHRG_VDATSRCENB0; + writel(val, usbmisc->base + MX7D_USB_OTG_PHY_CFG2); + spin_unlock_irqrestore(&usbmisc->lock, flags); + + /* TVDMSRC_DIS */ + msleep(20); + /* VDM_SRC is connected to D- and IDP_SINK is connected to D+ */ spin_lock_irqsave(&usbmisc->lock, flags); val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2); @@ -695,7 +705,8 @@ static int imx7d_charger_secondary_detection(struct imx_usbmisc_data *data) usbmisc->base + MX7D_USB_OTG_PHY_CFG2); spin_unlock_irqrestore(&usbmisc->lock, flags); - usleep_range(1000, 2000); + /* TVDMSRC_ON */ + msleep(40); /* * Per BC 1.2, check voltage of D+: @@ -798,7 +809,8 @@ static int imx7d_charger_primary_detection(struct imx_usbmisc_data *data) usbmisc->base + MX7D_USB_OTG_PHY_CFG2); spin_unlock_irqrestore(&usbmisc->lock, flags); - usleep_range(1000, 2000); + /* TVDPSRC_ON */ + msleep(40); /* Check if D- is less than VDAT_REF to determine an SDP per BC 1.2 */ val = readl(usbmisc->base + MX7D_USB_OTG_PHY_STATUS); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 533236366a03..2218941d35a3 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1218,7 +1218,12 @@ static int do_proc_bulk(struct usb_dev_state *ps, ret = usbfs_increase_memory_usage(len1 + sizeof(struct urb)); if (ret) return ret; - tbuf = kmalloc(len1, GFP_KERNEL); + + /* + * len1 can be almost arbitrarily large. Don't WARN if it's + * too big, just fail the request. + */ + tbuf = kmalloc(len1, GFP_KERNEL | __GFP_NOWARN); if (!tbuf) { ret = -ENOMEM; goto done; @@ -1696,7 +1701,7 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb if (num_sgs) { as->urb->sg = kmalloc_array(num_sgs, sizeof(struct scatterlist), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!as->urb->sg) { ret = -ENOMEM; goto error; @@ -1731,7 +1736,7 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb (uurb_start - as->usbm->vm_start); } else { as->urb->transfer_buffer = kmalloc(uurb->buffer_length, - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!as->urb->transfer_buffer) { ret = -ENOMEM; goto error; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index fc7d6cdacf16..df8e69e60aaf 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -41,6 +41,8 @@ #define USB_VENDOR_GENESYS_LOGIC 0x05e3 #define USB_VENDOR_SMSC 0x0424 #define USB_PRODUCT_USB5534B 0x5534 +#define USB_VENDOR_CYPRESS 0x04b4 +#define USB_PRODUCT_CY7C65632 0x6570 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 #define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 @@ -5698,6 +5700,11 @@ static const struct usb_device_id hub_id_table[] = { .bInterfaceClass = USB_CLASS_HUB, .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_CYPRESS, + .idProduct = USB_PRODUCT_CY7C65632, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, .idVendor = USB_VENDOR_GENESYS_LOGIC, .bInterfaceClass = USB_CLASS_HUB, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index b6e53d8212cd..4ac397e43e19 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1671,8 +1671,8 @@ static int dwc3_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); - dwc3_debugfs_exit(dwc); dwc3_core_exit_mode(dwc); + dwc3_debugfs_exit(dwc); dwc3_core_exit(dwc); dwc3_ulpi_exit(dwc); @@ -1690,11 +1690,6 @@ static int dwc3_remove(struct platform_device *pdev) return 0; } -static void dwc3_shutdown(struct platform_device *pdev) -{ - dwc3_remove(pdev); -} - #ifdef CONFIG_PM static int dwc3_core_init_for_resume(struct dwc3 *dwc) { @@ -2012,7 +2007,6 @@ MODULE_DEVICE_TABLE(acpi, dwc3_acpi_match); static struct platform_driver dwc3_driver = { .probe = dwc3_probe, .remove = dwc3_remove, - .shutdown = dwc3_shutdown, .driver = { .name = "dwc3", .of_match_table = of_match_ptr(of_dwc3_match), diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h index d0ac89c5b317..d223c54115f4 100644 --- a/drivers/usb/dwc3/debug.h +++ b/drivers/usb/dwc3/debug.h @@ -413,9 +413,12 @@ static inline const char *dwc3_gadget_generic_cmd_status_string(int status) #ifdef CONFIG_DEBUG_FS +extern void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep); extern void dwc3_debugfs_init(struct dwc3 *d); extern void dwc3_debugfs_exit(struct dwc3 *d); #else +static inline void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep) +{ } static inline void dwc3_debugfs_init(struct dwc3 *d) { } static inline void dwc3_debugfs_exit(struct dwc3 *d) diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index 7146ee2ac057..5dbbe53269d3 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -886,30 +886,14 @@ static void dwc3_debugfs_create_endpoint_files(struct dwc3_ep *dep, } } -static void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep, - struct dentry *parent) +void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep) { struct dentry *dir; - dir = debugfs_create_dir(dep->name, parent); + dir = debugfs_create_dir(dep->name, dep->dwc->root); dwc3_debugfs_create_endpoint_files(dep, dir); } -static void dwc3_debugfs_create_endpoint_dirs(struct dwc3 *dwc, - struct dentry *parent) -{ - int i; - - for (i = 0; i < dwc->num_eps; i++) { - struct dwc3_ep *dep = dwc->eps[i]; - - if (!dep) - continue; - - dwc3_debugfs_create_endpoint_dir(dep, parent); - } -} - void dwc3_debugfs_init(struct dwc3 *dwc) { struct dentry *root; @@ -940,7 +924,6 @@ void dwc3_debugfs_init(struct dwc3 *dwc) &dwc3_testmode_fops); debugfs_create_file("link_state", 0644, root, dwc, &dwc3_link_state_fops); - dwc3_debugfs_create_endpoint_dirs(dwc, root); } } diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c index bdf1f98dfad8..ffe301d6ea35 100644 --- a/drivers/usb/dwc3/dwc3-meson-g12a.c +++ b/drivers/usb/dwc3/dwc3-meson-g12a.c @@ -651,7 +651,7 @@ static int dwc3_meson_g12a_setup_regmaps(struct dwc3_meson_g12a *priv, return PTR_ERR(priv->usb_glue_regmap); /* Create a regmap for each USB2 PHY control register set */ - for (i = 0; i < priv->usb2_ports; i++) { + for (i = 0; i < priv->drvdata->num_phys; i++) { struct regmap_config u2p_regmap_config = { .reg_bits = 8, .val_bits = 32, @@ -659,6 +659,9 @@ static int dwc3_meson_g12a_setup_regmaps(struct dwc3_meson_g12a *priv, .max_register = U2P_R1, }; + if (!strstr(priv->drvdata->phy_names[i], "usb2")) + continue; + u2p_regmap_config.name = devm_kasprintf(priv->dev, GFP_KERNEL, "u2p-%d", i); if (!u2p_regmap_config.name) @@ -772,13 +775,13 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev) ret = priv->drvdata->usb_init(priv); if (ret) - goto err_disable_clks; + goto err_disable_regulator; /* Init PHYs */ for (i = 0 ; i < PHY_COUNT ; ++i) { ret = phy_init(priv->phys[i]); if (ret) - goto err_disable_clks; + goto err_disable_regulator; } /* Set PHY Power */ @@ -816,6 +819,10 @@ err_phys_exit: for (i = 0 ; i < PHY_COUNT ; ++i) phy_exit(priv->phys[i]); +err_disable_regulator: + if (priv->vbus) + regulator_disable(priv->vbus); + err_disable_clks: clk_bulk_disable_unprepare(priv->drvdata->num_clks, priv->drvdata->clks); diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 8b668ef46f7f..3cd294264372 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -292,6 +292,9 @@ static struct dwc3_ep *dwc3_wIndex_to_dep(struct dwc3 *dwc, __le16 wIndex_le) epnum |= 1; dep = dwc->eps[epnum]; + if (dep == NULL) + return NULL; + if (dep->flags & DWC3_EP_ENABLED) return dep; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 49ca5da5e279..f14c2aa83759 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1244,6 +1244,7 @@ static int dwc3_prepare_trbs_sg(struct dwc3_ep *dep, req->start_sg = sg_next(s); req->num_queued_sgs++; + req->num_pending_sgs--; /* * The number of pending SG entries may not correspond to the @@ -1251,7 +1252,7 @@ static int dwc3_prepare_trbs_sg(struct dwc3_ep *dep, * don't include unused SG entries. */ if (length == 0) { - req->num_pending_sgs -= req->request.num_mapped_sgs - req->num_queued_sgs; + req->num_pending_sgs = 0; break; } @@ -2260,13 +2261,10 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) } /* - * Synchronize any pending event handling before executing the controller - * halt routine. + * Synchronize and disable any further event handling while controller + * is being enabled/disabled. */ - if (!is_on) { - dwc3_gadget_disable_irq(dwc); - synchronize_irq(dwc->irq_gadget); - } + disable_irq(dwc->irq_gadget); spin_lock_irqsave(&dwc->lock, flags); @@ -2304,6 +2302,8 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) ret = dwc3_gadget_run_stop(dwc, is_on, false); spin_unlock_irqrestore(&dwc->lock, flags); + enable_irq(dwc->irq_gadget); + pm_runtime_put(dwc->dev); return ret; @@ -2753,6 +2753,8 @@ static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum) INIT_LIST_HEAD(&dep->started_list); INIT_LIST_HEAD(&dep->cancelled_list); + dwc3_debugfs_create_endpoint_dir(dep); + return 0; } @@ -2796,6 +2798,7 @@ static void dwc3_gadget_free_endpoints(struct dwc3 *dwc) list_del(&dep->endpoint.ep_list); } + debugfs_remove_recursive(debugfs_lookup(dep->name, dwc->root)); kfree(dep); } } @@ -2873,15 +2876,15 @@ static int dwc3_gadget_ep_reclaim_trb_sg(struct dwc3_ep *dep, struct dwc3_trb *trb = &dep->trb_pool[dep->trb_dequeue]; struct scatterlist *sg = req->sg; struct scatterlist *s; - unsigned int pending = req->num_pending_sgs; + unsigned int num_queued = req->num_queued_sgs; unsigned int i; int ret = 0; - for_each_sg(sg, s, pending, i) { + for_each_sg(sg, s, num_queued, i) { trb = &dep->trb_pool[dep->trb_dequeue]; req->sg = sg_next(s); - req->num_pending_sgs--; + req->num_queued_sgs--; ret = dwc3_gadget_ep_reclaim_completed_trb(dep, req, trb, event, status, true); @@ -2904,7 +2907,7 @@ static int dwc3_gadget_ep_reclaim_trb_linear(struct dwc3_ep *dep, static bool dwc3_gadget_ep_request_completed(struct dwc3_request *req) { - return req->num_pending_sgs == 0; + return req->num_pending_sgs == 0 && req->num_queued_sgs == 0; } static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, @@ -2913,7 +2916,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, { int ret; - if (req->num_pending_sgs) + if (req->request.num_mapped_sgs) ret = dwc3_gadget_ep_reclaim_trb_sg(dep, req, event, status); else @@ -4045,6 +4048,7 @@ err5: dwc3_gadget_free_endpoints(dwc); err4: usb_put_gadget(dwc->gadget); + dwc->gadget = NULL; err3: dma_free_coherent(dwc->sysdev, DWC3_BOUNCE_SIZE, dwc->bounce, dwc->bounce_addr); @@ -4064,6 +4068,9 @@ err0: void dwc3_gadget_exit(struct dwc3 *dwc) { + if (!dwc->gadget) + return; + usb_del_gadget(dwc->gadget); dwc3_gadget_free_endpoints(dwc); usb_put_gadget(dwc->gadget); diff --git a/drivers/usb/gadget/config.c b/drivers/usb/gadget/config.c index 8bb25773b61e..05507606b2b4 100644 --- a/drivers/usb/gadget/config.c +++ b/drivers/usb/gadget/config.c @@ -164,6 +164,14 @@ int usb_assign_descriptors(struct usb_function *f, { struct usb_gadget *g = f->config->cdev->gadget; + /* super-speed-plus descriptor falls back to super-speed one, + * if such a descriptor was provided, thus avoiding a NULL + * pointer dereference if a 5gbps capable gadget is used with + * a 10gbps capable config (device port + cable + host port) + */ + if (!ssp) + ssp = ss; + if (fs) { f->fs_descriptors = usb_copy_descriptors(fs); if (!f->fs_descriptors) diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c index 7f5cf488b2b1..ffe2486fce71 100644 --- a/drivers/usb/gadget/function/f_ecm.c +++ b/drivers/usb/gadget/function/f_ecm.c @@ -791,7 +791,7 @@ ecm_bind(struct usb_configuration *c, struct usb_function *f) fs_ecm_notify_desc.bEndpointAddress; status = usb_assign_descriptors(f, ecm_fs_function, ecm_hs_function, - ecm_ss_function, NULL); + ecm_ss_function, ecm_ss_function); if (status) goto fail; diff --git a/drivers/usb/gadget/function/f_eem.c b/drivers/usb/gadget/function/f_eem.c index cfcc4e81fb77..2cd9942707b4 100644 --- a/drivers/usb/gadget/function/f_eem.c +++ b/drivers/usb/gadget/function/f_eem.c @@ -302,7 +302,7 @@ static int eem_bind(struct usb_configuration *c, struct usb_function *f) eem_ss_out_desc.bEndpointAddress = eem_fs_out_desc.bEndpointAddress; status = usb_assign_descriptors(f, eem_fs_function, eem_hs_function, - eem_ss_function, NULL); + eem_ss_function, eem_ss_function); if (status) goto fail; @@ -495,7 +495,7 @@ static int eem_unwrap(struct gether *port, skb2 = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb2)) { DBG(cdev, "unable to unframe EEM packet\n"); - continue; + goto next; } skb_trim(skb2, len - ETH_FCS_LEN); @@ -505,7 +505,7 @@ static int eem_unwrap(struct gether *port, GFP_ATOMIC); if (unlikely(!skb3)) { dev_kfree_skb_any(skb2); - continue; + goto next; } dev_kfree_skb_any(skb2); skb_queue_tail(list, skb3); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index bf109191659a..d4844afeaffc 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3567,6 +3567,9 @@ static void ffs_func_unbind(struct usb_configuration *c, ffs->func = NULL; } + /* Drain any pending AIO completions */ + drain_workqueue(ffs->io_completion_wq); + if (!--opts->refcnt) functionfs_unbind(ffs); diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 1125f4715830..e55699308117 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -802,7 +802,8 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) hidg_fs_out_ep_desc.bEndpointAddress; status = usb_assign_descriptors(f, hidg_fs_descriptors, - hidg_hs_descriptors, hidg_ss_descriptors, NULL); + hidg_hs_descriptors, hidg_ss_descriptors, + hidg_ss_descriptors); if (status) goto fail; diff --git a/drivers/usb/gadget/function/f_loopback.c b/drivers/usb/gadget/function/f_loopback.c index b56ad7c3838b..ae41f556eb75 100644 --- a/drivers/usb/gadget/function/f_loopback.c +++ b/drivers/usb/gadget/function/f_loopback.c @@ -207,7 +207,7 @@ autoconf_fail: ss_loop_sink_desc.bEndpointAddress = fs_loop_sink_desc.bEndpointAddress; ret = usb_assign_descriptors(f, fs_loopback_descs, hs_loopback_descs, - ss_loopback_descs, NULL); + ss_loopback_descs, ss_loopback_descs); if (ret) return ret; diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 019bea8e09cc..855127249f24 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -583,7 +583,7 @@ static void ncm_do_notify(struct f_ncm *ncm) data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget)); data[1] = data[0]; - DBG(cdev, "notify speed %d\n", ncm_bitrate(cdev->gadget)); + DBG(cdev, "notify speed %u\n", ncm_bitrate(cdev->gadget)); ncm->notify_state = NCM_NOTIFY_CONNECT; break; } @@ -1101,11 +1101,11 @@ static struct sk_buff *ncm_wrap_ntb(struct gether *port, ncm->ndp_dgram_count = 1; /* Note: we skip opts->next_ndp_index */ - } - /* Delay the timer. */ - hrtimer_start(&ncm->task_timer, TX_TIMEOUT_NSECS, - HRTIMER_MODE_REL_SOFT); + /* Start the timer. */ + hrtimer_start(&ncm->task_timer, TX_TIMEOUT_NSECS, + HRTIMER_MODE_REL_SOFT); + } /* Add the datagram position entries */ ntb_ndp = skb_put_zero(ncm->skb_tx_ndp, dgram_idx_len); diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index f47fdc1fa7f1..59d382fe1bbf 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -1101,7 +1101,8 @@ autoconf_fail: ss_ep_out_desc.bEndpointAddress = fs_ep_out_desc.bEndpointAddress; ret = usb_assign_descriptors(f, fs_printer_function, - hs_printer_function, ss_printer_function, NULL); + hs_printer_function, ss_printer_function, + ss_printer_function); if (ret) return ret; diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c index 0739b05a0ef7..ee95e8f5f9d4 100644 --- a/drivers/usb/gadget/function/f_rndis.c +++ b/drivers/usb/gadget/function/f_rndis.c @@ -789,7 +789,7 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f) ss_notify_desc.bEndpointAddress = fs_notify_desc.bEndpointAddress; status = usb_assign_descriptors(f, eth_fs_function, eth_hs_function, - eth_ss_function, NULL); + eth_ss_function, eth_ss_function); if (status) goto fail; diff --git a/drivers/usb/gadget/function/f_serial.c b/drivers/usb/gadget/function/f_serial.c index e62713846350..1ed8ff0ac2d3 100644 --- a/drivers/usb/gadget/function/f_serial.c +++ b/drivers/usb/gadget/function/f_serial.c @@ -233,7 +233,7 @@ static int gser_bind(struct usb_configuration *c, struct usb_function *f) gser_ss_out_desc.bEndpointAddress = gser_fs_out_desc.bEndpointAddress; status = usb_assign_descriptors(f, gser_fs_function, gser_hs_function, - gser_ss_function, NULL); + gser_ss_function, gser_ss_function); if (status) goto fail; dev_dbg(&cdev->gadget->dev, "generic ttyGS%d: %s speed IN/%s OUT/%s\n", diff --git a/drivers/usb/gadget/function/f_sourcesink.c b/drivers/usb/gadget/function/f_sourcesink.c index 5a201ba7b155..1abf08e5164a 100644 --- a/drivers/usb/gadget/function/f_sourcesink.c +++ b/drivers/usb/gadget/function/f_sourcesink.c @@ -431,7 +431,8 @@ no_iso: ss_iso_sink_desc.bEndpointAddress = fs_iso_sink_desc.bEndpointAddress; ret = usb_assign_descriptors(f, fs_source_sink_descs, - hs_source_sink_descs, ss_source_sink_descs, NULL); + hs_source_sink_descs, ss_source_sink_descs, + ss_source_sink_descs); if (ret) return ret; diff --git a/drivers/usb/gadget/function/f_subset.c b/drivers/usb/gadget/function/f_subset.c index 4d945254905d..51c1cae162d9 100644 --- a/drivers/usb/gadget/function/f_subset.c +++ b/drivers/usb/gadget/function/f_subset.c @@ -358,7 +358,7 @@ geth_bind(struct usb_configuration *c, struct usb_function *f) fs_subset_out_desc.bEndpointAddress; status = usb_assign_descriptors(f, fs_eth_function, hs_eth_function, - ss_eth_function, NULL); + ss_eth_function, ss_eth_function); if (status) goto fail; diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 7acb507946e6..de161ee0b1f9 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -2057,7 +2057,8 @@ static int tcm_bind(struct usb_configuration *c, struct usb_function *f) uasp_fs_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress; ret = usb_assign_descriptors(f, uasp_fs_function_desc, - uasp_hs_function_desc, uasp_ss_function_desc, NULL); + uasp_hs_function_desc, uasp_ss_function_desc, + uasp_ss_function_desc); if (ret) goto ep_fail; diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 0c418ce50ba0..f1b35a39d1ba 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -1488,7 +1488,7 @@ static void usb3_start_pipen(struct renesas_usb3_ep *usb3_ep, struct renesas_usb3_request *usb3_req) { struct renesas_usb3 *usb3 = usb3_ep_to_usb3(usb3_ep); - struct renesas_usb3_request *usb3_req_first = usb3_get_request(usb3_ep); + struct renesas_usb3_request *usb3_req_first; unsigned long flags; int ret = -EAGAIN; u32 enable_bits = 0; @@ -1496,7 +1496,8 @@ static void usb3_start_pipen(struct renesas_usb3_ep *usb3_ep, spin_lock_irqsave(&usb3->lock, flags); if (usb3_ep->halt || usb3_ep->started) goto out; - if (usb3_req != usb3_req_first) + usb3_req_first = __usb3_get_request(usb3_ep); + if (!usb3_req_first || usb3_req != usb3_req_first) goto out; if (usb3_pn_change(usb3, usb3_ep->num) < 0) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 7bc18cf8042c..18c2bbddf080 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -59,6 +59,7 @@ #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI 0x461e +#define PCI_DEVICE_ID_AMD_RENOIR_XHCI 0x1639 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba #define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb @@ -182,6 +183,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_1))) xhci->quirks |= XHCI_U2_DISABLE_WAKE; + if (pdev->vendor == PCI_VENDOR_ID_AMD && + pdev->device == PCI_DEVICE_ID_AMD_RENOIR_XHCI) + xhci->quirks |= XHCI_BROKEN_D3COLD; + if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; @@ -539,7 +544,7 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) * Systems with the TI redriver that loses port status change events * need to have the registers polled during D3, so avoid D3cold. */ - if (xhci->quirks & XHCI_COMP_MODE_QUIRK) + if (xhci->quirks & (XHCI_COMP_MODE_QUIRK | XHCI_BROKEN_D3COLD)) pci_d3cold_disable(pdev); if (xhci->quirks & XHCI_PME_STUCK_QUIRK) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index a8e4189277da..6acd2329e08d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -828,14 +828,10 @@ static void xhci_giveback_invalidated_tds(struct xhci_virt_ep *ep) list_for_each_entry_safe(td, tmp_td, &ep->cancelled_td_list, cancelled_td_list) { - /* - * Doesn't matter what we pass for status, since the core will - * just overwrite it (because the URB has been unlinked). - */ ring = xhci_urb_to_transfer_ring(ep->xhci, td->urb); if (td->cancel_status == TD_CLEARED) - xhci_td_cleanup(ep->xhci, td, ring, 0); + xhci_td_cleanup(ep->xhci, td, ring, td->status); if (ep->xhci->xhc_state & XHCI_STATE_DYING) return; @@ -937,14 +933,18 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) continue; } /* - * If ring stopped on the TD we need to cancel, then we have to + * If a ring stopped on the TD we need to cancel then we have to * move the xHC endpoint ring dequeue pointer past this TD. + * Rings halted due to STALL may show hw_deq is past the stalled + * TD, but still require a set TR Deq command to flush xHC cache. */ hw_deq = xhci_get_hw_deq(xhci, ep->vdev, ep->ep_index, td->urb->stream_id); hw_deq &= ~0xf; - if (trb_in_td(xhci, td->start_seg, td->first_trb, + if (td->cancel_status == TD_HALTED) { + cached_td = td; + } else if (trb_in_td(xhci, td->start_seg, td->first_trb, td->last_trb, hw_deq, false)) { switch (td->cancel_status) { case TD_CLEARED: /* TD is already no-op */ diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 2595a8f057c4..e417f5ce13d1 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1892,6 +1892,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) +#define XHCI_BROKEN_D3COLD BIT_ULL(41) unsigned int num_active_eps; unsigned int limit_active_eps; diff --git a/drivers/usb/misc/brcmstb-usb-pinmap.c b/drivers/usb/misc/brcmstb-usb-pinmap.c index b3cfe8666ea7..336653091e3b 100644 --- a/drivers/usb/misc/brcmstb-usb-pinmap.c +++ b/drivers/usb/misc/brcmstb-usb-pinmap.c @@ -263,6 +263,8 @@ static int __init brcmstb_usb_pinmap_probe(struct platform_device *pdev) return -EINVAL; r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!r) + return -EINVAL; pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata) + diff --git a/drivers/usb/misc/trancevibrator.c b/drivers/usb/misc/trancevibrator.c index a3dfc77578ea..26baba3ab7d7 100644 --- a/drivers/usb/misc/trancevibrator.c +++ b/drivers/usb/misc/trancevibrator.c @@ -61,9 +61,9 @@ static ssize_t speed_store(struct device *dev, struct device_attribute *attr, /* Set speed */ retval = usb_control_msg(tv->udev, usb_sndctrlpipe(tv->udev, 0), 0x01, /* vendor request: set speed */ - USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_OTHER, + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_OTHER, tv->speed, /* speed value */ - 0, NULL, 0, USB_CTRL_GET_TIMEOUT); + 0, NULL, 0, USB_CTRL_SET_TIMEOUT); if (retval) { tv->speed = old; dev_dbg(&tv->udev->dev, "retval = %d\n", retval); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index b5d661644263..748139d26263 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -736,6 +736,7 @@ static int uss720_probe(struct usb_interface *intf, parport_announce_port(pp); usb_set_intfdata(intf, pp); + usb_put_dev(usbdev); return 0; probe_abort: diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 8f09a387b773..4c8f0112481f 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2009,9 +2009,8 @@ static void musb_pm_runtime_check_session(struct musb *musb) schedule_delayed_work(&musb->irq_work, msecs_to_jiffies(1000)); musb->quirk_retries--; - break; } - fallthrough; + break; case MUSB_QUIRK_B_INVALID_VBUS_91: if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb, diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index ee595d1bea0a..fcb812bc832c 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -252,9 +252,11 @@ struct cp210x_serial_private { u8 gpio_input; #endif u8 partnum; + u32 fw_version; speed_t min_speed; speed_t max_speed; bool use_actual_rate; + bool no_flow_control; }; enum cp210x_event_state { @@ -398,6 +400,7 @@ struct cp210x_special_chars { /* CP210X_VENDOR_SPECIFIC values */ #define CP210X_READ_2NCONFIG 0x000E +#define CP210X_GET_FW_VER_2N 0x0010 #define CP210X_READ_LATCH 0x00C2 #define CP210X_GET_PARTNUM 0x370B #define CP210X_GET_PORTCONFIG 0x370C @@ -537,6 +540,12 @@ struct cp210x_single_port_config { #define CP210X_2NCONFIG_GPIO_RSTLATCH_IDX 587 #define CP210X_2NCONFIG_GPIO_CONTROL_IDX 600 +/* CP2102N QFN20 port configuration values */ +#define CP2102N_QFN20_GPIO2_TXLED_MODE BIT(2) +#define CP2102N_QFN20_GPIO3_RXLED_MODE BIT(3) +#define CP2102N_QFN20_GPIO1_RS485_MODE BIT(4) +#define CP2102N_QFN20_GPIO0_CLK_MODE BIT(6) + /* CP210X_VENDOR_SPECIFIC, CP210X_WRITE_LATCH call writes these 0x2 bytes. */ struct cp210x_gpio_write { u8 mask; @@ -1122,6 +1131,7 @@ static bool cp210x_termios_change(const struct ktermios *a, const struct ktermio static void cp210x_set_flow_control(struct tty_struct *tty, struct usb_serial_port *port, struct ktermios *old_termios) { + struct cp210x_serial_private *priv = usb_get_serial_data(port->serial); struct cp210x_port_private *port_priv = usb_get_serial_port_data(port); struct cp210x_special_chars chars; struct cp210x_flow_ctl flow_ctl; @@ -1129,6 +1139,15 @@ static void cp210x_set_flow_control(struct tty_struct *tty, u32 ctl_hs; int ret; + /* + * Some CP2102N interpret ulXonLimit as ulFlowReplace (erratum + * CP2102N_E104). Report back that flow control is not supported. + */ + if (priv->no_flow_control) { + tty->termios.c_cflag &= ~CRTSCTS; + tty->termios.c_iflag &= ~(IXON | IXOFF); + } + if (old_termios && C_CRTSCTS(tty) == (old_termios->c_cflag & CRTSCTS) && I_IXON(tty) == (old_termios->c_iflag & IXON) && @@ -1185,19 +1204,20 @@ static void cp210x_set_flow_control(struct tty_struct *tty, port_priv->crtscts = false; } - if (I_IXOFF(tty)) + if (I_IXOFF(tty)) { flow_repl |= CP210X_SERIAL_AUTO_RECEIVE; - else + + flow_ctl.ulXonLimit = cpu_to_le32(128); + flow_ctl.ulXoffLimit = cpu_to_le32(128); + } else { flow_repl &= ~CP210X_SERIAL_AUTO_RECEIVE; + } if (I_IXON(tty)) flow_repl |= CP210X_SERIAL_AUTO_TRANSMIT; else flow_repl &= ~CP210X_SERIAL_AUTO_TRANSMIT; - flow_ctl.ulXonLimit = cpu_to_le32(128); - flow_ctl.ulXoffLimit = cpu_to_le32(128); - dev_dbg(&port->dev, "%s - ctrl = 0x%02x, flow = 0x%02x\n", __func__, ctl_hs, flow_repl); @@ -1733,7 +1753,19 @@ static int cp2102n_gpioconf_init(struct usb_serial *serial) priv->gpio_pushpull = (gpio_pushpull >> 3) & 0x0f; /* 0 indicates GPIO mode, 1 is alternate function */ - priv->gpio_altfunc = (gpio_ctrl >> 2) & 0x0f; + if (priv->partnum == CP210X_PARTNUM_CP2102N_QFN20) { + /* QFN20 is special... */ + if (gpio_ctrl & CP2102N_QFN20_GPIO0_CLK_MODE) /* GPIO 0 */ + priv->gpio_altfunc |= BIT(0); + if (gpio_ctrl & CP2102N_QFN20_GPIO1_RS485_MODE) /* GPIO 1 */ + priv->gpio_altfunc |= BIT(1); + if (gpio_ctrl & CP2102N_QFN20_GPIO2_TXLED_MODE) /* GPIO 2 */ + priv->gpio_altfunc |= BIT(2); + if (gpio_ctrl & CP2102N_QFN20_GPIO3_RXLED_MODE) /* GPIO 3 */ + priv->gpio_altfunc |= BIT(3); + } else { + priv->gpio_altfunc = (gpio_ctrl >> 2) & 0x0f; + } if (priv->partnum == CP210X_PARTNUM_CP2102N_QFN28) { /* @@ -1908,6 +1940,45 @@ static void cp210x_init_max_speed(struct usb_serial *serial) priv->use_actual_rate = use_actual_rate; } +static int cp210x_get_fw_version(struct usb_serial *serial, u16 value) +{ + struct cp210x_serial_private *priv = usb_get_serial_data(serial); + u8 ver[3]; + int ret; + + ret = cp210x_read_vendor_block(serial, REQTYPE_DEVICE_TO_HOST, value, + ver, sizeof(ver)); + if (ret) + return ret; + + dev_dbg(&serial->interface->dev, "%s - %d.%d.%d\n", __func__, + ver[0], ver[1], ver[2]); + + priv->fw_version = ver[0] << 16 | ver[1] << 8 | ver[2]; + + return 0; +} + +static void cp210x_determine_quirks(struct usb_serial *serial) +{ + struct cp210x_serial_private *priv = usb_get_serial_data(serial); + int ret; + + switch (priv->partnum) { + case CP210X_PARTNUM_CP2102N_QFN28: + case CP210X_PARTNUM_CP2102N_QFN24: + case CP210X_PARTNUM_CP2102N_QFN20: + ret = cp210x_get_fw_version(serial, CP210X_GET_FW_VER_2N); + if (ret) + break; + if (priv->fw_version <= 0x10004) + priv->no_flow_control = true; + break; + default: + break; + } +} + static int cp210x_attach(struct usb_serial *serial) { int result; @@ -1928,6 +1999,7 @@ static int cp210x_attach(struct usb_serial *serial) usb_set_serial_data(serial, priv); + cp210x_determine_quirks(serial); cp210x_init_max_speed(serial); result = cp210x_gpio_init(serial); diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 6f2659e59b2e..4a1f3a95d017 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -611,6 +611,7 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLX_PLUS_PID) }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORION_IO_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONMX_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX2_PID) }, @@ -1034,6 +1035,9 @@ static const struct usb_device_id id_table_combined[] = { /* Sienna devices */ { USB_DEVICE(FTDI_VID, FTDI_SIENNA_PID) }, { USB_DEVICE(ECHELON_VID, ECHELON_U20_PID) }, + /* IDS GmbH devices */ + { USB_DEVICE(IDS_VID, IDS_SI31A_PID) }, + { USB_DEVICE(IDS_VID, IDS_CM31A_PID) }, /* U-Blox devices */ { USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ZED_PID) }, { USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ODIN_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 3d47c6d72256..add602bebd82 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -581,6 +581,7 @@ #define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ #define FTDI_NT_ORIONLX_PLUS_PID 0x7c91 /* OrionLX+ Substation Automation Platform */ #define FTDI_NT_ORION_IO_PID 0x7c92 /* Orion I/O */ +#define FTDI_NT_ORIONMX_PID 0x7c93 /* OrionMX */ /* * Synapse Wireless product ids (FTDI_VID) @@ -1568,6 +1569,13 @@ #define UNJO_ISODEBUG_V1_PID 0x150D /* + * IDS GmbH + */ +#define IDS_VID 0x2CAF +#define IDS_SI31A_PID 0x13A2 +#define IDS_CM31A_PID 0x13A3 + +/* * U-Blox products (http://www.u-blox.com). */ #define UBLOX_VID 0x1546 diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c index 83c62f920c50..41f1b872d277 100644 --- a/drivers/usb/serial/omninet.c +++ b/drivers/usb/serial/omninet.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * USB ZyXEL omni.net LCD PLUS driver + * USB ZyXEL omni.net driver * * Copyright (C) 2013,2017 Johan Hovold <johan@kernel.org> * @@ -22,10 +22,11 @@ #include <linux/usb/serial.h> #define DRIVER_AUTHOR "Alessandro Zummo" -#define DRIVER_DESC "USB ZyXEL omni.net LCD PLUS Driver" +#define DRIVER_DESC "USB ZyXEL omni.net Driver" #define ZYXEL_VENDOR_ID 0x0586 #define ZYXEL_OMNINET_ID 0x1000 +#define ZYXEL_OMNI_56K_PLUS_ID 0x1500 /* This one seems to be a re-branded ZyXEL device */ #define BT_IGNITIONPRO_ID 0x2000 @@ -40,6 +41,7 @@ static void omninet_port_remove(struct usb_serial_port *port); static const struct usb_device_id id_table[] = { { USB_DEVICE(ZYXEL_VENDOR_ID, ZYXEL_OMNINET_ID) }, + { USB_DEVICE(ZYXEL_VENDOR_ID, ZYXEL_OMNI_56K_PLUS_ID) }, { USB_DEVICE(ZYXEL_VENDOR_ID, BT_IGNITIONPRO_ID) }, { } /* Terminating entry */ }; @@ -50,7 +52,7 @@ static struct usb_serial_driver zyxel_omninet_device = { .owner = THIS_MODULE, .name = "omninet", }, - .description = "ZyXEL - omni.net lcd plus usb", + .description = "ZyXEL - omni.net usb", .id_table = id_table, .num_bulk_out = 2, .calc_num_ports = omninet_calc_num_ports, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 3e79a543d3e7..7608584ef4fe 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1240,6 +1240,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1901, 0xff), /* Telit LN940 (MBIM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x7010, 0xff), /* Telit LE910-S1 (RNDIS) */ + .driver_info = NCTRL(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x7011, 0xff), /* Telit LE910-S1 (ECM) */ + .driver_info = NCTRL(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */ .driver_info = NCTRL(0) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index fd773d252691..940050c31482 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -113,6 +113,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) }, { USB_DEVICE(SANWA_VENDOR_ID, SANWA_PRODUCT_ID) }, { USB_DEVICE(ADLINK_VENDOR_ID, ADLINK_ND6530_PRODUCT_ID) }, + { USB_DEVICE(ADLINK_VENDOR_ID, ADLINK_ND6530GC_PRODUCT_ID) }, { USB_DEVICE(SMART_VENDOR_ID, SMART_PRODUCT_ID) }, { USB_DEVICE(AT_VENDOR_ID, AT_VTKIT3_PRODUCT_ID) }, { } /* Terminating entry */ diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index 0f681ddbfd28..6097ee8fccb2 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -158,6 +158,7 @@ /* ADLINK ND-6530 RS232,RS485 and RS422 adapter */ #define ADLINK_VENDOR_ID 0x0b63 #define ADLINK_ND6530_PRODUCT_ID 0x6530 +#define ADLINK_ND6530GC_PRODUCT_ID 0x653a /* SMART USB Serial Adapter */ #define SMART_VENDOR_ID 0x0b8c diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c index 5f2e7f668e68..067690dac24c 100644 --- a/drivers/usb/serial/quatech2.c +++ b/drivers/usb/serial/quatech2.c @@ -416,7 +416,7 @@ static void qt2_close(struct usb_serial_port *port) /* flush the port transmit buffer */ i = usb_control_msg(serial->dev, - usb_rcvctrlpipe(serial->dev, 0), + usb_sndctrlpipe(serial->dev, 0), QT2_FLUSH_DEVICE, 0x40, 1, port_priv->device_port, NULL, 0, QT2_USB_TIMEOUT); @@ -426,7 +426,7 @@ static void qt2_close(struct usb_serial_port *port) /* flush the port receive buffer */ i = usb_control_msg(serial->dev, - usb_rcvctrlpipe(serial->dev, 0), + usb_sndctrlpipe(serial->dev, 0), QT2_FLUSH_DEVICE, 0x40, 0, port_priv->device_port, NULL, 0, QT2_USB_TIMEOUT); @@ -639,7 +639,7 @@ static int qt2_attach(struct usb_serial *serial) int status; /* power on unit */ - status = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0), + status = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), 0xc2, 0x40, 0x8000, 0, NULL, 0, QT2_USB_TIMEOUT); if (status < 0) { diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index caa46ac23db9..310db5abea9d 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -37,6 +37,7 @@ /* Vendor and product ids */ #define TI_VENDOR_ID 0x0451 #define IBM_VENDOR_ID 0x04b3 +#define STARTECH_VENDOR_ID 0x14b0 #define TI_3410_PRODUCT_ID 0x3410 #define IBM_4543_PRODUCT_ID 0x4543 #define IBM_454B_PRODUCT_ID 0x454b @@ -370,6 +371,7 @@ static const struct usb_device_id ti_id_table_3410[] = { { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) }, + { USB_DEVICE(STARTECH_VENDOR_ID, TI_3410_PRODUCT_ID) }, { } /* terminator */ }; @@ -408,6 +410,7 @@ static const struct usb_device_id ti_id_table_combined[] = { { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) }, + { USB_DEVICE(STARTECH_VENDOR_ID, TI_3410_PRODUCT_ID) }, { } /* terminator */ }; diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c index 9da22ae3006c..77dabd306ba8 100644 --- a/drivers/usb/typec/mux.c +++ b/drivers/usb/typec/mux.c @@ -191,6 +191,7 @@ static void *typec_mux_match(struct fwnode_handle *fwnode, const char *id, bool match; int nval; u16 *val; + int ret; int i; /* @@ -218,10 +219,10 @@ static void *typec_mux_match(struct fwnode_handle *fwnode, const char *id, if (!val) return ERR_PTR(-ENOMEM); - nval = fwnode_property_read_u16_array(fwnode, "svid", val, nval); - if (nval < 0) { + ret = fwnode_property_read_u16_array(fwnode, "svid", val, nval); + if (ret < 0) { kfree(val); - return ERR_PTR(nval); + return ERR_PTR(ret); } for (i = 0; i < nval; i++) { @@ -238,7 +239,7 @@ find_mux: dev = class_find_device(&typec_mux_class, NULL, fwnode, mux_fwnode_match); - return dev ? to_typec_switch(dev) : ERR_PTR(-EPROBE_DEFER); + return dev ? to_typec_mux(dev) : ERR_PTR(-EPROBE_DEFER); } /** diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index 46a25b8db72e..ffa8aa12d5f1 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -582,10 +582,15 @@ static int pmc_usb_probe_iom(struct pmc_usb *pmc) acpi_dev_free_resource_list(&resource_list); if (!pmc->iom_base) { - put_device(&adev->dev); + acpi_dev_put(adev); return -ENOMEM; } + if (IS_ERR(pmc->iom_base)) { + acpi_dev_put(adev); + return PTR_ERR(pmc->iom_base); + } + pmc->iom_adev = adev; return 0; @@ -636,8 +641,10 @@ static int pmc_usb_probe(struct platform_device *pdev) break; ret = pmc_usb_register_port(pmc, i, fwnode); - if (ret) + if (ret) { + fwnode_handle_put(fwnode); goto err_remove_ports; + } } platform_set_drvdata(pdev, pmc); @@ -651,7 +658,7 @@ err_remove_ports: usb_role_switch_unregister(pmc->port[i].usb_sw); } - put_device(&pmc->iom_adev->dev); + acpi_dev_put(pmc->iom_adev); return ret; } @@ -667,7 +674,7 @@ static int pmc_usb_remove(struct platform_device *pdev) usb_role_switch_unregister(pmc->port[i].usb_sw); } - put_device(&pmc->iom_adev->dev); + acpi_dev_put(pmc->iom_adev); return 0; } diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 64133e586c64..63470cf7f4cd 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -401,6 +401,8 @@ struct tcpm_port { unsigned int nr_src_pdo; u32 snk_pdo[PDO_MAX_OBJECTS]; unsigned int nr_snk_pdo; + u32 snk_vdo_v1[VDO_MAX_OBJECTS]; + unsigned int nr_snk_vdo_v1; u32 snk_vdo[VDO_MAX_OBJECTS]; unsigned int nr_snk_vdo; @@ -1547,33 +1549,43 @@ static int tcpm_pd_svdm(struct tcpm_port *port, struct typec_altmode *adev, if (PD_VDO_VID(p[0]) != USB_SID_PD) break; - if (PD_VDO_SVDM_VER(p[0]) < svdm_version) + if (PD_VDO_SVDM_VER(p[0]) < svdm_version) { typec_partner_set_svdm_version(port->partner, PD_VDO_SVDM_VER(p[0])); - /* 6.4.4.3.1: Only respond as UFP (device) */ - if (port->data_role == TYPEC_DEVICE && + svdm_version = PD_VDO_SVDM_VER(p[0]); + } + + port->ams = DISCOVER_IDENTITY; + /* + * PD2.0 Spec 6.10.3: respond with NAK as DFP (data host) + * PD3.1 Spec 6.4.4.2.5.1: respond with NAK if "invalid field" or + * "wrong configuation" or "Unrecognized" + */ + if ((port->data_role == TYPEC_DEVICE || svdm_version >= SVDM_VER_2_0) && port->nr_snk_vdo) { - /* - * Product Type DFP and Connector Type are not defined in SVDM - * version 1.0 and shall be set to zero. - */ - if (typec_get_negotiated_svdm_version(typec) < SVDM_VER_2_0) - response[1] = port->snk_vdo[0] & ~IDH_DFP_MASK - & ~IDH_CONN_MASK; - else - response[1] = port->snk_vdo[0]; - for (i = 1; i < port->nr_snk_vdo; i++) - response[i + 1] = port->snk_vdo[i]; - rlen = port->nr_snk_vdo + 1; + if (svdm_version < SVDM_VER_2_0) { + for (i = 0; i < port->nr_snk_vdo_v1; i++) + response[i + 1] = port->snk_vdo_v1[i]; + rlen = port->nr_snk_vdo_v1 + 1; + + } else { + for (i = 0; i < port->nr_snk_vdo; i++) + response[i + 1] = port->snk_vdo[i]; + rlen = port->nr_snk_vdo + 1; + } } break; case CMD_DISCOVER_SVID: + port->ams = DISCOVER_SVIDS; break; case CMD_DISCOVER_MODES: + port->ams = DISCOVER_MODES; break; case CMD_ENTER_MODE: + port->ams = DFP_TO_UFP_ENTER_MODE; break; case CMD_EXIT_MODE: + port->ams = DFP_TO_UFP_EXIT_MODE; break; case CMD_ATTENTION: /* Attention command does not have response */ @@ -1930,6 +1942,9 @@ static void vdm_run_state_machine(struct tcpm_port *port) tcpm_log(port, "VDM Tx error, retry"); port->vdm_retries++; port->vdm_state = VDM_STATE_READY; + if (PD_VDO_SVDM(vdo_hdr) && PD_VDO_CMDT(vdo_hdr) == CMDT_INIT) + tcpm_ams_finish(port); + } else { tcpm_ams_finish(port); } break; @@ -2176,20 +2191,25 @@ static void tcpm_handle_alert(struct tcpm_port *port, const __le32 *payload, if (!type) { tcpm_log(port, "Alert message received with no type"); + tcpm_queue_message(port, PD_MSG_CTRL_NOT_SUPP); return; } /* Just handling non-battery alerts for now */ if (!(type & USB_PD_ADO_TYPE_BATT_STATUS_CHANGE)) { - switch (port->state) { - case SRC_READY: - case SNK_READY: + if (port->pwr_role == TYPEC_SOURCE) { + port->upcoming_state = GET_STATUS_SEND; + tcpm_ams_start(port, GETTING_SOURCE_SINK_STATUS); + } else { + /* + * Do not check SinkTxOk here in case the Source doesn't set its Rp to + * SinkTxOk in time. + */ + port->ams = GETTING_SOURCE_SINK_STATUS; tcpm_set_state(port, GET_STATUS_SEND, 0); - break; - default: - tcpm_queue_message(port, PD_MSG_CTRL_WAIT); - break; } + } else { + tcpm_queue_message(port, PD_MSG_CTRL_NOT_SUPP); } } @@ -2287,6 +2307,12 @@ static void tcpm_pd_data_request(struct tcpm_port *port, bool frs_enable; int ret; + if (tcpm_vdm_ams(port) && type != PD_DATA_VENDOR_DEF) { + port->vdm_state = VDM_STATE_ERR_BUSY; + tcpm_ams_finish(port); + mod_vdm_delayed_work(port, 0); + } + switch (type) { case PD_DATA_SOURCE_CAP: for (i = 0; i < cnt; i++) @@ -2417,14 +2443,22 @@ static void tcpm_pd_data_request(struct tcpm_port *port, NONE_AMS); break; case PD_DATA_VENDOR_DEF: - tcpm_handle_vdm_request(port, msg->payload, cnt); + if (tcpm_vdm_ams(port) || port->nr_snk_vdo) + tcpm_handle_vdm_request(port, msg->payload, cnt); + else if (port->negotiated_rev > PD_REV20) + tcpm_pd_handle_msg(port, PD_MSG_CTRL_NOT_SUPP, NONE_AMS); break; case PD_DATA_BIST: port->bist_request = le32_to_cpu(msg->payload[0]); tcpm_pd_handle_state(port, BIST_RX, BIST, 0); break; case PD_DATA_ALERT: - tcpm_handle_alert(port, msg->payload, cnt); + if (port->state != SRC_READY && port->state != SNK_READY) + tcpm_pd_handle_state(port, port->pwr_role == TYPEC_SOURCE ? + SRC_SOFT_RESET_WAIT_SNK_TX : SNK_SOFT_RESET, + NONE_AMS, 0); + else + tcpm_handle_alert(port, msg->payload, cnt); break; case PD_DATA_BATT_STATUS: case PD_DATA_GET_COUNTRY_INFO: @@ -2459,6 +2493,16 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port, enum pd_ctrl_msg_type type = pd_header_type_le(msg->header); enum tcpm_state next_state; + /* + * Stop VDM state machine if interrupted by other Messages while NOT_SUPP is allowed in + * VDM AMS if waiting for VDM responses and will be handled later. + */ + if (tcpm_vdm_ams(port) && type != PD_CTRL_NOT_SUPP && type != PD_CTRL_GOOD_CRC) { + port->vdm_state = VDM_STATE_ERR_BUSY; + tcpm_ams_finish(port); + mod_vdm_delayed_work(port, 0); + } + switch (type) { case PD_CTRL_GOOD_CRC: case PD_CTRL_PING: @@ -2717,7 +2761,14 @@ static void tcpm_pd_ext_msg_request(struct tcpm_port *port, enum pd_ext_msg_type type = pd_header_type_le(msg->header); unsigned int data_size = pd_ext_header_data_size_le(msg->ext_msg.header); - if (!(msg->ext_msg.header & PD_EXT_HDR_CHUNKED)) { + /* stopping VDM state machine if interrupted by other Messages */ + if (tcpm_vdm_ams(port)) { + port->vdm_state = VDM_STATE_ERR_BUSY; + tcpm_ams_finish(port); + mod_vdm_delayed_work(port, 0); + } + + if (!(le16_to_cpu(msg->ext_msg.header) & PD_EXT_HDR_CHUNKED)) { tcpm_pd_handle_msg(port, PD_MSG_CTRL_NOT_SUPP, NONE_AMS); tcpm_log(port, "Unchunked extended messages unsupported"); return; @@ -2731,24 +2782,16 @@ static void tcpm_pd_ext_msg_request(struct tcpm_port *port, switch (type) { case PD_EXT_STATUS: - /* - * If PPS related events raised then get PPS status to clear - * (see USB PD 3.0 Spec, 6.5.2.4) - */ - if (msg->ext_msg.data[USB_PD_EXT_SDB_EVENT_FLAGS] & - USB_PD_EXT_SDB_PPS_EVENTS) - tcpm_pd_handle_state(port, GET_PPS_STATUS_SEND, - GETTING_SOURCE_SINK_STATUS, 0); - - else - tcpm_pd_handle_state(port, ready_state(port), NONE_AMS, 0); - break; case PD_EXT_PPS_STATUS: - /* - * For now the PPS status message is used to clear events - * and nothing more. - */ - tcpm_pd_handle_state(port, ready_state(port), NONE_AMS, 0); + if (port->ams == GETTING_SOURCE_SINK_STATUS) { + tcpm_ams_finish(port); + tcpm_set_state(port, ready_state(port), 0); + } else { + /* unexpected Status or PPS_Status Message */ + tcpm_pd_handle_state(port, port->pwr_role == TYPEC_SOURCE ? + SRC_SOFT_RESET_WAIT_SNK_TX : SNK_SOFT_RESET, + NONE_AMS, 0); + } break; case PD_EXT_SOURCE_CAP_EXT: case PD_EXT_GET_BATT_CAP: @@ -2811,7 +2854,7 @@ static void tcpm_pd_rx_handler(struct kthread_work *work) "Data role mismatch, initiating error recovery"); tcpm_set_state(port, ERROR_RECOVERY, 0); } else { - if (msg->header & PD_HEADER_EXT_HDR) + if (le16_to_cpu(msg->header) & PD_HEADER_EXT_HDR) tcpm_pd_ext_msg_request(port, msg); else if (cnt) tcpm_pd_data_request(port, msg); @@ -5914,6 +5957,22 @@ sink: return ret; } + /* If sink-vdos is found, sink-vdos-v1 is expected for backward compatibility. */ + if (port->nr_snk_vdo) { + ret = fwnode_property_count_u32(fwnode, "sink-vdos-v1"); + if (ret < 0) + return ret; + else if (ret == 0) + return -ENODATA; + + port->nr_snk_vdo_v1 = min(ret, VDO_MAX_OBJECTS); + ret = fwnode_property_read_u32_array(fwnode, "sink-vdos-v1", + port->snk_vdo_v1, + port->nr_snk_vdo_v1); + if (ret < 0) + return ret; + } + return 0; } @@ -6279,6 +6338,11 @@ void tcpm_unregister_port(struct tcpm_port *port) { int i; + hrtimer_cancel(&port->send_discover_timer); + hrtimer_cancel(&port->enable_frs_timer); + hrtimer_cancel(&port->vdm_state_machine_timer); + hrtimer_cancel(&port->state_machine_timer); + tcpm_reset_port(port); for (i = 0; i < ARRAY_SIZE(port->port_altmode); i++) typec_unregister_altmode(port->port_altmode[i]); diff --git a/drivers/usb/typec/tcpm/wcove.c b/drivers/usb/typec/tcpm/wcove.c index 79ae63950050..5d125339687a 100644 --- a/drivers/usb/typec/tcpm/wcove.c +++ b/drivers/usb/typec/tcpm/wcove.c @@ -378,7 +378,7 @@ static int wcove_pd_transmit(struct tcpc_dev *tcpc, const u8 *data = (void *)msg; int i; - for (i = 0; i < pd_header_cnt(msg->header) * 4 + 2; i++) { + for (i = 0; i < pd_header_cnt_le(msg->header) * 4 + 2; i++) { ret = regmap_write(wcove->regmap, USBC_TX_DATA + i, data[i]); if (ret) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 1d8b7df59ff4..b7d104c80d85 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -717,8 +717,8 @@ static void ucsi_handle_connector_change(struct work_struct *work) ucsi_send_command(con->ucsi, command, NULL, 0); /* 3. ACK connector change */ - clear_bit(EVENT_PENDING, &ucsi->flags); ret = ucsi_acknowledge_connector_change(ucsi); + clear_bit(EVENT_PENDING, &ucsi->flags); if (ret) { dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret); goto out_unlock; @@ -1253,6 +1253,7 @@ err_unregister: } err_reset: + memset(&ucsi->cap, 0, sizeof(ucsi->cap)); ucsi_reset_ppm(ucsi); err: return ret; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 189e4385df40..dda5dc6f7737 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -15,6 +15,7 @@ #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> #include <linux/mlx5/mlx5_ifc_vdpa.h> +#include <linux/mlx5/mpfs.h> #include "mlx5_vdpa.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); @@ -1859,11 +1860,16 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb static void mlx5_vdpa_free(struct vdpa_device *vdev) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_net *ndev; ndev = to_mlx5_vdpa_ndev(mvdev); free_resources(ndev); + if (!is_zero_ether_addr(ndev->config.mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev)); + mlx5_mpfs_del_mac(pfmdev, ndev->config.mac); + } mlx5_vdpa_free_resources(&ndev->mvdev); mutex_destroy(&ndev->reslock); } @@ -1990,6 +1996,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) { struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev); struct virtio_net_config *config; + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_dev *mvdev; struct mlx5_vdpa_net *ndev; struct mlx5_core_dev *mdev; @@ -2023,10 +2030,17 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) if (err) goto err_mtu; + if (!is_zero_ether_addr(config->mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev)); + err = mlx5_mpfs_add_mac(pfmdev, config->mac); + if (err) + goto err_mtu; + } + mvdev->vdev.dma_dev = mdev->device; err = mlx5_vdpa_alloc_resources(&ndev->mvdev); if (err) - goto err_mtu; + goto err_mpfs; err = alloc_resources(ndev); if (err) @@ -2044,6 +2058,9 @@ err_reg: free_resources(ndev); err_res: mlx5_vdpa_free_resources(&ndev->mvdev); +err_mpfs: + if (!is_zero_ether_addr(config->mac)) + mlx5_mpfs_del_mac(pfmdev, config->mac); err_mtu: mutex_destroy(&ndev->reslock); put_device(&mvdev->vdev.dev); diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index 53ce78d7d07b..5e2e1b9a9fd3 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -2,6 +2,7 @@ config VFIO_PCI tristate "VFIO support for PCI devices" depends on VFIO && PCI && EVENTFD + depends on MMU select VFIO_VIRQFD select IRQ_BYPASS_MANAGER help diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index d57f037f65b8..70e28efbc51f 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1581,7 +1581,7 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev) if (len == 0xFF) { len = vfio_ext_cap_len(vdev, ecap, epos); if (len < 0) - return ret; + return len; } } diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 361e5b57e369..470fcf7dac56 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -291,7 +291,7 @@ err_irq: vfio_platform_regions_cleanup(vdev); err_reg: mutex_unlock(&driver_lock); - module_put(THIS_MODULE); + module_put(vdev->parent_module); return ret; } diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index a0747c35a778..a3e925a41b0d 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -2795,7 +2795,7 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu, return 0; } - size = sizeof(*cap_iovas) + (iovas * sizeof(*cap_iovas->iova_ranges)); + size = struct_size(cap_iovas, iova_ranges, iovas); cap_iovas = kzalloc(size, GFP_KERNEL); if (!cap_iovas) diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index b292887a2481..a591d291b231 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -52,6 +52,13 @@ static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; get_page(page); + + if (vmf->vma->vm_file) + page->mapping = vmf->vma->vm_file->f_mapping; + else + printk(KERN_ERR "no mapping available\n"); + + BUG_ON(!page->mapping); page->index = vmf->pgoff; vmf->page = page; @@ -144,6 +151,17 @@ static const struct vm_operations_struct fb_deferred_io_vm_ops = { .page_mkwrite = fb_deferred_io_mkwrite, }; +static int fb_deferred_io_set_page_dirty(struct page *page) +{ + if (!PageDirty(page)) + SetPageDirty(page); + return 0; +} + +static const struct address_space_operations fb_deferred_io_aops = { + .set_page_dirty = fb_deferred_io_set_page_dirty, +}; + int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma) { vma->vm_ops = &fb_deferred_io_vm_ops; @@ -194,12 +212,29 @@ void fb_deferred_io_init(struct fb_info *info) } EXPORT_SYMBOL_GPL(fb_deferred_io_init); +void fb_deferred_io_open(struct fb_info *info, + struct inode *inode, + struct file *file) +{ + file->f_mapping->a_ops = &fb_deferred_io_aops; +} +EXPORT_SYMBOL_GPL(fb_deferred_io_open); + void fb_deferred_io_cleanup(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; + struct page *page; + int i; BUG_ON(!fbdefio); cancel_delayed_work_sync(&info->deferred_work); + + /* clear out the mapping that we setup */ + for (i = 0 ; i < info->fix.smem_len; i += PAGE_SIZE) { + page = fb_deferred_io_page(info, i); + page->mapping = NULL; + } + mutex_destroy(&fbdefio->lock); } EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 072780b0e570..98f193078c05 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1415,6 +1415,10 @@ __releases(&info->lock) if (res) module_put(info->fbops->owner); } +#ifdef CONFIG_FB_DEFERRED_IO + if (info->fbdefio) + fb_deferred_io_open(info, inode, file); +#endif out: unlock_fb_info(info); if (res) diff --git a/drivers/video/fbdev/hgafb.c b/drivers/video/fbdev/hgafb.c index cc8e62ae93f6..bd3d07aa4f0e 100644 --- a/drivers/video/fbdev/hgafb.c +++ b/drivers/video/fbdev/hgafb.c @@ -558,7 +558,7 @@ static int hgafb_probe(struct platform_device *pdev) int ret; ret = hga_card_detect(); - if (!ret) + if (ret) return ret; printk(KERN_INFO "hgafb: %s with %ldK of memory detected.\n", diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index a4e9e6e07e93..d3c6bb22c5f4 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -322,6 +322,8 @@ static int afs_deliver_cb_callback(struct afs_call *call) return ret; call->unmarshall++; + fallthrough; + case 5: break; } @@ -418,6 +420,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) r->node[loop] = ntohl(b[loop + 5]); call->unmarshall++; + fallthrough; case 2: break; @@ -530,6 +533,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) r->node[loop] = ntohl(b[loop + 5]); call->unmarshall++; + fallthrough; case 2: break; @@ -663,6 +667,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + fallthrough; case 3: break; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 9fbe5a5ec9bd..78719f2f567e 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1919,7 +1919,9 @@ static void afs_rename_edit_dir(struct afs_operation *op) new_inode = d_inode(new_dentry); if (new_inode) { spin_lock(&new_inode->i_lock); - if (new_inode->i_nlink > 0) + if (S_ISDIR(new_inode->i_mode)) + clear_nlink(new_inode); + else if (new_inode->i_nlink > 0) drop_nlink(new_inode); spin_unlock(&new_inode->i_lock); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 2f695a260442..dd3f45d906d2 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -388,6 +388,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) req->file_size = vp->scb.status.size; call->unmarshall++; + fallthrough; case 5: break; @@ -1408,6 +1409,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) _debug("motd '%s'", p); call->unmarshall++; + fallthrough; case 8: break; @@ -1845,6 +1847,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) xdr_decode_AFSVolSync(&bp, &op->volsync); call->unmarshall++; + fallthrough; case 6: break; @@ -1979,6 +1982,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) xdr_decode_AFSVolSync(&bp, &op->volsync); call->unmarshall++; + fallthrough; case 4: break; diff --git a/fs/afs/main.c b/fs/afs/main.c index b2975256dadb..179004b15566 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -203,8 +203,8 @@ static int __init afs_init(void) goto error_fs; afs_proc_symlink = proc_symlink("fs/afs", NULL, "../self/net/afs"); - if (IS_ERR(afs_proc_symlink)) { - ret = PTR_ERR(afs_proc_symlink); + if (!afs_proc_symlink) { + ret = -ENOMEM; goto error_proc; } diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index dc9327332f06..00fca3c66ba6 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -593,6 +593,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) if (ret < 0) return ret; call->unmarshall = 6; + fallthrough; case 6: break; diff --git a/fs/afs/write.c b/fs/afs/write.c index 3edb6204b937..e9ccaa3baf2e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -730,7 +730,7 @@ static int afs_writepages_region(struct address_space *mapping, return ret; } - start += ret * PAGE_SIZE; + start += ret; cond_resched(); } while (wbc->nr_to_write > 0); @@ -837,6 +837,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); unsigned long priv; + vm_fault_t ret = VM_FAULT_RETRY; _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); @@ -848,14 +849,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) #ifdef CONFIG_AFS_FSCACHE if (PageFsCache(page) && wait_on_page_fscache_killable(page) < 0) - return VM_FAULT_RETRY; + goto out; #endif if (wait_on_page_writeback_killable(page)) - return VM_FAULT_RETRY; + goto out; if (lock_page_killable(page) < 0) - return VM_FAULT_RETRY; + goto out; /* We mustn't change page->private until writeback is complete as that * details the portion of the page we need to write back and we might @@ -863,7 +864,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) */ if (wait_on_page_writeback_killable(page) < 0) { unlock_page(page); - return VM_FAULT_RETRY; + goto out; } priv = afs_page_dirty(page, 0, thp_size(page)); @@ -877,8 +878,10 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) } file_update_time(file); + ret = VM_FAULT_LOCKED; +out: sb_end_pagefault(inode->i_sb); - return VM_FAULT_LOCKED; + return ret; } /* diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index aa57bdc8fc89..6d5c4e45cfef 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2442,16 +2442,16 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) spin_lock(&sinfo->lock); spin_lock(&cache->lock); if (!--cache->ro) { - num_bytes = cache->length - cache->reserved - - cache->pinned - cache->bytes_super - - cache->zone_unusable - cache->used; - sinfo->bytes_readonly -= num_bytes; if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes back */ cache->zone_unusable = cache->alloc_offset - cache->used; sinfo->bytes_zone_unusable += cache->zone_unusable; sinfo->bytes_readonly -= cache->zone_unusable; } + num_bytes = cache->length - cache->reserved - + cache->pinned - cache->bytes_super - + cache->zone_unusable - cache->used; + sinfo->bytes_readonly -= num_bytes; list_del_init(&cache->ro_list); } spin_unlock(&cache->lock); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index d17ac301032e..1346d698463a 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -457,7 +457,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bytes_left = compressed_len; for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { int submit = 0; - int len; + int len = 0; page = compressed_pages[pg_index]; page->mapping = inode->vfs_inode.i_mapping; @@ -465,10 +465,17 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); - if (pg_index == 0 && use_append) - len = bio_add_zone_append_page(bio, page, PAGE_SIZE, 0); - else - len = bio_add_page(bio, page, PAGE_SIZE, 0); + /* + * Page can only be added to bio if the current bio fits in + * stripe. + */ + if (!submit) { + if (pg_index == 0 && use_append) + len = bio_add_zone_append_page(bio, page, + PAGE_SIZE, 0); + else + len = bio_add_page(bio, page, PAGE_SIZE, 0); + } page->mapping = NULL; if (submit || len < PAGE_SIZE) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c9a3036c23bf..8d386a5587ee 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2648,6 +2648,24 @@ static int validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } + if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid, + BTRFS_FSID_SIZE)) { + btrfs_err(fs_info, + "superblock fsid doesn't match fsid of fs_devices: %pU != %pU", + fs_info->super_copy->fsid, fs_info->fs_devices->fsid); + ret = -EINVAL; + } + + if (btrfs_fs_incompat(fs_info, METADATA_UUID) && + memcmp(fs_info->fs_devices->metadata_uuid, + fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE)) { + btrfs_err(fs_info, +"superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU", + fs_info->super_copy->metadata_uuid, + fs_info->fs_devices->metadata_uuid); + ret = -EINVAL; + } + if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, @@ -3279,14 +3297,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device disk_super = fs_info->super_copy; - ASSERT(!memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid, - BTRFS_FSID_SIZE)); - - if (btrfs_fs_incompat(fs_info, METADATA_UUID)) { - ASSERT(!memcmp(fs_info->fs_devices->metadata_uuid, - fs_info->super_copy->metadata_uuid, - BTRFS_FSID_SIZE)); - } features = btrfs_super_flags(disk_super); if (features & BTRFS_SUPER_FLAG_CHANGING_FSID_V2) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f1d15b68994a..3d5c35e4cb76 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1868,7 +1868,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, trace_run_delayed_ref_head(fs_info, head, 0); btrfs_delayed_ref_unlock(head); btrfs_put_delayed_ref_head(head); - return 0; + return ret; } static struct btrfs_delayed_ref_head *btrfs_obtain_ref_head( diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 294602f139ef..441cee7fbb62 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -788,7 +788,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u64 end_byte = bytenr + len; u64 csum_end; struct extent_buffer *leaf; - int ret; + int ret = 0; const u32 csum_size = fs_info->csum_size; u32 blocksize_bits = fs_info->sectorsize_bits; @@ -806,6 +806,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) { + ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; @@ -862,7 +863,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, ret = btrfs_del_items(trans, root, path, path->slots[0], del_nr); if (ret) - goto out; + break; if (key.offset == bytenr) break; } else if (key.offset < bytenr && csum_end > end_byte) { @@ -906,8 +907,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, ret = btrfs_split_item(trans, root, path, &key, offset); if (ret && ret != -EAGAIN) { btrfs_abort_transaction(trans, ret); - goto out; + break; } + ret = 0; key.offset = end_byte - 1; } else { @@ -917,12 +919,41 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, } btrfs_release_path(path); } - ret = 0; -out: btrfs_free_path(path); return ret; } +static int find_next_csum_offset(struct btrfs_root *root, + struct btrfs_path *path, + u64 *next_offset) +{ + const u32 nritems = btrfs_header_nritems(path->nodes[0]); + struct btrfs_key found_key; + int slot = path->slots[0] + 1; + int ret; + + if (nritems == 0 || slot >= nritems) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) { + return ret; + } else if (ret > 0) { + *next_offset = (u64)-1; + return 0; + } + slot = path->slots[0]; + } + + btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); + + if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || + found_key.type != BTRFS_EXTENT_CSUM_KEY) + *next_offset = (u64)-1; + else + *next_offset = found_key.offset; + + return 0; +} + int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_ordered_sum *sums) @@ -938,7 +969,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, u64 total_bytes = 0; u64 csum_offset; u64 bytenr; - u32 nritems; u32 ins_size; int index = 0; int found_next; @@ -981,26 +1011,10 @@ again: goto insert; } } else { - int slot = path->slots[0] + 1; - /* we didn't find a csum item, insert one */ - nritems = btrfs_header_nritems(path->nodes[0]); - if (!nritems || (path->slots[0] >= nritems - 1)) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) { - goto out; - } else if (ret > 0) { - found_next = 1; - goto insert; - } - slot = path->slots[0]; - } - btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); - if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || - found_key.type != BTRFS_EXTENT_CSUM_KEY) { - found_next = 1; - goto insert; - } - next_offset = found_key.offset; + /* We didn't find a csum item, insert one. */ + ret = find_next_csum_offset(root, path, &next_offset); + if (ret < 0) + goto out; found_next = 1; goto insert; } @@ -1056,8 +1070,48 @@ extend_csum: tmp = sums->len - total_bytes; tmp >>= fs_info->sectorsize_bits; WARN_ON(tmp < 1); + extend_nr = max_t(int, 1, tmp); + + /* + * A log tree can already have checksum items with a subset of + * the checksums we are trying to log. This can happen after + * doing a sequence of partial writes into prealloc extents and + * fsyncs in between, with a full fsync logging a larger subrange + * of an extent for which a previous fast fsync logged a smaller + * subrange. And this happens in particular due to merging file + * extent items when we complete an ordered extent for a range + * covered by a prealloc extent - this is done at + * btrfs_mark_extent_written(). + * + * So if we try to extend the previous checksum item, which has + * a range that ends at the start of the range we want to insert, + * make sure we don't extend beyond the start offset of the next + * checksum item. If we are at the last item in the leaf, then + * forget the optimization of extending and add a new checksum + * item - it is not worth the complexity of releasing the path, + * getting the first key for the next leaf, repeat the btree + * search, etc, because log trees are temporary anyway and it + * would only save a few bytes of leaf space. + */ + if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) { + if (path->slots[0] + 1 >= + btrfs_header_nritems(path->nodes[0])) { + ret = find_next_csum_offset(root, path, &next_offset); + if (ret < 0) + goto out; + found_next = 1; + goto insert; + } + + ret = find_next_csum_offset(root, path, &next_offset); + if (ret < 0) + goto out; + + tmp = (next_offset - bytenr) >> fs_info->sectorsize_bits; + if (tmp <= INT_MAX) + extend_nr = min_t(int, extend_nr, tmp); + } - extend_nr = max_t(int, 1, (int)tmp); diff = (csum_offset + extend_nr) * csum_size; diff = min(diff, MAX_CSUM_ITEMS(fs_info, csum_size) * csum_size); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 3b10d98b4ebb..55f68422061d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1094,7 +1094,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, int del_nr = 0; int del_slot = 0; int recow; - int ret; + int ret = 0; u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); @@ -1315,7 +1315,7 @@ again: } out: btrfs_free_path(path); - return 0; + return ret; } /* diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 33f14573f2ec..46f392943f4d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3000,6 +3000,18 @@ out: if (ret || truncated) { u64 unwritten_start = start; + /* + * If we failed to finish this ordered extent for any reason we + * need to make sure BTRFS_ORDERED_IOERR is set on the ordered + * extent, and mark the inode with the error if it wasn't + * already set. Any error during writeback would have already + * set the mapping error, so we need to set it if we're the ones + * marking this ordered extent as failed. + */ + if (ret && !test_and_set_bit(BTRFS_ORDERED_IOERR, + &ordered_extent->flags)) + mapping_set_error(ordered_extent->inode->i_mapping, -EIO); + if (truncated) unwritten_start += logical_len; clear_extent_uptodate(io_tree, unwritten_start, end, NULL); @@ -9076,6 +9088,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, int ret2; bool root_log_pinned = false; bool dest_log_pinned = false; + bool need_abort = false; /* we only allow rename subvolume link between subvolumes */ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) @@ -9135,6 +9148,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, old_idx); if (ret) goto out_fail; + need_abort = true; } /* And now for the dest. */ @@ -9150,8 +9164,11 @@ static int btrfs_rename_exchange(struct inode *old_dir, new_ino, btrfs_ino(BTRFS_I(old_dir)), new_idx); - if (ret) + if (ret) { + if (need_abort) + btrfs_abort_transaction(trans, ret); goto out_fail; + } } /* Update inode version and ctime/mtime. */ diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index d434dc78dadf..9178da07cc9c 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -203,10 +203,7 @@ static int clone_copy_inline_extent(struct inode *dst, * inline extent's data to the page. */ ASSERT(key.offset > 0); - ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset, - inline_data, size, datal, - comp_type); - goto out; + goto copy_to_page; } } else if (i_size_read(dst) <= datal) { struct btrfs_file_extent_item *ei; @@ -222,13 +219,10 @@ static int clone_copy_inline_extent(struct inode *dst, BTRFS_FILE_EXTENT_INLINE) goto copy_inline_extent; - ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset, - inline_data, size, datal, comp_type); - goto out; + goto copy_to_page; } copy_inline_extent: - ret = 0; /* * We have no extent items, or we have an extent at offset 0 which may * or may not be inlined. All these cases are dealt the same way. @@ -240,11 +234,13 @@ copy_inline_extent: * clone. Deal with all these cases by copying the inline extent * data into the respective page at the destination inode. */ - ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset, - inline_data, size, datal, comp_type); - goto out; + goto copy_to_page; } + /* + * Release path before starting a new transaction so we don't hold locks + * that would confuse lockdep. + */ btrfs_release_path(path); /* * If we end up here it means were copy the inline extent into a leaf @@ -282,11 +278,6 @@ copy_inline_extent: out: if (!ret && !trans) { /* - * Release path before starting a new transaction so we don't - * hold locks that would confuse lockdep. - */ - btrfs_release_path(path); - /* * No transaction here means we copied the inline extent into a * page of the destination inode. * @@ -306,6 +297,21 @@ out: *trans_out = trans; return ret; + +copy_to_page: + /* + * Release our path because we don't need it anymore and also because + * copy_inline_to_page() needs to reserve data and metadata, which may + * need to flush delalloc when we are low on available space and + * therefore cause a deadlock if writeback of an inline extent needs to + * write to the same leaf or an ordered extent completion needs to write + * to the same leaf. + */ + btrfs_release_path(path); + + ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset, + inline_data, size, datal, comp_type); + goto out; } /** diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 326be57f2828..dbcf8bb2f3b9 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1574,7 +1574,9 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, if (ret) goto out; - btrfs_update_inode(trans, root, BTRFS_I(inode)); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); + if (ret) + goto out; } ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen; @@ -1749,7 +1751,9 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, if (nlink != inode->i_nlink) { set_nlink(inode, nlink); - btrfs_update_inode(trans, root, BTRFS_I(inode)); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); + if (ret) + goto out; } BTRFS_I(inode)->index_cnt = (u64)-1; @@ -1787,6 +1791,7 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, break; if (ret == 1) { + ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; @@ -1799,17 +1804,19 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, ret = btrfs_del_item(trans, root, path); if (ret) - goto out; + break; btrfs_release_path(path); inode = read_one_inode(root, key.offset); - if (!inode) - return -EIO; + if (!inode) { + ret = -EIO; + break; + } ret = fixup_inode_link_count(trans, root, inode); iput(inode); if (ret) - goto out; + break; /* * fixup on a directory may create new entries, @@ -1818,8 +1825,6 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, */ key.offset = (u64)-1; } - ret = 0; -out: btrfs_release_path(path); return ret; } @@ -3297,6 +3302,22 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, * begins and releases it only after writing its superblock. */ mutex_lock(&fs_info->tree_log_mutex); + + /* + * The previous transaction writeout phase could have failed, and thus + * marked the fs in an error state. We must not commit here, as we + * could have updated our generation in the super_for_commit and + * writing the super here would result in transid mismatches. If there + * is an error here just bail. + */ + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { + ret = -EIO; + btrfs_set_log_full_commit(trans); + btrfs_abort_transaction(trans, ret); + mutex_unlock(&fs_info->tree_log_mutex); + goto out_wake_log_root; + } + btrfs_set_super_log_root(fs_info->super_for_commit, log_root_start); btrfs_set_super_log_root_level(fs_info->super_for_commit, log_root_level); ret = write_all_supers(fs_info, 1); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 1bb8ee97aae0..f1f3b10d1dbb 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -150,6 +150,18 @@ static inline u32 sb_zone_number(int shift, int mirror) return (u32)zone; } +static inline sector_t zone_start_sector(u32 zone_number, + struct block_device *bdev) +{ + return (sector_t)zone_number << ilog2(bdev_zone_sectors(bdev)); +} + +static inline u64 zone_start_physical(u32 zone_number, + struct btrfs_zoned_device_info *zone_info) +{ + return (u64)zone_number << zone_info->zone_size_shift; +} + /* * Emulate blkdev_report_zones() for a non-zoned device. It slices up the block * device into static sized chunks and fake a conventional zone on each of @@ -405,8 +417,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) if (sb_zone + 1 >= zone_info->nr_zones) continue; - sector = sb_zone << (zone_info->zone_size_shift - SECTOR_SHIFT); - ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT, + ret = btrfs_get_dev_zones(device, + zone_start_physical(sb_zone, zone_info), &zone_info->sb_zones[sb_pos], &nr_zones); if (ret) @@ -721,7 +733,7 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, if (sb_zone + 1 >= nr_zones) return -ENOENT; - ret = blkdev_report_zones(bdev, sb_zone << zone_sectors_shift, + ret = blkdev_report_zones(bdev, zone_start_sector(sb_zone, bdev), BTRFS_NR_SB_LOG_ZONES, copy_zone_info_cb, zones); if (ret < 0) @@ -826,7 +838,7 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror) return -ENOENT; return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, - sb_zone << zone_sectors_shift, + zone_start_sector(sb_zone, bdev), zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS); } @@ -878,7 +890,8 @@ u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, if (!(end <= sb_zone || sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) { have_sb = true; - pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift; + pos = zone_start_physical( + sb_zone + BTRFS_NR_SB_LOG_ZONES, zinfo); break; } diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index 4a97fe12006b..37fc7d6ac457 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -72,15 +72,28 @@ struct smb3_key_debug_info { } __packed; /* - * Dump full key (32 byte encrypt/decrypt keys instead of 16 bytes) - * is needed if GCM256 (stronger encryption) negotiated + * Dump variable-sized keys */ struct smb3_full_key_debug_info { - __u64 Suid; + /* INPUT: size of userspace buffer */ + __u32 in_size; + + /* + * INPUT: 0 for current user, otherwise session to dump + * OUTPUT: session id that was dumped + */ + __u64 session_id; __u16 cipher_type; - __u8 auth_key[16]; /* SMB2_NTLMV2_SESSKEY_SIZE */ - __u8 smb3encryptionkey[32]; /* SMB3_ENC_DEC_KEY_SIZE */ - __u8 smb3decryptionkey[32]; /* SMB3_ENC_DEC_KEY_SIZE */ + __u8 session_key_length; + __u8 server_in_key_length; + __u8 server_out_key_length; + __u8 data[]; + /* + * return this struct with the keys appended at the end: + * __u8 session_key[session_key_length]; + * __u8 server_in_key[server_in_key_length]; + * __u8 server_out_key[server_out_key_length]; + */ } __packed; struct smb3_notify { diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index b53a87db282f..554d64fe171e 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -148,7 +148,8 @@ #define SMB3_SIGN_KEY_SIZE (16) /* - * Size of the smb3 encryption/decryption keys + * Size of the smb3 encryption/decryption key storage. + * This size is big enough to store any cipher key types. */ #define SMB3_ENC_DEC_KEY_SIZE (32) diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 28ec8d7c521a..d67d281ab863 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -33,6 +33,7 @@ #include "cifsfs.h" #include "cifs_ioctl.h" #include "smb2proto.h" +#include "smb2glob.h" #include <linux/btrfs.h> static long cifs_ioctl_query_info(unsigned int xid, struct file *filep, @@ -214,48 +215,112 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg) return 0; } -static int cifs_dump_full_key(struct cifs_tcon *tcon, unsigned long arg) +static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug_info __user *in) { - struct smb3_full_key_debug_info pfull_key_inf; - __u64 suid; - struct list_head *tmp; + struct smb3_full_key_debug_info out; struct cifs_ses *ses; + int rc = 0; bool found = false; + u8 __user *end; - if (!smb3_encryption_required(tcon)) - return -EOPNOTSUPP; + if (!smb3_encryption_required(tcon)) { + rc = -EOPNOTSUPP; + goto out; + } + + /* copy user input into our output buffer */ + if (copy_from_user(&out, in, sizeof(out))) { + rc = -EINVAL; + goto out; + } + + if (!out.session_id) { + /* if ses id is 0, use current user session */ + ses = tcon->ses; + } else { + /* otherwise if a session id is given, look for it in all our sessions */ + struct cifs_ses *ses_it = NULL; + struct TCP_Server_Info *server_it = NULL; - ses = tcon->ses; /* default to user id for current user */ - if (get_user(suid, (__u64 __user *)arg)) - suid = 0; - if (suid) { - /* search to see if there is a session with a matching SMB UID */ spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &tcon->ses->server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); - if (ses->Suid == suid) { - found = true; - break; + list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { + list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { + if (ses_it->Suid == out.session_id) { + ses = ses_it; + /* + * since we are using the session outside the crit + * section, we need to make sure it won't be released + * so increment its refcount + */ + ses->ses_count++; + found = true; + goto search_end; + } } } +search_end: spin_unlock(&cifs_tcp_ses_lock); - if (found == false) - return -EINVAL; - } /* else uses default user's SMB UID (ie current user) */ - - pfull_key_inf.cipher_type = le16_to_cpu(ses->server->cipher_type); - pfull_key_inf.Suid = ses->Suid; - memcpy(pfull_key_inf.auth_key, ses->auth_key.response, - 16 /* SMB2_NTLMV2_SESSKEY_SIZE */); - memcpy(pfull_key_inf.smb3decryptionkey, ses->smb3decryptionkey, - 32 /* SMB3_ENC_DEC_KEY_SIZE */); - memcpy(pfull_key_inf.smb3encryptionkey, - ses->smb3encryptionkey, 32 /* SMB3_ENC_DEC_KEY_SIZE */); - if (copy_to_user((void __user *)arg, &pfull_key_inf, - sizeof(struct smb3_full_key_debug_info))) - return -EFAULT; + if (!found) { + rc = -ENOENT; + goto out; + } + } - return 0; + switch (ses->server->cipher_type) { + case SMB2_ENCRYPTION_AES128_CCM: + case SMB2_ENCRYPTION_AES128_GCM: + out.session_key_length = CIFS_SESS_KEY_SIZE; + out.server_in_key_length = out.server_out_key_length = SMB3_GCM128_CRYPTKEY_SIZE; + break; + case SMB2_ENCRYPTION_AES256_CCM: + case SMB2_ENCRYPTION_AES256_GCM: + out.session_key_length = CIFS_SESS_KEY_SIZE; + out.server_in_key_length = out.server_out_key_length = SMB3_GCM256_CRYPTKEY_SIZE; + break; + default: + rc = -EOPNOTSUPP; + goto out; + } + + /* check if user buffer is big enough to store all the keys */ + if (out.in_size < sizeof(out) + out.session_key_length + out.server_in_key_length + + out.server_out_key_length) { + rc = -ENOBUFS; + goto out; + } + + out.session_id = ses->Suid; + out.cipher_type = le16_to_cpu(ses->server->cipher_type); + + /* overwrite user input with our output */ + if (copy_to_user(in, &out, sizeof(out))) { + rc = -EINVAL; + goto out; + } + + /* append all the keys at the end of the user buffer */ + end = in->data; + if (copy_to_user(end, ses->auth_key.response, out.session_key_length)) { + rc = -EINVAL; + goto out; + } + end += out.session_key_length; + + if (copy_to_user(end, ses->smb3encryptionkey, out.server_in_key_length)) { + rc = -EINVAL; + goto out; + } + end += out.server_in_key_length; + + if (copy_to_user(end, ses->smb3decryptionkey, out.server_out_key_length)) { + rc = -EINVAL; + goto out; + } + +out: + if (found) + cifs_put_smb_ses(ses); + return rc; } long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) @@ -371,6 +436,10 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) rc = -EOPNOTSUPP; break; case CIFS_DUMP_KEY: + /* + * Dump encryption keys. This is an old ioctl that only + * handles AES-128-{CCM,GCM}. + */ if (pSMBFile == NULL) break; if (!capable(CAP_SYS_ADMIN)) { @@ -398,11 +467,10 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) else rc = 0; break; - /* - * Dump full key (32 bytes instead of 16 bytes) is - * needed if GCM256 (stronger encryption) negotiated - */ case CIFS_DUMP_FULL_KEY: + /* + * Dump encryption keys (handles any key sizes) + */ if (pSMBFile == NULL) break; if (!capable(CAP_SYS_ADMIN)) { @@ -410,8 +478,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) break; } tcon = tlink_tcon(pSMBFile->tlink); - rc = cifs_dump_full_key(tcon, arg); - + rc = cifs_dump_full_key(tcon, (void __user *)arg); break; case CIFS_IOC_NOTIFY: if (!S_ISDIR(inode->i_mode)) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 9f24eb88297a..c205f93e0a10 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -958,6 +958,13 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) /* Internal types */ server->capabilities |= SMB2_NT_FIND | SMB2_LARGE_FILES; + /* + * SMB3.0 supports only 1 cipher and doesn't have a encryption neg context + * Set the cipher type manually. + */ + if (server->dialect == SMB30_PROT_ID && (server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION)) + server->cipher_type = SMB2_ENCRYPTION_AES128_CCM; + security_blob = smb2_get_data_area_len(&blob_offset, &blob_length, (struct smb2_sync_hdr *)rsp); /* diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index d6df908dccad..dafcb6ab050d 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -12,6 +12,11 @@ #include <linux/tracepoint.h> +/* + * Please use this 3-part article as a reference for writing new tracepoints: + * https://lwn.net/Articles/379903/ + */ + /* For logging errors in read or write */ DECLARE_EVENT_CLASS(smb3_rw_err_class, TP_PROTO(unsigned int xid, @@ -529,16 +534,16 @@ DECLARE_EVENT_CLASS(smb3_exit_err_class, TP_ARGS(xid, func_name, rc), TP_STRUCT__entry( __field(unsigned int, xid) - __field(const char *, func_name) + __string(func_name, func_name) __field(int, rc) ), TP_fast_assign( __entry->xid = xid; - __entry->func_name = func_name; + __assign_str(func_name, func_name); __entry->rc = rc; ), TP_printk("\t%s: xid=%u rc=%d", - __entry->func_name, __entry->xid, __entry->rc) + __get_str(func_name), __entry->xid, __entry->rc) ) #define DEFINE_SMB3_EXIT_ERR_EVENT(name) \ @@ -583,14 +588,14 @@ DECLARE_EVENT_CLASS(smb3_enter_exit_class, TP_ARGS(xid, func_name), TP_STRUCT__entry( __field(unsigned int, xid) - __field(const char *, func_name) + __string(func_name, func_name) ), TP_fast_assign( __entry->xid = xid; - __entry->func_name = func_name; + __assign_str(func_name, func_name); ), TP_printk("\t%s: xid=%u", - __entry->func_name, __entry->xid) + __get_str(func_name), __entry->xid) ) #define DEFINE_SMB3_ENTER_EXIT_EVENT(name) \ @@ -857,16 +862,16 @@ DECLARE_EVENT_CLASS(smb3_reconnect_class, TP_STRUCT__entry( __field(__u64, currmid) __field(__u64, conn_id) - __field(char *, hostname) + __string(hostname, hostname) ), TP_fast_assign( __entry->currmid = currmid; __entry->conn_id = conn_id; - __entry->hostname = hostname; + __assign_str(hostname, hostname); ), TP_printk("conn_id=0x%llx server=%s current_mid=%llu", __entry->conn_id, - __entry->hostname, + __get_str(hostname), __entry->currmid) ) @@ -891,7 +896,7 @@ DECLARE_EVENT_CLASS(smb3_credit_class, TP_STRUCT__entry( __field(__u64, currmid) __field(__u64, conn_id) - __field(char *, hostname) + __string(hostname, hostname) __field(int, credits) __field(int, credits_to_add) __field(int, in_flight) @@ -899,7 +904,7 @@ DECLARE_EVENT_CLASS(smb3_credit_class, TP_fast_assign( __entry->currmid = currmid; __entry->conn_id = conn_id; - __entry->hostname = hostname; + __assign_str(hostname, hostname); __entry->credits = credits; __entry->credits_to_add = credits_to_add; __entry->in_flight = in_flight; @@ -907,7 +912,7 @@ DECLARE_EVENT_CLASS(smb3_credit_class, TP_printk("conn_id=0x%llx server=%s current_mid=%llu " "credits=%d credit_change=%d in_flight=%d", __entry->conn_id, - __entry->hostname, + __get_str(hostname), __entry->currmid, __entry->credits, __entry->credits_to_add, diff --git a/fs/coredump.c b/fs/coredump.c index 2868e3e171ae..c3d8fc14b993 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -519,7 +519,7 @@ static bool dump_interrupted(void) * but then we need to teach dump_write() to restart and clear * TIF_SIGPENDING. */ - return signal_pending(current); + return fatal_signal_pending(current) || freezing(current); } static void wait_for_dump_helpers(struct file *file) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index e813acfaa6e8..ba7c01cd9a5d 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -893,7 +893,7 @@ ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf, copy[copy_len] = '\n'; - ret = simple_read_from_buffer(user_buf, count, ppos, copy, copy_len); + ret = simple_read_from_buffer(user_buf, count, ppos, copy, len); kfree(copy); return ret; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 1d252164d97b..8129a430d789 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -45,10 +45,13 @@ static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; static int debugfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *ia) { - int ret = security_locked_down(LOCKDOWN_DEBUGFS); + int ret; - if (ret && (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) - return ret; + if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { + ret = security_locked_down(LOCKDOWN_DEBUGFS); + if (ret) + return ret; + } return simple_setattr(&init_user_ns, dentry, ia); } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 77c84d6f1af6..cbf37b2cf871 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3206,7 +3206,10 @@ static int ext4_split_extent_at(handle_t *handle, ext4_ext_mark_unwritten(ex2); err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags); - if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + if (err != -ENOSPC && err != -EDQUOT) + goto out; + + if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { if (split_flag & EXT4_EXT_DATA_VALID1) { err = ext4_ext_zeroout(inode, ex2); @@ -3232,25 +3235,22 @@ static int ext4_split_extent_at(handle_t *handle, ext4_ext_pblock(&orig_ex)); } - if (err) - goto fix_extent_len; - /* update the extent length and mark as initialized */ - ex->ee_len = cpu_to_le16(ee_len); - ext4_ext_try_to_merge(handle, inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + path->p_depth); - if (err) - goto fix_extent_len; - - /* update extent status tree */ - err = ext4_zeroout_es(inode, &zero_ex); - - goto out; - } else if (err) - goto fix_extent_len; - -out: - ext4_ext_show_leaf(inode, path); - return err; + if (!err) { + /* update the extent length and mark as initialized */ + ex->ee_len = cpu_to_le16(ee_len); + ext4_ext_try_to_merge(handle, inode, path, ex); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); + if (!err) + /* update extent status tree */ + err = ext4_zeroout_es(inode, &zero_ex); + /* If we failed at this point, we don't know in which + * state the extent tree exactly is so don't try to fix + * length of the original extent as it may do even more + * damage. + */ + goto out; + } + } fix_extent_len: ex->ee_len = orig_ex.ee_len; @@ -3260,6 +3260,9 @@ fix_extent_len: */ ext4_ext_dirty(handle, inode, path + path->p_depth); return err; +out: + ext4_ext_show_leaf(inode, path); + return err; } /* diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index f98ca4f37ef6..e8195229c252 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1288,28 +1288,29 @@ struct dentry_info_args { }; static inline void tl_to_darg(struct dentry_info_args *darg, - struct ext4_fc_tl *tl) + struct ext4_fc_tl *tl, u8 *val) { - struct ext4_fc_dentry_info *fcd; + struct ext4_fc_dentry_info fcd; - fcd = (struct ext4_fc_dentry_info *)ext4_fc_tag_val(tl); + memcpy(&fcd, val, sizeof(fcd)); - darg->parent_ino = le32_to_cpu(fcd->fc_parent_ino); - darg->ino = le32_to_cpu(fcd->fc_ino); - darg->dname = fcd->fc_dname; - darg->dname_len = ext4_fc_tag_len(tl) - - sizeof(struct ext4_fc_dentry_info); + darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino); + darg->ino = le32_to_cpu(fcd.fc_ino); + darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname); + darg->dname_len = le16_to_cpu(tl->fc_len) - + sizeof(struct ext4_fc_dentry_info); } /* Unlink replay function */ -static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { struct inode *inode, *old_parent; struct qstr entry; struct dentry_info_args darg; int ret = 0; - tl_to_darg(&darg, tl); + tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino, darg.parent_ino, darg.dname_len); @@ -1399,13 +1400,14 @@ out: } /* Link replay function */ -static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { struct inode *inode; struct dentry_info_args darg; int ret = 0; - tl_to_darg(&darg, tl); + tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino, darg.parent_ino, darg.dname_len); @@ -1450,9 +1452,10 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino) /* * Inode replay function */ -static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { - struct ext4_fc_inode *fc_inode; + struct ext4_fc_inode fc_inode; struct ext4_inode *raw_inode; struct ext4_inode *raw_fc_inode; struct inode *inode = NULL; @@ -1460,9 +1463,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag); struct ext4_extent_header *eh; - fc_inode = (struct ext4_fc_inode *)ext4_fc_tag_val(tl); + memcpy(&fc_inode, val, sizeof(fc_inode)); - ino = le32_to_cpu(fc_inode->fc_ino); + ino = le32_to_cpu(fc_inode.fc_ino); trace_ext4_fc_replay(sb, tag, ino, 0, 0); inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); @@ -1474,12 +1477,13 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) ext4_fc_record_modified_inode(sb, ino); - raw_fc_inode = (struct ext4_inode *)fc_inode->fc_raw_inode; + raw_fc_inode = (struct ext4_inode *) + (val + offsetof(struct ext4_fc_inode, fc_raw_inode)); ret = ext4_get_fc_inode_loc(sb, ino, &iloc); if (ret) goto out; - inode_len = ext4_fc_tag_len(tl) - sizeof(struct ext4_fc_inode); + inode_len = le16_to_cpu(tl->fc_len) - sizeof(struct ext4_fc_inode); raw_inode = ext4_raw_inode(&iloc); memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block)); @@ -1547,14 +1551,15 @@ out: * inode for which we are trying to create a dentry here, should already have * been replayed before we start here. */ -static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { int ret = 0; struct inode *inode = NULL; struct inode *dir = NULL; struct dentry_info_args darg; - tl_to_darg(&darg, tl); + tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino, darg.parent_ino, darg.dname_len); @@ -1633,9 +1638,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino, /* Replay add range tag */ static int ext4_fc_replay_add_range(struct super_block *sb, - struct ext4_fc_tl *tl) + struct ext4_fc_tl *tl, u8 *val) { - struct ext4_fc_add_range *fc_add_ex; + struct ext4_fc_add_range fc_add_ex; struct ext4_extent newex, *ex; struct inode *inode; ext4_lblk_t start, cur; @@ -1645,15 +1650,14 @@ static int ext4_fc_replay_add_range(struct super_block *sb, struct ext4_ext_path *path = NULL; int ret; - fc_add_ex = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl); - ex = (struct ext4_extent *)&fc_add_ex->fc_ex; + memcpy(&fc_add_ex, val, sizeof(fc_add_ex)); + ex = (struct ext4_extent *)&fc_add_ex.fc_ex; trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE, - le32_to_cpu(fc_add_ex->fc_ino), le32_to_cpu(ex->ee_block), + le32_to_cpu(fc_add_ex.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_get_actual_len(ex)); - inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino), - EXT4_IGET_NORMAL); + inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; @@ -1762,32 +1766,33 @@ next: /* Replay DEL_RANGE tag */ static int -ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl) +ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { struct inode *inode; - struct ext4_fc_del_range *lrange; + struct ext4_fc_del_range lrange; struct ext4_map_blocks map; ext4_lblk_t cur, remaining; int ret; - lrange = (struct ext4_fc_del_range *)ext4_fc_tag_val(tl); - cur = le32_to_cpu(lrange->fc_lblk); - remaining = le32_to_cpu(lrange->fc_len); + memcpy(&lrange, val, sizeof(lrange)); + cur = le32_to_cpu(lrange.fc_lblk); + remaining = le32_to_cpu(lrange.fc_len); trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE, - le32_to_cpu(lrange->fc_ino), cur, remaining); + le32_to_cpu(lrange.fc_ino), cur, remaining); - inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL); + inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino)); + jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange.fc_ino)); return 0; } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n", - inode->i_ino, le32_to_cpu(lrange->fc_lblk), - le32_to_cpu(lrange->fc_len)); + inode->i_ino, le32_to_cpu(lrange.fc_lblk), + le32_to_cpu(lrange.fc_len)); while (remaining > 0) { map.m_lblk = cur; map.m_len = remaining; @@ -1808,8 +1813,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl) } ret = ext4_punch_hole(inode, - le32_to_cpu(lrange->fc_lblk) << sb->s_blocksize_bits, - le32_to_cpu(lrange->fc_len) << sb->s_blocksize_bits); + le32_to_cpu(lrange.fc_lblk) << sb->s_blocksize_bits, + le32_to_cpu(lrange.fc_len) << sb->s_blocksize_bits); if (ret) jbd_debug(1, "ext4_punch_hole returned %d", ret); ext4_ext_replay_shrink_inode(inode, @@ -1925,11 +1930,11 @@ static int ext4_fc_replay_scan(journal_t *journal, struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_replay_state *state; int ret = JBD2_FC_REPLAY_CONTINUE; - struct ext4_fc_add_range *ext; - struct ext4_fc_tl *tl; - struct ext4_fc_tail *tail; - __u8 *start, *end; - struct ext4_fc_head *head; + struct ext4_fc_add_range ext; + struct ext4_fc_tl tl; + struct ext4_fc_tail tail; + __u8 *start, *end, *cur, *val; + struct ext4_fc_head head; struct ext4_extent *ex; state = &sbi->s_fc_replay_state; @@ -1956,15 +1961,17 @@ static int ext4_fc_replay_scan(journal_t *journal, } state->fc_replay_expected_off++; - fc_for_each_tl(start, end, tl) { + for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) { + memcpy(&tl, cur, sizeof(tl)); + val = cur + sizeof(tl); jbd_debug(3, "Scan phase, tag:%s, blk %lld\n", - tag2str(le16_to_cpu(tl->fc_tag)), bh->b_blocknr); - switch (le16_to_cpu(tl->fc_tag)) { + tag2str(le16_to_cpu(tl.fc_tag)), bh->b_blocknr); + switch (le16_to_cpu(tl.fc_tag)) { case EXT4_FC_TAG_ADD_RANGE: - ext = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl); - ex = (struct ext4_extent *)&ext->fc_ex; + memcpy(&ext, val, sizeof(ext)); + ex = (struct ext4_extent *)&ext.fc_ex; ret = ext4_fc_record_regions(sb, - le32_to_cpu(ext->fc_ino), + le32_to_cpu(ext.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_get_actual_len(ex)); if (ret < 0) @@ -1978,18 +1985,18 @@ static int ext4_fc_replay_scan(journal_t *journal, case EXT4_FC_TAG_INODE: case EXT4_FC_TAG_PAD: state->fc_cur_tag++; - state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl, - sizeof(*tl) + ext4_fc_tag_len(tl)); + state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, + sizeof(tl) + le16_to_cpu(tl.fc_len)); break; case EXT4_FC_TAG_TAIL: state->fc_cur_tag++; - tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl); - state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl, - sizeof(*tl) + + memcpy(&tail, val, sizeof(tail)); + state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, + sizeof(tl) + offsetof(struct ext4_fc_tail, fc_crc)); - if (le32_to_cpu(tail->fc_tid) == expected_tid && - le32_to_cpu(tail->fc_crc) == state->fc_crc) { + if (le32_to_cpu(tail.fc_tid) == expected_tid && + le32_to_cpu(tail.fc_crc) == state->fc_crc) { state->fc_replay_num_tags = state->fc_cur_tag; state->fc_regions_valid = state->fc_regions_used; @@ -2000,19 +2007,19 @@ static int ext4_fc_replay_scan(journal_t *journal, state->fc_crc = 0; break; case EXT4_FC_TAG_HEAD: - head = (struct ext4_fc_head *)ext4_fc_tag_val(tl); - if (le32_to_cpu(head->fc_features) & + memcpy(&head, val, sizeof(head)); + if (le32_to_cpu(head.fc_features) & ~EXT4_FC_SUPPORTED_FEATURES) { ret = -EOPNOTSUPP; break; } - if (le32_to_cpu(head->fc_tid) != expected_tid) { + if (le32_to_cpu(head.fc_tid) != expected_tid) { ret = JBD2_FC_REPLAY_STOP; break; } state->fc_cur_tag++; - state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl, - sizeof(*tl) + ext4_fc_tag_len(tl)); + state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, + sizeof(tl) + le16_to_cpu(tl.fc_len)); break; default: ret = state->fc_replay_num_tags ? @@ -2036,11 +2043,11 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_fc_tl *tl; - __u8 *start, *end; + struct ext4_fc_tl tl; + __u8 *start, *end, *cur, *val; int ret = JBD2_FC_REPLAY_CONTINUE; struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state; - struct ext4_fc_tail *tail; + struct ext4_fc_tail tail; if (pass == PASS_SCAN) { state->fc_current_pass = PASS_SCAN; @@ -2067,49 +2074,52 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, start = (u8 *)bh->b_data; end = (__u8 *)bh->b_data + journal->j_blocksize - 1; - fc_for_each_tl(start, end, tl) { + for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) { + memcpy(&tl, cur, sizeof(tl)); + val = cur + sizeof(tl); + if (state->fc_replay_num_tags == 0) { ret = JBD2_FC_REPLAY_STOP; ext4_fc_set_bitmaps_and_counters(sb); break; } jbd_debug(3, "Replay phase, tag:%s\n", - tag2str(le16_to_cpu(tl->fc_tag))); + tag2str(le16_to_cpu(tl.fc_tag))); state->fc_replay_num_tags--; - switch (le16_to_cpu(tl->fc_tag)) { + switch (le16_to_cpu(tl.fc_tag)) { case EXT4_FC_TAG_LINK: - ret = ext4_fc_replay_link(sb, tl); + ret = ext4_fc_replay_link(sb, &tl, val); break; case EXT4_FC_TAG_UNLINK: - ret = ext4_fc_replay_unlink(sb, tl); + ret = ext4_fc_replay_unlink(sb, &tl, val); break; case EXT4_FC_TAG_ADD_RANGE: - ret = ext4_fc_replay_add_range(sb, tl); + ret = ext4_fc_replay_add_range(sb, &tl, val); break; case EXT4_FC_TAG_CREAT: - ret = ext4_fc_replay_create(sb, tl); + ret = ext4_fc_replay_create(sb, &tl, val); break; case EXT4_FC_TAG_DEL_RANGE: - ret = ext4_fc_replay_del_range(sb, tl); + ret = ext4_fc_replay_del_range(sb, &tl, val); break; case EXT4_FC_TAG_INODE: - ret = ext4_fc_replay_inode(sb, tl); + ret = ext4_fc_replay_inode(sb, &tl, val); break; case EXT4_FC_TAG_PAD: trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0, - ext4_fc_tag_len(tl), 0); + le16_to_cpu(tl.fc_len), 0); break; case EXT4_FC_TAG_TAIL: trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0, - ext4_fc_tag_len(tl), 0); - tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl); - WARN_ON(le32_to_cpu(tail->fc_tid) != expected_tid); + le16_to_cpu(tl.fc_len), 0); + memcpy(&tail, val, sizeof(tail)); + WARN_ON(le32_to_cpu(tail.fc_tid) != expected_tid); break; case EXT4_FC_TAG_HEAD: break; default: - trace_ext4_fc_replay(sb, le16_to_cpu(tl->fc_tag), 0, - ext4_fc_tag_len(tl), 0); + trace_ext4_fc_replay(sb, le16_to_cpu(tl.fc_tag), 0, + le16_to_cpu(tl.fc_len), 0); ret = -ECANCELED; break; } diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index b77f70f55a62..937c381b4c85 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -153,13 +153,6 @@ struct ext4_fc_replay_state { #define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1) #endif -#define fc_for_each_tl(__start, __end, __tl) \ - for (tl = (struct ext4_fc_tl *)(__start); \ - (__u8 *)tl < (__u8 *)(__end); \ - tl = (struct ext4_fc_tl *)((__u8 *)tl + \ - sizeof(struct ext4_fc_tl) + \ - + le16_to_cpu(tl->fc_len))) - static inline const char *tag2str(__u16 tag) { switch (tag) { @@ -186,16 +179,4 @@ static inline const char *tag2str(__u16 tag) } } -/* Get length of a particular tlv */ -static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl) -{ - return le16_to_cpu(tl->fc_len); -} - -/* Get a pointer to "value" of a tlv */ -static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl) -{ - return (__u8 *)tl + sizeof(*tl); -} - #endif /* __FAST_COMMIT_H__ */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 81a17a3cd80e..9bab7fd4ccd5 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -322,14 +322,16 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) if (is_directory) { count = ext4_used_dirs_count(sb, gdp) - 1; ext4_used_dirs_set(sb, gdp, count); - percpu_counter_dec(&sbi->s_dirs_counter); + if (percpu_counter_initialized(&sbi->s_dirs_counter)) + percpu_counter_dec(&sbi->s_dirs_counter); } ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); - percpu_counter_inc(&sbi->s_freeinodes_counter); + if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) + percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { struct flex_groups *fg; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3239e6669e84..c2c22c2baac0 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3217,7 +3217,7 @@ static int ext4_mb_init_backend(struct super_block *sb) */ if (sbi->s_es->s_log_groups_per_flex >= 32) { ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); - goto err_freesgi; + goto err_freebuddy; } sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index afb9d05a99ba..a4af26d4459a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1376,7 +1376,8 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct dx_hash_info *hinfo = &name->hinfo; int len; - if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) { + if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding || + (IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir))) { cf_name->name = NULL; return 0; } @@ -1427,7 +1428,8 @@ static bool ext4_match(struct inode *parent, #endif #ifdef CONFIG_UNICODE - if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent)) { + if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) && + (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) { if (fname->cf_name.name) { struct qstr cf = {.name = fname->cf_name.name, .len = fname->cf_name.len}; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7dc94f3e18e6..d29f6aa7d96e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4462,14 +4462,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (sb->s_blocksize != blocksize) { + /* + * bh must be released before kill_bdev(), otherwise + * it won't be freed and its page also. kill_bdev() + * is called by sb_set_blocksize(). + */ + brelse(bh); /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); + bh = NULL; goto failed_mount; } - brelse(bh); logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = ext4_sb_bread_unmovable(sb, logical_sb_block); @@ -5202,8 +5208,9 @@ failed_mount: kfree(get_qf_name(sb, sbi, i)); #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); - ext4_blkdev_remove(sbi); + /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */ brelse(bh); + ext4_blkdev_remove(sbi); out_fail: sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 6f825dedc3d4..55fcab60a59a 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -315,7 +315,9 @@ EXT4_ATTR_FEATURE(verity); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); EXT4_ATTR_FEATURE(fast_commit); +#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) EXT4_ATTR_FEATURE(encrypted_casefold); +#endif static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), @@ -333,7 +335,9 @@ static struct attribute *ext4_feat_attrs[] = { #endif ATTR_LIST(metadata_csum_seed), ATTR_LIST(fast_commit), +#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) ATTR_LIST(encrypted_casefold), +#endif NULL, }; ATTRIBUTE_GROUPS(ext4_feat); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index a0b542d84cd9..493a83e3f590 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -911,8 +911,11 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) current->backing_dev_info = inode_to_bdi(inode); buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); current->backing_dev_info = NULL; - if (unlikely(buffered <= 0)) + if (unlikely(buffered <= 0)) { + if (!ret) + ret = buffered; goto out_unlock; + } /* * We need to ensure that the page cache pages are written to diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ea7fc5c641c7..d9cb261f55b0 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -582,6 +582,16 @@ out_locked: spin_unlock(&gl->gl_lockref.lock); } +static bool is_system_glock(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); + + if (gl == m_ip->i_gl) + return true; + return false; +} + /** * do_xmote - Calls the DLM to change the state of a lock * @gl: The lock state @@ -671,17 +681,25 @@ skip_inval: * to see sd_log_error and withdraw, and in the meantime, requeue the * work for later. * + * We make a special exception for some system glocks, such as the + * system statfs inode glock, which needs to be granted before the + * gfs2_quotad daemon can exit, and that exit needs to finish before + * we can unmount the withdrawn file system. + * * However, if we're just unlocking the lock (say, for unmount, when * gfs2_gl_hash_clear calls clear_glock) and recovery is complete * then it's okay to tell dlm to unlock it. */ if (unlikely(sdp->sd_log_error && !gfs2_withdrawn(sdp))) gfs2_withdraw_delayed(sdp); - if (glock_blocked_by_withdraw(gl)) { - if (target != LM_ST_UNLOCKED || - test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags)) { + if (glock_blocked_by_withdraw(gl) && + (target != LM_ST_UNLOCKED || + test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags))) { + if (!is_system_glock(gl)) { gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD); goto out; + } else { + clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); } } @@ -1466,9 +1484,11 @@ void gfs2_glock_dq(struct gfs2_holder *gh) glock_blocked_by_withdraw(gl) && gh->gh_gl != sdp->sd_jinode_gl) { sdp->sd_glock_dqs_held++; + spin_unlock(&gl->gl_lockref.lock); might_sleep(); wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY, TASK_UNINTERRUPTIBLE); + spin_lock(&gl->gl_lockref.lock); } if (gh->gh_flags & GL_NOCACHE) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1775,6 +1795,7 @@ __acquires(&lru_lock) while(!list_empty(list)) { gl = list_first_entry(list, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); + clear_bit(GLF_LRU, &gl->gl_flags); if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); @@ -1820,7 +1841,6 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); - clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; } diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 454095e9fedf..54d3fbeb3002 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -396,7 +396,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) struct timespec64 atime; u16 height, depth; umode_t mode = be32_to_cpu(str->di_mode); - bool is_new = ip->i_inode.i_flags & I_NEW; + bool is_new = ip->i_inode.i_state & I_NEW; if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) goto corrupt; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 97d54e581a7b..42c15cfc0821 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -926,10 +926,10 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags) } /** - * ail_drain - drain the ail lists after a withdraw + * gfs2_ail_drain - drain the ail lists after a withdraw * @sdp: Pointer to GFS2 superblock */ -static void ail_drain(struct gfs2_sbd *sdp) +void gfs2_ail_drain(struct gfs2_sbd *sdp) { struct gfs2_trans *tr; @@ -956,6 +956,7 @@ static void ail_drain(struct gfs2_sbd *sdp) list_del(&tr->tr_list); gfs2_trans_free(sdp, tr); } + gfs2_drain_revokes(sdp); spin_unlock(&sdp->sd_ail_lock); } @@ -1162,7 +1163,6 @@ out_withdraw: if (tr && list_empty(&tr->tr_list)) list_add(&tr->tr_list, &sdp->sd_ail1_list); spin_unlock(&sdp->sd_ail_lock); - ail_drain(sdp); /* frees all transactions */ tr = NULL; goto out_end; } diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index eea58015710e..fc905c2af53c 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -93,5 +93,6 @@ extern int gfs2_logd(void *data); extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); extern void gfs2_glock_remove_revoke(struct gfs2_glock *gl); extern void gfs2_flush_revokes(struct gfs2_sbd *sdp); +extern void gfs2_ail_drain(struct gfs2_sbd *sdp); #endif /* __LOG_DOT_H__ */ diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 221e7118cc3b..8ee05d25dfa6 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -885,7 +885,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_log_write_page(sdp, page); } -static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) +void gfs2_drain_revokes(struct gfs2_sbd *sdp) { struct list_head *head = &sdp->sd_log_revokes; struct gfs2_bufdata *bd; @@ -900,6 +900,11 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) } } +static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) +{ + gfs2_drain_revokes(sdp); +} + static void revoke_lo_before_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, int pass) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 31b6dd0d2e5d..f707601597dc 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -20,6 +20,7 @@ extern void gfs2_log_submit_bio(struct bio **biop, int opf); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); extern int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, bool keep_cache); +extern void gfs2_drain_revokes(struct gfs2_sbd *sdp); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { return sdp->sd_ldptrs; diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 3e08027a6c81..f4325b44956d 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -131,6 +131,7 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || !sdp->sd_jdesc) return; + gfs2_ail_drain(sdp); /* frees all transactions */ inode = sdp->sd_jdesc->jd_inode; ip = GFS2_I(inode); i_gl = ip->i_gl; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 55efd3dd04f6..30dee68458c7 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -735,6 +735,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, __SetPageUptodate(page); error = huge_add_to_page_cache(page, mapping, index); if (unlikely(error)) { + restore_reserve_on_error(h, &pseudo_vma, addr, page); put_page(page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; diff --git a/fs/io-wq.c b/fs/io-wq.c index 5361a9b4b47b..b3e8624a37d0 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -979,13 +979,16 @@ static bool io_task_work_match(struct callback_head *cb, void *data) return cwd->wqe->wq == data; } +void io_wq_exit_start(struct io_wq *wq) +{ + set_bit(IO_WQ_BIT_EXIT, &wq->state); +} + static void io_wq_exit_workers(struct io_wq *wq) { struct callback_head *cb; int node; - set_bit(IO_WQ_BIT_EXIT, &wq->state); - if (!wq->task) return; @@ -1003,13 +1006,16 @@ static void io_wq_exit_workers(struct io_wq *wq) struct io_wqe *wqe = wq->wqes[node]; io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL); - spin_lock_irq(&wq->hash->wait.lock); - list_del_init(&wq->wqes[node]->wait.entry); - spin_unlock_irq(&wq->hash->wait.lock); } rcu_read_unlock(); io_worker_ref_put(wq); wait_for_completion(&wq->worker_done); + + for_each_node(node) { + spin_lock_irq(&wq->hash->wait.lock); + list_del_init(&wq->wqes[node]->wait.entry); + spin_unlock_irq(&wq->hash->wait.lock); + } put_task_struct(wq->task); wq->task = NULL; } @@ -1020,8 +1026,6 @@ static void io_wq_destroy(struct io_wq *wq) cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - io_wq_exit_workers(wq); - for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; struct io_cb_cancel_data match = { @@ -1036,16 +1040,13 @@ static void io_wq_destroy(struct io_wq *wq) kfree(wq); } -void io_wq_put(struct io_wq *wq) -{ - if (refcount_dec_and_test(&wq->refs)) - io_wq_destroy(wq); -} - void io_wq_put_and_exit(struct io_wq *wq) { + WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state)); + io_wq_exit_workers(wq); - io_wq_put(wq); + if (refcount_dec_and_test(&wq->refs)) + io_wq_destroy(wq); } static bool io_wq_worker_affinity(struct io_worker *worker, void *data) diff --git a/fs/io-wq.h b/fs/io-wq.h index 0e6d310999e8..af2df0680ee2 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -122,7 +122,7 @@ struct io_wq_data { }; struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); -void io_wq_put(struct io_wq *wq); +void io_wq_exit_start(struct io_wq *wq); void io_wq_put_and_exit(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); diff --git a/fs/io_uring.c b/fs/io_uring.c index 5f82954004f6..fa8794c61af7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -783,6 +783,11 @@ struct io_task_work { task_work_func_t func; }; +enum { + IORING_RSRC_FILE = 0, + IORING_RSRC_BUFFER = 1, +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -8228,6 +8233,7 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, { int i, ret; + imu->acct_pages = 0; for (i = 0; i < nr_pages; i++) { if (!PageCompound(pages[i])) { imu->acct_pages++; @@ -9039,11 +9045,16 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx) struct io_tctx_node *node; unsigned long index; - tctx->io_wq = NULL; xa_for_each(&tctx->xa, index, node) io_uring_del_task_file(index); - if (wq) + if (wq) { + /* + * Must be after io_uring_del_task_file() (removes nodes under + * uring_lock) to avoid race with io_uring_try_cancel_iowq(). + */ + tctx->io_wq = NULL; io_wq_put_and_exit(wq); + } } static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) @@ -9078,6 +9089,9 @@ static void io_uring_cancel_sqpoll(struct io_sq_data *sqd) if (!current->io_uring) return; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); + WARN_ON_ONCE(!sqd || sqd->thread != current); atomic_inc(&tctx->in_idle); @@ -9112,6 +9126,9 @@ void __io_uring_cancel(struct files_struct *files) DEFINE_WAIT(wait); s64 inflight; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); + /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); do { @@ -9659,7 +9676,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | - IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS; + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | + IORING_FEAT_RSRC_TAGS; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -9899,7 +9917,7 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, } static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, - unsigned size) + unsigned size, unsigned type) { struct io_uring_rsrc_update2 up; @@ -9907,13 +9925,13 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; - if (!up.nr) + if (!up.nr || up.resv) return -EINVAL; - return __io_register_rsrc_update(ctx, up.type, &up, up.nr); + return __io_register_rsrc_update(ctx, type, &up, up.nr); } static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, - unsigned int size) + unsigned int size, unsigned int type) { struct io_uring_rsrc_register rr; @@ -9924,10 +9942,10 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, memset(&rr, 0, sizeof(rr)); if (copy_from_user(&rr, arg, size)) return -EFAULT; - if (!rr.nr) + if (!rr.nr || rr.resv || rr.resv2) return -EINVAL; - switch (rr.type) { + switch (type) { case IORING_RSRC_FILE: return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); @@ -9949,8 +9967,10 @@ static bool io_register_op_must_quiesce(int op) case IORING_REGISTER_PROBE: case IORING_REGISTER_PERSONALITY: case IORING_UNREGISTER_PERSONALITY: - case IORING_REGISTER_RSRC: - case IORING_REGISTER_RSRC_UPDATE: + case IORING_REGISTER_FILES2: + case IORING_REGISTER_FILES_UPDATE2: + case IORING_REGISTER_BUFFERS2: + case IORING_REGISTER_BUFFERS_UPDATE: return false; default: return true; @@ -10076,11 +10096,19 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, case IORING_REGISTER_RESTRICTIONS: ret = io_register_restrictions(ctx, arg, nr_args); break; - case IORING_REGISTER_RSRC: - ret = io_register_rsrc(ctx, arg, nr_args); + case IORING_REGISTER_FILES2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); + break; + case IORING_REGISTER_FILES_UPDATE2: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_FILE); + break; + case IORING_REGISTER_BUFFERS2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); break; - case IORING_REGISTER_RSRC_UPDATE: - ret = io_register_rsrc_update(ctx, arg, nr_args); + case IORING_REGISTER_BUFFERS_UPDATE: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_BUFFER); break; default: ret = -EINVAL; diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig index 578112713703..b4db21022cb4 100644 --- a/fs/netfs/Kconfig +++ b/fs/netfs/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config NETFS_SUPPORT - tristate "Support for network filesystem high-level I/O" + tristate help This option enables support for network filesystems, including helpers for high-level buffered I/O, abstracting out read diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 193841d03de0..725614625ed4 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -1068,7 +1068,7 @@ int netfs_write_begin(struct file *file, struct address_space *mapping, DEFINE_READAHEAD(ractl, file, NULL, mapping, index); retry: - page = grab_cache_page_write_begin(mapping, index, 0); + page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index cfeaadf56bf0..330f65727c45 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -406,7 +406,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) if (cl_init->hostname == NULL) { WARN_ON(1); - return NULL; + return ERR_PTR(-EINVAL); } /* see if the client already exists */ diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index d158a500c25c..d2103852475f 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -718,7 +718,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, if (unlikely(!p)) goto out_err; fl->fh_array[i]->size = be32_to_cpup(p++); - if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { + if (fl->fh_array[i]->size > NFS_MAXFHSIZE) { printk(KERN_ERR "NFS: Too big fh %d received %d\n", i, fl->fh_array[i]->size); goto out_err; diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 93e60e921f92..bc0c698f3350 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -362,7 +362,7 @@ static const struct kernel_param_ops param_ops_nfs_timeout = { .set = param_set_nfs_timeout, .get = param_get_nfs_timeout, }; -#define param_check_nfs_timeout(name, p) __param_check(name, p, int); +#define param_check_nfs_timeout(name, p) __param_check(name, p, int) module_param(nfs_mountpoint_expiry_timeout, nfs_timeout, 0644); MODULE_PARM_DESC(nfs_mountpoint_expiry_timeout, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 065cb04222a1..543d916f79ab 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -205,6 +205,7 @@ struct nfs4_exception { struct inode *inode; nfs4_stateid *stateid; long timeout; + unsigned char task_is_privileged : 1; unsigned char delay : 1, recovering : 1, retry : 1; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 889a9f4c0310..42719384e25f 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -435,8 +435,8 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, */ nfs_mark_client_ready(clp, -EPERM); } - nfs_put_client(clp); clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags); + nfs_put_client(clp); return old; error: diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 57b3821d975a..a1e5c6b85ded 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -211,7 +211,7 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) case SEEK_HOLE: case SEEK_DATA: ret = nfs42_proc_llseek(filep, offset, whence); - if (ret != -ENOTSUPP) + if (ret != -EOPNOTSUPP) return ret; fallthrough; default: diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 87d04f2c9385..e653654c10bc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -589,6 +589,8 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ goto out_retry; } if (exception->recovering) { + if (exception->task_is_privileged) + return -EDEADLOCK; ret = nfs4_wait_clnt_recover(clp); if (test_bit(NFS_MIG_FAILED, &server->mig_status)) return -EIO; @@ -614,6 +616,8 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server, goto out_retry; } if (exception->recovering) { + if (exception->task_is_privileged) + return -EDEADLOCK; rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); @@ -1706,7 +1710,7 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, rcu_read_unlock(); trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0); - if (!signal_pending(current)) { + if (!fatal_signal_pending(current)) { if (schedule_timeout(5*HZ) == 0) status = -EAGAIN; else @@ -3487,7 +3491,7 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst, write_sequnlock(&state->seqlock); trace_nfs4_close_stateid_update_wait(state->inode, dst, 0); - if (signal_pending(current)) + if (fatal_signal_pending(current)) status = -EINTR; else if (schedule_timeout(5*HZ) != 0) @@ -3878,6 +3882,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL) + server->caps |= NFS_CAP_SECURITY_LABEL; +#endif if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID)) server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID; if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE)) @@ -3898,10 +3906,6 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->fattr_valid &= ~NFS_ATTR_FATTR_CTIME; if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)) server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME; -#ifdef CONFIG_NFS_V4_SECURITY_LABEL - if (!(res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL)) - server->fattr_valid &= ~NFS_ATTR_FATTR_V4_SECURITY_LABEL; -#endif memcpy(server->attr_bitmask_nl, res.attr_bitmask, sizeof(server->attr_bitmask)); server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL; @@ -5968,6 +5972,14 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen do { err = __nfs4_proc_set_acl(inode, buf, buflen); trace_nfs4_set_acl(inode, err); + if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) { + /* + * no need to retry since the kernel + * isn't involved in encoding the ACEs. + */ + err = -EINVAL; + break; + } err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); } while (exception.retry); @@ -6409,6 +6421,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) struct nfs4_exception exception = { .inode = data->inode, .stateid = &data->stateid, + .task_is_privileged = data->args.seq_args.sa_privileged, }; if (!nfs4_sequence_done(task, &data->res.seq_res)) @@ -6532,7 +6545,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data = kzalloc(sizeof(*data), GFP_NOFS); if (data == NULL) return -ENOMEM; - nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0); nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP, @@ -6563,6 +6575,12 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, } } + if (!data->inode) + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, + 1); + else + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, + 0); task_setup_data.callback_data = data; msg.rpc_argp = &data->args; msg.rpc_resp = &data->res; @@ -9640,15 +9658,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) &task_setup_data.rpc_client, &msg); dprintk("--> %s\n", __func__); + lrp->inode = nfs_igrab_and_active(lrp->args.inode); if (!sync) { - lrp->inode = nfs_igrab_and_active(lrp->args.inode); if (!lrp->inode) { nfs4_layoutreturn_release(lrp); return -EAGAIN; } task_setup_data.flags |= RPC_TASK_ASYNC; } - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); + if (!lrp->inode) + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, + 1); + else + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, + 0); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index eb1ef3462e84..ccef43e02b48 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -430,10 +430,6 @@ TRACE_DEFINE_ENUM(O_CLOEXEC); { O_NOATIME, "O_NOATIME" }, \ { O_CLOEXEC, "O_CLOEXEC" }) -TRACE_DEFINE_ENUM(FMODE_READ); -TRACE_DEFINE_ENUM(FMODE_WRITE); -TRACE_DEFINE_ENUM(FMODE_EXEC); - #define show_fmode_flags(mode) \ __print_flags(mode, "|", \ { ((__force unsigned long)FMODE_READ), "READ" }, \ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6c20b28d9d7c..cf9cc62ec48e 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1094,15 +1094,16 @@ nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *prev = NULL; unsigned int size; - if (mirror->pg_count != 0) { - prev = nfs_list_entry(mirror->pg_list.prev); - } else { + if (list_empty(&mirror->pg_list)) { if (desc->pg_ops->pg_init) desc->pg_ops->pg_init(desc, req); if (desc->pg_error < 0) return 0; mirror->pg_base = req->wb_pgbase; - } + mirror->pg_count = 0; + mirror->pg_recoalesce = 0; + } else + prev = nfs_list_entry(mirror->pg_list.prev); if (desc->pg_maxretrans && req->wb_nio > desc->pg_maxretrans) { if (NFS_SERVER(desc->pg_inode)->flags & NFS_MOUNT_SOFTERR) @@ -1127,18 +1128,13 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) { struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); - if (!list_empty(&mirror->pg_list)) { int error = desc->pg_ops->pg_doio(desc); if (error < 0) desc->pg_error = error; - else + if (list_empty(&mirror->pg_list)) mirror->pg_bytes_written += mirror->pg_count; } - if (list_empty(&mirror->pg_list)) { - mirror->pg_count = 0; - mirror->pg_base = 0; - } } static void @@ -1227,10 +1223,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) do { list_splice_init(&mirror->pg_list, &head); - mirror->pg_bytes_written -= mirror->pg_count; - mirror->pg_count = 0; - mirror->pg_base = 0; - mirror->pg_recoalesce = 0; while (!list_empty(&head)) { struct nfs_page *req; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 03e0b34c4a64..2c01ee805306 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1317,6 +1317,11 @@ _pnfs_return_layout(struct inode *ino) { struct pnfs_layout_hdr *lo = NULL; struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; LIST_HEAD(tmp_list); const struct cred *cred; nfs4_stateid stateid; @@ -1344,16 +1349,10 @@ _pnfs_return_layout(struct inode *ino) } valid_layout = pnfs_layout_is_valid(lo); pnfs_clear_layoutcommit(ino, &tmp_list); - pnfs_mark_matching_lsegs_return(lo, &tmp_list, NULL, 0); + pnfs_mark_matching_lsegs_return(lo, &tmp_list, &range, 0); - if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { - struct pnfs_layout_range range = { - .iomode = IOMODE_ANY, - .offset = 0, - .length = NFS4_MAX_UINT64, - }; + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range); - } /* Don't send a LAYOUTRETURN if list was initially empty */ if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) || @@ -2678,7 +2677,7 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_range); void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - u64 rd_size = req->wb_bytes; + u64 rd_size; pnfs_generic_pg_check_layout(pgio); pnfs_generic_pg_check_range(pgio, req); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 19a212f9725d..fe58525cfed4 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1379,7 +1379,7 @@ static const struct kernel_param_ops param_ops_portnr = { .set = param_set_portnr, .get = param_get_uint, }; -#define param_check_portnr(name, p) __param_check(name, p, unsigned int); +#define param_check_portnr(name, p) __param_check(name, p, unsigned int) module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644); module_param_named(callback_nr_threads, nfs_callback_nr_threads, ushort, 0644); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 71fefb30e015..64864fb40b40 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -424,11 +424,18 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, * events generated by the listener process itself, without disclosing * the pids of other processes. */ - if (!capable(CAP_SYS_ADMIN) && + if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) && task_tgid(current) != event->pid) metadata.pid = 0; - if (path && path->mnt && path->dentry) { + /* + * For now, fid mode is required for an unprivileged listener and + * fid mode does not report fd in events. Keep this check anyway + * for safety in case fid mode requirement is relaxed in the future + * to allow unprivileged listener to get events with no fd and no fid. + */ + if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) && + path && path->mnt && path->dentry) { fd = create_fd(group, path, &f); if (fd < 0) return fd; @@ -464,7 +471,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, info_type, fanotify_info_name(info), info->name_len, buf, count); if (ret < 0) - return ret; + goto out_close_fd; buf += ret; count -= ret; @@ -512,7 +519,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, fanotify_event_object_fh(event), info_type, dot, dot_len, buf, count); if (ret < 0) - return ret; + goto out_close_fd; buf += ret; count -= ret; @@ -1040,6 +1047,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) int f_flags, fd; unsigned int fid_mode = flags & FANOTIFY_FID_BITS; unsigned int class = flags & FANOTIFY_CLASS_BITS; + unsigned int internal_flags = 0; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -1053,6 +1061,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) */ if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode) return -EPERM; + + /* + * Setting the internal flag FANOTIFY_UNPRIV on the group + * prevents setting mount/filesystem marks on this group and + * prevents reporting pid and open fd in events. + */ + internal_flags |= FANOTIFY_UNPRIV; } #ifdef CONFIG_AUDITSYSCALL @@ -1105,7 +1120,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) goto out_destroy_group; } - group->fanotify_data.flags = flags; + group->fanotify_data.flags = flags | internal_flags; group->memcg = get_mem_cgroup_from_mm(current->mm); group->fanotify_data.merge_hash = fanotify_alloc_merge_hash(); @@ -1305,11 +1320,13 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, group = f.file->private_data; /* - * An unprivileged user is not allowed to watch a mount point nor - * a filesystem. + * An unprivileged user is not allowed to setup mount nor filesystem + * marks. This also includes setting up such marks by a group that + * was initialized by an unprivileged user. */ ret = -EPERM; - if (!capable(CAP_SYS_ADMIN) && + if ((!capable(CAP_SYS_ADMIN) || + FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) && mark_type != FAN_MARK_INODE) goto fput_and_out; @@ -1460,6 +1477,7 @@ static int __init fanotify_user_setup(void) max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS, FANOTIFY_DEFAULT_MAX_USER_MARKS); + BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index a712b2aaa9ac..57f0d5d9f934 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -144,7 +144,7 @@ void fanotify_show_fdinfo(struct seq_file *m, struct file *f) struct fsnotify_group *group = f->private_data; seq_printf(m, "fanotify flags:%x event-flags:%x\n", - group->fanotify_data.flags, + group->fanotify_data.flags & FANOTIFY_INIT_FLAGS, group->fanotify_data.f_flags); show_fdinfo(m, f, fanotify_fdinfo); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index f17c3d33fb18..775657943057 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1856,6 +1856,45 @@ out: } /* + * zero out partial blocks of one cluster. + * + * start: file offset where zero starts, will be made upper block aligned. + * len: it will be trimmed to the end of current cluster if "start + len" + * is bigger than it. + */ +static int ocfs2_zeroout_partial_cluster(struct inode *inode, + u64 start, u64 len) +{ + int ret; + u64 start_block, end_block, nr_blocks; + u64 p_block, offset; + u32 cluster, p_cluster, nr_clusters; + struct super_block *sb = inode->i_sb; + u64 end = ocfs2_align_bytes_to_clusters(sb, start); + + if (start + len < end) + end = start + len; + + start_block = ocfs2_blocks_for_bytes(sb, start); + end_block = ocfs2_blocks_for_bytes(sb, end); + nr_blocks = end_block - start_block; + if (!nr_blocks) + return 0; + + cluster = ocfs2_bytes_to_clusters(sb, start); + ret = ocfs2_get_clusters(inode, cluster, &p_cluster, + &nr_clusters, NULL); + if (ret) + return ret; + if (!p_cluster) + return 0; + + offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); + p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; + return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); +} + +/* * Parts of this function taken from xfs_change_file_space() */ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, @@ -1865,7 +1904,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, { int ret; s64 llen; - loff_t size; + loff_t size, orig_isize; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct buffer_head *di_bh = NULL; handle_t *handle; @@ -1896,6 +1935,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, goto out_inode_unlock; } + orig_isize = i_size_read(inode); switch (sr->l_whence) { case 0: /*SEEK_SET*/ break; @@ -1903,7 +1943,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, sr->l_start += f_pos; break; case 2: /*SEEK_END*/ - sr->l_start += i_size_read(inode); + sr->l_start += orig_isize; break; default: ret = -EINVAL; @@ -1957,6 +1997,14 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, default: ret = -EINVAL; } + + /* zeroout eof blocks in the cluster. */ + if (!ret && change_size && orig_isize < size) { + ret = ocfs2_zeroout_partial_cluster(inode, orig_isize, + size - orig_isize); + if (!ret) + i_size_write(inode, size); + } up_write(&OCFS2_I(inode)->ip_alloc_sem); if (ret) { mlog_errno(ret); @@ -1973,9 +2021,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, goto out_inode_unlock; } - if (change_size && i_size_read(inode) < size) - i_size_write(inode, size); - inode->i_ctime = inode->i_mtime = current_time(inode); ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); if (ret < 0) diff --git a/fs/proc/base.c b/fs/proc/base.c index 3851bfcdba56..9cbd915025ad 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2674,6 +2674,13 @@ out: } #ifdef CONFIG_SECURITY +static int proc_pid_attr_open(struct inode *inode, struct file *file) +{ + file->private_data = NULL; + __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); + return 0; +} + static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { @@ -2703,6 +2710,10 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, void *page; int rv; + /* A task may only write when it was the opener. */ + if (file->private_data != current->mm) + return -EPERM; + rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { @@ -2750,9 +2761,11 @@ out: } static const struct file_operations proc_pid_attr_operations = { + .open = proc_pid_attr_open, .read = proc_pid_attr_read, .write = proc_pid_attr_write, .llseek = generic_file_llseek, + .release = mem_release, }; #define LSM_DIR_OPS(LSM) \ diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index e32a1833d523..bbfea8022a3b 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -325,10 +325,22 @@ out: error2 = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, 0); if (error2) return error2; - ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved + - xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <= - pag->pagf_freeblks + pag->pagf_flcount); + + /* + * If there isn't enough space in the AG to satisfy the + * reservation, let the caller know that there wasn't enough + * space. Callers are responsible for deciding what to do + * next, since (in theory) we can stumble along with + * insufficient reservation if data blocks are being freed to + * replenish the AG's free space. + */ + if (!error && + xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved + + xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved > + pag->pagf_freeblks + pag->pagf_flcount) + error = -ENOSPC; } + return error; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 7e3b9b01431e..a3e0e6f672d6 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -605,7 +605,6 @@ xfs_bmap_btree_to_extents( ASSERT(cur); ASSERT(whichfork != XFS_COW_FORK); - ASSERT(!xfs_need_iread_extents(ifp)); ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE); ASSERT(be16_to_cpu(rblock->bb_level) == 1); ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1); @@ -5350,7 +5349,6 @@ __xfs_bunmapi( xfs_fsblock_t sum; xfs_filblks_t len = *rlen; /* length to unmap in file */ xfs_fileoff_t max_len; - xfs_agnumber_t prev_agno = NULLAGNUMBER, agno; xfs_fileoff_t end; struct xfs_iext_cursor icur; bool done = false; @@ -5442,16 +5440,6 @@ __xfs_bunmapi( del = got; wasdel = isnullstartblock(del.br_startblock); - /* - * Make sure we don't touch multiple AGF headers out of order - * in a single transaction, as that could cause AB-BA deadlocks. - */ - if (!wasdel && !isrt) { - agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); - if (prev_agno != NULLAGNUMBER && prev_agno > agno) - break; - prev_agno = agno; - } if (got.br_startoff < start) { del.br_startoff = start; del.br_blockcount -= start - got.br_startoff; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 5c9a7440d9e4..f3254a4f4cb4 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -559,8 +559,17 @@ xfs_dinode_calc_crc( /* * Validate di_extsize hint. * - * The rules are documented at xfs_ioctl_setattr_check_extsize(). - * These functions must be kept in sync with each other. + * 1. Extent size hint is only valid for directories and regular files. + * 2. FS_XFLAG_EXTSIZE is only valid for regular files. + * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories. + * 4. Hint cannot be larger than MAXTEXTLEN. + * 5. Can be changed on directories at any time. + * 6. Hint value of 0 turns off hints, clears inode flags. + * 7. Extent size must be a multiple of the appropriate block size. + * For realtime files, this is the rt extent size. + * 8. For non-realtime files, the extent size hint must be limited + * to half the AG size to avoid alignment extending the extent beyond the + * limits of the AG. */ xfs_failaddr_t xfs_inode_validate_extsize( @@ -580,6 +589,28 @@ xfs_inode_validate_extsize( inherit_flag = (flags & XFS_DIFLAG_EXTSZINHERIT); extsize_bytes = XFS_FSB_TO_B(mp, extsize); + /* + * This comment describes a historic gap in this verifier function. + * + * On older kernels, the extent size hint verifier doesn't check that + * the extent size hint is an integer multiple of the realtime extent + * size on a directory with both RTINHERIT and EXTSZINHERIT flags set. + * The verifier has always enforced the alignment rule for regular + * files with the REALTIME flag set. + * + * If a directory with a misaligned extent size hint is allowed to + * propagate that hint into a new regular realtime file, the result + * is that the inode cluster buffer verifier will trigger a corruption + * shutdown the next time it is run. + * + * Unfortunately, there could be filesystems with these misconfigured + * directories in the wild, so we cannot add a check to this verifier + * at this time because that will result a new source of directory + * corruption errors when reading an existing filesystem. Instead, we + * permit the misconfiguration to pass through the verifiers so that + * callers of this function can correct and mitigate externally. + */ + if (rt_flag) blocksize_bytes = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; else @@ -616,8 +647,15 @@ xfs_inode_validate_extsize( /* * Validate di_cowextsize hint. * - * The rules are documented at xfs_ioctl_setattr_check_cowextsize(). - * These functions must be kept in sync with each other. + * 1. CoW extent size hint can only be set if reflink is enabled on the fs. + * The inode does not have to have any shared blocks, but it must be a v3. + * 2. FS_XFLAG_COWEXTSIZE is only valid for directories and regular files; + * for a directory, the hint is propagated to new files. + * 3. Can be changed on files & directories at any time. + * 4. Hint value of 0 turns off hints, clears inode flags. + * 5. Extent size must be a multiple of the appropriate block size. + * 6. The extent size hint must be limited to half the AG size to avoid + * alignment extending the extent beyond the limits of the AG. */ xfs_failaddr_t xfs_inode_validate_cowextsize( diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 78324e043e25..8d595a5c4abd 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -143,6 +143,23 @@ xfs_trans_log_inode( } /* + * Inode verifiers on older kernels don't check that the extent size + * hint is an integer multiple of the rt extent size on a directory + * with both rtinherit and extszinherit flags set. If we're logging a + * directory that is misconfigured in this way, clear the hint. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && + (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) { + xfs_info_once(ip->i_mount, + "Correcting misaligned extent size hint in inode 0x%llx.", ip->i_ino); + ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | + XFS_DIFLAG_EXTSZINHERIT); + ip->i_extsize = 0; + flags |= XFS_ILOG_CORE; + } + + /* * Record the specific change for fdatasync optimisation. This allows * fdatasync to skip log forces for inodes that are only timestamp * dirty. diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 0369eb22c1bb..e4c2da4566f1 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -690,6 +690,7 @@ xfs_inode_inherit_flags( const struct xfs_inode *pip) { unsigned int di_flags = 0; + xfs_failaddr_t failaddr; umode_t mode = VFS_I(ip)->i_mode; if (S_ISDIR(mode)) { @@ -729,6 +730,24 @@ xfs_inode_inherit_flags( di_flags |= XFS_DIFLAG_FILESTREAM; ip->i_diflags |= di_flags; + + /* + * Inode verifiers on older kernels only check that the extent size + * hint is an integer multiple of the rt extent size on realtime files. + * They did not check the hint alignment on a directory with both + * rtinherit and extszinherit flags set. If the misaligned hint is + * propagated from a directory into a new realtime file, new file + * allocations will fail due to math errors in the rt allocator and/or + * trip the verifiers. Validate the hint settings in the new file so + * that we don't let broken hints propagate. + */ + failaddr = xfs_inode_validate_extsize(ip->i_mount, ip->i_extsize, + VFS_I(ip)->i_mode, ip->i_diflags); + if (failaddr) { + ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | + XFS_DIFLAG_EXTSZINHERIT); + ip->i_extsize = 0; + } } /* Propagate di_flags2 from a parent inode to a child inode. */ @@ -737,12 +756,22 @@ xfs_inode_inherit_flags2( struct xfs_inode *ip, const struct xfs_inode *pip) { + xfs_failaddr_t failaddr; + if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) { ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE; ip->i_cowextsize = pip->i_cowextsize; } if (pip->i_diflags2 & XFS_DIFLAG2_DAX) ip->i_diflags2 |= XFS_DIFLAG2_DAX; + + /* Don't let invalid cowextsize hints propagate. */ + failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize, + VFS_I(ip)->i_mode, ip->i_diflags, ip->i_diflags2); + if (failaddr) { + ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = 0; + } } /* diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 3925bfcb2365..1fe4c1fc0aea 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1267,20 +1267,8 @@ out_error: } /* - * extent size hint validation is somewhat cumbersome. Rules are: - * - * 1. extent size hint is only valid for directories and regular files - * 2. FS_XFLAG_EXTSIZE is only valid for regular files - * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories. - * 4. can only be changed on regular files if no extents are allocated - * 5. can be changed on directories at any time - * 6. extsize hint of 0 turns off hints, clears inode flags. - * 7. Extent size must be a multiple of the appropriate block size. - * 8. for non-realtime files, the extent size hint must be limited - * to half the AG size to avoid alignment extending the extent beyond the - * limits of the AG. - * - * Please keep this function in sync with xfs_scrub_inode_extsize. + * Validate a proposed extent size hint. For regular files, the hint can only + * be changed if no extents are allocated. */ static int xfs_ioctl_setattr_check_extsize( @@ -1288,86 +1276,65 @@ xfs_ioctl_setattr_check_extsize( struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; - xfs_extlen_t size; - xfs_fsblock_t extsize_fsb; + xfs_failaddr_t failaddr; + uint16_t new_diflags; if (!fa->fsx_valid) return 0; if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents && - ((ip->i_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) + XFS_FSB_TO_B(mp, ip->i_extsize) != fa->fsx_extsize) return -EINVAL; - if (fa->fsx_extsize == 0) - return 0; - - extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); - if (extsize_fsb > MAXEXTLEN) + if (fa->fsx_extsize & mp->m_blockmask) return -EINVAL; - if (XFS_IS_REALTIME_INODE(ip) || - (fa->fsx_xflags & FS_XFLAG_REALTIME)) { - size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; - } else { - size = mp->m_sb.sb_blocksize; - if (extsize_fsb > mp->m_sb.sb_agblocks / 2) + new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); + + /* + * Inode verifiers on older kernels don't check that the extent size + * hint is an integer multiple of the rt extent size on a directory + * with both rtinherit and extszinherit flags set. Don't let sysadmins + * misconfigure directories. + */ + if ((new_diflags & XFS_DIFLAG_RTINHERIT) && + (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) { + unsigned int rtextsize_bytes; + + rtextsize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); + if (fa->fsx_extsize % rtextsize_bytes) return -EINVAL; } - if (fa->fsx_extsize % size) - return -EINVAL; - - return 0; + failaddr = xfs_inode_validate_extsize(ip->i_mount, + XFS_B_TO_FSB(mp, fa->fsx_extsize), + VFS_I(ip)->i_mode, new_diflags); + return failaddr != NULL ? -EINVAL : 0; } -/* - * CoW extent size hint validation rules are: - * - * 1. CoW extent size hint can only be set if reflink is enabled on the fs. - * The inode does not have to have any shared blocks, but it must be a v3. - * 2. FS_XFLAG_COWEXTSIZE is only valid for directories and regular files; - * for a directory, the hint is propagated to new files. - * 3. Can be changed on files & directories at any time. - * 4. CoW extsize hint of 0 turns off hints, clears inode flags. - * 5. Extent size must be a multiple of the appropriate block size. - * 6. The extent size hint must be limited to half the AG size to avoid - * alignment extending the extent beyond the limits of the AG. - * - * Please keep this function in sync with xfs_scrub_inode_cowextsize. - */ static int xfs_ioctl_setattr_check_cowextsize( struct xfs_inode *ip, struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; - xfs_extlen_t size; - xfs_fsblock_t cowextsize_fsb; + xfs_failaddr_t failaddr; + uint64_t new_diflags2; + uint16_t new_diflags; if (!fa->fsx_valid) return 0; - if (!(fa->fsx_xflags & FS_XFLAG_COWEXTSIZE)) - return 0; - - if (!xfs_sb_version_hasreflink(&ip->i_mount->m_sb)) + if (fa->fsx_cowextsize & mp->m_blockmask) return -EINVAL; - if (fa->fsx_cowextsize == 0) - return 0; + new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); + new_diflags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); - cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize); - if (cowextsize_fsb > MAXEXTLEN) - return -EINVAL; - - size = mp->m_sb.sb_blocksize; - if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2) - return -EINVAL; - - if (fa->fsx_cowextsize % size) - return -EINVAL; - - return 0; + failaddr = xfs_inode_validate_cowextsize(ip->i_mount, + XFS_B_TO_FSB(mp, fa->fsx_cowextsize), + VFS_I(ip)->i_mode, new_diflags, new_diflags2); + return failaddr != NULL ? -EINVAL : 0; } static int diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h index 3c392b1512ac..7ec1a9207517 100644 --- a/fs/xfs/xfs_message.h +++ b/fs/xfs/xfs_message.h @@ -73,6 +73,8 @@ do { \ xfs_printk_once(xfs_warn, dev, fmt, ##__VA_ARGS__) #define xfs_notice_once(dev, fmt, ...) \ xfs_printk_once(xfs_notice, dev, fmt, ##__VA_ARGS__) +#define xfs_info_once(dev, fmt, ...) \ + xfs_printk_once(xfs_info, dev, fmt, ##__VA_ARGS__) void assfail(struct xfs_mount *mp, char *expr, char *f, int l); void asswarn(struct xfs_mount *mp, char *expr, char *f, int l); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 40a9c101565e..17325416e2de 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -960,6 +960,7 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT #define PERCPU_DECRYPTED_SECTION \ . = ALIGN(PAGE_SIZE); \ + *(.data..decrypted) \ *(.data..percpu..decrypted) \ . = ALIGN(PAGE_SIZE); #else diff --git a/include/dt-bindings/usb/pd.h b/include/dt-bindings/usb/pd.h index fef3ef65967f..e6526b138174 100644 --- a/include/dt-bindings/usb/pd.h +++ b/include/dt-bindings/usb/pd.h @@ -106,6 +106,10 @@ * <20:16> :: Reserved, Shall be set to zero * <15:0> :: USB-IF assigned VID for this cable vendor */ + +/* PD Rev2.0 definition */ +#define IDH_PTYPE_UNDEF 0 + /* SOP Product Type (UFP) */ #define IDH_PTYPE_NOT_UFP 0 #define IDH_PTYPE_HUB 1 @@ -163,10 +167,10 @@ #define UFP_VDO_VER1_2 2 /* Device Capability */ -#define DEV_USB2_CAPABLE BIT(0) -#define DEV_USB2_BILLBOARD BIT(1) -#define DEV_USB3_CAPABLE BIT(2) -#define DEV_USB4_CAPABLE BIT(3) +#define DEV_USB2_CAPABLE (1 << 0) +#define DEV_USB2_BILLBOARD (1 << 1) +#define DEV_USB3_CAPABLE (1 << 2) +#define DEV_USB4_CAPABLE (1 << 3) /* Connector Type */ #define UFP_RECEPTACLE 2 @@ -191,9 +195,9 @@ /* Alternate Modes */ #define UFP_ALTMODE_NOT_SUPP 0 -#define UFP_ALTMODE_TBT3 BIT(0) -#define UFP_ALTMODE_RECFG BIT(1) -#define UFP_ALTMODE_NO_RECFG BIT(2) +#define UFP_ALTMODE_TBT3 (1 << 0) +#define UFP_ALTMODE_RECFG (1 << 1) +#define UFP_ALTMODE_NO_RECFG (1 << 2) /* USB Highest Speed */ #define UFP_USB2_ONLY 0 @@ -217,9 +221,9 @@ * <4:0> :: Port number */ #define DFP_VDO_VER1_1 1 -#define HOST_USB2_CAPABLE BIT(0) -#define HOST_USB3_CAPABLE BIT(1) -#define HOST_USB4_CAPABLE BIT(2) +#define HOST_USB2_CAPABLE (1 << 0) +#define HOST_USB3_CAPABLE (1 << 1) +#define HOST_USB4_CAPABLE (1 << 2) #define DFP_RECEPTACLE 2 #define DFP_CAPTIVE 3 @@ -228,7 +232,25 @@ | ((pnum) & 0x1f)) /* - * Passive Cable VDO + * Cable VDO (for both Passive and Active Cable VDO in PD Rev2.0) + * --------- + * <31:28> :: Cable HW version + * <27:24> :: Cable FW version + * <23:20> :: Reserved, Shall be set to zero + * <19:18> :: type-C to Type-A/B/C/Captive (00b == A, 01 == B, 10 == C, 11 == Captive) + * <17> :: Reserved, Shall be set to zero + * <16:13> :: cable latency (0001 == <10ns(~1m length)) + * <12:11> :: cable termination type (11b == both ends active VCONN req) + * <10> :: SSTX1 Directionality support (0b == fixed, 1b == cfgable) + * <9> :: SSTX2 Directionality support + * <8> :: SSRX1 Directionality support + * <7> :: SSRX2 Directionality support + * <6:5> :: Vbus current handling capability (01b == 3A, 10b == 5A) + * <4> :: Vbus through cable (0b == no, 1b == yes) + * <3> :: SOP" controller present? (0b == no, 1b == yes) + * <2:0> :: USB SS Signaling support + * + * Passive Cable VDO (PD Rev3.0+) * --------- * <31:28> :: Cable HW version * <27:24> :: Cable FW version @@ -244,7 +266,7 @@ * <4:3> :: Reserved, Shall be set to zero * <2:0> :: USB highest speed * - * Active Cable VDO 1 + * Active Cable VDO 1 (PD Rev3.0+) * --------- * <31:28> :: Cable HW version * <27:24> :: Cable FW version @@ -266,7 +288,9 @@ #define CABLE_VDO_VER1_0 0 #define CABLE_VDO_VER1_3 3 -/* Connector Type */ +/* Connector Type (_ATYPE and _BTYPE are for PD Rev2.0 only) */ +#define CABLE_ATYPE 0 +#define CABLE_BTYPE 1 #define CABLE_CTYPE 2 #define CABLE_CAPTIVE 3 @@ -303,12 +327,22 @@ #define CABLE_CURR_3A 1 #define CABLE_CURR_5A 2 +/* USB SuperSpeed Signaling Support (PD Rev2.0) */ +#define CABLE_USBSS_U2_ONLY 0 +#define CABLE_USBSS_U31_GEN1 1 +#define CABLE_USBSS_U31_GEN2 2 + /* USB Highest Speed */ #define CABLE_USB2_ONLY 0 #define CABLE_USB32_GEN1 1 #define CABLE_USB32_4_GEN2 2 #define CABLE_USB4_GEN3 3 +#define VDO_CABLE(hw, fw, cbl, lat, term, tx1d, tx2d, rx1d, rx2d, cur, vps, sopp, usbss) \ + (((hw) & 0x7) << 28 | ((fw) & 0x7) << 24 | ((cbl) & 0x3) << 18 \ + | ((lat) & 0x7) << 13 | ((term) & 0x3) << 11 | (tx1d) << 10 \ + | (tx2d) << 9 | (rx1d) << 8 | (rx2d) << 7 | ((cur) & 0x3) << 5 \ + | (vps) << 4 | (sopp) << 3 | ((usbss) & 0x7)) #define VDO_PCABLE(hw, fw, ver, conn, lat, term, vbm, cur, spd) \ (((hw) & 0xf) << 28 | ((fw) & 0xf) << 24 | ((ver) & 0x7) << 21 \ | ((conn) & 0x3) << 18 | ((lat) & 0xf) << 13 | ((term) & 0x3) << 11 \ @@ -374,6 +408,35 @@ | (iso) << 2 | (gen)) /* + * AMA VDO (PD Rev2.0) + * --------- + * <31:28> :: Cable HW version + * <27:24> :: Cable FW version + * <23:12> :: Reserved, Shall be set to zero + * <11> :: SSTX1 Directionality support (0b == fixed, 1b == cfgable) + * <10> :: SSTX2 Directionality support + * <9> :: SSRX1 Directionality support + * <8> :: SSRX2 Directionality support + * <7:5> :: Vconn power + * <4> :: Vconn power required + * <3> :: Vbus power required + * <2:0> :: USB SS Signaling support + */ +#define VDO_AMA(hw, fw, tx1d, tx2d, rx1d, rx2d, vcpwr, vcr, vbr, usbss) \ + (((hw) & 0x7) << 28 | ((fw) & 0x7) << 24 \ + | (tx1d) << 11 | (tx2d) << 10 | (rx1d) << 9 | (rx2d) << 8 \ + | ((vcpwr) & 0x7) << 5 | (vcr) << 4 | (vbr) << 3 \ + | ((usbss) & 0x7)) + +#define PD_VDO_AMA_VCONN_REQ(vdo) (((vdo) >> 4) & 1) +#define PD_VDO_AMA_VBUS_REQ(vdo) (((vdo) >> 3) & 1) + +#define AMA_USBSS_U2_ONLY 0 +#define AMA_USBSS_U31_GEN1 1 +#define AMA_USBSS_U31_GEN2 2 +#define AMA_USBSS_BBONLY 3 + +/* * VPD VDO * --------- * <31:28> :: HW version diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index f180240dc95f..11e555cfaecb 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -37,7 +37,6 @@ bool topology_scale_freq_invariant(void); enum scale_freq_source { SCALE_FREQ_SOURCE_CPUFREQ = 0, SCALE_FREQ_SOURCE_ARCH, - SCALE_FREQ_SOURCE_CPPC, }; struct scale_freq_data { diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 565deea6ffe8..8612f8fc86c1 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -830,6 +830,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_proto_hdr); struct virtchnl_proto_hdrs { u8 tunnel_level; + u8 pad[3]; /** * specify where protocol header start from. * 0 - from the outer layer diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 559ee05f86b2..fb8f6d2cd104 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -232,7 +232,7 @@ struct css_set { struct list_head task_iters; /* - * On the default hierarhcy, ->subsys[ssid] may point to a css + * On the default hierarchy, ->subsys[ssid] may point to a css * attached to an ancestor instead of the cgroup this css_set is * associated with. The following node is anchored at * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to @@ -668,7 +668,7 @@ struct cgroup_subsys { */ bool threaded:1; - /* the following two fields are initialized automtically during boot */ + /* the following two fields are initialized automatically during boot */ int id; const char *name; @@ -757,7 +757,7 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. * On boot, sock_cgroup_data records the cgroup that the sock was created * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overriden to carry prioidx and/or + * net_cls starts being used, the area is overridden to carry prioidx and/or * classid. The two modes are distinguished by whether the lowest bit is * set. Clear bit indicates cgroup pointer while set bit prioidx and * classid. diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4f2f79de083e..6bc9c76680b2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -32,7 +32,7 @@ struct kernel_clone_args; #ifdef CONFIG_CGROUPS /* - * All weight knobs on the default hierarhcy should use the following min, + * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index c043b8d2b17b..183ddd5fd072 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -199,6 +199,7 @@ * must end with any of these keywords: * break; * fallthrough; + * continue; * goto <label>; * return [expression]; * diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..f1a00040fa53 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -570,7 +570,7 @@ struct device { * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. - * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. + * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { @@ -583,9 +583,7 @@ struct device_link { u32 flags; refcount_t rpm_active; struct kref kref; -#ifdef CONFIG_SRCU - struct rcu_head rcu_head; -#endif + struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 8b2b1d68b954..136b8d97d8c0 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -3,6 +3,7 @@ #define __LINUX_ENTRYKVM_H #include <linux/entry-common.h> +#include <linux/tick.h> /* Transfer to guest mode work */ #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK @@ -57,7 +58,7 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu); static inline void xfer_to_guest_mode_prepare(void) { lockdep_assert_irqs_disabled(); - rcu_nocb_flush_deferred_wakeup(); + tick_nohz_user_enter_prepare(); } /** diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index bad41bcb25df..a16dbeced152 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -51,6 +51,10 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_INIT_FLAGS (FANOTIFY_ADMIN_INIT_FLAGS | \ FANOTIFY_USER_INIT_FLAGS) +/* Internal group flags */ +#define FANOTIFY_UNPRIV 0x80000000 +#define FANOTIFY_INTERNAL_GROUP_FLAGS (FANOTIFY_UNPRIV) + #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ FAN_MARK_FILESYSTEM) diff --git a/include/linux/fb.h b/include/linux/fb.h index a8dccd23c249..ecfbcc0553a5 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -659,6 +659,9 @@ static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, /* drivers/video/fb_defio.c */ int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma); extern void fb_deferred_io_init(struct fb_info *info); +extern void fb_deferred_io_open(struct fb_info *info, + struct inode *inode, + struct file *file); extern void fb_deferred_io_cleanup(struct fb_info *info); extern int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasync); diff --git a/include/linux/hid.h b/include/linux/hid.h index 271021e20a3f..10e922cee4eb 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1167,8 +1167,7 @@ static inline void hid_hw_wait(struct hid_device *hdev) */ static inline u32 hid_report_len(struct hid_report *report) { - /* equivalent to DIV_ROUND_UP(report->size, 8) + !!(report->id > 0) */ - return ((report->size - 1) >> 3) + 1 + (report->id > 0); + return DIV_ROUND_UP(report->size, 8) + (report->id > 0); } int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 232e1bd507a7..9b0487c88571 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -332,12 +332,30 @@ static inline struct host1x_device *to_host1x_device(struct device *dev) int host1x_device_init(struct host1x_device *device); int host1x_device_exit(struct host1x_device *device); -int __host1x_client_register(struct host1x_client *client, - struct lock_class_key *key); -#define host1x_client_register(class) \ - ({ \ - static struct lock_class_key __key; \ - __host1x_client_register(class, &__key); \ +void __host1x_client_init(struct host1x_client *client, struct lock_class_key *key); +void host1x_client_exit(struct host1x_client *client); + +#define host1x_client_init(client) \ + ({ \ + static struct lock_class_key __key; \ + __host1x_client_init(client, &__key); \ + }) + +int __host1x_client_register(struct host1x_client *client); + +/* + * Note that this wrapper calls __host1x_client_init() for compatibility + * with existing callers. Callers that want to separately initialize and + * register a host1x client must first initialize using either of the + * __host1x_client_init() or host1x_client_init() functions and then use + * the low-level __host1x_client_register() function to avoid the client + * getting reinitialized. + */ +#define host1x_client_register(client) \ + ({ \ + static struct lock_class_key __key; \ + __host1x_client_init(client, &__key); \ + __host1x_client_register(client); \ }) int host1x_client_unregister(struct host1x_client *client); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9626fda5efce..2a8ebe6c222e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -286,6 +286,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; +extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_page(struct page *page) { @@ -294,7 +295,7 @@ static inline bool is_huge_zero_page(struct page *page) static inline bool is_huge_zero_pmd(pmd_t pmd) { - return is_huge_zero_page(pmd_page(pmd)); + return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); } static inline bool is_huge_zero_pud(pud_t pud) @@ -440,6 +441,11 @@ static inline bool is_huge_zero_page(struct page *page) return false; } +static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return false; +} + static inline bool is_huge_zero_pud(pud_t pud) { return false; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b92f25ccef58..6504346a1947 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -149,6 +149,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_huge_page(struct page *page, struct list_head *list); +int get_hwpoison_huge_page(struct page *page, bool *hugetlb); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -339,6 +340,11 @@ static inline bool isolate_huge_page(struct page *page, struct list_head *list) return false; } +static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +{ + return 0; +} + static inline void putback_active_hugepage(struct page *page) { } @@ -604,6 +610,8 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h); diff --git a/include/linux/init.h b/include/linux/init.h index 045ad1650ed1..d82b4b2e1d25 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -242,7 +242,8 @@ extern bool initcall_debug; asm(".section \"" __sec "\", \"a\" \n" \ __stringify(__name) ": \n" \ ".long " __stringify(__stub) " - . \n" \ - ".previous \n"); + ".previous \n"); \ + static_assert(__same_type(initcall_t, &fn)); #else #define ____define_initcall(fn, __unused, __name, __sec) \ static initcall_t __name __used \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2f34487e21f2..8583ed3ff344 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,6 +10,7 @@ #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> +#include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> @@ -146,7 +147,7 @@ static inline bool is_error_page(struct page *page) */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 #define KVM_REQUEST_ARCH_BASE 8 @@ -265,6 +266,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. @@ -1179,7 +1185,15 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { - return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; + /* + * The index was checked originally in search_memslots. To avoid + * that a malicious guest builds a Spectre gadget out of e.g. page + * table walks, do not let the processor speculate loads outside + * the guest's registered memslots. + */ + unsigned long offset = gfn - slot->base_gfn; + offset = array_index_nospec(offset, slot->npages); + return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h index a57af878fd0c..4a5966475a35 100644 --- a/include/linux/mfd/rohm-bd70528.h +++ b/include/linux/mfd/rohm-bd70528.h @@ -26,9 +26,7 @@ struct bd70528_data { struct mutex rtc_timer_lock; }; -#define BD70528_BUCK_VOLTS 17 -#define BD70528_BUCK_VOLTS 17 -#define BD70528_BUCK_VOLTS 17 +#define BD70528_BUCK_VOLTS 0x10 #define BD70528_LDO_VOLTS 0x20 #define BD70528_REG_BUCK1_EN 0x0F diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index c7ab69c87ee8..3b5f3a7db4bd 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -26,11 +26,11 @@ enum { BD71828_REGULATOR_AMOUNT, }; -#define BD71828_BUCK1267_VOLTS 0xEF -#define BD71828_BUCK3_VOLTS 0x10 -#define BD71828_BUCK4_VOLTS 0x20 -#define BD71828_BUCK5_VOLTS 0x10 -#define BD71828_LDO_VOLTS 0x32 +#define BD71828_BUCK1267_VOLTS 0x100 +#define BD71828_BUCK3_VOLTS 0x20 +#define BD71828_BUCK4_VOLTS 0x40 +#define BD71828_BUCK5_VOLTS 0x20 +#define BD71828_LDO_VOLTS 0x40 /* LDO6 is fixed 1.8V voltage */ #define BD71828_LDO_6_VOLTAGE 1800000 diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 236a7d04f891..30bb59fe970c 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -630,6 +630,7 @@ struct mlx4_caps { bool wol_port[MLX4_MAX_PORTS + 1]; struct mlx4_rate_limit_caps rl_caps; u32 health_buffer_addrs; + bool map_clock_to_user; }; struct mlx4_buf_list { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8e8d7e90616..f8902bcd91e2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -542,6 +542,10 @@ struct mlx5_core_roce { enum { MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0, MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1, + /* Set during device detach to block any further devices + * creation/deletion on drivers rescan. Unset during device attach. + */ + MLX5_PRIV_FLAGS_DETACH = 1 << 2, }; struct mlx5_adev { @@ -703,6 +707,27 @@ struct mlx5_hv_vhca; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) +enum { + MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, + MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, +}; + +enum { + MR_CACHE_LAST_STD_ENTRY = 20, + MLX5_IMR_MTT_CACHE_ENTRY, + MLX5_IMR_KSM_CACHE_ENTRY, + MAX_MR_CACHE_ENTRIES +}; + +struct mlx5_profile { + u64 mask; + u8 log_max_qp; + struct { + int size; + int limit; + } mr_cache[MAX_MR_CACHE_ENTRIES]; +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -731,7 +756,7 @@ struct mlx5_core_dev { struct mutex intf_state_mutex; unsigned long intf_state; struct mlx5_priv priv; - struct mlx5_profile *profile; + struct mlx5_profile profile; u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_dm *dm; @@ -1083,18 +1108,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey) return mkey & 0xff; } -enum { - MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, - MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, -}; - -enum { - MR_CACHE_LAST_STD_ENTRY = 20, - MLX5_IMR_MTT_CACHE_ENTRY, - MLX5_IMR_KSM_CACHE_ENTRY, - MAX_MR_CACHE_ENTRIES -}; - /* Async-atomic event notifier used by mlx5 core to forward FW * evetns recived from event queue to mlx5 consumers. * Optimise event queue dipatching. @@ -1148,15 +1161,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, struct ib_device *device, struct rdma_netdev_alloc_params *params); -struct mlx5_profile { - u64 mask; - u8 log_max_qp; - struct { - int size; - int limit; - } mr_cache[MAX_MR_CACHE_ENTRIES]; -}; - enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6d16eed6850e..eb86e80e4643 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1289,6 +1289,8 @@ enum mlx5_fc_bulk_alloc_bitmask { #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) +#define MLX5_FT_MAX_MULTIPATH_LEVEL 63 + enum { MLX5_STEERING_FORMAT_CONNECTX_5 = 0, MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, diff --git a/include/linux/mlx5/mpfs.h b/include/linux/mlx5/mpfs.h new file mode 100644 index 000000000000..bf700c8d5516 --- /dev/null +++ b/include/linux/mlx5/mpfs.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2021 Mellanox Technologies Ltd. + */ + +#ifndef _MLX5_MPFS_ +#define _MLX5_MPFS_ + +struct mlx5_core_dev; + +#ifdef CONFIG_MLX5_MPFS +int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); +int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); +#else /* #ifndef CONFIG_MLX5_MPFS */ +static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +#endif + +#endif diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 028f442530cf..60ffeb6b67ae 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -85,4 +85,5 @@ mlx5_core_hairpin_create(struct mlx5_core_dev *func_mdev, struct mlx5_hairpin_params *params); void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair); +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp); #endif /* __TRANSOBJ_H__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index c274f75efcf9..8ae31622deef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1719,6 +1719,7 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ + struct page *single_page; /* Locked page to be unmapped */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, @@ -1766,6 +1767,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); +void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1786,6 +1788,7 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, BUG(); return -EFAULT; } +static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5aacc1c10a45..8f0fb62e8975 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,13 +445,6 @@ struct mm_struct { */ atomic_t has_pinned; - /** - * @write_protect_seq: Locked when any thread is write - * protecting pages mapped by this mm to enforce a later COW, - * for instance during page table copying for fork(). - */ - seqcount_t write_protect_seq; - #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif @@ -460,6 +453,18 @@ struct mm_struct { spinlock_t page_table_lock; /* Protects page tables and some * counters */ + /* + * With some kernel config, the current mmap_lock's offset + * inside 'mm_struct' is at 0x120, which is very optimal, as + * its two hot fields 'count' and 'owner' sit in 2 different + * cachelines, and when mmap_lock is highly contended, both + * of the 2 fields will be accessed frequently, current layout + * will help to reduce cache bouncing. + * + * So please be careful with adding new fields before + * mmap_lock, which can easily push the 2 fields into one + * cacheline. + */ struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These @@ -480,7 +485,15 @@ struct mm_struct { unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; + /** + * @write_protect_seq: Locked when any thread is write + * protecting pages mapped by this mm to enforce a later COW, + * for instance during page table copying for fork(). + */ + seqcount_t write_protect_seq; + spinlock_t arg_lock; /* protect the below fields */ + unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; diff --git a/include/linux/pci.h b/include/linux/pci.h index 4c048ed5bc55..d1f0916c6a37 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2347,6 +2347,7 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, struct device_node; struct irq_domain; struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus); +bool pci_host_of_has_msi_map(struct device *dev); /* Arch may override this (weak) */ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); @@ -2354,6 +2355,7 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); #else /* CONFIG_OF */ static inline struct irq_domain * pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } +static inline bool pci_host_of_has_msi_map(struct device *dev) { return false; } #endif /* CONFIG_OF */ static inline struct device_node * diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 46b13780c2c8..a43047b1030d 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -432,6 +432,14 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ +#ifndef pte_sw_mkyoung +static inline pte_t pte_sw_mkyoung(pte_t pte) +{ + return pte; +} +#define pte_sw_mkyoung pte_sw_mkyoung +#endif + #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 60d2b26026a2..852743f07e3e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -496,6 +496,11 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. + * Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * Bits [23:16] are currently reserved for future use. + * Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index fafc1beea504..9837fb011f2f 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -50,6 +50,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_QUIRK_REINIT_ON_RESUME BIT(27) #define SYSC_QUIRK_GPMC_DEBUG BIT(26) #define SYSC_MODULE_QUIRK_ENA_RESETDONE BIT(25) #define SYSC_MODULE_QUIRK_PRUSS BIT(24) diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 0d47fd33b228..51d7f1b8b32a 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -235,7 +235,7 @@ extern int ptp_clock_index(struct ptp_clock *ptp); * @ppm: Parts per million, but with a 16 bit binary fractional field */ -extern s32 scaled_ppm_to_ppb(long ppm); +extern long scaled_ppm_to_ppb(long ppm); /** * ptp_find_pin() - obtain the pin index of a given auxiliary function diff --git a/include/linux/rmap.h b/include/linux/rmap.h index def5c62c93b3..8d04e7deedc6 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -91,6 +91,7 @@ enum ttu_flags { TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ + TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */ TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 6f155f99aa16..4ab7bfc675f1 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1109,6 +1109,7 @@ struct pcr_ops { }; enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; +enum ASPM_MODE {ASPM_MODE_CFG, ASPM_MODE_REG}; #define ASPM_L1_1_EN BIT(0) #define ASPM_L1_2_EN BIT(1) @@ -1234,6 +1235,7 @@ struct rtsx_pcr { u8 card_drive_sel; #define ASPM_L1_EN 0x02 u8 aspm_en; + enum ASPM_MODE aspm_mode; bool aspm_enabled; #define PCR_MS_PMOS (1 << 0) diff --git a/include/linux/sched.h b/include/linux/sched.h index d2c881384517..28a98fc4ded4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -350,11 +350,19 @@ struct load_weight { * Only for tasks we track a moving average of the past instantaneous * estimated utilization. This allows to absorb sporadic drops in utilization * of an otherwise almost periodic task. + * + * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg + * updates. When a task is dequeued, its util_est should not be updated if its + * util_avg has not been updated in the meantime. + * This information is mapped into the MSB bit of util_est.enqueued at dequeue + * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg + * for a task) it is safe to use MSB. */ struct util_est { unsigned int enqueued; unsigned int ewma; #define UTIL_EST_WEIGHT_SHIFT 2 +#define UTIL_AVG_UNCHANGED 0x80000000 } __attribute__((__aligned__(sizeof(u64)))); /* diff --git a/include/linux/socket.h b/include/linux/socket.h index b8fc5c53ba6f..0d8e3dcb7f88 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); - -extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 360a3bc767ca..74239d65c7fd 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -644,8 +644,8 @@ struct spi_controller { int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; - u8 unused_native_cs; - u8 max_native_cs; + s8 unused_native_cs; + s8 max_native_cs; /* statistics */ struct spi_statistics statistics; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d81fe8b364d0..61b622e334ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -368,6 +368,8 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size, unsigned int num_prealloc, unsigned int max_req); void xprt_free(struct rpc_xprt *); +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task); +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req); static inline int xprt_enable_swap(struct rpc_xprt *xprt) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d9b7c9132c2f..6430a94c6981 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -23,6 +23,16 @@ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) +/* Clear all flags but only keep swp_entry_t related information */ +static inline pte_t pte_swp_clear_flags(pte_t pte) +{ + if (pte_swp_soft_dirty(pte)) + pte = pte_swp_clear_soft_dirty(pte); + if (pte_swp_uffd_wp(pte)) + pte = pte_swp_clear_uffd_wp(pte); + return pte; +} + /* * Store a type+offset into a swp_entry_t in an arch-independent format */ @@ -66,10 +76,7 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; - if (pte_swp_soft_dirty(pte)) - pte = pte_swp_clear_soft_dirty(pte); - if (pte_swp_uffd_wp(pte)) - pte = pte_swp_clear_uffd_wp(pte); + pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } diff --git a/include/linux/tick.h b/include/linux/tick.h index 7340613c7eff..1a0ff88fa107 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -11,6 +11,7 @@ #include <linux/context_tracking_state.h> #include <linux/cpumask.h> #include <linux/sched.h> +#include <linux/rcupdate.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void __init tick_init(void); @@ -300,4 +301,10 @@ static inline void tick_nohz_task_switch(void) __tick_nohz_task_switch(); } +static inline void tick_nohz_user_enter_prepare(void) +{ + if (tick_nohz_full_cpu(smp_processor_id())) + rcu_nocb_flush_deferred_wakeup(); +} + #endif diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index bf00259493e0..96b7ff66f074 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -460,7 +460,7 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_RECEIVER_RESPONSE 15 /* 15ms max */ #define PD_T_SOURCE_ACTIVITY 45 #define PD_T_SINK_ACTIVITY 135 -#define PD_T_SINK_WAIT_CAP 240 +#define PD_T_SINK_WAIT_CAP 310 /* 310 - 620 ms */ #define PD_T_PS_TRANSITION 500 #define PD_T_SRC_TRANSITION 35 #define PD_T_DRP_SNK 40 diff --git a/include/linux/usb/pd_ext_sdb.h b/include/linux/usb/pd_ext_sdb.h index 0eb83ce19597..b517ebc8f0ff 100644 --- a/include/linux/usb/pd_ext_sdb.h +++ b/include/linux/usb/pd_ext_sdb.h @@ -24,8 +24,4 @@ enum usb_pd_ext_sdb_fields { #define USB_PD_EXT_SDB_EVENT_OVP BIT(3) #define USB_PD_EXT_SDB_EVENT_CF_CV_MODE BIT(4) -#define USB_PD_EXT_SDB_PPS_EVENTS (USB_PD_EXT_SDB_EVENT_OCP | \ - USB_PD_EXT_SDB_EVENT_OTP | \ - USB_PD_EXT_SDB_EVENT_OVP) - #endif /* __LINUX_USB_PD_EXT_SDB_H */ diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h index 48ecca8530ff..b655d8666f55 100644 --- a/include/net/caif/caif_dev.h +++ b/include/net/caif/caif_dev.h @@ -119,7 +119,7 @@ void caif_free_client(struct cflayer *adap_layer); * The link_support layer is used to add any Link Layer specific * framing. */ -void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, +int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)( struct sk_buff *, struct net_device *, diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h index 2aa5e91d8457..8819ff4db35a 100644 --- a/include/net/caif/cfcnfg.h +++ b/include/net/caif/cfcnfg.h @@ -62,7 +62,7 @@ void cfcnfg_remove(struct cfcnfg *cfg); * @fcs: Specify if checksum is used in CAIF Framing Layer. * @head_room: Head space needed by link specific protocol. */ -void +int cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h index 14a55e03bb3c..67cce8757175 100644 --- a/include/net/caif/cfserl.h +++ b/include/net/caif/cfserl.h @@ -9,4 +9,5 @@ #include <net/caif/caif_layer.h> struct cflayer *cfserl_create(int instance, bool use_stx); +void cfserl_release(struct cflayer *layer); #endif diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5224f885a99a..58c2cd417e89 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5760,7 +5760,7 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); */ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, - u8 data_offset); + u8 data_offset, bool is_amsdu); /** * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3 @@ -5772,7 +5772,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype) { - return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0); + return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0, false); } /** diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 445b66c6eb7e..e89530d0d9c6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5537,7 +5537,7 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw, * * This function iterates over the interfaces associated with a given * hardware that are currently active and calls the callback for them. - * This version can only be used while holding the RTNL. + * This version can only be used while holding the wiphy mutex. * * @hw: the hardware struct of which the interfaces should be iterated over * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags @@ -6392,7 +6392,12 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, /** * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header - * of injected frames + * of injected frames. + * + * To accurately parse and take into account rate and retransmission fields, + * you must initialize the chandef field in the ieee80211_tx_info structure + * of the skb before calling this function. + * * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fa5887143f0d..bdc0459a595e 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -184,6 +184,9 @@ struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); + +struct ns_common *get_net_ns(struct ns_common *ns); +struct net *get_net_ns_by_fd(int fd); #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> @@ -203,13 +206,22 @@ static inline void net_ns_get_ownership(const struct net *net, } static inline void net_ns_barrier(void) {} + +static inline struct ns_common *get_net_ns(struct ns_common *ns) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct net *get_net_ns_by_fd(int fd) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_NET_NS */ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); -struct net *get_net_ns_by_fd(int fd); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 51d8eb99764d..48ef7460ff30 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -157,7 +157,6 @@ enum nf_flow_flags { NF_FLOW_HW, NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, - NF_FLOW_HW_REFRESH, NF_FLOW_HW_PENDING, }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 27eeb613bb4e..0a5655e300b5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1506,16 +1506,10 @@ struct nft_trans_chain { struct nft_trans_table { bool update; - u8 state; - u32 flags; }; #define nft_trans_table_update(trans) \ (((struct nft_trans_table *)trans->data)->update) -#define nft_trans_table_state(trans) \ - (((struct nft_trans_table *)trans->data)->state) -#define nft_trans_table_flags(trans) \ - (((struct nft_trans_table *)trans->data)->flags) struct nft_trans_elem { struct nft_set *set; diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index bd76e8e082c0..1df0f8074c9d 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -298,6 +298,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, struct sk_buff **resp); struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev); +void nci_hci_deallocate(struct nci_dev *ndev); int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event, const u8 *param, size_t param_len); int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 255e4f4b521f..ec7823921bd2 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -709,6 +709,17 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, cls_common->extack = extack; } +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) +{ + struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + + if (tc_skb_ext) + memset(tc_skb_ext, 0, sizeof(*tc_skb_ext)); + return tc_skb_ext; +} +#endif + enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f5c1bee0cd6a..6d7b12cba015 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -128,12 +128,7 @@ void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { if (qdisc_run_begin(q)) { - /* NOLOCK qdisc must check 'state' under the qdisc seqlock - * to avoid racing with dev_qdisc_reset() - */ - if (!(q->flags & TCQ_F_NOLOCK) || - likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) - __qdisc_run(q); + __qdisc_run(q); qdisc_run_end(q); } } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f7a6e14491fb..1e625519ae96 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -36,6 +36,7 @@ struct qdisc_rate_table { enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, + __QDISC_STATE_MISSED, }; struct qdisc_size_table { @@ -159,8 +160,33 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc) static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { + if (spin_trylock(&qdisc->seqlock)) + goto nolock_empty; + + /* If the MISSED flag is set, it means other thread has + * set the MISSED flag before second spin_trylock(), so + * we can return false here to avoid multi cpus doing + * the set_bit() and second spin_trylock() concurrently. + */ + if (test_bit(__QDISC_STATE_MISSED, &qdisc->state)) + return false; + + /* Set the MISSED flag before the second spin_trylock(), + * if the second spin_trylock() return false, it means + * other cpu holding the lock will do dequeuing for us + * or it will see the MISSED flag set after releasing + * lock and reschedule the net_tx_action() to do the + * dequeuing. + */ + set_bit(__QDISC_STATE_MISSED, &qdisc->state); + + /* Retry again in case other CPU may not see the new flag + * after it releases the lock at the end of qdisc_run_end(). + */ if (!spin_trylock(&qdisc->seqlock)) return false; + +nolock_empty: WRITE_ONCE(qdisc->empty, false); } else if (qdisc_is_running(qdisc)) { return false; @@ -176,8 +202,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) static inline void qdisc_run_end(struct Qdisc *qdisc) { write_seqcount_end(&qdisc->running); - if (qdisc->flags & TCQ_F_NOLOCK) + if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); + + if (unlikely(test_bit(__QDISC_STATE_MISSED, + &qdisc->state))) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + __netif_schedule(qdisc); + } + } } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) diff --git a/include/net/sock.h b/include/net/sock.h index 42bc5e1a627f..7a7058f4f265 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1934,7 +1934,8 @@ static inline u32 net_tx_rndhash(void) static inline void sk_set_txhash(struct sock *sk) { - sk->sk_txhash = net_tx_rndhash(); + /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ + WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); } static inline bool sk_rethink_txhash(struct sock *sk) @@ -2206,9 +2207,12 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock, static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { - if (sk->sk_txhash) { + /* This pairs with WRITE_ONCE() in sk_set_txhash() */ + u32 txhash = READ_ONCE(sk->sk_txhash); + + if (txhash) { skb->l4_hash = 1; - skb->hash = sk->sk_txhash; + skb->hash = txhash; } } @@ -2231,13 +2235,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) sk_mem_charge(sk, skb->truesize); } -static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) +static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; + return true; } + return false; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, @@ -2264,8 +2270,13 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk); static inline int sock_error(struct sock *sk) { int err; - if (likely(!sk->sk_err)) + + /* Avoid an atomic operation for the common case. + * This is racy since another cpu/thread can change sk_err under us. + */ + if (likely(data_race(!sk->sk_err))) return 0; + err = xchg(&sk->sk_err, 0); return -err; } diff --git a/include/net/tls.h b/include/net/tls.h index 3eccb525e8f7..8341a8d1e807 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -193,7 +193,11 @@ struct tls_offload_context_tx { (sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX) enum tls_context_flags { - TLS_RX_SYNC_RUNNING = 0, + /* tls_device_down was called after the netdev went down, device state + * was released, and kTLS works in software, even though rx_conf is + * still TLS_HW (needed for transition). + */ + TLS_RX_DEV_DEGRADED = 0, /* Unlike RX where resync is driven entirely by the core in TX only * the driver knows when things went out of sync, so we need the flag * to be atomic. @@ -266,6 +270,7 @@ struct tls_context { /* cache cold stuff */ struct proto *sk_proto; + struct sock *sk; void (*sk_destruct)(struct sock *sk); @@ -448,6 +453,9 @@ static inline u16 tls_user_config(struct tls_context *ctx, bool tx) struct sk_buff * tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb); +struct sk_buff * +tls_validate_xmit_skb_sw(struct sock *sk, struct net_device *dev, + struct sk_buff *skb); static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) { diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 1358a0ceb4d0..0bc29c4516e7 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -81,7 +81,7 @@ struct snd_compr_stream; #define SND_SOC_DAIFMT_CBP_CFP (1 << 12) /* codec clk provider & frame provider */ #define SND_SOC_DAIFMT_CBC_CFP (2 << 12) /* codec clk consumer & frame provider */ #define SND_SOC_DAIFMT_CBP_CFC (3 << 12) /* codec clk provider & frame consumer */ -#define SND_SOC_DAIFMT_CBC_CFC (4 << 12) /* codec clk consumer & frame follower */ +#define SND_SOC_DAIFMT_CBC_CFC (4 << 12) /* codec clk consumer & frame consumer */ /* previous definitions kept for backwards-compatibility, do not use in new contributions */ #define SND_SOC_DAIFMT_CBM_CFM SND_SOC_DAIFMT_CBP_CFP diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 6de5a7fc066b..d2a942086fcb 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -863,8 +863,7 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) -#define __NR_quotactl_path 443 -__SYSCALL(__NR_quotactl_path, sys_quotactl_path) +/* 443 is reserved for quotactl_path */ #define __NR_landlock_create_ruleset 444 __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff) +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127 diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index ee93428ced9a..225ec87d4f22 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -611,6 +611,7 @@ #define KEY_VOICECOMMAND 0x246 /* Listening Voice Command */ #define KEY_ASSISTANT 0x247 /* AL Context-aware desktop assistant */ #define KEY_KBD_LAYOUT_NEXT 0x248 /* AC Next Keyboard Layout Select */ +#define KEY_EMOJI_PICKER 0x249 /* Show/hide emoji picker (HUTRR101) */ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index e1ae46683301..162ff99ed2cb 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -280,6 +280,7 @@ struct io_uring_params { #define IORING_FEAT_SQPOLL_NONFIXED (1U << 7) #define IORING_FEAT_EXT_ARG (1U << 8) #define IORING_FEAT_NATIVE_WORKERS (1U << 9) +#define IORING_FEAT_RSRC_TAGS (1U << 10) /* * io_uring_register(2) opcodes and arguments @@ -298,8 +299,12 @@ enum { IORING_UNREGISTER_PERSONALITY = 10, IORING_REGISTER_RESTRICTIONS = 11, IORING_REGISTER_ENABLE_RINGS = 12, - IORING_REGISTER_RSRC = 13, - IORING_REGISTER_RSRC_UPDATE = 14, + + /* extended with tagging */ + IORING_REGISTER_FILES2 = 13, + IORING_REGISTER_FILES_UPDATE2 = 14, + IORING_REGISTER_BUFFERS2 = 15, + IORING_REGISTER_BUFFERS_UPDATE = 16, /* this goes last */ IORING_REGISTER_LAST @@ -312,14 +317,10 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; -enum { - IORING_RSRC_FILE = 0, - IORING_RSRC_BUFFER = 1, -}; - struct io_uring_rsrc_register { - __u32 type; __u32 nr; + __u32 resv; + __u64 resv2; __aligned_u64 data; __aligned_u64 tags; }; @@ -335,8 +336,8 @@ struct io_uring_rsrc_update2 { __u32 resv; __aligned_u64 data; __aligned_u64 tags; - __u32 type; __u32 nr; + __u32 resv2; }; /* Skip updating fd indexes set to this value in the fd table */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 3fd9a7e9d90c..79d9c44d1ad7 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index f0c35ce8628c..4fe842c3a3a9 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -54,7 +54,7 @@ #define VIRTIO_ID_SOUND 25 /* virtio sound */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ -#define VIRTIO_ID_BT 28 /* virtio bluetooth */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ +#define VIRTIO_ID_BT 40 /* virtio bluetooth */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/init/Kconfig b/init/Kconfig index 1ea12c64e4c9..a61c92066c2e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -442,6 +442,7 @@ config AUDITSYSCALL source "kernel/irq/Kconfig" source "kernel/time/Kconfig" +source "kernel/bpf/Kconfig" source "kernel/Kconfig.preempt" menu "CPU/Task time and stats accounting" @@ -1713,46 +1714,6 @@ config KALLSYMS_BASE_RELATIVE # syscall, maps, verifier -config BPF_LSM - bool "LSM Instrumentation with BPF" - depends on BPF_EVENTS - depends on BPF_SYSCALL - depends on SECURITY - depends on BPF_JIT - help - Enables instrumentation of the security hooks with eBPF programs for - implementing dynamic MAC and Audit Policies. - - If you are unsure how to answer this question, answer N. - -config BPF_SYSCALL - bool "Enable bpf() system call" - select BPF - select IRQ_WORK - select TASKS_TRACE_RCU - select BINARY_PRINTF - select NET_SOCK_MSG if INET - default n - help - Enable the bpf() system call that allows to manipulate eBPF - programs and maps via file descriptors. - -config ARCH_WANT_DEFAULT_BPF_JIT - bool - -config BPF_JIT_ALWAYS_ON - bool "Permanently enable BPF JIT and remove BPF interpreter" - depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT - help - Enables BPF JIT and removes BPF interpreter to avoid - speculative execution of BPF instructions by the interpreter - -config BPF_JIT_DEFAULT_ON - def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON - depends on HAVE_EBPF_JIT && BPF_JIT - -source "kernel/bpf/preload/Kconfig" - config USERFAULTFD bool "Enable userfaultfd() system call" depends on MMU diff --git a/init/main.c b/init/main.c index eb01e121d2f1..e9c42a183e33 100644 --- a/init/main.c +++ b/init/main.c @@ -1537,7 +1537,7 @@ static noinline void __init kernel_init_freeable(void) */ set_mems_allowed(node_states[N_MEMORY]); - cad_pid = task_pid(current); + cad_pid = get_pid(task_pid(current)); smp_prepare_cpus(setup_max_cpus); diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig new file mode 100644 index 000000000000..bd04f4a44c01 --- /dev/null +++ b/kernel/bpf/Kconfig @@ -0,0 +1,89 @@ +# SPDX-License-Identifier: GPL-2.0-only + +# BPF interpreter that, for example, classic socket filters depend on. +config BPF + bool + +# Used by archs to tell that they support BPF JIT compiler plus which +# flavour. Only one of the two can be selected for a specific arch since +# eBPF JIT supersedes the cBPF JIT. + +# Classic BPF JIT (cBPF) +config HAVE_CBPF_JIT + bool + +# Extended BPF JIT (eBPF) +config HAVE_EBPF_JIT + bool + +# Used by archs to tell that they want the BPF JIT compiler enabled by +# default for kernels that were compiled with BPF JIT support. +config ARCH_WANT_DEFAULT_BPF_JIT + bool + +menu "BPF subsystem" + +config BPF_SYSCALL + bool "Enable bpf() system call" + select BPF + select IRQ_WORK + select TASKS_TRACE_RCU + select BINARY_PRINTF + select NET_SOCK_MSG if INET + default n + help + Enable the bpf() system call that allows to manipulate BPF programs + and maps via file descriptors. + +config BPF_JIT + bool "Enable BPF Just In Time compiler" + depends on BPF + depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT + depends on MODULES + help + BPF programs are normally handled by a BPF interpreter. This option + allows the kernel to generate native code when a program is loaded + into the kernel. This will significantly speed-up processing of BPF + programs. + + Note, an admin should enable this feature changing: + /proc/sys/net/core/bpf_jit_enable + /proc/sys/net/core/bpf_jit_harden (optional) + /proc/sys/net/core/bpf_jit_kallsyms (optional) + +config BPF_JIT_ALWAYS_ON + bool "Permanently enable BPF JIT and remove BPF interpreter" + depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT + help + Enables BPF JIT and removes BPF interpreter to avoid speculative + execution of BPF instructions by the interpreter. + +config BPF_JIT_DEFAULT_ON + def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON + depends on HAVE_EBPF_JIT && BPF_JIT + +config BPF_UNPRIV_DEFAULT_OFF + bool "Disable unprivileged BPF by default" + depends on BPF_SYSCALL + help + Disables unprivileged BPF by default by setting the corresponding + /proc/sys/kernel/unprivileged_bpf_disabled knob to 2. An admin can + still reenable it by setting it to 0 later on, or permanently + disable it by setting it to 1 (from which no other transition to + 0 is possible anymore). + +source "kernel/bpf/preload/Kconfig" + +config BPF_LSM + bool "Enable BPF LSM Instrumentation" + depends on BPF_EVENTS + depends on BPF_SYSCALL + depends on SECURITY + depends on BPF_JIT + help + Enables instrumentation of the security hooks with BPF programs for + implementing dynamic MAC and Audit Policies. + + If you are unsure how to answer this question, answer N. + +endmenu # "BPF subsystem" diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 5efb2b24012c..da471bf01b97 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -107,10 +107,12 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_inode_storage_get_proto; case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; +#ifdef CONFIG_NET case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; +#endif /* CONFIG_NET */ case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 0600ed325fa0..f982a9f0dbc4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5206,6 +5206,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->ret_size = ret; for (i = 0; i < nargs; i++) { + if (i == nargs - 1 && args[i].type == 0) { + bpf_log(log, + "The function %s with variable args is unsupported.\n", + tname); + return -EINVAL; + } ret = __get_type_size(btf, args[i].type, &t); if (ret < 0) { bpf_log(log, @@ -5213,6 +5219,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]); return -EINVAL; } + if (ret == 0) { + bpf_log(log, + "The function %s has malformed void argument.\n", + tname); + return -EINVAL; + } m->arg_size[i] = ret; } m->nr_args = nargs; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 544773970dbc..a2f1f15ce432 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -14,6 +14,7 @@ #include <linux/jiffies.h> #include <linux/pid_namespace.h> #include <linux/proc_ns.h> +#include <linux/security.h> #include "../../lib/kstrtox.h" @@ -692,38 +693,41 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, return -EINVAL; } -/* Per-cpu temp buffers which can be used by printf-like helpers for %s or %p +/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary + * arguments representation. */ -#define MAX_PRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BUF_LEN 512 -struct bpf_printf_buf { - char tmp_buf[MAX_PRINTF_BUF_LEN]; +/* Support executing three nested bprintf helper calls on a given CPU */ +#define MAX_BPRINTF_NEST_LEVEL 3 +struct bpf_bprintf_buffers { + char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; }; -static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf); -static DEFINE_PER_CPU(int, bpf_printf_buf_used); +static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); +static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); static int try_get_fmt_tmp_buf(char **tmp_buf) { - struct bpf_printf_buf *bufs; - int used; + struct bpf_bprintf_buffers *bufs; + int nest_level; preempt_disable(); - used = this_cpu_inc_return(bpf_printf_buf_used); - if (WARN_ON_ONCE(used > 1)) { - this_cpu_dec(bpf_printf_buf_used); + nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); + if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_printf_buf); - *tmp_buf = bufs->tmp_buf; + bufs = this_cpu_ptr(&bpf_bprintf_bufs); + *tmp_buf = bufs->tmp_bufs[nest_level - 1]; return 0; } void bpf_bprintf_cleanup(void) { - if (this_cpu_read(bpf_printf_buf_used)) { - this_cpu_dec(bpf_printf_buf_used); + if (this_cpu_read(bpf_bprintf_nest_level)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); } } @@ -760,7 +764,7 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) return -EBUSY; - tmp_buf_end = tmp_buf + MAX_PRINTF_BUF_LEN; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; *bin_args = (u32 *)tmp_buf; } @@ -1066,11 +1070,13 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return &bpf_probe_read_kernel_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return &bpf_probe_read_kernel_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_snprintf: diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index f25b719ac786..84b3b35fc0d0 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -221,25 +221,20 @@ static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static size_t bpf_ringbuf_mmap_page_cnt(const struct bpf_ringbuf *rb) -{ - size_t data_pages = (rb->mask + 1) >> PAGE_SHIFT; - - /* consumer page + producer page + 2 x data pages */ - return RINGBUF_POS_PAGES + 2 * data_pages; -} - static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; - size_t mmap_sz; rb_map = container_of(map, struct bpf_ringbuf_map, map); - mmap_sz = bpf_ringbuf_mmap_page_cnt(rb_map->rb) << PAGE_SHIFT; - - if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > mmap_sz) - return -EINVAL; + if (vma->vm_flags & VM_WRITE) { + /* allow writable mapping for the consumer_pos only */ + if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EPERM; + } else { + vma->vm_flags &= ~VM_MAYWRITE; + } + /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } @@ -315,6 +310,9 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + if (len > rb->mask + 1) + return NULL; + cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 941ca06d9dfa..ea04b0deb5ce 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -50,7 +50,8 @@ static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); -int sysctl_unprivileged_bpf_disabled __read_mostly; +int sysctl_unprivileged_bpf_disabled __read_mostly = + IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 757476c91c98..c6a27574242d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6409,18 +6409,10 @@ enum { }; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, - const struct bpf_reg_state *off_reg, - u32 *alu_limit, u8 opcode) + u32 *alu_limit, bool mask_to_left) { - bool off_is_neg = off_reg->smin_value < 0; - bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || - (opcode == BPF_SUB && !off_is_neg); u32 max = 0, ptr_limit = 0; - if (!tnum_is_const(off_reg->var_off) && - (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) - return REASON_BOUNDS; - switch (ptr_reg->type) { case PTR_TO_STACK: /* Offset 0 is out-of-bounds, but acceptable start for the @@ -6486,15 +6478,41 @@ static bool sanitize_needed(u8 opcode) return opcode == BPF_ADD || opcode == BPF_SUB; } +struct bpf_sanitize_info { + struct bpf_insn_aux_data aux; + bool mask_to_left; +}; + +static struct bpf_verifier_state * +sanitize_speculative_path(struct bpf_verifier_env *env, + const struct bpf_insn *insn, + u32 next_idx, u32 curr_idx) +{ + struct bpf_verifier_state *branch; + struct bpf_reg_state *regs; + + branch = push_stack(env, next_idx, curr_idx, true); + if (branch && insn) { + regs = branch->frame[branch->curframe]->regs; + if (BPF_SRC(insn->code) == BPF_K) { + mark_reg_unknown(env, regs, insn->dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X) { + mark_reg_unknown(env, regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->src_reg); + } + } + return branch; +} + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, - struct bpf_insn_aux_data *tmp_aux, + struct bpf_sanitize_info *info, const bool commit_window) { - struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux; + struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; bool off_is_imm = tnum_is_const(off_reg->var_off); bool off_is_neg = off_reg->smin_value < 0; @@ -6515,7 +6533,16 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (vstate->speculative) goto do_sim; - err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode); + if (!commit_window) { + if (!tnum_is_const(off_reg->var_off) && + (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) + return REASON_BOUNDS; + + info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + } + + err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); if (err < 0) return err; @@ -6523,8 +6550,8 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, /* In commit phase we narrow the masking window based on * the observed pointer move after the simulated operation. */ - alu_state = tmp_aux->alu_state; - alu_limit = abs(tmp_aux->alu_limit - alu_limit); + alu_state = info->aux.alu_state; + alu_limit = abs(info->aux.alu_limit - alu_limit); } else { alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; @@ -6539,8 +6566,12 @@ do_sim: /* If we're in commit phase, we're done here given we already * pushed the truncated dst_reg into the speculative verification * stack. + * + * Also, when register is a known constant, we rewrite register-based + * operation to immediate-based, and thus do not need masking (and as + * a consequence, do not need to simulate the zero-truncation either). */ - if (commit_window) + if (commit_window || off_is_imm) return 0; /* Simulate and find potential out-of-bounds access under @@ -6556,12 +6587,26 @@ do_sim: tmp = *dst_reg; *dst_reg = *ptr_reg; } - ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); + ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, + env->insn_idx); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? REASON_STACK : 0; } +static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) +{ + struct bpf_verifier_state *vstate = env->cur_state; + + /* If we simulate paths under speculation, we don't update the + * insn as 'seen' such that when we verify unreachable paths in + * the non-speculative domain, sanitize_dead_code() can still + * rewrite/sanitize them. + */ + if (!vstate->speculative) + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; +} + static int sanitize_err(struct bpf_verifier_env *env, const struct bpf_insn *insn, int reason, const struct bpf_reg_state *off_reg, @@ -6685,7 +6730,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; - struct bpf_insn_aux_data tmp_aux = {}; + struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; int ret; @@ -6754,7 +6799,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, - &tmp_aux, false); + &info, false); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -6895,7 +6940,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, - &tmp_aux, true); + &info, true); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -7084,11 +7129,10 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umax_val = src_reg->u32_max_value; - /* Assuming scalar64_min_max_and will be called so its safe - * to skip updating register for known 32-bit case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. @@ -7108,7 +7152,6 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } - } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, @@ -7155,11 +7198,10 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; - /* Assuming scalar64_min_max_or will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima @@ -7224,11 +7266,10 @@ static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; - /* Assuming scalar64_min_max_xor will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; @@ -8744,14 +8785,28 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (err) return err; } + if (pred == 1) { - /* only follow the goto, ignore fall-through */ + /* Only follow the goto, ignore fall-through. If needed, push + * the fall-through branch for simulation under speculative + * execution. + */ + if (!env->bypass_spec_v1 && + !sanitize_speculative_path(env, insn, *insn_idx + 1, + *insn_idx)) + return -EFAULT; *insn_idx += insn->off; return 0; } else if (pred == 0) { - /* only follow fall-through branch, since - * that's where the program will go + /* Only follow the fall-through branch, since that's where the + * program will go. If needed, push the goto branch for + * simulation under speculative execution. */ + if (!env->bypass_spec_v1 && + !sanitize_speculative_path(env, insn, + *insn_idx + insn->off + 1, + *insn_idx)) + return -EFAULT; return 0; } @@ -10624,7 +10679,7 @@ static int do_check(struct bpf_verifier_env *env) } regs = cur_regs(env); - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { @@ -10851,7 +10906,7 @@ process_bpf_exit: return err; env->insn_idx++; - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -11360,6 +11415,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, { struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; + u32 old_seen = old_data[off].seen; u32 prog_len; int i; @@ -11380,7 +11436,8 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); for (i = off; i < off + cnt - 1; i++) { - new_data[i].seen = env->pass_cnt; + /* Expand insni[off]'s seen count to the patched range. */ + new_data[i].seen = old_seen; new_data[i].zext_dst = insn_has_def32(env, insn + i); } env->insn_aux_data = new_data; @@ -12704,6 +12761,9 @@ static void free_states(struct bpf_verifier_env *env) * insn_aux_data was touched. These variables are compared to clear temporary * data from failed pass. For testing and experiments do_check_common() can be * run multiple times even when prior attempt to verify is unsuccessful. + * + * Note that special handling is needed on !env->bypass_spec_v1 if this is + * ever called outside of error path with subsequent program rejection. */ static void sanitize_insn_aux_data(struct bpf_verifier_env *env) { @@ -13200,6 +13260,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, return 0; } +BTF_SET_START(btf_id_deny) +BTF_ID_UNUSED +#ifdef CONFIG_SMP +BTF_ID(func, migrate_disable) +BTF_ID(func, migrate_enable) +#endif +#if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU +BTF_ID(func, rcu_read_unlock_strict) +#endif +BTF_SET_END(btf_id_deny) + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; @@ -13259,6 +13330,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; + } else if (prog->type == BPF_PROG_TYPE_TRACING && + btf_id_set_contains(&btf_id_deny, btf_id)) { + return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); @@ -13358,12 +13432,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; - if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env->prog); - if (ret) - goto skip_full_check; - } - env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); @@ -13391,6 +13459,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (ret < 0) goto skip_full_check; + if (bpf_prog_is_dev_bound(env->prog->aux)) { + ret = bpf_prog_offload_verifier_prep(env->prog); + if (ret) + goto skip_full_check; + } + ret = check_cfg(env); if (ret < 0) goto skip_full_check; diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 391aa570369b..1f274d7fc934 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -820,6 +820,10 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent struct cgroup *cgrp = kn->priv; int ret; + /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ + if (strchr(new_name_str, '\n')) + return -EINVAL; + if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (kn->parent != new_parent) @@ -1001,7 +1005,7 @@ static int check_cgroupfs_options(struct fs_context *fc) ctx->subsys_mask &= enabled; /* - * In absense of 'none', 'name=' or subsystem name options, + * In absence of 'none', 'name=' and subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e049edd66776..21ecc6ee6a6d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -468,7 +468,7 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, * @cgrp: the cgroup of interest * @ss: the subsystem of interest * - * Find and get @cgrp's css assocaited with @ss. If the css doesn't exist + * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, @@ -1633,7 +1633,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) /** * css_clear_dir - remove subsys files in a cgroup directory - * @css: taget css + * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { @@ -5350,7 +5350,7 @@ out_unlock: /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to - * initate destruction and put the css ref from kill_css(). + * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { @@ -5634,8 +5634,6 @@ int __init cgroup_init_early(void) return 0; } -static u16 cgroup_disable_mask __initdata; - /** * cgroup_init - cgroup initialization * @@ -5694,12 +5692,8 @@ int __init cgroup_init(void) * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ - if (cgroup_disable_mask & (1 << ssid)) { - static_branch_disable(cgroup_subsys_enabled_key[ssid]); - printk(KERN_INFO "Disabling %s control group subsystem\n", - ss->name); + if (!cgroup_ssid_enabled(ssid)) continue; - } if (cgroup1_ssid_disabled(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", @@ -6058,7 +6052,7 @@ out_revert: * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* - * cgroup_can_fork() succeded and cleans up references we took to + * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, @@ -6214,7 +6208,10 @@ static int __init cgroup_disable(char *str) if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; - cgroup_disable_mask |= 1 << i; + + static_branch_disable(cgroup_subsys_enabled_key[i]); + pr_info("Disabling %s control group subsystem\n", + ss->name); } } return 1; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a945504c0ae7..adb5190c4429 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3376,7 +3376,7 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) } /** - * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed + * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index ae042c347c64..3135406608c7 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -244,7 +244,7 @@ EXPORT_SYMBOL(rdmacg_uncharge); * This function follows charging resource in hierarchical way. * It will fail if the charge would cause the new value to exceed the * hierarchical limit. - * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. + * Returns 0 if the charge succeeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. * Returns pointer to rdmacg for this resource when charging is successful. * * Charger needs to account resources on two criteria. diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 3a3fd2993a65..cee265cb535c 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -75,7 +75,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) * @root: root of the tree to traversal * @cpu: target cpu * - * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts + * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 825284baaf46..684a6061a13a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -464,6 +464,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); + VMCOREINFO_NUMBER(SECTION_SIZE_BITS); VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); #endif VMCOREINFO_STRUCT_SIZE(page); diff --git a/kernel/entry/common.c b/kernel/entry/common.c index a0b3b04fb596..bf16395b9e13 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -5,6 +5,7 @@ #include <linux/highmem.h> #include <linux/livepatch.h> #include <linux/audit.h> +#include <linux/tick.h> #include "common.h" @@ -186,7 +187,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, local_irq_disable_exit_to_user(); /* Check if any of the above work has queued a deferred wakeup */ - rcu_nocb_flush_deferred_wakeup(); + tick_nohz_user_enter_prepare(); ti_work = READ_ONCE(current_thread_info()->flags); } @@ -202,7 +203,7 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs) lockdep_assert_irqs_disabled(); /* Flush pending rcuog wakeup before the last need_resched() check */ - rcu_nocb_flush_deferred_wakeup(); + tick_nohz_user_enter_prepare(); if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK)) ti_work = exit_to_user_mode_loop(regs, ti_work); diff --git a/kernel/events/core.c b/kernel/events/core.c index 6fee4a7e88d7..fe88d6eea3c2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4609,7 +4609,9 @@ find_get_context(struct pmu *pmu, struct task_struct *task, cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); ctx = &cpuctx->ctx; get_ctx(ctx); + raw_spin_lock_irqsave(&ctx->lock, flags); ++ctx->pin_count; + raw_spin_unlock_irqrestore(&ctx->lock, flags); return ctx; } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 23a7a0ba1388..db8c248ebc8c 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -70,9 +70,6 @@ bool irq_work_queue(struct irq_work *work) if (!irq_work_claim(work)) return false; - /*record irq_work call stack in order to print it in KASAN reports*/ - kasan_record_aux_stack(work); - /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 7a1414622051..94232186fccb 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -391,6 +391,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) /* No obstacles. */ return vprintk_default(fmt, args); } +EXPORT_SYMBOL(vprintk); void __init printk_safe_init(void) { @@ -411,4 +412,3 @@ void __init printk_safe_init(void) /* Flush pending messages that did not have scheduled IRQ works. */ printk_safe_flush(); } -EXPORT_SYMBOL(vprintk); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5226cc26a095..4ca80df205ce 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6389,7 +6389,6 @@ int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr) { return __sched_setscheduler(p, attr, false, true); } -EXPORT_SYMBOL_GPL(sched_setattr_nocheck); /** * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 9c882f20803e..c5aacbd492a1 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -885,6 +885,7 @@ static const struct seq_operations sched_debug_sops = { #define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F)) #define __P(F) __PS(#F, F) #define P(F) __PS(#F, p->F) +#define PM(F, M) __PS(#F, p->F & (M)) #define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F))) #define __PN(F) __PSN(#F, F) #define PN(F) __PSN(#F, p->F) @@ -1011,7 +1012,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(se.avg.util_avg); P(se.avg.last_update_time); P(se.avg.util_est.ewma); - P(se.avg.util_est.enqueued); + PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED); #endif #ifdef CONFIG_UCLAMP_TASK __PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3248e24a90b0..bfaa6e1f6067 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3298,6 +3298,24 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) #ifdef CONFIG_SMP #ifdef CONFIG_FAIR_GROUP_SCHED + +static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->load.weight) + return false; + + if (cfs_rq->avg.load_sum) + return false; + + if (cfs_rq->avg.util_sum) + return false; + + if (cfs_rq->avg.runnable_sum) + return false; + + return true; +} + /** * update_tg_load_avg - update the tg's load avg * @cfs_rq: the cfs_rq whose avg changed @@ -3499,10 +3517,9 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf static inline void update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; + long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; unsigned long load_avg; u64 load_sum = 0; - s64 delta_sum; u32 divider; if (!runnable_sum) @@ -3549,13 +3566,13 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq load_sum = (s64)se_weight(se) * runnable_sum; load_avg = div_s64(load_sum, divider); - delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; - delta_avg = load_avg - se->avg.load_avg; + delta = load_avg - se->avg.load_avg; se->avg.load_sum = runnable_sum; se->avg.load_avg = load_avg; - add_positive(&cfs_rq->avg.load_avg, delta_avg); - add_positive(&cfs_rq->avg.load_sum, delta_sum); + + add_positive(&cfs_rq->avg.load_avg, delta); + cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3766,11 +3783,17 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { + /* + * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. + * See ___update_load_avg() for details. + */ + u32 divider = get_pelt_divider(&cfs_rq->avg); + dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); - sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); @@ -3902,7 +3925,7 @@ static inline unsigned long _task_util_est(struct task_struct *p) { struct util_est ue = READ_ONCE(p->se.avg.util_est); - return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED); + return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED)); } static inline unsigned long task_util_est(struct task_struct *p) @@ -4002,7 +4025,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, * Reset EWMA on utilization increases, the moving average is used only * to smooth utilization decreases. */ - ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED); + ue.enqueued = task_util(p); if (sched_feat(UTIL_EST_FASTUP)) { if (ue.ewma < ue.enqueued) { ue.ewma = ue.enqueued; @@ -4051,6 +4074,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, ue.ewma += last_ewma_diff; ue.ewma >>= UTIL_EST_WEIGHT_SHIFT; done: + ue.enqueued |= UTIL_AVG_UNCHANGED; WRITE_ONCE(p->se.avg.util_est, ue); trace_sched_util_est_se_tp(&p->se); @@ -4085,6 +4109,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) #else /* CONFIG_SMP */ +static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + return true; +} + #define UPDATE_TG 0x0 #define SKIP_AGE_LOAD 0x0 #define DO_ATTACH 0x0 @@ -4743,8 +4772,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - cfs_rq->throttled_clock_task; - /* Add cfs_rq with already running entity in the list */ - if (cfs_rq->nr_running >= 1) + /* Add cfs_rq with load or one or more already running entities to the list */ + if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running) list_add_leaf_cfs_rq(cfs_rq); } @@ -7990,23 +8019,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done) #ifdef CONFIG_FAIR_GROUP_SCHED -static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) -{ - if (cfs_rq->load.weight) - return false; - - if (cfs_rq->avg.load_sum) - return false; - - if (cfs_rq->avg.util_sum) - return false; - - if (cfs_rq->avg.runnable_sum) - return false; - - return true; -} - static bool __update_blocked_fair(struct rq *rq, bool *done) { struct cfs_rq *cfs_rq, *pos; @@ -8030,7 +8042,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) /* Propagate pending load changes to the parent, if any: */ se = cfs_rq->tg->se[cpu]; if (se && !skip_blocked_update(se)) - update_load_avg(cfs_rq_of(se), se, 0); + update_load_avg(cfs_rq_of(se), se, UPDATE_TG); /* * There can be a lot of idle CPU cgroups. Don't let fully diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 1462846d244e..cfe94ffd2b38 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -42,15 +42,6 @@ static inline u32 get_pelt_divider(struct sched_avg *avg) return LOAD_AVG_MAX - 1024 + avg->period_contrib; } -/* - * When a task is dequeued, its estimated utilization should not be update if - * its util_avg has not been updated at least once. - * This flag is used to synchronize util_avg updates with util_est updates. - * We map this information into the LSB bit of the utilization saved at - * dequeue time (i.e. util_est.dequeued). - */ -#define UTIL_AVG_UNCHANGED 0x1 - static inline void cfs_se_util_change(struct sched_avg *avg) { unsigned int enqueued; @@ -58,7 +49,7 @@ static inline void cfs_se_util_change(struct sched_avg *avg) if (!sched_feat(UTIL_EST)) return; - /* Avoid store if the flag has been already set */ + /* Avoid store if the flag has been already reset */ enqueued = avg->util_est.enqueued; if (!(enqueued & UTIL_AVG_UNCHANGED)) return; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 6ecd3f3a52b5..9f58049ac16d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1105,28 +1105,30 @@ static int seccomp_do_user_notification(int this_syscall, up(&match->notif->request); wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM); - mutex_unlock(&match->notify_lock); /* * This is where we wait for a reply from userspace. */ -wait: - err = wait_for_completion_interruptible(&n.ready); - mutex_lock(&match->notify_lock); - if (err == 0) { - /* Check if we were woken up by a addfd message */ + do { + mutex_unlock(&match->notify_lock); + err = wait_for_completion_interruptible(&n.ready); + mutex_lock(&match->notify_lock); + if (err != 0) + goto interrupted; + addfd = list_first_entry_or_null(&n.addfd, struct seccomp_kaddfd, list); - if (addfd && n.state != SECCOMP_NOTIFY_REPLIED) { + /* Check if we were woken up by a addfd message */ + if (addfd) seccomp_handle_addfd(addfd); - mutex_unlock(&match->notify_lock); - goto wait; - } - ret = n.val; - err = n.error; - flags = n.flags; - } + } while (n.state != SECCOMP_NOTIFY_REPLIED); + + ret = n.val; + err = n.error; + flags = n.flags; + +interrupted: /* If there were any pending addfd calls, clear them out */ list_for_each_entry_safe(addfd, tmp, &n.addfd, list) { /* The process went away before we got a chance to handle it */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 14edf84cc571..d4a78e08f6d8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -225,7 +225,27 @@ static int bpf_stats_handler(struct ctl_table *table, int write, mutex_unlock(&bpf_stats_enabled_mutex); return ret; } -#endif + +static int bpf_unpriv_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, unpriv_enable = *(int *)table->data; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + return ret; +} +#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */ /* * /proc/sys support @@ -2600,10 +2620,9 @@ static struct ctl_table kern_table[] = { .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, - /* only handle a transition from default "0" to "1" */ - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_ONE, + .proc_handler = bpf_unpriv_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = &two, }, { .procname = "bpf_stats_enabled", diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 828b091501ca..6784f27a3099 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -230,6 +230,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; +EXPORT_SYMBOL_GPL(tick_nohz_full_mask); bool tick_nohz_full_running; EXPORT_SYMBOL_GPL(tick_nohz_full_running); static atomic_t tick_dep_mask; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d2d7cf6cfe83..7a52bc172841 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -215,16 +215,11 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = { static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { - int ret = security_locked_down(LOCKDOWN_BPF_READ); + int ret; - if (unlikely(ret < 0)) - goto fail; ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) - goto fail; - return ret; -fail: - memset(dst, 0, size); + memset(dst, 0, size); return ret; } @@ -246,10 +241,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_proto = { static __always_inline int bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) { - int ret = security_locked_down(LOCKDOWN_BPF_READ); - - if (unlikely(ret < 0)) - goto fail; + int ret; /* * The strncpy_from_kernel_nofault() call will likely not fill the @@ -262,11 +254,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) */ ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) - goto fail; - - return ret; -fail: - memset(dst, 0, size); + memset(dst, 0, size); return ret; } @@ -1011,16 +999,20 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return &bpf_probe_read_kernel_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return &bpf_probe_read_kernel_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: - return &bpf_probe_read_compat_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: - return &bpf_probe_read_compat_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2e8a3fde7104..72ef4dccbcc4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1967,12 +1967,18 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, static void print_ip_ins(const char *fmt, const unsigned char *p) { + char ins[MCOUNT_INSN_SIZE]; int i; + if (copy_from_kernel_nofault(ins, p, MCOUNT_INSN_SIZE)) { + printk(KERN_CONT "%s[FAULT] %px\n", fmt, p); + return; + } + printk(KERN_CONT "%s", fmt); for (i = 0; i < MCOUNT_INSN_SIZE; i++) - printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); + printk(KERN_CONT "%s%02x", i ? ":" : "", ins[i]); } enum ftrace_bug_type ftrace_bug_type; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a21ef9cd2aae..d23a09d3eb37 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2198,9 +2198,6 @@ struct saved_cmdlines_buffer { }; static struct saved_cmdlines_buffer *savedcmd; -/* temporary disable recording */ -static atomic_t trace_record_taskinfo_disabled __read_mostly; - static inline char *get_saved_cmdlines(int idx) { return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; @@ -2486,8 +2483,6 @@ static bool tracing_record_taskinfo_skip(int flags) { if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) return true; - if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on()) - return true; if (!__this_cpu_read(trace_taskinfo_save)) return true; return false; @@ -2736,7 +2731,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, (entry = this_cpu_read(trace_buffered_event))) { /* Try to use the per cpu buffer first */ val = this_cpu_inc_return(trace_buffered_event_cnt); - if ((len < (PAGE_SIZE - sizeof(*entry))) && val == 1) { + if ((len < (PAGE_SIZE - sizeof(*entry) - sizeof(entry->array[0]))) && val == 1) { trace_event_setup(entry, type, trace_ctx); entry->array[0] = len; return entry; @@ -3998,9 +3993,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EBUSY); #endif - if (!iter->snapshot) - atomic_inc(&trace_record_taskinfo_disabled); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -4043,9 +4035,6 @@ static void s_stop(struct seq_file *m, void *p) return; #endif - if (!iter->snapshot) - atomic_dec(&trace_record_taskinfo_disabled); - trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index c1637f90c8a3..4702efb00ff2 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -115,9 +115,9 @@ u64 notrace trace_clock_global(void) prev_time = READ_ONCE(trace_clock_struct.prev_time); now = sched_clock_cpu(this_cpu); - /* Make sure that now is always greater than prev_time */ + /* Make sure that now is always greater than or equal to prev_time */ if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time; /* * If in an NMI context then dont risk lockups and simply return @@ -131,7 +131,7 @@ u64 notrace trace_clock_global(void) /* Reread prev_time in case it was already updated */ prev_time = READ_ONCE(trace_clock_struct.prev_time); if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time; trace_clock_struct.prev_time = now; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b19d759e55a5..50142fc08902 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -50,6 +50,7 @@ #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> +#include <linux/kvm_para.h> #include "workqueue_internal.h" @@ -5772,6 +5773,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; + unsigned long now = jiffies; struct worker_pool *pool; int pi; @@ -5786,6 +5788,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) if (list_empty(&pool->worklist)) continue; + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like a stall. + */ + kvm_check_and_clear_guest_paused(); + /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); @@ -5799,12 +5807,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) ts = touched; /* did we stall? */ - if (time_after(jiffies, ts + thresh)) { + if (time_after(now, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", - jiffies_to_msecs(jiffies - pool_ts) / 1000); + jiffies_to_msecs(now - pool_ts) / 1000); } } diff --git a/lib/crc64.c b/lib/crc64.c index 47cfa054827f..9f852a89ee2a 100644 --- a/lib/crc64.c +++ b/lib/crc64.c @@ -37,7 +37,7 @@ MODULE_LICENSE("GPL v2"); /** * crc64_be - Calculate bitwise big-endian ECMA-182 CRC64 * @crc: seed value for computation. 0 or (u64)~0 for a new CRC calculation, - or the previous crc64 value if computing incrementally. + * or the previous crc64 value if computing incrementally. * @p: pointer to buffer over which CRC64 is run * @len: length of buffer @p */ diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index a1071cdefb5a..af9302141bcf 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -275,7 +275,7 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref, wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch, percpu_ref_switch_lock); - if (data->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD)) + if (data->force_atomic || percpu_ref_is_dying(ref)) __percpu_ref_switch_to_atomic(ref, confirm_switch); else __percpu_ref_switch_to_percpu(ref); @@ -385,7 +385,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, spin_lock_irqsave(&percpu_ref_switch_lock, flags); - WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD, + WARN_ONCE(percpu_ref_is_dying(ref), "%s called more than once on %ps!", __func__, ref->data->release); @@ -465,7 +465,7 @@ void percpu_ref_resurrect(struct percpu_ref *ref) spin_lock_irqsave(&percpu_ref_switch_lock, flags); - WARN_ON_ONCE(!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)); + WARN_ON_ONCE(!percpu_ref_is_dying(ref)); WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count)); ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD; diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 05efe98a9ac2..297d1b349c19 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -192,7 +192,7 @@ static void __init pmd_advanced_tests(struct mm_struct *mm, pr_debug("Validating PMD advanced\n"); /* Align the address wrt HPAGE_PMD_SIZE */ - vaddr = (vaddr & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE; + vaddr &= HPAGE_PMD_MASK; pgtable_trans_huge_deposit(mm, pmdp, pgtable); @@ -330,7 +330,7 @@ static void __init pud_advanced_tests(struct mm_struct *mm, pr_debug("Validating PUD advanced\n"); /* Align the address wrt HPAGE_PUD_SIZE */ - vaddr = (vaddr & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE; + vaddr &= HPAGE_PUD_MASK; set_pud_at(mm, vaddr, pudp, pud); pudp_set_wrprotect(mm, vaddr, pudp); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 63ed6b25deaa..6d2a0119fc58 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -62,6 +62,7 @@ static struct shrinker deferred_split_shrinker; static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; +unsigned long huge_zero_pfn __read_mostly = ~0UL; bool transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -98,6 +99,7 @@ retry: __free_pages(zero_page, compound_order(zero_page)); goto retry; } + WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); @@ -147,6 +149,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -2044,7 +2047,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { - _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it @@ -2053,16 +2056,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, zap_deposited_table(mm, pmd); if (vma_is_special_huge(vma)) return; - page = pmd_page(_pmd); - if (!PageDirty(page) && pmd_dirty(_pmd)) - set_page_dirty(page); - if (!PageReferenced(page) && pmd_young(_pmd)) - SetPageReferenced(page); - page_remove_rmap(page, true); - put_page(page); + if (unlikely(is_pmd_migration_entry(old_pmd))) { + swp_entry_t entry; + + entry = pmd_to_swp_entry(old_pmd); + page = migration_entry_to_page(entry); + } else { + page = pmd_page(old_pmd); + if (!PageDirty(page) && pmd_dirty(old_pmd)) + set_page_dirty(page); + if (!PageReferenced(page) && pmd_young(old_pmd)) + SetPageReferenced(page); + page_remove_rmap(page, true); + put_page(page); + } add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; - } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { + } + + if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside @@ -2338,17 +2350,17 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_page(struct page *page) { - enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | + enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; - bool unmap_success; VM_BUG_ON_PAGE(!PageHead(page), page); if (PageAnon(page)) ttu_flags |= TTU_SPLIT_FREEZE; - unmap_success = try_to_unmap(page, ttu_flags); - VM_BUG_ON_PAGE(!unmap_success, page); + try_to_unmap(page, ttu_flags); + + VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); } static void remap_page(struct page *page, unsigned int nr) @@ -2659,7 +2671,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) struct deferred_split *ds_queue = get_deferred_split_queue(head); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; - int count, mapcount, extra_pins, ret; + int extra_pins, ret; pgoff_t end; VM_BUG_ON_PAGE(is_huge_zero_page(head), head); @@ -2718,7 +2730,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } unmap_page(head); - VM_BUG_ON_PAGE(compound_mapcount(head), head); /* block interrupt reentry in xa_lock and spinlock */ local_irq_disable(); @@ -2736,9 +2747,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&ds_queue->split_queue_lock); - count = page_count(head); - mapcount = total_mapcount(head); - if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { + if (page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { ds_queue->split_queue_len--; list_del(page_deferred_list(head)); @@ -2758,16 +2767,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) __split_huge_page(page, list, end); ret = 0; } else { - if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - pr_alert("total_mapcount: %u, page_count(): %u\n", - mapcount, count); - if (PageTail(page)) - dump_page(head, NULL); - dump_page(page, "total_mapcount(head) > 0"); - BUG(); - } spin_unlock(&ds_queue->split_queue_lock); -fail: if (mapping) +fail: + if (mapping) xa_unlock(&mapping->i_pages); local_irq_enable(); remap_page(head, thp_nr_pages(head)); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 95918f410c0f..e0a5f9cbbece 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1793,7 +1793,7 @@ retry: SetPageHWPoison(page); ClearPageHWPoison(head); } - remove_hugetlb_page(h, page, false); + remove_hugetlb_page(h, head, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); update_and_free_page(h, head); @@ -2121,12 +2121,18 @@ out: * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. + * + * vma_del_reservation is used in error paths where an entry in the reserve + * map was created during huge page allocation and must be removed. It is to + * be called after calling vma_needs_reservation to determine if a reservation + * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, + VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, @@ -2170,11 +2176,21 @@ static long __vma_reservation_common(struct hstate *h, ret = region_del(resv, idx, idx + 1); } break; + case VMA_DEL_RESV: + if (vma->vm_flags & VM_MAYSHARE) { + region_abort(resv, idx, idx + 1, 1); + ret = region_del(resv, idx, idx + 1); + } else { + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); + } + break; default: BUG(); } - if (vma->vm_flags & VM_MAYSHARE) + if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. @@ -2222,25 +2238,39 @@ static long vma_add_reservation(struct hstate *h, return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } +static long vma_del_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); +} + /* - * This routine is called to restore a reservation on error paths. In the - * specific error paths, a huge page was allocated (via alloc_huge_page) - * and is about to be freed. If a reservation for the page existed, - * alloc_huge_page would have consumed the reservation and set - * HPageRestoreReserve in the newly allocated page. When the page is freed - * via free_huge_page, the global reservation count will be incremented if - * HPageRestoreReserve is set. However, free_huge_page can not adjust the - * reserve map. Adjust the reserve map here to be consistent with global - * reserve count adjustments to be made by free_huge_page. + * This routine is called to restore reservation information on error paths. + * It should ONLY be called for pages allocated via alloc_huge_page(), and + * the hugetlb mutex should remain held when calling this routine. + * + * It handles two specific cases: + * 1) A reservation was in place and the page consumed the reservation. + * HPageRestoreReserve is set in the page. + * 2) No reservation was in place for the page, so HPageRestoreReserve is + * not set. However, alloc_huge_page always updates the reserve map. + * + * In case 1, free_huge_page later in the error path will increment the + * global reserve count. But, free_huge_page does not have enough context + * to adjust the reservation map. This case deals primarily with private + * mappings. Adjust the reserve map here to be consistent with global + * reserve count adjustments to be made by free_huge_page. Make sure the + * reserve map indicates there is a reservation present. + * + * In case 2, simply undo reserve map modifications done by alloc_huge_page. */ -static void restore_reserve_on_error(struct hstate *h, - struct vm_area_struct *vma, unsigned long address, - struct page *page) +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page) { - if (unlikely(HPageRestoreReserve(page))) { - long rc = vma_needs_reservation(h, vma, address); + long rc = vma_needs_reservation(h, vma, address); - if (unlikely(rc < 0)) { + if (HPageRestoreReserve(page)) { + if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear HPageRestoreReserve so that @@ -2253,16 +2283,57 @@ static void restore_reserve_on_error(struct hstate *h, * accounting of reserve counts. */ ClearHPageRestoreReserve(page); - } else if (rc) { - rc = vma_add_reservation(h, vma, address); - if (unlikely(rc < 0)) + else if (rc) + (void)vma_add_reservation(h, vma, address); + else + vma_end_reservation(h, vma, address); + } else { + if (!rc) { + /* + * This indicates there is an entry in the reserve map + * added by alloc_huge_page. We know it was added + * before the alloc_huge_page call, otherwise + * HPageRestoreReserve would be set on the page. + * Remove the entry so that a subsequent allocation + * does not consume a reservation. + */ + rc = vma_del_reservation(h, vma, address); + if (rc < 0) /* - * See above comment about rare out of - * memory condition. + * VERY rare out of memory condition. Since + * we can not delete the entry, set + * HPageRestoreReserve so that the reserve + * count will be incremented when the page + * is freed. This reserve will be consumed + * on a subsequent allocation. */ - ClearHPageRestoreReserve(page); + SetHPageRestoreReserve(page); + } else if (rc < 0) { + /* + * Rare out of memory condition from + * vma_needs_reservation call. Memory allocation is + * only attempted if a new entry is needed. Therefore, + * this implies there is not an entry in the + * reserve map. + * + * For shared mappings, no entry in the map indicates + * no reservation. We are done. + */ + if (!(vma->vm_flags & VM_MAYSHARE)) + /* + * For private mappings, no entry indicates + * a reservation is present. Since we can + * not add an entry, set SetHPageRestoreReserve + * on the page so reserve count will be + * incremented when freed. This reserve will + * be consumed on a subsequent allocation. + */ + SetHPageRestoreReserve(page); } else - vma_end_reservation(h, vma, address); + /* + * No reservation present, do nothing + */ + vma_end_reservation(h, vma, address); } } @@ -4037,6 +4108,8 @@ again: spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { + restore_reserve_on_error(h, vma, addr, + new); put_page(new); /* dst_entry won't change as in child */ goto again; @@ -4889,10 +4962,20 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (!page) goto out; } else if (!*pagep) { - ret = -ENOMEM; + /* If a page already exists, then it's UFFDIO_COPY for + * a non-missing case. Return -EEXIST. + */ + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + ret = -EEXIST; + goto out; + } + page = alloc_huge_page(dst_vma, dst_addr, 0); - if (IS_ERR(page)) + if (IS_ERR(page)) { + ret = -ENOMEM; goto out; + } ret = copy_huge_page_from_user(page, (const void __user *) src_addr, @@ -4996,6 +5079,7 @@ out_release_unlock: if (vm_shared || is_continue) unlock_page(page); out_release_nounlock: + restore_reserve_on_error(h, dst_vma, dst_addr, page); put_page(page); goto out; } @@ -5847,6 +5931,21 @@ unlock: return ret; } +int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +{ + int ret = 0; + + *hugetlb = false; + spin_lock_irq(&hugetlb_lock); + if (PageHeadHuge(page)) { + *hugetlb = true; + if (HPageFreed(page) || HPageMigratable(page)) + ret = get_page_unless_zero(page); + } + spin_unlock_irq(&hugetlb_lock); + return ret; +} + void putback_active_hugepage(struct page *page) { spin_lock_irq(&hugetlb_lock); diff --git a/mm/internal.h b/mm/internal.h index 2f1182948aa6..e8fdb531f887 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -384,27 +384,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* - * At what user virtual address is page expected in @vma? + * At what user virtual address is page expected in vma? + * Returns -EFAULT if all of the page is outside the range of vma. + * If page is a compound head, the entire compound page is considered. */ static inline unsigned long -__vma_address(struct page *page, struct vm_area_struct *vma) +vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page_to_pgoff(page); - return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page); + if (pgoff >= vma->vm_pgoff) { + address = vma->vm_start + + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address >= vma->vm_end) + address = -EFAULT; + } else if (PageHead(page) && + pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { + /* Test above avoids possibility of wrap to 0 on 32-bit */ + address = vma->vm_start; + } else { + address = -EFAULT; + } + return address; } +/* + * Then at what user virtual address will none of the page be found in vma? + * Assumes that vma_address() already returned a good starting address. + * If page is a compound head, the entire compound page is considered. + */ static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) +vma_address_end(struct page *page, struct vm_area_struct *vma) { - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE; - - /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); - - return max(start, vma->vm_start); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page) + compound_nr(page); + address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address > vma->vm_end) + address = vma->vm_end; + return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, diff --git a/mm/kasan/init.c b/mm/kasan/init.c index c4605ac9837b..348f31d15a97 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -220,8 +220,8 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, /** * kasan_populate_early_shadow - populate shadow memory region with * kasan_early_shadow_page - * @shadow_start - start of the memory range to populate - * @shadow_end - end of the memory range to populate + * @shadow_start: start of the memory range to populate + * @shadow_end: end of the memory range to populate */ int __ref kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index e18fbbd5d9b4..4d21ac44d5d3 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -627,10 +627,10 @@ static void toggle_allocation_gate(struct work_struct *work) * During low activity with no allocations we might wait a * while; let's avoid the hung task warning. */ - wait_event_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), - sysctl_hung_task_timeout_secs * HZ / 2); + wait_event_idle_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), + sysctl_hung_task_timeout_secs * HZ / 2); } else { - wait_event(allocation_wait, atomic_read(&kfence_allocation_gate)); + wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate)); } /* Disable static key and reset timer. */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 85ad98c00fd9..0143d32bc666 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -949,6 +949,17 @@ static int page_action(struct page_state *ps, struct page *p, return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } +/* + * Return true if a page type of a given page is supported by hwpoison + * mechanism (while handling could fail), otherwise false. This function + * does not return true for hugetlb or device memory pages, so it's assumed + * to be called only in the context where we never have such pages. + */ +static inline bool HWPoisonHandlable(struct page *page) +{ + return PageLRU(page) || __PageMovable(page); +} + /** * __get_hwpoison_page() - Get refcount for memory error handling: * @page: raw error page (hit by memory error) @@ -959,8 +970,22 @@ static int page_action(struct page_state *ps, struct page *p, static int __get_hwpoison_page(struct page *page) { struct page *head = compound_head(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_huge_page(head, &hugetlb); + if (hugetlb) + return ret; - if (!PageHuge(head) && PageTransHuge(head)) { + /* + * This check prevents from calling get_hwpoison_unless_zero() + * for any unsupported type of page in order to reduce the risk of + * unexpected races caused by taking a page refcount. + */ + if (!HWPoisonHandlable(head)) + return 0; + + if (PageTransHuge(head)) { /* * Non anonymous thp exists only in allocation/free time. We * can't handle such a case correctly, so let's give it up. @@ -1017,7 +1042,7 @@ try_again: ret = -EIO; } } else { - if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) { + if (PageHuge(p) || HWPoisonHandlable(p)) { ret = 1; } else { /* @@ -1527,7 +1552,12 @@ try_again: return 0; } - if (!PageTransTail(p) && !PageLRU(p)) + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p)) goto identify_page_state; /* diff --git a/mm/memory.c b/mm/memory.c index 730daa00952b..486f4a2874e7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1361,7 +1361,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ + } else if (details && details->single_page && + PageTransCompound(details->single_page) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); } + /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is @@ -2939,6 +2950,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* @@ -3236,6 +3248,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } /** + * unmap_mapping_page() - Unmap single page from processes. + * @page: The locked page to be unmapped. + * + * Unmap this page from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a page, it may find that + * the page has been remapped again: and then uses unmap_mapping_page() + * to unmap it finally. + */ +void unmap_mapping_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct zap_details details = { }; + + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageTail(page)); + + details.check_mapping = mapping; + details.first_index = page->index; + details.last_index = page->index + thp_nr_pages(page) - 1; + details.single_page = page; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + +/** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. @@ -3602,6 +3644,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); @@ -3786,6 +3829,8 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); + else + entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); diff --git a/mm/migrate.c b/mm/migrate.c index b234c3f3acb7..41ff2c9896c4 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -295,6 +295,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, goto out; page = migration_entry_to_page(entry); + page = compound_head(page); /* * Once page cache replacement of page migration started, page_count diff --git a/mm/page_alloc.c b/mm/page_alloc.c index aaa1655cf682..d1f5de1c1283 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -9158,6 +9158,8 @@ bool take_page_off_buddy(struct page *page) del_page_from_free_list(page_head, zone, page_order); break_down_buddy_pages(zone, page_head, page, 0, page_order, migratetype); + if (!is_migrate_isolate(migratetype)) + __mod_zone_freepage_state(zone, -1, migratetype); ret = true; break; } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 2cf01d933f13..e37bd43904af 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -212,23 +212,34 @@ restart: pvmw->ptl = NULL; } } else if (!pmd_present(pmde)) { + /* + * If PVMW_SYNC, take and drop THP pmd lock so that we + * cannot return prematurely, while zap_huge_pmd() has + * cleared *pmd but not decremented compound_mapcount(). + */ + if ((pvmw->flags & PVMW_SYNC) && + PageTransCompound(pvmw->page)) { + spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); + + spin_unlock(ptl); + } return false; } if (!map_pte(pvmw)) goto next_pte; while (1) { + unsigned long end; + if (check_pte(pvmw)) return true; next_pte: /* Seek to next pte only makes sense for THP */ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) return not_found(pvmw); + end = vma_address_end(pvmw->page, pvmw->vma); do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= pvmw->vma->vm_end || - pvmw->address >= - __vma_address(pvmw->page, pvmw->vma) + - thp_size(pvmw->page)) + if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ if (pvmw->address % PMD_SIZE == 0) { @@ -266,14 +277,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .vma = vma, .flags = PVMW_SYNC, }; - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE; - if (unlikely(end < vma->vm_start || start >= vma->vm_end)) + pvmw.address = vma_address(page, vma); + if (pvmw.address == -EFAULT) return 0; - pvmw.address = max(start, vma->vm_start); if (!page_vma_mapped_walk(&pvmw)) return 0; page_vma_mapped_walk_done(&pvmw); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index c2210e1cdb51..4e640baf9794 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -135,9 +135,8 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON(!pmd_present(*pmdp)); - /* Below assumes pmd_present() is true */ - VM_BUG_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); + VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && + !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; diff --git a/mm/rmap.c b/mm/rmap.c index 693a610e181d..e05c300048e6 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -707,7 +707,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* @@ -717,15 +716,13 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping) { - if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) - return -EFAULT; - } else + } else if (!vma->vm_file) { return -EFAULT; - address = __vma_address(page, vma); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { return -EFAULT; - return address; + } + + return vma_address(page, vma); } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) @@ -919,7 +916,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, - min(vma->vm_end, address + page_size(page))); + vma_address_end(page, vma)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { @@ -1405,6 +1402,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; + /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; @@ -1426,9 +1432,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - address, - min(vma->vm_end, address + page_size(page))); + address, range.end); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted @@ -1777,7 +1784,13 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) else rmap_walk(page, &rwc); - return !page_mapcount(page) ? true : false; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + return !page_mapcount(page); } /** @@ -1874,6 +1887,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) @@ -1928,6 +1942,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) diff --git a/mm/slab_common.c b/mm/slab_common.c index a4a571428c51..7cab77655f11 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -97,8 +97,7 @@ EXPORT_SYMBOL(kmem_cache_size); #ifdef CONFIG_DEBUG_VM static int kmem_cache_sanity_check(const char *name, unsigned int size) { - if (!name || in_interrupt() || size < sizeof(void *) || - size > KMALLOC_MAX_SIZE) { + if (!name || in_interrupt() || size > KMALLOC_MAX_SIZE) { pr_err("kmem_cache_create(%s) integrity check failed\n", name); return -EINVAL; } diff --git a/mm/slub.c b/mm/slub.c index 3f96e099817a..61bd40e3eb9a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/bit_spinlock.h> #include <linux/interrupt.h> +#include <linux/swab.h> #include <linux/bitops.h> #include <linux/slab.h> #include "slab.h" @@ -712,15 +713,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, + print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, s->red_left_pad); else if (p > addr + 16) print_section(KERN_ERR, "Bytes b4 ", p - 16, 16); - print_section(KERN_ERR, "Object ", p, + print_section(KERN_ERR, "Object ", p, min_t(unsigned int, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p + s->object_size, + print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); off = get_info_end(s); @@ -732,7 +733,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != size_from_object(s)) /* Beginning of the filler is the free pointer */ - print_section(KERN_ERR, "Padding ", p + off, + print_section(KERN_ERR, "Padding ", p + off, size_from_object(s) - off); dump_stack(); @@ -909,11 +910,11 @@ static int check_object(struct kmem_cache *s, struct page *page, u8 *endobject = object + s->object_size; if (s->flags & SLAB_RED_ZONE) { - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Left Redzone", object - s->red_left_pad, val, s->red_left_pad)) return 0; - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Right Redzone", endobject, val, s->inuse - s->object_size)) return 0; } else { @@ -928,7 +929,7 @@ static int check_object(struct kmem_cache *s, struct page *page, if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && (!check_bytes_and_report(s, page, p, "Poison", p, POISON_FREE, s->object_size - 1) || - !check_bytes_and_report(s, page, p, "Poison", + !check_bytes_and_report(s, page, p, "End Poison", p + s->object_size - 1, POISON_END, 1))) return 0; /* @@ -3689,7 +3690,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) { slab_flags_t flags = s->flags; unsigned int size = s->object_size; - unsigned int freepointer_area; unsigned int order; /* @@ -3698,13 +3698,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * the possible location of the free pointer. */ size = ALIGN(size, sizeof(void *)); - /* - * This is the area of the object where a freepointer can be - * safely written. If redzoning adds more to the inuse size, we - * can't use that portion for writing the freepointer, so - * s->offset must be limited within this for the general case. - */ - freepointer_area = size; #ifdef CONFIG_SLUB_DEBUG /* @@ -3730,19 +3723,21 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) /* * With that we have determined the number of bytes in actual use - * by the object. This is the potential offset to the free pointer. + * by the object and redzoning. */ s->inuse = size; - if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || - s->ctor)) { + if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || + ((flags & SLAB_RED_ZONE) && s->object_size < sizeof(void *)) || + s->ctor) { /* * Relocate free pointer after the object if it is not * permitted to overwrite the first word of the object on * kmem_cache_free. * * This is the case if we do RCU, have a constructor or - * destructor or are poisoning the objects. + * destructor, are poisoning the objects, or are + * redzoning an object smaller than sizeof(void *). * * The assumption that s->offset >= s->inuse means free * pointer is outside of the object is used in the @@ -3751,13 +3746,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) */ s->offset = size; size += sizeof(void *); - } else if (freepointer_area > sizeof(void *)) { + } else { /* * Store freelist pointer near middle of object to keep * it away from the edges of the object to avoid small * sized over/underflows from neighboring allocations. */ - s->offset = ALIGN(freepointer_area / 2, sizeof(void *)); + s->offset = ALIGN_DOWN(s->object_size / 2, sizeof(void *)); } #ifdef CONFIG_SLUB_DEBUG diff --git a/mm/sparse.c b/mm/sparse.c index b2ada9dc00cb..55c18aff3e42 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -344,6 +344,15 @@ size_t mem_section_usage_size(void) return sizeof(struct mem_section_usage) + usemap_size(); } +static inline phys_addr_t pgdat_to_phys(struct pglist_data *pgdat) +{ +#ifndef CONFIG_NEED_MULTIPLE_NODES + return __pa_symbol(pgdat); +#else + return __pa(pgdat); +#endif +} + #ifdef CONFIG_MEMORY_HOTREMOVE static struct mem_section_usage * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, @@ -362,7 +371,7 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, * from the same section as the pgdat where possible to avoid * this problem. */ - goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); + goal = pgdat_to_phys(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); limit = goal + (1UL << PA_SECTION_SHIFT); nid = early_pfn_to_nid(goal >> PAGE_SHIFT); again: @@ -390,7 +399,7 @@ static void __init check_usemap_section_nr(int nid, } usemap_snr = pfn_to_section_nr(__pa(usage) >> PAGE_SHIFT); - pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT); + pgdat_snr = pfn_to_section_nr(pgdat_to_phys(pgdat) >> PAGE_SHIFT); if (usemap_snr == pgdat_snr) return; diff --git a/mm/swapfile.c b/mm/swapfile.c index 149e77454e3c..996afa8131c8 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1900,7 +1900,7 @@ unsigned int count_swap_pages(int type, int free) static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { - return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte); + return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* diff --git a/mm/truncate.c b/mm/truncate.c index 95af244b112a..234ddd879caa 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -167,13 +167,10 @@ void do_invalidatepage(struct page *page, unsigned int offset, * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void -truncate_cleanup_page(struct address_space *mapping, struct page *page) +static void truncate_cleanup_page(struct page *page) { - if (page_mapped(page)) { - unsigned int nr = thp_nr_pages(page); - unmap_mapping_pages(mapping, page->index, nr, false); - } + if (page_mapped(page)) + unmap_mapping_page(page); if (page_has_private(page)) do_invalidatepage(page, 0, thp_size(page)); @@ -218,7 +215,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return -EIO; - truncate_cleanup_page(mapping, page); + truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } @@ -325,7 +322,7 @@ void truncate_inode_pages_range(struct address_space *mapping, index = indices[pagevec_count(&pvec) - 1] + 1; truncate_exceptional_pvec_entries(mapping, &pvec, indices); for (i = 0; i < pagevec_count(&pvec); i++) - truncate_cleanup_page(mapping, pvec.pages[i]); + truncate_cleanup_page(pvec.pages[i]); delete_from_page_cache_batch(mapping, &pvec); for (i = 0; i < pagevec_count(&pvec); i++) unlock_page(pvec.pages[i]); @@ -639,6 +636,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } + if (!did_range_unmap && page_mapped(page)) { + /* + * If page is mapped, before taking its lock, + * zap the rest of the file in one hit. + */ + unmap_mapping_pages(mapping, index, + (1 + end - index), false); + did_range_unmap = 1; + } + lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { @@ -646,23 +653,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } wait_on_page_writeback(page); - if (page_mapped(page)) { - if (!did_range_unmap) { - /* - * Zap the rest of the file in one hit. - */ - unmap_mapping_pages(mapping, index, - (1 + end - index), false); - did_range_unmap = 1; - } else { - /* - * Just zap this page - */ - unmap_mapping_pages(mapping, index, - 1, false); - } - } + + if (page_mapped(page)) + unmap_mapping_page(page); BUG_ON(page_mapped(page)); + ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page)) diff --git a/net/Kconfig b/net/Kconfig index f5ee7c65e6b4..c7392c449b25 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -302,21 +302,6 @@ config BQL select DQL default y -config BPF_JIT - bool "enable BPF Just In Time compiler" - depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT - depends on MODULES - help - Berkeley Packet Filter filtering capabilities are normally handled - by an interpreter. This option allows kernel to generate a native - code when filter is loaded in memory. This should speedup - packet sniffing (libpcap/tcpdump). - - Note, admin should enable this feature changing: - /proc/sys/net/core/bpf_jit_enable - /proc/sys/net/core/bpf_jit_harden (optional) - /proc/sys/net/core/bpf_jit_kallsyms (optional) - config BPF_STREAM_PARSER bool "enable BPF STREAM_PARSER" depends on INET @@ -470,15 +455,3 @@ config ETHTOOL_NETLINK e.g. notification messages. endif # if NET - -# Used by archs to tell that they support BPF JIT compiler plus which flavour. -# Only one of the two can be selected for a specific arch since eBPF JIT supersedes -# the cBPF JIT. - -# Classic BPF JIT (cBPF) -config HAVE_CBPF_JIT - bool - -# Extended BPF JIT (eBPF) -config HAVE_EBPF_JIT - bool diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index be18af481d7d..c7236daa2415 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -768,7 +768,7 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, if (a && a->status & ATIF_PROBE) { a->status |= ATIF_PROBE_FAIL; /* - * we do not respond to probe or request packets for + * we do not respond to probe or request packets of * this address while we are probing this address */ goto unlock; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 789f257be24f..fc8be49010b9 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -409,8 +409,10 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) if (WARN_ON(!forw_packet->if_outgoing)) return; - if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) + if (forw_packet->if_outgoing->soft_iface != soft_iface) { + pr_warn("%s: soft interface switch for queued OGM\n", __func__); return; + } if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) return; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index fd12f1652bdf..7d71d104fdfd 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1610,8 +1610,13 @@ setup_failed: } else { /* Init failed, cleanup */ flush_work(&hdev->tx_work); - flush_work(&hdev->cmd_work); + + /* Since hci_rx_work() is possible to awake new cmd_work + * it should be flushed first to avoid unexpected call of + * hci_cmd_work() + */ flush_work(&hdev->rx_work); + flush_work(&hdev->cmd_work); skb_queue_purge(&hdev->cmd_q); skb_queue_purge(&hdev->rx_q); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 251b9128f530..eed0dd066e12 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -762,7 +762,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) /* Detach sockets from device */ read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { - bh_lock_sock_nested(sk); + lock_sock(sk); if (hci_pi(sk)->hdev == hdev) { hci_pi(sk)->hdev = NULL; sk->sk_err = EPIPE; @@ -771,7 +771,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) hci_dev_put(hdev); } - bh_unlock_sock(sk); + release_sock(sk); } read_unlock(&hci_sk_list.lock); } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 372e3b25aaa4..7dd51da73845 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -3229,7 +3229,7 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) { struct l2cap_chan *chan; - bt_dev_dbg(pchan->conn->hcon->hdev, "pchan %p", pchan); + BT_DBG("pchan %p", pchan); chan = l2cap_chan_create(); if (!chan) @@ -3250,7 +3250,7 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) */ atomic_set(&chan->nesting, L2CAP_NESTING_SMP); - bt_dev_dbg(pchan->conn->hcon->hdev, "created chan %p", chan); + BT_DBG("created chan %p", chan); return chan; } @@ -3354,7 +3354,7 @@ static void smp_del_chan(struct l2cap_chan *chan) { struct smp_dev *smp; - bt_dev_dbg(chan->conn->hcon->hdev, "chan %p", chan); + BT_DBG("chan %p", chan); smp = chan->data; if (smp) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 7ce8a77cc6b6..e013d33f1c7c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -90,8 +90,8 @@ struct bridge_mcast_stats { #endif struct br_tunnel_info { - __be64 tunnel_id; - struct metadata_dst *tunnel_dst; + __be64 tunnel_id; + struct metadata_dst __rcu *tunnel_dst; }; /* private vlan flags */ diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 0d3a8c01552e..01017448ebde 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -41,26 +41,33 @@ static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, br_vlan_tunnel_rht_params); } +static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan) +{ + struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst); + + WRITE_ONCE(vlan->tinfo.tunnel_id, 0); + RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL); + dst_release(&tdst->dst); +} + void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan) { - if (!vlan->tinfo.tunnel_dst) + if (!rcu_access_pointer(vlan->tinfo.tunnel_dst)) return; rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); - vlan->tinfo.tunnel_id = 0; - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; + vlan_tunnel_info_release(vlan); } static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u32 tun_id) { - struct metadata_dst *metadata = NULL; + struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); int err; - if (vlan->tinfo.tunnel_dst) + if (metadata) return -EEXIST; metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, @@ -69,8 +76,8 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return -EINVAL; metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; - vlan->tinfo.tunnel_dst = metadata; - vlan->tinfo.tunnel_id = key; + rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata); + WRITE_ONCE(vlan->tinfo.tunnel_id, key); err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); @@ -79,9 +86,7 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return 0; out: - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; - vlan->tinfo.tunnel_id = 0; + vlan_tunnel_info_release(vlan); return err; } @@ -182,12 +187,15 @@ int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + struct metadata_dst *tunnel_dst; + __be64 tunnel_id; int err; - if (!vlan || !vlan->tinfo.tunnel_id) + if (!vlan) return 0; - if (unlikely(!skb_vlan_tag_present(skb))) + tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id); + if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb))) return 0; skb_dst_drop(skb); @@ -195,7 +203,9 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, if (err) return err; - skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst)); + tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); + if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst)) + skb_dst_set(skb, &tunnel_dst->dst); return 0; } diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index c10e5a55758d..440139706130 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -308,7 +308,7 @@ static void dev_flowctrl(struct net_device *dev, int on) caifd_put(caifd); } -void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, +int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)(struct sk_buff *, struct net_device *, @@ -319,11 +319,12 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, enum cfcnfg_phy_preference pref; struct cfcnfg *cfg = get_cfcnfg(dev_net(dev)); struct caif_device_entry_list *caifdevs; + int res; caifdevs = caif_device_list(dev_net(dev)); caifd = caif_device_alloc(dev); if (!caifd) - return; + return -ENOMEM; *layer = &caifd->layer; spin_lock_init(&caifd->flow_lock); @@ -344,7 +345,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, strlcpy(caifd->layer.name, dev->name, sizeof(caifd->layer.name)); caifd->layer.transmit = transmit; - cfcnfg_add_phy_layer(cfg, + res = cfcnfg_add_phy_layer(cfg, dev, &caifd->layer, pref, @@ -354,6 +355,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, mutex_unlock(&caifdevs->lock); if (rcv_func) *rcv_func = receive; + return res; } EXPORT_SYMBOL(caif_enroll_dev); @@ -368,6 +370,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, struct cflayer *layer, *link_support; int head_room = 0; struct caif_device_entry_list *caifdevs; + int res; cfg = get_cfcnfg(dev_net(dev)); caifdevs = caif_device_list(dev_net(dev)); @@ -393,8 +396,10 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, break; } } - caif_enroll_dev(dev, caifdev, link_support, head_room, + res = caif_enroll_dev(dev, caifdev, link_support, head_room, &layer, NULL); + if (res) + cfserl_release(link_support); caifdev->flowctrl = dev_flowctrl; break; diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index a0116b9503d9..b02e1292f7f1 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -115,6 +115,11 @@ static struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN], return (struct cflayer *) this; } +static void cfusbl_release(struct cflayer *layer) +{ + kfree(layer); +} + static struct packet_type caif_usb_type __read_mostly = { .type = cpu_to_be16(ETH_P_802_EX1), }; @@ -127,6 +132,7 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, struct cflayer *layer, *link_support; struct usbnet *usbnet; struct usb_device *usbdev; + int res; /* Check whether we have a NCM device, and find its VID/PID. */ if (!(dev->dev.parent && dev->dev.parent->driver && @@ -169,8 +175,11 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, if (dev->num_tx_queues > 1) pr_warn("USB device uses more than one tx queue\n"); - caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN, + res = caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN, &layer, &caif_usb_type.func); + if (res) + goto err; + if (!pack_added) dev_add_pack(&caif_usb_type); pack_added = true; @@ -178,6 +187,9 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, strlcpy(layer->name, dev->name, sizeof(layer->name)); return 0; +err: + cfusbl_release(link_support); + return res; } static struct notifier_block caif_device_notifier = { diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index 399239a14420..cac30e676ac9 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -450,7 +450,7 @@ unlock: rcu_read_unlock(); } -void +int cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, @@ -459,7 +459,7 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, { struct cflayer *frml; struct cfcnfg_phyinfo *phyinfo = NULL; - int i; + int i, res = 0; u8 phyid; mutex_lock(&cnfg->lock); @@ -473,12 +473,15 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, goto got_phyid; } pr_warn("Too many CAIF Link Layers (max 6)\n"); + res = -EEXIST; goto out; got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); - if (!phyinfo) + if (!phyinfo) { + res = -ENOMEM; goto out_err; + } phy_layer->id = phyid; phyinfo->pref = pref; @@ -492,8 +495,10 @@ got_phyid: frml = cffrml_create(phyid, fcs); - if (!frml) + if (!frml) { + res = -ENOMEM; goto out_err; + } phyinfo->frm_layer = frml; layer_set_up(frml, cnfg->mux); @@ -511,11 +516,12 @@ got_phyid: list_add_rcu(&phyinfo->node, &cnfg->phys); out: mutex_unlock(&cnfg->lock); - return; + return res; out_err: kfree(phyinfo); mutex_unlock(&cnfg->lock); + return res; } EXPORT_SYMBOL(cfcnfg_add_phy_layer); diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c index e11725a4bb0e..40cd57ad0a0f 100644 --- a/net/caif/cfserl.c +++ b/net/caif/cfserl.c @@ -31,6 +31,11 @@ static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt); static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid); +void cfserl_release(struct cflayer *layer) +{ + kfree(layer); +} + struct cflayer *cfserl_create(int instance, bool use_stx) { struct cfserl *this = kzalloc(sizeof(struct cfserl), GFP_ATOMIC); diff --git a/net/can/bcm.c b/net/can/bcm.c index 909b9e684e04..f3e4d9528fa3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -125,7 +125,7 @@ struct bcm_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; @@ -133,6 +133,10 @@ struct bcm_sock { char procname [32]; /* inode number in decimal with \0 */ }; +static LIST_HEAD(bcm_notifier_list); +static DEFINE_SPINLOCK(bcm_notifier_lock); +static struct bcm_sock *bcm_busy_notifier; + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -402,6 +406,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; @@ -439,6 +444,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) /* this element is not throttled anymore */ data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV); + memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; @@ -560,6 +566,7 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) } /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; @@ -1378,20 +1385,15 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* * notification handler for netdevice status changes */ -static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void bcm_notify(struct bcm_sock *bo, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; switch (msg) { @@ -1426,7 +1428,28 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); } } +} +static int bcm_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&bcm_notifier_lock); + list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { + spin_unlock(&bcm_notifier_lock); + bcm_notify(bcm_busy_notifier, msg, dev); + spin_lock(&bcm_notifier_lock); + } + bcm_busy_notifier = NULL; + spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } @@ -1446,9 +1469,9 @@ static int bcm_init(struct sock *sk) INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ - bo->notifier.notifier_call = bcm_notifier; - - register_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + list_add_tail(&bo->notifier, &bcm_notifier_list); + spin_unlock(&bcm_notifier_lock); return 0; } @@ -1471,7 +1494,14 @@ static int bcm_release(struct socket *sock) /* remove bcm_ops, timer, rx_unregister(), etc. */ - unregister_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + while (bcm_busy_notifier == bo) { + spin_unlock(&bcm_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&bcm_notifier_lock); + } + list_del(&bo->notifier); + spin_unlock(&bcm_notifier_lock); lock_sock(sk); @@ -1692,6 +1722,10 @@ static struct pernet_operations canbcm_pernet_ops __read_mostly = { .exit = canbcm_pernet_exit, }; +static struct notifier_block canbcm_notifier = { + .notifier_call = bcm_notifier +}; + static int __init bcm_module_init(void) { int err; @@ -1705,12 +1739,14 @@ static int __init bcm_module_init(void) } register_pernet_subsys(&canbcm_pernet_ops); + register_netdevice_notifier(&canbcm_notifier); return 0; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); + unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } diff --git a/net/can/isotp.c b/net/can/isotp.c index 9f94ad3caee9..be6183f8ca11 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -143,10 +143,14 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; struct tpcon rx, tx; - struct notifier_block notifier; + struct list_head notifier; wait_queue_head_t wait; }; +static LIST_HEAD(isotp_notifier_list); +static DEFINE_SPINLOCK(isotp_notifier_lock); +static struct isotp_sock *isotp_busy_notifier; + static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; @@ -1013,7 +1017,14 @@ static int isotp_release(struct socket *sock) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - unregister_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + while (isotp_busy_notifier == so) { + spin_unlock(&isotp_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&isotp_notifier_lock); + } + list_del(&so->notifier); + spin_unlock(&isotp_notifier_lock); lock_sock(sk); @@ -1062,27 +1073,31 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (len < ISOTP_MIN_NAMELEN) return -EINVAL; + if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) + return -EADDRNOTAVAIL; + + if (!addr->can_ifindex) + return -ENODEV; + + lock_sock(sk); + /* do not register frame reception for functional addressing */ if (so->opt.flags & CAN_ISOTP_SF_BROADCAST) do_rx_reg = 0; /* do not validate rx address for functional addressing */ if (do_rx_reg) { - if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) - return -EADDRNOTAVAIL; + if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) { + err = -EADDRNOTAVAIL; + goto out; + } - if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) - return -EADDRNOTAVAIL; + if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) { + err = -EADDRNOTAVAIL; + goto out; + } } - if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) - return -EADDRNOTAVAIL; - - if (!addr->can_ifindex) - return -ENODEV; - - lock_sock(sk); - if (so->bound && addr->can_ifindex == so->ifindex && addr->can_addr.tp.rx_id == so->rxid && addr->can_addr.tp.tx_id == so->txid) @@ -1164,16 +1179,13 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) return ISOTP_MIN_NAMELEN; } -static int isotp_setsockopt(struct socket *sock, int level, int optname, +static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int ret = 0; - if (level != SOL_CAN_ISOTP) - return -EINVAL; - if (so->bound) return -EISCONN; @@ -1248,6 +1260,22 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, return ret; } +static int isotp_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) + +{ + struct sock *sk = sock->sk; + int ret; + + if (level != SOL_CAN_ISOTP) + return -EINVAL; + + lock_sock(sk); + ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen); + release_sock(sk); + return ret; +} + static int isotp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { @@ -1300,21 +1328,16 @@ static int isotp_getsockopt(struct socket *sock, int level, int optname, return 0; } -static int isotp_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void isotp_notify(struct isotp_sock *so, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier); struct sock *sk = &so->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (so->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -1340,7 +1363,28 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); break; } +} + +static int isotp_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&isotp_notifier_lock); + list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { + spin_unlock(&isotp_notifier_lock); + isotp_notify(isotp_busy_notifier, msg, dev); + spin_lock(&isotp_notifier_lock); + } + isotp_busy_notifier = NULL; + spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; } @@ -1377,8 +1421,9 @@ static int isotp_init(struct sock *sk) init_waitqueue_head(&so->wait); - so->notifier.notifier_call = isotp_notifier; - register_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + list_add_tail(&so->notifier, &isotp_notifier_list); + spin_unlock(&isotp_notifier_lock); return 0; } @@ -1425,6 +1470,10 @@ static const struct can_proto isotp_can_proto = { .prot = &isotp_proto, }; +static struct notifier_block canisotp_notifier = { + .notifier_call = isotp_notifier +}; + static __init int isotp_module_init(void) { int err; @@ -1434,6 +1483,8 @@ static __init int isotp_module_init(void) err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed\n"); + else + register_netdevice_notifier(&canisotp_notifier); return err; } @@ -1441,6 +1492,7 @@ static __init int isotp_module_init(void) static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); + unregister_netdevice_notifier(&canisotp_notifier); } module_init(isotp_module_init); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index e09d087ba240..c3946c355882 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -330,6 +330,9 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) if ((do_skcb->offset + do_skb->len) < offset_start) { __skb_unlink(do_skb, &session->skb_queue); + /* drop ref taken in j1939_session_skb_queue() */ + skb_unref(do_skb); + kfree_skb(do_skb); } spin_unlock_irqrestore(&session->skb_queue.lock, flags); @@ -349,12 +352,13 @@ void j1939_session_skb_queue(struct j1939_session *session, skcb->flags |= J1939_ECU_LOCAL_SRC; + skb_get(skb); skb_queue_tail(&session->skb_queue, skb); } static struct -sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, - unsigned int offset_start) +sk_buff *j1939_session_skb_get_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *do_skcb; @@ -371,6 +375,10 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, skb = do_skb; } } + + if (skb) + skb_get(skb); + spin_unlock_irqrestore(&session->skb_queue.lock, flags); if (!skb) @@ -381,12 +389,12 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, return skb; } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct sk_buff *j1939_session_skb_get(struct j1939_session *session) { unsigned int offset_start; offset_start = session->pkt.dpo * 7; - return j1939_session_skb_find_by_offset(session, offset_start); + return j1939_session_skb_get_by_offset(session, offset_start); } /* see if we are receiver @@ -776,7 +784,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); + se_skb = j1939_session_skb_get_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -801,7 +809,8 @@ static int j1939_session_tx_dat(struct j1939_session *session) netdev_err_once(priv->ndev, "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", __func__, session, skcb->offset, se_skb->len , session->pkt.tx); - return -EOVERFLOW; + ret = -EOVERFLOW; + goto out_free; } if (!len) { @@ -835,6 +844,12 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (pkt_done) j1939_tp_set_rxtimeout(session, 250); + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + return ret; } @@ -1007,7 +1022,7 @@ static int j1939_xtp_txnext_receiver(struct j1939_session *session) static int j1939_simple_txnext(struct j1939_session *session) { struct j1939_priv *priv = session->priv; - struct sk_buff *se_skb = j1939_session_skb_find(session); + struct sk_buff *se_skb = j1939_session_skb_get(session); struct sk_buff *skb; int ret; @@ -1015,8 +1030,10 @@ static int j1939_simple_txnext(struct j1939_session *session) return 0; skb = skb_clone(se_skb, GFP_ATOMIC); - if (!skb) - return -ENOMEM; + if (!skb) { + ret = -ENOMEM; + goto out_free; + } can_skb_set_owner(skb, se_skb->sk); @@ -1024,12 +1041,18 @@ static int j1939_simple_txnext(struct j1939_session *session) ret = j1939_send_one(priv, skb); if (ret) - return ret; + goto out_free; j1939_sk_errqueue(session, J1939_ERRQUEUE_SCHED); j1939_sk_queue_activate_next(session); - return 0; + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + + return ret; } static bool j1939_session_deactivate_locked(struct j1939_session *session) @@ -1170,9 +1193,10 @@ static void j1939_session_completed(struct j1939_session *session) struct sk_buff *skb; if (!session->transmission) { - skb = j1939_session_skb_find(session); + skb = j1939_session_skb_get(session); /* distribute among j1939 receivers */ j1939_sk_recv(session->priv, skb); + consume_skb(skb); } j1939_session_deactivate_activate_next(session); @@ -1744,7 +1768,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *skcb; - struct sk_buff *se_skb; + struct sk_buff *se_skb = NULL; const u8 *dat; u8 *tpdat; int offset; @@ -1786,7 +1810,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, goto out_session_cancel; } - se_skb = j1939_session_skb_find_by_offset(session, packet * 7); + se_skb = j1939_session_skb_get_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1848,11 +1872,13 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_tp_set_rxtimeout(session, 250); } session->last_cmd = 0xff; + consume_skb(se_skb); j1939_session_put(session); return; out_session_cancel: + kfree_skb(se_skb); j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); j1939_session_put(session); diff --git a/net/can/raw.c b/net/can/raw.c index 139d9471ddcf..ac96fc210025 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -83,7 +83,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; @@ -95,6 +95,10 @@ struct raw_sock { struct uniqframe __percpu *uniq; }; +static LIST_HEAD(raw_notifier_list); +static DEFINE_SPINLOCK(raw_notifier_lock); +static struct raw_sock *raw_busy_notifier; + /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. @@ -263,21 +267,16 @@ static int raw_enable_allfilters(struct net *net, struct net_device *dev, return err; } -static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *ptr) +static void raw_notify(struct raw_sock *ro, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (ro->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -305,7 +304,28 @@ static int raw_notifier(struct notifier_block *nb, sk->sk_error_report(sk); break; } +} + +static int raw_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + spin_lock(&raw_notifier_lock); + list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { + spin_unlock(&raw_notifier_lock); + raw_notify(raw_busy_notifier, msg, dev); + spin_lock(&raw_notifier_lock); + } + raw_busy_notifier = NULL; + spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } @@ -334,9 +354,9 @@ static int raw_init(struct sock *sk) return -ENOMEM; /* set notifier */ - ro->notifier.notifier_call = raw_notifier; - - register_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + list_add_tail(&ro->notifier, &raw_notifier_list); + spin_unlock(&raw_notifier_lock); return 0; } @@ -351,7 +371,14 @@ static int raw_release(struct socket *sock) ro = raw_sk(sk); - unregister_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + while (raw_busy_notifier == ro) { + spin_unlock(&raw_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&raw_notifier_lock); + } + list_del(&ro->notifier); + spin_unlock(&raw_notifier_lock); lock_sock(sk); @@ -889,6 +916,10 @@ static const struct can_proto raw_can_proto = { .prot = &raw_proto, }; +static struct notifier_block canraw_notifier = { + .notifier_call = raw_notifier +}; + static __init int raw_module_init(void) { int err; @@ -898,6 +929,8 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) pr_err("can: registration of raw protocol failed\n"); + else + register_netdevice_notifier(&canraw_notifier); return err; } @@ -905,6 +938,7 @@ static __init int raw_module_init(void) static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); + unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); diff --git a/net/compat.c b/net/compat.c index ddd15af3a283..210fc3b4d0d8 100644 --- a/net/compat.c +++ b/net/compat.c @@ -177,7 +177,7 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, if (kcmlen > stackbuf_size) kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL); if (kcmsg == NULL) - return -ENOBUFS; + return -ENOMEM; /* Now copy them over neatly. */ memset(kcmsg, 0, kcmlen); diff --git a/net/core/dev.c b/net/core/dev.c index 222b1d322c96..ef8cf7619baf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3853,7 +3853,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (q->flags & TCQ_F_NOLOCK) { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); + if (likely(!netif_xmit_frozen_or_stopped(txq))) + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -5025,25 +5026,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); + rcu_read_lock(); + while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; - if (!(q->flags & TCQ_F_NOLOCK)) { - root_lock = qdisc_lock(q); - spin_lock(root_lock); - } /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); + + if (!(q->flags & TCQ_F_NOLOCK)) { + root_lock = qdisc_lock(q); + spin_lock(root_lock); + } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, + &q->state))) { + /* There is a synchronize_net() between + * STATE_DEACTIVATED flag being set and + * qdisc_reset()/some_qdisc_is_busy() in + * dev_deactivate(), so we can safely bail out + * early here to avoid data race between + * qdisc_deactivate() and some_qdisc_is_busy() + * for lockless qdisc. + */ + clear_bit(__QDISC_STATE_SCHED, &q->state); + continue; + } + clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } + + rcu_read_unlock(); } xfrm_dev_backlog(sd); diff --git a/net/core/devlink.c b/net/core/devlink.c index 4eb969518ee0..051432ea4f69 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -705,7 +705,6 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->phys.port_number)) return -EMSGSIZE; @@ -8631,7 +8630,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: if (!attrs->split) n = snprintf(name, len, "p%u", attrs->phys.port_number); else @@ -8679,6 +8677,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + return -EOPNOTSUPP; } if (n >= len) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index cd80ffed6d26..a9f937975080 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -1168,7 +1168,7 @@ static void notify_rule_change(int event, struct fib_rule *rule, { struct net *net; struct sk_buff *skb; - int err = -ENOBUFS; + int err = -ENOMEM; net = ops->fro_net; skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); diff --git a/net/core/filter.c b/net/core/filter.c index cae56d08a670..65ab4e21c087 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3784,6 +3784,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); + skb_reset_mac_len(skb); } return ret; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 98f20efbfadf..bf774575ad71 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -238,6 +238,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 43b6ac4c4439..9b5a767eddd5 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -641,6 +641,18 @@ void __put_net(struct net *net) } EXPORT_SYMBOL_GPL(__put_net); +/** + * get_net_ns - increment the refcount of the network namespace + * @ns: common namespace (net) + * + * Returns the net's common namespace. + */ +struct ns_common *get_net_ns(struct ns_common *ns) +{ + return &get_net(container_of(ns, struct net, ns))->ns; +} +EXPORT_SYMBOL_GPL(get_net_ns); + struct net *get_net_ns_by_fd(int fd) { struct file *file; @@ -660,14 +672,8 @@ struct net *get_net_ns_by_fd(int fd) fput(file); return net; } - -#else -struct net *get_net_ns_by_fd(int fd) -{ - return ERR_PTR(-EINVAL); -} -#endif EXPORT_SYMBOL_GPL(get_net_ns_by_fd); +#endif struct net *get_net_ns_by_pid(pid_t pid) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 714d5fa38546..ec931b080156 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4842,6 +4842,10 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout; + /* Notification info is only filled for bridge ports, not the bridge + * device itself. Therefore, a zero notification length is valid and + * should not result in an error. + */ if (!skb->len) goto errout; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ad22870298c..bbc3b4b62032 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1253,6 +1253,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; + bool is_zerocopy; u32 lo, hi; u16 len; @@ -1267,6 +1268,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; + is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); @@ -1274,7 +1276,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; - if (!uarg->zerocopy) + if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; diff --git a/net/core/sock.c b/net/core/sock.c index c761c4a0b66b..946888afef88 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -815,10 +815,18 @@ void sock_set_rcvbuf(struct sock *sk, int val) } EXPORT_SYMBOL(sock_set_rcvbuf); +static void __sock_set_mark(struct sock *sk, u32 val) +{ + if (val != sk->sk_mark) { + sk->sk_mark = val; + sk_dst_reset(sk); + } +} + void sock_set_mark(struct sock *sk, u32 val) { lock_sock(sk); - sk->sk_mark = val; + __sock_set_mark(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_mark); @@ -1126,10 +1134,10 @@ set_sndbuf: case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; - } else if (val != sk->sk_mark) { - sk->sk_mark = val; - sk_dst_reset(sk); + break; } + + __sock_set_mark(sk, val); break; case SO_RXQ_OVFL: @@ -2132,10 +2140,10 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (can_skb_orphan_partial(skb)) - skb_set_owner_sk_safe(skb, skb->sk); - else - skb_orphan(skb); + if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) + return; + + skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); diff --git a/net/dsa/master.c b/net/dsa/master.c index 052a977914a6..63adbc21a735 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -147,8 +147,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, struct dsa_switch *ds = cpu_dp->ds; int port = cpu_dp->index; int len = ETH_GSTRING_LEN; - int mcount = 0, count; - unsigned int i; + int mcount = 0, count, i; uint8_t pfx[4]; uint8_t *ndata; @@ -178,6 +177,8 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, */ ds->ops->get_strings(ds, port, stringset, ndata); count = ds->ops->get_sset_count(ds, port, stringset); + if (count < 0) + return; for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 8c0f3c6ab365..d4756b920108 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -776,13 +776,15 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { - int count; + int count = 0; - count = 4; - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, dp->index, sset); + if (ds->ops->get_sset_count) { + count = ds->ops->get_sset_count(ds, dp->index, sset); + if (count < 0) + return count; + } - return count; + return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 008c1ec6e20c..122ad5833fb1 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -64,7 +64,7 @@ #define DSA_8021Q_SUBVLAN_HI_SHIFT 9 #define DSA_8021Q_SUBVLAN_HI_MASK GENMASK(9, 9) #define DSA_8021Q_SUBVLAN_LO_SHIFT 4 -#define DSA_8021Q_SUBVLAN_LO_MASK GENMASK(4, 3) +#define DSA_8021Q_SUBVLAN_LO_MASK GENMASK(5, 4) #define DSA_8021Q_SUBVLAN_HI(x) (((x) & GENMASK(2, 2)) >> 2) #define DSA_8021Q_SUBVLAN_LO(x) ((x) & GENMASK(1, 0)) #define DSA_8021Q_SUBVLAN(x) \ diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 2a6733a6449a..5d38e90895ac 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -95,7 +95,7 @@ static int get_module_eeprom_by_page(struct net_device *dev, if (dev->sfp_bus) return sfp_get_module_eeprom_by_page(dev->sfp_bus, page_data, extack); - if (ops->get_module_info) + if (ops->get_module_eeprom_by_page) return ops->get_module_eeprom_by_page(dev, page_data, extack); return -EOPNOTSUPP; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 3fa7a394eabf..baa5d10043cb 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1421,7 +1421,7 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, if (eeprom.offset + eeprom.len > total_len) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1486,7 +1486,7 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1765,7 +1765,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) return -EFAULT; test.len = test_len; - data = kmalloc_array(test_len, sizeof(u64), GFP_USER); + data = kcalloc(test_len, sizeof(u64), GFP_USER); if (!data) return -ENOMEM; @@ -2293,7 +2293,7 @@ static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; ret = ops->get_tunable(dev, &tuna, data); @@ -2485,7 +2485,7 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; if (phy_drv_tunable) { diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c index b7642dc96d50..ec07f5765e03 100644 --- a/net/ethtool/stats.c +++ b/net/ethtool/stats.c @@ -119,7 +119,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, */ memset(&data->phy_stats, 0xff, sizeof(data->phy_stats)); memset(&data->mac_stats, 0xff, sizeof(data->mac_stats)); - memset(&data->ctrl_stats, 0xff, sizeof(data->mac_stats)); + memset(&data->ctrl_stats, 0xff, sizeof(data->ctrl_stats)); memset(&data->rmon_stats, 0xff, sizeof(data->rmon_stats)); if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index b3029fff715d..2d51b7ab4dc5 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -353,6 +353,8 @@ static int strset_reply_size(const struct ethnl_req_info *req_base, int len = 0; int ret; + len += nla_total_size(0); /* ETHTOOL_A_STRSET_STRINGSETS */ + for (i = 0; i < ETH_SS_COUNT; i++) { const struct strset_info *set_info = &data->sets[i]; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index bfcdc75fc01e..26c32407f029 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -218,6 +218,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); hsr_forward_skb(skb, master); } else { atomic_long_inc(&dev->tx_dropped); @@ -259,6 +260,7 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master) goto out; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 6852e9bccf5b..ceb8afb2a62f 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -474,8 +474,8 @@ static void handle_std_frame(struct sk_buff *skb, } } -void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame) +int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) { struct hsr_port *port = frame->port_rcv; struct hsr_priv *hsr = port->hsr; @@ -483,20 +483,26 @@ void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, /* HSRv0 supervisory frames double as a tag so treat them as tagged. */ if ((!hsr->prot_version && proto == htons(ETH_P_PRP)) || proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return -EINVAL; + /* HSR tagged frame :- Data or Supervision */ frame->skb_std = NULL; frame->skb_prp = NULL; frame->skb_hsr = skb; frame->sequence_nr = hsr_get_skb_sequence_nr(skb); - return; + return 0; } /* Standard frame or PRP from master port */ handle_std_frame(skb, frame); + + return 0; } -void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame) +int prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) { /* Supervision frame */ struct prp_rct *rct = skb_get_PRP_rct(skb); @@ -507,9 +513,11 @@ void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, frame->skb_std = NULL; frame->skb_prp = skb; frame->sequence_nr = prp_get_skb_sequence_nr(rct); - return; + return 0; } handle_std_frame(skb, frame); + + return 0; } static int fill_frame_info(struct hsr_frame_info *frame, @@ -519,9 +527,10 @@ static int fill_frame_info(struct hsr_frame_info *frame, struct hsr_vlan_ethhdr *vlan_hdr; struct ethhdr *ethhdr; __be16 proto; + int ret; - /* Check if skb contains hsr_ethhdr */ - if (skb->mac_len < sizeof(struct hsr_ethhdr)) + /* Check if skb contains ethhdr */ + if (skb->mac_len < sizeof(struct ethhdr)) return -EINVAL; memset(frame, 0, sizeof(*frame)); @@ -548,7 +557,10 @@ static int fill_frame_info(struct hsr_frame_info *frame, frame->is_from_san = false; frame->port_rcv = port; - hsr->proto_ops->fill_frame_info(proto, skb, frame); + ret = hsr->proto_ops->fill_frame_info(proto, skb, frame); + if (ret) + return ret; + check_local_dest(port->hsr, skb, frame); return 0; diff --git a/net/hsr/hsr_forward.h b/net/hsr/hsr_forward.h index b6acaafa83fc..206636750b30 100644 --- a/net/hsr/hsr_forward.h +++ b/net/hsr/hsr_forward.h @@ -24,8 +24,8 @@ struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port); bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); -void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); -void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); +int prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); +int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); #endif /* __HSR_FORWARD_H */ diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 8f264672b70b..53d1f7a82463 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -186,8 +186,8 @@ struct hsr_proto_ops { struct hsr_port *port); struct sk_buff * (*create_tagged_frame)(struct hsr_frame_info *frame, struct hsr_port *port); - void (*fill_frame_info)(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); + int (*fill_frame_info)(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); bool (*invalid_dan_ingress_frame)(__be16 protocol); void (*update_san_info)(struct hsr_node *node, bool is_sup); }; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index c5227d42faf5..b70e6bbf6021 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -60,12 +60,11 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) goto finish_pass; skb_push(skb, ETH_HLEN); - - if (skb_mac_header(skb) != skb->data) { - WARN_ONCE(1, "%s:%d: Malformed frame at source port %s)\n", - __func__, __LINE__, port->dev->name); - goto finish_consume; - } + skb_reset_mac_header(skb); + if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || + protocol == htons(ETH_P_HSR)) + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + skb_reset_mac_len(skb); hsr_forward_skb(skb, port); diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 0c1b0770c59e..29bf97640166 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -680,8 +680,10 @@ int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info) nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) || nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, be32_to_cpu(params.frame_counter)) || - ieee802154_llsec_fill_key_id(msg, ¶ms.out_key)) + ieee802154_llsec_fill_key_id(msg, ¶ms.out_key)) { + rc = -ENOBUFS; goto out_free; + } dev_put(dev); @@ -1184,7 +1186,7 @@ static int llsec_iter_devkeys(struct llsec_dump_data *data) { struct ieee802154_llsec_device *dpos; struct ieee802154_llsec_device_key *kpos; - int rc = 0, idx = 0, idx2; + int idx = 0, idx2; list_for_each_entry(dpos, &data->table->devices, list) { if (idx++ < data->s_idx) @@ -1200,7 +1202,7 @@ static int llsec_iter_devkeys(struct llsec_dump_data *data) data->nlmsg_seq, dpos->hwaddr, kpos, data->dev)) { - return rc = -EMSGSIZE; + return -EMSGSIZE; } data->s_idx2++; @@ -1209,7 +1211,7 @@ static int llsec_iter_devkeys(struct llsec_dump_data *data) data->s_idx++; } - return rc; + return 0; } int ieee802154_llsec_dump_devkeys(struct sk_buff *skb, diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 2cdc7e63fe17..88215b5c93aa 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -241,8 +241,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info) } if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || - nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name)) + nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name)) { + rc = -EMSGSIZE; goto nla_put_failure; + } dev_put(dev); wpan_phy_put(phy); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 05f6bd89a7dd..0cf2374c143b 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -1298,19 +1298,20 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla, if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla, nl802154_dev_addr_policy, NULL)) return -EINVAL; - if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || - !attrs[NL802154_DEV_ADDR_ATTR_MODE] || - !(attrs[NL802154_DEV_ADDR_ATTR_SHORT] || - attrs[NL802154_DEV_ADDR_ATTR_EXTENDED])) + if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || !attrs[NL802154_DEV_ADDR_ATTR_MODE]) return -EINVAL; addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]); addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]); switch (addr->mode) { case NL802154_DEV_ADDR_SHORT: + if (!attrs[NL802154_DEV_ADDR_ATTR_SHORT]) + return -EINVAL; addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]); break; case NL802154_DEV_ADDR_EXTENDED: + if (!attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]) + return -EINVAL; addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]); break; default: diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f17870ee558b..2f94d221c00e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -575,7 +575,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, return err; } - if (!inet_sk(sk)->inet_num && inet_autobind(sk)) + if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->connect(sk, uaddr, addr_len); } @@ -803,7 +803,7 @@ int inet_send_prepare(struct sock *sk) sock_rps_record_flow(sk); /* We may need to bind the socket. */ - if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind && + if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind && inet_autobind(sk)) return -EAGAIN; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index dff4f0eb96b0..9e41eff4a685 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -185,6 +185,7 @@ BTF_ID(func, tcp_reno_cong_avoid) BTF_ID(func, tcp_reno_undo_cwnd) BTF_ID(func, tcp_slow_start) BTF_ID(func, tcp_cong_avoid_ai) +#ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE #if IS_BUILTIN(CONFIG_TCP_CONG_CUBIC) BTF_ID(func, cubictcp_init) @@ -213,6 +214,7 @@ BTF_ID(func, bbr_min_tso_segs) BTF_ID(func, bbr_set_state) #endif #endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_X86 */ BTF_SET_END(bpf_tcp_ca_kfunc_ids) static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index bfaf327e9d12..e0480c6cebaa 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -472,6 +472,7 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) kfree(doi_def->map.std->lvl.local); kfree(doi_def->map.std->cat.cipso); kfree(doi_def->map.std->cat.local); + kfree(doi_def->map.std); break; } kfree(doi_def); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2e35f68da40a..1c6429c353a9 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1989,7 +1989,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 7b6931a4d775..752e392083e6 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -759,6 +759,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); + /* if we don't have a source address at this point, fall back to the + * dummy address instead of sending out a packet with a source address + * of 0.0.0.0 + */ + if (!fl4.saddr) + fl4.saddr = htonl(INADDR_DUMMY); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7b272bbed2b4..6b3c558a4f23 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1801,6 +1801,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; + ip_mc_clear_src(i); ip_ma_put(i); } } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index bc2f6ca97152..816d8aad5a68 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -886,7 +886,7 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d /* - * Copy BOOTP-supplied string if not already set. + * Copy BOOTP-supplied string */ static int __init ic_bootp_string(char *dest, char *src, int len, int max) { @@ -935,12 +935,15 @@ static void __init ic_do_bootp_ext(u8 *ext) } break; case 12: /* Host name */ - ic_bootp_string(utsname()->nodename, ext+1, *ext, - __NEW_UTS_LEN); - ic_host_name_set = 1; + if (!ic_host_name_set) { + ic_bootp_string(utsname()->nodename, ext+1, *ext, + __NEW_UTS_LEN); + ic_host_name_set = 1; + } break; case 15: /* Domain name (DNS) */ - ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); + if (!ic_domain[0]) + ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); break; case 17: /* Root path */ if (!root_server_path[0]) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 1c9f71a37258..95a718397fd1 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -954,6 +954,7 @@ bool ping_rcv(struct sk_buff *skb) struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + bool rc = false; /* We assume the packet has already been checked by icmp_rcv */ @@ -968,14 +969,15 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); - if (skb2) - ping_queue_rcv_skb(sk, skb2); + if (skb2 && !ping_queue_rcv_skb(sk, skb2)) + rc = true; sock_put(sk); - return true; } - pr_debug("no socket, dropping\n"); - return false; + if (!rc) + pr_debug("no socket, dropping\n"); + + return rc; } EXPORT_SYMBOL_GPL(ping_rcv); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f6787c55f6ab..6a36ac98476f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2056,6 +2056,19 @@ martian_source: return err; } +/* get device for dst_alloc with local routes */ +static struct net_device *ip_rt_get_dev(struct net *net, + const struct fib_result *res) +{ + struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; + struct net_device *dev = NULL; + + if (nhc) + dev = l3mdev_master_dev_rcu(nhc->nhc_dev); + + return dev ? : net->loopback_dev; +} + /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet @@ -2212,7 +2225,7 @@ local_input: } } - rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, + rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, IN_DEV_ORCONF(in_dev, NOPOLICY), false); if (!rth) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 15f5504adf5b..1307ad0d3b9e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2607,6 +2607,9 @@ void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_branch_unlikely(&udp_encap_needed_key)) { @@ -2857,10 +2860,17 @@ int udp_abort(struct sock *sk, int err) { lock_sock(sk); + /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing + * with close() + */ + if (sock_flag(sk, SOCK_DEAD)) + goto out; + sk->sk_err = err; sk->sk_error_report(sk); __udp_disconnect(sk, 0); +out: release_sock(sk); return 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b0ef65eb9bd2..701eb82acd1c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5827,7 +5827,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL; if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]), diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 0d59efb6b49e..d36ef9d25e73 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1745,10 +1745,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) IPV6_TLV_PADN, 0 }; /* we assume size > sizeof(ra) here */ - /* limit our allocations to order-0 page */ - size = min_t(int, size, SKB_MAX_ORDER(0, 0)); skb = sock_alloc_send_skb(sk, size, 1, &err); - if (!skb) return NULL; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index e204163c7036..92f3235fa287 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -135,6 +135,17 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, } EXPORT_SYMBOL_GPL(nft_fib6_eval_type); +static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph) +{ + if (likely(next != IPPROTO_ICMPV6)) + return false; + + if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY) + return false; + + return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL; +} + void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -163,10 +174,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph); - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && - nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv, nft_in(pkt)); - return; + if (nft_hook(pkt) == NF_INET_PRE_ROUTING || + nft_hook(pkt) == NF_INET_INGRESS) { + if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) || + nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) { + nft_fib_store_result(dest, priv, nft_in(pkt)); + return; + } } *dest = 0; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 47a0dc46cbdb..28e44782c94d 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -343,7 +343,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - if (!(fhdr->frag_off & htons(0xFFF9))) { + if (!(fhdr->frag_off & htons(IP6_OFFSET | IP6_MF))) { /* It is not a fragmented frame */ skb->transport_header += sizeof(struct frag_hdr); __IP6_INC_STATS(net, @@ -351,6 +351,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = ntohs(hdr->payload_len) + + sizeof(struct ipv6hdr); return 1; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a22822bdbf39..d417e514bd52 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3673,11 +3673,11 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (nh) { if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); - goto out; + goto out_free; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); - goto out; + goto out_free; } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); @@ -3714,6 +3714,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, out: fib6_info_release(rt); return ERR_PTR(err); +out_free: + ip_fib_metrics_put(rt->fib6_metrics); + kfree(rt); + return ERR_PTR(err); } int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index aa98294a3ad3..f7c8110ece5f 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -271,6 +271,9 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, if (ipip6_tunnel_create(dev) < 0) goto failed_free; + if (!parms->name[0]) + strcpy(parms->name, dev->name); + return nt; failed_free: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 199b080d418a..3fcd86f4dfdc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1598,6 +1598,9 @@ void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 9245c0421bda..fc34ae2b604c 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -4,7 +4,7 @@ * * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 - 2019 Intel Corporation + * Copyright (C) 2018 - 2019, 2021 Intel Corporation */ #include <linux/debugfs.h> @@ -387,10 +387,17 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct ieee80211_local *local = file->private_data; + int ret; rtnl_lock(); + wiphy_lock(local->hw.wiphy); __ieee80211_suspend(&local->hw, NULL); - __ieee80211_resume(&local->hw); + ret = __ieee80211_resume(&local->hw); + wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); return count; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8fcbaa1eedf3..648696b49f89 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -50,12 +50,6 @@ struct ieee80211_local; #define IEEE80211_ENCRYPT_HEADROOM 8 #define IEEE80211_ENCRYPT_TAILROOM 18 -/* IEEE 802.11 (Ch. 9.5 Defragmentation) requires support for concurrent - * reception of at least three fragmented frames. This limit can be increased - * by changing this define, at the cost of slower frame reassembly and - * increased memory use (about 2 kB of RAM per entry). */ -#define IEEE80211_FRAGMENT_MAX 4 - /* power level hasn't been configured (or set to automatic) */ #define IEEE80211_UNSET_POWER_LEVEL INT_MIN @@ -88,18 +82,6 @@ extern const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS]; #define IEEE80211_MAX_NAN_INSTANCE_ID 255 -struct ieee80211_fragment_entry { - struct sk_buff_head skb_list; - unsigned long first_frag_time; - u16 seq; - u16 extra_len; - u16 last_frag; - u8 rx_queue; - bool check_sequential_pn; /* needed for CCMP/GCMP */ - u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ -}; - - struct ieee80211_bss { u32 device_ts_beacon, device_ts_presp; @@ -241,8 +223,15 @@ struct ieee80211_rx_data { */ int security_idx; - u32 tkip_iv32; - u16 tkip_iv16; + union { + struct { + u32 iv32; + u16 iv16; + } tkip; + struct { + u8 pn[IEEE80211_CCMP_PN_LEN]; + } ccm_gcm; + }; }; struct ieee80211_csa_settings { @@ -902,9 +891,7 @@ struct ieee80211_sub_if_data { char name[IFNAMSIZ]; - /* Fragment table for host-based reassembly */ - struct ieee80211_fragment_entry fragments[IEEE80211_FRAGMENT_MAX]; - unsigned int fragment_next; + struct ieee80211_fragment_cache frags; /* TID bitmap for NoAck policy */ u16 noack_map; @@ -1455,7 +1442,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (WARN_ON_ONCE(!chanctx_conf)) { + if (!chanctx_conf) { rcu_read_unlock(); return NULL; } @@ -2320,4 +2307,7 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, #define debug_noinline #endif +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache); +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache); + #endif /* IEEE80211_I_H */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7032a2b59249..137fa4c50e07 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -8,7 +8,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -476,14 +476,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do GFP_KERNEL); } - /* APs need special treatment */ if (sdata->vif.type == NL80211_IFTYPE_AP) { - struct ieee80211_sub_if_data *vlan, *tmpsdata; - - /* down all dependent devices, that is VLANs */ - list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, - u.vlan.list) - dev_close(vlan->dev); WARN_ON(!list_empty(&sdata->u.ap.vlans)); } else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* remove all packets in parent bc_buf pointing to this dev */ @@ -641,6 +634,15 @@ static int ieee80211_stop(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + /* close all dependent VLAN interfaces before locking wiphy */ + if (sdata->vif.type == NL80211_IFTYPE_AP) { + struct ieee80211_sub_if_data *vlan, *tmpsdata; + + list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, + u.vlan.list) + dev_close(vlan->dev); + } + wiphy_lock(sdata->local->hw.wiphy); ieee80211_do_stop(sdata, true); wiphy_unlock(sdata->local->hw.wiphy); @@ -677,16 +679,12 @@ static void ieee80211_set_multicast_list(struct net_device *dev) */ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) { - int i; - /* free extra data */ ieee80211_free_keys(sdata, false); ieee80211_debugfs_remove_netdev(sdata); - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - __skb_queue_purge(&sdata->fragments[i].skb_list); - sdata->fragment_next = 0; + ieee80211_destroy_frag_cache(&sdata->frags); if (ieee80211_vif_is_mesh(&sdata->vif)) ieee80211_mesh_teardown_sdata(sdata); @@ -1595,6 +1593,9 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: + if (!list_empty(&sdata->u.ap.vlans)) + return -EBUSY; + break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_OCB: @@ -1930,8 +1931,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->wdev.wiphy = local->hw.wiphy; sdata->local = local; - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - skb_queue_head_init(&sdata->fragments[i].skb_list); + ieee80211_init_frag_cache(&sdata->frags); INIT_LIST_HEAD(&sdata->key_list); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 56c068cb49c4..f695fc80088b 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -799,6 +799,7 @@ int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { + static atomic_t key_color = ATOMIC_INIT(0); struct ieee80211_key *old_key; int idx = key->conf.keyidx; bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; @@ -850,6 +851,12 @@ int ieee80211_key_link(struct ieee80211_key *key, key->sdata = sdata; key->sta = sta; + /* + * Assign a unique ID to every key so we can easily prevent mixed + * key and fragment cache attacks. + */ + key->color = atomic_inc_return(&key_color); + increment_tailroom_need_count(sdata); ret = ieee80211_key_replace(sdata, sta, pairwise, old_key, key); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 7ad72e9b4991..1e326c89d721 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -128,6 +128,8 @@ struct ieee80211_key { } debugfs; #endif + unsigned int color; + /* * key config, must be last because it contains key * material as variable length member diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 62145e5f9628..f33a3acd7f96 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -252,6 +252,7 @@ static void ieee80211_restart_work(struct work_struct *work) struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); struct ieee80211_sub_if_data *sdata; + int ret; /* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -301,8 +302,12 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for all packet processing to be done */ synchronize_net(); - ieee80211_reconfig(local); + ret = ieee80211_reconfig(local); wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2480bd0577bb..3f2aad2e7436 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4062,10 +4062,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (elems.mbssid_config_ie) bss_conf->profile_periodicity = elems.mbssid_config_ie->profile_periodicity; + else + bss_conf->profile_periodicity = 0; if (elems.ext_capab_len >= 11 && (elems.ext_capab[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) bss_conf->ema_ap = true; + else + bss_conf->ema_ap = false; /* continue assoc process */ ifmgd->assoc_data->timeout = jiffies; @@ -5802,12 +5806,16 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 3) sdata->vif.bss_conf.profile_periodicity = elem->data[2]; + else + sdata->vif.bss_conf.profile_periodicity = 0; elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 11 && (elem->data[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) sdata->vif.bss_conf.ema_ap = true; + else + sdata->vif.bss_conf.ema_ap = false; } else { assoc_data->timeout = jiffies; assoc_data->timeout_started = true; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 6487b05da6fa..a6f3fb4a9197 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1514,7 +1514,7 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) return; - if (time_is_before_jiffies(mi->sample_time)) + if (time_is_after_jiffies(mi->sample_time)) return; mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 62047e93e217..af0ef456eb0f 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/jiffies.h> @@ -2123,19 +2123,34 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) return result; } +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + skb_queue_head_init(&cache->entries[i].skb_list); +} + +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + __skb_queue_purge(&cache->entries[i].skb_list); +} + static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_add(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct sk_buff **skb) { struct ieee80211_fragment_entry *entry; - entry = &sdata->fragments[sdata->fragment_next++]; - if (sdata->fragment_next >= IEEE80211_FRAGMENT_MAX) - sdata->fragment_next = 0; + entry = &cache->entries[cache->next++]; + if (cache->next >= IEEE80211_FRAGMENT_MAX) + cache->next = 0; - if (!skb_queue_empty(&entry->skb_list)) - __skb_queue_purge(&entry->skb_list); + __skb_queue_purge(&entry->skb_list); __skb_queue_tail(&entry->skb_list, *skb); /* no need for locking */ *skb = NULL; @@ -2150,14 +2165,14 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, } static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_find(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct ieee80211_hdr *hdr) { struct ieee80211_fragment_entry *entry; int i, idx; - idx = sdata->fragment_next; + idx = cache->next; for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) { struct ieee80211_hdr *f_hdr; struct sk_buff *f_skb; @@ -2166,7 +2181,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, if (idx < 0) idx = IEEE80211_FRAGMENT_MAX - 1; - entry = &sdata->fragments[idx]; + entry = &cache->entries[idx]; if (skb_queue_empty(&entry->skb_list) || entry->seq != seq || entry->rx_queue != rx_queue || entry->last_frag + 1 != frag) @@ -2194,15 +2209,27 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, return NULL; } +static bool requires_sequential_pn(struct ieee80211_rx_data *rx, __le16 fc) +{ + return rx->key && + (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && + ieee80211_has_protected(fc); +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) { + struct ieee80211_fragment_cache *cache = &rx->sdata->frags; struct ieee80211_hdr *hdr; u16 sc; __le16 fc; unsigned int frag, seq; struct ieee80211_fragment_entry *entry; struct sk_buff *skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; @@ -2213,14 +2240,15 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (is_multicast_ether_addr(hdr->addr1)) { - I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount); - goto out_no_led; - } + if (rx->sta) + cache = &rx->sta->frags; if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) goto out; + if (is_multicast_ether_addr(hdr->addr1)) + return RX_DROP_MONITOR; + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -2236,20 +2264,17 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (frag == 0) { /* This is the first fragment of a new frame. */ - entry = ieee80211_reassemble_add(rx->sdata, frag, seq, + entry = ieee80211_reassemble_add(cache, frag, seq, rx->seqno_idx, &(rx->skb)); - if (rx->key && - (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && - ieee80211_has_protected(fc)) { + if (requires_sequential_pn(rx, fc)) { int queue = rx->security_idx; /* Store CCMP/GCMP PN so that we can verify that the * next fragment has a sequential PN value. */ entry->check_sequential_pn = true; + entry->is_protected = true; + entry->key_color = rx->key->color; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); @@ -2261,6 +2286,11 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sizeof(rx->key->u.gcmp.rx_pn[queue])); BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != IEEE80211_GCMP_PN_LEN); + } else if (rx->key && + (ieee80211_has_protected(fc) || + (status->flag & RX_FLAG_DECRYPTED))) { + entry->is_protected = true; + entry->key_color = rx->key->color; } return RX_QUEUED; } @@ -2268,7 +2298,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) /* This is a fragment for a frame that should already be pending in * fragment cache. Add this fragment to the end of the pending entry. */ - entry = ieee80211_reassemble_find(rx->sdata, frag, seq, + entry = ieee80211_reassemble_find(cache, frag, seq, rx->seqno_idx, hdr); if (!entry) { I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag); @@ -2283,25 +2313,39 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; - int queue; - if (!rx->key || - (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) + if (!requires_sequential_pn(rx, fc)) + return RX_DROP_UNUSABLE; + + /* Prevent mixed key and fragment cache attacks */ + if (entry->key_color != rx->key->color) return RX_DROP_UNUSABLE; + memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { pn[i]++; if (pn[i]) break; } - queue = rx->security_idx; - rpn = rx->key->u.ccmp.rx_pn[queue]; + + rpn = rx->ccm_gcm.pn; if (memcmp(pn, rpn, IEEE80211_CCMP_PN_LEN)) return RX_DROP_UNUSABLE; memcpy(entry->last_pn, pn, IEEE80211_CCMP_PN_LEN); + } else if (entry->is_protected && + (!rx->key || + (!ieee80211_has_protected(fc) && + !(status->flag & RX_FLAG_DECRYPTED)) || + rx->key->color != entry->key_color)) { + /* Drop this as a mixed key or fragment cache attack, even + * if for TKIP Michael MIC should protect us, and WEP is a + * lost cause anyway. + */ + return RX_DROP_UNUSABLE; + } else if (entry->is_protected && rx->key && + entry->key_color != rx->key->color && + (status->flag & RX_FLAG_DECRYPTED)) { + return RX_DROP_UNUSABLE; } skb_pull(rx->skb, ieee80211_hdrlen(fc)); @@ -2330,7 +2374,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) out: ieee80211_led_rx(rx->local); - out_no_led: if (rx->sta) rx->sta->rx_stats.packets++; return RX_CONTINUE; @@ -2494,13 +2537,13 @@ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx, __le16 fc) struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; /* - * Allow EAPOL frames to us/the PAE group address regardless - * of whether the frame was encrypted or not. + * Allow EAPOL frames to us/the PAE group address regardless of + * whether the frame was encrypted or not, and always disallow + * all other destination addresses for them. */ - if (ehdr->h_proto == rx->sdata->control_port_protocol && - (ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || - ether_addr_equal(ehdr->h_dest, pae_group_addr))) - return true; + if (unlikely(ehdr->h_proto == rx->sdata->control_port_protocol)) + return ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || + ether_addr_equal(ehdr->h_dest, pae_group_addr); if (ieee80211_802_1x_port_control(rx) || ieee80211_drop_unencrypted(rx, fc)) @@ -2525,8 +2568,28 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { + struct ethhdr *ehdr = (void *)skb_mac_header(skb); + memset(skb->cb, 0, sizeof(skb->cb)); + /* + * 802.1X over 802.11 requires that the authenticator address + * be used for EAPOL frames. However, 802.1X allows the use of + * the PAE group address instead. If the interface is part of + * a bridge and we pass the frame with the PAE group address, + * then the bridge will forward it to the network (even if the + * client was not associated yet), which isn't supposed to + * happen. + * To avoid that, rewrite the destination address to our own + * address, so that the authenticator (e.g. hostapd) will see + * the frame, but bridge won't forward it anywhere else. Note + * that due to earlier filtering, the only other address can + * be the PAE group address. + */ + if (unlikely(skb->protocol == sdata->control_port_protocol && + !ether_addr_equal(ehdr->h_dest, sdata->vif.addr))) + ether_addr_copy(ehdr->h_dest, sdata->vif.addr); + /* deliver to local stack */ if (rx->list) list_add_tail(&skb->list, rx->list); @@ -2566,6 +2629,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) if ((sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && + ehdr->h_proto != rx->sdata->control_port_protocol && (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) { if (is_multicast_ether_addr(ehdr->h_dest) && ieee80211_vif_get_num_mcast_if(sdata) != 0) { @@ -2675,7 +2739,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) if (ieee80211_data_to_8023_exthdr(skb, ðhdr, rx->sdata->vif.addr, rx->sdata->vif.type, - data_offset)) + data_offset, true)) return RX_DROP_UNUSABLE; ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr, @@ -2732,6 +2796,23 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) if (is_multicast_ether_addr(hdr->addr1)) return RX_DROP_UNUSABLE; + if (rx->key) { + /* + * We should not receive A-MSDUs on pre-HT connections, + * and HT connections cannot use old ciphers. Thus drop + * them, as in those cases we couldn't even have SPP + * A-MSDUs or such. + */ + switch (rx->key->conf.cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + case WLAN_CIPHER_SUITE_TKIP: + return RX_DROP_UNUSABLE; + default: + break; + } + } + return __ieee80211_rx_h_amsdu(rx, 0); } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index d4cc9ac2d703..6b50cb5e0e3c 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -251,13 +251,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; + size_t min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); + + if (!ieee80211_is_probe_resp(mgmt->frame_control) && + !ieee80211_is_beacon(mgmt->frame_control) && + !ieee80211_is_s1g_beacon(mgmt->frame_control)) + return; if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { - if (skb->len < 15) - return; - } else if (skb->len < 24 || - (!ieee80211_is_probe_resp(mgmt->frame_control) && - !ieee80211_is_beacon(mgmt->frame_control))) + if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon); + } + + if (skb->len < min_hdr_len) return; sdata1 = rcu_dereference(local->scan_sdata); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index ec6973ee88ef..f2fb69da9b6e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/module.h> @@ -392,6 +392,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, u64_stats_init(&sta->rx_stats.syncp); + ieee80211_init_frag_cache(&sta->frags); + sta->sta_state = IEEE80211_STA_NONE; /* Mark TID as unreserved */ @@ -1102,6 +1104,8 @@ static void __sta_info_destroy_part2(struct sta_info *sta) ieee80211_sta_debugfs_remove(sta); + ieee80211_destroy_frag_cache(&sta->frags); + cleanup_single_sta(sta); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 78b9d0c7cc58..0333072ebd98 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -3,7 +3,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright(c) 2020 Intel Corporation + * Copyright(c) 2020-2021 Intel Corporation */ #ifndef STA_INFO_H @@ -439,6 +439,34 @@ struct ieee80211_sta_rx_stats { }; /* + * IEEE 802.11-2016 (10.6 "Defragmentation") recommends support for "concurrent + * reception of at least one MSDU per access category per associated STA" + * on APs, or "at least one MSDU per access category" on other interface types. + * + * This limit can be increased by changing this define, at the cost of slower + * frame reassembly and increased memory use while fragments are pending. + */ +#define IEEE80211_FRAGMENT_MAX 4 + +struct ieee80211_fragment_entry { + struct sk_buff_head skb_list; + unsigned long first_frag_time; + u16 seq; + u16 extra_len; + u16 last_frag; + u8 rx_queue; + u8 check_sequential_pn:1, /* needed for CCMP/GCMP */ + is_protected:1; + u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ + unsigned int key_color; +}; + +struct ieee80211_fragment_cache { + struct ieee80211_fragment_entry entries[IEEE80211_FRAGMENT_MAX]; + unsigned int next; +}; + +/* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being @@ -531,6 +559,7 @@ struct ieee80211_sta_rx_stats { * @status_stats.last_ack_signal: last ACK signal * @status_stats.ack_signal_filled: last ACK signal validity * @status_stats.avg_ack_signal: average ACK signal + * @frags: fragment cache */ struct sta_info { /* General information, mostly static */ @@ -639,6 +668,8 @@ struct sta_info { struct cfg80211_chan_def tdls_chandef; + struct ieee80211_fragment_cache frags; + /* keep last! */ struct ieee80211_sta sta; }; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0b719f3d2dec..2651498d05e8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2014,6 +2014,26 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, ieee80211_tx(sdata, sta, skb, false); } +static bool ieee80211_validate_radiotap_len(struct sk_buff *skb) +{ + struct ieee80211_radiotap_header *rthdr = + (struct ieee80211_radiotap_header *)skb->data; + + /* check for not even having the fixed radiotap header part */ + if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) + return false; /* too short to be possibly valid */ + + /* is it a header version we can trust to find length from? */ + if (unlikely(rthdr->it_version)) + return false; /* only version 0 is supported */ + + /* does the skb contain enough to deliver on the alleged length? */ + if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) + return false; /* skb too short for claimed rt header extent */ + + return true; +} + bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev) { @@ -2022,8 +2042,6 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[info->band]; int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, NULL); u16 txflags; @@ -2036,17 +2054,8 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, u8 vht_mcs = 0, vht_nss = 0; int i; - /* check for not even having the fixed radiotap header part */ - if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) - return false; /* too short to be possibly valid */ - - /* is it a header version we can trust to find length from? */ - if (unlikely(rthdr->it_version)) - return false; /* only version 0 is supported */ - - /* does the skb contain enough to deliver on the alleged length? */ - if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) - return false; /* skb too short for claimed rt header extent */ + if (!ieee80211_validate_radiotap_len(skb)) + return false; info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_DONTFRAG; @@ -2186,6 +2195,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, return false; if (rate_found) { + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[info->band]; + info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { @@ -2199,7 +2211,7 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, } else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) { ieee80211_rate_set_vht(info->control.rates, vht_mcs, vht_nss); - } else { + } else if (sband) { for (i = 0; i < sband->n_bitrates; i++) { if (rate * 5 != sband->bitrates[i].bitrate) continue; @@ -2236,8 +2248,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_CTL_INJECTED; - /* Sanity-check and process the injection radiotap header */ - if (!ieee80211_parse_tx_radiotap(skb, dev)) + /* Sanity-check the length of the radiotap header */ + if (!ieee80211_validate_radiotap_len(skb)) goto fail; /* we now know there is a radiotap header with a length we can use */ @@ -2351,6 +2363,14 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, ieee80211_select_queue_80211(sdata, skb, hdr); skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority)); + /* + * Process the radiotap header. This will now take into account the + * selected chandef above to accurately set injection rates and + * retransmissions. + */ + if (!ieee80211_parse_tx_radiotap(skb, dev)) + goto fail_rcu; + /* remove the injection radiotap header */ skb_pull(skb, len_rthdr); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 0a0481f5af48..060059ef9668 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -947,7 +947,7 @@ static void ieee80211_parse_extension_element(u32 *crc, switch (elem->data[0]) { case WLAN_EID_EXT_HE_MU_EDCA: - if (len == sizeof(*elems->mu_edca_param_set)) { + if (len >= sizeof(*elems->mu_edca_param_set)) { elems->mu_edca_param_set = data; if (crc) *crc = crc32_be(*crc, (void *)elem, @@ -968,7 +968,7 @@ static void ieee80211_parse_extension_element(u32 *crc, } break; case WLAN_EID_EXT_UORA: - if (len == 1) + if (len >= 1) elems->uora_element = data; break; case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: @@ -976,7 +976,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->max_channel_switch_time = data; break; case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: - if (len == sizeof(*elems->mbssid_config_ie)) + if (len >= sizeof(*elems->mbssid_config_ie)) elems->mbssid_config_ie = data; break; case WLAN_EID_EXT_HE_SPR: @@ -985,7 +985,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->he_spr = data; break; case WLAN_EID_EXT_HE_6GHZ_CAPA: - if (len == sizeof(*elems->he_6ghz_capa)) + if (len >= sizeof(*elems->he_6ghz_capa)) elems->he_6ghz_capa = data; break; } @@ -1074,14 +1074,14 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, switch (id) { case WLAN_EID_LINK_ID: - if (elen + 2 != sizeof(struct ieee80211_tdls_lnkie)) { + if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) { elem_parse_failed = true; break; } elems->lnk_id = (void *)(pos - 2); break; case WLAN_EID_CHAN_SWITCH_TIMING: - if (elen != sizeof(struct ieee80211_ch_switch_timing)) { + if (elen < sizeof(struct ieee80211_ch_switch_timing)) { elem_parse_failed = true; break; } @@ -1244,7 +1244,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->sec_chan_offs = (void *)pos; break; case WLAN_EID_CHAN_SWITCH_PARAM: - if (elen != + if (elen < sizeof(*elems->mesh_chansw_params_ie)) { elem_parse_failed = true; break; @@ -1253,7 +1253,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, break; case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: if (!action || - elen != sizeof(*elems->wide_bw_chansw_ie)) { + elen < sizeof(*elems->wide_bw_chansw_ie)) { elem_parse_failed = true; break; } @@ -1272,7 +1272,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, ie = cfg80211_find_ie(WLAN_EID_WIDE_BW_CHANNEL_SWITCH, pos, elen); if (ie) { - if (ie[1] == sizeof(*elems->wide_bw_chansw_ie)) + if (ie[1] >= sizeof(*elems->wide_bw_chansw_ie)) elems->wide_bw_chansw_ie = (void *)(ie + 2); else @@ -1316,7 +1316,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; case WLAN_EID_ADDBA_EXT: - if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + if (elen < sizeof(struct ieee80211_addba_ext_ie)) { elem_parse_failed = true; break; } @@ -1342,7 +1342,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem, elems); break; case WLAN_EID_S1G_CAPABILITIES: - if (elen == sizeof(*elems->s1g_capab)) + if (elen >= sizeof(*elems->s1g_capab)) elems->s1g_capab = (void *)pos; else elem_parse_failed = true; @@ -2178,8 +2178,6 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) list_for_each_entry(ctx, &local->chanctx_list, list) ctx->driver_present = false; mutex_unlock(&local->chanctx_mtx); - - cfg80211_shutdown_all_interfaces(local->hw.wiphy); } static void ieee80211_assign_chanctx(struct ieee80211_local *local, diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 91bf32af55e9..bca47fad5a16 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -3,6 +3,7 @@ * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen <j@w1.fi> * Copyright (C) 2016-2017 Intel Deutschland GmbH + * Copyright (C) 2020-2021 Intel Corporation */ #include <linux/netdevice.h> @@ -167,8 +168,8 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) update_iv: /* update IV in key information to be able to detect replays */ - rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip_iv32; - rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip_iv16; + rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip.iv32; + rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip.iv16; return RX_CONTINUE; @@ -294,8 +295,8 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, hdr->addr1, hwaccel, rx->security_idx, - &rx->tkip_iv32, - &rx->tkip_iv16); + &rx->tkip.iv32, + &rx->tkip.iv16); if (res != TKIP_DECRYPT_OK) return RX_DROP_UNUSABLE; @@ -553,6 +554,8 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, } memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove CCMP header and MIC */ @@ -781,6 +784,8 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) } memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove GCMP header and MIC */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 99fc21406168..9b263f27ce9b 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -130,7 +130,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); } else { - pr_warn("MP_JOIN bad option size"); mp_opt->mp_join = 0; } break; @@ -357,6 +356,8 @@ void mptcp_get_options(const struct sk_buff *skb, length--; continue; default: + if (length < 2) + return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; @@ -1024,7 +1025,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR); } else { mptcp_pm_add_addr_echoed(msk, &mp_opt.addr); - mptcp_pm_del_add_timer(msk, &mp_opt.addr); + mptcp_pm_del_add_timer(msk, &mp_opt.addr, true); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 6ba040897738..2469e06a3a9d 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -346,18 +346,18 @@ out: struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) + struct mptcp_addr_info *addr, bool check_id) { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); - if (entry) + if (entry && (!check_id || entry->addr.id == addr->id)) entry->retrans_times = ADD_ADDR_RETRANS_MAX; spin_unlock_bh(&msk->pm.lock); - if (entry) + if (entry && (!check_id || entry->addr.id == addr->id)) sk_stop_timer_sync(sk, &entry->add_timer); return entry; @@ -1064,7 +1064,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; - entry = mptcp_pm_del_add_timer(msk, addr); + entry = mptcp_pm_del_add_timer(msk, addr, false); if (entry) { list_del(&entry->list); kfree(entry); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 29a2d690d8d5..632350018fb6 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -280,11 +280,13 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, /* try to fetch required memory from subflow */ if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - if (ssk->sk_forward_alloc < skb->truesize) - goto drop; - __sk_mem_reclaim(ssk, skb->truesize); - if (!sk_rmem_schedule(sk, skb, skb->truesize)) + int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT; + + if (ssk->sk_forward_alloc < amount) goto drop; + + ssk->sk_forward_alloc -= amount; + sk->sk_forward_alloc += amount; } /* the skb map_seq accounts for the skb offset: @@ -668,18 +670,22 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ -static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; if (inet_sk_state_load(sk) == TCP_CLOSE) - return; - - mptcp_data_lock(sk); + return false; __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); + if (unlikely(ssk->sk_err)) { + if (!sock_owned_by_user(sk)) + __mptcp_error_report(sk); + else + set_bit(MPTCP_ERROR_REPORT, &msk->flags); + } /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but @@ -688,7 +694,7 @@ static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); - mptcp_data_unlock(sk); + return moved > 0; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) @@ -696,7 +702,6 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); int sk_rbuf, ssk_rbuf; - bool wake; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing @@ -705,28 +710,22 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (unlikely(subflow->disposable)) return; - /* move_skbs_to_msk below can legitly clear the data_avail flag, - * but we will need later to properly woke the reader, cache its - * value - */ - wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL; - if (wake) - set_bit(MPTCP_DATA_READY, &msk->flags); - ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) sk_rbuf = ssk_rbuf; - /* over limit? can't append more skbs to msk */ + /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) - goto wake; - - move_skbs_to_msk(msk, ssk); + return; -wake: - if (wake) + /* Wake-up the reader only for in-sequence data */ + mptcp_data_lock(sk); + if (move_skbs_to_msk(msk, ssk)) { + set_bit(MPTCP_DATA_READY, &msk->flags); sk->sk_data_ready(sk); + } + mptcp_data_unlock(sk); } static bool mptcp_do_flush_join_list(struct mptcp_sock *msk) @@ -858,7 +857,7 @@ static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) sock_owned_by_me(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->data_avail) + if (READ_ONCE(subflow->data_avail)) return mptcp_subflow_tcp_sock(subflow); } @@ -879,12 +878,18 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq, !mpext->frozen; } +/* we can append data to the given data frag if: + * - there is space available in the backing page_frag + * - the data frag tail matches the current page_frag free offset + * - the data frag end sequence number matches the current write seq + */ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, const struct page_frag *pfrag, const struct mptcp_data_frag *df) { return df && pfrag->page == df->page && pfrag->size - pfrag->offset > 0 && + pfrag->offset == (df->offset + df->data_len) && df->data_seq + df->data_len == msk->write_seq; } @@ -941,6 +946,10 @@ static void __mptcp_update_wmem(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock)); +#endif + if (!msk->wmem_reserved) return; @@ -1079,10 +1088,20 @@ out: static void __mptcp_clean_una_wakeup(struct sock *sk) { +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock)); +#endif __mptcp_clean_una(sk); mptcp_write_space(sk); } +static void mptcp_clean_una_wakeup(struct sock *sk) +{ + mptcp_data_lock(sk); + __mptcp_clean_una_wakeup(sk); + mptcp_data_unlock(sk); +} + static void mptcp_enter_memory_pressure(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1935,6 +1954,9 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); tcp_cleanup_rbuf(ssk, moved); + + if (unlikely(ssk->sk_err)) + __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done); @@ -2293,7 +2315,7 @@ static void __mptcp_retrans(struct sock *sk) struct sock *ssk; int ret; - __mptcp_clean_una_wakeup(sk); + mptcp_clean_una_wakeup(sk); dfrag = mptcp_rtx_head(sk); if (!dfrag) { if (mptcp_data_fin_enabled(msk)) { @@ -2418,13 +2440,12 @@ static int __mptcp_init_sock(struct sock *sk) timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); - tcp_assign_congestion_control(sk); - return 0; } static int mptcp_init_sock(struct sock *sk) { + struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int ret; @@ -2442,6 +2463,16 @@ static int mptcp_init_sock(struct sock *sk) if (ret) return ret; + /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will + * propagate the correct value + */ + tcp_assign_congestion_control(sk); + strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name); + + /* no need to keep a reference to the ops, the name will suffice */ + tcp_cleanup_congestion_control(sk); + icsk->icsk_ca_ops = NULL; + sk_sockets_allocated_inc(sk); sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; @@ -2616,7 +2647,6 @@ static void __mptcp_destroy_sock(struct sock *sk) sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); - tcp_cleanup_congestion_control(sk); sk_refcnt_debug_release(sk); mptcp_dispose_initial_subflow(msk); sock_put(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index edc0128730df..385796f0ef19 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -258,6 +258,7 @@ struct mptcp_sock { } rcvq_space; u32 setsockopt_seq; + char ca_name[TCP_CA_NAME_MAX]; }; #define mptcp_lock_sock(___sk, cb) do { \ @@ -361,7 +362,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) enum mptcp_data_avail { MPTCP_SUBFLOW_NODATA, MPTCP_SUBFLOW_DATA_AVAIL, - MPTCP_SUBFLOW_OOO_DATA }; struct mptcp_delegated_action { @@ -671,7 +671,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr); + struct mptcp_addr_info *addr, bool check_id); struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, struct mptcp_addr_info *addr); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 00d941b66c1e..a79798189599 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -547,7 +547,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t } if (ret == 0) - tcp_set_congestion_control(sk, name, false, cap_net_admin); + strcpy(msk->ca_name, name); release_sock(sk); return ret; @@ -705,7 +705,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG)); if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops) - tcp_set_congestion_control(ssk, inet_csk(sk)->icsk_ca_ops->name, false, true); + tcp_set_congestion_control(ssk, msk->ca_name, false, true); } static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a5ede357cfbc..be1de4084196 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -630,21 +630,20 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, /* if the sk is MP_CAPABLE, we try to fetch the client key */ if (subflow_req->mp_capable) { - if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) { - /* here we can receive and accept an in-window, - * out-of-order pkt, which will not carry the MP_CAPABLE - * opt even on mptcp enabled paths - */ - goto create_msk; - } - + /* we can receive and accept an in-window, out-of-order pkt, + * which may not carry the MP_CAPABLE opt even on mptcp enabled + * paths: always try to extract the peer key, and fallback + * for packets missing it. + * Even OoO DSS packets coming legitly after dropped or + * reordered MPC will cause fallback, but we don't have other + * options. + */ mptcp_get_options(skb, &mp_opt); if (!mp_opt.mp_capable) { fallback = true; goto create_child; } -create_msk: new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req); if (!new_msk) fallback = true; @@ -785,10 +784,10 @@ static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); } -static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) +static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d", - ssn, subflow->map_subflow_seq, subflow->map_data_len); + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + ssn, subflow->map_subflow_seq, subflow->map_data_len); } static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) @@ -813,13 +812,13 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) /* Mapping covers data later in the subflow stream, * currently unsupported. */ - warn_bad_map(subflow, ssn); + dbg_bad_map(subflow, ssn); return false; } if (unlikely(!before(ssn, subflow->map_subflow_seq + subflow->map_data_len))) { /* Mapping does covers past subflow data, invalid */ - warn_bad_map(subflow, ssn + skb->len); + dbg_bad_map(subflow, ssn); return false; } return true; @@ -867,7 +866,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len = mpext->data_len; if (data_len == 0) { - pr_err("Infinite mapping not handled"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); return MAPPING_INVALID; } @@ -1002,7 +1000,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); if (subflow->data_avail) return true; @@ -1013,21 +1011,11 @@ static bool subflow_check_data_avail(struct sock *ssk) status = get_mapping_status(ssk, msk); trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue)); - if (status == MAPPING_INVALID) { - ssk->sk_err = EBADMSG; - goto fatal; - } - if (status == MAPPING_DUMMY) { - __mptcp_do_fallback(msk); - skb = skb_peek(&ssk->sk_receive_queue); - subflow->map_valid = 1; - subflow->map_seq = READ_ONCE(msk->ack_seq); - subflow->map_data_len = skb->len; - subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - - subflow->ssn_offset; - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; - return true; - } + if (unlikely(status == MAPPING_INVALID)) + goto fallback; + + if (unlikely(status == MAPPING_DUMMY)) + goto fallback; if (status != MAPPING_OK) goto no_data; @@ -1040,10 +1028,8 @@ static bool subflow_check_data_avail(struct sock *ssk) * MP_CAPABLE-based mapping */ if (unlikely(!READ_ONCE(msk->can_ack))) { - if (!subflow->mpc_map) { - ssk->sk_err = EBADMSG; - goto fatal; - } + if (!subflow->mpc_map) + goto fallback; WRITE_ONCE(msk->remote_key, subflow->remote_key); WRITE_ONCE(msk->ack_seq, subflow->map_seq); WRITE_ONCE(msk->can_ack, true); @@ -1053,35 +1039,43 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, ack_seq); - if (ack_seq == old_ack) { - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; - break; - } else if (after64(ack_seq, old_ack)) { - subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA; - break; + if (unlikely(before64(ack_seq, old_ack))) { + mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + continue; } - /* only accept in-sequence mapping. Old values are spurious - * retransmission - */ - mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + break; } return true; no_data: subflow_sched_work_if_closed(msk, ssk); return false; -fatal: - /* fatal protocol error, close the socket */ - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - ssk->sk_error_report(ssk); - tcp_set_state(ssk, TCP_CLOSE); - subflow->reset_transient = 0; - subflow->reset_reason = MPTCP_RST_EMPTCP; - tcp_send_active_reset(ssk, GFP_ATOMIC); - subflow->data_avail = 0; - return false; + +fallback: + /* RFC 8684 section 3.7. */ + if (subflow->mp_join || subflow->fully_established) { + /* fatal protocol error, close the socket. + * subflow_error_report() will introduce the appropriate barriers + */ + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + subflow->reset_transient = 0; + subflow->reset_reason = MPTCP_RST_EMPTCP; + tcp_send_active_reset(ssk, GFP_ATOMIC); + WRITE_ONCE(subflow->data_avail, 0); + return false; + } + + __mptcp_do_fallback(msk); + skb = skb_peek(&ssk->sk_receive_queue); + subflow->map_valid = 1; + subflow->map_seq = READ_ONCE(msk->ack_seq); + subflow->map_data_len = skb->len; + subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + return true; } bool mptcp_subflow_data_available(struct sock *sk) @@ -1092,7 +1086,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1120,41 +1114,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = tcp_full_space(sk); } -static void subflow_data_ready(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - u16 state = 1 << inet_sk_state_load(sk); - struct sock *parent = subflow->conn; - struct mptcp_sock *msk; - - msk = mptcp_sk(parent); - if (state & TCPF_LISTEN) { - /* MPJ subflow are removed from accept queue before reaching here, - * avoid stray wakeups - */ - if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) - return; - - set_bit(MPTCP_DATA_READY, &msk->flags); - parent->sk_data_ready(parent); - return; - } - - WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && - !subflow->mp_join && !(state & TCPF_CLOSE)); - - if (mptcp_subflow_data_available(sk)) - mptcp_data_ready(parent, sk); -} - -static void subflow_write_space(struct sock *ssk) -{ - struct sock *sk = mptcp_subflow_ctx(ssk)->conn; - - mptcp_propagate_sndbuf(sk, ssk); - mptcp_write_space(sk); -} - void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1195,6 +1154,43 @@ static void subflow_error_report(struct sock *ssk) mptcp_data_unlock(sk); } +static void subflow_data_ready(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + u16 state = 1 << inet_sk_state_load(sk); + struct sock *parent = subflow->conn; + struct mptcp_sock *msk; + + msk = mptcp_sk(parent); + if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + + set_bit(MPTCP_DATA_READY, &msk->flags); + parent->sk_data_ready(parent); + return; + } + + WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && + !subflow->mp_join && !(state & TCPF_CLOSE)); + + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); +} + +static void subflow_write_space(struct sock *ssk) +{ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); +} + static struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { @@ -1505,6 +1501,8 @@ static void subflow_state_change(struct sock *sk) */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index d45dbcba8b49..c25097092a06 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1367,7 +1367,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ip_vs_addr_copy(svc->af, &svc->addr, &u->addr); svc->port = u->port; svc->fwmark = u->fwmark; - svc->flags = u->flags; + svc->flags = u->flags & ~IP_VS_SVC_F_HASHED; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; svc->ipvs = ipvs; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 89e5bac384d7..dc9ca12b0489 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -664,7 +664,7 @@ int nf_conntrack_proto_init(void) #if IS_ENABLED(CONFIG_IPV6) cleanup_sockopt: - nf_unregister_sockopt(&so_getorigdst6); + nf_unregister_sockopt(&so_getorigdst); #endif return ret; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 39c02d1aeedf..1d02650dd715 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -306,8 +306,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, { flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; - if (likely(!nf_flowtable_hw_offload(flow_table) || - !test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags))) + if (likely(!nf_flowtable_hw_offload(flow_table))) return; nf_flow_offload_add(flow_table, flow); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 2af7bdb38407..528b2f172684 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -902,10 +902,11 @@ static void flow_offload_work_add(struct flow_offload_work *offload) err = flow_offload_rule_add(offload, flow_rule); if (err < 0) - set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); - else - set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); + goto out; + + set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); +out: nf_flow_offload_destroy(flow_rule); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b100c04a0e43..3d6d49420db8 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -31,6 +31,9 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, int length = (th->doff * 4) - sizeof(*th); u8 buf[40], *ptr; + if (unlikely(length < 0)) + return false; + ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); if (ptr == NULL) return false; @@ -47,6 +50,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length--; continue; default: + if (length < 2) + return true; opsize = *ptr++; if (opsize < 2) return true; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d63d2d8f769c..bf4d6ec9fc55 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -736,7 +736,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || - nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) || + nla_put_be32(skb, NFTA_TABLE_FLAGS, + htonl(table->flags & NFT_TABLE_F_MASK)) || nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) || nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle), NFTA_TABLE_PAD)) @@ -947,20 +948,22 @@ err_register_hooks: static void nf_tables_table_disable(struct net *net, struct nft_table *table) { + table->flags &= ~NFT_TABLE_F_DORMANT; nft_table_disable(net, table, 0); + table->flags |= NFT_TABLE_F_DORMANT; } -enum { - NFT_TABLE_STATE_UNCHANGED = 0, - NFT_TABLE_STATE_DORMANT, - NFT_TABLE_STATE_WAKEUP -}; +#define __NFT_TABLE_F_INTERNAL (NFT_TABLE_F_MASK + 1) +#define __NFT_TABLE_F_WAS_DORMANT (__NFT_TABLE_F_INTERNAL << 0) +#define __NFT_TABLE_F_WAS_AWAKEN (__NFT_TABLE_F_INTERNAL << 1) +#define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ + __NFT_TABLE_F_WAS_AWAKEN) static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; u32 flags; - int ret = 0; + int ret; if (!ctx->nla[NFTA_TABLE_FLAGS]) return 0; @@ -985,21 +988,27 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if ((flags & NFT_TABLE_F_DORMANT) && !(ctx->table->flags & NFT_TABLE_F_DORMANT)) { - nft_trans_table_state(trans) = NFT_TABLE_STATE_DORMANT; + ctx->table->flags |= NFT_TABLE_F_DORMANT; + if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) + ctx->table->flags |= __NFT_TABLE_F_WAS_AWAKEN; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { - ret = nf_tables_table_enable(ctx->net, ctx->table); - if (ret >= 0) - nft_trans_table_state(trans) = NFT_TABLE_STATE_WAKEUP; + ctx->table->flags &= ~NFT_TABLE_F_DORMANT; + if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) { + ret = nf_tables_table_enable(ctx->net, ctx->table); + if (ret < 0) + goto err_register_hooks; + + ctx->table->flags |= __NFT_TABLE_F_WAS_DORMANT; + } } - if (ret < 0) - goto err; - nft_trans_table_flags(trans) = flags; nft_trans_table_update(trans) = true; nft_trans_commit_list_add_tail(ctx->net, trans); + return 0; -err: + +err_register_hooks: nft_trans_destroy(trans); return ret; } @@ -1905,7 +1914,7 @@ static int nft_chain_parse_netdev(struct net *net, static int nft_chain_parse_hook(struct net *net, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, - bool autoload) + struct netlink_ext_ack *extack, bool autoload) { struct nftables_pernet *nft_net = nft_pernet(net); struct nlattr *ha[NFTA_HOOK_MAX + 1]; @@ -1935,8 +1944,10 @@ static int nft_chain_parse_hook(struct net *net, if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, autoload); - if (IS_ERR(type)) + if (IS_ERR(type)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return PTR_ERR(type); + } } if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; @@ -1945,8 +1956,11 @@ static int nft_chain_parse_hook(struct net *net, hook->priority <= NF_IP_PRI_CONNTRACK) return -EOPNOTSUPP; - if (!try_module_get(type->owner)) + if (!try_module_get(type->owner)) { + if (nla[NFTA_CHAIN_TYPE]) + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return -ENOENT; + } hook->type = type; @@ -2057,7 +2071,8 @@ static int nft_chain_add(struct nft_table *table, struct nft_chain *chain) static u64 chain_id; static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, - u8 policy, u32 flags) + u8 policy, u32 flags, + struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; @@ -2079,7 +2094,8 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; - err = nft_chain_parse_hook(net, nla, &hook, family, true); + err = nft_chain_parse_hook(net, nla, &hook, family, extack, + true); if (err < 0) return err; @@ -2234,7 +2250,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return -EEXIST; } err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family, - false); + extack, false); if (err < 0) return err; @@ -2447,7 +2463,7 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, extack); } - return nf_tables_addchain(&ctx, family, genmask, policy, flags); + return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack); } static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, @@ -3328,8 +3344,10 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, if (n == NFT_RULE_MAXEXPRS) goto err1; err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, tmp); goto err1; + } size += expr_info[n].ops->size; n++; } @@ -4346,13 +4364,45 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_set_alloc_name(&ctx, set, name); kfree(name); if (err < 0) - goto err_set_alloc_name; + goto err_set_name; + + udata = NULL; + if (udlen) { + udata = set->data + size; + nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); + } + + INIT_LIST_HEAD(&set->bindings); + INIT_LIST_HEAD(&set->catchall_list); + set->table = table; + write_pnet(&set->net, net); + set->ops = ops; + set->ktype = ktype; + set->klen = desc.klen; + set->dtype = dtype; + set->objtype = objtype; + set->dlen = desc.dlen; + set->flags = flags; + set->size = desc.size; + set->policy = policy; + set->udlen = udlen; + set->udata = udata; + set->timeout = timeout; + set->gc_int = gc_int; + + set->field_count = desc.field_count; + for (i = 0; i < desc.field_count; i++) + set->field_len[i] = desc.field_len[i]; + + err = ops->init(set, &desc, nla); + if (err < 0) + goto err_set_init; if (nla[NFTA_SET_EXPR]) { expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_alloc_name; + goto err_set_expr_alloc; } set->exprs[0] = expr; set->num_exprs++; @@ -4363,75 +4413,44 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_EXPR)) { err = -EINVAL; - goto err_set_alloc_name; + goto err_set_expr_alloc; } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { err = -E2BIG; - goto err_set_init; + goto err_set_expr_alloc; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; - goto err_set_init; + goto err_set_expr_alloc; } expr = nft_set_elem_expr_alloc(&ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_init; + goto err_set_expr_alloc; } set->exprs[i++] = expr; set->num_exprs++; } } - udata = NULL; - if (udlen) { - udata = set->data + size; - nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); - } - - INIT_LIST_HEAD(&set->bindings); - INIT_LIST_HEAD(&set->catchall_list); - set->table = table; - write_pnet(&set->net, net); - set->ops = ops; - set->ktype = ktype; - set->klen = desc.klen; - set->dtype = dtype; - set->objtype = objtype; - set->dlen = desc.dlen; - set->flags = flags; - set->size = desc.size; - set->policy = policy; - set->udlen = udlen; - set->udata = udata; - set->timeout = timeout; - set->gc_int = gc_int; set->handle = nf_tables_alloc_handle(table); - set->field_count = desc.field_count; - for (i = 0; i < desc.field_count; i++) - set->field_len[i] = desc.field_len[i]; - - err = ops->init(set, &desc, nla); - if (err < 0) - goto err_set_init; - err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err_set_trans; + goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err_set_trans: - ops->destroy(set); -err_set_init: +err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); -err_set_alloc_name: + + ops->destroy(set); +err_set_init: kfree(set->name); err_set_name: kvfree(set); @@ -8547,10 +8566,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (nft_trans_table_state(trans) == NFT_TABLE_STATE_DORMANT) + if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { + nft_trans_destroy(trans); + break; + } + if (trans->ctx.table->flags & NFT_TABLE_F_DORMANT) nf_tables_table_disable(net, trans->ctx.table); - trans->ctx.table->flags = nft_trans_table_flags(trans); + trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; } else { nft_clear(net, trans->ctx.table); } @@ -8768,9 +8791,17 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (nft_trans_table_state(trans) == NFT_TABLE_STATE_WAKEUP) + if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { + nft_trans_destroy(trans); + break; + } + if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_DORMANT) { nf_tables_table_disable(net, trans->ctx.table); - + trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; + } else if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_AWAKEN) { + trans->ctx.table->flags &= ~NFT_TABLE_F_DORMANT; + } + trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; nft_trans_destroy(trans); } else { list_del_rcu(&trans->ctx.table->list); diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 322ac5dd5402..752b10cae524 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -380,10 +380,14 @@ static int nfnl_cthelper_update(const struct nlattr * const tb[], struct nf_conntrack_helper *helper) { + u32 size; int ret; - if (tb[NFCTH_PRIV_DATA_LEN]) - return -EBUSY; + if (tb[NFCTH_PRIV_DATA_LEN]) { + size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); + if (size != helper->data_len) + return -EBUSY; + } if (tb[NFCTH_POLICY]) { ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 0592a9456084..337e22d8b40b 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1217,7 +1217,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, struct nf_conn *ct; ct = nf_ct_get(pkt->skb, &ctinfo); - if (!ct || ctinfo == IP_CT_UNTRACKED) { + if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) { regs->verdict.code = NFT_BREAK; return; } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 528a2d7ca991..dce866d93fee 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -408,8 +408,8 @@ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, * * Return: true on match, false otherwise. */ -static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); unsigned long *res_map, *fill_map; diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583e..d84afb8fa79a 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -178,6 +178,8 @@ struct nft_pipapo_elem { int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, union nft_pipapo_map_bucket *mt, bool match_only); +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index d65ae0e23028..eabdb8d552ee 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1131,6 +1131,9 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, bool map_index; int i, ret = 0; + if (unlikely(!irq_fpu_usable())) + return nft_pipapo_lookup(net, set, key, ext); + m = rcu_dereference(priv->match); /* This also protects access to all data related to scratch maps */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3a62f97acf39..6133e412b948 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -461,11 +461,13 @@ void netlink_table_ungrab(void) static inline void netlink_lock_table(void) { + unsigned long flags; + /* read_lock() synchronizes us to netlink_table_grab */ - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); } static inline void diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 53dbe733f998..6cfd30fc0798 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -110,6 +110,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) if (!llcp_sock->service_name) { nfc_llcp_local_put(llcp_sock->local); llcp_sock->local = NULL; + llcp_sock->dev = NULL; ret = -ENOMEM; goto put_dev; } @@ -119,6 +120,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) llcp_sock->local = NULL; kfree(llcp_sock->service_name); llcp_sock->service_name = NULL; + llcp_sock->dev = NULL; ret = -EADDRINUSE; goto put_dev; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 9a585332ea84..da7fe9db1b00 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1191,6 +1191,7 @@ EXPORT_SYMBOL(nci_allocate_device); void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); + nci_hci_deallocate(ndev); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 6b275a387a92..96865142104f 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -792,3 +792,8 @@ struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev) return hdev; } + +void nci_hci_deallocate(struct nci_dev *ndev) +{ + kfree(ndev->hci_dev); +} diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 9c7eb8455ba8..5f1d438a0a23 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -329,7 +329,7 @@ static int rawsock_create(struct net *net, struct socket *sock, return -ESOCKTNOSUPPORT; if (sock->type == SOCK_RAW) { - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; sock->ops = &rawsock_raw_ops; } else { diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 96b524ceabca..896b8f5bc885 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -611,6 +611,14 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, spin_lock(&meter->lock); long_delta_ms = (now_ms - meter->used); /* ms */ + if (long_delta_ms < 0) { + /* This condition means that we have several threads fighting + * for a meter lock, and the one who received the packets a + * bit later wins. Assuming that all racing threads received + * packets at the same time to avoid overflow. + */ + long_delta_ms = 0; + } /* Make sure delta_ms will not be too large, so that bucket will not * wrap around below. diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ba96db1880ea..330ba68828e7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -422,7 +422,8 @@ static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; - if (ktime_to_timespec64_cond(skb->tstamp, ts)) + if ((flags & SOF_TIMESTAMPING_SOFTWARE) && + ktime_to_timespec64_cond(skb->tstamp, ts)) return TP_STATUS_TS_SOFTWARE; return 0; @@ -2340,7 +2341,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, skb_copy_bits(skb, 0, h.raw + macoff, snaplen); - if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) + /* Always timestamp; prefer an existing software timestamp taken + * closer to the time of capture. + */ + ts_status = tpacket_get_timestamp(skb, &ts, + po->tp_tstamp | SOF_TIMESTAMPING_SOFTWARE); + if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; @@ -2677,7 +2683,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2890,7 +2896,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -3028,10 +3034,13 @@ static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - if (po->tx_ring.pg_vec) + /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. + * tpacket_snd() will redo the check safely. + */ + if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); - else - return packet_snd(sock, msg, len); + + return packet_snd(sock, msg, len); } /* @@ -3162,7 +3171,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, /* prevents packet_notifier() from calling * register_prot_hook() */ - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); dev_curr = po->prot_hook.dev; @@ -3172,17 +3181,17 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } BUG_ON(po->running); - po->num = proto; + WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } @@ -3496,7 +3505,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); @@ -3511,16 +3520,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex; if (peer) return -EOPNOTSUPP; + ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; - sll->sll_protocol = po->num; + sll->sll_ifindex = ifindex; + sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -4099,7 +4110,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -4405,7 +4416,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, was_running = po->running; num = po->num; if (was_running) { - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); @@ -4440,7 +4451,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, spin_lock(&po->bind_lock); if (was_running) { - po->num = num; + WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); @@ -4610,8 +4621,8 @@ static int packet_seq_show(struct seq_file *seq, void *v) s, refcount_read(&s->sk_refcnt), s->sk_type, - ntohs(po->num), - po->ifindex, + ntohs(READ_ONCE(po->num)), + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index c0477bec09bd..f2efaa4225f9 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -436,7 +436,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) struct qrtr_sock *ipc; struct sk_buff *skb; struct qrtr_cb *cb; - unsigned int size; + size_t size; unsigned int ver; size_t hdrlen; diff --git a/net/rds/connection.c b/net/rds/connection.c index f2fcab182095..a3bc4b54d491 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -240,12 +240,23 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (loop_trans) { rds_trans_put(loop_trans); conn->c_loopback = 1; - if (is_outgoing && trans->t_prefer_loopback) { - /* "outgoing" connection - and the transport - * says it wants the connection handled by the - * loopback transport. This is what TCP does. - */ - trans = &rds_loop_transport; + if (trans->t_prefer_loopback) { + if (likely(is_outgoing)) { + /* "outgoing" connection to local address. + * Protocol says it wants the connection + * handled by the loopback transport. + * This is what TCP does. + */ + trans = &rds_loop_transport; + } else { + /* No transport currently in use + * should end up here, but if it + * does, reset/destroy the connection. + */ + kmem_cache_free(rds_conn_slab, conn); + conn = ERR_PTR(-EOPNOTSUPP); + goto out; + } } } diff --git a/net/rds/recv.c b/net/rds/recv.c index 4db109fb6ec2..5b426dc3634d 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -714,7 +714,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (rds_cmsg_recv(inc, msg, rs)) { ret = -EFAULT; - goto out; + break; } rds_recvmsg_zcookie(rs, msg); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 43db0eca911f..abf19c0e3ba0 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -313,8 +313,8 @@ out: } #endif -static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, - __u32 scope_id) +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id) { struct net_device *dev = NULL; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/rds/tcp.h b/net/rds/tcp.h index bad9cf49d565..dc8d745d6857 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -59,7 +59,8 @@ u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; void rds_tcp_accept_work(struct sock *sk); - +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id); /* tcp_connect.c */ int rds_tcp_conn_path_connect(struct rds_conn_path *cp); void rds_tcp_conn_path_shutdown(struct rds_conn_path *conn); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 101cf14215a0..09cadd556d1e 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -167,6 +167,12 @@ int rds_tcp_accept_one(struct socket *sock) } #endif + if (!rds_tcp_laddr_check(sock_net(sock->sk), peer_addr, dev_if)) { + /* local address connection is only allowed via loopback */ + ret = -EOPNOTSUPP; + goto out; + } + conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, &rds_tcp_transport, 0, GFP_KERNEL, dev_if); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index ec7a1c438df9..a656baa321fe 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -904,14 +904,19 @@ static int tcf_ct_act_nat(struct sk_buff *skb, } err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); - if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ct_nat_execute(skb, ct, ctinfo, range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } } return err; #else @@ -984,7 +989,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, */ cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force); if (!cached) { - if (!commit && tcf_ct_flow_table_lookup(p, skb, family)) { + if (tcf_ct_flow_table_lookup(p, skb, family)) { skip_add = true; goto do_nat; } @@ -1022,10 +1027,11 @@ do_nat: * even if the connection is already confirmed. */ nf_conntrack_confirm(skb); - } else if (!skip_add) { - tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo); } + if (!skip_add) + tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo); + out_push: skb_push_rcsum(skb, nh_ofs); @@ -1202,9 +1208,6 @@ static int tcf_ct_fill_params(struct net *net, sizeof(p->zone)); } - if (p->zone == NF_CT_DEFAULT_ZONE_ID) - return 0; - nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0); tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL); if (!tmpl) { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 40fbea626dfd..279f9e2a2319 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1624,7 +1624,7 @@ int tcf_classify_ingress(struct sk_buff *skb, /* If we missed on some chain */ if (ret == TC_ACT_UNSPEC && last_executed_chain) { - ext = skb_ext_add(skb, TC_SKB_EXT); + ext = tc_skb_ext_alloc(skb); if (WARN_ON_ONCE(!ext)) return TC_ACT_SHOT; ext->chain = last_executed_chain; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 7d37638ee1c7..951542843cab 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -943,7 +943,7 @@ static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); - if (!tcph) + if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, @@ -967,6 +967,8 @@ static const void *cake_get_tcpopt(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -1104,6 +1106,8 @@ static bool cake_tcph_may_drop(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -2338,7 +2342,7 @@ static int cake_config_precedence(struct Qdisc *sch) /* List of known Diffserv codepoints: * - * Least Effort (CS1) + * Least Effort (CS1, LE) * Best Effort (CS0) * Max Reliability & LLT "Lo" (TOS1) * Max Throughput (TOS2) @@ -2360,7 +2364,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Total 25 codepoints. */ -/* List of traffic classes in RFC 4594: +/* List of traffic classes in RFC 4594, updated by RFC 8622: * (roughly descending order of contended priority) * (roughly ascending order of uncontended throughput) * @@ -2375,7 +2379,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Ops, Admin, Management (CS2,TOS1) - eg. ssh * Standard Service (CS0 & unrecognised codepoints) * High Throughput Data (AF1x,TOS2) - eg. web traffic - * Low Priority Data (CS1) - eg. BitTorrent + * Low Priority Data (CS1,LE) - eg. BitTorrent * Total 12 traffic classes. */ @@ -2391,7 +2395,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) * Video Streaming (AF4x, AF3x, CS3) * Bog Standard (CS0 etc.) * High Throughput (AF1x, TOS2) - * Background Traffic (CS1) + * Background Traffic (CS1, LE) * * Total 8 traffic classes. */ @@ -2435,7 +2439,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1) * Best Effort (CS0, AF1x, TOS2, and those not specified) - * Background Traffic (CS1) + * Background Traffic (CS1, LE) * * Total 4 traffic classes. */ @@ -2473,7 +2477,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) static int cake_config_diffserv3(struct Qdisc *sch) { /* Simplified Diffserv structure with 3 tins. - * Low Priority (CS1) + * Low Priority (CS1, LE) * Best Effort * Latency Sensitive (TOS4, VA, EF, CS6, CS7) */ diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index cd2748e2d4a2..d320bcfb2da2 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -407,7 +407,8 @@ static void dsmark_reset(struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - qdisc_reset(p->q); + if (p->q) + qdisc_reset(p->q); sch->qstats.backlog = 0; sch->q.qlen = 0; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 949163fe68af..cac684952edc 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -138,8 +138,15 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Classifies packet into corresponding flow */ idx = fq_pie_classify(skb, sch, &ret); - sel_flow = &q->flows[idx]; + if (idx == 0) { + if (ret & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return ret; + } + idx--; + sel_flow = &q->flows[idx]; /* Checks whether adding a new packet would exceed memory limit */ get_pie_cb(skb)->mem_usage = skb->truesize; memory_limited = q->memory_usage > q->memory_limit + skb->truesize; @@ -297,9 +304,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, goto flow_error; } q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]); - if (!q->flows_cnt || q->flows_cnt >= 65536) { + if (!q->flows_cnt || q->flows_cnt > 65536) { NL_SET_ERR_MSG_MOD(extack, - "Number of flows must range in [1..65535]"); + "Number of flows must range in [1..65536]"); goto flow_error; } } @@ -367,7 +374,7 @@ static void fq_pie_timer(struct timer_list *t) struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock; /* to lock qdisc for probability calculations */ - u16 idx; + u32 idx; root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -388,7 +395,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, { struct fq_pie_sched_data *q = qdisc_priv(sch); int err; - u16 idx; + u32 idx; pie_params_init(&q->p_params); sch->limit = 10 * 1024; @@ -500,7 +507,7 @@ static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) static void fq_pie_reset(struct Qdisc *sch) { struct fq_pie_sched_data *q = qdisc_priv(sch); - u16 idx; + u32 idx; INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 44991ea726fc..fc8b56bcabf3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -35,6 +35,25 @@ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; EXPORT_SYMBOL(default_qdisc_ops); +static void qdisc_maybe_clear_missed(struct Qdisc *q, + const struct netdev_queue *txq) +{ + clear_bit(__QDISC_STATE_MISSED, &q->state); + + /* Make sure the below netif_xmit_frozen_or_stopped() + * checking happens after clearing STATE_MISSED. + */ + smp_mb__after_atomic(); + + /* Checking netif_xmit_frozen_or_stopped() again to + * make sure STATE_MISSED is set if the STATE_MISSED + * set by netif_tx_wake_queue()'s rescheduling of + * net_tx_action() is cleared by the above clear_bit(). + */ + if (!netif_xmit_frozen_or_stopped(txq)) + set_bit(__QDISC_STATE_MISSED, &q->state); +} + /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with @@ -74,6 +93,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) } } else { skb = SKB_XOFF_MAGIC; + qdisc_maybe_clear_missed(q, txq); } } @@ -242,6 +262,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, } } else { skb = NULL; + qdisc_maybe_clear_missed(q, txq); } if (lock) spin_unlock(lock); @@ -251,8 +272,10 @@ validate: *validate = true; if ((q->flags & TCQ_F_ONETXQUEUE) && - netif_xmit_frozen_or_stopped(txq)) + netif_xmit_frozen_or_stopped(txq)) { + qdisc_maybe_clear_missed(q, txq); return skb; + } skb = qdisc_dequeue_skb_bad_txq(q); if (unlikely(skb)) { @@ -311,6 +334,8 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); + else + qdisc_maybe_clear_missed(q, txq); HARD_TX_UNLOCK(dev, txq); } else { @@ -640,8 +665,10 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; + bool need_retry = true; int band; +retry: for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); @@ -652,6 +679,23 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) } if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); + } else if (need_retry && + test_bit(__QDISC_STATE_MISSED, &qdisc->state)) { + /* Delay clearing the STATE_MISSED here to reduce + * the overhead of the second spin_trylock() in + * qdisc_run_begin() and __netif_schedule() calling + * in qdisc_run_end(). + */ + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + + /* Make sure dequeuing happens after clearing + * STATE_MISSED. + */ + smp_mb__after_atomic(); + + need_retry = false; + + goto retry; } else { WRITE_ONCE(qdisc->empty, true); } @@ -1158,8 +1202,10 @@ static void dev_reset_queue(struct net_device *dev, qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); + } } static bool some_qdisc_is_busy(struct net_device *dev) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 081c11d5717c..8827987ba903 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1488,7 +1488,8 @@ static void htb_parent_to_leaf_offload(struct Qdisc *sch, struct Qdisc *old_q; /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ - qdisc_refcount_inc(new_q); + if (new_q) + qdisc_refcount_inc(new_q); old_q = htb_graft_helper(dev_queue, new_q); WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); } @@ -1675,10 +1676,9 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, cl->parent->common.classid, NULL); if (q->offload) { - if (new_q) { + if (new_q) htb_set_lockdep_class_child(new_q); - htb_parent_to_leaf_offload(sch, dev_queue, new_q); - } + htb_parent_to_leaf_offload(sch, dev_queue, new_q); } } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 40f9f6c4a0a1..a79d193ff872 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4473,6 +4473,7 @@ static int sctp_setsockopt_encap_port(struct sock *sk, transports) t->encap_port = encap_port; + asoc->encap_port = encap_port; return 0; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index e92df779af73..55871b277f47 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -307,7 +307,7 @@ static struct ctl_table sctp_net_table[] = { .data = &init_net.sctp.encap_port, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &udp_port_max, }, diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 94b31f2551bc..967712ba52a0 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -429,6 +429,8 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev); int smcd_register_dev(struct smcd_dev *smcd) { + int rc; + mutex_lock(&smcd_dev_list.mutex); if (list_empty(&smcd_dev_list.list)) { u8 *system_eid = NULL; @@ -448,7 +450,14 @@ int smcd_register_dev(struct smcd_dev *smcd) dev_name(&smcd->dev), smcd->pnetid, smcd->pnetid_by_user ? " (user defined)" : ""); - return device_add(&smcd->dev); + rc = device_add(&smcd->dev); + if (rc) { + mutex_lock(&smcd_dev_list.mutex); + list_del(&smcd->list); + mutex_unlock(&smcd_dev_list.mutex); + } + + return rc; } EXPORT_SYMBOL_GPL(smcd_register_dev); diff --git a/net/socket.c b/net/socket.c index 27e3e7d53f8e..4f2c6d2795d0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1072,19 +1072,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -/** - * get_net_ns - increment the refcount of the network namespace - * @ns: common namespace (net) - * - * Returns the net's common namespace. - */ - -struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} -EXPORT_SYMBOL_GPL(get_net_ns); - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f555d335e910..42623d6b8f0e 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1677,13 +1677,6 @@ call_reserveresult(struct rpc_task *task) return; } - /* - * Even though there was an error, we may have acquired - * a request slot somehow. Make sure not to leak it. - */ - if (task->tk_rqstp) - xprt_release(task); - switch (status) { case -ENOMEM: rpc_delay(task, HZ >> 2); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e5b5a960a69b..3509a7f139b9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -70,6 +70,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -1606,17 +1607,40 @@ xprt_transmit(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } -static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) +static void xprt_complete_request_init(struct rpc_task *task) +{ + if (task->tk_rqstp) + xprt_request_init(task); +} + +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) { set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); + rpc_sleep_on(&xprt->backlog, task, xprt_complete_request_init); +} +EXPORT_SYMBOL_GPL(xprt_add_backlog); + +static bool __xprt_set_rq(struct rpc_task *task, void *data) +{ + struct rpc_rqst *req = data; + + if (task->tk_rqstp == NULL) { + memset(req, 0, sizeof(*req)); /* mark unused */ + task->tk_rqstp = req; + return true; + } + return false; } -static void xprt_wake_up_backlog(struct rpc_xprt *xprt) +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) { - if (rpc_wake_up_next(&xprt->backlog) == NULL) + if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) { clear_bit(XPRT_CONGESTED, &xprt->state); + return false; + } + return true; } +EXPORT_SYMBOL_GPL(xprt_wake_up_backlog); static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task) { @@ -1626,7 +1650,7 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task goto out; spin_lock(&xprt->reserve_lock); if (test_bit(XPRT_CONGESTED, &xprt->state)) { - rpc_sleep_on(&xprt->backlog, task, NULL); + xprt_add_backlog(xprt, task); ret = true; } spin_unlock(&xprt->reserve_lock); @@ -1703,11 +1727,11 @@ EXPORT_SYMBOL_GPL(xprt_alloc_slot); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { spin_lock(&xprt->reserve_lock); - if (!xprt_dynamic_free_slot(xprt, req)) { + if (!xprt_wake_up_backlog(xprt, req) && + !xprt_dynamic_free_slot(xprt, req)) { memset(req, 0, sizeof(*req)); /* mark unused */ list_add(&req->rq_list, &xprt->free); } - xprt_wake_up_backlog(xprt); spin_unlock(&xprt->reserve_lock); } EXPORT_SYMBOL_GPL(xprt_free_slot); @@ -1894,10 +1918,10 @@ void xprt_release(struct rpc_task *task) xdr_free_bvec(&req->rq_snd_buf); if (req->rq_cred != NULL) put_rpccred(req->rq_cred); - task->tk_rqstp = NULL; if (req->rq_release_snd_buf) req->rq_release_snd_buf(req); + task->tk_rqstp = NULL; if (likely(!bc_prealloc(req))) xprt->ops->free_slot(xprt, req); else diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 649f7d8b9733..c335c1361564 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -628,8 +628,9 @@ out_mapping_err: return false; } -/* The tail iovec might not reside in the same page as the - * head iovec. +/* The tail iovec may include an XDR pad for the page list, + * as well as additional content, and may not reside in the + * same page as the head iovec. */ static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, struct xdr_buf *xdr, @@ -747,19 +748,27 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct xdr_buf *xdr) { - struct kvec *tail = &xdr->tail[0]; - if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) return false; - /* If there is a Read chunk, the page list is handled + /* If there is a Read chunk, the page list is being handled * via explicit RDMA, and thus is skipped here. */ - if (tail->iov_len) { - if (!rpcrdma_prepare_tail_iov(req, xdr, - offset_in_page(tail->iov_base), - tail->iov_len)) + /* Do not include the tail if it is only an XDR pad */ + if (xdr->tail[0].iov_len > 3) { + unsigned int page_base, len; + + /* If the content in the page list is an odd length, + * xdr_write_pages() adds a pad at the beginning of + * the tail iovec. Force the tail's non-pad content to + * land at the next XDR position in the Send message. + */ + page_base = offset_in_page(xdr->tail[0].iov_base); + len = xdr->tail[0].iov_len; + page_base += len & 3; + len -= len & 3; + if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len)) return false; kref_get(&req->rl_kref); } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 09953597d055..19a49d26b1e4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -520,9 +520,8 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) return; out_sleep: - set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); task->tk_status = -EAGAIN; + xprt_add_backlog(xprt, task); } /** @@ -537,10 +536,11 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst) struct rpcrdma_xprt *r_xprt = container_of(xprt, struct rpcrdma_xprt, rx_xprt); - memset(rqst, 0, sizeof(*rqst)); - rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); - if (unlikely(!rpc_wake_up_next(&xprt->backlog))) - clear_bit(XPRT_CONGESTED, &xprt->state); + rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + if (!xprt_wake_up_backlog(xprt, rqst)) { + memset(rqst, 0, sizeof(*rqst)); + rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + } } static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt, diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 1e965a380896..649c23518ec0 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1201,6 +1201,20 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt) } /** + * rpcrdma_reply_put - Put reply buffers back into pool + * @buffers: buffer pool + * @req: object to return + * + */ +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + if (req->rl_reply) { + rpcrdma_rep_put(buffers, req->rl_reply); + req->rl_reply = NULL; + } +} + +/** * rpcrdma_buffer_get - Get a request buffer * @buffers: Buffer pool from which to obtain a buffer * @@ -1228,9 +1242,7 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) */ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) { - if (req->rl_reply) - rpcrdma_rep_put(buffers, req->rl_reply); - req->rl_reply = NULL; + rpcrdma_reply_put(buffers, req); spin_lock(&buffers->rb_lock); list_add(&req->rl_list, &buffers->rb_send_bufs); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 436ad7312614..5d231d94e944 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -479,6 +479,7 @@ struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep); +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size, gfp_t flags); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 47aa47a2b07c..316d04945587 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1010,6 +1010,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req) kernel_sock_shutdown(transport->sock, SHUT_RDWR); return -ENOTCONN; } + if (!transport->inet) + return -ENOTCONN; xs_pktdump("packet data:", req->rq_svec->iov_base, diff --git a/net/tipc/core.c b/net/tipc/core.c index 5cc1f0307215..3f4542e0f065 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -60,7 +60,7 @@ static int __net_init tipc_init_net(struct net *net) tn->trial_addr = 0; tn->addr_trial_end = 0; tn->capabilities = TIPC_NODE_CAPABILITIES; - INIT_WORK(&tn->final_work.work, tipc_net_finalize_work); + INIT_WORK(&tn->work, tipc_net_finalize_work); memset(tn->node_id, 0, sizeof(tn->node_id)); memset(tn->node_id_string, 0, sizeof(tn->node_id_string)); tn->mon_threshold = TIPC_DEF_MON_THRESHOLD; @@ -110,7 +110,7 @@ static void __net_exit tipc_exit_net(struct net *net) tipc_detach_loopback(net); /* Make sure the tipc_net_finalize_work() finished */ - cancel_work_sync(&tn->final_work.work); + cancel_work_sync(&tn->work); tipc_net_stop(net); tipc_bcast_stop(net); @@ -119,6 +119,8 @@ static void __net_exit tipc_exit_net(struct net *net) #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_stop(&tipc_net(net)->crypto_tx); #endif + while (atomic_read(&tn->wq_count)) + cond_resched(); } static void __net_exit tipc_pernet_pre_exit(struct net *net) diff --git a/net/tipc/core.h b/net/tipc/core.h index 03de7b213f55..0a3f7a70a50a 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -91,12 +91,6 @@ extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; -struct tipc_net_work { - struct work_struct work; - struct net *net; - u32 addr; -}; - struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; @@ -148,7 +142,9 @@ struct tipc_net { struct tipc_crypto *crypto_tx; #endif /* Work item for net finalize */ - struct tipc_net_work final_work; + struct work_struct work; + /* The numbers of work queues in schedule */ + atomic_t wq_count; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 5380f605b851..da69e1abf68f 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -168,7 +168,7 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, /* Apply trial address if we just left trial period */ if (!trial && !self) { - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } @@ -308,7 +308,7 @@ static void tipc_disc_timeout(struct timer_list *t) if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) { mod_timer(&d->timer, jiffies + TIPC_DISC_INIT); spin_unlock_bh(&d->lock); - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); return; } diff --git a/net/tipc/link.c b/net/tipc/link.c index 115109259430..c44b4bfaaee6 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -372,6 +372,11 @@ char tipc_link_plane(struct tipc_link *l) return l->net_plane; } +struct net *tipc_link_net(struct tipc_link *l) +{ + return l->net; +} + void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) { l->peer_caps = capabilities; diff --git a/net/tipc/link.h b/net/tipc/link.h index fc07232c9a12..a16f401fdabd 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -156,4 +156,5 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); bool tipc_link_too_silent(struct tipc_link *l); +struct net *tipc_link_net(struct tipc_link *l); #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 3f0a25345a7c..ce6ab54822d8 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -149,18 +149,13 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (unlikely(head)) goto err; *buf = NULL; + if (skb_has_frag_list(frag) && __skb_linearize(frag)) + goto err; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; TIPC_SKB_CB(head)->tail = NULL; - if (skb_is_nonlinear(head)) { - skb_walk_frags(head, tail) { - TIPC_SKB_CB(head)->tail = tail; - } - } else { - skb_frag_list_init(head); - } return 0; } diff --git a/net/tipc/net.c b/net/tipc/net.c index a130195af188..0e95572e56b4 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -41,6 +41,7 @@ #include "socket.h" #include "node.h" #include "bcast.h" +#include "link.h" #include "netlink.h" #include "monitor.h" @@ -142,19 +143,9 @@ static void tipc_net_finalize(struct net *net, u32 addr) void tipc_net_finalize_work(struct work_struct *work) { - struct tipc_net_work *fwork; + struct tipc_net *tn = container_of(work, struct tipc_net, work); - fwork = container_of(work, struct tipc_net_work, work); - tipc_net_finalize(fwork->net, fwork->addr); -} - -void tipc_sched_net_finalize(struct net *net, u32 addr) -{ - struct tipc_net *tn = tipc_net(net); - - tn->final_work.net = net; - tn->final_work.addr = addr; - schedule_work(&tn->final_work.work); + tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/node.c b/net/tipc/node.c index 8217905348f4..81af92954c6c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -423,18 +423,18 @@ static void tipc_node_write_unlock(struct tipc_node *n) write_unlock_bh(&n->lock); if (flags & TIPC_NOTIFY_NODE_DOWN) - tipc_publ_notify(net, publ_list, n->addr, n->capabilities); + tipc_publ_notify(net, publ_list, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_NODE_UP) - tipc_named_node_up(net, n->addr, n->capabilities); + tipc_named_node_up(net, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_LINK_UP) { - tipc_mon_peer_up(net, n->addr, bearer_id); - tipc_nametbl_publish(net, &ua, &sk, n->link_id); + tipc_mon_peer_up(net, sk.node, bearer_id); + tipc_nametbl_publish(net, &ua, &sk, sk.ref); } if (flags & TIPC_NOTIFY_LINK_DOWN) { - tipc_mon_peer_down(net, n->addr, bearer_id); - tipc_nametbl_withdraw(net, &ua, &sk, n->link_id); + tipc_mon_peer_down(net, sk.node, bearer_id); + tipc_nametbl_withdraw(net, &ua, &sk, sk.ref); } } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 58935cd0d068..53af72824c9c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1262,7 +1262,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); - __skb_dequeue(arrvq); + /* Decrease the skb's refcnt as increasing in the + * function tipc_skb_peek + */ + kfree_skb(__skb_dequeue(arrvq)); } spin_unlock_bh(&inputq->lock); __skb_queue_purge(&tmpq); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index e556d2cdc064..c2bb818704c8 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -814,6 +814,7 @@ static void cleanup_bearer(struct work_struct *work) kfree_rcu(rcast, rcu); } + atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); synchronize_net(); @@ -834,6 +835,7 @@ static void tipc_udp_disable(struct tipc_bearer *b) RCU_INIT_POINTER(ub->bearer, NULL); /* sock_release need to be done outside of rtnl lock */ + atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); INIT_WORK(&ub->work, cleanup_bearer); schedule_work(&ub->work); } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 76a6f8c2eec4..bd9f1567aa39 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -50,6 +50,7 @@ static void tls_device_gc_task(struct work_struct *work); static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task); static LIST_HEAD(tls_device_gc_list); static LIST_HEAD(tls_device_list); +static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); static void tls_device_free_ctx(struct tls_context *ctx) @@ -680,15 +681,13 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx, struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); struct net_device *netdev; - if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags))) - return; - trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type); + rcu_read_lock(); netdev = READ_ONCE(tls_ctx->netdev); if (netdev) netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, TLS_OFFLOAD_CTX_DIR_RX); - clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags); + rcu_read_unlock(); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC); } @@ -761,6 +760,8 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) if (tls_ctx->rx_conf != TLS_HW) return; + if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) + return; prot = &tls_ctx->prot_info; rx_ctx = tls_offload_ctx_rx(tls_ctx); @@ -963,6 +964,17 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, ctx->sw.decrypted |= is_decrypted; + if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) { + if (likely(is_encrypted || is_decrypted)) + return 0; + + /* After tls_device_down disables the offload, the next SKB will + * likely have initial fragments decrypted, and final ones not + * decrypted. We need to reencrypt that single SKB. + */ + return tls_device_reencrypt(sk, skb); + } + /* Return immediately if the record is either entirely plaintext or * entirely ciphertext. Otherwise handle reencrypt partially decrypted * record. @@ -1292,6 +1304,26 @@ static int tls_device_down(struct net_device *netdev) spin_unlock_irqrestore(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &list, list) { + /* Stop offloaded TX and switch to the fallback. + * tls_is_sk_tx_device_offloaded will return false. + */ + WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw); + + /* Stop the RX and TX resync. + * tls_dev_resync must not be called after tls_dev_del. + */ + WRITE_ONCE(ctx->netdev, NULL); + + /* Start skipping the RX resync logic completely. */ + set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags); + + /* Sync with inflight packets. After this point: + * TX: no non-encrypted packets will be passed to the driver. + * RX: resync requests from the driver will be ignored. + */ + synchronize_net(); + + /* Release the offload context on the driver side. */ if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); @@ -1299,15 +1331,21 @@ static int tls_device_down(struct net_device *netdev) !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); - WRITE_ONCE(ctx->netdev, NULL); - smp_mb__before_atomic(); /* pairs with test_and_set_bit() */ - while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags)) - usleep_range(10, 200); + dev_put(netdev); - list_del_init(&ctx->list); - if (refcount_dec_and_test(&ctx->refcount)) - tls_device_free_ctx(ctx); + /* Move the context to a separate list for two reasons: + * 1. When the context is deallocated, list_del is called. + * 2. It's no longer an offloaded context, so we don't want to + * run offload-specific code on this context. + */ + spin_lock_irqsave(&tls_device_lock, flags); + list_move_tail(&ctx->list, &tls_device_down_list); + spin_unlock_irqrestore(&tls_device_lock, flags); + + /* Device contexts for RX and TX will be freed in on sk_destruct + * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. + */ } up_write(&device_offload_lock); diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index cacf040872c7..e40bedd112b6 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -431,6 +431,13 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk, } EXPORT_SYMBOL_GPL(tls_validate_xmit_skb); +struct sk_buff *tls_validate_xmit_skb_sw(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb) +{ + return tls_sw_fallback(sk, skb); +} + struct sk_buff *tls_encrypt_skb(struct sk_buff *skb) { return tls_sw_fallback(skb->sk, skb); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 47b7c5334c34..fde56ff49163 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -636,6 +636,7 @@ struct tls_context *tls_ctx_create(struct sock *sk) mutex_init(&ctx->tx_lock); rcu_assign_pointer(icsk->icsk_ulp_data, ctx); ctx->sk_proto = READ_ONCE(sk->sk_prot); + ctx->sk = sk; return ctx; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 1dcb34dfd56b..694de024d0ee 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -37,6 +37,7 @@ #include <linux/sched/signal.h> #include <linux/module.h> +#include <linux/splice.h> #include <crypto/aead.h> #include <net/strparser.h> @@ -1281,7 +1282,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, } static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, - int flags, long timeo, int *err) + bool nonblock, long timeo, int *err) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1306,7 +1307,7 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, if (sock_flag(sk, SOCK_DONE)) return NULL; - if ((flags & MSG_DONTWAIT) || !timeo) { + if (nonblock || !timeo) { *err = -EAGAIN; return NULL; } @@ -1786,7 +1787,7 @@ int tls_sw_recvmsg(struct sock *sk, bool async_capable; bool async = false; - skb = tls_wait_data(sk, psock, flags, timeo, &err); + skb = tls_wait_data(sk, psock, flags & MSG_DONTWAIT, timeo, &err); if (!skb) { if (psock) { int ret = sk_msg_recvmsg(sk, psock, msg, len, @@ -1990,9 +1991,9 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); - skb = tls_wait_data(sk, NULL, flags, timeo, &err); + skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err); if (!skb) goto splice_read_end; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5a31307ceb76..5d1192ceb139 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -535,12 +535,14 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.mnt = NULL; state = sk->sk_state; sk->sk_state = TCP_CLOSE; + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; + unix_state_unlock(sk); wake_up_interruptible_all(&u->peer_wait); - skpair = unix_peer(sk); - if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); @@ -555,7 +557,6 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ - unix_peer(sk) = NULL; } /* Try to flush out this socket. Throw out buffers at least */ diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 2eee93985ab0..af590ae606b6 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -28,7 +28,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" @(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ - cat $^ ; \ + echo | cat - $^ ; \ echo '};'; \ echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ ) > $@ diff --git a/net/wireless/core.c b/net/wireless/core.c index 6fbf7537faf5..8d0883e81093 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1340,6 +1340,11 @@ void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, rdev->devlist_generation++; wdev->registered = true; + if (wdev->netdev && + sysfs_create_link(&wdev->netdev->dev.kobj, &rdev->wiphy.dev.kobj, + "phy80211")) + pr_err("failed to add phy80211 symlink to netdev!\n"); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); } @@ -1365,14 +1370,6 @@ int cfg80211_register_netdevice(struct net_device *dev) if (ret) goto out; - if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, - "phy80211")) { - pr_err("failed to add phy80211 symlink to netdev!\n"); - unregister_netdevice(dev); - ret = -EINVAL; - goto out; - } - cfg80211_register_wdev(rdev, wdev); ret = 0; out: diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 6bdd96408022..d245968b74cb 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -334,6 +334,7 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, gfp_t gfp) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_pmsr_request *tmp, *prev, *to_free = NULL; struct sk_buff *msg; void *hdr; @@ -364,9 +365,20 @@ free_msg: nlmsg_free(msg); free_request: spin_lock_bh(&wdev->pmsr_lock); - list_del(&req->list); + /* + * cfg80211_pmsr_process_abort() may have already moved this request + * to the free list, and will free it later. In this case, don't free + * it here. + */ + list_for_each_entry_safe(tmp, prev, &wdev->pmsr_list, list) { + if (tmp == req) { + list_del(&req->list); + to_free = req; + break; + } + } spin_unlock_bh(&wdev->pmsr_lock); - kfree(req); + kfree(to_free); } EXPORT_SYMBOL_GPL(cfg80211_pmsr_complete); diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 9b959e3b09c6..0c3f05c9be27 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -133,6 +133,10 @@ static int wiphy_resume(struct device *dev) if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); wiphy_unlock(&rdev->wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(&rdev->wiphy); + rtnl_unlock(); return ret; diff --git a/net/wireless/util.c b/net/wireless/util.c index 382c5262d997..18dba3d7c638 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -542,7 +542,7 @@ EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, - u8 data_offset) + u8 data_offset, bool is_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { @@ -629,7 +629,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, skb_copy_bits(skb, hdrlen, &payload, sizeof(payload)); tmp.h_proto = payload.proto; - if (likely((ether_addr_equal(payload.hdr, rfc1042_header) && + if (likely((!is_amsdu && ether_addr_equal(payload.hdr, rfc1042_header) && tmp.h_proto != htons(ETH_P_AARP) && tmp.h_proto != htons(ETH_P_IPX)) || ether_addr_equal(payload.hdr, bridge_tunnel_header))) @@ -771,6 +771,9 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, remaining = skb->len - offset; if (subframe_len > remaining) goto purge; + /* mitigate A-MSDU aggregation injection attacks */ + if (ether_addr_equal(eth.h_dest, rfc1042_header)) + goto purge; offset += sizeof(struct ethhdr); last = remaining <= subframe_len + padding; @@ -1056,6 +1059,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; + case NL80211_IFTYPE_OCB: + cfg80211_leave_ocb(rdev, dev); + break; default: break; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 44d6566dd23e..1816899499ce 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -536,7 +536,7 @@ static int x25_create(struct net *net, struct socket *sock, int protocol, if (protocol) goto out; - rc = -ENOBUFS; + rc = -ENOMEM; if ((sk = x25_alloc_socket(net, kern)) == NULL) goto out; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index aa696854be78..53e300f860bb 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -1255,7 +1255,7 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) for (i = 0; i < batch_size; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; + tx_desc->addr = (*frame_nb + i) * opt_xsk_frame_size; tx_desc->len = PKT_SIZE; } diff --git a/samples/vfio-mdev/mdpy-fb.c b/samples/vfio-mdev/mdpy-fb.c index 21dbf63d6e41..9ec93d90e8a5 100644 --- a/samples/vfio-mdev/mdpy-fb.c +++ b/samples/vfio-mdev/mdpy-fb.c @@ -117,22 +117,27 @@ static int mdpy_fb_probe(struct pci_dev *pdev, if (format != DRM_FORMAT_XRGB8888) { pci_err(pdev, "format mismatch (0x%x != 0x%x)\n", format, DRM_FORMAT_XRGB8888); - return -EINVAL; + ret = -EINVAL; + goto err_release_regions; } if (width < 100 || width > 10000) { pci_err(pdev, "width (%d) out of range\n", width); - return -EINVAL; + ret = -EINVAL; + goto err_release_regions; } if (height < 100 || height > 10000) { pci_err(pdev, "height (%d) out of range\n", height); - return -EINVAL; + ret = -EINVAL; + goto err_release_regions; } pci_info(pdev, "mdpy found: %dx%d framebuffer\n", width, height); info = framebuffer_alloc(sizeof(struct mdpy_fb_par), &pdev->dev); - if (!info) + if (!info) { + ret = -ENOMEM; goto err_release_regions; + } pci_set_drvdata(pdev, info); par = info->par; diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index dd87cea9fba7..a7883e455290 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -59,7 +59,7 @@ quiet_cmd_ld_ko_o = LD [M] $@ quiet_cmd_btf_ko = BTF [M] $@ cmd_btf_ko = \ if [ -f vmlinux ]; then \ - LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@; \ + LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J --btf_base vmlinux $@; \ else \ printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ fi; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index f4de4c97015b..0e0f6466b18d 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -240,7 +240,7 @@ gen_btf() fi info "BTF" ${2} - LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${extra_paholeopt} ${1} + LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${extra_paholeopt} ${1} # Create ${2} which contains just .BTF section but no symbols. Add # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h index f9b19524da11..1e9baa5c4fc6 100644 --- a/scripts/recordmcount.h +++ b/scripts/recordmcount.h @@ -192,15 +192,20 @@ static unsigned int get_symindex(Elf_Sym const *sym, Elf32_Word const *symtab, Elf32_Word const *symtab_shndx) { unsigned long offset; + unsigned short shndx = w2(sym->st_shndx); int index; - if (sym->st_shndx != SHN_XINDEX) - return w2(sym->st_shndx); + if (shndx > SHN_UNDEF && shndx < SHN_LORESERVE) + return shndx; - offset = (unsigned long)sym - (unsigned long)symtab; - index = offset / sizeof(*sym); + if (shndx == SHN_XINDEX) { + offset = (unsigned long)sym - (unsigned long)symtab; + index = offset / sizeof(*sym); - return w(symtab_shndx[index]); + return w(symtab_shndx[index]); + } + + return 0; } static unsigned int get_shnum(Elf_Ehdr const *ehdr, Elf_Shdr const *shdr0) diff --git a/sound/core/control_led.c b/sound/core/control_led.c index 25f57c14f294..a90e31dbde61 100644 --- a/sound/core/control_led.c +++ b/sound/core/control_led.c @@ -17,6 +17,9 @@ MODULE_LICENSE("GPL"); #define MAX_LED (((SNDRV_CTL_ELEM_ACCESS_MIC_LED - SNDRV_CTL_ELEM_ACCESS_SPK_LED) \ >> SNDRV_CTL_ELEM_ACCESS_LED_SHIFT) + 1) +#define to_led_card_dev(_dev) \ + container_of(_dev, struct snd_ctl_led_card, dev) + enum snd_ctl_led_mode { MODE_FOLLOW_MUTE = 0, MODE_FOLLOW_ROUTE, @@ -371,6 +374,21 @@ static void snd_ctl_led_disconnect(struct snd_card *card) snd_ctl_led_refresh(); } +static void snd_ctl_led_card_release(struct device *dev) +{ + struct snd_ctl_led_card *led_card = to_led_card_dev(dev); + + kfree(led_card); +} + +static void snd_ctl_led_release(struct device *dev) +{ +} + +static void snd_ctl_led_dev_release(struct device *dev) +{ +} + /* * sysfs */ @@ -663,6 +681,7 @@ static void snd_ctl_led_sysfs_add(struct snd_card *card) led_card->number = card->number; led_card->led = led; device_initialize(&led_card->dev); + led_card->dev.release = snd_ctl_led_card_release; if (dev_set_name(&led_card->dev, "card%d", card->number) < 0) goto cerr; led_card->dev.parent = &led->dev; @@ -681,7 +700,6 @@ cerr: put_device(&led_card->dev); cerr2: printk(KERN_ERR "snd_ctl_led: unable to add card%d", card->number); - kfree(led_card); } } @@ -700,8 +718,7 @@ static void snd_ctl_led_sysfs_remove(struct snd_card *card) snprintf(link_name, sizeof(link_name), "led-%s", led->name); sysfs_remove_link(&card->ctl_dev.kobj, link_name); sysfs_remove_link(&led_card->dev.kobj, "card"); - device_del(&led_card->dev); - kfree(led_card); + device_unregister(&led_card->dev); led->cards[card->number] = NULL; } } @@ -723,6 +740,7 @@ static int __init snd_ctl_led_init(void) device_initialize(&snd_ctl_led_dev); snd_ctl_led_dev.class = sound_class; + snd_ctl_led_dev.release = snd_ctl_led_dev_release; dev_set_name(&snd_ctl_led_dev, "ctl-led"); if (device_add(&snd_ctl_led_dev)) { put_device(&snd_ctl_led_dev); @@ -733,15 +751,16 @@ static int __init snd_ctl_led_init(void) INIT_LIST_HEAD(&led->controls); device_initialize(&led->dev); led->dev.parent = &snd_ctl_led_dev; + led->dev.release = snd_ctl_led_release; led->dev.groups = snd_ctl_led_dev_attr_groups; dev_set_name(&led->dev, led->name); if (device_add(&led->dev)) { put_device(&led->dev); for (; group > 0; group--) { led = &snd_ctl_leds[group - 1]; - device_del(&led->dev); + device_unregister(&led->dev); } - device_del(&snd_ctl_led_dev); + device_unregister(&snd_ctl_led_dev); return -ENOMEM; } } @@ -767,9 +786,9 @@ static void __exit snd_ctl_led_exit(void) } for (group = 0; group < MAX_LED; group++) { led = &snd_ctl_leds[group]; - device_del(&led->dev); + device_unregister(&led->dev); } - device_del(&snd_ctl_led_dev); + device_unregister(&snd_ctl_led_dev); snd_ctl_led_clean(NULL); } diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index 1645e4142e30..9863be6fd43e 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -297,8 +297,16 @@ int snd_seq_timer_open(struct snd_seq_queue *q) return err; } spin_lock_irq(&tmr->lock); - tmr->timeri = t; + if (tmr->timeri) + err = -EBUSY; + else + tmr->timeri = t; spin_unlock_irq(&tmr->lock); + if (err < 0) { + snd_timer_close(t); + snd_timer_instance_free(t); + return err; + } return 0; } diff --git a/sound/core/timer.c b/sound/core/timer.c index 6898b1ac0d7f..92b7008fcdb8 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -520,9 +520,10 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event) return; if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) return; + event += 10; /* convert to SNDRV_TIMER_EVENT_MXXX */ list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) - ts->ccallback(ts, event + 100, &tstamp, resolution); + ts->ccallback(ts, event, &tstamp, resolution); } /* start/continue a master timer */ diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index e0faa6601966..5805c5de39fb 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -804,7 +804,7 @@ static void generate_pkt_descs(struct amdtp_stream *s, struct pkt_desc *descs, static inline void cancel_stream(struct amdtp_stream *s) { s->packet_index = -1; - if (current_work() == &s->period_work) + if (in_interrupt()) amdtp_stream_pcm_abort(s); WRITE_ONCE(s->pcm_buffer_pointer, SNDRV_PCM_POS_XRUN); } diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index ab5ff7867eb9..d8be146793ee 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -331,6 +331,10 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x51c8, }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cc, + }, #endif }; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index a31009afc025..5462f771c2f9 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2917,6 +2917,7 @@ static int hda_codec_runtime_resume(struct device *dev) #ifdef CONFIG_PM_SLEEP static int hda_codec_pm_prepare(struct device *dev) { + dev->power.power_state = PMSG_SUSPEND; return pm_runtime_suspended(dev); } @@ -2924,6 +2925,10 @@ static void hda_codec_pm_complete(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); + /* If no other pm-functions are called between prepare() and complete() */ + if (dev->power.power_state.event == PM_EVENT_SUSPEND) + dev->power.power_state = PMSG_RESUME; + if (pm_runtime_suspended(dev) && (codec->jackpoll_interval || hda_codec_need_resume(codec) || codec->forced_resume)) pm_request_resume(dev); diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index b638fc2ef6f7..1f8018f9ce57 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3520,6 +3520,7 @@ static int cap_sw_put(struct snd_kcontrol *kcontrol, static const struct snd_kcontrol_new cap_sw_temp = { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = "Capture Switch", + .access = SNDRV_CTL_ELEM_ACCESS_READWRITE, .info = cap_sw_info, .get = cap_sw_get, .put = cap_sw_put, diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 79ade335c8a0..470753b36c8a 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2485,6 +2485,9 @@ static const struct pci_device_id azx_ids[] = { /* Alderlake-P */ { PCI_DEVICE(0x8086, 0x51c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Alderlake-M */ + { PCI_DEVICE(0x8086, 0x51cc), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Elkhart Lake */ { PCI_DEVICE(0x8086, 0x4b55), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 726507d0b04c..8629e84fef23 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -2206,10 +2206,9 @@ static void cs8409_cs42l42_fixups(struct hda_codec *codec, break; case HDA_FIXUP_ACT_PROBE: - /* Set initial volume on Bullseye to -26 dB */ - if (codec->fixup_id == CS8409_BULLSEYE) - snd_hda_codec_amp_init_stereo(codec, CS8409_CS42L42_DMIC_ADC_PIN_NID, - HDA_INPUT, 0, 0xff, 0x19); + /* Set initial DMIC volume to -26 dB */ + snd_hda_codec_amp_init_stereo(codec, CS8409_CS42L42_DMIC_ADC_PIN_NID, + HDA_INPUT, 0, 0xff, 0x19); snd_hda_gen_add_kctl(&spec->gen, NULL, &cs8409_cs42l42_hp_volume_mixer); snd_hda_gen_add_kctl(&spec->gen, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 552e2cb73291..ab5113cccffa 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2603,6 +2603,28 @@ static const struct hda_model_fixup alc882_fixup_models[] = { {} }; +static const struct snd_hda_pin_quirk alc882_pin_fixup_tbl[] = { + SND_HDA_PIN_QUIRK(0x10ec1220, 0x1043, "ASUS", ALC1220_FIXUP_CLEVO_P950, + {0x14, 0x01014010}, + {0x15, 0x01011012}, + {0x16, 0x01016011}, + {0x18, 0x01a19040}, + {0x19, 0x02a19050}, + {0x1a, 0x0181304f}, + {0x1b, 0x0221401f}, + {0x1e, 0x01456130}), + SND_HDA_PIN_QUIRK(0x10ec1220, 0x1462, "MS-7C35", ALC1220_FIXUP_CLEVO_P950, + {0x14, 0x01015010}, + {0x15, 0x01011012}, + {0x16, 0x01011011}, + {0x18, 0x01a11040}, + {0x19, 0x02a19050}, + {0x1a, 0x0181104f}, + {0x1b, 0x0221401f}, + {0x1e, 0x01451130}), + {} +}; + /* * BIOS auto configuration */ @@ -2644,6 +2666,7 @@ static int patch_alc882(struct hda_codec *codec) snd_hda_pick_fixup(codec, alc882_fixup_models, alc882_fixup_tbl, alc882_fixups); + snd_hda_pick_pin_fixup(codec, alc882_pin_fixup_tbl, alc882_fixups, true); snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE); alc_auto_parse_customize_define(codec); @@ -6543,6 +6566,9 @@ enum { ALC295_FIXUP_ASUS_DACS, ALC295_FIXUP_HP_OMEN, ALC285_FIXUP_HP_SPECTRE_X360, + ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, + ALC623_FIXUP_LENOVO_THINKSTATION_P340, + ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -8109,6 +8135,27 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_SPEAKER2_TO_DAC1, }, + [ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_ideapad_s740_coef, + .chained = true, + .chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK, + }, + [ALC623_FIXUP_LENOVO_THINKSTATION_P340] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_no_shutup, + .chained = true, + .chain_id = ALC283_FIXUP_HEADSET_MIC, + }, + [ALC255_FIXUP_ACER_HEADPHONE_AND_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x21, 0x03211030 }, /* Change the Headphone location to Left */ + { } + }, + .chained = true, + .chain_id = ALC255_FIXUP_XIAOMI_HEADSET_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8145,6 +8192,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X), @@ -8266,12 +8314,15 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x82bf, "HP G3 mini", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO), + SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), @@ -8290,7 +8341,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), SND_PCI_QUIRK(0x103c, 0x8846, "HP EliteBook 850 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x884b, "HP EliteBook 840 Aero G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x884c, "HP EliteBook 840 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x886d, "HP ZBook Fury 17.3 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x888d, "HP ZBook Power 15.6 inch G8 Mobile Workstation PC", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), @@ -8427,7 +8484,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0xc019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xc022, "Clevo NH77[DC][QW]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), - SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), @@ -8477,6 +8534,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), + SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -8692,6 +8750,9 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC245_FIXUP_HP_X360_AMP, .name = "alc245-hp-x360-amp"}, {.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"}, + {.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"}, + {.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"}, + {.id = ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, .name = "alc255-acer-headphone-and-mic"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c index f22bb2bdf527..8148b0d22e88 100644 --- a/sound/soc/amd/raven/acp3x-pcm-dma.c +++ b/sound/soc/amd/raven/acp3x-pcm-dma.c @@ -235,10 +235,6 @@ static int acp3x_dma_open(struct snd_soc_component *component, return ret; } - if (!adata->play_stream && !adata->capture_stream && - !adata->i2ssp_play_stream && !adata->i2ssp_capture_stream) - rv_writel(1, adata->acp3x_base + mmACP_EXTERNAL_INTR_ENB); - i2s_data->acp3x_base = adata->acp3x_base; runtime->private_data = i2s_data; return ret; @@ -365,12 +361,6 @@ static int acp3x_dma_close(struct snd_soc_component *component, } } - /* Disable ACP irq, when the current stream is being closed and - * another stream is also not active. - */ - if (!adata->play_stream && !adata->capture_stream && - !adata->i2ssp_play_stream && !adata->i2ssp_capture_stream) - rv_writel(0, adata->acp3x_base + mmACP_EXTERNAL_INTR_ENB); return 0; } diff --git a/sound/soc/amd/raven/acp3x.h b/sound/soc/amd/raven/acp3x.h index 03fe93913e12..c3f0c8b7545d 100644 --- a/sound/soc/amd/raven/acp3x.h +++ b/sound/soc/amd/raven/acp3x.h @@ -77,6 +77,7 @@ #define ACP_POWER_OFF_IN_PROGRESS 0x03 #define ACP3x_ITER_IRER_SAMP_LEN_MASK 0x38 +#define ACP_EXT_INTR_STAT_CLEAR_MASK 0xFFFFFFFF struct acp3x_platform_info { u16 play_i2s_instance; diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c index d3536fd6a124..a013a607b3d4 100644 --- a/sound/soc/amd/raven/pci-acp3x.c +++ b/sound/soc/amd/raven/pci-acp3x.c @@ -76,6 +76,19 @@ static int acp3x_reset(void __iomem *acp3x_base) return -ETIMEDOUT; } +static void acp3x_enable_interrupts(void __iomem *acp_base) +{ + rv_writel(0x01, acp_base + mmACP_EXTERNAL_INTR_ENB); +} + +static void acp3x_disable_interrupts(void __iomem *acp_base) +{ + rv_writel(ACP_EXT_INTR_STAT_CLEAR_MASK, acp_base + + mmACP_EXTERNAL_INTR_STAT); + rv_writel(0x00, acp_base + mmACP_EXTERNAL_INTR_CNTL); + rv_writel(0x00, acp_base + mmACP_EXTERNAL_INTR_ENB); +} + static int acp3x_init(struct acp3x_dev_data *adata) { void __iomem *acp3x_base = adata->acp3x_base; @@ -93,6 +106,7 @@ static int acp3x_init(struct acp3x_dev_data *adata) pr_err("ACP3x reset failed\n"); return ret; } + acp3x_enable_interrupts(acp3x_base); return 0; } @@ -100,6 +114,7 @@ static int acp3x_deinit(void __iomem *acp3x_base) { int ret; + acp3x_disable_interrupts(acp3x_base); /* Reset */ ret = acp3x_reset(acp3x_base); if (ret) { diff --git a/sound/soc/codecs/ak5558.c b/sound/soc/codecs/ak5558.c index 34aed80db0eb..37d4600b6f2c 100644 --- a/sound/soc/codecs/ak5558.c +++ b/sound/soc/codecs/ak5558.c @@ -307,7 +307,7 @@ static struct snd_soc_dai_driver ak5558_dai = { }; static struct snd_soc_dai_driver ak5552_dai = { - .name = "ak5558-aif", + .name = "ak5552-aif", .capture = { .stream_name = "Capture", .channels_min = 1, diff --git a/sound/soc/codecs/cs35l32.c b/sound/soc/codecs/cs35l32.c index f4067230ac42..88e79b9f52ed 100644 --- a/sound/soc/codecs/cs35l32.c +++ b/sound/soc/codecs/cs35l32.c @@ -261,6 +261,9 @@ static const struct regmap_config cs35l32_regmap = { .readable_reg = cs35l32_readable_register, .precious_reg = cs35l32_precious_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs35l32_handle_of_data(struct i2c_client *i2c_client, diff --git a/sound/soc/codecs/cs35l33.c b/sound/soc/codecs/cs35l33.c index 7ad7b733af9b..e8f3dcfd144d 100644 --- a/sound/soc/codecs/cs35l33.c +++ b/sound/soc/codecs/cs35l33.c @@ -1201,6 +1201,7 @@ static int cs35l33_i2c_probe(struct i2c_client *i2c_client, dev_err(&i2c_client->dev, "CS35L33 Device ID (%X). Expected ID %X\n", devid, CS35L33_CHIP_ID); + ret = -EINVAL; goto err_enable; } diff --git a/sound/soc/codecs/cs35l34.c b/sound/soc/codecs/cs35l34.c index 110ee2d06358..3d3c3c34dfe2 100644 --- a/sound/soc/codecs/cs35l34.c +++ b/sound/soc/codecs/cs35l34.c @@ -800,6 +800,9 @@ static struct regmap_config cs35l34_regmap = { .readable_reg = cs35l34_readable_register, .precious_reg = cs35l34_precious_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs35l34_handle_of_data(struct i2c_client *i2c_client, diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index bf982e145e94..77473c226f9e 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -399,6 +399,9 @@ static const struct regmap_config cs42l42_regmap = { .reg_defaults = cs42l42_reg_defaults, .num_reg_defaults = ARRAY_SIZE(cs42l42_reg_defaults), .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static DECLARE_TLV_DB_SCALE(adc_tlv, -9600, 100, false); diff --git a/sound/soc/codecs/cs42l56.c b/sound/soc/codecs/cs42l56.c index c44a5cdb796e..7cdffdf6b8cf 100644 --- a/sound/soc/codecs/cs42l56.c +++ b/sound/soc/codecs/cs42l56.c @@ -1175,7 +1175,7 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client, struct cs42l56_platform_data *pdata = dev_get_platdata(&i2c_client->dev); int ret, i; - unsigned int devid = 0; + unsigned int devid; unsigned int alpha_rev, metal_rev; unsigned int reg; @@ -1245,6 +1245,11 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client, } ret = regmap_read(cs42l56->regmap, CS42L56_CHIP_ID_1, ®); + if (ret) { + dev_err(&i2c_client->dev, "Failed to read chip ID: %d\n", ret); + return ret; + } + devid = reg & CS42L56_CHIP_ID_MASK; if (devid != CS42L56_DEVID) { dev_err(&i2c_client->dev, diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c index c3f974ec78e5..e92bacaab53f 100644 --- a/sound/soc/codecs/cs42l73.c +++ b/sound/soc/codecs/cs42l73.c @@ -1268,6 +1268,9 @@ static const struct regmap_config cs42l73_regmap = { .volatile_reg = cs42l73_volatile_register, .readable_reg = cs42l73_readable_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs42l73_i2c_probe(struct i2c_client *i2c_client, diff --git a/sound/soc/codecs/cs53l30.c b/sound/soc/codecs/cs53l30.c index 3d67cbf9eaaa..abe0cc0bc03a 100644 --- a/sound/soc/codecs/cs53l30.c +++ b/sound/soc/codecs/cs53l30.c @@ -912,6 +912,9 @@ static struct regmap_config cs53l30_regmap = { .writeable_reg = cs53l30_writeable_register, .readable_reg = cs53l30_readable_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs53l30_i2c_probe(struct i2c_client *client, diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c index bd3c523a8617..13009d08b09a 100644 --- a/sound/soc/codecs/da7219.c +++ b/sound/soc/codecs/da7219.c @@ -2181,10 +2181,7 @@ static int da7219_register_dai_clks(struct snd_soc_component *component) ret); goto err; } - - da7219->dai_clks[i] = devm_clk_hw_get_clk(dev, dai_clk_hw, NULL); - if (IS_ERR(da7219->dai_clks[i])) - return PTR_ERR(da7219->dai_clks[i]); + da7219->dai_clks[i] = dai_clk_hw->clk; /* For DT setup onecell data, otherwise create lookup */ if (np) { diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index b0ebfc8d180c..171ab7f519c0 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -3579,6 +3579,7 @@ static const struct of_device_id rx_macro_dt_match[] = { { .compatible = "qcom,sm8250-lpass-rx-macro" }, { } }; +MODULE_DEVICE_TABLE(of, rx_macro_dt_match); static struct platform_driver rx_macro_driver = { .driver = { diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index acd2fbc0ca7c..27a0d5defd27 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -1846,6 +1846,7 @@ static const struct of_device_id tx_macro_dt_match[] = { { .compatible = "qcom,sm8250-lpass-tx-macro" }, { } }; +MODULE_DEVICE_TABLE(of, tx_macro_dt_match); static struct platform_driver tx_macro_driver = { .driver = { .name = "tx_macro", diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c index 4be24e7f51c8..f8e49e45ce33 100644 --- a/sound/soc/codecs/max98088.c +++ b/sound/soc/codecs/max98088.c @@ -41,6 +41,7 @@ struct max98088_priv { enum max98088_type devtype; struct max98088_pdata *pdata; struct clk *mclk; + unsigned char mclk_prescaler; unsigned int sysclk; struct max98088_cdata dai[2]; int eq_textcnt; @@ -998,13 +999,16 @@ static int max98088_dai1_hw_params(struct snd_pcm_substream *substream, /* Configure NI when operating as master */ if (snd_soc_component_read(component, M98088_REG_14_DAI1_FORMAT) & M98088_DAI_MAS) { + unsigned long pclk; + if (max98088->sysclk == 0) { dev_err(component->dev, "Invalid system clock frequency\n"); return -EINVAL; } ni = 65536ULL * (rate < 50000 ? 96ULL : 48ULL) * (unsigned long long int)rate; - do_div(ni, (unsigned long long int)max98088->sysclk); + pclk = DIV_ROUND_CLOSEST(max98088->sysclk, max98088->mclk_prescaler); + ni = DIV_ROUND_CLOSEST_ULL(ni, pclk); snd_soc_component_write(component, M98088_REG_12_DAI1_CLKCFG_HI, (ni >> 8) & 0x7F); snd_soc_component_write(component, M98088_REG_13_DAI1_CLKCFG_LO, @@ -1065,13 +1069,16 @@ static int max98088_dai2_hw_params(struct snd_pcm_substream *substream, /* Configure NI when operating as master */ if (snd_soc_component_read(component, M98088_REG_1C_DAI2_FORMAT) & M98088_DAI_MAS) { + unsigned long pclk; + if (max98088->sysclk == 0) { dev_err(component->dev, "Invalid system clock frequency\n"); return -EINVAL; } ni = 65536ULL * (rate < 50000 ? 96ULL : 48ULL) * (unsigned long long int)rate; - do_div(ni, (unsigned long long int)max98088->sysclk); + pclk = DIV_ROUND_CLOSEST(max98088->sysclk, max98088->mclk_prescaler); + ni = DIV_ROUND_CLOSEST_ULL(ni, pclk); snd_soc_component_write(component, M98088_REG_1A_DAI2_CLKCFG_HI, (ni >> 8) & 0x7F); snd_soc_component_write(component, M98088_REG_1B_DAI2_CLKCFG_LO, @@ -1113,8 +1120,10 @@ static int max98088_dai_set_sysclk(struct snd_soc_dai *dai, */ if ((freq >= 10000000) && (freq < 20000000)) { snd_soc_component_write(component, M98088_REG_10_SYS_CLK, 0x10); + max98088->mclk_prescaler = 1; } else if ((freq >= 20000000) && (freq < 30000000)) { snd_soc_component_write(component, M98088_REG_10_SYS_CLK, 0x20); + max98088->mclk_prescaler = 2; } else { dev_err(component->dev, "Invalid master clock frequency\n"); return -EINVAL; diff --git a/sound/soc/codecs/rt5659.c b/sound/soc/codecs/rt5659.c index 87f5709fe2cc..4a50b169fe03 100644 --- a/sound/soc/codecs/rt5659.c +++ b/sound/soc/codecs/rt5659.c @@ -2433,13 +2433,18 @@ static int set_dmic_power(struct snd_soc_dapm_widget *w, return 0; } -static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { +static const struct snd_soc_dapm_widget rt5659_particular_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("LDO2", RT5659_PWR_ANLG_3, RT5659_PWR_LDO2_BIT, 0, NULL, 0), - SND_SOC_DAPM_SUPPLY("PLL", RT5659_PWR_ANLG_3, RT5659_PWR_PLL_BIT, 0, - NULL, 0), + SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5659_PWR_ANLG_2, RT5659_PWR_MB1_BIT, + 0, NULL, 0), SND_SOC_DAPM_SUPPLY("Mic Det Power", RT5659_PWR_VOL, RT5659_PWR_MIC_DET_BIT, 0, NULL, 0), +}; + +static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { + SND_SOC_DAPM_SUPPLY("PLL", RT5659_PWR_ANLG_3, RT5659_PWR_PLL_BIT, 0, + NULL, 0), SND_SOC_DAPM_SUPPLY("Mono Vref", RT5659_PWR_ANLG_1, RT5659_PWR_VREF3_BIT, 0, NULL, 0), @@ -2464,8 +2469,6 @@ static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { RT5659_ADC_MONO_R_ASRC_SFT, 0, NULL, 0), /* Input Side */ - SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5659_PWR_ANLG_2, RT5659_PWR_MB1_BIT, - 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MICBIAS2", RT5659_PWR_ANLG_2, RT5659_PWR_MB2_BIT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MICBIAS3", RT5659_PWR_ANLG_2, RT5659_PWR_MB3_BIT, @@ -3660,10 +3663,23 @@ static int rt5659_set_bias_level(struct snd_soc_component *component, static int rt5659_probe(struct snd_soc_component *component) { + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); struct rt5659_priv *rt5659 = snd_soc_component_get_drvdata(component); rt5659->component = component; + switch (rt5659->pdata.jd_src) { + case RT5659_JD_HDA_HEADER: + break; + + default: + snd_soc_dapm_new_controls(dapm, + rt5659_particular_dapm_widgets, + ARRAY_SIZE(rt5659_particular_dapm_widgets)); + break; + } + return 0; } diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index fed80c8f994f..e78ba3b064c4 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -462,7 +462,8 @@ static int rt5682_io_init(struct device *dev, struct sdw_slave *slave) regmap_update_bits(rt5682->regmap, RT5682_CBJ_CTRL_2, RT5682_EXT_JD_SRC, RT5682_EXT_JD_SRC_MANUAL); - regmap_write(rt5682->regmap, RT5682_CBJ_CTRL_1, 0xd042); + regmap_write(rt5682->regmap, RT5682_CBJ_CTRL_1, 0xd142); + regmap_update_bits(rt5682->regmap, RT5682_CBJ_CTRL_5, 0x0700, 0x0600); regmap_update_bits(rt5682->regmap, RT5682_CBJ_CTRL_3, RT5682_CBJ_IN_BUF_EN, RT5682_CBJ_IN_BUF_EN); regmap_update_bits(rt5682->regmap, RT5682_SAR_IL_CMD_1, diff --git a/sound/soc/codecs/rt711-sdca.c b/sound/soc/codecs/rt711-sdca.c index cc36739f7fcf..24a084e0b48a 100644 --- a/sound/soc/codecs/rt711-sdca.c +++ b/sound/soc/codecs/rt711-sdca.c @@ -683,13 +683,13 @@ static int rt711_sdca_set_fu1e_capture_ctl(struct rt711_sdca_priv *rt711) ch_r = (rt711->fu1e_dapm_mute || rt711->fu1e_mixer_r_mute) ? 0x01 : 0x00; err = regmap_write(rt711->regmap, - SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT711_SDCA_ENT_USER_FU1E, + SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT711_SDCA_ENT_USER_FU1E, RT711_SDCA_CTL_FU_MUTE, CH_L), ch_l); if (err < 0) return err; err = regmap_write(rt711->regmap, - SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT711_SDCA_ENT_USER_FU1E, + SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT711_SDCA_ENT_USER_FU1E, RT711_SDCA_CTL_FU_MUTE, CH_R), ch_r); if (err < 0) return err; diff --git a/sound/soc/codecs/sti-sas.c b/sound/soc/codecs/sti-sas.c index ffdf7e559515..82a24e330065 100644 --- a/sound/soc/codecs/sti-sas.c +++ b/sound/soc/codecs/sti-sas.c @@ -408,6 +408,7 @@ static const struct of_device_id sti_sas_dev_match[] = { }, {}, }; +MODULE_DEVICE_TABLE(of, sti_sas_dev_match); static int sti_sas_driver_probe(struct platform_device *pdev) { diff --git a/sound/soc/codecs/tas2562.h b/sound/soc/codecs/tas2562.h index 81866aeb3fbf..55b2a1f52ca3 100644 --- a/sound/soc/codecs/tas2562.h +++ b/sound/soc/codecs/tas2562.h @@ -57,13 +57,13 @@ #define TAS2562_TDM_CFG0_RAMPRATE_MASK BIT(5) #define TAS2562_TDM_CFG0_RAMPRATE_44_1 BIT(5) #define TAS2562_TDM_CFG0_SAMPRATE_MASK GENMASK(3, 1) -#define TAS2562_TDM_CFG0_SAMPRATE_7305_8KHZ 0x0 -#define TAS2562_TDM_CFG0_SAMPRATE_14_7_16KHZ 0x1 -#define TAS2562_TDM_CFG0_SAMPRATE_22_05_24KHZ 0x2 -#define TAS2562_TDM_CFG0_SAMPRATE_29_4_32KHZ 0x3 -#define TAS2562_TDM_CFG0_SAMPRATE_44_1_48KHZ 0x4 -#define TAS2562_TDM_CFG0_SAMPRATE_88_2_96KHZ 0x5 -#define TAS2562_TDM_CFG0_SAMPRATE_176_4_192KHZ 0x6 +#define TAS2562_TDM_CFG0_SAMPRATE_7305_8KHZ (0x0 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_14_7_16KHZ (0x1 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_22_05_24KHZ (0x2 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_29_4_32KHZ (0x3 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_44_1_48KHZ (0x4 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_88_2_96KHZ (0x5 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_176_4_192KHZ (0x6 << 1) #define TAS2562_TDM_CFG2_RIGHT_JUSTIFY BIT(6) diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 0917d65d6921..556c284f49dd 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -119,6 +119,7 @@ config SND_SOC_FSL_RPMSG tristate "NXP Audio Base On RPMSG support" depends on COMMON_CLK depends on RPMSG + depends on SND_IMX_SOC || SND_IMX_SOC = n select SND_SOC_IMX_RPMSG if SND_IMX_SOC != n help Say Y if you want to add rpmsg audio support for the Freescale CPUs. diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index c62bfd1c3ac7..4f55b316cf0f 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -744,6 +744,7 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) /* Initialize sound card */ priv->pdev = pdev; priv->card.dev = &pdev->dev; + priv->card.owner = THIS_MODULE; ret = snd_soc_of_parse_card_name(&priv->card, "model"); if (ret) { snprintf(priv->name, sizeof(priv->name), "%s-audio", diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index 2c8a2fcb7922..5e71382467e8 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -209,7 +209,7 @@ static void graph_parse_mclk_fs(struct device_node *top, static int graph_parse_node(struct asoc_simple_priv *priv, struct device_node *ep, struct link_info *li, - int is_cpu) + int *cpu) { struct device *dev = simple_priv_to_dev(priv); struct device_node *top = dev->of_node; @@ -217,9 +217,9 @@ static int graph_parse_node(struct asoc_simple_priv *priv, struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); struct snd_soc_dai_link_component *dlc; struct asoc_simple_dai *dai; - int ret, single = 0; + int ret; - if (is_cpu) { + if (cpu) { dlc = asoc_link_to_cpu(dai_link, 0); dai = simple_props_to_dai_cpu(dai_props, 0); } else { @@ -229,7 +229,7 @@ static int graph_parse_node(struct asoc_simple_priv *priv, graph_parse_mclk_fs(top, ep, dai_props); - ret = asoc_simple_parse_dai(ep, dlc, &single); + ret = asoc_simple_parse_dai(ep, dlc, cpu); if (ret < 0) return ret; @@ -241,9 +241,6 @@ static int graph_parse_node(struct asoc_simple_priv *priv, if (ret < 0) return ret; - if (is_cpu) - asoc_simple_canonicalize_cpu(dlc, single); - return 0; } @@ -276,33 +273,29 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, struct link_info *li) { struct device *dev = simple_priv_to_dev(priv); - struct snd_soc_card *card = simple_priv_to_card(priv); struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); struct device_node *top = dev->of_node; struct device_node *ep = li->cpu ? cpu_ep : codec_ep; - struct device_node *port; - struct device_node *ports; - struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); - struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); char dai_name[64]; int ret; - port = of_get_parent(ep); - ports = of_get_parent(port); - dev_dbg(dev, "link_of DPCM (%pOF)\n", ep); if (li->cpu) { + struct snd_soc_card *card = simple_priv_to_card(priv); + struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); + int is_single_links = 0; + /* Codec is dummy */ /* FE settings */ dai_link->dynamic = 1; dai_link->dpcm_merged_format = 1; - ret = graph_parse_node(priv, cpu_ep, li, 1); + ret = graph_parse_node(priv, cpu_ep, li, &is_single_links); if (ret) - goto out_put_node; + return ret; snprintf(dai_name, sizeof(dai_name), "fe.%pOFP.%s", cpus->of_node, cpus->dai_name); @@ -318,8 +311,13 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, */ if (card->component_chaining && !soc_component_is_pcm(cpus)) dai_link->no_pcm = 1; + + asoc_simple_canonicalize_cpu(cpus, is_single_links); } else { - struct snd_soc_codec_conf *cconf; + struct snd_soc_codec_conf *cconf = simple_props_to_codec_conf(dai_props, 0); + struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); + struct device_node *port; + struct device_node *ports; /* CPU is dummy */ @@ -327,22 +325,25 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, dai_link->no_pcm = 1; dai_link->be_hw_params_fixup = asoc_simple_be_hw_params_fixup; - cconf = simple_props_to_codec_conf(dai_props, 0); - - ret = graph_parse_node(priv, codec_ep, li, 0); + ret = graph_parse_node(priv, codec_ep, li, NULL); if (ret < 0) - goto out_put_node; + return ret; snprintf(dai_name, sizeof(dai_name), "be.%pOFP.%s", codecs->of_node, codecs->dai_name); /* check "prefix" from top node */ + port = of_get_parent(ep); + ports = of_get_parent(port); snd_soc_of_parse_node_prefix(top, cconf, codecs->of_node, "prefix"); if (of_node_name_eq(ports, "ports")) snd_soc_of_parse_node_prefix(ports, cconf, codecs->of_node, "prefix"); snd_soc_of_parse_node_prefix(port, cconf, codecs->of_node, "prefix"); + + of_node_put(ports); + of_node_put(port); } graph_parse_convert(dev, ep, &dai_props->adata); @@ -351,11 +352,8 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, ret = graph_link_init(priv, cpu_ep, codec_ep, li, dai_name); -out_put_node: li->link++; - of_node_put(ports); - of_node_put(port); return ret; } @@ -369,20 +367,23 @@ static int graph_dai_link_of(struct asoc_simple_priv *priv, struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); char dai_name[64]; - int ret; + int ret, is_single_links = 0; dev_dbg(dev, "link_of (%pOF)\n", cpu_ep); - ret = graph_parse_node(priv, cpu_ep, li, 1); + ret = graph_parse_node(priv, cpu_ep, li, &is_single_links); if (ret < 0) return ret; - ret = graph_parse_node(priv, codec_ep, li, 0); + ret = graph_parse_node(priv, codec_ep, li, NULL); if (ret < 0) return ret; snprintf(dai_name, sizeof(dai_name), "%s-%s", cpus->dai_name, codecs->dai_name); + + asoc_simple_canonicalize_cpu(cpus, is_single_links); + ret = graph_link_init(priv, cpu_ep, codec_ep, li, dai_name); if (ret < 0) return ret; diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index a1373be4558f..0015f534d42d 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -93,12 +93,11 @@ static void simple_parse_convert(struct device *dev, } static void simple_parse_mclk_fs(struct device_node *top, - struct device_node *cpu, - struct device_node *codec, + struct device_node *np, struct simple_dai_props *props, char *prefix) { - struct device_node *node = of_get_parent(cpu); + struct device_node *node = of_get_parent(np); char prop[128]; snprintf(prop, sizeof(prop), "%smclk-fs", PREFIX); @@ -106,12 +105,71 @@ static void simple_parse_mclk_fs(struct device_node *top, snprintf(prop, sizeof(prop), "%smclk-fs", prefix); of_property_read_u32(node, prop, &props->mclk_fs); - of_property_read_u32(cpu, prop, &props->mclk_fs); - of_property_read_u32(codec, prop, &props->mclk_fs); + of_property_read_u32(np, prop, &props->mclk_fs); of_node_put(node); } +static int simple_parse_node(struct asoc_simple_priv *priv, + struct device_node *np, + struct link_info *li, + char *prefix, + int *cpu) +{ + struct device *dev = simple_priv_to_dev(priv); + struct device_node *top = dev->of_node; + struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); + struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); + struct snd_soc_dai_link_component *dlc; + struct asoc_simple_dai *dai; + int ret; + + if (cpu) { + dlc = asoc_link_to_cpu(dai_link, 0); + dai = simple_props_to_dai_cpu(dai_props, 0); + } else { + dlc = asoc_link_to_codec(dai_link, 0); + dai = simple_props_to_dai_codec(dai_props, 0); + } + + simple_parse_mclk_fs(top, np, dai_props, prefix); + + ret = asoc_simple_parse_dai(np, dlc, cpu); + if (ret) + return ret; + + ret = asoc_simple_parse_clk(dev, np, dai, dlc); + if (ret) + return ret; + + ret = asoc_simple_parse_tdm(np, dai); + if (ret) + return ret; + + return 0; +} + +static int simple_link_init(struct asoc_simple_priv *priv, + struct device_node *node, + struct device_node *codec, + struct link_info *li, + char *prefix, char *name) +{ + struct device *dev = simple_priv_to_dev(priv); + struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); + int ret; + + ret = asoc_simple_parse_daifmt(dev, node, codec, + prefix, &dai_link->dai_fmt); + if (ret < 0) + return 0; + + dai_link->init = asoc_simple_dai_init; + dai_link->ops = &simple_ops; + + return asoc_simple_set_dailink_name(dev, dai_link, name); +} + static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, struct device_node *np, struct device_node *codec, @@ -121,24 +179,21 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, struct device *dev = simple_priv_to_dev(priv); struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct asoc_simple_dai *dai; - struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); - struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); - struct snd_soc_dai_link_component *platforms = asoc_link_to_platform(dai_link, 0); struct device_node *top = dev->of_node; struct device_node *node = of_get_parent(np); char *prefix = ""; + char dai_name[64]; int ret; dev_dbg(dev, "link_of DPCM (%pOF)\n", np); - li->link++; - /* For single DAI link & old style of DT node */ if (is_top) prefix = PREFIX; if (li->cpu) { + struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); + struct snd_soc_dai_link_component *platforms = asoc_link_to_platform(dai_link, 0); int is_single_links = 0; /* Codec is dummy */ @@ -147,25 +202,16 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, dai_link->dynamic = 1; dai_link->dpcm_merged_format = 1; - dai = simple_props_to_dai_cpu(dai_props, 0); - - ret = asoc_simple_parse_dai(np, cpus, &is_single_links); - if (ret) - goto out_put_node; - - ret = asoc_simple_parse_clk(dev, np, dai, cpus); + ret = simple_parse_node(priv, np, li, prefix, &is_single_links); if (ret < 0) goto out_put_node; - ret = asoc_simple_set_dailink_name(dev, dai_link, - "fe.%s", - cpus->dai_name); - if (ret < 0) - goto out_put_node; + snprintf(dai_name, sizeof(dai_name), "fe.%s", cpus->dai_name); asoc_simple_canonicalize_cpu(cpus, is_single_links); asoc_simple_canonicalize_platform(platforms, cpus); } else { + struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); struct snd_soc_codec_conf *cconf; /* CPU is dummy */ @@ -174,22 +220,13 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, dai_link->no_pcm = 1; dai_link->be_hw_params_fixup = asoc_simple_be_hw_params_fixup; - dai = simple_props_to_dai_codec(dai_props, 0); cconf = simple_props_to_codec_conf(dai_props, 0); - ret = asoc_simple_parse_dai(np, codecs, NULL); + ret = simple_parse_node(priv, np, li, prefix, NULL); if (ret < 0) goto out_put_node; - ret = asoc_simple_parse_clk(dev, np, dai, codecs); - if (ret < 0) - goto out_put_node; - - ret = asoc_simple_set_dailink_name(dev, dai_link, - "be.%s", - codecs->dai_name); - if (ret < 0) - goto out_put_node; + snprintf(dai_name, sizeof(dai_name), "be.%s", codecs->dai_name); /* check "prefix" from top node */ snd_soc_of_parse_node_prefix(top, cconf, codecs->of_node, @@ -201,23 +238,14 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, } simple_parse_convert(dev, np, &dai_props->adata); - simple_parse_mclk_fs(top, np, codec, dai_props, prefix); - - ret = asoc_simple_parse_tdm(np, dai); - if (ret) - goto out_put_node; - - ret = asoc_simple_parse_daifmt(dev, node, codec, - prefix, &dai_link->dai_fmt); - if (ret < 0) - goto out_put_node; snd_soc_dai_link_set_capabilities(dai_link); - dai_link->ops = &simple_ops; - dai_link->init = asoc_simple_dai_init; + ret = simple_link_init(priv, node, codec, li, prefix, dai_name); out_put_node: + li->link++; + of_node_put(node); return ret; } @@ -230,23 +258,19 @@ static int simple_dai_link_of(struct asoc_simple_priv *priv, { struct device *dev = simple_priv_to_dev(priv); struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); - struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct asoc_simple_dai *cpu_dai = simple_props_to_dai_cpu(dai_props, 0); - struct asoc_simple_dai *codec_dai = simple_props_to_dai_codec(dai_props, 0); struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); struct snd_soc_dai_link_component *platforms = asoc_link_to_platform(dai_link, 0); - struct device_node *top = dev->of_node; struct device_node *cpu = NULL; struct device_node *node = NULL; struct device_node *plat = NULL; + char dai_name[64]; char prop[128]; char *prefix = ""; int ret, single_cpu = 0; cpu = np; node = of_get_parent(np); - li->link++; dev_dbg(dev, "link_of (%pOF)\n", node); @@ -257,18 +281,11 @@ static int simple_dai_link_of(struct asoc_simple_priv *priv, snprintf(prop, sizeof(prop), "%splat", prefix); plat = of_get_child_by_name(node, prop); - ret = asoc_simple_parse_daifmt(dev, node, codec, - prefix, &dai_link->dai_fmt); - if (ret < 0) - goto dai_link_of_err; - - simple_parse_mclk_fs(top, cpu, codec, dai_props, prefix); - - ret = asoc_simple_parse_dai(cpu, cpus, &single_cpu); + ret = simple_parse_node(priv, cpu, li, prefix, &single_cpu); if (ret < 0) goto dai_link_of_err; - ret = asoc_simple_parse_dai(codec, codecs, NULL); + ret = simple_parse_node(priv, codec, li, prefix, NULL); if (ret < 0) goto dai_link_of_err; @@ -276,39 +293,20 @@ static int simple_dai_link_of(struct asoc_simple_priv *priv, if (ret < 0) goto dai_link_of_err; - ret = asoc_simple_parse_tdm(cpu, cpu_dai); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_parse_tdm(codec, codec_dai); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_parse_clk(dev, cpu, cpu_dai, cpus); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_parse_clk(dev, codec, codec_dai, codecs); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_set_dailink_name(dev, dai_link, - "%s-%s", - cpus->dai_name, - codecs->dai_name); - if (ret < 0) - goto dai_link_of_err; - - dai_link->ops = &simple_ops; - dai_link->init = asoc_simple_dai_init; + snprintf(dai_name, sizeof(dai_name), + "%s-%s", cpus->dai_name, codecs->dai_name); asoc_simple_canonicalize_cpu(cpus, single_cpu); asoc_simple_canonicalize_platform(platforms, cpus); + ret = simple_link_init(priv, node, codec, li, prefix, dai_name); + dai_link_of_err: of_node_put(plat); of_node_put(node); + li->link++; + return ret; } diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index df2f5d55e8ff..22dbd9d93c1e 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -574,6 +574,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* Glavey TM800A550L */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* Above strings are too generic, also match on BIOS version */ + DMI_MATCH(DMI_BIOS_VERSION, "ZY-8-BI-PX4S70VTR400-X423B-005-D"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), @@ -652,6 +663,20 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_MONO_SPEAKER | BYT_RT5640_MCLK_EN), }, + { /* Lenovo Miix 3-830 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 3-830"), + }, + .driver_data = (void *)(BYT_RT5640_IN1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Linx Linx7 tablet */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LINX"), diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index c62d2612e8f5..a6e95db6b3fb 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -93,8 +93,30 @@ static void lpass_cpu_daiops_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); + struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; + unsigned int id = dai->driver->id; clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]); + /* + * Ensure LRCLK is disabled even in device node validation. + * Will not impact if disabled in lpass_cpu_daiops_trigger() + * suspend. + */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_DISABLE); + else + regmap_fields_write(i2sctl->micen, id, LPAIF_I2SCTL_MICEN_DISABLE); + + /* + * BCLK may not be enabled if lpass_cpu_daiops_prepare is called before + * lpass_cpu_daiops_shutdown. It's paired with the clk_enable in + * lpass_cpu_daiops_prepare. + */ + if (drvdata->mi2s_was_prepared[dai->driver->id]) { + drvdata->mi2s_was_prepared[dai->driver->id] = false; + clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); + } + clk_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]); } @@ -275,6 +297,18 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + /* + * Ensure lpass BCLK/LRCLK is enabled during + * device resume as lpass_cpu_daiops_prepare() is not called + * after the device resumes. We don't check mi2s_was_prepared before + * enable/disable BCLK in trigger events because: + * 1. These trigger events are paired, so the BCLK + * enable_count is balanced. + * 2. the BCLK can be shared (ex: headset and headset mic), + * we need to increase the enable_count so that we don't + * turn off the shared BCLK while other devices are using + * it. + */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_ENABLE); @@ -296,6 +330,10 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + /* + * To ensure lpass BCLK/LRCLK is disabled during + * device suspend. + */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_DISABLE); @@ -315,12 +353,53 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, return ret; } +static int lpass_cpu_daiops_prepare(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); + struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; + unsigned int id = dai->driver->id; + int ret; + + /* + * Ensure lpass BCLK/LRCLK is enabled bit before playback/capture + * data flow starts. This allows other codec to have some delay before + * the data flow. + * (ex: to drop start up pop noise before capture starts). + */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_ENABLE); + else + ret = regmap_fields_write(i2sctl->micen, id, LPAIF_I2SCTL_MICEN_ENABLE); + + if (ret) { + dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); + return ret; + } + + /* + * Check mi2s_was_prepared before enabling BCLK as lpass_cpu_daiops_prepare can + * be called multiple times. It's paired with the clk_disable in + * lpass_cpu_daiops_shutdown. + */ + if (!drvdata->mi2s_was_prepared[dai->driver->id]) { + ret = clk_enable(drvdata->mi2s_bit_clk[id]); + if (ret) { + dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); + return ret; + } + drvdata->mi2s_was_prepared[dai->driver->id] = true; + } + return 0; +} + const struct snd_soc_dai_ops asoc_qcom_lpass_cpu_dai_ops = { .set_sysclk = lpass_cpu_daiops_set_sysclk, .startup = lpass_cpu_daiops_startup, .shutdown = lpass_cpu_daiops_shutdown, .hw_params = lpass_cpu_daiops_hw_params, .trigger = lpass_cpu_daiops_trigger, + .prepare = lpass_cpu_daiops_prepare, }; EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_dai_ops); @@ -835,18 +914,8 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) if (dai_id == LPASS_DP_RX) continue; - drvdata->mi2s_osr_clk[dai_id] = devm_clk_get(dev, + drvdata->mi2s_osr_clk[dai_id] = devm_clk_get_optional(dev, variant->dai_osr_clk_names[i]); - if (IS_ERR(drvdata->mi2s_osr_clk[dai_id])) { - dev_warn(dev, - "%s() error getting optional %s: %ld\n", - __func__, - variant->dai_osr_clk_names[i], - PTR_ERR(drvdata->mi2s_osr_clk[dai_id])); - - drvdata->mi2s_osr_clk[dai_id] = NULL; - } - drvdata->mi2s_bit_clk[dai_id] = devm_clk_get(dev, variant->dai_bit_clk_names[i]); if (IS_ERR(drvdata->mi2s_bit_clk[dai_id])) { diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h index 83b2e08ade06..7f72214404ba 100644 --- a/sound/soc/qcom/lpass.h +++ b/sound/soc/qcom/lpass.h @@ -67,6 +67,10 @@ struct lpass_data { /* MI2S SD lines to use for playback/capture */ unsigned int mi2s_playback_sd_mode[LPASS_MAX_MI2S_PORTS]; unsigned int mi2s_capture_sd_mode[LPASS_MAX_MI2S_PORTS]; + + /* The state of MI2S prepare dai_ops was called */ + bool mi2s_was_prepared[LPASS_MAX_MI2S_PORTS]; + int hdmi_port_enable; /* low-power audio interface (LPAIF) registers */ diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 1c0904acb935..a76974ccfce1 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2225,6 +2225,8 @@ static char *fmt_single_name(struct device *dev, int *id) return NULL; name = devm_kstrdup(dev, devname, GFP_KERNEL); + if (!name) + return NULL; /* are we a "%s.%d" name (platform and SPI components) */ found = strstr(name, dev->driver->name); diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 73076d425efb..4893a56208e0 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1901,7 +1901,7 @@ static void stream_caps_new_ver(struct snd_soc_tplg_stream_caps *dest, * @src: older version of pcm as a source * @pcm: latest version of pcm created from the source * - * Support from vesion 4. User should free the returned pcm manually. + * Support from version 4. User should free the returned pcm manually. */ static int pcm_new_ver(struct soc_tplg *tplg, struct snd_soc_tplg_pcm *src, @@ -2089,7 +2089,7 @@ static void set_link_hw_format(struct snd_soc_dai_link *link, * @src: old version of phyical link config as a source * @link: latest version of physical link config created from the source * - * Support from vesion 4. User need free the returned link config manually. + * Support from version 4. User need free the returned link config manually. */ static int link_new_ver(struct soc_tplg *tplg, struct snd_soc_tplg_link_config *src, @@ -2400,7 +2400,7 @@ static int soc_tplg_dai_elems_load(struct soc_tplg *tplg, * @src: old version of manifest as a source * @manifest: latest version of manifest created from the source * - * Support from vesion 4. Users need free the returned manifest manually. + * Support from version 4. Users need free the returned manifest manually. */ static int manifest_new_ver(struct soc_tplg *tplg, struct snd_soc_tplg_manifest *src, diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index 8d7bab433fb3..c1f9f0f58464 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -421,11 +421,16 @@ static int ssp_dai_hw_params(struct snd_pcm_substream *substream, struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, SOF_AUDIO_PCM_DRV_NAME); struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component); + struct sof_ipc_fw_version *v = &sdev->fw_ready.version; struct sof_ipc_dai_config *config; struct snd_sof_dai *sof_dai; struct sof_ipc_reply reply; int ret; + /* DAI_CONFIG IPC during hw_params is not supported in older firmware */ + if (v->abi_version < SOF_ABI_VER(3, 18, 0)) + return 0; + list_for_each_entry(sof_dai, &sdev->dai_list, list) { if (!sof_dai->cpu_dai_name || !sof_dai->dai_config) continue; diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c index fd265803f7bc..c83fb6255961 100644 --- a/sound/soc/sof/pm.c +++ b/sound/soc/sof/pm.c @@ -256,6 +256,7 @@ suspend: /* reset FW state */ sdev->fw_state = SOF_FW_BOOT_NOT_STARTED; + sdev->enabled_cores_mask = 0; return ret; } diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index c1561237ee24..3aa1cf262402 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -484,10 +484,7 @@ static int stm32_sai_add_mclk_provider(struct stm32_sai_sub_data *sai) dev_err(dev, "mclk register returned %d\n", ret); return ret; } - - sai->sai_mclk = devm_clk_hw_get_clk(dev, hw, NULL); - if (IS_ERR(sai->sai_mclk)) - return PTR_ERR(sai->sai_mclk); + sai->sai_mclk = hw->clk; /* register mclk provider */ return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw); diff --git a/sound/usb/format.c b/sound/usb/format.c index e6ff317a6785..2287f8c65315 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -436,7 +436,7 @@ static bool check_valid_altsetting_v2v3(struct snd_usb_audio *chip, int iface, if (snd_BUG_ON(altsetting >= 64 - 8)) return false; - err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC2_CS_CUR, + err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC2_CS_CUR, USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN, UAC2_AS_VAL_ALT_SETTINGS << 8, iface, &raw_data, sizeof(raw_data)); diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index fda66b2dbb01..37ad77524c0b 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -3060,7 +3060,7 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer) case USB_ID(0x1235, 0x8203): /* Focusrite Scarlett 6i6 2nd Gen */ case USB_ID(0x1235, 0x8204): /* Focusrite Scarlett 18i8 2nd Gen */ case USB_ID(0x1235, 0x8201): /* Focusrite Scarlett 18i20 2nd Gen */ - err = snd_scarlett_gen2_controls_create(mixer); + err = snd_scarlett_gen2_init(mixer); break; case USB_ID(0x041e, 0x323b): /* Creative Sound Blaster E1 */ diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 560c2ade829d..4caf379d5b99 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -635,7 +635,7 @@ static int scarlett2_usb( /* send a second message to get the response */ err = snd_usb_ctl_msg(mixer->chip->dev, - usb_sndctrlpipe(mixer->chip->dev, 0), + usb_rcvctrlpipe(mixer->chip->dev, 0), SCARLETT2_USB_VENDOR_SPECIFIC_CMD_RESP, USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN, 0, @@ -1997,38 +1997,11 @@ static int scarlett2_mixer_status_create(struct usb_mixer_interface *mixer) return usb_submit_urb(mixer->urb, GFP_KERNEL); } -/* Entry point */ -int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer) +static int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer, + const struct scarlett2_device_info *info) { - const struct scarlett2_device_info *info; int err; - /* only use UAC_VERSION_2 */ - if (!mixer->protocol) - return 0; - - switch (mixer->chip->usb_id) { - case USB_ID(0x1235, 0x8203): - info = &s6i6_gen2_info; - break; - case USB_ID(0x1235, 0x8204): - info = &s18i8_gen2_info; - break; - case USB_ID(0x1235, 0x8201): - info = &s18i20_gen2_info; - break; - default: /* device not (yet) supported */ - return -EINVAL; - } - - if (!(mixer->chip->setup & SCARLETT2_ENABLE)) { - usb_audio_err(mixer->chip, - "Focusrite Scarlett Gen 2 Mixer Driver disabled; " - "use options snd_usb_audio device_setup=1 " - "to enable and report any issues to g@b4.vu"); - return 0; - } - /* Initialise private data, routing, sequence number */ err = scarlett2_init_private(mixer, info); if (err < 0) @@ -2073,3 +2046,51 @@ int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer) return 0; } + +int snd_scarlett_gen2_init(struct usb_mixer_interface *mixer) +{ + struct snd_usb_audio *chip = mixer->chip; + const struct scarlett2_device_info *info; + int err; + + /* only use UAC_VERSION_2 */ + if (!mixer->protocol) + return 0; + + switch (chip->usb_id) { + case USB_ID(0x1235, 0x8203): + info = &s6i6_gen2_info; + break; + case USB_ID(0x1235, 0x8204): + info = &s18i8_gen2_info; + break; + case USB_ID(0x1235, 0x8201): + info = &s18i20_gen2_info; + break; + default: /* device not (yet) supported */ + return -EINVAL; + } + + if (!(chip->setup & SCARLETT2_ENABLE)) { + usb_audio_info(chip, + "Focusrite Scarlett Gen 2 Mixer Driver disabled; " + "use options snd_usb_audio vid=0x%04x pid=0x%04x " + "device_setup=1 to enable and report any issues " + "to g@b4.vu", + USB_ID_VENDOR(chip->usb_id), + USB_ID_PRODUCT(chip->usb_id)); + return 0; + } + + usb_audio_info(chip, + "Focusrite Scarlett Gen 2 Mixer Driver enabled pid=0x%04x", + USB_ID_PRODUCT(chip->usb_id)); + + err = snd_scarlett_gen2_controls_create(mixer, info); + if (err < 0) + usb_audio_err(mixer->chip, + "Error initialising Scarlett Mixer Driver: %d", + err); + + return err; +} diff --git a/sound/usb/mixer_scarlett_gen2.h b/sound/usb/mixer_scarlett_gen2.h index 52e1dad77afd..668c6b0cb50a 100644 --- a/sound/usb/mixer_scarlett_gen2.h +++ b/sound/usb/mixer_scarlett_gen2.h @@ -2,6 +2,6 @@ #ifndef __USB_MIXER_SCARLETT_GEN2_H #define __USB_MIXER_SCARLETT_GEN2_H -int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer); +int snd_scarlett_gen2_init(struct usb_mixer_interface *mixer); #endif /* __USB_MIXER_SCARLETT_GEN2_H */ diff --git a/tools/arch/mips/include/uapi/asm/perf_regs.h b/tools/arch/mips/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..d0f4ecd616cf --- /dev/null +++ b/tools/arch/mips/include/uapi/asm/perf_regs.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_MIPS_PERF_REGS_H +#define _ASM_MIPS_PERF_REGS_H + +enum perf_event_mips_regs { + PERF_REG_MIPS_PC, + PERF_REG_MIPS_R1, + PERF_REG_MIPS_R2, + PERF_REG_MIPS_R3, + PERF_REG_MIPS_R4, + PERF_REG_MIPS_R5, + PERF_REG_MIPS_R6, + PERF_REG_MIPS_R7, + PERF_REG_MIPS_R8, + PERF_REG_MIPS_R9, + PERF_REG_MIPS_R10, + PERF_REG_MIPS_R11, + PERF_REG_MIPS_R12, + PERF_REG_MIPS_R13, + PERF_REG_MIPS_R14, + PERF_REG_MIPS_R15, + PERF_REG_MIPS_R16, + PERF_REG_MIPS_R17, + PERF_REG_MIPS_R18, + PERF_REG_MIPS_R19, + PERF_REG_MIPS_R20, + PERF_REG_MIPS_R21, + PERF_REG_MIPS_R22, + PERF_REG_MIPS_R23, + PERF_REG_MIPS_R24, + PERF_REG_MIPS_R25, + PERF_REG_MIPS_R26, + PERF_REG_MIPS_R27, + PERF_REG_MIPS_R28, + PERF_REG_MIPS_R29, + PERF_REG_MIPS_R30, + PERF_REG_MIPS_R31, + PERF_REG_MIPS_MAX = PERF_REG_MIPS_R31 + 1, +}; +#endif /* _ASM_MIPS_PERF_REGS_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index b7dd944dc867..8f28fafa98b3 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -56,11 +56,8 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_IOMMU_SUPPORT -# define DISABLE_ENQCMD 0 -#else -# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) -#endif +/* Force disable because it's broken beyond repair */ +#define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) #ifdef CONFIG_X86_SGX # define DISABLE_SGX 0 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 5a3022c8af82..0662f644aad9 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -437,6 +437,8 @@ struct kvm_vmx_nested_state_hdr { __u16 flags; } smm; + __u16 pad; + __u32 flags; __u64 preemption_timer_deadline; }; diff --git a/tools/bootconfig/include/linux/bootconfig.h b/tools/bootconfig/include/linux/bootconfig.h index 078cbd2ba651..de7f30f99af3 100644 --- a/tools/bootconfig/include/linux/bootconfig.h +++ b/tools/bootconfig/include/linux/bootconfig.h @@ -4,4 +4,8 @@ #include "../../../../include/linux/bootconfig.h" +#ifndef fallthrough +# define fallthrough +#endif + #endif diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 7362bef1a368..6cd6080cac04 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -399,6 +399,7 @@ static int apply_xbc(const char *path, const char *xbc_path) } /* TODO: Ensure the @path is initramfs/initrd image */ if (fstat(fd, &stat) < 0) { + ret = -errno; pr_err("Failed to get the size of %s\n", path); goto out; } diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 790944c35602..baee8591ac76 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -30,7 +30,8 @@ CGROUP COMMANDS | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | | **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** } +| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | +| **sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -106,6 +107,7 @@ DESCRIPTION **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8); **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8); **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8). + **sock_release** closing an userspace inet socket (since 5.9). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 358c7309d419..fe1b38e7e887 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -44,7 +44,7 @@ PROG COMMANDS | **cgroup/connect4** | **cgroup/connect6** | **cgroup/getpeername4** | **cgroup/getpeername6** | | **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | | **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | -| **cgroup/getsockopt** | **cgroup/setsockopt** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | | **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } | *ATTACH_TYPE* := { diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index d67518bcbd44..cc33c5824a2f 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -478,7 +478,7 @@ _bpftool() cgroup/recvmsg4 cgroup/recvmsg6 \ cgroup/post_bind4 cgroup/post_bind6 \ cgroup/sysctl cgroup/getsockopt \ - cgroup/setsockopt struct_ops \ + cgroup/setsockopt cgroup/sock_release struct_ops \ fentry fexit freplace sk_lookup" -- \ "$cur" ) ) return 0 @@ -1021,7 +1021,7 @@ _bpftool() device bind4 bind6 post_bind4 post_bind6 connect4 connect6 \ getpeername4 getpeername6 getsockname4 getsockname6 \ sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \ - setsockopt' + setsockopt sock_release' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag name' case $prev in @@ -1032,7 +1032,7 @@ _bpftool() ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|getpeername4|\ getpeername6|getsockname4|getsockname6|sendmsg4|sendmsg6|\ - recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt) + recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt|sock_release) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index d901cc1b904a..6e53b1d393f4 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -28,7 +28,8 @@ " connect6 | getpeername4 | getpeername6 |\n" \ " getsockname4 | getsockname6 | sendmsg4 |\n" \ " sendmsg6 | recvmsg4 | recvmsg6 |\n" \ - " sysctl | getsockopt | setsockopt }" + " sysctl | getsockopt | setsockopt |\n" \ + " sock_release }" static unsigned int query_flags; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 3f067d2d7584..da4846c9856a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2138,7 +2138,7 @@ static int do_help(int argc, char **argv) " cgroup/getpeername4 | cgroup/getpeername6 |\n" " cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n" " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" - " cgroup/getsockopt | cgroup/setsockopt |\n" + " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" " struct_ops | fentry | fexit | freplace | sk_lookup }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 6de5a7fc066b..d2a942086fcb 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -863,8 +863,7 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) -#define __NR_quotactl_path 443 -__SYSCALL(__NR_quotactl_path, sys_quotactl_path) +/* 443 is reserved for quotactl_path */ #define __NR_landlock_create_ruleset 444 __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index f44eb0a04afd..4c32e97dcdf0 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -185,7 +185,7 @@ struct fsxattr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) /* - * A jump here: 130-131 are reserved for zoned block devices + * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) */ diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff) +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 3fd9a7e9d90c..79d9c44d1ad7 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index bf8143505c49..f92880a15645 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -464,7 +464,7 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via - * siginfo_t::si_perf, e.g. to permit user to identify the event. + * siginfo_t::si_perf_data, e.g. to permit user to identify the event. */ __u64 sig_data; }; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e2a3cf437814..c41d9b2b59ac 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3216,6 +3216,9 @@ static int add_dummy_ksym_var(struct btf *btf) const struct btf_var_secinfo *vs; const struct btf_type *sec; + if (!btf) + return 0; + sec_btf_id = btf__find_by_name_kind(btf, KSYMS_SEC, BTF_KIND_DATASEC); if (sec_btf_id < 0) diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index ee426226928f..acbcf6c7bdf8 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -41,6 +41,11 @@ #define ELF_C_READ_MMAP ELF_C_READ #endif +/* Older libelf all end up in this expression, for both 32 and 64 bit */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(o) ((o) & 0x03) +#endif + #define BTF_INFO_ENC(kind, kind_flag, vlen) \ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 6061431ee04c..e9b619aa0cdf 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -1094,7 +1094,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, goto out_put_ctx; } if (xsk->fd == umem->fd) - umem->rx_ring_setup_done = true; + umem->tx_ring_setup_done = true; } err = xsk_get_mmap_offsets(xsk->fd, &off); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 24295d39713b..523aa4157f80 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -747,6 +747,10 @@ int arch_rewrite_retpolines(struct objtool_file *file) list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) + continue; + if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) continue; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 743c2e9d0f56..41bca1d13d8e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -717,7 +717,7 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) { - struct section *symtab; + struct section *symtab, *symtab_shndx; struct symbol *sym; Elf_Data *data; Elf_Scn *s; @@ -769,6 +769,29 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) symtab->len += data->d_size; symtab->changed = true; + symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); + if (symtab_shndx) { + s = elf_getscn(elf->elf, symtab_shndx->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return NULL; + } + + data = elf_newdata(s); + if (!data) { + WARN_ELF("elf_newdata"); + return NULL; + } + + data->d_buf = &sym->sym.st_size; /* conveniently 0 */ + data->d_size = sizeof(Elf32_Word); + data->d_align = 4; + data->d_type = ELF_T_WORD; + + symtab_shndx->len += 4; + symtab_shndx->changed = true; + } + sym->sec = find_section_by_index(elf, 0); elf_add_symbol(elf, sym); diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 1dcec73c910c..bcf3eca5afbe 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -108,9 +108,9 @@ displayed as follows: perf script --itrace=ibxwpe -F+flags -The flags are "bcrosyiABEx" which stand for branch, call, return, conditional, -system, asynchronous, interrupt, transaction abort, trace begin, trace end, and -in transaction, respectively. +The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional, +system, asynchronous, interrupt, transaction abort, trace begin, trace end, +in transaction, VM-entry, and VM-exit respectively. perf script also supports higher level ways to dump instruction traces: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 5b8b61075039..48a5f5b26dd4 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -183,14 +183,15 @@ OPTIONS At this point usage is displayed, and perf-script exits. The flags field is synthesized and may have a value when Instruction - Trace decoding. The flags are "bcrosyiABEx" which stand for branch, + Trace decoding. The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional, system, asynchronous, interrupt, - transaction abort, trace begin, trace end, and in transaction, + transaction abort, trace begin, trace end, in transaction, VM-Entry, and VM-Exit respectively. Known combinations of flags are printed more nicely e.g. "call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b", "int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs", "async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB", - "tr end" for "bE". However the "x" flag will be display separately in those + "tr end" for "bE", "vmentry" for "bcg", "vmexit" for "bch". + However the "x" flag will be displayed separately in those cases e.g. "jcc (x)" for a condition branch within a transaction. The callindent field is synthesized and may have a value when diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 406a9519145e..73df23dd664c 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -90,7 +90,6 @@ endif ifeq ($(ARCH),mips) NO_PERF_REGS := 0 CFLAGS += -I$(OUTPUT)arch/mips/include/generated - CFLAGS += -I../../arch/mips/include/uapi -I../../arch/mips/include/generated/uapi LIBUNWIND_LIBS = -lunwind -lunwind-mips endif diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 9974f5f8e49b..9cd1c34f31b5 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -357,7 +357,7 @@ 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 442 n64 mount_setattr sys_mount_setattr -443 n64 quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 n64 landlock_create_ruleset sys_landlock_create_ruleset 445 n64 landlock_add_rule sys_landlock_add_rule 446 n64 landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 2e68fbb57cc6..8f052ff4058c 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -522,7 +522,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 7e4a2aba366d..0690263df1dd 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -445,7 +445,7 @@ 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index ecd551b08d05..ce18119ea0d0 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,7 +364,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 87f5b1a4a7fa..833405c27dae 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -80,6 +80,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits) if (!perf_header__has_feat(&session->header, HEADER_BUILD_ID)) with_hits = true; + if (zstd_init(&(session->zstd_data), 0) < 0) + pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); + /* * in pipe-mode, the only way to get the buildids is to parse * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 3337b5f93336..84803abeb942 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -2714,6 +2714,12 @@ int cmd_record(int argc, const char **argv) rec->no_buildid = true; } + if (rec->opts.record_cgroup && !perf_can_record_cgroup()) { + pr_err("Kernel has no cgroup sampling support.\n"); + err = -EINVAL; + goto out_opts; + } + if (rec->opts.kcore) rec->data.is_dir = true; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5a830ae09418..f9f74a514315 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -572,7 +572,8 @@ static int enable_counters(void) * - we have initial delay configured */ if (!target__none(&target) || stat_config.initial_delay) { - evlist__enable(evsel_list); + if (!all_counters_use_bpf) + evlist__enable(evsel_list); if (stat_config.initial_delay > 0) pr_info(EVLIST_ENABLED_MSG); } @@ -581,13 +582,19 @@ static int enable_counters(void) static void disable_counters(void) { + struct evsel *counter; + /* * If we don't have tracee (attaching to task or cpu), counters may * still be running. To get accurate group ratios, we must stop groups * from counting before reading their constituent counters. */ - if (!target__none(&target)) - evlist__disable(evsel_list); + if (!target__none(&target)) { + evlist__for_each_entry(evsel_list, counter) + bpf_counter__disable(counter); + if (!all_counters_use_bpf) + evlist__disable(evsel_list); + } } static volatile int workload_exec_errno; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index dd8ff287e930..c783558332b8 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -39,6 +39,7 @@ arch/x86/lib/x86-opcode-map.txt arch/x86/tools/gen-insn-attr-x86.awk arch/arm/include/uapi/asm/perf_regs.h arch/arm64/include/uapi/asm/perf_regs.h +arch/mips/include/uapi/asm/perf_regs.h arch/powerpc/include/uapi/asm/perf_regs.h arch/s390/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/perf_regs.h diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 20cb91ef06ff..2f6b67189b42 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -443,6 +443,8 @@ int main(int argc, const char **argv) const char *cmd; char sbuf[STRERR_BUFSIZE]; + perf_debug_setup(); + /* libsubcmd init */ exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); pager_init(PERF_PAGER_ENVIRONMENT); @@ -531,8 +533,6 @@ int main(int argc, const char **argv) */ pthread__block_sigwinch(); - perf_debug_setup(); - while (1) { static int done_help; diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json index 616f29098c71..605be14f441c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json @@ -1,46 +1,56 @@ [ { - "EventCode": "1003C", + "EventCode": "0x1003C", "EventName": "PM_EXEC_STALL_DMISS_L2L3", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3." }, { - "EventCode": "34056", + "EventCode": "0x1E054", + "EventName": "PM_EXEC_STALL_DMISS_L21_L31", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." + }, + { + "EventCode": "0x34054", + "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." + }, + { + "EventCode": "0x34056", "EventName": "PM_EXEC_STALL_LOAD_FINISH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction." }, { - "EventCode": "3006C", + "EventCode": "0x3006C", "EventName": "PM_RUN_CYC_SMT2_MODE", "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode." }, { - "EventCode": "300F4", + "EventCode": "0x300F4", "EventName": "PM_RUN_INST_CMPL_CONC", "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set." }, { - "EventCode": "4C016", + "EventCode": "0x4C016", "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict." }, { - "EventCode": "4D014", + "EventCode": "0x4D014", "EventName": "PM_EXEC_STALL_LOAD", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit." }, { - "EventCode": "4D016", + "EventCode": "0x4D016", "EventName": "PM_EXEC_STALL_PTESYNC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit." }, { - "EventCode": "401EA", + "EventCode": "0x401EA", "EventName": "PM_THRESH_EXC_128", "BriefDescription": "Threshold counter exceeded a value of 128." }, { - "EventCode": "400F6", + "EventCode": "0x400F6", "EventName": "PM_BR_MPRED_CMPL", "BriefDescription": "A mispredicted branch completed. Includes direction and target." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json index 703cd431ae5b..54acb55e2c8c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json @@ -1,6 +1,6 @@ [ { - "EventCode": "4016E", + "EventCode": "0x4016E", "EventName": "PM_THRESH_NOT_MET", "BriefDescription": "Threshold counter did not meet threshold." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json index eac8609dcc90..558f9530f54e 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json @@ -1,216 +1,246 @@ [ { - "EventCode": "10004", + "EventCode": "0x10004", "EventName": "PM_EXEC_STALL_TRANSLATION", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve." }, { - "EventCode": "10010", + "EventCode": "0x10006", + "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." + }, + { + "EventCode": "0x10010", "EventName": "PM_PMC4_OVERFLOW", "BriefDescription": "The event selected for PMC4 caused the event counter to overflow." }, { - "EventCode": "10020", + "EventCode": "0x10020", "EventName": "PM_PMC4_REWIND", "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged." }, { - "EventCode": "10038", + "EventCode": "0x10038", "EventName": "PM_DISP_STALL_TRANSLATION", "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss." }, { - "EventCode": "1003A", + "EventCode": "0x1003A", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict." }, { - "EventCode": "1E050", + "EventCode": "0x1D05E", + "EventName": "PM_DISP_STALL_HELD_HALT_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." + }, + { + "EventCode": "0x1E050", "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." }, { - "EventCode": "1F054", + "EventCode": "0x1F054", "EventName": "PM_DTLB_HIT", "BriefDescription": "The PTE required by the instruction was resident in the TLB (data TLB access). When MMCR1[16]=0 this event counts only demand hits. When MMCR1[16]=1 this event includes demand and prefetch. Applies to both HPT and RPT." }, { - "EventCode": "101E8", + "EventCode": "0x10064", + "EventName": "PM_DISP_STALL_IC_L2", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." + }, + { + "EventCode": "0x101E8", "EventName": "PM_THRESH_EXC_256", "BriefDescription": "Threshold counter exceeded a count of 256." }, { - "EventCode": "101EC", + "EventCode": "0x101EC", "EventName": "PM_THRESH_MET", "BriefDescription": "Threshold exceeded." }, { - "EventCode": "100F2", + "EventCode": "0x100F2", "EventName": "PM_1PLUS_PPC_CMPL", "BriefDescription": "Cycles in which at least one instruction is completed by this thread." }, { - "EventCode": "100F6", + "EventCode": "0x100F6", "EventName": "PM_IERAT_MISS", "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event." }, { - "EventCode": "100F8", + "EventCode": "0x100F8", "EventName": "PM_DISP_STALL_CYC", "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)." }, { - "EventCode": "20114", + "EventCode": "0x20006", + "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." + }, + { + "EventCode": "0x20114", "EventName": "PM_MRK_L2_RC_DISP", "BriefDescription": "Marked instruction RC dispatched in L2." }, { - "EventCode": "2C010", + "EventCode": "0x2C010", "EventName": "PM_EXEC_STALL_LSU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions." }, { - "EventCode": "2C016", + "EventCode": "0x2C016", "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS", "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss." }, { - "EventCode": "2C01E", + "EventCode": "0x2C01E", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict." }, { - "EventCode": "2D01A", + "EventCode": "0x2D01A", "EventName": "PM_DISP_STALL_IC_MISS", "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss." }, { - "EventCode": "2D01C", - "EventName": "PM_CMPL_STALL_STCX", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing." - }, - { - "EventCode": "2E018", + "EventCode": "0x2E018", "EventName": "PM_DISP_STALL_FETCH", "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held." }, { - "EventCode": "2E01A", + "EventCode": "0x2E01A", "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full." }, { - "EventCode": "2C142", + "EventCode": "0x2C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC2", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "24050", + "EventCode": "0x24050", "EventName": "PM_IOPS_DISP", "BriefDescription": "Internal Operations dispatched. PM_IOPS_DISP / PM_INST_DISP will show the average number of internal operations per PowerPC instruction." }, { - "EventCode": "2405E", + "EventCode": "0x2405E", "EventName": "PM_ISSUE_CANCEL", "BriefDescription": "An instruction issued and the issue was later cancelled. Only one cancel per PowerPC instruction." }, { - "EventCode": "200FA", + "EventCode": "0x200FA", "EventName": "PM_BR_TAKEN_CMPL", "BriefDescription": "Branch Taken instruction completed." }, { - "EventCode": "30012", + "EventCode": "0x30004", + "EventName": "PM_DISP_STALL_FLUSH", + "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." + }, + { + "EventCode": "0x3000A", + "EventName": "PM_DISP_STALL_ITLB_MISS", + "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss." + }, + { + "EventCode": "0x30012", "EventName": "PM_FLUSH_COMPLETION", "BriefDescription": "The instruction that was next to complete (oldest in the pipeline) did not complete because it suffered a flush." }, { - "EventCode": "30014", + "EventCode": "0x30014", "EventName": "PM_EXEC_STALL_STORE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit." }, { - "EventCode": "30018", + "EventCode": "0x30018", "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together." }, { - "EventCode": "30026", + "EventCode": "0x30026", "EventName": "PM_EXEC_STALL_STORE_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1." }, { - "EventCode": "3012A", + "EventCode": "0x3012A", "EventName": "PM_MRK_L2_RC_DONE", "BriefDescription": "L2 RC machine completed the transaction for the marked instruction." }, { - "EventCode": "3F046", + "EventCode": "0x3F046", "EventName": "PM_ITLB_HIT_1G", "BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { - "EventCode": "34058", + "EventCode": "0x34058", "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS", "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss." }, { - "EventCode": "3D05C", + "EventCode": "0x3D05C", "EventName": "PM_DISP_STALL_HELD_RENAME_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." }, { - "EventCode": "3E052", + "EventCode": "0x3E052", "EventName": "PM_DISP_STALL_IC_L3", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3." }, { - "EventCode": "3E054", + "EventCode": "0x3E054", "EventName": "PM_LD_MISS_L1", "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." }, { - "EventCode": "301EA", + "EventCode": "0x301EA", "EventName": "PM_THRESH_EXC_1024", "BriefDescription": "Threshold counter exceeded a value of 1024." }, { - "EventCode": "300FA", + "EventCode": "0x300FA", "EventName": "PM_INST_FROM_L3MISS", "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." }, { - "EventCode": "40006", + "EventCode": "0x40006", "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, { - "EventCode": "40116", + "EventCode": "0x40116", "EventName": "PM_MRK_LARX_FIN", "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "4C010", + "EventCode": "0x4C010", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch." }, { - "EventCode": "4D01E", + "EventCode": "0x4D01E", "EventName": "PM_DISP_STALL_BR_MPRED", "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch." }, { - "EventCode": "4E010", + "EventCode": "0x4E010", "EventName": "PM_DISP_STALL_IC_L3MISS", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3." }, { - "EventCode": "4E01A", + "EventCode": "0x4E01A", "EventName": "PM_DISP_STALL_HELD_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason." }, { - "EventCode": "44056", + "EventCode": "0x4003C", + "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." + }, + { + "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL", "BriefDescription": "Vector store instructions completed." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/locks.json b/tools/perf/pmu-events/arch/powerpc/power10/locks.json index 016d8de0e14a..b5a0d6521963 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/locks.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/locks.json @@ -1,11 +1,11 @@ [ { - "EventCode": "1E058", + "EventCode": "0x1E058", "EventName": "PM_STCX_FAIL_FIN", "BriefDescription": "Conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "4E050", + "EventCode": "0x4E050", "EventName": "PM_STCX_PASS_FIN", "BriefDescription": "Conditional store instruction (STCX) passed. LARX and STCX are instructions used to acquire a lock." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json index 93a5a5910648..58b5dfe3a273 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json @@ -1,146 +1,141 @@ [ { - "EventCode": "1002C", + "EventCode": "0x1002C", "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS", "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request." }, { - "EventCode": "10132", + "EventCode": "0x10132", "EventName": "PM_MRK_INST_ISSUED", "BriefDescription": "Marked instruction issued. Note that stores always get issued twice, the address gets issued to the LSU and the data gets issued to the VSU. Also, issues can sometimes get killed/cancelled and cause multiple sequential issues for the same instruction." }, { - "EventCode": "101E0", + "EventCode": "0x101E0", "EventName": "PM_MRK_INST_DISP", "BriefDescription": "The thread has dispatched a randomly sampled marked instruction." }, { - "EventCode": "101E2", + "EventCode": "0x101E2", "EventName": "PM_MRK_BR_TAKEN_CMPL", "BriefDescription": "Marked Branch Taken instruction completed." }, { - "EventCode": "20112", + "EventCode": "0x20112", "EventName": "PM_MRK_NTF_FIN", "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch." }, { - "EventCode": "2C01C", + "EventCode": "0x2C01C", "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip." }, { - "EventCode": "20138", + "EventCode": "0x20138", "EventName": "PM_MRK_ST_NEST", "BriefDescription": "A store has been sampled/marked and is at the point of execution where it has completed in the core and can no longer be flushed. At this point the store is sent to the L2." }, { - "EventCode": "2013A", + "EventCode": "0x2013A", "EventName": "PM_MRK_BRU_FIN", "BriefDescription": "Marked Branch instruction finished." }, { - "EventCode": "2C144", + "EventCode": "0x2C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC2", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[15:27]." }, { - "EventCode": "24156", + "EventCode": "0x24156", "EventName": "PM_MRK_STCX_FIN", "BriefDescription": "Marked conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "24158", + "EventCode": "0x24158", "EventName": "PM_MRK_INST", "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens." }, { - "EventCode": "2415C", + "EventCode": "0x2415C", "EventName": "PM_MRK_BR_CMPL", "BriefDescription": "A marked branch completed. All branches are included." }, { - "EventCode": "200FD", + "EventCode": "0x200FD", "EventName": "PM_L1_ICACHE_MISS", "BriefDescription": "Demand iCache Miss." }, { - "EventCode": "30130", + "EventCode": "0x30130", "EventName": "PM_MRK_INST_FIN", "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU." }, { - "EventCode": "34146", + "EventCode": "0x34146", "EventName": "PM_MRK_LD_CMPL", "BriefDescription": "Marked loads completed." }, { - "EventCode": "3E158", + "EventCode": "0x3E158", "EventName": "PM_MRK_STCX_FAIL", "BriefDescription": "Marked conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "3E15A", + "EventCode": "0x3E15A", "EventName": "PM_MRK_ST_FIN", "BriefDescription": "The marked instruction was a store of any kind." }, { - "EventCode": "30068", + "EventCode": "0x30068", "EventName": "PM_L1_ICACHE_RELOADED_PREF", "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)." }, { - "EventCode": "301E4", + "EventCode": "0x301E4", "EventName": "PM_MRK_BR_MPRED_CMPL", "BriefDescription": "Marked Branch Mispredicted. Includes direction and target." }, { - "EventCode": "300F6", + "EventCode": "0x300F6", "EventName": "PM_LD_DEMAND_MISS_L1", "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish." }, { - "EventCode": "300FE", + "EventCode": "0x300FE", "EventName": "PM_DATA_FROM_L3MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." }, { - "EventCode": "40012", + "EventCode": "0x40012", "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, { - "EventCode": "40134", + "EventCode": "0x40134", "EventName": "PM_MRK_INST_TIMEO", "BriefDescription": "Marked instruction finish timeout (instruction was lost)." }, { - "EventCode": "4003C", - "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." - }, - { - "EventCode": "4505A", + "EventCode": "0x4505A", "EventName": "PM_SP_FLOP_CMPL", "BriefDescription": "Single Precision floating point instructions completed." }, { - "EventCode": "4D058", + "EventCode": "0x4D058", "EventName": "PM_VECTOR_FLOP_CMPL", "BriefDescription": "Vector floating point instructions completed." }, { - "EventCode": "4D05A", + "EventCode": "0x4D05A", "EventName": "PM_NON_MATH_FLOP_CMPL", "BriefDescription": "Non Math instructions completed." }, { - "EventCode": "401E0", + "EventCode": "0x401E0", "EventName": "PM_MRK_INST_CMPL", "BriefDescription": "marked instruction completed." }, { - "EventCode": "400FE", + "EventCode": "0x400FE", "EventName": "PM_DATA_FROM_MEMORY", "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json index b01141eeebee..843b51f531e9 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json @@ -1,191 +1,186 @@ [ { - "EventCode": "1000A", + "EventCode": "0x1000A", "EventName": "PM_PMC3_REWIND", "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged." }, { - "EventCode": "1C040", + "EventCode": "0x1C040", "EventName": "PM_XFER_FROM_SRC_PMC1", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "1C142", + "EventCode": "0x1C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC1", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "1C144", + "EventCode": "0x1C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]." }, { - "EventCode": "1C056", + "EventCode": "0x1C056", "EventName": "PM_DERAT_MISS_4K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1C058", + "EventCode": "0x1C058", "EventName": "PM_DTLB_MISS_16G", "BriefDescription": "Data TLB reload (after a miss) page size 16G. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1C05C", + "EventCode": "0x1C05C", "EventName": "PM_DTLB_MISS_2M", "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1E056", + "EventCode": "0x1E056", "EventName": "PM_EXEC_STALL_STORE_PIPE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions." }, { - "EventCode": "1F150", + "EventCode": "0x1F150", "EventName": "PM_MRK_ST_L2_CYC", "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion." }, { - "EventCode": "10062", + "EventCode": "0x10062", "EventName": "PM_LD_L3MISS_PEND_CYC", "BriefDescription": "Cycles L3 miss was pending for this thread." }, { - "EventCode": "20010", + "EventCode": "0x20010", "EventName": "PM_PMC1_OVERFLOW", "BriefDescription": "The event selected for PMC1 caused the event counter to overflow." }, { - "EventCode": "2001A", + "EventCode": "0x2001A", "EventName": "PM_ITLB_HIT", "BriefDescription": "The PTE required to translate the instruction address was resident in the TLB (instruction TLB access/IERAT reload). Applies to both HPT and RPT. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2003E", + "EventCode": "0x2003E", "EventName": "PM_PTESYNC_FIN", "BriefDescription": "Ptesync instruction finished in the store unit. Only one ptesync can finish at a time." }, { - "EventCode": "2C040", + "EventCode": "0x2C040", "EventName": "PM_XFER_FROM_SRC_PMC2", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "2C054", + "EventCode": "0x2C054", "EventName": "PM_DERAT_MISS_64K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2C056", + "EventCode": "0x2C056", "EventName": "PM_DTLB_MISS_4K", "BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2D154", + "EventCode": "0x2D154", "EventName": "PM_MRK_DERAT_MISS_64K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "200F6", + "EventCode": "0x200F6", "EventName": "PM_DERAT_MISS", "BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3000A", - "EventName": "PM_DISP_STALL_ITLB_MISS", - "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss." - }, - { - "EventCode": "30016", + "EventCode": "0x30016", "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve." }, { - "EventCode": "3C040", + "EventCode": "0x3C040", "EventName": "PM_XFER_FROM_SRC_PMC3", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "3C142", + "EventCode": "0x3C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC3", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "3C144", + "EventCode": "0x3C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]." }, { - "EventCode": "3C054", + "EventCode": "0x3C054", "EventName": "PM_DERAT_MISS_16M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3C056", + "EventCode": "0x3C056", "EventName": "PM_DTLB_MISS_64K", "BriefDescription": "Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3C058", + "EventCode": "0x3C058", "EventName": "PM_LARX_FIN", "BriefDescription": "Load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "301E2", + "EventCode": "0x301E2", "EventName": "PM_MRK_ST_CMPL", "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores." }, { - "EventCode": "300FC", + "EventCode": "0x300FC", "EventName": "PM_DTLB_MISS", "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity." }, { - "EventCode": "4D02C", + "EventCode": "0x4D02C", "EventName": "PM_PMC1_REWIND", "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged." }, { - "EventCode": "4003E", + "EventCode": "0x4003E", "EventName": "PM_LD_CMPL", "BriefDescription": "Loads completed." }, { - "EventCode": "4C040", + "EventCode": "0x4C040", "EventName": "PM_XFER_FROM_SRC_PMC4", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "4C142", + "EventCode": "0x4C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC4", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "4C144", + "EventCode": "0x4C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]." }, { - "EventCode": "4C056", + "EventCode": "0x4C056", "EventName": "PM_DTLB_MISS_16M", "BriefDescription": "Data TLB reload (after a miss) page size 16M. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4C05A", + "EventCode": "0x4C05A", "EventName": "PM_DTLB_MISS_1G", "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4C15E", + "EventCode": "0x4C15E", "EventName": "PM_MRK_DTLB_MISS_64K", "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4D056", + "EventCode": "0x4D056", "EventName": "PM_NON_FMA_FLOP_CMPL", "BriefDescription": "Non FMA instruction completed." }, { - "EventCode": "40164", + "EventCode": "0x40164", "EventName": "PM_MRK_DERAT_MISS_2M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index a119e56cbf1c..7d0de1a2860b 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -1,296 +1,271 @@ [ { - "EventCode": "10016", + "EventCode": "0x10016", "EventName": "PM_VSU0_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 0." }, { - "EventCode": "1001C", + "EventCode": "0x1001C", "EventName": "PM_ULTRAVISOR_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state." }, { - "EventCode": "100F0", + "EventCode": "0x100F0", "EventName": "PM_CYC", "BriefDescription": "Processor cycles." }, { - "EventCode": "10134", + "EventCode": "0x10134", "EventName": "PM_MRK_ST_DONE_L2", "BriefDescription": "Marked stores completed in L2 (RC machine done)." }, { - "EventCode": "1505E", + "EventCode": "0x1505E", "EventName": "PM_LD_HIT_L1", "BriefDescription": "Loads that finished without experiencing an L1 miss." }, { - "EventCode": "1D05E", - "EventName": "PM_DISP_STALL_HELD_HALT_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." - }, - { - "EventCode": "1E054", - "EventName": "PM_EXEC_STALL_DMISS_L21_L31", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." - }, - { - "EventCode": "1E05A", - "EventName": "PM_CMPL_STALL_LWSYNC", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete." - }, - { - "EventCode": "1F056", + "EventCode": "0x1F056", "EventName": "PM_DISP_SS0_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions." }, { - "EventCode": "1F15C", + "EventCode": "0x1F15C", "EventName": "PM_MRK_STCX_L2_CYC", "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)." }, { - "EventCode": "10066", + "EventCode": "0x10066", "EventName": "PM_ADJUNCT_CYC", "BriefDescription": "Cycles in which the thread is in Adjunct state. MSR[S HV PR] bits = 011." }, { - "EventCode": "101E4", + "EventCode": "0x101E4", "EventName": "PM_MRK_L1_ICACHE_MISS", "BriefDescription": "Marked Instruction suffered an icache Miss." }, { - "EventCode": "101EA", + "EventCode": "0x101EA", "EventName": "PM_MRK_L1_RELOAD_VALID", "BriefDescription": "Marked demand reload." }, { - "EventCode": "100F4", + "EventCode": "0x100F4", "EventName": "PM_FLOP_CMPL", "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops." }, { - "EventCode": "100FA", + "EventCode": "0x100FA", "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC", "BriefDescription": "Cycles when at least one thread has the run latch set." }, { - "EventCode": "100FC", + "EventCode": "0x100FC", "EventName": "PM_LD_REF_L1", "BriefDescription": "All L1 D cache load references counted at finish, gated by reject. In P9 and earlier this event counted only cacheable loads but in P10 both cacheable and non-cacheable loads are included." }, { - "EventCode": "20006", - "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." - }, - { - "EventCode": "2000C", + "EventCode": "0x2000C", "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC", "BriefDescription": "Cycles when the run latch is set for all threads." }, { - "EventCode": "2E010", + "EventCode": "0x2E010", "EventName": "PM_ADJUNCT_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state." }, { - "EventCode": "2E014", + "EventCode": "0x2E014", "EventName": "PM_STCX_FIN", "BriefDescription": "Conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "20130", + "EventCode": "0x20130", "EventName": "PM_MRK_INST_DECODED", "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only." }, { - "EventCode": "20132", + "EventCode": "0x20132", "EventName": "PM_MRK_DFU_ISSUE", "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time." }, { - "EventCode": "20134", + "EventCode": "0x20134", "EventName": "PM_MRK_FXU_ISSUE", "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time." }, { - "EventCode": "2505C", + "EventCode": "0x2505C", "EventName": "PM_VSU_ISSUE", "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations." }, { - "EventCode": "2F054", + "EventCode": "0x2F054", "EventName": "PM_DISP_SS1_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 1 dispatches either 1 or 2 instructions." }, { - "EventCode": "2F056", + "EventCode": "0x2F056", "EventName": "PM_DISP_SS1_4_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 1 dispatches either 3 or 4 instructions." }, { - "EventCode": "2006C", + "EventCode": "0x2006C", "EventName": "PM_RUN_CYC_SMT4_MODE", "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode." }, { - "EventCode": "201E0", + "EventCode": "0x201E0", "EventName": "PM_MRK_DATA_FROM_MEMORY", "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load." }, { - "EventCode": "201E4", + "EventCode": "0x201E4", "EventName": "PM_MRK_DATA_FROM_L3MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load." }, { - "EventCode": "201E8", + "EventCode": "0x201E8", "EventName": "PM_THRESH_EXC_512", "BriefDescription": "Threshold counter exceeded a value of 512." }, { - "EventCode": "200F2", + "EventCode": "0x200F2", "EventName": "PM_INST_DISP", "BriefDescription": "PowerPC instructions dispatched." }, { - "EventCode": "30132", + "EventCode": "0x30132", "EventName": "PM_MRK_VSU_FIN", "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit." }, { - "EventCode": "30038", + "EventCode": "0x30038", "EventName": "PM_EXEC_STALL_DMISS_LMEM", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory." }, { - "EventCode": "3F04A", + "EventCode": "0x3F04A", "EventName": "PM_LSU_ST5_FIN", "BriefDescription": "LSU Finished an internal operation in ST2 port." }, { - "EventCode": "34054", - "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." - }, - { - "EventCode": "3405A", + "EventCode": "0x3405A", "EventName": "PM_PRIVILEGED_INST_CMPL", "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state." }, { - "EventCode": "3F150", + "EventCode": "0x3F150", "EventName": "PM_MRK_ST_DRAIN_CYC", "BriefDescription": "cycles to drain st from core to L2." }, { - "EventCode": "3F054", + "EventCode": "0x3F054", "EventName": "PM_DISP_SS0_4_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 3 or 4 instructions." }, { - "EventCode": "3F056", + "EventCode": "0x3F056", "EventName": "PM_DISP_SS0_8_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 5, 6, 7 or 8 instructions." }, { - "EventCode": "30162", + "EventCode": "0x30162", "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD", "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill." }, { - "EventCode": "40114", + "EventCode": "0x40114", "EventName": "PM_MRK_START_PROBE_NOP_DISP", "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0." }, { - "EventCode": "4001C", + "EventCode": "0x4001C", "EventName": "PM_VSU_FIN", "BriefDescription": "VSU instructions finished." }, { - "EventCode": "4C01A", + "EventCode": "0x4C01A", "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip." }, { - "EventCode": "4D012", + "EventCode": "0x4D012", "EventName": "PM_PMC3_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged." }, { - "EventCode": "4D022", + "EventCode": "0x4D022", "EventName": "PM_HYPERVISOR_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state." }, { - "EventCode": "4D026", + "EventCode": "0x4D026", "EventName": "PM_ULTRAVISOR_CYC", "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110." }, { - "EventCode": "4D028", + "EventCode": "0x4D028", "EventName": "PM_PRIVILEGED_CYC", "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00." }, { - "EventCode": "40030", + "EventCode": "0x40030", "EventName": "PM_INST_FIN", "BriefDescription": "Instructions finished." }, { - "EventCode": "44146", + "EventCode": "0x44146", "EventName": "PM_MRK_STCX_CORE_CYC", "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2." }, { - "EventCode": "44054", + "EventCode": "0x44054", "EventName": "PM_VECTOR_LD_CMPL", "BriefDescription": "Vector load instructions completed." }, { - "EventCode": "45054", + "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only." }, { - "EventCode": "45056", + "EventCode": "0x45056", "EventName": "PM_SCALAR_FLOP_CMPL", "BriefDescription": "Scalar floating point instructions completed." }, { - "EventCode": "4505C", + "EventCode": "0x4505C", "EventName": "PM_MATH_FLOP_CMPL", "BriefDescription": "Math floating point instructions completed." }, { - "EventCode": "4D05E", + "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL", "BriefDescription": "A branch completed. All branches are included." }, { - "EventCode": "4E15E", + "EventCode": "0x4E15E", "EventName": "PM_MRK_INST_FLUSHED", "BriefDescription": "The marked instruction was flushed." }, { - "EventCode": "401E6", + "EventCode": "0x401E6", "EventName": "PM_MRK_INST_FROM_L3MISS", "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction." }, { - "EventCode": "401E8", + "EventCode": "0x401E8", "EventName": "PM_MRK_DATA_FROM_L2MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load." }, { - "EventCode": "400F0", + "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load Missed L1, counted at finish time." }, { - "EventCode": "400FA", + "EventCode": "0x400FA", "EventName": "PM_RUN_INST_CMPL", "BriefDescription": "Completed PowerPC instructions gated by the run latch." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json index b61b5cc157ee..b8aded6045fa 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json @@ -1,296 +1,291 @@ [ { - "EventCode": "100FE", + "EventCode": "0x100FE", "EventName": "PM_INST_CMPL", "BriefDescription": "PowerPC instructions completed." }, { - "EventCode": "10006", - "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." - }, - { - "EventCode": "1000C", + "EventCode": "0x1000C", "EventName": "PM_LSU_LD0_FIN", "BriefDescription": "LSU Finished an internal operation in LD0 port." }, { - "EventCode": "1000E", + "EventCode": "0x1000E", "EventName": "PM_MMA_ISSUED", "BriefDescription": "MMA instructions issued." }, { - "EventCode": "10012", + "EventCode": "0x10012", "EventName": "PM_LSU_ST0_FIN", "BriefDescription": "LSU Finished an internal operation in ST0 port." }, { - "EventCode": "10014", + "EventCode": "0x10014", "EventName": "PM_LSU_ST4_FIN", "BriefDescription": "LSU Finished an internal operation in ST4 port." }, { - "EventCode": "10018", + "EventCode": "0x10018", "EventName": "PM_IC_DEMAND_CYC", "BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss." }, { - "EventCode": "10022", + "EventCode": "0x10022", "EventName": "PM_PMC2_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged." }, { - "EventCode": "10024", + "EventCode": "0x10024", "EventName": "PM_PMC5_OVERFLOW", "BriefDescription": "The event selected for PMC5 caused the event counter to overflow." }, { - "EventCode": "10058", + "EventCode": "0x10058", "EventName": "PM_EXEC_STALL_FIN_AT_DISP", "BriefDescription": "Cycles in which the oldest instruction in the pipeline finished at dispatch and did not require execution in the LSU, BRU or VSU." }, { - "EventCode": "1005A", + "EventCode": "0x1005A", "EventName": "PM_FLUSH_MPRED", "BriefDescription": "A flush occurred due to a mispredicted branch. Includes target and direction." }, { - "EventCode": "1C05A", + "EventCode": "0x1C05A", "EventName": "PM_DERAT_MISS_2M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "10064", - "EventName": "PM_DISP_STALL_IC_L2", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." + "EventCode": "0x1E05A", + "EventName": "PM_CMPL_STALL_LWSYNC", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete." }, { - "EventCode": "10068", + "EventCode": "0x10068", "EventName": "PM_BR_FIN", "BriefDescription": "A branch instruction finished. Includes predicted/mispredicted/unconditional." }, { - "EventCode": "1006A", + "EventCode": "0x1006A", "EventName": "PM_FX_LSU_FIN", "BriefDescription": "Simple fixed point instruction issued to the store unit. Measured at finish time." }, { - "EventCode": "1006C", + "EventCode": "0x1006C", "EventName": "PM_RUN_CYC_ST_MODE", "BriefDescription": "Cycles when the run latch is set and the core is in ST mode." }, { - "EventCode": "20004", + "EventCode": "0x20004", "EventName": "PM_ISSUE_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was dispatched but not issued yet." }, { - "EventCode": "2000A", + "EventCode": "0x2000A", "EventName": "PM_HYPERVISOR_CYC", "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010." }, { - "EventCode": "2000E", + "EventCode": "0x2000E", "EventName": "PM_LSU_LD1_FIN", "BriefDescription": "LSU Finished an internal operation in LD1 port." }, { - "EventCode": "2C014", + "EventCode": "0x2C014", "EventName": "PM_CMPL_STALL_SPECIAL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline required special handling before completing." }, { - "EventCode": "2C018", + "EventCode": "0x2C018", "EventName": "PM_EXEC_STALL_DMISS_L3MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a source beyond the local L2 or local L3." }, { - "EventCode": "2D010", + "EventCode": "0x2D010", "EventName": "PM_LSU_ST1_FIN", "BriefDescription": "LSU Finished an internal operation in ST1 port." }, { - "EventCode": "2D012", + "EventCode": "0x2D012", "EventName": "PM_VSU1_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 1." }, { - "EventCode": "2D018", + "EventCode": "0x2D018", "EventName": "PM_EXEC_STALL_VSU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the VSU (includes FXU, VSU, CRU)." }, { - "EventCode": "2E01E", + "EventCode": "0x2D01C", + "EventName": "PM_CMPL_STALL_STCX", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing." + }, + { + "EventCode": "0x2E01E", "EventName": "PM_EXEC_STALL_NTC_FLUSH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch." }, { - "EventCode": "2013C", + "EventCode": "0x2013C", "EventName": "PM_MRK_FX_LSU_FIN", "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time." }, { - "EventCode": "2405A", + "EventCode": "0x2405A", "EventName": "PM_NTC_FIN", "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status." }, { - "EventCode": "201E2", + "EventCode": "0x201E2", "EventName": "PM_MRK_LD_MISS_L1", "BriefDescription": "Marked DL1 Demand Miss counted at finish time." }, { - "EventCode": "200F4", + "EventCode": "0x200F4", "EventName": "PM_RUN_CYC", "BriefDescription": "Processor cycles gated by the run latch." }, { - "EventCode": "30004", - "EventName": "PM_DISP_STALL_FLUSH", - "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." - }, - { - "EventCode": "30008", + "EventCode": "0x30008", "EventName": "PM_EXEC_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting to finish in one of the execution units (BRU, LSU, VSU). Only cycles between issue and finish are counted in this category." }, { - "EventCode": "3001A", + "EventCode": "0x3001A", "EventName": "PM_LSU_ST2_FIN", "BriefDescription": "LSU Finished an internal operation in ST2 port." }, { - "EventCode": "30020", + "EventCode": "0x30020", "EventName": "PM_PMC2_REWIND", "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged." }, { - "EventCode": "30022", + "EventCode": "0x30022", "EventName": "PM_PMC4_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged." }, { - "EventCode": "30024", + "EventCode": "0x30024", "EventName": "PM_PMC6_OVERFLOW", "BriefDescription": "The event selected for PMC6 caused the event counter to overflow." }, { - "EventCode": "30028", + "EventCode": "0x30028", "EventName": "PM_CMPL_STALL_MEM_ECC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC." }, { - "EventCode": "30036", + "EventCode": "0x30036", "EventName": "PM_EXEC_STALL_SIMPLE_FX", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a simple fixed point instruction executing in the Load Store Unit." }, { - "EventCode": "3003A", + "EventCode": "0x3003A", "EventName": "PM_CMPL_STALL_EXCEPTION", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete." }, { - "EventCode": "3F044", + "EventCode": "0x3F044", "EventName": "PM_VSU2_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 2." }, { - "EventCode": "30058", + "EventCode": "0x30058", "EventName": "PM_TLBIE_FIN", "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." }, { - "EventCode": "3D058", + "EventCode": "0x3D058", "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE", "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)." }, { - "EventCode": "30066", + "EventCode": "0x30066", "EventName": "PM_LSU_FIN", "BriefDescription": "LSU Finished an internal operation (up to 4 per cycle)." }, { - "EventCode": "40004", + "EventCode": "0x40004", "EventName": "PM_FXU_ISSUE", "BriefDescription": "A fixed point instruction was issued to the VSU." }, { - "EventCode": "40008", + "EventCode": "0x40008", "EventName": "PM_NTC_ALL_FIN", "BriefDescription": "Cycles in which both instructions in the ICT entry pair show as finished. These are the cycles between finish and completion for the oldest pair of instructions in the pipeline." }, { - "EventCode": "40010", + "EventCode": "0x40010", "EventName": "PM_PMC3_OVERFLOW", "BriefDescription": "The event selected for PMC3 caused the event counter to overflow." }, { - "EventCode": "4C012", + "EventCode": "0x4C012", "EventName": "PM_EXEC_STALL_DERAT_ONLY_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered an ERAT miss and waited for it resolve." }, { - "EventCode": "4C018", + "EventCode": "0x4C018", "EventName": "PM_CMPL_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline cannot complete because the thread was blocked for any reason." }, { - "EventCode": "4C01E", + "EventCode": "0x4C01E", "EventName": "PM_LSU_ST3_FIN", "BriefDescription": "LSU Finished an internal operation in ST3 port." }, { - "EventCode": "4D018", + "EventCode": "0x4D018", "EventName": "PM_EXEC_STALL_BRU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Branch unit." }, { - "EventCode": "4D01A", + "EventCode": "0x4D01A", "EventName": "PM_CMPL_STALL_HWSYNC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a hwsync waiting for response from L2 before completing." }, { - "EventCode": "4D01C", + "EventCode": "0x4D01C", "EventName": "PM_EXEC_STALL_TLBIEL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIEL instruction executing in the Load Store Unit. TLBIEL instructions have lower overhead than TLBIE instructions because they don't get set to the nest." }, { - "EventCode": "4E012", + "EventCode": "0x4E012", "EventName": "PM_EXEC_STALL_UNKNOWN", "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together." }, { - "EventCode": "4D020", + "EventCode": "0x4D020", "EventName": "PM_VSU3_ISSUE", "BriefDescription": "VSU instruction was issued to VSU pipe 3." }, { - "EventCode": "40132", + "EventCode": "0x40132", "EventName": "PM_MRK_LSU_FIN", "BriefDescription": "LSU marked instruction finish." }, { - "EventCode": "45058", + "EventCode": "0x45058", "EventName": "PM_IC_MISS_CMPL", "BriefDescription": "Non-speculative icache miss, counted at completion." }, { - "EventCode": "4D050", + "EventCode": "0x4D050", "EventName": "PM_VSU_NON_FLOP_CMPL", "BriefDescription": "Non-floating point VSU instructions completed." }, { - "EventCode": "4D052", + "EventCode": "0x4D052", "EventName": "PM_2FLOP_CMPL", "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed." }, { - "EventCode": "400F2", + "EventCode": "0x400F2", "EventName": "PM_1PLUS_PPC_DISP", "BriefDescription": "Cycles at least one Instr Dispatched." }, { - "EventCode": "400F8", + "EventCode": "0x400F8", "EventName": "PM_FLUSH", "BriefDescription": "Flush (any type)." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json index ea122a91ceb0..b5d1bd39cfb2 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json @@ -1,21 +1,21 @@ [ { - "EventCode": "301E8", + "EventCode": "0x301E8", "EventName": "PM_THRESH_EXC_64", "BriefDescription": "Threshold counter exceeded a value of 64." }, { - "EventCode": "45050", + "EventCode": "0x45050", "EventName": "PM_1FLOP_CMPL", "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." }, { - "EventCode": "45052", + "EventCode": "0x45052", "EventName": "PM_4FLOP_CMPL", "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." }, { - "EventCode": "4D054", + "EventCode": "0x4D054", "EventName": "PM_8FLOP_CMPL", "BriefDescription": "Four Double Precision vector instructions completed." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json index 5a714e3dd71a..db3766dca07c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json @@ -1,56 +1,56 @@ [ { - "EventCode": "1F15E", + "EventCode": "0x1F15E", "EventName": "PM_MRK_START_PROBE_NOP_CMPL", "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed." }, { - "EventCode": "20016", + "EventCode": "0x20016", "EventName": "PM_ST_FIN", "BriefDescription": "Store finish count. Includes speculative activity." }, { - "EventCode": "20018", + "EventCode": "0x20018", "EventName": "PM_ST_FWD", "BriefDescription": "Store forwards that finished." }, { - "EventCode": "2011C", + "EventCode": "0x2011C", "EventName": "PM_MRK_NTF_CYC", "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)." }, { - "EventCode": "2E01C", + "EventCode": "0x2E01C", "EventName": "PM_EXEC_STALL_TLBIE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit." }, { - "EventCode": "201E6", + "EventCode": "0x201E6", "EventName": "PM_THRESH_EXC_32", "BriefDescription": "Threshold counter exceeded a value of 32." }, { - "EventCode": "200F0", + "EventCode": "0x200F0", "EventName": "PM_ST_CMPL", "BriefDescription": "Stores completed from S2Q (2nd-level store queue). This event includes regular stores, stcx and cache inhibited stores. The following operations are excluded (pteupdate, snoop tlbie complete, store atomics, miso, load atomic payloads, tlbie, tlbsync, slbieg, isync, msgsnd, slbiag, cpabort, copy, tcheck, tend, stsync, dcbst, icbi, dcbf, hwsync, lwsync, ptesync, eieio, msgsync)." }, { - "EventCode": "200FE", + "EventCode": "0x200FE", "EventName": "PM_DATA_FROM_L2MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss." }, { - "EventCode": "30010", + "EventCode": "0x30010", "EventName": "PM_PMC2_OVERFLOW", "BriefDescription": "The event selected for PMC2 caused the event counter to overflow." }, { - "EventCode": "4D010", + "EventCode": "0x4D010", "EventName": "PM_PMC1_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged." }, { - "EventCode": "4D05C", + "EventCode": "0x4D05C", "EventName": "PM_DPP_FLOP_CMPL", "BriefDescription": "Double-Precision or Quad-Precision instructions completed." } diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 7422b0ea8790..9604446f8360 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -960,7 +960,7 @@ static int get_maxfds(void) struct rlimit rlim; if (getrlimit(RLIMIT_NOFILE, &rlim) == 0) - return min((int)rlim.rlim_max / 2, 512); + return min(rlim.rlim_max / 2, (rlim_t)512); return 512; } diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 7daa8bb70a5a..711d4f9f5645 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -91,6 +91,11 @@ from __future__ import print_function import sys +# Only change warnings if the python -W option was not used +if not sys.warnoptions: + import warnings + # PySide2 causes deprecation warnings, ignore them. + warnings.filterwarnings("ignore", category=DeprecationWarning) import argparse import weakref import threading @@ -125,8 +130,9 @@ if pyside_version_1: from PySide.QtGui import * from PySide.QtSql import * -from decimal import * -from ctypes import * +from decimal import Decimal, ROUND_HALF_UP +from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \ + c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong from multiprocessing import Process, Array, Value, Event # xrange is range in Python3 @@ -3868,7 +3874,7 @@ def CopyTableCellsToClipboard(view, as_csv=False, with_hdr=False): if with_hdr: model = indexes[0].model() for col in range(min_col, max_col + 1): - val = model.headerData(col, Qt.Horizontal) + val = model.headerData(col, Qt.Horizontal, Qt.DisplayRole) if as_csv: text += sep + ToCSValue(val) sep = "," diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 4a7b8deef3fd..8c10955eff93 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=1 comm=1 diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c index 76a53126efdf..d4b0ef74defc 100644 --- a/tools/perf/tests/pfm.c +++ b/tools/perf/tests/pfm.c @@ -131,8 +131,8 @@ static int test__pfm_group(void) }, { .events = "{},{instructions}", - .nr_events = 0, - .nr_groups = 0, + .nr_events = 1, + .nr_groups = 1, }, { .events = "{instructions},{instructions}", diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh index 22eb31e48ca7..2f9948b3d943 100755 --- a/tools/perf/tests/shell/stat_bpf_counters.sh +++ b/tools/perf/tests/shell/stat_bpf_counters.sh @@ -11,9 +11,9 @@ compare_number() second_num=$2 # upper bound is first_num * 110% - upper=$(( $first_num + $first_num / 10 )) + upper=$(expr $first_num + $first_num / 10 ) # lower bound is first_num * 90% - lower=$(( $first_num - $first_num / 10 )) + lower=$(expr $first_num - $first_num / 10 ) if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then echo "The difference between $first_num and $second_num are greater than 10%." diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index b8fc5c53ba6f..0d8e3dcb7f88 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); - -extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ddb52f748c8e..5ed674a2f55e 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -451,10 +451,10 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, goto out; } - err = -1; link = bpf_program__attach(skel->progs.on_switch); - if (!link) { + if (IS_ERR(link)) { pr_err("Failed to attach leader program\n"); + err = PTR_ERR(link); goto out; } @@ -521,9 +521,10 @@ static int bperf__load(struct evsel *evsel, struct target *target) evsel->bperf_leader_link_fd = bpf_link_get_fd_by_id(entry.link_id); if (evsel->bperf_leader_link_fd < 0 && - bperf_reload_leader_program(evsel, attr_map_fd, &entry)) + bperf_reload_leader_program(evsel, attr_map_fd, &entry)) { + err = -1; goto out; - + } /* * The bpf_link holds reference to the leader program, and the * leader program holds reference to the maps. Therefore, if @@ -550,6 +551,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) /* Step 2: load the follower skeleton */ evsel->follower_skel = bperf_follower_bpf__open(); if (!evsel->follower_skel) { + err = -1; pr_err("Failed to open follower skeleton\n"); goto out; } diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index b2f4920e19a6..7d2ba8419b0c 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -975,9 +975,13 @@ static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) if ((tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) && die_compare_name(die_mem, fvp->name) && - /* Does the DIE have location information or external instance? */ + /* + * Does the DIE have location information or const value + * or external instance? + */ (dwarf_attr(die_mem, DW_AT_external, &attr) || - dwarf_attr(die_mem, DW_AT_location, &attr))) + dwarf_attr(die_mem, DW_AT_location, &attr) || + dwarf_attr(die_mem, DW_AT_const_value, &attr))) return DIE_FIND_CB_END; if (dwarf_haspc(die_mem, fvp->addr)) return DIE_FIND_CB_CONTINUE; diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 9130f6fad8d5..bc5e4f294e9e 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -144,6 +144,7 @@ static void perf_env__purge_bpf(struct perf_env *env) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); rb_erase(&node->rb_node, root); + free(node->info_linear); free(node); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 8a62fb39e365..19ad64f2bd83 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -100,7 +100,7 @@ enum { PERF_IP_FLAG_VMEXIT = 1ULL << 12, }; -#define PERF_IP_FLAG_CHARS "bcrosyiABEx" +#define PERF_IP_FLAG_CHARS "bcrosyiABExgh" #define PERF_BRANCH_MASK (\ PERF_IP_FLAG_BRANCH |\ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 6e5c41528c7d..6ea3e677dc1e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -425,9 +425,6 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name) if (affinity__setup(&affinity) < 0) return; - evlist__for_each_entry(evlist, pos) - bpf_counter__disable(pos); - /* Disable 'immediate' events last */ for (imm = 0; imm <= 1; imm++) { evlist__for_each_cpu(evlist, i, cpu) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4a3cd1b5bb33..a8d8463f8ee5 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -428,6 +428,7 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->auto_merge_stats = orig->auto_merge_stats; evsel->collect_stat = orig->collect_stat; evsel->weak_group = orig->weak_group; + evsel->use_config_name = orig->use_config_name; if (evsel__copy_config_terms(evsel, orig) < 0) goto out_err; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 75cf5dbfe208..bdad52a06438 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -83,8 +83,10 @@ struct evsel { bool collect_stat; bool weak_group; bool bpf_counter; + bool use_config_name; int bpf_fd; struct bpf_object *bpf_obj; + struct list_head config_terms; }; /* @@ -116,10 +118,8 @@ struct evsel { bool merged_stat; bool reset_group; bool errored; - bool use_config_name; struct hashmap *per_pkg_mask; struct evsel *leader; - struct list_head config_terms; int err; int cpu_iter; struct { diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 8c59677bee13..20ad663978cc 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1146,6 +1146,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) decoder->set_fup_tx_flags = false; decoder->tx_flags = decoder->fup_tx_flags; decoder->state.type = INTEL_PT_TRANSACTION; + if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX) + decoder->state.type |= INTEL_PT_BRANCH; decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; decoder->state.flags = decoder->fup_tx_flags; @@ -1220,8 +1222,10 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) return 0; if (err == -EAGAIN || intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { + bool no_tip = decoder->pkt_state != INTEL_PT_STATE_FUP; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - if (intel_pt_fup_event(decoder)) + if (intel_pt_fup_event(decoder) && no_tip) return 0; return -EAGAIN; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 8658d42ce57a..0dfec8761b9a 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -707,8 +707,10 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, *ip += intel_pt_insn->length; - if (to_ip && *ip == to_ip) + if (to_ip && *ip == to_ip) { + intel_pt_insn->length = 0; goto out_no_cache; + } if (*ip >= al.map->end) break; @@ -1198,6 +1200,7 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt, static void intel_pt_sample_flags(struct intel_pt_queue *ptq) { + ptq->insn_len = 0; if (ptq->state->flags & INTEL_PT_ABORT_TX) { ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT; } else if (ptq->state->flags & INTEL_PT_ASYNC) { @@ -1211,7 +1214,6 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq) ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT; - ptq->insn_len = 0; } else { if (ptq->state->from_ip) ptq->flags = intel_pt_insn_type(ptq->state->insn_op); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 3ff4936a15a4..da19be7da284 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -776,10 +776,10 @@ static int machine__process_ksymbol_register(struct machine *machine, if (dso) { dso->kernel = DSO_SPACE__KERNEL; map = map__new2(0, dso); + dso__put(dso); } if (!dso || !map) { - dso__put(dso); return -ENOMEM; } @@ -792,6 +792,7 @@ static int machine__process_ksymbol_register(struct machine *machine, map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; maps__insert(&machine->kmaps, map); + map__put(map); dso__set_loaded(dso); if (is_bpf_image(event->ksymbol.name)) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 8336dd8e8098..d3cf2dee36c8 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -162,10 +162,10 @@ static bool contains_event(struct evsel **metric_events, int num_events, return false; } -static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2) +static bool evsel_same_pmu_or_none(struct evsel *ev1, struct evsel *ev2) { if (!ev1->pmu_name || !ev2->pmu_name) - return false; + return true; return !strcmp(ev1->pmu_name, ev2->pmu_name); } @@ -288,7 +288,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, */ if (!has_constraint && ev->leader != metric_events[i]->leader && - evsel_same_pmu(ev->leader, metric_events[i]->leader)) + evsel_same_pmu_or_none(ev->leader, metric_events[i]->leader)) break; if (!strcmp(metric_events[i]->name, ev->name)) { set_bit(ev->idx, evlist_used); @@ -1073,16 +1073,18 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); if (ret) - return ret; + goto out; ret = resolve_metric(d->metric_no_group, d->metric_list, NULL, d->ids); if (ret) - return ret; + goto out; *(d->has_match) = true; - return *d->ret; +out: + *(d->ret) = ret; + return ret; } static int metricgroup__add_metric(const char *metric, bool metric_no_group, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4dad14265b81..84108c17f48d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -150,6 +150,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { .symbol = "bpf-output", .alias = "", }, + [PERF_COUNT_SW_CGROUP_SWITCHES] = { + .symbol = "cgroup-switches", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -2928,9 +2932,14 @@ restart: } for (i = 0; i < max; i++, syms++) { + /* + * New attr.config still not supported here, the latest + * example was PERF_COUNT_SW_CGROUP_SWITCHES + */ + if (syms->symbol == NULL) + continue; - if (event_glob != NULL && syms->symbol != NULL && - !(strglobmatch(syms->symbol, event_glob) || + if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index fb8646cc3e83..923849024b15 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -347,6 +347,7 @@ emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EM dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } +cgroup-switches { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); } /* * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately. diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 829af17a0867..020411682a3c 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -103,6 +103,11 @@ static void perf_probe_build_id(struct evsel *evsel) evsel->core.attr.build_id = 1; } +static void perf_probe_cgroup(struct evsel *evsel) +{ + evsel->core.attr.cgroup = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); @@ -182,3 +187,8 @@ bool perf_can_record_build_id(void) { return perf_probe_api(perf_probe_build_id); } + +bool perf_can_record_cgroup(void) +{ + return perf_probe_api(perf_probe_cgroup); +} diff --git a/tools/perf/util/perf_api_probe.h b/tools/perf/util/perf_api_probe.h index f12ca55f509a..b104168efb15 100644 --- a/tools/perf/util/perf_api_probe.h +++ b/tools/perf/util/perf_api_probe.h @@ -12,5 +12,6 @@ bool perf_can_record_switch_events(void); bool perf_can_record_text_poke_events(void); bool perf_can_sample_identifier(void); bool perf_can_record_build_id(void); +bool perf_can_record_cgroup(void); #endif // __PERF_API_PROBE_H diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index d735acb6c29c..6eef6dfeaa57 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -62,8 +62,16 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, } /* no event */ - if (*q == '\0') + if (*q == '\0') { + if (*sep == '}') { + if (grp_evt < 0) { + ui__error("cannot close a non-existing event group\n"); + goto error; + } + grp_evt--; + } continue; + } memset(&attr, 0, sizeof(attr)); event_attr_init(&attr); @@ -107,6 +115,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, grp_evt = -1; } } + free(p_orig); return 0; error: free(p_orig); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 866f2d514d72..b029c29ce227 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -190,6 +190,9 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, immediate_value_is_supported()) { Dwarf_Sword snum; + if (!tvar) + return 0; + dwarf_formsdata(&attr, &snum); ret = asprintf(&tvar->value, "\\%ld", (long)snum); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 106b3d60881a..e59242c361ce 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1723,6 +1723,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, if (event->header.size < hdr_sz || event->header.size > buf_sz) return -1; + buf += hdr_sz; rest = event->header.size - hdr_sz; if (readn(fd, buf, rest) != (ssize_t)rest) diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index a76fff5e7d83..ca326f98c7a2 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -541,7 +541,7 @@ static void uniquify_event_name(struct evsel *counter) char *config; int ret = 0; - if (counter->uniquified_name || + if (counter->uniquified_name || counter->use_config_name || !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, strlen(counter->pmu_name))) return; @@ -555,10 +555,8 @@ static void uniquify_event_name(struct evsel *counter) } } else { if (perf_pmu__has_hybrid()) { - if (!counter->use_config_name) { - ret = asprintf(&new_name, "%s/%s/", - counter->pmu_name, counter->name); - } + ret = asprintf(&new_name, "%s/%s/", + counter->pmu_name, counter->name); } else { ret = asprintf(&new_name, "%s [%s]", counter->name, counter->pmu_name); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 4c56aa837434..a73345730ba9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -2412,6 +2412,7 @@ int cleanup_sdt_note_list(struct list_head *sdt_notes) list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) { list_del_init(&pos->note_list); + zfree(&pos->args); zfree(&pos->name); zfree(&pos->provider); free(pos); diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 12ee40284da0..2060bc122c53 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -40,7 +40,7 @@ struct ipv6_packet pkt_v6 = { .tcp.doff = 5, }; -static int settimeo(int fd, int timeout_ms) +int settimeo(int fd, int timeout_ms) { struct timeval timeout = { .tv_sec = 3 }; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 7205f8afdba1..5e0d51c07b63 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -33,6 +33,7 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; +int settimeo(int fd, int timeout_ms); int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); int connect_to_fd(int server_fd, int timeout_ms); diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index de78617f6550..f9a8ae331963 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -86,8 +86,9 @@ void test_ringbuf(void) const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample); pthread_t thread; long bg_ret = -1; - int err, cnt; + int err, cnt, rb_fd; int page_size = getpagesize(); + void *mmap_ptr, *tmp_ptr; skel = test_ringbuf__open(); if (CHECK(!skel, "skel_open", "skeleton open failed\n")) @@ -101,6 +102,52 @@ void test_ringbuf(void) if (CHECK(err != 0, "skel_load", "skeleton load failed\n")) goto cleanup; + rb_fd = bpf_map__fd(skel->maps.ringbuf); + /* good read/write cons_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0); + ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"); + tmp_ptr = mremap(mmap_ptr, page_size, 2 * page_size, MREMAP_MAYMOVE); + if (!ASSERT_ERR_PTR(tmp_ptr, "rw_extend")) + goto cleanup; + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_cons_pos_protect"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw"); + + /* bad writeable prod_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_prod_pos"); + ASSERT_EQ(err, -EPERM, "wr_prod_pos_err"); + + /* bad writeable data pages */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_one"); + ASSERT_EQ(err, -EPERM, "wr_data_page_one_err"); + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 3 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_two"); + mmap_ptr = mmap(NULL, 2 * page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_all"); + + /* good read-only pages */ + mmap_ptr = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED, rb_fd, 0); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 4 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, 4 * page_size), "unmap_ro"); + + /* good read-only pages with initial offset */ + mmap_ptr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, rb_fd, page_size); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 3 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_ro"); + /* only trigger BPF program for current process */ skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c new file mode 100644 index 000000000000..5703c918812b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -0,0 +1,785 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link + * between src and dst. The netns fwd has veth links to each src and dst. The + * client is in src and server in dst. The test installs a TC BPF program to each + * host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the + * neigh addr population and redirect or ii) bpf_redirect_peer() for namespace + * switch from ingress side; it also installs a checker prog on the egress side + * to drop unexpected traffic. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <linux/limits.h> +#include <linux/sysctl.h> +#include <linux/if_tun.h> +#include <linux/if.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <sys/stat.h> +#include <sys/mount.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "test_tc_neigh_fib.skel.h" +#include "test_tc_neigh.skel.h" +#include "test_tc_peer.skel.h" + +#define NS_SRC "ns_src" +#define NS_FWD "ns_fwd" +#define NS_DST "ns_dst" + +#define IP4_SRC "172.16.1.100" +#define IP4_DST "172.16.2.100" +#define IP4_TUN_SRC "172.17.1.100" +#define IP4_TUN_FWD "172.17.1.200" +#define IP4_PORT 9004 + +#define IP6_SRC "0::1:dead:beef:cafe" +#define IP6_DST "0::2:dead:beef:cafe" +#define IP6_TUN_SRC "1::1:dead:beef:cafe" +#define IP6_TUN_FWD "1::2:dead:beef:cafe" +#define IP6_PORT 9006 + +#define IP4_SLL "169.254.0.1" +#define IP4_DLL "169.254.0.2" +#define IP4_NET "169.254.0.0" + +#define MAC_DST_FWD "00:11:22:33:44:55" +#define MAC_DST "00:22:33:44:55:66" + +#define IFADDR_STR_LEN 18 +#define PING_ARGS "-i 0.2 -c 3 -w 10 -q" + +#define SRC_PROG_PIN_FILE "/sys/fs/bpf/test_tc_src" +#define DST_PROG_PIN_FILE "/sys/fs/bpf/test_tc_dst" +#define CHK_PROG_PIN_FILE "/sys/fs/bpf/test_tc_chk" + +#define TIMEOUT_MILLIS 10000 + +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, strerror(errno), ##__VA_ARGS__) + +static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL}; + +static int write_file(const char *path, const char *newval) +{ + FILE *f; + + f = fopen(path, "r+"); + if (!f) + return -1; + if (fwrite(newval, strlen(newval), 1, f) != 1) { + log_err("writing to %s failed", path); + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +struct nstoken { + int orig_netns_fd; +}; + +static int setns_by_fd(int nsfd) +{ + int err; + + err = setns(nsfd, CLONE_NEWNET); + close(nsfd); + + if (!ASSERT_OK(err, "setns")) + return err; + + /* Switch /sys to the new namespace so that e.g. /sys/class/net + * reflects the devices in the new namespace. + */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "unshare")) + return err; + + err = umount2("/sys", MNT_DETACH); + if (!ASSERT_OK(err, "umount2 /sys")) + return err; + + err = mount("sysfs", "/sys", "sysfs", 0, NULL); + if (!ASSERT_OK(err, "mount /sys")) + return err; + + err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); + if (!ASSERT_OK(err, "mount /sys/fs/bpf")) + return err; + + return 0; +} + +/** + * open_netns() - Switch to specified network namespace by name. + * + * Returns token with which to restore the original namespace + * using close_netns(). + */ +static struct nstoken *open_netns(const char *name) +{ + int nsfd; + char nspath[PATH_MAX]; + int err; + struct nstoken *token; + + token = malloc(sizeof(struct nstoken)); + if (!ASSERT_OK_PTR(token, "malloc token")) + return NULL; + + token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) + goto fail; + + snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); + nsfd = open(nspath, O_RDONLY | O_CLOEXEC); + if (!ASSERT_GE(nsfd, 0, "open netns fd")) + goto fail; + + err = setns_by_fd(nsfd); + if (!ASSERT_OK(err, "setns_by_fd")) + goto fail; + + return token; +fail: + free(token); + return NULL; +} + +static void close_netns(struct nstoken *token) +{ + ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); + free(token); +} + +static int netns_setup_namespaces(const char *verb) +{ + const char * const *ns = namespaces; + char cmd[128]; + + while (*ns) { + snprintf(cmd, sizeof(cmd), "ip netns %s %s", verb, *ns); + if (!ASSERT_OK(system(cmd), cmd)) + return -1; + ns++; + } + return 0; +} + +struct netns_setup_result { + int ifindex_veth_src_fwd; + int ifindex_veth_dst_fwd; +}; + +static int get_ifaddr(const char *name, char *ifaddr) +{ + char path[PATH_MAX]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/address", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(ifaddr, 1, IFADDR_STR_LEN, f); + if (!ASSERT_EQ(ret, IFADDR_STR_LEN, "fread ifaddr")) { + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +static int get_ifindex(const char *name) +{ + char path[PATH_MAX]; + char buf[32]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/ifindex", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(buf, 1, sizeof(buf), f); + if (!ASSERT_GT(ret, 0, "fread ifindex")) { + fclose(f); + return -1; + } + fclose(f); + return atoi(buf); +} + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto fail; \ + }) + +static int netns_setup_links_and_routes(struct netns_setup_result *result) +{ + struct nstoken *nstoken = NULL; + char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {}; + + SYS("ip link add veth_src type veth peer name veth_src_fwd"); + SYS("ip link add veth_dst type veth peer name veth_dst_fwd"); + + SYS("ip link set veth_dst_fwd address " MAC_DST_FWD); + SYS("ip link set veth_dst address " MAC_DST); + + if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr)) + goto fail; + + result->ifindex_veth_src_fwd = get_ifindex("veth_src_fwd"); + if (result->ifindex_veth_src_fwd < 0) + goto fail; + result->ifindex_veth_dst_fwd = get_ifindex("veth_dst_fwd"); + if (result->ifindex_veth_dst_fwd < 0) + goto fail; + + SYS("ip link set veth_src netns " NS_SRC); + SYS("ip link set veth_src_fwd netns " NS_FWD); + SYS("ip link set veth_dst_fwd netns " NS_FWD); + SYS("ip link set veth_dst netns " NS_DST); + + /** setup in 'src' namespace */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto fail; + + SYS("ip addr add " IP4_SRC "/32 dev veth_src"); + SYS("ip addr add " IP6_SRC "/128 dev veth_src nodad"); + SYS("ip link set dev veth_src up"); + + SYS("ip route add " IP4_DST "/32 dev veth_src scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_src scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_src scope global"); + + SYS("ip neigh add " IP4_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + SYS("ip neigh add " IP6_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + + close_netns(nstoken); + + /** setup in 'fwd' namespace */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto fail; + + /* The fwd netns automatically gets a v6 LL address / routes, but also + * needs v4 one in order to start ARP probing. IP4_NET route is added + * to the endpoints so that the ARP processing will reply. + */ + SYS("ip addr add " IP4_SLL "/32 dev veth_src_fwd"); + SYS("ip addr add " IP4_DLL "/32 dev veth_dst_fwd"); + SYS("ip link set dev veth_src_fwd up"); + SYS("ip link set dev veth_dst_fwd up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_src_fwd scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_src_fwd scope global"); + SYS("ip route add " IP4_DST "/32 dev veth_dst_fwd scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_dst_fwd scope global"); + + close_netns(nstoken); + + /** setup in 'dst' namespace */ + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + goto fail; + + SYS("ip addr add " IP4_DST "/32 dev veth_dst"); + SYS("ip addr add " IP6_DST "/128 dev veth_dst nodad"); + SYS("ip link set dev veth_dst up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_dst scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_dst scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_dst scope global"); + + SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + close_netns(nstoken); + + return 0; +fail: + if (nstoken) + close_netns(nstoken); + return -1; +} + +static int netns_load_bpf(void) +{ + SYS("tc qdisc add dev veth_src_fwd clsact"); + SYS("tc filter add dev veth_src_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + SYS("tc filter add dev veth_src_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + return 0; +fail: + return -1; +} + +static void test_tcp(int family, const char *addr, __u16 port) +{ + int listen_fd = -1, accept_fd = -1, client_fd = -1; + char buf[] = "testing testing"; + int n; + struct nstoken *nstoken; + + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + return; + + listen_fd = start_server(family, SOCK_STREAM, addr, port, 0); + if (!ASSERT_GE(listen_fd, 0, "listen")) + goto done; + + close_netns(nstoken); + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto done; + + client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto done; + + accept_fd = accept(listen_fd, NULL, NULL); + if (!ASSERT_GE(accept_fd, 0, "accept")) + goto done; + + if (!ASSERT_OK(settimeo(accept_fd, TIMEOUT_MILLIS), "settimeo")) + goto done; + + n = write(client_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + + n = read(accept_fd, buf, sizeof(buf)); + ASSERT_EQ(n, sizeof(buf), "recv from server"); + +done: + if (nstoken) + close_netns(nstoken); + if (listen_fd >= 0) + close(listen_fd); + if (accept_fd >= 0) + close(accept_fd); + if (client_fd >= 0) + close(client_fd); +} + +static int test_ping(int family, const char *addr) +{ + const char *ping = family == AF_INET6 ? "ping6" : "ping"; + + SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping, addr); + return 0; +fail: + return -1; +} + +static void test_connectivity(void) +{ + test_tcp(AF_INET, IP4_DST, IP4_PORT); + test_ping(AF_INET, IP4_DST); + test_tcp(AF_INET6, IP6_DST, IP6_PORT); + test_ping(AF_INET6, IP6_DST); +} + +static int set_forwarding(bool enable) +{ + int err; + + err = write_file("/proc/sys/net/ipv4/ip_forward", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv4.ip_forward=0")) + return err; + + err = write_file("/proc/sys/net/ipv6/conf/all/forwarding", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv6.forwarding=0")) + return err; + + return 0; +} + +static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh_fib *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh_fib__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh_fib__open")) + goto done; + + if (!ASSERT_OK(test_tc_neigh_fib__load(skel), "test_tc_neigh_fib__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + /* bpf_fib_lookup() checks if forwarding is enabled */ + if (!ASSERT_OK(set_forwarding(true), "enable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh_fib__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_neigh(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_neigh__load(skel); + if (!ASSERT_OK(err, "test_tc_neigh__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_peer(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken; + struct test_tc_peer *skel; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_peer__destroy(skel); + close_netns(nstoken); +} + +static int tun_open(char *name) +{ + struct ifreq ifr; + int fd, err; + + fd = open("/dev/net/tun", O_RDWR); + if (!ASSERT_GE(fd, 0, "open /dev/net/tun")) + return -1; + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_flags = IFF_TUN | IFF_NO_PI; + if (*name) + strncpy(ifr.ifr_name, name, IFNAMSIZ); + + err = ioctl(fd, TUNSETIFF, &ifr); + if (!ASSERT_OK(err, "ioctl TUNSETIFF")) + goto fail; + + SYS("ip link set dev %s up", name); + + return fd; +fail: + close(fd); + return -1; +} + +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +enum { + SRC_TO_TARGET = 0, + TARGET_TO_SRC = 1, +}; + +static int tun_relay_loop(int src_fd, int target_fd) +{ + fd_set rfds, wfds; + + FD_ZERO(&rfds); + FD_ZERO(&wfds); + + for (;;) { + char buf[1500]; + int direction, nread, nwrite; + + FD_SET(src_fd, &rfds); + FD_SET(target_fd, &rfds); + + if (select(1 + MAX(src_fd, target_fd), &rfds, NULL, NULL, NULL) < 0) { + log_err("select failed"); + return 1; + } + + direction = FD_ISSET(src_fd, &rfds) ? SRC_TO_TARGET : TARGET_TO_SRC; + + nread = read(direction == SRC_TO_TARGET ? src_fd : target_fd, buf, sizeof(buf)); + if (nread < 0) { + log_err("read failed"); + return 1; + } + + nwrite = write(direction == SRC_TO_TARGET ? target_fd : src_fd, buf, nread); + if (nwrite != nread) { + log_err("write failed"); + return 1; + } + } +} + +static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) +{ + struct test_tc_peer *skel = NULL; + struct nstoken *nstoken = NULL; + int err; + int tunnel_pid = -1; + int src_fd, target_fd; + int ifindex; + + /* Start a L3 TUN/TAP tunnel between the src and dst namespaces. + * This test is using TUN/TAP instead of e.g. IPIP or GRE tunnel as those + * expose the L2 headers encapsulating the IP packet to BPF and hence + * don't have skb in suitable state for this test. Alternative to TUN/TAP + * would be e.g. Wireguard which would appear as a pure L3 device to BPF, + * but that requires much more complicated setup. + */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) + return; + + src_fd = tun_open("tun_src"); + if (!ASSERT_GE(src_fd, 0, "tun_open tun_src")) + goto fail; + + close_netns(nstoken); + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) + goto fail; + + target_fd = tun_open("tun_fwd"); + if (!ASSERT_GE(target_fd, 0, "tun_open tun_fwd")) + goto fail; + + tunnel_pid = fork(); + if (!ASSERT_GE(tunnel_pid, 0, "fork tun_relay_loop")) + goto fail; + + if (tunnel_pid == 0) + exit(tun_relay_loop(src_fd, target_fd)); + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto fail; + + ifindex = get_ifindex("tun_fwd"); + if (!ASSERT_GE(ifindex, 0, "get_ifindex tun_fwd")) + goto fail; + + skel->rodata->IFINDEX_SRC = ifindex; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto fail; + + err = bpf_program__pin(skel->progs.tc_src_l3, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_dst_l3, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto fail; + + /* Load "tc_src_l3" to the tun_fwd interface to redirect packets + * towards dst, and "tc_dst" to redirect packets + * and "tc_chk" on veth_dst_fwd to drop non-redirected packets. + */ + SYS("tc qdisc add dev tun_fwd clsact"); + SYS("tc filter add dev tun_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + /* Setup route and neigh tables */ + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP4_TUN_FWD "/24"); + + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad"); + + SYS("ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global"); + SYS("ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global"); + + SYS("ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto fail; + + test_connectivity(); + +fail: + if (tunnel_pid > 0) { + kill(tunnel_pid, SIGTERM); + waitpid(tunnel_pid, NULL, 0); + } + if (src_fd >= 0) + close(src_fd); + if (target_fd >= 0) + close(target_fd); + if (skel) + test_tc_peer__destroy(skel); + if (nstoken) + close_netns(nstoken); +} + +#define RUN_TEST(name) \ + ({ \ + struct netns_setup_result setup_result; \ + if (test__start_subtest(#name)) \ + if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \ + if (ASSERT_OK(netns_setup_links_and_routes(&setup_result), \ + "setup links and routes")) \ + test_ ## name(&setup_result); \ + netns_setup_namespaces("delete"); \ + } \ + }) + +static void *test_tc_redirect_run_tests(void *arg) +{ + RUN_TEST(tc_redirect_peer); + RUN_TEST(tc_redirect_peer_l3); + RUN_TEST(tc_redirect_neigh); + RUN_TEST(tc_redirect_neigh_fib); + return NULL; +} + +void test_tc_redirect(void) +{ + pthread_t test_thread; + int err; + + /* Run the tests in their own thread to isolate the namespace changes + * so they do not affect the environment of other tests. + * (specifically needed because of unshare(CLONE_NEWNS) in open_netns()) + */ + err = pthread_create(&test_thread, NULL, &test_tc_redirect_run_tests, NULL); + if (ASSERT_OK(err, "pthread_create")) + ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join"); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index b985ac4e7a81..0c93d326a663 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -33,17 +33,8 @@ a.s6_addr32[3] == b.s6_addr32[3]) #endif -enum { - dev_src, - dev_dst, -}; - -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb, __be32 addr) @@ -79,14 +70,8 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -static __always_inline int get_dev_ifindex(int which) -{ - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); - - return ifindex ? *ifindex : 0; -} - -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -98,7 +83,8 @@ SEC("chk_egress") int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -119,10 +105,11 @@ SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_src), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -143,7 +130,7 @@ SEC("src_ingress") int tc_src(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_dst), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index d82ed3457030..f7ab69cf018e 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,8 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -142,12 +143,14 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { return tc_redir(skb); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fc84a7685aa2..fe818cd5f010 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -5,41 +5,59 @@ #include <linux/bpf.h> #include <linux/stddef.h> #include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/ip.h> #include <bpf/bpf_helpers.h> -enum { - dev_src, - dev_dst, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; +static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -static __always_inline int get_dev_ifindex(int which) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); + return TC_ACT_SHOT; +} - return ifindex ? *ifindex : 0; +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) +{ + return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { - return TC_ACT_SHOT; + return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress_l3") +int tc_dst_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_src), 0); + return bpf_redirect(IFINDEX_SRC, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress_l3") +int tc_src_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_dst), 0); + __u16 proto = skb->protocol; + + if (bpf_skb_change_head(skb, ETH_HLEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, 0, &src_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN, &dst_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN + ETH_ALEN, &proto, sizeof(__u16), 0) != 0) + return TC_ACT_SHOT; + + return bpf_redirect_peer(IFINDEX_DST, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tc_redirect.sh b/tools/testing/selftests/bpf/test_tc_redirect.sh deleted file mode 100755 index 8868aa1ca902..000000000000 --- a/tools/testing/selftests/bpf/test_tc_redirect.sh +++ /dev/null @@ -1,216 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link -# between src and dst. The netns fwd has veth links to each src and dst. The -# client is in src and server in dst. The test installs a TC BPF program to each -# host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the -# neigh addr population and redirect or ii) bpf_redirect_peer() for namespace -# switch from ingress side; it also installs a checker prog on the egress side -# to drop unexpected traffic. - -if [[ $EUID -ne 0 ]]; then - echo "This script must be run as root" - echo "FAIL" - exit 1 -fi - -# check that needed tools are present -command -v nc >/dev/null 2>&1 || \ - { echo >&2 "nc is not available"; exit 1; } -command -v dd >/dev/null 2>&1 || \ - { echo >&2 "dd is not available"; exit 1; } -command -v timeout >/dev/null 2>&1 || \ - { echo >&2 "timeout is not available"; exit 1; } -command -v ping >/dev/null 2>&1 || \ - { echo >&2 "ping is not available"; exit 1; } -if command -v ping6 >/dev/null 2>&1; then PING6=ping6; else PING6=ping; fi -command -v perl >/dev/null 2>&1 || \ - { echo >&2 "perl is not available"; exit 1; } -command -v jq >/dev/null 2>&1 || \ - { echo >&2 "jq is not available"; exit 1; } -command -v bpftool >/dev/null 2>&1 || \ - { echo >&2 "bpftool is not available"; exit 1; } - -readonly GREEN='\033[0;92m' -readonly RED='\033[0;31m' -readonly NC='\033[0m' # No Color - -readonly PING_ARG="-c 3 -w 10 -q" - -readonly TIMEOUT=10 - -readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)" -readonly NS_FWD="ns-fwd-$(mktemp -u XXXXXX)" -readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)" - -readonly IP4_SRC="172.16.1.100" -readonly IP4_DST="172.16.2.100" - -readonly IP6_SRC="::1:dead:beef:cafe" -readonly IP6_DST="::2:dead:beef:cafe" - -readonly IP4_SLL="169.254.0.1" -readonly IP4_DLL="169.254.0.2" -readonly IP4_NET="169.254.0.0" - -netns_cleanup() -{ - ip netns del ${NS_SRC} - ip netns del ${NS_FWD} - ip netns del ${NS_DST} -} - -netns_setup() -{ - ip netns add "${NS_SRC}" - ip netns add "${NS_FWD}" - ip netns add "${NS_DST}" - - ip link add veth_src type veth peer name veth_src_fwd - ip link add veth_dst type veth peer name veth_dst_fwd - - ip link set veth_src netns ${NS_SRC} - ip link set veth_src_fwd netns ${NS_FWD} - - ip link set veth_dst netns ${NS_DST} - ip link set veth_dst_fwd netns ${NS_FWD} - - ip -netns ${NS_SRC} addr add ${IP4_SRC}/32 dev veth_src - ip -netns ${NS_DST} addr add ${IP4_DST}/32 dev veth_dst - - # The fwd netns automatically get a v6 LL address / routes, but also - # needs v4 one in order to start ARP probing. IP4_NET route is added - # to the endpoints so that the ARP processing will reply. - - ip -netns ${NS_FWD} addr add ${IP4_SLL}/32 dev veth_src_fwd - ip -netns ${NS_FWD} addr add ${IP4_DLL}/32 dev veth_dst_fwd - - ip -netns ${NS_SRC} addr add ${IP6_SRC}/128 dev veth_src nodad - ip -netns ${NS_DST} addr add ${IP6_DST}/128 dev veth_dst nodad - - ip -netns ${NS_SRC} link set dev veth_src up - ip -netns ${NS_FWD} link set dev veth_src_fwd up - - ip -netns ${NS_DST} link set dev veth_dst up - ip -netns ${NS_FWD} link set dev veth_dst_fwd up - - ip -netns ${NS_SRC} route add ${IP4_DST}/32 dev veth_src scope global - ip -netns ${NS_SRC} route add ${IP4_NET}/16 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP4_SRC}/32 dev veth_src_fwd scope global - - ip -netns ${NS_SRC} route add ${IP6_DST}/128 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP6_SRC}/128 dev veth_src_fwd scope global - - ip -netns ${NS_DST} route add ${IP4_SRC}/32 dev veth_dst scope global - ip -netns ${NS_DST} route add ${IP4_NET}/16 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP4_DST}/32 dev veth_dst_fwd scope global - - ip -netns ${NS_DST} route add ${IP6_SRC}/128 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP6_DST}/128 dev veth_dst_fwd scope global - - fmac_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/address) - fmac_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/address) - - ip -netns ${NS_SRC} neigh add ${IP4_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP4_SRC} dev veth_dst lladdr $fmac_dst - - ip -netns ${NS_SRC} neigh add ${IP6_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP6_SRC} dev veth_dst lladdr $fmac_dst -} - -netns_test_connectivity() -{ - set +e - - ip netns exec ${NS_DST} bash -c "nc -4 -l -p 9004 &" - ip netns exec ${NS_DST} bash -c "nc -6 -l -p 9006 &" - - TEST="TCPv4 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP4_DST}/9004" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="TCPv6 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP6_DST}/9006" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv4 connectivity test" - ip netns exec ${NS_SRC} ping $PING_ARG ${IP4_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv6 connectivity test" - ip netns exec ${NS_SRC} $PING6 $PING_ARG ${IP6_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - set -e -} - -hex_mem_str() -{ - perl -e 'print join(" ", unpack("(H2)8", pack("L", @ARGV)))' $1 -} - -netns_setup_bpf() -{ - local obj=$1 - local use_forwarding=${2:-0} - - ip netns exec ${NS_FWD} tc qdisc add dev veth_src_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd ingress bpf da obj $obj sec src_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd egress bpf da obj $obj sec chk_egress - - ip netns exec ${NS_FWD} tc qdisc add dev veth_dst_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd ingress bpf da obj $obj sec dst_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd egress bpf da obj $obj sec chk_egress - - if [ "$use_forwarding" -eq "1" ]; then - # bpf_fib_lookup() checks if forwarding is enabled - ip netns exec ${NS_FWD} sysctl -w net.ipv4.ip_forward=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_dst_fwd.forwarding=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_src_fwd.forwarding=1 - return 0 - fi - - veth_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/ifindex) - veth_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/ifindex) - - progs=$(ip netns exec ${NS_FWD} bpftool net --json | jq -r '.[] | .tc | map(.id) | .[]') - for prog in $progs; do - map=$(bpftool prog show id $prog --json | jq -r '.map_ids | .? | .[]') - if [ ! -z "$map" ]; then - bpftool map update id $map key hex $(hex_mem_str 0) value hex $(hex_mem_str $veth_src) - bpftool map update id $map key hex $(hex_mem_str 1) value hex $(hex_mem_str $veth_dst) - fi - done -} - -trap netns_cleanup EXIT -set -e - -netns_setup -netns_setup_bpf test_tc_neigh.o -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_neigh_fib.o 1 -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_peer.o -netns_test_connectivity diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 1512092e1e68..3a9e332c5e36 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1147,7 +1147,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } } - if (test->insn_processed) { + if (!unpriv && test->insn_processed) { uint32_t insn_processed; char *proc; diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c index ca8fdb1b3f01..7d7ebee5cc7a 100644 --- a/tools/testing/selftests/bpf/verifier/and.c +++ b/tools/testing/selftests/bpf/verifier/and.c @@ -61,6 +61,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R1 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 0 }, diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 8a1caf46ffbc..e061e8799ce2 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -508,6 +508,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT }, { @@ -528,6 +530,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT }, { @@ -569,6 +573,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -589,6 +595,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -609,6 +617,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -674,6 +684,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -695,6 +707,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c index 17fe33a75034..2c8935b3e65d 100644 --- a/tools/testing/selftests/bpf/verifier/dead_code.c +++ b/tools/testing/selftests/bpf/verifier/dead_code.c @@ -8,6 +8,8 @@ BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 7, }, diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c index bd5cae4a7f73..1c857b2fbdf0 100644 --- a/tools/testing/selftests/bpf/verifier/jmp32.c +++ b/tools/testing/selftests/bpf/verifier/jmp32.c @@ -87,6 +87,8 @@ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -150,6 +152,8 @@ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -213,6 +217,8 @@ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -280,6 +286,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -348,6 +356,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -416,6 +426,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -484,6 +496,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -552,6 +566,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -620,6 +636,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -688,6 +706,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -756,6 +776,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c index 8dcd4e0383d5..11fc68da735e 100644 --- a/tools/testing/selftests/bpf/verifier/jset.c +++ b/tools/testing/selftests/bpf/verifier/jset.c @@ -82,8 +82,8 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .retval_unpriv = 1, - .result_unpriv = ACCEPT, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .retval = 1, .result = ACCEPT, }, @@ -141,7 +141,8 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .result_unpriv = ACCEPT, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -162,6 +163,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .result_unpriv = ACCEPT, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c index 07eaa04412ae..8ab94d65f3d5 100644 --- a/tools/testing/selftests/bpf/verifier/stack_ptr.c +++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c @@ -295,8 +295,6 @@ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), BPF_EXIT_INSN(), }, - .result_unpriv = REJECT, - .errstr_unpriv = "invalid write to stack R1 off=0 size=1", .result = ACCEPT, .retval = 42, }, diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c index bd436df5cc32..111801aea5e3 100644 --- a/tools/testing/selftests/bpf/verifier/unpriv.c +++ b/tools/testing/selftests/bpf/verifier/unpriv.c @@ -420,6 +420,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R7 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 0, }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index e5913fd3b903..a3e593ddfafc 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -120,7 +120,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R2 tried to add from different maps, paths or scalars", + .errstr_unpriv = "R2 pointer comparison prohibited", .retval = 0, }, { @@ -159,7 +159,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), // fake-dead code; targeted from branch A to - // prevent dead code sanitization + // prevent dead code sanitization, rejected + // via branch B however BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -167,7 +168,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R2 tried to add from different maps, paths or scalars", + .errstr_unpriv = "R0 invalid mem access 'inv'", .retval = 0, }, { @@ -300,8 +301,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -371,8 +370,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -472,8 +469,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -766,8 +761,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index bd83158e0e0b..524c857a049c 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -41,5 +41,6 @@ /kvm_create_max_vcpus /kvm_page_table_test /memslot_modification_stress_test +/memslot_perf_test /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index e439d027939d..daaee1888b12 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,7 +33,7 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c @@ -74,6 +74,7 @@ TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test +TEST_GEN_PROGS_x86_64 += memslot_perf_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 5f7a229c3af1..b74704305835 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -9,6 +9,7 @@ #define _GNU_SOURCE /* for pipe2 */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -38,6 +39,7 @@ static int nr_vcpus = 1; static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static size_t demand_paging_size; static char *guest_data_prototype; static void *vcpu_worker(void *data) @@ -71,36 +73,51 @@ static void *vcpu_worker(void *data) return NULL; } -static int handle_uffd_page_request(int uffd, uint64_t addr) +static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) { - pid_t tid; + pid_t tid = syscall(__NR_gettid); struct timespec start; struct timespec ts_diff; - struct uffdio_copy copy; int r; - tid = syscall(__NR_gettid); + clock_gettime(CLOCK_MONOTONIC, &start); - copy.src = (uint64_t)guest_data_prototype; - copy.dst = addr; - copy.len = perf_test_args.host_page_size; - copy.mode = 0; + if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) { + struct uffdio_copy copy; - clock_gettime(CLOCK_MONOTONIC, &start); + copy.src = (uint64_t)guest_data_prototype; + copy.dst = addr; + copy.len = demand_paging_size; + copy.mode = 0; - r = ioctl(uffd, UFFDIO_COPY, ©); - if (r == -1) { - pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n", - addr, tid, errno); - return r; + r = ioctl(uffd, UFFDIO_COPY, ©); + if (r == -1) { + pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else if (uffd_mode == UFFDIO_REGISTER_MODE_MINOR) { + struct uffdio_continue cont = {0}; + + cont.range.start = addr; + cont.range.len = demand_paging_size; + + r = ioctl(uffd, UFFDIO_CONTINUE, &cont); + if (r == -1) { + pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else { + TEST_FAIL("Invalid uffd mode %d", uffd_mode); } ts_diff = timespec_elapsed(start); - PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, + PER_PAGE_DEBUG("UFFD page-in %d \t%ld ns\n", tid, timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - perf_test_args.host_page_size, addr, tid); + demand_paging_size, addr, tid); return 0; } @@ -108,6 +125,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) bool quit_uffd_thread; struct uffd_handler_args { + int uffd_mode; int uffd; int pipefd; useconds_t delay; @@ -169,7 +187,7 @@ static void *uffd_handler_thread_fn(void *arg) if (r == -1) { if (errno == EAGAIN) continue; - pr_info("Read of uffd gor errno %d", errno); + pr_info("Read of uffd got errno %d\n", errno); return NULL; } @@ -184,7 +202,7 @@ static void *uffd_handler_thread_fn(void *arg) if (delay) usleep(delay); addr = msg.arg.pagefault.address; - r = handle_uffd_page_request(uffd, addr); + r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr); if (r < 0) return NULL; pages++; @@ -198,43 +216,53 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } -static int setup_demand_paging(struct kvm_vm *vm, - pthread_t *uffd_handler_thread, int pipefd, - useconds_t uffd_delay, - struct uffd_handler_args *uffd_args, - void *hva, uint64_t len) +static void setup_demand_paging(struct kvm_vm *vm, + pthread_t *uffd_handler_thread, int pipefd, + int uffd_mode, useconds_t uffd_delay, + struct uffd_handler_args *uffd_args, + void *hva, void *alias, uint64_t len) { + bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR); int uffd; struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; + uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - if (uffd == -1) { - pr_info("uffd creation failed\n"); - return -1; + PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", + is_minor ? "MINOR" : "MISSING", + is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); + + /* In order to get minor faults, prefault via the alias. */ + if (is_minor) { + size_t p; + + expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE; + + TEST_ASSERT(alias != NULL, "Alias required for minor faults"); + for (p = 0; p < (len / demand_paging_size); ++p) { + memcpy(alias + (p * demand_paging_size), + guest_data_prototype, demand_paging_size); + } } + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno); + uffdio_api.api = UFFD_API; uffdio_api.features = 0; - if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { - pr_info("ioctl uffdio_api failed\n"); - return -1; - } + TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1, + "ioctl UFFDIO_API failed: %" PRIu64, + (uint64_t)uffdio_api.api); uffdio_register.range.start = (uint64_t)hva; uffdio_register.range.len = len; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { - pr_info("ioctl uffdio_register failed\n"); - return -1; - } - - if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) != - UFFD_API_RANGE_IOCTLS) { - pr_info("unexpected userfaultfd ioctl set\n"); - return -1; - } + uffdio_register.mode = uffd_mode; + TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1, + "ioctl UFFDIO_REGISTER failed"); + TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) == + expected_ioctls, "missing userfaultfd ioctls"); + uffd_args->uffd_mode = uffd_mode; uffd_args->uffd = uffd; uffd_args->pipefd = pipefd; uffd_args->delay = uffd_delay; @@ -243,13 +271,12 @@ static int setup_demand_paging(struct kvm_vm *vm, PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n", hva, hva + len); - - return 0; } struct test_params { - bool use_uffd; + int uffd_mode; useconds_t uffd_delay; + enum vm_mem_backing_src_type src_type; bool partition_vcpu_memory_access; }; @@ -267,14 +294,16 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - VM_MEM_SRC_ANONYMOUS); + p->src_type); perf_test_args.wr_fract = 1; - guest_data_prototype = malloc(perf_test_args.host_page_size); + demand_paging_size = get_backing_src_pagesz(p->src_type); + + guest_data_prototype = malloc(demand_paging_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); + memset(guest_data_prototype, 0xAB, demand_paging_size); vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); @@ -282,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, p->partition_vcpu_memory_access); - if (p->use_uffd) { + if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); @@ -296,6 +325,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vm_paddr_t vcpu_gpa; void *vcpu_hva; + void *vcpu_alias; uint64_t vcpu_mem_size; @@ -310,8 +340,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); - /* Cache the HVA pointer of the region */ + /* Cache the host addresses of the region */ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); /* * Set up user fault fd to handle demand paging @@ -321,13 +352,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) O_CLOEXEC | O_NONBLOCK); TEST_ASSERT(!r, "Failed to set up pipefd"); - r = setup_demand_paging(vm, - &uffd_handler_threads[vcpu_id], - pipefds[vcpu_id * 2], - p->uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_mem_size); - if (r < 0) - exit(-r); + setup_demand_paging(vm, &uffd_handler_threads[vcpu_id], + pipefds[vcpu_id * 2], p->uffd_mode, + p->uffd_delay, &uffd_args[vcpu_id], + vcpu_hva, vcpu_alias, + vcpu_mem_size); } } @@ -355,7 +384,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("All vCPU threads joined\n"); - if (p->use_uffd) { + if (p->uffd_mode) { char c; /* Tell the user fault fd handler threads to quit */ @@ -377,7 +406,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) free(guest_data_prototype); free(vcpu_threads); - if (p->use_uffd) { + if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); free(pipefds); @@ -387,17 +416,19 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n" - " [-b memory] [-v vcpus] [-o]\n", name); + printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" + " [-b memory] [-t type] [-v vcpus] [-o]\n", name); guest_modes_help(); - printf(" -u: use User Fault FD to handle vCPU page\n" - " faults.\n"); + printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" + " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); printf(" -d: add a delay in usec to the User Fault\n" " FD handler to simulate demand paging\n" " overheads. Ignored without -u.\n"); printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); + printf(" -t: The type of backing memory to use. Default: anonymous\n"); + backing_src_help(); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -409,19 +440,24 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { + .src_type = VM_MEM_SRC_ANONYMOUS, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); break; case 'u': - p.use_uffd = true; + if (!strcmp("MISSING", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MISSING; + else if (!strcmp("MINOR", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR; + TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'."); break; case 'd': p.uffd_delay = strtoul(optarg, NULL, 0); @@ -430,6 +466,9 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; + case 't': + p.src_type = parse_backing_src_type(optarg); + break; case 'v': nr_vcpus = atoi(optarg); TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, @@ -445,6 +484,11 @@ int main(int argc, char *argv[]) } } + if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && + !backing_src_is_shared(p.src_type)) { + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + } + for_each_guest_mode(run_test, &p); return 0; diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index 5aadf84c91c0..4b8db3bce610 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -132,6 +132,36 @@ static void run_test(uint32_t run) TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run); } +void wait_for_child_setup(pid_t pid) +{ + /* + * Wait for the child to post to the semaphore, but wake up periodically + * to check if the child exited prematurely. + */ + for (;;) { + const struct timespec wait_period = { .tv_sec = 1 }; + int status; + + if (!sem_timedwait(sem, &wait_period)) + return; + + /* Child is still running, keep waiting. */ + if (pid != waitpid(pid, &status, WNOHANG)) + continue; + + /* + * Child is no longer running, which is not expected. + * + * If it exited with a non-zero status, we explicitly forward + * the child's status in case it exited with KSFT_SKIP. + */ + if (WIFEXITED(status)) + exit(WEXITSTATUS(status)); + else + TEST_ASSERT(false, "Child exited unexpectedly"); + } +} + int main(int argc, char **argv) { uint32_t i; @@ -148,7 +178,7 @@ int main(int argc, char **argv) run_test(i); /* This function always exits */ pr_debug("%s: [%d] waiting semaphore\n", __func__, i); - sem_wait(sem); + wait_for_child_setup(pid); r = (rand() % DELAY_US_MAX) + 1; pr_debug("%s: [%d] waiting %dus\n", __func__, i, r); usleep(r); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a8f022794ce3..35739567189e 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -43,6 +43,7 @@ enum vm_guest_mode { VM_MODE_P40V48_4K, VM_MODE_P40V48_64K, VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, NUM_VM_MODES, }; @@ -60,7 +61,7 @@ enum vm_guest_mode { #elif defined(__s390x__) -#define VM_MODE_DEFAULT VM_MODE_P52V48_4K +#define VM_MODE_DEFAULT VM_MODE_P47V64_4K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 16) @@ -77,6 +78,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int open_kvm_dev_path_or_exit(void); int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, @@ -146,6 +148,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); /* * Address Guest Virtual to Guest Physical @@ -283,10 +286,11 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]); -/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */ +/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]); + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); /* * Adds a vCPU with reasonable defaults (e.g. a stack) @@ -302,7 +306,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm); unsigned int vm_get_page_size(struct kvm_vm *vm); unsigned int vm_get_page_shift(struct kvm_vm *vm); -unsigned int vm_get_max_gfn(struct kvm_vm *vm); +uint64_t vm_get_max_gfn(struct kvm_vm *vm); int vm_get_fd(struct kvm_vm *vm); unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index fade3130eb01..d79be15dd3d2 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -17,6 +17,7 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> +#include <sys/mman.h> #include "kselftest.h" static inline int _no_printf(const char *format, ...) { return 0; } @@ -84,6 +85,8 @@ enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB, + VM_MEM_SRC_SHMEM, + VM_MEM_SRC_SHARED_HUGETLB, NUM_SRC_TYPES, }; @@ -100,4 +103,13 @@ size_t get_backing_src_pagesz(uint32_t i); void backing_src_help(void); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +/* + * Whether or not the given source type is shared memory (as opposed to + * anonymous). + */ +static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) +{ + return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 1c4753fff19e..82171f17c1d7 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -268,7 +268,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) /* Create a VM with enough guest pages */ guest_num_pages = test_mem_size / guest_page_size; - vm = vm_create_with_vcpus(mode, nr_vcpus, + vm = vm_create_with_vcpus(mode, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, guest_num_pages, 0, guest_code, NULL); /* Align down GPA of the testing memslot */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..a2b732cf96ea 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -32,6 +32,34 @@ static void *align(void *x, size_t size) } /* + * Open KVM_DEV_PATH if available, otherwise exit the entire program. + * + * Input Args: + * flags - The flags to pass when opening KVM_DEV_PATH. + * + * Return: + * The opened file descriptor of /dev/kvm. + */ +static int _open_kvm_dev_path_or_exit(int flags) +{ + int fd; + + fd = open(KVM_DEV_PATH, flags); + if (fd < 0) { + print_skip("%s not available, is KVM loaded? (errno: %d)", + KVM_DEV_PATH, errno); + exit(KSFT_SKIP); + } + + return fd; +} + +int open_kvm_dev_path_or_exit(void) +{ + return _open_kvm_dev_path_or_exit(O_RDONLY); +} + +/* * Capability * * Input Args: @@ -52,12 +80,9 @@ int kvm_check_cap(long cap) int ret; int kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); - + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" + TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" " rc: %i errno: %i", ret, errno); close(kvm_fd); @@ -128,9 +153,7 @@ void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) static void vm_open(struct kvm_vm *vm, int perm) { - vm->kvm_fd = open(KVM_DEV_PATH, perm); - if (vm->kvm_fd < 0) - exit(KSFT_SKIP); + vm->kvm_fd = _open_kvm_dev_path_or_exit(perm); if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { print_skip("immediate_exit not available"); @@ -152,6 +175,7 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", + [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -169,6 +193,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { { 40, 48, 0x1000, 12 }, { 40, 48, 0x10000, 16 }, { 0, 0, 0x1000, 12 }, + { 47, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -203,7 +228,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -252,6 +279,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms"); #endif break; + case VM_MODE_P47V64_4K: + vm->pgtable_levels = 5; + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); } @@ -283,21 +313,50 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } +/* + * VM Create with customized parameters + * + * Input Args: + * mode - VM Mode (e.g. VM_MODE_P52V48_4K) + * nr_vcpus - VCPU count + * slot0_mem_pages - Slot0 physical memory size + * extra_mem_pages - Non-slot0 physical memory total size + * num_percpu_pages - Per-cpu physical memory pages + * guest_code - Guest entry point + * vcpuids - VCPU IDs + * + * Output Args: None + * + * Return: + * Pointer to opaque structure that describes the created VM. + * + * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K), + * with customized slot0 memory size, at least 512 pages currently. + * extra_mem_pages is only used to calculate the maximum page table size, + * no real memory allocation for non-slot0 memory in this function. + */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]) + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]) { + uint64_t vcpu_pages, extra_pg_pages, pages; + struct kvm_vm *vm; + int i; + + /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */ + if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES) + slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES; + /* The maximum page table size for a memory region will be when the * smallest pages are used. Considering each page contains x page * table descriptors, the total extra size for page tables (for extra * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller * than N/x*2. */ - uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; - uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; - struct kvm_vm *vm; - int i; + vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; + extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; + pages = slot0_mem_pages + vcpu_pages + extra_pg_pages; TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), "nr_vcpus = %d too large for host, max-vcpus = %d", @@ -329,8 +388,8 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]) { - return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages, - num_percpu_pages, guest_code, vcpuids); + return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, + extra_mem_pages, num_percpu_pages, guest_code, vcpuids); } struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, @@ -355,13 +414,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -424,14 +484,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -546,11 +613,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(®ion->list); + if (unlink) { + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); @@ -569,14 +641,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -658,13 +732,64 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->gpa_node, parent, cur); + rb_insert_color(®ion->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->hva_node, parent, cur); + rb_insert_color(®ion->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * * Input Args: * vm - Virtual Machine - * backing_src - Storage source for this region. - * NULL to use anonymous memory. + * src_type - Storage source for this region. + * NULL to use anonymous memory. * guest_paddr - Starting guest physical address * slot - KVM region slot * npages - Number of physical pages @@ -722,7 +847,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -755,11 +881,30 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, if (alignment > 1) region->mmap_size += alignment; + region->fd = -1; + if (backing_src_is_shared(src_type)) { + int memfd_flags = MFD_CLOEXEC; + + if (src_type == VM_MEM_SRC_SHARED_HUGETLB) + memfd_flags |= MFD_HUGETLB; + + region->fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(region->fd != -1, + "memfd_create failed, errno: %i", errno); + + ret = ftruncate(region->fd, region->mmap_size); + TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); + + ret = fallocate(region->fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + region->mmap_size); + TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); + } + region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS - | vm_mem_backing_src_alias(src_type)->flag, - -1, 0); + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); TEST_ASSERT(region->mmap_start != MAP_FAILED, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); @@ -793,8 +938,23 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(®ion->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, ®ion->slot_node, slot); + + /* If shared memory, create an alias. */ + if (region->fd >= 0) { + region->mmap_alias = mmap(NULL, region->mmap_size, + PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); + TEST_ASSERT(region->mmap_alias != MAP_FAILED, + "mmap of alias failed, errno: %i", errno); + + /* Align host alias address */ + region->host_alias = align(region->mmap_alias, alignment); + } } /* @@ -817,10 +977,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -905,7 +1065,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -925,9 +1085,7 @@ static int vcpu_mmap_sz(void) { int dev_fd, ret; - dev_fd = open(KVM_DEV_PATH, O_RDONLY); - if (dev_fd < 0) - exit(KSFT_SKIP); + dev_fd = open_kvm_dev_path_or_exit(); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), @@ -1099,6 +1257,9 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm, pgd_memslot); + vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + data_memslot); /* * Find an unused range of virtual page addresses of at least @@ -1108,11 +1269,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, /* Map the virtual pages. */ for (vm_vaddr_t vaddr = vaddr_start; pages > 0; - pages--, vaddr += vm->page_size) { - vm_paddr_t paddr; - - paddr = vm_phy_page_alloc(vm, - KVM_UTIL_MIN_PFN * vm->page_size, data_memslot); + pages--, vaddr += vm->page_size, paddr += vm->page_size) { virt_pg_map(vm, vaddr, paddr, pgd_memslot); @@ -1177,16 +1334,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1208,15 +1363,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); + + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); + + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1224,6 +1386,42 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) } /* + * Address VM physical to Host Virtual *alias*. + * + * Input Args: + * vm - Virtual Machine + * gpa - VM physical address + * + * Output Args: None + * + * Return: + * Equivalent address within the host virtual *alias* area, or NULL + * (without failing the test) if the guest memory is not shared (so + * no alias exists). + * + * When vm_create() and related functions are called with a shared memory + * src_type, we also create a writable, shared alias mapping of the + * underlying guest memory. This allows the host to manipulate guest memory + * without mapping that memory in the guest's address space. And, for + * userfaultfd-based demand paging, we can do so without triggering userfaults. + */ +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) +{ + struct userspace_mem_region *region; + uintptr_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) + return NULL; + + if (!region->host_alias) + return NULL; + + offset = gpa - region->region.guest_phys_addr; + return (void *) ((uintptr_t) region->host_alias + offset); +} + +/* * VM Create IRQ Chip * * Input Args: @@ -1822,6 +2020,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1829,7 +2028,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, @@ -2015,10 +2214,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) if (vm == NULL) { /* Ensure that the KVM vendor-specific module is loaded. */ - f = fopen(KVM_DEV_PATH, "r"); - TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d", - errno); - fclose(f); + close(open_kvm_dev_path_or_exit()); } f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); @@ -2041,7 +2237,7 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm) return vm->page_shift; } -unsigned int vm_get_max_gfn(struct kvm_vm *vm) +uint64_t vm_get_max_gfn(struct kvm_vm *vm) { return vm->max_gfn; } diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 91ce1b5d480b..a03febc24ba6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" struct userspace_mem_region { @@ -16,9 +19,13 @@ struct userspace_mem_region { int fd; off_t offset; void *host_mem; + void *host_alias; void *mmap_start; + void *mmap_alias; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -31,6 +38,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -43,7 +56,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 81490b9b4e32..7397ca299835 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020, Google LLC. */ +#include <inttypes.h> #include "kvm_util.h" #include "perf_test_util.h" @@ -68,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, "Guest memory size is not guest page size aligned."); - vm = vm_create_with_vcpus(mode, vcpus, + vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES, (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size, 0, guest_code, NULL); @@ -80,7 +81,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, */ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + " guest pages: %" PRIx64 " max gfn: %" PRIx64 + " vcpus: %d wss: %" PRIx64 "]\n", guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c" diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 63d2bc7d757b..af1031fed97f 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -166,72 +166,89 @@ size_t get_def_hugetlb_pagesz(void) return 0; } +#define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS) +#define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB) + const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) { static const struct vm_mem_backing_src_alias aliases[] = { [VM_MEM_SRC_ANONYMOUS] = { .name = "anonymous", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_THP] = { .name = "anonymous_thp", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB] = { .name = "anonymous_hugetlb", - .flag = MAP_HUGETLB, + .flag = ANON_HUGE_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = { .name = "anonymous_hugetlb_16kb", - .flag = MAP_HUGETLB | MAP_HUGE_16KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = { .name = "anonymous_hugetlb_64kb", - .flag = MAP_HUGETLB | MAP_HUGE_64KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_64KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = { .name = "anonymous_hugetlb_512kb", - .flag = MAP_HUGETLB | MAP_HUGE_512KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = { .name = "anonymous_hugetlb_1mb", - .flag = MAP_HUGETLB | MAP_HUGE_1MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = { .name = "anonymous_hugetlb_2mb", - .flag = MAP_HUGETLB | MAP_HUGE_2MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = { .name = "anonymous_hugetlb_8mb", - .flag = MAP_HUGETLB | MAP_HUGE_8MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_8MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = { .name = "anonymous_hugetlb_16mb", - .flag = MAP_HUGETLB | MAP_HUGE_16MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = { .name = "anonymous_hugetlb_32mb", - .flag = MAP_HUGETLB | MAP_HUGE_32MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_32MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = { .name = "anonymous_hugetlb_256mb", - .flag = MAP_HUGETLB | MAP_HUGE_256MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_256MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = { .name = "anonymous_hugetlb_512mb", - .flag = MAP_HUGETLB | MAP_HUGE_512MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = { .name = "anonymous_hugetlb_1gb", - .flag = MAP_HUGETLB | MAP_HUGE_1GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = { .name = "anonymous_hugetlb_2gb", - .flag = MAP_HUGETLB | MAP_HUGE_2GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = { .name = "anonymous_hugetlb_16gb", - .flag = MAP_HUGETLB | MAP_HUGE_16GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16GB, + }, + [VM_MEM_SRC_SHMEM] = { + .name = "shmem", + .flag = MAP_SHARED, + }, + [VM_MEM_SRC_SHARED_HUGETLB] = { + .name = "shared_hugetlb", + /* + * No MAP_HUGETLB, we use MFD_HUGETLB instead. Since + * we're using "file backed" memory, we need to specify + * this when the FD is created, not when the area is + * mapped. + */ + .flag = MAP_SHARED, }, }; _Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES, @@ -250,10 +267,12 @@ size_t get_backing_src_pagesz(uint32_t i) switch (i) { case VM_MEM_SRC_ANONYMOUS: + case VM_MEM_SRC_SHMEM: return getpagesize(); case VM_MEM_SRC_ANONYMOUS_THP: return get_trans_hugepagesz(); case VM_MEM_SRC_ANONYMOUS_HUGETLB: + case VM_MEM_SRC_SHARED_HUGETLB: return get_def_hugetlb_pagesz(); default: return MAP_HUGE_PAGE_SIZE(flag); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index a8906e60a108..efe235044421 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -657,9 +657,7 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", @@ -691,9 +689,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) buffer.header.nmsrs = 1; buffer.entry.index = msr_index; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header); TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" @@ -986,9 +982,7 @@ struct kvm_msr_list *kvm_get_msr_index_list(void) struct kvm_msr_list *list; int nmsrs, r, kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); nmsrs = kvm_get_num_msrs_fd(kvm_fd); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); @@ -1312,9 +1306,7 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n", diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 6096bf0a5b34..98351ba0933c 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -71,14 +71,22 @@ struct memslot_antagonist_args { }; static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, - uint64_t nr_modifications, uint64_t gpa) + uint64_t nr_modifications) { + const uint64_t pages = 1; + uint64_t gpa; int i; + /* + * Add the dummy memslot just below the perf_test_util memslot, which is + * at the top of the guest physical address space. + */ + gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + for (i = 0; i < nr_modifications; i++) { usleep(delay); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, - DUMMY_MEMSLOT_INDEX, 1, 0); + DUMMY_MEMSLOT_INDEX, pages, 0); vm_mem_region_delete(vm, DUMMY_MEMSLOT_INDEX); } @@ -120,11 +128,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Started all vCPUs\n"); add_remove_memslot(vm, p->memslot_modification_delay, - p->nr_memslot_modifications, - guest_test_phys_mem + - (guest_percpu_mem_size * nr_vcpus) + - perf_test_args.host_page_size + - perf_test_args.guest_page_size); + p->nr_memslot_modifications); run_vcpus = false; diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c new file mode 100644 index 000000000000..11239652d805 --- /dev/null +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -0,0 +1,1037 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A memslot-related performance benchmark. + * + * Copyright (C) 2021 Oracle and/or its affiliates. + * + * Basic guest setup / host vCPU thread code lifted from set_memory_region_test. + */ +#include <pthread.h> +#include <sched.h> +#include <semaphore.h> +#include <stdatomic.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <time.h> +#include <unistd.h> + +#include <linux/compiler.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#define VCPU_ID 0 + +#define MEM_SIZE ((512U << 20) + 4096) +#define MEM_SIZE_PAGES (MEM_SIZE / 4096) +#define MEM_GPA 0x10000000UL +#define MEM_AUX_GPA MEM_GPA +#define MEM_SYNC_GPA MEM_AUX_GPA +#define MEM_TEST_GPA (MEM_AUX_GPA + 4096) +#define MEM_TEST_SIZE (MEM_SIZE - 4096) +static_assert(MEM_SIZE % 4096 == 0, "invalid mem size"); +static_assert(MEM_TEST_SIZE % 4096 == 0, "invalid mem test size"); + +/* + * 32 MiB is max size that gets well over 100 iterations on 509 slots. + * Considering that each slot needs to have at least one page up to + * 8194 slots in use can then be tested (although with slightly + * limited resolution). + */ +#define MEM_SIZE_MAP ((32U << 20) + 4096) +#define MEM_SIZE_MAP_PAGES (MEM_SIZE_MAP / 4096) +#define MEM_TEST_MAP_SIZE (MEM_SIZE_MAP - 4096) +#define MEM_TEST_MAP_SIZE_PAGES (MEM_TEST_MAP_SIZE / 4096) +static_assert(MEM_SIZE_MAP % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES % 2 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES > 2, "invalid map test region size"); + +/* + * 128 MiB is min size that fills 32k slots with at least one page in each + * while at the same time gets 100+ iterations in such test + */ +#define MEM_TEST_UNMAP_SIZE (128U << 20) +#define MEM_TEST_UNMAP_SIZE_PAGES (MEM_TEST_UNMAP_SIZE / 4096) +/* 2 MiB chunk size like a typical huge page */ +#define MEM_TEST_UNMAP_CHUNK_PAGES (2U << (20 - 12)) +static_assert(MEM_TEST_UNMAP_SIZE <= MEM_TEST_SIZE, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE % 4096 == 0, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE_PAGES % + (2 * MEM_TEST_UNMAP_CHUNK_PAGES) == 0, + "invalid unmap test region size"); + +/* + * For the move active test the middle of the test area is placed on + * a memslot boundary: half lies in the memslot being moved, half in + * other memslot(s). + * + * When running this test with 32k memslots (32764, really) each memslot + * contains 4 pages. + * The last one additionally contains the remaining 21 pages of memory, + * for the total size of 25 pages. + * Hence, the maximum size here is 50 pages. + */ +#define MEM_TEST_MOVE_SIZE_PAGES (50) +#define MEM_TEST_MOVE_SIZE (MEM_TEST_MOVE_SIZE_PAGES * 4096) +#define MEM_TEST_MOVE_GPA_DEST (MEM_GPA + MEM_SIZE) +static_assert(MEM_TEST_MOVE_SIZE <= MEM_TEST_SIZE, + "invalid move test region size"); + +#define MEM_TEST_VAL_1 0x1122334455667788 +#define MEM_TEST_VAL_2 0x99AABBCCDDEEFF00 + +struct vm_data { + struct kvm_vm *vm; + pthread_t vcpu_thread; + uint32_t nslots; + uint64_t npages; + uint64_t pages_per_slot; + void **hva_slots; + bool mmio_ok; + uint64_t mmio_gpa_min; + uint64_t mmio_gpa_max; +}; + +struct sync_area { + atomic_bool start_flag; + atomic_bool exit_flag; + atomic_bool sync_flag; + void *move_area_ptr; +}; + +/* + * Technically, we need also for the atomic bool to be address-free, which + * is recommended, but not strictly required, by C11 for lockless + * implementations. + * However, in practice both GCC and Clang fulfill this requirement on + * all KVM-supported platforms. + */ +static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); + +static sem_t vcpu_ready; + +static bool map_unmap_verify; + +static bool verbose; +#define pr_info_v(...) \ + do { \ + if (verbose) \ + pr_info(__VA_ARGS__); \ + } while (0) + +static void *vcpu_worker(void *data) +{ + struct vm_data *vm = data; + struct kvm_run *run; + struct ucall uc; + uint64_t cmd; + + run = vcpu_state(vm->vm, VCPU_ID); + while (1) { + vcpu_run(vm->vm, VCPU_ID); + + if (run->exit_reason == KVM_EXIT_IO) { + cmd = get_ucall(vm->vm, VCPU_ID, &uc); + if (cmd != UCALL_SYNC) + break; + + sem_post(&vcpu_ready); + continue; + } + + if (run->exit_reason != KVM_EXIT_MMIO) + break; + + TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); + TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); + TEST_ASSERT(run->mmio.len == 8, + "Unexpected exit mmio size = %u", run->mmio.len); + TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && + run->mmio.phys_addr <= vm->mmio_gpa_max, + "Unexpected exit mmio address = 0x%llx", + run->mmio.phys_addr); + } + + if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) + TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0], + __FILE__, uc.args[1], uc.args[2]); + + return NULL; +} + +static void wait_for_vcpu(void) +{ + struct timespec ts; + + TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts), + "clock_gettime() failed: %d\n", errno); + + ts.tv_sec += 2; + TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts), + "sem_timedwait() failed: %d\n", errno); +} + +static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) +{ + uint64_t gpage, pgoffs; + uint32_t slot, slotoffs; + void *base; + + TEST_ASSERT(gpa >= MEM_GPA, "Too low gpa to translate"); + TEST_ASSERT(gpa < MEM_GPA + data->npages * 4096, + "Too high gpa to translate"); + gpa -= MEM_GPA; + + gpage = gpa / 4096; + pgoffs = gpa % 4096; + slot = min(gpage / data->pages_per_slot, (uint64_t)data->nslots - 1); + slotoffs = gpage - (slot * data->pages_per_slot); + + if (rempages) { + uint64_t slotpages; + + if (slot == data->nslots - 1) + slotpages = data->npages - slot * data->pages_per_slot; + else + slotpages = data->pages_per_slot; + + TEST_ASSERT(!pgoffs, + "Asking for remaining pages in slot but gpa not page aligned"); + *rempages = slotpages - slotoffs; + } + + base = data->hva_slots[slot]; + return (uint8_t *)base + slotoffs * 4096 + pgoffs; +} + +static uint64_t vm_slot2gpa(struct vm_data *data, uint32_t slot) +{ + TEST_ASSERT(slot < data->nslots, "Too high slot number"); + + return MEM_GPA + slot * data->pages_per_slot * 4096; +} + +static struct vm_data *alloc_vm(void) +{ + struct vm_data *data; + + data = malloc(sizeof(*data)); + TEST_ASSERT(data, "malloc(vmdata) failed"); + + data->vm = NULL; + data->hva_slots = NULL; + + return data; +} + +static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, + void *guest_code, uint64_t mempages, + struct timespec *slot_runtime) +{ + uint32_t max_mem_slots; + uint64_t rempages; + uint64_t guest_addr; + uint32_t slot; + struct timespec tstart; + struct sync_area *sync; + + max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); + TEST_ASSERT(max_mem_slots > 1, + "KVM_CAP_NR_MEMSLOTS should be greater than 1"); + TEST_ASSERT(nslots > 1 || nslots == -1, + "Slot count cap should be greater than 1"); + if (nslots != -1) + max_mem_slots = min(max_mem_slots, (uint32_t)nslots); + pr_info_v("Allowed number of memory slots: %"PRIu32"\n", max_mem_slots); + + TEST_ASSERT(mempages > 1, + "Can't test without any memory"); + + data->npages = mempages; + data->nslots = max_mem_slots - 1; + data->pages_per_slot = mempages / data->nslots; + if (!data->pages_per_slot) { + *maxslots = mempages + 1; + return false; + } + + rempages = mempages % data->nslots; + data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); + TEST_ASSERT(data->hva_slots, "malloc() fail"); + + data->vm = vm_create_default(VCPU_ID, mempages, guest_code); + + pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", + max_mem_slots - 1, data->pages_per_slot, rempages); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + for (slot = 1, guest_addr = MEM_GPA; slot < max_mem_slots; slot++) { + uint64_t npages; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 1) + npages += rempages; + + vm_userspace_mem_region_add(data->vm, VM_MEM_SRC_ANONYMOUS, + guest_addr, slot, npages, + 0); + guest_addr += npages * 4096; + } + *slot_runtime = timespec_elapsed(tstart); + + for (slot = 0, guest_addr = MEM_GPA; slot < max_mem_slots - 1; slot++) { + uint64_t npages; + uint64_t gpa; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 2) + npages += rempages; + + gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, + slot + 1); + TEST_ASSERT(gpa == guest_addr, + "vm_phy_pages_alloc() failed\n"); + + data->hva_slots[slot] = addr_gpa2hva(data->vm, guest_addr); + memset(data->hva_slots[slot], 0, npages * 4096); + + guest_addr += npages * 4096; + } + + virt_map(data->vm, MEM_GPA, MEM_GPA, mempages, 0); + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + atomic_init(&sync->start_flag, false); + atomic_init(&sync->exit_flag, false); + atomic_init(&sync->sync_flag, false); + + data->mmio_ok = false; + + return true; +} + +static void launch_vm(struct vm_data *data) +{ + pr_info_v("Launching the test VM\n"); + + pthread_create(&data->vcpu_thread, NULL, vcpu_worker, data); + + /* Ensure the guest thread is spun up. */ + wait_for_vcpu(); +} + +static void free_vm(struct vm_data *data) +{ + kvm_vm_free(data->vm); + free(data->hva_slots); + free(data); +} + +static void wait_guest_exit(struct vm_data *data) +{ + pthread_join(data->vcpu_thread, NULL); +} + +static void let_guest_run(struct sync_area *sync) +{ + atomic_store_explicit(&sync->start_flag, true, memory_order_release); +} + +static void guest_spin_until_start(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + while (!atomic_load_explicit(&sync->start_flag, memory_order_acquire)) + ; +} + +static void make_guest_exit(struct sync_area *sync) +{ + atomic_store_explicit(&sync->exit_flag, true, memory_order_release); +} + +static bool _guest_should_exit(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + return atomic_load_explicit(&sync->exit_flag, memory_order_acquire); +} + +#define guest_should_exit() unlikely(_guest_should_exit()) + +/* + * noinline so we can easily see how much time the host spends waiting + * for the guest. + * For the same reason use alarm() instead of polling clock_gettime() + * to implement a wait timeout. + */ +static noinline void host_perform_sync(struct sync_area *sync) +{ + alarm(2); + + atomic_store_explicit(&sync->sync_flag, true, memory_order_release); + while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire)) + ; + + alarm(0); +} + +static bool guest_perform_sync(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + bool expected; + + do { + if (guest_should_exit()) + return false; + + expected = true; + } while (!atomic_compare_exchange_weak_explicit(&sync->sync_flag, + &expected, false, + memory_order_acq_rel, + memory_order_relaxed)); + + return true; +} + +static void guest_code_test_memslot_move(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + uintptr_t base = (typeof(base))READ_ONCE(sync->move_area_ptr); + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (!guest_should_exit()) { + uintptr_t ptr; + + for (ptr = base; ptr < base + MEM_TEST_MOVE_SIZE; + ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + /* + * No host sync here since the MMIO exits are so expensive + * that the host would spend most of its time waiting for + * the guest and so instead of measuring memslot move + * performance we would measure the performance and + * likelihood of MMIO exits + */ + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_map(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_unmap(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr = MEM_TEST_GPA; + + /* + * We can afford to access (map) just a small number of pages + * per host sync as otherwise the host will spend + * a significant amount of its time waiting for the guest + * (instead of doing unmap operations), so this will + * effectively turn this test into a map performance test. + * + * Just access a single page to be on the safe side. + */ + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + ptr += MEM_TEST_UNMAP_SIZE / 2; + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_rw(void) +{ + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + 4096 / 2; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) { + uint64_t val = *(uint64_t *)ptr; + + GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val); + *(uint64_t *)ptr = 0; + } + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static bool test_memslot_move_prepare(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots, bool isactive) +{ + uint64_t movesrcgpa, movetestgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + + if (isactive) { + uint64_t lastpages; + + vm_gpa2hva(data, movesrcgpa, &lastpages); + if (lastpages < MEM_TEST_MOVE_SIZE_PAGES / 2) { + *maxslots = 0; + return false; + } + } + + movetestgpa = movesrcgpa - (MEM_TEST_MOVE_SIZE / (isactive ? 2 : 1)); + sync->move_area_ptr = (void *)movetestgpa; + + if (isactive) { + data->mmio_ok = true; + data->mmio_gpa_min = movesrcgpa; + data->mmio_gpa_max = movesrcgpa + MEM_TEST_MOVE_SIZE / 2 - 1; + } + + return true; +} + +static bool test_memslot_move_prepare_active(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, true); +} + +static bool test_memslot_move_prepare_inactive(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, false); +} + +static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t movesrcgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, + MEM_TEST_MOVE_GPA_DEST); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, movesrcgpa); +} + +static void test_memslot_do_unmap(struct vm_data *data, + uint64_t offsp, uint64_t count) +{ + uint64_t gpa, ctr; + + for (gpa = MEM_TEST_GPA + offsp * 4096, ctr = 0; ctr < count; ) { + uint64_t npages; + void *hva; + int ret; + + hva = vm_gpa2hva(data, gpa, &npages); + TEST_ASSERT(npages, "Empty memory slot at gptr 0x%"PRIx64, gpa); + npages = min(npages, count - ctr); + ret = madvise(hva, npages * 4096, MADV_DONTNEED); + TEST_ASSERT(!ret, + "madvise(%p, MADV_DONTNEED) on VM memory should not fail for gptr 0x%"PRIx64, + hva, gpa); + ctr += npages; + gpa += npages * 4096; + } + TEST_ASSERT(ctr == count, + "madvise(MADV_DONTNEED) should exactly cover all of the requested area"); +} + +static void test_memslot_map_unmap_check(struct vm_data *data, + uint64_t offsp, uint64_t valexp) +{ + uint64_t gpa; + uint64_t *val; + + if (!map_unmap_verify) + return; + + gpa = MEM_TEST_GPA + offsp * 4096; + val = (typeof(val))vm_gpa2hva(data, gpa, NULL); + TEST_ASSERT(*val == valexp, + "Guest written values should read back correctly before unmap (%"PRIu64" vs %"PRIu64" @ %"PRIx64")", + *val, valexp, gpa); + *val = 0; +} + +static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync) +{ + /* + * Unmap the second half of the test area while guest writes to (maps) + * the first half. + */ + test_memslot_do_unmap(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_MAP_SIZE_PAGES / 2); + + /* + * Wait for the guest to finish writing the first half of the test + * area, verify the written value on the first and the last page of + * this area and then unmap it. + * Meanwhile, the guest is writing to (mapping) the second half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + test_memslot_map_unmap_check(data, + MEM_TEST_MAP_SIZE_PAGES / 2 - 1, + MEM_TEST_VAL_1); + test_memslot_do_unmap(data, 0, MEM_TEST_MAP_SIZE_PAGES / 2); + + + /* + * Wait for the guest to finish writing the second half of the test + * area and verify the written value on the first and the last page + * of this area. + * The area will be unmapped at the beginning of the next loop + * iteration. + * Meanwhile, the guest is writing to (mapping) the first half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES - 1, + MEM_TEST_VAL_2); +} + +static void test_memslot_unmap_loop_common(struct vm_data *data, + struct sync_area *sync, + uint64_t chunk) +{ + uint64_t ctr; + + /* + * Wait for the guest to finish mapping page(s) in the first half + * of the test area, verify the written value and then perform unmap + * of this area. + * Meanwhile, the guest is writing to (mapping) page(s) in the second + * half of the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + for (ctr = 0; ctr < MEM_TEST_UNMAP_SIZE_PAGES / 2; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); + + /* Likewise, but for the opposite host / guest areas */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_UNMAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + for (ctr = MEM_TEST_UNMAP_SIZE_PAGES / 2; + ctr < MEM_TEST_UNMAP_SIZE_PAGES; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); +} + +static void test_memslot_unmap_loop(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, 1); +} + +static void test_memslot_unmap_loop_chunked(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, MEM_TEST_UNMAP_CHUNK_PAGES); +} + +static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t gptr; + + for (gptr = MEM_TEST_GPA + 4096 / 2; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) + *(uint64_t *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2; + + host_perform_sync(sync); + + for (gptr = MEM_TEST_GPA; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) { + uint64_t *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL); + uint64_t val = *vptr; + + TEST_ASSERT(val == MEM_TEST_VAL_1, + "Guest written values should read back correctly (is %"PRIu64" @ %"PRIx64")", + val, gptr); + *vptr = 0; + } + + host_perform_sync(sync); +} + +struct test_data { + const char *name; + uint64_t mem_size; + void (*guest_code)(void); + bool (*prepare)(struct vm_data *data, struct sync_area *sync, + uint64_t *maxslots); + void (*loop)(struct vm_data *data, struct sync_area *sync); +}; + +static bool test_execute(int nslots, uint64_t *maxslots, + unsigned int maxtime, + const struct test_data *tdata, + uint64_t *nloops, + struct timespec *slot_runtime, + struct timespec *guest_runtime) +{ + uint64_t mem_size = tdata->mem_size ? : MEM_SIZE_PAGES; + struct vm_data *data; + struct sync_area *sync; + struct timespec tstart; + bool ret = true; + + data = alloc_vm(); + if (!prepare_vm(data, nslots, maxslots, tdata->guest_code, + mem_size, slot_runtime)) { + ret = false; + goto exit_free; + } + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + + if (tdata->prepare && + !tdata->prepare(data, sync, maxslots)) { + ret = false; + goto exit_free; + } + + launch_vm(data); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + let_guest_run(sync); + + while (1) { + *guest_runtime = timespec_elapsed(tstart); + if (guest_runtime->tv_sec >= maxtime) + break; + + tdata->loop(data, sync); + + (*nloops)++; + } + + make_guest_exit(sync); + wait_guest_exit(data); + +exit_free: + free_vm(data); + + return ret; +} + +static const struct test_data tests[] = { + { + .name = "map", + .mem_size = MEM_SIZE_MAP_PAGES, + .guest_code = guest_code_test_memslot_map, + .loop = test_memslot_map_loop, + }, + { + .name = "unmap", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop, + }, + { + .name = "unmap chunked", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop_chunked, + }, + { + .name = "move active area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_active, + .loop = test_memslot_move_loop, + }, + { + .name = "move inactive area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_inactive, + .loop = test_memslot_move_loop, + }, + { + .name = "RW", + .guest_code = guest_code_test_memslot_rw, + .loop = test_memslot_rw_loop + }, +}; + +#define NTESTS ARRAY_SIZE(tests) + +struct test_args { + int tfirst; + int tlast; + int nslots; + int seconds; + int runs; +}; + +static void help(char *name, struct test_args *targs) +{ + int ctr; + + pr_info("usage: %s [-h] [-v] [-d] [-s slots] [-f first_test] [-e last_test] [-l test_length] [-r run_count]\n", + name); + pr_info(" -h: print this help screen.\n"); + pr_info(" -v: enable verbose mode (not for benchmarking).\n"); + pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", + targs->nslots); + pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", + targs->tfirst, NTESTS - 1); + pr_info(" -e: specify the last test to run (currently: %i; max %zu)\n", + targs->tlast, NTESTS - 1); + pr_info(" -l: specify the test length in seconds (currently: %i)\n", + targs->seconds); + pr_info(" -r: specify the number of runs per test (currently: %i)\n", + targs->runs); + + pr_info("\nAvailable tests:\n"); + for (ctr = 0; ctr < NTESTS; ctr++) + pr_info("%d: %s\n", ctr, tests[ctr].name); +} + +static bool parse_args(int argc, char *argv[], + struct test_args *targs) +{ + int opt; + + while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + switch (opt) { + case 'h': + default: + help(argv[0], targs); + return false; + case 'v': + verbose = true; + break; + case 'd': + map_unmap_verify = true; + break; + case 's': + targs->nslots = atoi(optarg); + if (targs->nslots <= 0 && targs->nslots != -1) { + pr_info("Slot count cap has to be positive or -1 for no cap\n"); + return false; + } + break; + case 'f': + targs->tfirst = atoi(optarg); + if (targs->tfirst < 0) { + pr_info("First test to run has to be non-negative\n"); + return false; + } + break; + case 'e': + targs->tlast = atoi(optarg); + if (targs->tlast < 0 || targs->tlast >= NTESTS) { + pr_info("Last test to run has to be non-negative and less than %zu\n", + NTESTS); + return false; + } + break; + case 'l': + targs->seconds = atoi(optarg); + if (targs->seconds < 0) { + pr_info("Test length in seconds has to be non-negative\n"); + return false; + } + break; + case 'r': + targs->runs = atoi(optarg); + if (targs->runs <= 0) { + pr_info("Runs per test has to be positive\n"); + return false; + } + break; + } + } + + if (optind < argc) { + help(argv[0], targs); + return false; + } + + if (targs->tfirst > targs->tlast) { + pr_info("First test to run cannot be greater than the last test to run\n"); + return false; + } + + return true; +} + +struct test_result { + struct timespec slot_runtime, guest_runtime, iter_runtime; + int64_t slottimens, runtimens; + uint64_t nloops; +}; + +static bool test_loop(const struct test_data *data, + const struct test_args *targs, + struct test_result *rbestslottime, + struct test_result *rbestruntime) +{ + uint64_t maxslots; + struct test_result result; + + result.nloops = 0; + if (!test_execute(targs->nslots, &maxslots, targs->seconds, data, + &result.nloops, + &result.slot_runtime, &result.guest_runtime)) { + if (maxslots) + pr_info("Memslot count too high for this test, decrease the cap (max is %"PRIu64")\n", + maxslots); + else + pr_info("Memslot count may be too high for this test, try adjusting the cap\n"); + + return false; + } + + pr_info("Test took %ld.%.9lds for slot setup + %ld.%.9lds all iterations\n", + result.slot_runtime.tv_sec, result.slot_runtime.tv_nsec, + result.guest_runtime.tv_sec, result.guest_runtime.tv_nsec); + if (!result.nloops) { + pr_info("No full loops done - too short test time or system too loaded?\n"); + return true; + } + + result.iter_runtime = timespec_div(result.guest_runtime, + result.nloops); + pr_info("Done %"PRIu64" iterations, avg %ld.%.9lds each\n", + result.nloops, + result.iter_runtime.tv_sec, + result.iter_runtime.tv_nsec); + result.slottimens = timespec_to_ns(result.slot_runtime); + result.runtimens = timespec_to_ns(result.iter_runtime); + + /* + * Only rank the slot setup time for tests using the whole test memory + * area so they are comparable + */ + if (!data->mem_size && + (!rbestslottime->slottimens || + result.slottimens < rbestslottime->slottimens)) + *rbestslottime = result; + if (!rbestruntime->runtimens || + result.runtimens < rbestruntime->runtimens) + *rbestruntime = result; + + return true; +} + +int main(int argc, char *argv[]) +{ + struct test_args targs = { + .tfirst = 0, + .tlast = NTESTS - 1, + .nslots = -1, + .seconds = 5, + .runs = 1, + }; + struct test_result rbestslottime; + int tctr; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + if (!parse_args(argc, argv, &targs)) + return -1; + + rbestslottime.slottimens = 0; + for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) { + const struct test_data *data = &tests[tctr]; + unsigned int runctr; + struct test_result rbestruntime; + + if (tctr > targs.tfirst) + pr_info("\n"); + + pr_info("Testing %s performance with %i runs, %d seconds each\n", + data->name, targs.runs, targs.seconds); + + rbestruntime.runtimens = 0; + for (runctr = 0; runctr < targs.runs; runctr++) + if (!test_loop(data, &targs, + &rbestslottime, &rbestruntime)) + break; + + if (rbestruntime.runtimens) + pr_info("Best runtime result was %ld.%.9lds per iteration (with %"PRIu64" iterations)\n", + rbestruntime.iter_runtime.tv_sec, + rbestruntime.iter_runtime.tv_nsec, + rbestruntime.nloops); + } + + if (rbestslottime.slottimens) + pr_info("Best slot setup time for the whole test area was %ld.%.9lds\n", + rbestslottime.slot_runtime.tv_sec, + rbestslottime.slot_runtime.tv_nsec); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c index 9b78e8889638..8c77537af5a1 100644 --- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c @@ -19,7 +19,12 @@ struct { u32 function; u32 index; } mangled_cpuids[] = { + /* + * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR, + * which are not controlled for by this test. + */ {.function = 0xd, .index = 0}, + {.function = 0xd, .index = 1}, }; static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c index cb953df4d7d0..8aed0db1331d 100644 --- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c +++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c @@ -37,9 +37,7 @@ static void test_get_msr_index(void) int old_res, res, kvm_fd, r; struct kvm_msr_list *list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_index_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); @@ -101,9 +99,7 @@ static void test_get_msr_feature(void) int res, old_res, i, kvm_fd; struct kvm_msr_list *feature_list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_feature_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); diff --git a/tools/testing/selftests/nci/.gitignore b/tools/testing/selftests/nci/.gitignore new file mode 100644 index 000000000000..448eeb4590fc --- /dev/null +++ b/tools/testing/selftests/nci/.gitignore @@ -0,0 +1 @@ +/nci_dev diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 76d9487fb03c..5abe92d55b69 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1384,12 +1384,37 @@ ipv4_rt_replace() ipv4_rt_replace_mpath } +# checks that cached input route on VRF port is deleted +# when VRF is deleted +ipv4_local_rt_cache() +{ + run_cmd "ip addr add 10.0.0.1/32 dev lo" + run_cmd "ip netns add test-ns" + run_cmd "ip link add veth-outside type veth peer name veth-inside" + run_cmd "ip link add vrf-100 type vrf table 1100" + run_cmd "ip link set veth-outside master vrf-100" + run_cmd "ip link set veth-inside netns test-ns" + run_cmd "ip link set veth-outside up" + run_cmd "ip link set vrf-100 up" + run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100" + run_cmd "ip netns exec test-ns ip link set veth-inside up" + run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1" + run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1" + run_cmd "ip link delete vrf-100" + + # if we do not hang test is a success + log_test $? 0 "Cached route removed from VRF port device" +} + ipv4_route_test() { route_setup ipv4_rt_add ipv4_rt_replace + ipv4_local_rt_cache route_cleanup } diff --git a/tools/testing/selftests/net/icmp.sh b/tools/testing/selftests/net/icmp.sh new file mode 100755 index 000000000000..e4b04cd1644a --- /dev/null +++ b/tools/testing/selftests/net/icmp.sh @@ -0,0 +1,74 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for checking ICMP response with dummy address instead of 0.0.0.0. +# Sets up two namespaces like: +# +----------------------+ +--------------------+ +# | ns1 | v4-via-v6 routes: | ns2 | +# | | ' | | +# | +--------+ -> 172.16.1.0/24 -> +--------+ | +# | | veth0 +--------------------------+ veth0 | | +# | +--------+ <- 172.16.0.0/24 <- +--------+ | +# | 172.16.0.1 | | 2001:db8:1::2/64 | +# | 2001:db8:1::2/64 | | | +# +----------------------+ +--------------------+ +# +# And then tries to ping 172.16.1.1 from ns1. This results in a "net +# unreachable" message being sent from ns2, but there is no IPv4 address set in +# that address space, so the kernel should substitute the dummy address +# 192.0.0.8 defined in RFC7600. + +NS1=ns1 +NS2=ns2 +H1_IP=172.16.0.1/32 +H1_IP6=2001:db8:1::1 +RT1=172.16.1.0/24 +PINGADDR=172.16.1.1 +RT2=172.16.0.0/24 +H2_IP6=2001:db8:1::2 + +TMPFILE=$(mktemp) + +cleanup() +{ + rm -f "$TMPFILE" + ip netns del $NS1 + ip netns del $NS2 +} + +trap cleanup EXIT + +# Namespaces +ip netns add $NS1 +ip netns add $NS2 + +# Connectivity +ip -netns $NS1 link add veth0 type veth peer name veth0 netns $NS2 +ip -netns $NS1 link set dev veth0 up +ip -netns $NS2 link set dev veth0 up +ip -netns $NS1 addr add $H1_IP dev veth0 +ip -netns $NS1 addr add $H1_IP6/64 dev veth0 nodad +ip -netns $NS2 addr add $H2_IP6/64 dev veth0 nodad +ip -netns $NS1 route add $RT1 via inet6 $H2_IP6 +ip -netns $NS2 route add $RT2 via inet6 $H1_IP6 + +# Make sure ns2 will respond with ICMP unreachable +ip netns exec $NS2 sysctl -qw net.ipv4.icmp_ratelimit=0 net.ipv4.ip_forward=1 + +# Run the test - a ping runs in the background, and we capture ICMP responses +# with tcpdump; -c 1 means it should exit on the first ping, but add a timeout +# in case something goes wrong +ip netns exec $NS1 ping -w 3 -i 0.5 $PINGADDR >/dev/null & +ip netns exec $NS1 timeout 10 tcpdump -tpni veth0 -c 1 'icmp and icmp[icmptype] != icmp-echo' > $TMPFILE 2>/dev/null + +# Parse response and check for dummy address +# tcpdump output looks like: +# IP 192.0.0.8 > 172.16.0.1: ICMP net 172.16.1.1 unreachable, length 92 +RESP_IP=$(awk '{print $2}' < $TMPFILE) +if [[ "$RESP_IP" != "192.0.0.8" ]]; then + echo "FAIL - got ICMP response from $RESP_IP, should be 192.0.0.8" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 3c4cb72ed8a4..2b495dc8d78e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -197,9 +197,6 @@ ip -net "$ns4" link set ns4eth3 up ip -net "$ns4" route add default via 10.0.3.2 ip -net "$ns4" route add default via dead:beef:3::2 -# use TCP syn cookies, even if no flooding was detected. -ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 - set_ethtool_flags() { local ns="$1" local dev="$2" @@ -501,6 +498,7 @@ do_transfer() local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -518,10 +516,14 @@ do_transfer() "${stat_synrx_now_l}" "${expect_synrx}" 1>&2 retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then - printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ - "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 - rets=1 + if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then + if [ ${stat_ooo_now} -eq 0 ]; then + printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ + "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 + rets=1 + else + printf "[ Note ] fallback due to TCP OoO" + fi fi if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then @@ -732,6 +734,14 @@ for sender in $ns1 $ns2 $ns3 $ns4;do exit $ret fi + # ns1<->ns2 is not subject to reordering/tc delays. Use it to test + # mptcp syncookie support. + if [ $sender = $ns1 ]; then + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 + else + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1 + fi + run_tests "$ns2" $sender 10.0.1.2 run_tests "$ns2" $sender dead:beef:1::2 run_tests "$ns2" $sender 10.0.2.1 diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index a8fa64136282..7f26591f236b 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 readonly BASE="ns-$(mktemp -u XXXXXX)" diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 2fedc0781ce8..11d7cdb898c0 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -18,7 +18,8 @@ ret=0 cleanup() { local ns - local -r jobs="$(jobs -p)" + local jobs + readonly jobs="$(jobs -p)" [ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null rm -f $STATS @@ -108,7 +109,7 @@ chk_gro() { if [ ! -f ../bpf/xdp_dummy.o ]; then echo "Missing xdp_dummy helper. Build bpf selftest first" - exit -1 + exit 1 fi create_ns diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 3171069a6b46..cd6430b39982 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ +TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh new file mode 100755 index 000000000000..6caf6ac8c285 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_fib.sh @@ -0,0 +1,221 @@ +#!/bin/bash +# +# This tests the fib expression. +# +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns1="ns1-$sfx" +ns2="ns2-$sfx" +nsrouter="nsrouter-$sfx" +timeout=4 + +log_netns=$(sysctl -n net.netfilter.nf_log_all_netns) + +cleanup() +{ + ip netns del ${ns1} + ip netns del ${ns2} + ip netns del ${nsrouter} + + [ $log_netns -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns=$log_netns +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add ${nsrouter} +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace" + exit $ksft_skip +fi + +trap cleanup EXIT + +dmesg | grep -q ' nft_rpfilter: ' +if [ $? -eq 0 ]; then + dmesg -c | grep ' nft_rpfilter: ' + echo "WARN: a previous test run has failed" 1>&2 +fi + +sysctl -q net.netfilter.nf_log_all_netns=1 +ip netns add ${ns1} +ip netns add ${ns2} + +load_ruleset() { + local netns=$1 + +ip netns exec ${netns} nft -f /dev/stdin <<EOF +table inet filter { + chain prerouting { + type filter hook prerouting priority 0; policy accept; + fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop + } +} +EOF +} + +load_ruleset_count() { + local netns=$1 + +ip netns exec ${netns} nft -f /dev/stdin <<EOF +table inet filter { + chain prerouting { + type filter hook prerouting priority 0; policy accept; + ip daddr 1.1.1.1 fib saddr . iif oif missing counter drop + ip6 daddr 1c3::c01d fib saddr . iif oif missing counter drop + } +} +EOF +} + +check_drops() { + dmesg | grep -q ' nft_rpfilter: ' + if [ $? -eq 0 ]; then + dmesg | grep ' nft_rpfilter: ' + echo "FAIL: rpfilter did drop packets" + return 1 + fi + + return 0 +} + +check_fib_counter() { + local want=$1 + local ns=$2 + local address=$3 + + line=$(ip netns exec ${ns} nft list table inet filter | grep 'fib saddr . iif' | grep $address | grep "packets $want" ) + ret=$? + + if [ $ret -ne 0 ];then + echo "Netns $ns fib counter doesn't match expected packet count of $want for $address" 1>&2 + ip netns exec ${ns} nft list table inet filter + return 1 + fi + + if [ $want -gt 0 ]; then + echo "PASS: fib expression did drop packets for $address" + fi + + return 0 +} + +load_ruleset ${nsrouter} +load_ruleset ${ns1} +load_ruleset ${ns2} + +ip link add veth0 netns ${nsrouter} type veth peer name eth0 netns ${ns1} > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip +fi +ip link add veth1 netns ${nsrouter} type veth peer name eth0 netns ${ns2} + +ip -net ${nsrouter} link set lo up +ip -net ${nsrouter} link set veth0 up +ip -net ${nsrouter} addr add 10.0.1.1/24 dev veth0 +ip -net ${nsrouter} addr add dead:1::1/64 dev veth0 + +ip -net ${nsrouter} link set veth1 up +ip -net ${nsrouter} addr add 10.0.2.1/24 dev veth1 +ip -net ${nsrouter} addr add dead:2::1/64 dev veth1 + +ip -net ${ns1} link set lo up +ip -net ${ns1} link set eth0 up + +ip -net ${ns2} link set lo up +ip -net ${ns2} link set eth0 up + +ip -net ${ns1} addr add 10.0.1.99/24 dev eth0 +ip -net ${ns1} addr add dead:1::99/64 dev eth0 +ip -net ${ns1} route add default via 10.0.1.1 +ip -net ${ns1} route add default via dead:1::1 + +ip -net ${ns2} addr add 10.0.2.99/24 dev eth0 +ip -net ${ns2} addr add dead:2::99/64 dev eth0 +ip -net ${ns2} route add default via 10.0.2.1 +ip -net ${ns2} route add default via dead:2::1 + +test_ping() { + local daddr4=$1 + local daddr6=$2 + + ip netns exec ${ns1} ping -c 1 -q $daddr4 > /dev/null + ret=$? + if [ $ret -ne 0 ];then + check_drops + echo "FAIL: ${ns1} cannot reach $daddr4, ret $ret" 1>&2 + return 1 + fi + + ip netns exec ${ns1} ping -c 3 -q $daddr6 > /dev/null + ret=$? + if [ $ret -ne 0 ];then + check_drops + echo "FAIL: ${ns1} cannot reach $daddr6, ret $ret" 1>&2 + return 1 + fi + + return 0 +} + +ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null +ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + +sleep 3 + +test_ping 10.0.2.1 dead:2::1 || exit 1 +check_drops || exit 1 + +test_ping 10.0.2.99 dead:2::99 || exit 1 +check_drops || exit 1 + +echo "PASS: fib expression did not cause unwanted packet drops" + +ip netns exec ${nsrouter} nft flush table inet filter + +ip -net ${ns1} route del default +ip -net ${ns1} -6 route del default + +ip -net ${ns1} addr del 10.0.1.99/24 dev eth0 +ip -net ${ns1} addr del dead:1::99/64 dev eth0 + +ip -net ${ns1} addr add 10.0.2.99/24 dev eth0 +ip -net ${ns1} addr add dead:2::99/64 dev eth0 + +ip -net ${ns1} route add default via 10.0.2.1 +ip -net ${ns1} -6 route add default via dead:2::1 + +ip -net ${nsrouter} addr add dead:2::1/64 dev veth0 + +# switch to ruleset that doesn't log, this time +# its expected that this does drop the packets. +load_ruleset_count ${nsrouter} + +# ns1 has a default route, but nsrouter does not. +# must not check return value, ping to 1.1.1.1 will +# fail. +check_fib_counter 0 ${nsrouter} 1.1.1.1 || exit 1 +check_fib_counter 0 ${nsrouter} 1c3::c01d || exit 1 + +ip netns exec ${ns1} ping -c 1 -W 1 -q 1.1.1.1 > /dev/null +check_fib_counter 1 ${nsrouter} 1.1.1.1 || exit 1 + +sleep 2 +ip netns exec ${ns1} ping -c 3 -q 1c3::c01d > /dev/null +check_fib_counter 3 ${nsrouter} 1c3::c01d || exit 1 + +exit 0 diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index bed4b5318a86..8f3e72e626fa 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -10,6 +10,7 @@ /proc-self-map-files-002 /proc-self-syscall /proc-self-wchan +/proc-subset-pid /proc-uptime-001 /proc-uptime-002 /read diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json index 1cda2e11b3ad..773c5027553d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json @@ -9,11 +9,11 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536", - "expExitCode": "2", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_pie flows 65536", + "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc", - "matchCount": "0", + "matchPattern": "qdisc fq_pie 1: root refcnt 2 limit 10240p flows 65536", + "matchCount": "1", "teardown": [ "$IP link del dev $DUMMY" ] diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 7ed7cd95e58f..ebc4ee0fe179 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -363,6 +363,7 @@ ip1 -6 rule add table main suppress_prefixlength 0 ip1 -4 route add default dev wg0 table 51820 ip1 -4 rule add not fwmark 51820 table 51820 ip1 -4 rule add table main suppress_prefixlength 0 +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/vethc/rp_filter' # Flood the pings instead of sending just one, to trigger routing table reference counting bugs. n1 ping -W 1 -c 100 -f 192.168.99.7 n1 ping -W 1 -c 100 -f abab::1111 diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 4eecb432a66c..74db83a0aedd 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -19,7 +19,6 @@ CONFIG_NETFILTER_XTABLES=y CONFIG_NETFILTER_XT_NAT=y CONFIG_NETFILTER_XT_MATCH_LENGTH=y CONFIG_NETFILTER_XT_MARK=y -CONFIG_NF_CONNTRACK_IPV4=y CONFIG_NF_NAT_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6b4feb92dc79..6a6bc7af0e28 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -307,6 +307,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { return kvm_make_all_cpus_request_except(kvm, req, NULL); } +EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) @@ -2929,6 +2930,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) goto out; if (signal_pending(current)) goto out; + if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) + goto out; ret = 0; out: @@ -2973,8 +2976,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && !need_resched() && - ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); } prepare_to_rcuwait(&vcpu->wait); diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index c9bb3957f58a..28fda42e471b 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -40,21 +40,17 @@ static int __connect(struct irq_bypass_producer *prod, if (prod->add_consumer) ret = prod->add_consumer(prod, cons); - if (ret) - goto err_add_consumer; - - ret = cons->add_producer(cons, prod); - if (ret) - goto err_add_producer; + if (!ret) { + ret = cons->add_producer(cons, prod); + if (ret && prod->del_consumer) + prod->del_consumer(prod, cons); + } if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); -err_add_producer: - if (prod->del_consumer) - prod->del_consumer(prod, cons); -err_add_consumer: + return ret; } |