summaryrefslogtreecommitdiff
path: root/arch/s390
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/Kbuild4
-rw-r--r--arch/s390/Kconfig90
-rw-r--r--arch/s390/Makefile1
-rw-r--r--arch/s390/appldata/appldata_base.c2
-rw-r--r--arch/s390/boot/startup.c22
-rw-r--r--arch/s390/configs/debug_defconfig14
-rw-r--r--arch/s390/configs/defconfig12
-rw-r--r--arch/s390/configs/zfcpdump_defconfig1
-rw-r--r--arch/s390/crypto/paes_s390.c4
-rw-r--r--arch/s390/hypfs/Makefile11
-rw-r--r--arch/s390/hypfs/hypfs.h10
-rw-r--r--arch/s390/hypfs/hypfs_dbfs.c31
-rw-r--r--arch/s390/hypfs/hypfs_diag.c453
-rw-r--r--arch/s390/hypfs/hypfs_diag.h35
-rw-r--r--arch/s390/hypfs/hypfs_diag_fs.c393
-rw-r--r--arch/s390/hypfs/hypfs_vm.c175
-rw-r--r--arch/s390/hypfs/hypfs_vm.h50
-rw-r--r--arch/s390/hypfs/hypfs_vm_fs.c139
-rw-r--r--arch/s390/hypfs/inode.c39
-rw-r--r--arch/s390/include/asm/Kbuild1
-rw-r--r--arch/s390/include/asm/debug.h4
-rw-r--r--arch/s390/include/asm/diag.h3
-rw-r--r--arch/s390/include/asm/ftrace.h17
-rw-r--r--arch/s390/include/asm/io.h21
-rw-r--r--arch/s390/include/asm/kfence.h2
-rw-r--r--arch/s390/include/asm/kvm_host.h3
-rw-r--r--arch/s390/include/asm/maccess.h3
-rw-r--r--arch/s390/include/asm/page.h12
-rw-r--r--arch/s390/include/asm/pfault.h26
-rw-r--r--arch/s390/include/asm/pgalloc.h8
-rw-r--r--arch/s390/include/asm/pgtable.h35
-rw-r--r--arch/s390/include/asm/sclp.h1
-rw-r--r--arch/s390/include/asm/setup.h9
-rw-r--r--arch/s390/include/asm/tlb.h4
-rw-r--r--arch/s390/include/asm/uv.h6
-rw-r--r--arch/s390/include/uapi/asm/pkey.h2
-rw-r--r--arch/s390/include/uapi/asm/ptrace.h2
-rw-r--r--arch/s390/kernel/Makefile7
-rw-r--r--arch/s390/kernel/asm-offsets.c9
-rw-r--r--arch/s390/kernel/cert_store.c811
-rw-r--r--arch/s390/kernel/diag.c25
-rw-r--r--arch/s390/kernel/ebcdic.c2
-rw-r--r--arch/s390/kernel/entry.S2
-rw-r--r--arch/s390/kernel/ipl.c32
-rw-r--r--arch/s390/kernel/machine_kexec.c1
-rw-r--r--arch/s390/kernel/machine_kexec_file.c4
-rw-r--r--arch/s390/kernel/mcount.S65
-rw-r--r--arch/s390/kernel/setup.c3
-rw-r--r--arch/s390/kernel/smp.c16
-rw-r--r--arch/s390/kernel/sthyi.c10
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/s390/kernel/uv.c3
-rw-r--r--arch/s390/kvm/intercept.c9
-rw-r--r--arch/s390/kvm/kvm-s390.h12
-rw-r--r--arch/s390/kvm/pv.c22
-rw-r--r--arch/s390/lib/mem.S2
-rw-r--r--arch/s390/lib/tishift.S2
-rw-r--r--arch/s390/mm/Makefile1
-rw-r--r--arch/s390/mm/cmm.c2
-rw-r--r--arch/s390/mm/dump_pagetables.c2
-rw-r--r--arch/s390/mm/extmem.c9
-rw-r--r--arch/s390/mm/fault.c235
-rw-r--r--arch/s390/mm/gmap.c6
-rw-r--r--arch/s390/mm/maccess.c7
-rw-r--r--arch/s390/mm/pfault.c248
-rw-r--r--arch/s390/mm/pgalloc.c176
-rw-r--r--arch/s390/mm/vmem.c6
-rw-r--r--arch/s390/pci/pci.c57
-rw-r--r--arch/s390/pci/pci_clp.c7
69 files changed, 2260 insertions, 1179 deletions
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index 76e362277179..a5d3503b353c 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -3,11 +3,11 @@ obj-y += kernel/
obj-y += mm/
obj-$(CONFIG_KVM) += kvm/
obj-y += crypto/
-obj-$(CONFIG_S390_HYPFS_FS) += hypfs/
+obj-$(CONFIG_S390_HYPFS) += hypfs/
obj-$(CONFIG_APPLDATA_BASE) += appldata/
obj-y += net/
obj-$(CONFIG_PCI) += pci/
-obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/
+obj-$(CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY) += purgatory/
# for cleaning
subdir- += boot tools
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 91514d535c46..ae29e4392664 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -127,8 +127,8 @@ config S390
select ARCH_WANTS_NO_INSTR
select ARCH_WANT_DEFAULT_BPF_JIT
select ARCH_WANT_IPC_PARSE_VERSION
- select ARCH_WANT_OPTIMIZE_VMEMMAP
select ARCH_WANT_KERNEL_PMD_MKWRITE
+ select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
select BUILDTIME_TABLE_SORT
select CLONE_BACKWARDS2
select DMA_OPS if PCI
@@ -144,6 +144,7 @@ config S390
select GENERIC_SMP_IDLE_THREAD
select GENERIC_TIME_VSYSCALL
select GENERIC_VDSO_TIME_NS
+ select GENERIC_IOREMAP if PCI
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_JUMP_LABEL
@@ -175,6 +176,7 @@ config S390
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_ARG_ACCESS_API
select HAVE_FUNCTION_ERROR_INJECTION
+ select HAVE_FUNCTION_GRAPH_RETVAL
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
@@ -214,6 +216,7 @@ config S390
select HAVE_VIRT_CPU_ACCOUNTING_IDLE
select IOMMU_HELPER if PCI
select IOMMU_SUPPORT if PCI
+ select KEXEC
select MMU_GATHER_MERGE_VMAS
select MMU_GATHER_NO_GATHER
select MMU_GATHER_RCU_TABLE_FREE
@@ -245,6 +248,25 @@ config PGTABLE_LEVELS
source "kernel/livepatch/Kconfig"
+config ARCH_SUPPORTS_KEXEC
+ def_bool y
+
+config ARCH_SUPPORTS_KEXEC_FILE
+ def_bool CRYPTO && CRYPTO_SHA256 && CRYPTO_SHA256_S390
+
+config ARCH_SUPPORTS_KEXEC_SIG
+ def_bool MODULE_SIG_FORMAT
+
+config ARCH_SUPPORTS_KEXEC_PURGATORY
+ def_bool KEXEC_FILE
+
+config ARCH_SUPPORTS_CRASH_DUMP
+ def_bool y
+ help
+ Refer to <file:Documentation/arch/s390/zfcpdump.rst> for more details on this.
+ This option also enables s390 zfcpdump.
+ See also <file:Documentation/arch/s390/zfcpdump.rst>
+
menu "Processor type and features"
config HAVE_MARCH_Z10_FEATURES
@@ -483,35 +505,16 @@ config SCHED_TOPOLOGY
source "kernel/Kconfig.hz"
-config KEXEC
- def_bool y
- select KEXEC_CORE
-
-config KEXEC_FILE
- bool "kexec file based system call"
- select KEXEC_CORE
- depends on CRYPTO
- depends on CRYPTO_SHA256
- depends on CRYPTO_SHA256_S390
- help
- Enable the kexec file based system call. In contrast to the normal
- kexec system call this system call takes file descriptors for the
- kernel and initramfs as arguments.
-
-config ARCH_HAS_KEXEC_PURGATORY
- def_bool y
- depends on KEXEC_FILE
-
-config KEXEC_SIG
- bool "Verify kernel signature during kexec_file_load() syscall"
- depends on KEXEC_FILE && MODULE_SIG_FORMAT
+config CERT_STORE
+ bool "Get user certificates via DIAG320"
+ depends on KEYS
+ select CRYPTO_LIB_SHA256
help
- This option makes kernel signature verification mandatory for
- the kexec_file_load() syscall.
+ Enable this option if you want to access user-provided secure boot
+ certificates via DIAG 0x320.
- In addition to that option, you need to enable signature
- verification for the corresponding kernel image type being
- loaded in order for this to work.
+ These certificates will be made available via the keyring named
+ 'cert_store'.
config KERNEL_NOBP
def_bool n
@@ -734,22 +737,6 @@ config VFIO_AP
endmenu
-menu "Dump support"
-
-config CRASH_DUMP
- bool "kernel crash dumps"
- select KEXEC
- help
- Generate crash dump after being started by kexec.
- Crash dump kernels are loaded in the main kernel with kexec-tools
- into a specially reserved region and then later executed after
- a crash by kdump/kexec.
- Refer to <file:Documentation/s390/zfcpdump.rst> for more details on this.
- This option also enables s390 zfcpdump.
- See also <file:Documentation/s390/zfcpdump.rst>
-
-endmenu
-
config CCW
def_bool y
@@ -868,13 +855,24 @@ config APPLDATA_NET_SUM
This can also be compiled as a module, which will be called
appldata_net_sum.o.
-config S390_HYPFS_FS
+config S390_HYPFS
def_bool y
+ prompt "s390 hypervisor information"
+ help
+ This provides several binary files at (debugfs)/s390_hypfs/ to
+ provide accounting information in an s390 hypervisor environment.
+
+config S390_HYPFS_FS
+ def_bool n
prompt "s390 hypervisor file system support"
select SYS_HYPERVISOR
+ depends on S390_HYPFS
help
This is a virtual file system intended to provide accounting
- information in an s390 hypervisor environment.
+ information in an s390 hypervisor environment. This file system
+ is deprecated and should not be used.
+
+ Say N if you are unsure.
source "arch/s390/kvm/Kconfig"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 5ed242897b0d..a53a36ee0731 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -119,7 +119,6 @@ export KBUILD_CFLAGS_DECOMPRESSOR
OBJCOPYFLAGS := -O binary
libs-y += arch/s390/lib/
-drivers-y += drivers/s390/
boot := arch/s390/boot
syscalls := arch/s390/kernel/syscalls
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index bbefe5e86bdf..3b0994625652 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -365,7 +365,7 @@ int appldata_register_ops(struct appldata_ops *ops)
ops->ctl_table[0].proc_handler = appldata_generic_handler;
ops->ctl_table[0].data = ops;
- ops->sysctl_header = register_sysctl(appldata_proc_name, ops->ctl_table);
+ ops->sysctl_header = register_sysctl_sz(appldata_proc_name, ops->ctl_table, 1);
if (!ops->sysctl_header)
goto out;
return 0;
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 64bd7ac3e35d..b9681cb22753 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -27,6 +27,7 @@ struct page *__bootdata_preserved(vmemmap);
unsigned long __bootdata_preserved(vmemmap_size);
unsigned long __bootdata_preserved(MODULES_VADDR);
unsigned long __bootdata_preserved(MODULES_END);
+unsigned long __bootdata_preserved(max_mappable);
unsigned long __bootdata(ident_map_size);
u64 __bootdata_preserved(stfle_fac_list[16]);
@@ -176,6 +177,7 @@ static unsigned long setup_kernel_memory_layout(void)
unsigned long asce_limit;
unsigned long rte_size;
unsigned long pages;
+ unsigned long vsize;
unsigned long vmax;
pages = ident_map_size / PAGE_SIZE;
@@ -183,19 +185,19 @@ static unsigned long setup_kernel_memory_layout(void)
vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);
/* choose kernel address space layout: 4 or 3 levels. */
- vmemmap_start = round_up(ident_map_size, _REGION3_SIZE);
- if (IS_ENABLED(CONFIG_KASAN) ||
- vmalloc_size > _REGION2_SIZE ||
- vmemmap_start + vmemmap_size + vmalloc_size + MODULES_LEN >
- _REGION2_SIZE) {
+ vsize = round_up(ident_map_size, _REGION3_SIZE) + vmemmap_size +
+ MODULES_LEN + MEMCPY_REAL_SIZE + ABS_LOWCORE_MAP_SIZE;
+ vsize = size_add(vsize, vmalloc_size);
+ if (IS_ENABLED(CONFIG_KASAN) || (vsize > _REGION2_SIZE)) {
asce_limit = _REGION1_SIZE;
rte_size = _REGION2_SIZE;
} else {
asce_limit = _REGION2_SIZE;
rte_size = _REGION3_SIZE;
}
+
/*
- * forcing modules and vmalloc area under the ultravisor
+ * Forcing modules and vmalloc area under the ultravisor
* secure storage limit, so that any vmalloc allocation
* we do could be used to back secure guest storage.
*/
@@ -204,7 +206,7 @@ static unsigned long setup_kernel_memory_layout(void)
/* force vmalloc and modules below kasan shadow */
vmax = min(vmax, KASAN_SHADOW_START);
#endif
- __memcpy_real_area = round_down(vmax - PAGE_SIZE, PAGE_SIZE);
+ __memcpy_real_area = round_down(vmax - MEMCPY_REAL_SIZE, PAGE_SIZE);
__abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE,
sizeof(struct lowcore));
MODULES_END = round_down(__abs_lowcore, _SEGMENT_SIZE);
@@ -220,8 +222,9 @@ static unsigned long setup_kernel_memory_layout(void)
pages = SECTION_ALIGN_UP(pages);
/* keep vmemmap_start aligned to a top level region table entry */
vmemmap_start = round_down(VMALLOC_START - pages * sizeof(struct page), rte_size);
- /* vmemmap_start is the future VMEM_MAX_PHYS, make sure it is within MAX_PHYSMEM */
vmemmap_start = min(vmemmap_start, 1UL << MAX_PHYSMEM_BITS);
+ /* maximum mappable address as seen by arch_get_mappable_range() */
+ max_mappable = vmemmap_start;
/* make sure identity map doesn't overlay with vmemmap */
ident_map_size = min(ident_map_size, vmemmap_start);
vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page);
@@ -286,8 +289,9 @@ void startup_kernel(void)
setup_lpp();
safe_addr = mem_safe_offset();
+
/*
- * reserve decompressor memory together with decompression heap, buffer and
+ * Reserve decompressor memory together with decompression heap, buffer and
* memory which might be occupied by uncompressed kernel at default 1Mb
* position (if KASLR is off or failed).
*/
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index aa95cf6dfabb..af2fbe48e16c 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -116,7 +116,6 @@ CONFIG_UNIX=y
CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
-CONFIG_NET_TC_SKB_EXT=y
CONFIG_SMC=m
CONFIG_SMC_DIAG=m
CONFIG_INET=y
@@ -193,6 +192,7 @@ CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NETFILTER_XTABLES_COMPAT=y
CONFIG_NETFILTER_XT_SET=m
CONFIG_NETFILTER_XT_TARGET_AUDIT=m
CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -379,6 +379,7 @@ CONFIG_NET_ACT_SIMP=m
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_NET_ACT_GATE=m
+CONFIG_NET_TC_SKB_EXT=y
CONFIG_DNS_RESOLVER=y
CONFIG_OPENVSWITCH=m
CONFIG_VSOCKETS=m
@@ -395,6 +396,7 @@ CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_S390=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_SAFE=y
+# CONFIG_FW_LOADER is not set
CONFIG_CONNECTOR=y
CONFIG_ZRAM=y
CONFIG_BLK_DEV_LOOP=m
@@ -502,7 +504,6 @@ CONFIG_NLMON=m
# CONFIG_NET_VENDOR_GOOGLE is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_WANGXUN is not set
# CONFIG_NET_VENDOR_LITEX is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
@@ -542,6 +543,7 @@ CONFIG_MLX5_CORE_EN=y
# CONFIG_NET_VENDOR_TI is not set
# CONFIG_NET_VENDOR_VERTEXCOM is not set
# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WANGXUN is not set
# CONFIG_NET_VENDOR_WIZNET is not set
# CONFIG_NET_VENDOR_XILINX is not set
CONFIG_PPP=m
@@ -624,7 +626,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y
CONFIG_QUOTA_DEBUG=y
CONFIG_QFMT_V1=m
CONFIG_QFMT_V2=m
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
@@ -646,7 +648,6 @@ CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_TMPFS_INODE64=y
CONFIG_HUGETLBFS=y
-CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
@@ -690,7 +691,6 @@ CONFIG_HARDENED_USERCOPY=y
CONFIG_FORTIFY_SOURCE=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
CONFIG_SECURITY_LANDLOCK=y
@@ -744,7 +744,6 @@ CONFIG_CRYPTO_MD4=m
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_SM3_GENERIC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_WP512=m
@@ -836,6 +835,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300
# CONFIG_RCU_TRACE is not set
CONFIG_LATENCYTOP=y
CONFIG_BOOTTIME_TRACING=y
+CONFIG_FUNCTION_GRAPH_RETVAL=y
CONFIG_FPROBE=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_STACK_TRACER=y
@@ -844,6 +844,7 @@ CONFIG_PREEMPT_TRACER=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_USER_EVENTS=y
CONFIG_HIST_TRIGGERS=y
CONFIG_FTRACE_STARTUP_TEST=y
# CONFIG_EVENT_TRACE_STARTUP_TEST is not set
@@ -866,6 +867,7 @@ CONFIG_FAIL_MAKE_REQUEST=y
CONFIG_FAIL_IO_TIMEOUT=y
CONFIG_FAIL_FUTEX=y
CONFIG_FAULT_INJECTION_DEBUG_FS=y
+CONFIG_FAULT_INJECTION_CONFIGFS=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
CONFIG_LKDTM=m
CONFIG_TEST_MIN_HEAP=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index f041945f9148..3f263b767a4c 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -107,7 +107,6 @@ CONFIG_UNIX=y
CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
-CONFIG_NET_TC_SKB_EXT=y
CONFIG_SMC=m
CONFIG_SMC_DIAG=m
CONFIG_INET=y
@@ -184,6 +183,7 @@ CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NETFILTER_XTABLES_COMPAT=y
CONFIG_NETFILTER_XT_SET=m
CONFIG_NETFILTER_XT_TARGET_AUDIT=m
CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -369,6 +369,7 @@ CONFIG_NET_ACT_SIMP=m
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_NET_ACT_GATE=m
+CONFIG_NET_TC_SKB_EXT=y
CONFIG_DNS_RESOLVER=y
CONFIG_OPENVSWITCH=m
CONFIG_VSOCKETS=m
@@ -385,6 +386,7 @@ CONFIG_HOTPLUG_PCI_S390=y
CONFIG_UEVENT_HELPER=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_SAFE=y
+# CONFIG_FW_LOADER is not set
CONFIG_CONNECTOR=y
CONFIG_ZRAM=y
CONFIG_BLK_DEV_LOOP=m
@@ -492,7 +494,6 @@ CONFIG_NLMON=m
# CONFIG_NET_VENDOR_GOOGLE is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_WANGXUN is not set
# CONFIG_NET_VENDOR_LITEX is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
@@ -532,6 +533,7 @@ CONFIG_MLX5_CORE_EN=y
# CONFIG_NET_VENDOR_TI is not set
# CONFIG_NET_VENDOR_VERTEXCOM is not set
# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WANGXUN is not set
# CONFIG_NET_VENDOR_WIZNET is not set
# CONFIG_NET_VENDOR_XILINX is not set
CONFIG_PPP=m
@@ -609,7 +611,7 @@ CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
CONFIG_QFMT_V1=m
CONFIG_QFMT_V2=m
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
@@ -673,7 +675,6 @@ CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
CONFIG_SECURITY_LANDLOCK=y
@@ -729,7 +730,6 @@ CONFIG_CRYPTO_MD4=m
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_SM3_GENERIC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_WP512=m
@@ -787,12 +787,14 @@ CONFIG_RCU_REF_SCALE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LATENCYTOP=y
CONFIG_BOOTTIME_TRACING=y
+CONFIG_FUNCTION_GRAPH_RETVAL=y
CONFIG_FPROBE=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_STACK_TRACER=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_USER_EVENTS=y
CONFIG_HIST_TRIGGERS=y
CONFIG_SAMPLES=y
CONFIG_SAMPLE_TRACE_PRINTK=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 6f68b39817ef..e62fb2015102 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -53,7 +53,6 @@ CONFIG_ZFCP=y
# CONFIG_HVC_IUCV is not set
# CONFIG_HW_RANDOM_S390 is not set
# CONFIG_HMC_DRV is not set
-# CONFIG_S390_UV_UAPI is not set
# CONFIG_S390_TAPE is not set
# CONFIG_VMCP is not set
# CONFIG_MONWRITER is not set
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index d29a9d908797..8b541e44151d 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -35,7 +35,7 @@
* and padding is also possible, the limits need to be generous.
*/
#define PAES_MIN_KEYSIZE 16
-#define PAES_MAX_KEYSIZE 320
+#define PAES_MAX_KEYSIZE MAXEP11AESKEYBLOBSIZE
static u8 *ctrblk;
static DEFINE_MUTEX(ctrblk_lock);
@@ -103,7 +103,7 @@ static inline void _free_kb_keybuf(struct key_blob *kb)
{
if (kb->key && kb->key != kb->keybuf
&& kb->keylen > sizeof(kb->keybuf)) {
- kfree(kb->key);
+ kfree_sensitive(kb->key);
kb->key = NULL;
}
}
diff --git a/arch/s390/hypfs/Makefile b/arch/s390/hypfs/Makefile
index 06f601509ce9..c34854d298f8 100644
--- a/arch/s390/hypfs/Makefile
+++ b/arch/s390/hypfs/Makefile
@@ -3,7 +3,12 @@
# Makefile for the linux hypfs filesystem routines.
#
-obj-$(CONFIG_S390_HYPFS_FS) += s390_hypfs.o
+obj-$(CONFIG_S390_HYPFS) += hypfs_dbfs.o
+obj-$(CONFIG_S390_HYPFS) += hypfs_diag.o
+obj-$(CONFIG_S390_HYPFS) += hypfs_diag0c.o
+obj-$(CONFIG_S390_HYPFS) += hypfs_sprp.o
+obj-$(CONFIG_S390_HYPFS) += hypfs_vm.o
-s390_hypfs-objs := inode.o hypfs_diag.o hypfs_vm.o hypfs_dbfs.o hypfs_sprp.o
-s390_hypfs-objs += hypfs_diag0c.o
+obj-$(CONFIG_S390_HYPFS_FS) += hypfs_diag_fs.o
+obj-$(CONFIG_S390_HYPFS_FS) += hypfs_vm_fs.o
+obj-$(CONFIG_S390_HYPFS_FS) += inode.o
diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h
index 05f3f9aee5fc..65f4036fd541 100644
--- a/arch/s390/hypfs/hypfs.h
+++ b/arch/s390/hypfs/hypfs.h
@@ -46,6 +46,15 @@ void hypfs_diag0c_exit(void);
void hypfs_sprp_init(void);
void hypfs_sprp_exit(void);
+int __hypfs_fs_init(void);
+
+static inline int hypfs_fs_init(void)
+{
+ if (IS_ENABLED(CONFIG_S390_HYPFS_FS))
+ return __hypfs_fs_init();
+ return 0;
+}
+
/* debugfs interface */
struct hypfs_dbfs_file;
@@ -69,7 +78,6 @@ struct hypfs_dbfs_file {
struct dentry *dentry;
};
-extern void hypfs_dbfs_init(void);
extern void hypfs_dbfs_exit(void);
extern void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df);
extern void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df);
diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c
index f4c7dbfaf8ee..4024599eb448 100644
--- a/arch/s390/hypfs/hypfs_dbfs.c
+++ b/arch/s390/hypfs/hypfs_dbfs.c
@@ -90,12 +90,33 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df)
debugfs_remove(df->dentry);
}
-void hypfs_dbfs_init(void)
+static int __init hypfs_dbfs_init(void)
{
- dbfs_dir = debugfs_create_dir("s390_hypfs", NULL);
-}
+ int rc = -ENODATA;
-void hypfs_dbfs_exit(void)
-{
+ dbfs_dir = debugfs_create_dir("s390_hypfs", NULL);
+ if (hypfs_diag_init())
+ goto fail_dbfs_exit;
+ if (hypfs_vm_init())
+ goto fail_hypfs_diag_exit;
+ hypfs_sprp_init();
+ if (hypfs_diag0c_init())
+ goto fail_hypfs_sprp_exit;
+ rc = hypfs_fs_init();
+ if (rc)
+ goto fail_hypfs_diag0c_exit;
+ return 0;
+
+fail_hypfs_diag0c_exit:
+ hypfs_diag0c_exit();
+fail_hypfs_sprp_exit:
+ hypfs_sprp_exit();
+ hypfs_vm_exit();
+fail_hypfs_diag_exit:
+ hypfs_diag_exit();
+ pr_err("Initialization of hypfs failed with rc=%i\n", rc);
+fail_dbfs_exit:
debugfs_remove(dbfs_dir);
+ return rc;
}
+device_initcall(hypfs_dbfs_init)
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index c3be533c4cd3..279b7bba4d43 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -18,188 +18,27 @@
#include <linux/mm.h>
#include <asm/diag.h>
#include <asm/ebcdic.h>
+#include "hypfs_diag.h"
#include "hypfs.h"
-#define TMP_SIZE 64 /* size of temporary buffers */
-
#define DBFS_D204_HDR_VERSION 0
-static char *diag224_cpu_names; /* diag 224 name table */
static enum diag204_sc diag204_store_sc; /* used subcode for store */
static enum diag204_format diag204_info_type; /* used diag 204 data format */
static void *diag204_buf; /* 4K aligned buffer for diag204 data */
-static void *diag204_buf_vmalloc; /* vmalloc pointer for diag204 data */
static int diag204_buf_pages; /* number of pages for diag204 data */
static struct dentry *dbfs_d204_file;
-/*
- * DIAG 204 member access functions.
- *
- * Since we have two different diag 204 data formats for old and new s390
- * machines, we do not access the structs directly, but use getter functions for
- * each struct member instead. This should make the code more readable.
- */
-
-/* Time information block */
-
-static inline int info_blk_hdr__size(enum diag204_format type)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return sizeof(struct diag204_info_blk_hdr);
- else /* DIAG204_INFO_EXT */
- return sizeof(struct diag204_x_info_blk_hdr);
-}
-
-static inline __u8 info_blk_hdr__npar(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_info_blk_hdr *)hdr)->npar;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_info_blk_hdr *)hdr)->npar;
-}
-
-static inline __u8 info_blk_hdr__flags(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_info_blk_hdr *)hdr)->flags;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_info_blk_hdr *)hdr)->flags;
-}
-
-/* Partition header */
-
-static inline int part_hdr__size(enum diag204_format type)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return sizeof(struct diag204_part_hdr);
- else /* DIAG204_INFO_EXT */
- return sizeof(struct diag204_x_part_hdr);
-}
-
-static inline __u8 part_hdr__rcpus(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_part_hdr *)hdr)->cpus;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_part_hdr *)hdr)->rcpus;
-}
-
-static inline void part_hdr__part_name(enum diag204_format type, void *hdr,
- char *name)
-{
- if (type == DIAG204_INFO_SIMPLE)
- memcpy(name, ((struct diag204_part_hdr *)hdr)->part_name,
- DIAG204_LPAR_NAME_LEN);
- else /* DIAG204_INFO_EXT */
- memcpy(name, ((struct diag204_x_part_hdr *)hdr)->part_name,
- DIAG204_LPAR_NAME_LEN);
- EBCASC(name, DIAG204_LPAR_NAME_LEN);
- name[DIAG204_LPAR_NAME_LEN] = 0;
- strim(name);
-}
-
-/* CPU info block */
-
-static inline int cpu_info__size(enum diag204_format type)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return sizeof(struct diag204_cpu_info);
- else /* DIAG204_INFO_EXT */
- return sizeof(struct diag204_x_cpu_info);
-}
-
-static inline __u8 cpu_info__ctidx(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_cpu_info *)hdr)->ctidx;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_cpu_info *)hdr)->ctidx;
-}
-
-static inline __u16 cpu_info__cpu_addr(enum diag204_format type, void *hdr)
+enum diag204_format diag204_get_info_type(void)
{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_cpu_info *)hdr)->cpu_addr;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_cpu_info *)hdr)->cpu_addr;
+ return diag204_info_type;
}
-static inline __u64 cpu_info__acc_time(enum diag204_format type, void *hdr)
+static void diag204_set_info_type(enum diag204_format type)
{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_cpu_info *)hdr)->acc_time;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_cpu_info *)hdr)->acc_time;
-}
-
-static inline __u64 cpu_info__lp_time(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_cpu_info *)hdr)->lp_time;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_cpu_info *)hdr)->lp_time;
-}
-
-static inline __u64 cpu_info__online_time(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return 0; /* online_time not available in simple info */
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_cpu_info *)hdr)->online_time;
-}
-
-/* Physical header */
-
-static inline int phys_hdr__size(enum diag204_format type)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return sizeof(struct diag204_phys_hdr);
- else /* DIAG204_INFO_EXT */
- return sizeof(struct diag204_x_phys_hdr);
-}
-
-static inline __u8 phys_hdr__cpus(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_phys_hdr *)hdr)->cpus;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_phys_hdr *)hdr)->cpus;
-}
-
-/* Physical CPU info block */
-
-static inline int phys_cpu__size(enum diag204_format type)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return sizeof(struct diag204_phys_cpu);
- else /* DIAG204_INFO_EXT */
- return sizeof(struct diag204_x_phys_cpu);
-}
-
-static inline __u16 phys_cpu__cpu_addr(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_phys_cpu *)hdr)->cpu_addr;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_phys_cpu *)hdr)->cpu_addr;
-}
-
-static inline __u64 phys_cpu__mgm_time(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_phys_cpu *)hdr)->mgm_time;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_phys_cpu *)hdr)->mgm_time;
-}
-
-static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr)
-{
- if (type == DIAG204_INFO_SIMPLE)
- return ((struct diag204_phys_cpu *)hdr)->ctidx;
- else /* DIAG204_INFO_EXT */
- return ((struct diag204_x_phys_cpu *)hdr)->ctidx;
+ diag204_info_type = type;
}
/* Diagnose 204 functions */
@@ -212,43 +51,11 @@ static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr)
static void diag204_free_buffer(void)
{
- if (!diag204_buf)
- return;
- if (diag204_buf_vmalloc) {
- vfree(diag204_buf_vmalloc);
- diag204_buf_vmalloc = NULL;
- } else {
- free_pages((unsigned long) diag204_buf, 0);
- }
+ vfree(diag204_buf);
diag204_buf = NULL;
}
-static void *page_align_ptr(void *ptr)
-{
- return (void *) PAGE_ALIGN((unsigned long) ptr);
-}
-
-static void *diag204_alloc_vbuf(int pages)
-{
- /* The buffer has to be page aligned! */
- diag204_buf_vmalloc = vmalloc(array_size(PAGE_SIZE, (pages + 1)));
- if (!diag204_buf_vmalloc)
- return ERR_PTR(-ENOMEM);
- diag204_buf = page_align_ptr(diag204_buf_vmalloc);
- diag204_buf_pages = pages;
- return diag204_buf;
-}
-
-static void *diag204_alloc_rbuf(void)
-{
- diag204_buf = (void*)__get_free_pages(GFP_KERNEL,0);
- if (!diag204_buf)
- return ERR_PTR(-ENOMEM);
- diag204_buf_pages = 1;
- return diag204_buf;
-}
-
-static void *diag204_get_buffer(enum diag204_format fmt, int *pages)
+void *diag204_get_buffer(enum diag204_format fmt, int *pages)
{
if (diag204_buf) {
*pages = diag204_buf_pages;
@@ -256,15 +63,19 @@ static void *diag204_get_buffer(enum diag204_format fmt, int *pages)
}
if (fmt == DIAG204_INFO_SIMPLE) {
*pages = 1;
- return diag204_alloc_rbuf();
} else {/* DIAG204_INFO_EXT */
*pages = diag204((unsigned long)DIAG204_SUBC_RSI |
(unsigned long)DIAG204_INFO_EXT, 0, NULL);
if (*pages <= 0)
- return ERR_PTR(-ENOSYS);
- else
- return diag204_alloc_vbuf(*pages);
+ return ERR_PTR(-EOPNOTSUPP);
}
+ diag204_buf = __vmalloc_node(array_size(*pages, PAGE_SIZE),
+ PAGE_SIZE, GFP_KERNEL, NUMA_NO_NODE,
+ __builtin_return_address(0));
+ if (!diag204_buf)
+ return ERR_PTR(-ENOMEM);
+ diag204_buf_pages = *pages;
+ return diag204_buf;
}
/*
@@ -291,13 +102,13 @@ static int diag204_probe(void)
if (diag204((unsigned long)DIAG204_SUBC_STIB7 |
(unsigned long)DIAG204_INFO_EXT, pages, buf) >= 0) {
diag204_store_sc = DIAG204_SUBC_STIB7;
- diag204_info_type = DIAG204_INFO_EXT;
+ diag204_set_info_type(DIAG204_INFO_EXT);
goto out;
}
if (diag204((unsigned long)DIAG204_SUBC_STIB6 |
(unsigned long)DIAG204_INFO_EXT, pages, buf) >= 0) {
diag204_store_sc = DIAG204_SUBC_STIB6;
- diag204_info_type = DIAG204_INFO_EXT;
+ diag204_set_info_type(DIAG204_INFO_EXT);
goto out;
}
diag204_free_buffer();
@@ -313,10 +124,10 @@ static int diag204_probe(void)
if (diag204((unsigned long)DIAG204_SUBC_STIB4 |
(unsigned long)DIAG204_INFO_SIMPLE, pages, buf) >= 0) {
diag204_store_sc = DIAG204_SUBC_STIB4;
- diag204_info_type = DIAG204_INFO_SIMPLE;
+ diag204_set_info_type(DIAG204_INFO_SIMPLE);
goto out;
} else {
- rc = -ENOSYS;
+ rc = -EOPNOTSUPP;
goto fail_store;
}
out:
@@ -327,58 +138,13 @@ fail_alloc:
return rc;
}
-static int diag204_do_store(void *buf, int pages)
+int diag204_store(void *buf, int pages)
{
int rc;
- rc = diag204((unsigned long) diag204_store_sc |
- (unsigned long) diag204_info_type, pages, buf);
- return rc < 0 ? -ENOSYS : 0;
-}
-
-static void *diag204_store(void)
-{
- void *buf;
- int pages, rc;
-
- buf = diag204_get_buffer(diag204_info_type, &pages);
- if (IS_ERR(buf))
- goto out;
- rc = diag204_do_store(buf, pages);
- if (rc)
- return ERR_PTR(rc);
-out:
- return buf;
-}
-
-/* Diagnose 224 functions */
-
-static int diag224_get_name_table(void)
-{
- /* memory must be below 2GB */
- diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA);
- if (!diag224_cpu_names)
- return -ENOMEM;
- if (diag224(diag224_cpu_names)) {
- free_page((unsigned long) diag224_cpu_names);
- return -EOPNOTSUPP;
- }
- EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16);
- return 0;
-}
-
-static void diag224_delete_name_table(void)
-{
- free_page((unsigned long) diag224_cpu_names);
-}
-
-static int diag224_idx2name(int index, char *name)
-{
- memcpy(name, diag224_cpu_names + ((index + 1) * DIAG204_CPU_NAME_LEN),
- DIAG204_CPU_NAME_LEN);
- name[DIAG204_CPU_NAME_LEN] = 0;
- strim(name);
- return 0;
+ rc = diag204((unsigned long)diag204_store_sc |
+ (unsigned long)diag204_get_info_type(), pages, buf);
+ return rc < 0 ? -EOPNOTSUPP : 0;
}
struct dbfs_d204_hdr {
@@ -403,8 +169,8 @@ static int dbfs_d204_create(void **data, void **data_free_ptr, size_t *size)
base = vzalloc(buf_size);
if (!base)
return -ENOMEM;
- d204 = page_align_ptr(base + sizeof(d204->hdr)) - sizeof(d204->hdr);
- rc = diag204_do_store(d204->buf, diag204_buf_pages);
+ d204 = PTR_ALIGN(base + sizeof(d204->hdr), PAGE_SIZE) - sizeof(d204->hdr);
+ rc = diag204_store(d204->buf, diag204_buf_pages);
if (rc) {
vfree(base);
return rc;
@@ -433,176 +199,21 @@ __init int hypfs_diag_init(void)
return -ENODATA;
}
- if (diag204_info_type == DIAG204_INFO_EXT)
+ if (diag204_get_info_type() == DIAG204_INFO_EXT)
hypfs_dbfs_create_file(&dbfs_file_d204);
- if (MACHINE_IS_LPAR) {
- rc = diag224_get_name_table();
- if (rc) {
- pr_err("The hardware system does not provide all "
- "functions required by hypfs\n");
- debugfs_remove(dbfs_d204_file);
- return rc;
- }
+ rc = hypfs_diag_fs_init();
+ if (rc) {
+ pr_err("The hardware system does not provide all functions required by hypfs\n");
+ debugfs_remove(dbfs_d204_file);
}
- return 0;
+ return rc;
}
void hypfs_diag_exit(void)
{
debugfs_remove(dbfs_d204_file);
- diag224_delete_name_table();
+ hypfs_diag_fs_exit();
diag204_free_buffer();
hypfs_dbfs_remove_file(&dbfs_file_d204);
}
-
-/*
- * Functions to create the directory structure
- * *******************************************
- */
-
-static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
-{
- struct dentry *cpu_dir;
- char buffer[TMP_SIZE];
- void *rc;
-
- snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_info_type,
- cpu_info));
- cpu_dir = hypfs_mkdir(cpus_dir, buffer);
- rc = hypfs_create_u64(cpu_dir, "mgmtime",
- cpu_info__acc_time(diag204_info_type, cpu_info) -
- cpu_info__lp_time(diag204_info_type, cpu_info));
- if (IS_ERR(rc))
- return PTR_ERR(rc);
- rc = hypfs_create_u64(cpu_dir, "cputime",
- cpu_info__lp_time(diag204_info_type, cpu_info));
- if (IS_ERR(rc))
- return PTR_ERR(rc);
- if (diag204_info_type == DIAG204_INFO_EXT) {
- rc = hypfs_create_u64(cpu_dir, "onlinetime",
- cpu_info__online_time(diag204_info_type,
- cpu_info));
- if (IS_ERR(rc))
- return PTR_ERR(rc);
- }
- diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer);
- rc = hypfs_create_str(cpu_dir, "type", buffer);
- return PTR_ERR_OR_ZERO(rc);
-}
-
-static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
-{
- struct dentry *cpus_dir;
- struct dentry *lpar_dir;
- char lpar_name[DIAG204_LPAR_NAME_LEN + 1];
- void *cpu_info;
- int i;
-
- part_hdr__part_name(diag204_info_type, part_hdr, lpar_name);
- lpar_name[DIAG204_LPAR_NAME_LEN] = 0;
- lpar_dir = hypfs_mkdir(systems_dir, lpar_name);
- if (IS_ERR(lpar_dir))
- return lpar_dir;
- cpus_dir = hypfs_mkdir(lpar_dir, "cpus");
- if (IS_ERR(cpus_dir))
- return cpus_dir;
- cpu_info = part_hdr + part_hdr__size(diag204_info_type);
- for (i = 0; i < part_hdr__rcpus(diag204_info_type, part_hdr); i++) {
- int rc;
- rc = hypfs_create_cpu_files(cpus_dir, cpu_info);
- if (rc)
- return ERR_PTR(rc);
- cpu_info += cpu_info__size(diag204_info_type);
- }
- return cpu_info;
-}
-
-static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info)
-{
- struct dentry *cpu_dir;
- char buffer[TMP_SIZE];
- void *rc;
-
- snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_info_type,
- cpu_info));
- cpu_dir = hypfs_mkdir(cpus_dir, buffer);
- if (IS_ERR(cpu_dir))
- return PTR_ERR(cpu_dir);
- rc = hypfs_create_u64(cpu_dir, "mgmtime",
- phys_cpu__mgm_time(diag204_info_type, cpu_info));
- if (IS_ERR(rc))
- return PTR_ERR(rc);
- diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer);
- rc = hypfs_create_str(cpu_dir, "type", buffer);
- return PTR_ERR_OR_ZERO(rc);
-}
-
-static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
-{
- int i;
- void *cpu_info;
- struct dentry *cpus_dir;
-
- cpus_dir = hypfs_mkdir(parent_dir, "cpus");
- if (IS_ERR(cpus_dir))
- return cpus_dir;
- cpu_info = phys_hdr + phys_hdr__size(diag204_info_type);
- for (i = 0; i < phys_hdr__cpus(diag204_info_type, phys_hdr); i++) {
- int rc;
- rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info);
- if (rc)
- return ERR_PTR(rc);
- cpu_info += phys_cpu__size(diag204_info_type);
- }
- return cpu_info;
-}
-
-int hypfs_diag_create_files(struct dentry *root)
-{
- struct dentry *systems_dir, *hyp_dir;
- void *time_hdr, *part_hdr;
- int i, rc;
- void *buffer, *ptr;
-
- buffer = diag204_store();
- if (IS_ERR(buffer))
- return PTR_ERR(buffer);
-
- systems_dir = hypfs_mkdir(root, "systems");
- if (IS_ERR(systems_dir)) {
- rc = PTR_ERR(systems_dir);
- goto err_out;
- }
- time_hdr = (struct x_info_blk_hdr *)buffer;
- part_hdr = time_hdr + info_blk_hdr__size(diag204_info_type);
- for (i = 0; i < info_blk_hdr__npar(diag204_info_type, time_hdr); i++) {
- part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr);
- if (IS_ERR(part_hdr)) {
- rc = PTR_ERR(part_hdr);
- goto err_out;
- }
- }
- if (info_blk_hdr__flags(diag204_info_type, time_hdr) &
- DIAG204_LPAR_PHYS_FLG) {
- ptr = hypfs_create_phys_files(root, part_hdr);
- if (IS_ERR(ptr)) {
- rc = PTR_ERR(ptr);
- goto err_out;
- }
- }
- hyp_dir = hypfs_mkdir(root, "hyp");
- if (IS_ERR(hyp_dir)) {
- rc = PTR_ERR(hyp_dir);
- goto err_out;
- }
- ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor");
- if (IS_ERR(ptr)) {
- rc = PTR_ERR(ptr);
- goto err_out;
- }
- rc = 0;
-
-err_out:
- return rc;
-}
diff --git a/arch/s390/hypfs/hypfs_diag.h b/arch/s390/hypfs/hypfs_diag.h
new file mode 100644
index 000000000000..7090eff27fef
--- /dev/null
+++ b/arch/s390/hypfs/hypfs_diag.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Hypervisor filesystem for Linux on s390. Diag 204 and 224
+ * implementation.
+ *
+ * Copyright IBM Corp. 2006, 2008
+ * Author(s): Michael Holzheu <holzheu@de.ibm.com>
+ */
+
+#ifndef _S390_HYPFS_DIAG_H_
+#define _S390_HYPFS_DIAG_H_
+
+#include <asm/diag.h>
+
+enum diag204_format diag204_get_info_type(void);
+void *diag204_get_buffer(enum diag204_format fmt, int *pages);
+int diag204_store(void *buf, int pages);
+
+int __hypfs_diag_fs_init(void);
+void __hypfs_diag_fs_exit(void);
+
+static inline int hypfs_diag_fs_init(void)
+{
+ if (IS_ENABLED(CONFIG_S390_HYPFS_FS))
+ return __hypfs_diag_fs_init();
+ return 0;
+}
+
+static inline void hypfs_diag_fs_exit(void)
+{
+ if (IS_ENABLED(CONFIG_S390_HYPFS_FS))
+ __hypfs_diag_fs_exit();
+}
+
+#endif /* _S390_HYPFS_DIAG_H_ */
diff --git a/arch/s390/hypfs/hypfs_diag_fs.c b/arch/s390/hypfs/hypfs_diag_fs.c
new file mode 100644
index 000000000000..00a6d370a280
--- /dev/null
+++ b/arch/s390/hypfs/hypfs_diag_fs.c
@@ -0,0 +1,393 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hypervisor filesystem for Linux on s390. Diag 204 and 224
+ * implementation.
+ *
+ * Copyright IBM Corp. 2006, 2008
+ * Author(s): Michael Holzheu <holzheu@de.ibm.com>
+ */
+
+#define KMSG_COMPONENT "hypfs"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <asm/diag.h>
+#include <asm/ebcdic.h>
+#include "hypfs_diag.h"
+#include "hypfs.h"
+
+#define TMP_SIZE 64 /* size of temporary buffers */
+
+static char *diag224_cpu_names; /* diag 224 name table */
+static int diag224_idx2name(int index, char *name);
+
+/*
+ * DIAG 204 member access functions.
+ *
+ * Since we have two different diag 204 data formats for old and new s390
+ * machines, we do not access the structs directly, but use getter functions for
+ * each struct member instead. This should make the code more readable.
+ */
+
+/* Time information block */
+
+static inline int info_blk_hdr__size(enum diag204_format type)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return sizeof(struct diag204_info_blk_hdr);
+ else /* DIAG204_INFO_EXT */
+ return sizeof(struct diag204_x_info_blk_hdr);
+}
+
+static inline __u8 info_blk_hdr__npar(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_info_blk_hdr *)hdr)->npar;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_info_blk_hdr *)hdr)->npar;
+}
+
+static inline __u8 info_blk_hdr__flags(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_info_blk_hdr *)hdr)->flags;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_info_blk_hdr *)hdr)->flags;
+}
+
+/* Partition header */
+
+static inline int part_hdr__size(enum diag204_format type)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return sizeof(struct diag204_part_hdr);
+ else /* DIAG204_INFO_EXT */
+ return sizeof(struct diag204_x_part_hdr);
+}
+
+static inline __u8 part_hdr__rcpus(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_part_hdr *)hdr)->cpus;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_part_hdr *)hdr)->rcpus;
+}
+
+static inline void part_hdr__part_name(enum diag204_format type, void *hdr,
+ char *name)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ memcpy(name, ((struct diag204_part_hdr *)hdr)->part_name,
+ DIAG204_LPAR_NAME_LEN);
+ else /* DIAG204_INFO_EXT */
+ memcpy(name, ((struct diag204_x_part_hdr *)hdr)->part_name,
+ DIAG204_LPAR_NAME_LEN);
+ EBCASC(name, DIAG204_LPAR_NAME_LEN);
+ name[DIAG204_LPAR_NAME_LEN] = 0;
+ strim(name);
+}
+
+/* CPU info block */
+
+static inline int cpu_info__size(enum diag204_format type)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return sizeof(struct diag204_cpu_info);
+ else /* DIAG204_INFO_EXT */
+ return sizeof(struct diag204_x_cpu_info);
+}
+
+static inline __u8 cpu_info__ctidx(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_cpu_info *)hdr)->ctidx;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_cpu_info *)hdr)->ctidx;
+}
+
+static inline __u16 cpu_info__cpu_addr(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_cpu_info *)hdr)->cpu_addr;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_cpu_info *)hdr)->cpu_addr;
+}
+
+static inline __u64 cpu_info__acc_time(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_cpu_info *)hdr)->acc_time;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_cpu_info *)hdr)->acc_time;
+}
+
+static inline __u64 cpu_info__lp_time(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_cpu_info *)hdr)->lp_time;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_cpu_info *)hdr)->lp_time;
+}
+
+static inline __u64 cpu_info__online_time(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return 0; /* online_time not available in simple info */
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_cpu_info *)hdr)->online_time;
+}
+
+/* Physical header */
+
+static inline int phys_hdr__size(enum diag204_format type)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return sizeof(struct diag204_phys_hdr);
+ else /* DIAG204_INFO_EXT */
+ return sizeof(struct diag204_x_phys_hdr);
+}
+
+static inline __u8 phys_hdr__cpus(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_phys_hdr *)hdr)->cpus;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_phys_hdr *)hdr)->cpus;
+}
+
+/* Physical CPU info block */
+
+static inline int phys_cpu__size(enum diag204_format type)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return sizeof(struct diag204_phys_cpu);
+ else /* DIAG204_INFO_EXT */
+ return sizeof(struct diag204_x_phys_cpu);
+}
+
+static inline __u16 phys_cpu__cpu_addr(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_phys_cpu *)hdr)->cpu_addr;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_phys_cpu *)hdr)->cpu_addr;
+}
+
+static inline __u64 phys_cpu__mgm_time(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_phys_cpu *)hdr)->mgm_time;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_phys_cpu *)hdr)->mgm_time;
+}
+
+static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr)
+{
+ if (type == DIAG204_INFO_SIMPLE)
+ return ((struct diag204_phys_cpu *)hdr)->ctidx;
+ else /* DIAG204_INFO_EXT */
+ return ((struct diag204_x_phys_cpu *)hdr)->ctidx;
+}
+
+/*
+ * Functions to create the directory structure
+ * *******************************************
+ */
+
+static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
+{
+ struct dentry *cpu_dir;
+ char buffer[TMP_SIZE];
+ void *rc;
+
+ snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_get_info_type(),
+ cpu_info));
+ cpu_dir = hypfs_mkdir(cpus_dir, buffer);
+ rc = hypfs_create_u64(cpu_dir, "mgmtime",
+ cpu_info__acc_time(diag204_get_info_type(), cpu_info) -
+ cpu_info__lp_time(diag204_get_info_type(), cpu_info));
+ if (IS_ERR(rc))
+ return PTR_ERR(rc);
+ rc = hypfs_create_u64(cpu_dir, "cputime",
+ cpu_info__lp_time(diag204_get_info_type(), cpu_info));
+ if (IS_ERR(rc))
+ return PTR_ERR(rc);
+ if (diag204_get_info_type() == DIAG204_INFO_EXT) {
+ rc = hypfs_create_u64(cpu_dir, "onlinetime",
+ cpu_info__online_time(diag204_get_info_type(),
+ cpu_info));
+ if (IS_ERR(rc))
+ return PTR_ERR(rc);
+ }
+ diag224_idx2name(cpu_info__ctidx(diag204_get_info_type(), cpu_info), buffer);
+ rc = hypfs_create_str(cpu_dir, "type", buffer);
+ return PTR_ERR_OR_ZERO(rc);
+}
+
+static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
+{
+ struct dentry *cpus_dir;
+ struct dentry *lpar_dir;
+ char lpar_name[DIAG204_LPAR_NAME_LEN + 1];
+ void *cpu_info;
+ int i;
+
+ part_hdr__part_name(diag204_get_info_type(), part_hdr, lpar_name);
+ lpar_name[DIAG204_LPAR_NAME_LEN] = 0;
+ lpar_dir = hypfs_mkdir(systems_dir, lpar_name);
+ if (IS_ERR(lpar_dir))
+ return lpar_dir;
+ cpus_dir = hypfs_mkdir(lpar_dir, "cpus");
+ if (IS_ERR(cpus_dir))
+ return cpus_dir;
+ cpu_info = part_hdr + part_hdr__size(diag204_get_info_type());
+ for (i = 0; i < part_hdr__rcpus(diag204_get_info_type(), part_hdr); i++) {
+ int rc;
+
+ rc = hypfs_create_cpu_files(cpus_dir, cpu_info);
+ if (rc)
+ return ERR_PTR(rc);
+ cpu_info += cpu_info__size(diag204_get_info_type());
+ }
+ return cpu_info;
+}
+
+static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info)
+{
+ struct dentry *cpu_dir;
+ char buffer[TMP_SIZE];
+ void *rc;
+
+ snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_get_info_type(),
+ cpu_info));
+ cpu_dir = hypfs_mkdir(cpus_dir, buffer);
+ if (IS_ERR(cpu_dir))
+ return PTR_ERR(cpu_dir);
+ rc = hypfs_create_u64(cpu_dir, "mgmtime",
+ phys_cpu__mgm_time(diag204_get_info_type(), cpu_info));
+ if (IS_ERR(rc))
+ return PTR_ERR(rc);
+ diag224_idx2name(phys_cpu__ctidx(diag204_get_info_type(), cpu_info), buffer);
+ rc = hypfs_create_str(cpu_dir, "type", buffer);
+ return PTR_ERR_OR_ZERO(rc);
+}
+
+static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
+{
+ int i;
+ void *cpu_info;
+ struct dentry *cpus_dir;
+
+ cpus_dir = hypfs_mkdir(parent_dir, "cpus");
+ if (IS_ERR(cpus_dir))
+ return cpus_dir;
+ cpu_info = phys_hdr + phys_hdr__size(diag204_get_info_type());
+ for (i = 0; i < phys_hdr__cpus(diag204_get_info_type(), phys_hdr); i++) {
+ int rc;
+
+ rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info);
+ if (rc)
+ return ERR_PTR(rc);
+ cpu_info += phys_cpu__size(diag204_get_info_type());
+ }
+ return cpu_info;
+}
+
+int hypfs_diag_create_files(struct dentry *root)
+{
+ struct dentry *systems_dir, *hyp_dir;
+ void *time_hdr, *part_hdr;
+ void *buffer, *ptr;
+ int i, rc, pages;
+
+ buffer = diag204_get_buffer(diag204_get_info_type(), &pages);
+ if (IS_ERR(buffer))
+ return PTR_ERR(buffer);
+ rc = diag204_store(buffer, pages);
+ if (rc)
+ return rc;
+
+ systems_dir = hypfs_mkdir(root, "systems");
+ if (IS_ERR(systems_dir)) {
+ rc = PTR_ERR(systems_dir);
+ goto err_out;
+ }
+ time_hdr = (struct x_info_blk_hdr *)buffer;
+ part_hdr = time_hdr + info_blk_hdr__size(diag204_get_info_type());
+ for (i = 0; i < info_blk_hdr__npar(diag204_get_info_type(), time_hdr); i++) {
+ part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr);
+ if (IS_ERR(part_hdr)) {
+ rc = PTR_ERR(part_hdr);
+ goto err_out;
+ }
+ }
+ if (info_blk_hdr__flags(diag204_get_info_type(), time_hdr) &
+ DIAG204_LPAR_PHYS_FLG) {
+ ptr = hypfs_create_phys_files(root, part_hdr);
+ if (IS_ERR(ptr)) {
+ rc = PTR_ERR(ptr);
+ goto err_out;
+ }
+ }
+ hyp_dir = hypfs_mkdir(root, "hyp");
+ if (IS_ERR(hyp_dir)) {
+ rc = PTR_ERR(hyp_dir);
+ goto err_out;
+ }
+ ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor");
+ if (IS_ERR(ptr)) {
+ rc = PTR_ERR(ptr);
+ goto err_out;
+ }
+ rc = 0;
+
+err_out:
+ return rc;
+}
+
+/* Diagnose 224 functions */
+
+static int diag224_idx2name(int index, char *name)
+{
+ memcpy(name, diag224_cpu_names + ((index + 1) * DIAG204_CPU_NAME_LEN),
+ DIAG204_CPU_NAME_LEN);
+ name[DIAG204_CPU_NAME_LEN] = 0;
+ strim(name);
+ return 0;
+}
+
+static int diag224_get_name_table(void)
+{
+ /* memory must be below 2GB */
+ diag224_cpu_names = (char *)__get_free_page(GFP_KERNEL | GFP_DMA);
+ if (!diag224_cpu_names)
+ return -ENOMEM;
+ if (diag224(diag224_cpu_names)) {
+ free_page((unsigned long)diag224_cpu_names);
+ return -EOPNOTSUPP;
+ }
+ EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16);
+ return 0;
+}
+
+static void diag224_delete_name_table(void)
+{
+ free_page((unsigned long)diag224_cpu_names);
+}
+
+int __init __hypfs_diag_fs_init(void)
+{
+ if (MACHINE_IS_LPAR)
+ return diag224_get_name_table();
+ return 0;
+}
+
+void __hypfs_diag_fs_exit(void)
+{
+ diag224_delete_name_table();
+}
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index a3d881ca0a98..3db40ad853e0 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -14,47 +14,15 @@
#include <asm/diag.h>
#include <asm/ebcdic.h>
#include <asm/timex.h>
+#include "hypfs_vm.h"
#include "hypfs.h"
-#define NAME_LEN 8
#define DBFS_D2FC_HDR_VERSION 0
static char local_guest[] = " ";
static char all_guests[] = "* ";
static char *all_groups = all_guests;
-static char *guest_query;
-
-struct diag2fc_data {
- __u32 version;
- __u32 flags;
- __u64 used_cpu;
- __u64 el_time;
- __u64 mem_min_kb;
- __u64 mem_max_kb;
- __u64 mem_share_kb;
- __u64 mem_used_kb;
- __u32 pcpus;
- __u32 lcpus;
- __u32 vcpus;
- __u32 ocpus;
- __u32 cpu_max;
- __u32 cpu_shares;
- __u32 cpu_use_samp;
- __u32 cpu_delay_samp;
- __u32 page_wait_samp;
- __u32 idle_samp;
- __u32 other_samp;
- __u32 total_samp;
- char guest_name[NAME_LEN];
-};
-
-struct diag2fc_parm_list {
- char userid[NAME_LEN];
- char aci_grp[NAME_LEN];
- __u64 addr;
- __u32 size;
- __u32 fmt;
-};
+char *diag2fc_guest_query;
static int diag2fc(int size, char* query, void *addr)
{
@@ -62,10 +30,10 @@ static int diag2fc(int size, char* query, void *addr)
unsigned long rc;
struct diag2fc_parm_list parm_list;
- memcpy(parm_list.userid, query, NAME_LEN);
- ASCEBC(parm_list.userid, NAME_LEN);
- memcpy(parm_list.aci_grp, all_groups, NAME_LEN);
- ASCEBC(parm_list.aci_grp, NAME_LEN);
+ memcpy(parm_list.userid, query, DIAG2FC_NAME_LEN);
+ ASCEBC(parm_list.userid, DIAG2FC_NAME_LEN);
+ memcpy(parm_list.aci_grp, all_groups, DIAG2FC_NAME_LEN);
+ ASCEBC(parm_list.aci_grp, DIAG2FC_NAME_LEN);
parm_list.addr = (unsigned long)addr;
parm_list.size = size;
parm_list.fmt = 0x02;
@@ -87,7 +55,7 @@ static int diag2fc(int size, char* query, void *addr)
/*
* Allocate buffer for "query" and store diag 2fc at "offset"
*/
-static void *diag2fc_store(char *query, unsigned int *count, int offset)
+void *diag2fc_store(char *query, unsigned int *count, int offset)
{
void *data;
int size;
@@ -108,132 +76,11 @@ static void *diag2fc_store(char *query, unsigned int *count, int offset)
return data;
}
-static void diag2fc_free(const void *data)
+void diag2fc_free(const void *data)
{
vfree(data);
}
-#define ATTRIBUTE(dir, name, member) \
-do { \
- void *rc; \
- rc = hypfs_create_u64(dir, name, member); \
- if (IS_ERR(rc)) \
- return PTR_ERR(rc); \
-} while(0)
-
-static int hypfs_vm_create_guest(struct dentry *systems_dir,
- struct diag2fc_data *data)
-{
- char guest_name[NAME_LEN + 1] = {};
- struct dentry *guest_dir, *cpus_dir, *samples_dir, *mem_dir;
- int dedicated_flag, capped_value;
-
- capped_value = (data->flags & 0x00000006) >> 1;
- dedicated_flag = (data->flags & 0x00000008) >> 3;
-
- /* guest dir */
- memcpy(guest_name, data->guest_name, NAME_LEN);
- EBCASC(guest_name, NAME_LEN);
- strim(guest_name);
- guest_dir = hypfs_mkdir(systems_dir, guest_name);
- if (IS_ERR(guest_dir))
- return PTR_ERR(guest_dir);
- ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time);
-
- /* logical cpu information */
- cpus_dir = hypfs_mkdir(guest_dir, "cpus");
- if (IS_ERR(cpus_dir))
- return PTR_ERR(cpus_dir);
- ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu);
- ATTRIBUTE(cpus_dir, "capped", capped_value);
- ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag);
- ATTRIBUTE(cpus_dir, "count", data->vcpus);
- /*
- * Note: The "weight_min" attribute got the wrong name.
- * The value represents the number of non-stopped (operating)
- * CPUS.
- */
- ATTRIBUTE(cpus_dir, "weight_min", data->ocpus);
- ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max);
- ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares);
-
- /* memory information */
- mem_dir = hypfs_mkdir(guest_dir, "mem");
- if (IS_ERR(mem_dir))
- return PTR_ERR(mem_dir);
- ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb);
- ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb);
- ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb);
- ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb);
-
- /* samples */
- samples_dir = hypfs_mkdir(guest_dir, "samples");
- if (IS_ERR(samples_dir))
- return PTR_ERR(samples_dir);
- ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp);
- ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp);
- ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp);
- ATTRIBUTE(samples_dir, "idle", data->idle_samp);
- ATTRIBUTE(samples_dir, "other", data->other_samp);
- ATTRIBUTE(samples_dir, "total", data->total_samp);
- return 0;
-}
-
-int hypfs_vm_create_files(struct dentry *root)
-{
- struct dentry *dir, *file;
- struct diag2fc_data *data;
- unsigned int count = 0;
- int rc, i;
-
- data = diag2fc_store(guest_query, &count, 0);
- if (IS_ERR(data))
- return PTR_ERR(data);
-
- /* Hypervisor Info */
- dir = hypfs_mkdir(root, "hyp");
- if (IS_ERR(dir)) {
- rc = PTR_ERR(dir);
- goto failed;
- }
- file = hypfs_create_str(dir, "type", "z/VM Hypervisor");
- if (IS_ERR(file)) {
- rc = PTR_ERR(file);
- goto failed;
- }
-
- /* physical cpus */
- dir = hypfs_mkdir(root, "cpus");
- if (IS_ERR(dir)) {
- rc = PTR_ERR(dir);
- goto failed;
- }
- file = hypfs_create_u64(dir, "count", data->lcpus);
- if (IS_ERR(file)) {
- rc = PTR_ERR(file);
- goto failed;
- }
-
- /* guests */
- dir = hypfs_mkdir(root, "systems");
- if (IS_ERR(dir)) {
- rc = PTR_ERR(dir);
- goto failed;
- }
-
- for (i = 0; i < count; i++) {
- rc = hypfs_vm_create_guest(dir, &(data[i]));
- if (rc)
- goto failed;
- }
- diag2fc_free(data);
- return 0;
-
-failed:
- diag2fc_free(data);
- return rc;
-}
-
struct dbfs_d2fc_hdr {
u64 len; /* Length of d2fc buffer without header */
u16 version; /* Version of header */
@@ -252,7 +99,7 @@ static int dbfs_diag2fc_create(void **data, void **data_free_ptr, size_t *size)
struct dbfs_d2fc *d2fc;
unsigned int count;
- d2fc = diag2fc_store(guest_query, &count, sizeof(d2fc->hdr));
+ d2fc = diag2fc_store(diag2fc_guest_query, &count, sizeof(d2fc->hdr));
if (IS_ERR(d2fc))
return PTR_ERR(d2fc);
store_tod_clock_ext(&d2fc->hdr.tod_ext);
@@ -277,9 +124,9 @@ int hypfs_vm_init(void)
if (!MACHINE_IS_VM)
return 0;
if (diag2fc(0, all_guests, NULL) > 0)
- guest_query = all_guests;
+ diag2fc_guest_query = all_guests;
else if (diag2fc(0, local_guest, NULL) > 0)
- guest_query = local_guest;
+ diag2fc_guest_query = local_guest;
else
return -EACCES;
hypfs_dbfs_create_file(&dbfs_file_2fc);
diff --git a/arch/s390/hypfs/hypfs_vm.h b/arch/s390/hypfs/hypfs_vm.h
new file mode 100644
index 000000000000..fe2e5851addd
--- /dev/null
+++ b/arch/s390/hypfs/hypfs_vm.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Hypervisor filesystem for Linux on s390. z/VM implementation.
+ *
+ * Copyright IBM Corp. 2006
+ * Author(s): Michael Holzheu <holzheu@de.ibm.com>
+ */
+
+#ifndef _S390_HYPFS_VM_H_
+#define _S390_HYPFS_VM_H_
+
+#define DIAG2FC_NAME_LEN 8
+
+struct diag2fc_data {
+ __u32 version;
+ __u32 flags;
+ __u64 used_cpu;
+ __u64 el_time;
+ __u64 mem_min_kb;
+ __u64 mem_max_kb;
+ __u64 mem_share_kb;
+ __u64 mem_used_kb;
+ __u32 pcpus;
+ __u32 lcpus;
+ __u32 vcpus;
+ __u32 ocpus;
+ __u32 cpu_max;
+ __u32 cpu_shares;
+ __u32 cpu_use_samp;
+ __u32 cpu_delay_samp;
+ __u32 page_wait_samp;
+ __u32 idle_samp;
+ __u32 other_samp;
+ __u32 total_samp;
+ char guest_name[DIAG2FC_NAME_LEN];
+};
+
+struct diag2fc_parm_list {
+ char userid[DIAG2FC_NAME_LEN];
+ char aci_grp[DIAG2FC_NAME_LEN];
+ __u64 addr;
+ __u32 size;
+ __u32 fmt;
+};
+
+void *diag2fc_store(char *query, unsigned int *count, int offset);
+void diag2fc_free(const void *data);
+extern char *diag2fc_guest_query;
+
+#endif /* _S390_HYPFS_VM_H_ */
diff --git a/arch/s390/hypfs/hypfs_vm_fs.c b/arch/s390/hypfs/hypfs_vm_fs.c
new file mode 100644
index 000000000000..6011289afa8c
--- /dev/null
+++ b/arch/s390/hypfs/hypfs_vm_fs.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hypervisor filesystem for Linux on s390. z/VM implementation.
+ *
+ * Copyright IBM Corp. 2006
+ * Author(s): Michael Holzheu <holzheu@de.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+#include <asm/extable.h>
+#include <asm/diag.h>
+#include <asm/ebcdic.h>
+#include <asm/timex.h>
+#include "hypfs_vm.h"
+#include "hypfs.h"
+
+#define ATTRIBUTE(dir, name, member) \
+do { \
+ void *rc; \
+ rc = hypfs_create_u64(dir, name, member); \
+ if (IS_ERR(rc)) \
+ return PTR_ERR(rc); \
+} while (0)
+
+static int hypfs_vm_create_guest(struct dentry *systems_dir,
+ struct diag2fc_data *data)
+{
+ char guest_name[DIAG2FC_NAME_LEN + 1] = {};
+ struct dentry *guest_dir, *cpus_dir, *samples_dir, *mem_dir;
+ int dedicated_flag, capped_value;
+
+ capped_value = (data->flags & 0x00000006) >> 1;
+ dedicated_flag = (data->flags & 0x00000008) >> 3;
+
+ /* guest dir */
+ memcpy(guest_name, data->guest_name, DIAG2FC_NAME_LEN);
+ EBCASC(guest_name, DIAG2FC_NAME_LEN);
+ strim(guest_name);
+ guest_dir = hypfs_mkdir(systems_dir, guest_name);
+ if (IS_ERR(guest_dir))
+ return PTR_ERR(guest_dir);
+ ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time);
+
+ /* logical cpu information */
+ cpus_dir = hypfs_mkdir(guest_dir, "cpus");
+ if (IS_ERR(cpus_dir))
+ return PTR_ERR(cpus_dir);
+ ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu);
+ ATTRIBUTE(cpus_dir, "capped", capped_value);
+ ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag);
+ ATTRIBUTE(cpus_dir, "count", data->vcpus);
+ /*
+ * Note: The "weight_min" attribute got the wrong name.
+ * The value represents the number of non-stopped (operating)
+ * CPUS.
+ */
+ ATTRIBUTE(cpus_dir, "weight_min", data->ocpus);
+ ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max);
+ ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares);
+
+ /* memory information */
+ mem_dir = hypfs_mkdir(guest_dir, "mem");
+ if (IS_ERR(mem_dir))
+ return PTR_ERR(mem_dir);
+ ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb);
+ ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb);
+ ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb);
+ ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb);
+
+ /* samples */
+ samples_dir = hypfs_mkdir(guest_dir, "samples");
+ if (IS_ERR(samples_dir))
+ return PTR_ERR(samples_dir);
+ ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp);
+ ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp);
+ ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp);
+ ATTRIBUTE(samples_dir, "idle", data->idle_samp);
+ ATTRIBUTE(samples_dir, "other", data->other_samp);
+ ATTRIBUTE(samples_dir, "total", data->total_samp);
+ return 0;
+}
+
+int hypfs_vm_create_files(struct dentry *root)
+{
+ struct dentry *dir, *file;
+ struct diag2fc_data *data;
+ unsigned int count = 0;
+ int rc, i;
+
+ data = diag2fc_store(diag2fc_guest_query, &count, 0);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ /* Hypervisor Info */
+ dir = hypfs_mkdir(root, "hyp");
+ if (IS_ERR(dir)) {
+ rc = PTR_ERR(dir);
+ goto failed;
+ }
+ file = hypfs_create_str(dir, "type", "z/VM Hypervisor");
+ if (IS_ERR(file)) {
+ rc = PTR_ERR(file);
+ goto failed;
+ }
+
+ /* physical cpus */
+ dir = hypfs_mkdir(root, "cpus");
+ if (IS_ERR(dir)) {
+ rc = PTR_ERR(dir);
+ goto failed;
+ }
+ file = hypfs_create_u64(dir, "count", data->lcpus);
+ if (IS_ERR(file)) {
+ rc = PTR_ERR(file);
+ goto failed;
+ }
+
+ /* guests */
+ dir = hypfs_mkdir(root, "systems");
+ if (IS_ERR(dir)) {
+ rc = PTR_ERR(dir);
+ goto failed;
+ }
+
+ for (i = 0; i < count; i++) {
+ rc = hypfs_vm_create_guest(dir, &data[i]);
+ if (rc)
+ goto failed;
+ }
+ diag2fc_free(data);
+ return 0;
+
+failed:
+ diag2fc_free(data);
+ return rc;
+}
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index ee919bfc8186..ada83149932f 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -53,7 +53,7 @@ static void hypfs_update_update(struct super_block *sb)
struct inode *inode = d_inode(sb_info->update_file);
sb_info->last_update = ktime_get_seconds();
- inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
}
/* directory tree removal functions */
@@ -101,7 +101,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode)
ret->i_mode = mode;
ret->i_uid = hypfs_info->uid;
ret->i_gid = hypfs_info->gid;
- ret->i_atime = ret->i_mtime = ret->i_ctime = current_time(ret);
+ ret->i_atime = ret->i_mtime = inode_set_ctime_current(ret);
if (S_ISDIR(mode))
set_nlink(ret, 2);
}
@@ -460,45 +460,18 @@ static const struct super_operations hypfs_s_ops = {
.show_options = hypfs_show_options,
};
-static int __init hypfs_init(void)
+int __init __hypfs_fs_init(void)
{
int rc;
- hypfs_dbfs_init();
-
- if (hypfs_diag_init()) {
- rc = -ENODATA;
- goto fail_dbfs_exit;
- }
- if (hypfs_vm_init()) {
- rc = -ENODATA;
- goto fail_hypfs_diag_exit;
- }
- hypfs_sprp_init();
- if (hypfs_diag0c_init()) {
- rc = -ENODATA;
- goto fail_hypfs_sprp_exit;
- }
rc = sysfs_create_mount_point(hypervisor_kobj, "s390");
if (rc)
- goto fail_hypfs_diag0c_exit;
+ return rc;
rc = register_filesystem(&hypfs_type);
if (rc)
- goto fail_filesystem;
+ goto fail;
return 0;
-
-fail_filesystem:
+fail:
sysfs_remove_mount_point(hypervisor_kobj, "s390");
-fail_hypfs_diag0c_exit:
- hypfs_diag0c_exit();
-fail_hypfs_sprp_exit:
- hypfs_sprp_exit();
- hypfs_vm_exit();
-fail_hypfs_diag_exit:
- hypfs_diag_exit();
- pr_err("Initialization of hypfs failed with rc=%i\n", rc);
-fail_dbfs_exit:
- hypfs_dbfs_exit();
return rc;
}
-device_initcall(hypfs_init)
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 1a18d7b82f86..4b904110d27c 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -5,6 +5,5 @@ generated-y += syscall_table.h
generated-y += unistd_nr.h
generic-y += asm-offsets.h
-generic-y += export.h
generic-y += kvm_types.h
generic-y += mcs_spinlock.h
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index ac665b9670c5..ccd4e148b5ed 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -222,7 +222,7 @@ static inline debug_entry_t *debug_text_event(debug_info_t *id, int level,
/*
* IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are
- * stored in the s390dbf. See Documentation/s390/s390dbf.rst for more details!
+ * stored in the s390dbf. See Documentation/arch/s390/s390dbf.rst for more details!
*/
extern debug_entry_t *
__debug_sprintf_event(debug_info_t *id, int level, char *string, ...)
@@ -350,7 +350,7 @@ static inline debug_entry_t *debug_text_exception(debug_info_t *id, int level,
/*
* IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are
- * stored in the s390dbf. See Documentation/s390/s390dbf.rst for more details!
+ * stored in the s390dbf. See Documentation/arch/s390/s390dbf.rst for more details!
*/
extern debug_entry_t *
__debug_sprintf_exception(debug_info_t *id, int level, char *string, ...)
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 902e0330dd91..bed804137537 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -36,6 +36,7 @@ enum diag_stat_enum {
DIAG_STAT_X304,
DIAG_STAT_X308,
DIAG_STAT_X318,
+ DIAG_STAT_X320,
DIAG_STAT_X500,
NR_DIAG_STAT
};
@@ -108,6 +109,8 @@ enum diag204_sc {
DIAG204_SUBC_STIB7 = 7
};
+#define DIAG204_SUBCODE_MASK 0xffff
+
/* The two available diag 204 data formats */
enum diag204_format {
DIAG204_INFO_SIMPLE = 0,
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index e5c5cb1207e2..5a82b08f03cd 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -54,6 +54,23 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
return NULL;
}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+struct fgraph_ret_regs {
+ unsigned long gpr2;
+ unsigned long fp;
+};
+
+static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
+{
+ return ret_regs->gpr2;
+}
+
+static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
+{
+ return ret_regs->fp;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
static __always_inline unsigned long
ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs)
{
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index e3882b012bfa..4453ad7c11ac 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -22,11 +22,18 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
#define IO_SPACE_LIMIT 0
-void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot);
-void __iomem *ioremap(phys_addr_t addr, size_t size);
-void __iomem *ioremap_wc(phys_addr_t addr, size_t size);
-void __iomem *ioremap_wt(phys_addr_t addr, size_t size);
-void iounmap(volatile void __iomem *addr);
+/*
+ * I/O memory mapping functions.
+ */
+#define ioremap_prot ioremap_prot
+#define iounmap iounmap
+
+#define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL)
+
+#define ioremap_wc(addr, size) \
+ ioremap_prot((addr), (size), pgprot_val(pgprot_writecombine(PAGE_KERNEL)))
+#define ioremap_wt(addr, size) \
+ ioremap_prot((addr), (size), pgprot_val(pgprot_writethrough(PAGE_KERNEL)))
static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
{
@@ -51,10 +58,6 @@ static inline void ioport_unmap(void __iomem *p)
#define pci_iomap_wc pci_iomap_wc
#define pci_iomap_wc_range pci_iomap_wc_range
-#define ioremap ioremap
-#define ioremap_wt ioremap_wt
-#define ioremap_wc ioremap_wc
-
#define memcpy_fromio(dst, src, count) zpci_memcpy_fromio(dst, src, count)
#define memcpy_toio(dst, src, count) zpci_memcpy_toio(dst, src, count)
#define memset_io(dst, val, count) zpci_memset_io(dst, val, count)
diff --git a/arch/s390/include/asm/kfence.h b/arch/s390/include/asm/kfence.h
index d55ba878378b..e47fd8cbe701 100644
--- a/arch/s390/include/asm/kfence.h
+++ b/arch/s390/include/asm/kfence.h
@@ -35,7 +35,7 @@ static __always_inline void kfence_split_mapping(void)
static inline bool kfence_protect_page(unsigned long addr, bool protect)
{
- __kernel_map_pages(virt_to_page(addr), 1, !protect);
+ __kernel_map_pages(virt_to_page((void *)addr), 1, !protect);
return true;
}
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 2bbc3d54959d..91bfecb91321 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -1028,6 +1028,9 @@ static inline int sie64a(struct kvm_s390_sie_block *sie_block, u64 *rsa)
extern char sie_exit;
+bool kvm_s390_pv_is_protected(struct kvm *kvm);
+bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu);
+
extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc);
extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc);
diff --git a/arch/s390/include/asm/maccess.h b/arch/s390/include/asm/maccess.h
index cfec3141fdba..50225940d971 100644
--- a/arch/s390/include/asm/maccess.h
+++ b/arch/s390/include/asm/maccess.h
@@ -4,6 +4,9 @@
#include <linux/types.h>
+#define MEMCPY_REAL_SIZE PAGE_SIZE
+#define MEMCPY_REAL_MASK PAGE_MASK
+
struct iov_iter;
extern unsigned long __memcpy_real_area;
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index a9c138fcd2ad..cfec0743314e 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -191,8 +191,16 @@ int arch_make_page_accessible(struct page *page);
#define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys))
#define page_to_phys(page) pfn_to_phys(page_to_pfn(page))
-#define pfn_to_virt(pfn) __va(pfn_to_phys(pfn))
-#define virt_to_pfn(kaddr) (phys_to_pfn(__pa(kaddr)))
+static inline void *pfn_to_virt(unsigned long pfn)
+{
+ return __va(pfn_to_phys(pfn));
+}
+
+static inline unsigned long virt_to_pfn(const void *kaddr)
+{
+ return phys_to_pfn(__pa(kaddr));
+}
+
#define pfn_to_kaddr(pfn) pfn_to_virt(pfn)
#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr))
diff --git a/arch/s390/include/asm/pfault.h b/arch/s390/include/asm/pfault.h
new file mode 100644
index 000000000000..a1bee4a1e470
--- /dev/null
+++ b/arch/s390/include/asm/pfault.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 1999, 2023
+ */
+#ifndef _ASM_S390_PFAULT_H
+#define _ASM_S390_PFAULT_H
+
+#include <linux/errno.h>
+
+int __pfault_init(void);
+void __pfault_fini(void);
+
+static inline int pfault_init(void)
+{
+ if (IS_ENABLED(CONFIG_PFAULT))
+ return __pfault_init();
+ return -EOPNOTSUPP;
+}
+
+static inline void pfault_fini(void)
+{
+ if (IS_ENABLED(CONFIG_PFAULT))
+ __pfault_fini();
+}
+
+#endif /* _ASM_S390_PFAULT_H */
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 17eb618f1348..376b4b23bdaa 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -86,7 +86,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
if (!table)
return NULL;
crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
- if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+ if (!pagetable_pmd_ctor(virt_to_ptdesc(table))) {
crst_table_free(mm, table);
return NULL;
}
@@ -97,7 +97,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
if (mm_pmd_folded(mm))
return;
- pgtable_pmd_page_dtor(virt_to_page(pmd));
+ pagetable_pmd_dtor(virt_to_ptdesc(pmd));
crst_table_free(mm, (unsigned long *) pmd);
}
@@ -143,6 +143,10 @@ static inline void pmd_populate(struct mm_struct *mm,
#define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
#define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
+/* arch use pte_free_defer() implementation in arch/s390/mm/pgalloc.c */
+#define pte_free_defer pte_free_defer
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
+
void vmem_map_init(void);
void *vmem_crst_alloc(unsigned long val);
pte_t *vmem_pte_alloc(void);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 83c5da39237d..fb3ee7758b76 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -47,6 +47,7 @@ static inline void update_page_count(int level, long count)
* tables contain all the necessary information.
*/
#define update_mmu_cache(vma, address, ptep) do { } while (0)
+#define update_mmu_cache_range(vmf, vma, addr, ptep, nr) do { } while (0)
#define update_mmu_cache_pmd(vma, address, ptep) do { } while (0)
/*
@@ -89,8 +90,6 @@ extern unsigned long __bootdata_preserved(VMALLOC_END);
extern struct page *__bootdata_preserved(vmemmap);
extern unsigned long __bootdata_preserved(vmemmap_size);
-#define VMEM_MAX_PHYS ((unsigned long) vmemmap)
-
extern unsigned long __bootdata_preserved(MODULES_VADDR);
extern unsigned long __bootdata_preserved(MODULES_END);
#define MODULES_VADDR MODULES_VADDR
@@ -1316,20 +1315,34 @@ pgprot_t pgprot_writecombine(pgprot_t prot);
pgprot_t pgprot_writethrough(pgprot_t prot);
/*
- * Certain architectures need to do special things when PTEs
- * within a page table are directly modified. Thus, the following
- * hook is made available.
+ * Set multiple PTEs to consecutive pages with a single call. All PTEs
+ * are within the same folio, PMD and VMA.
*/
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t entry)
+static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t entry, unsigned int nr)
{
if (pte_present(entry))
entry = clear_pte_bit(entry, __pgprot(_PAGE_UNUSED));
- if (mm_has_pgste(mm))
- ptep_set_pte_at(mm, addr, ptep, entry);
- else
- set_pte(ptep, entry);
+ if (mm_has_pgste(mm)) {
+ for (;;) {
+ ptep_set_pte_at(mm, addr, ptep, entry);
+ if (--nr == 0)
+ break;
+ ptep++;
+ entry = __pte(pte_val(entry) + PAGE_SIZE);
+ addr += PAGE_SIZE;
+ }
+ } else {
+ for (;;) {
+ set_pte(ptep, entry);
+ if (--nr == 0)
+ break;
+ ptep++;
+ entry = __pte(pte_val(entry) + PAGE_SIZE);
+ }
+ }
}
+#define set_ptes set_ptes
/*
* Conversion functions: convert a page and protection to a page entry,
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index dac7da88f61f..5742d23bba13 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -86,6 +86,7 @@ struct sclp_info {
unsigned char has_kss : 1;
unsigned char has_gisaf : 1;
unsigned char has_diag318 : 1;
+ unsigned char has_diag320 : 1;
unsigned char has_sipl : 1;
unsigned char has_sipl_eckd : 1;
unsigned char has_dirq : 1;
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index f191255c60db..b30fe91166e3 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -74,6 +74,7 @@ extern unsigned int zlib_dfltcc_support;
extern int noexec_disabled;
extern unsigned long ident_map_size;
+extern unsigned long max_mappable;
/* The Write Back bit position in the physaddr is given by the SLPC PCI */
extern unsigned long mio_wb_bit_mask;
@@ -117,14 +118,6 @@ extern unsigned int console_irq;
#define SET_CONSOLE_VT220 do { console_mode = 4; } while (0)
#define SET_CONSOLE_HVC do { console_mode = 5; } while (0)
-#ifdef CONFIG_PFAULT
-extern int pfault_init(void);
-extern void pfault_fini(void);
-#else /* CONFIG_PFAULT */
-#define pfault_init() ({-1;})
-#define pfault_fini() do { } while (0)
-#endif /* CONFIG_PFAULT */
-
#ifdef CONFIG_VMCP
void vmcp_cma_reserve(void);
#else
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b91f4a9b044c..383b1f91442c 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -89,12 +89,12 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
{
if (mm_pmd_folded(tlb->mm))
return;
- pgtable_pmd_page_dtor(virt_to_page(pmd));
+ pagetable_pmd_dtor(virt_to_ptdesc(pmd));
__tlb_adjust_range(tlb, address, PAGE_SIZE);
tlb->mm->context.flush_mm = 1;
tlb->freed_tables = 1;
tlb->cleared_puds = 1;
- tlb_remove_table(tlb, pmd);
+ tlb_remove_ptdesc(tlb, pmd);
}
/*
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index d6bb2f4f78d1..d2cd42bb2c26 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -463,6 +463,7 @@ static inline int is_prot_virt_host(void)
return prot_virt_host;
}
+int uv_pin_shared(unsigned long paddr);
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
int uv_destroy_owned_page(unsigned long paddr);
@@ -475,6 +476,11 @@ void setup_uv(void);
#define is_prot_virt_host() 0
static inline void setup_uv(void) {}
+static inline int uv_pin_shared(unsigned long paddr)
+{
+ return 0;
+}
+
static inline int uv_destroy_owned_page(unsigned long paddr)
{
return 0;
diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h
index 5faf0a1d2c16..5ad76471e73f 100644
--- a/arch/s390/include/uapi/asm/pkey.h
+++ b/arch/s390/include/uapi/asm/pkey.h
@@ -26,7 +26,7 @@
#define MAXCLRKEYSIZE 32 /* a clear key value may be up to 32 bytes */
#define MAXAESCIPHERKEYSIZE 136 /* our aes cipher keys have always 136 bytes */
#define MINEP11AESKEYBLOBSIZE 256 /* min EP11 AES key blob size */
-#define MAXEP11AESKEYBLOBSIZE 320 /* max EP11 AES key blob size */
+#define MAXEP11AESKEYBLOBSIZE 336 /* max EP11 AES key blob size */
/* Minimum size of a key blob */
#define MINKEYBLOBSIZE SECKEYBLOBSIZE
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index f0fe3bcc78a8..bb0826024bb9 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -8,6 +8,8 @@
#ifndef _UAPI_S390_PTRACE_H
#define _UAPI_S390_PTRACE_H
+#include <linux/const.h>
+
/*
* Offsets in the user_regs_struct. They are used for the ptrace
* system call and in entry.S
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 6b2a051e1f8a..0df2b88cc0da 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -37,9 +37,9 @@ CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls
obj-y := head64.o traps.o time.o process.o earlypgm.o early.o setup.o idle.o vtime.o
obj-y += processor.o syscall.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o cpufeature.o
-obj-y += sysinfo.o lgr.o os_info.o machine_kexec.o
+obj-y += sysinfo.o lgr.o os_info.o
obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
-obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
+obj-y += entry.o reipl.o kdebugfs.o alternative.o
obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o
@@ -63,12 +63,13 @@ obj-$(CONFIG_RETHOOK) += rethook.o
obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o
obj-$(CONFIG_FUNCTION_TRACER) += mcount.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o
obj-$(CONFIG_UPROBES) += uprobes.o
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o
obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o
-
+obj-$(CONFIG_CERT_STORE) += cert_store.o
obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_arch.o
obj-$(CONFIG_PERF_EVENTS) += perf_event.o
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 81cf72088041..fa5f6885c74a 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -12,6 +12,7 @@
#include <linux/sched.h>
#include <linux/purgatory.h>
#include <linux/pgtable.h>
+#include <linux/ftrace.h>
#include <asm/idle.h>
#include <asm/gmap.h>
#include <asm/stacktrace.h>
@@ -177,5 +178,13 @@ int main(void)
DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size));
DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line));
DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size));
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ /* function graph return value tracing */
+ OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2);
+ OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp);
+ DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs));
+#endif
+ OFFSET(__FTRACE_REGS_PT_REGS, ftrace_regs, regs);
+ DEFINE(__FTRACE_REGS_SIZE, sizeof(struct ftrace_regs));
return 0;
}
diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c
new file mode 100644
index 000000000000..3986a044eb36
--- /dev/null
+++ b/arch/s390/kernel/cert_store.c
@@ -0,0 +1,811 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DIAG 0x320 support and certificate store handling
+ *
+ * Copyright IBM Corp. 2023
+ * Author(s): Anastasia Eskova <anastasia.eskova@ibm.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/key-type.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <crypto/sha2.h>
+#include <keys/user-type.h>
+#include <asm/debug.h>
+#include <asm/diag.h>
+#include <asm/ebcdic.h>
+#include <asm/sclp.h>
+
+#define DIAG_MAX_RETRIES 10
+
+#define VCE_FLAGS_VALID_MASK 0x80
+
+#define ISM_LEN_DWORDS 4
+#define VCSSB_LEN_BYTES 128
+#define VCSSB_LEN_NO_CERTS 4
+#define VCB_LEN_NO_CERTS 64
+#define VC_NAME_LEN_BYTES 64
+
+#define CERT_STORE_KEY_TYPE_NAME "cert_store_key"
+#define CERT_STORE_KEYRING_NAME "cert_store"
+
+static debug_info_t *cert_store_dbf;
+static debug_info_t *cert_store_hexdump;
+
+#define pr_dbf_msg(fmt, ...) \
+ debug_sprintf_event(cert_store_dbf, 3, fmt "\n", ## __VA_ARGS__)
+
+enum diag320_subcode {
+ DIAG320_SUBCODES = 0,
+ DIAG320_STORAGE = 1,
+ DIAG320_CERT_BLOCK = 2,
+};
+
+enum diag320_rc {
+ DIAG320_RC_OK = 0x0001,
+ DIAG320_RC_CS_NOMATCH = 0x0306,
+};
+
+/* Verification Certificates Store Support Block (VCSSB). */
+struct vcssb {
+ u32 vcssb_length;
+ u8 pad_0x04[3];
+ u8 version;
+ u8 pad_0x08[8];
+ u32 cs_token;
+ u8 pad_0x14[12];
+ u16 total_vc_index_count;
+ u16 max_vc_index_count;
+ u8 pad_0x24[28];
+ u32 max_vce_length;
+ u32 max_vcxe_length;
+ u8 pad_0x48[8];
+ u32 max_single_vcb_length;
+ u32 total_vcb_length;
+ u32 max_single_vcxb_length;
+ u32 total_vcxb_length;
+ u8 pad_0x60[32];
+} __packed __aligned(8);
+
+/* Verification Certificate Entry (VCE) Header. */
+struct vce_header {
+ u32 vce_length;
+ u8 flags;
+ u8 key_type;
+ u16 vc_index;
+ u8 vc_name[VC_NAME_LEN_BYTES]; /* EBCDIC */
+ u8 vc_format;
+ u8 pad_0x49;
+ u16 key_id_length;
+ u8 pad_0x4c;
+ u8 vc_hash_type;
+ u16 vc_hash_length;
+ u8 pad_0x50[4];
+ u32 vc_length;
+ u8 pad_0x58[8];
+ u16 vc_hash_offset;
+ u16 vc_offset;
+ u8 pad_0x64[28];
+} __packed __aligned(4);
+
+/* Verification Certificate Block (VCB) Header. */
+struct vcb_header {
+ u32 vcb_input_length;
+ u8 pad_0x04[4];
+ u16 first_vc_index;
+ u16 last_vc_index;
+ u32 pad_0x0c;
+ u32 cs_token;
+ u8 pad_0x14[12];
+ u32 vcb_output_length;
+ u8 pad_0x24[3];
+ u8 version;
+ u16 stored_vc_count;
+ u16 remaining_vc_count;
+ u8 pad_0x2c[20];
+} __packed __aligned(4);
+
+/* Verification Certificate Block (VCB). */
+struct vcb {
+ struct vcb_header vcb_hdr;
+ u8 vcb_buf[];
+} __packed __aligned(4);
+
+/* Verification Certificate Entry (VCE). */
+struct vce {
+ struct vce_header vce_hdr;
+ u8 cert_data_buf[];
+} __packed __aligned(4);
+
+static void cert_store_key_describe(const struct key *key, struct seq_file *m)
+{
+ char ascii[VC_NAME_LEN_BYTES + 1];
+
+ /*
+ * First 64 bytes of the key description is key name in EBCDIC CP 500.
+ * Convert it to ASCII for displaying in /proc/keys.
+ */
+ strscpy(ascii, key->description, sizeof(ascii));
+ EBCASC_500(ascii, VC_NAME_LEN_BYTES);
+ seq_puts(m, ascii);
+
+ seq_puts(m, &key->description[VC_NAME_LEN_BYTES]);
+ if (key_is_positive(key))
+ seq_printf(m, ": %u", key->datalen);
+}
+
+/*
+ * Certificate store key type takes over properties of
+ * user key but cannot be updated.
+ */
+static struct key_type key_type_cert_store_key = {
+ .name = CERT_STORE_KEY_TYPE_NAME,
+ .preparse = user_preparse,
+ .free_preparse = user_free_preparse,
+ .instantiate = generic_key_instantiate,
+ .revoke = user_revoke,
+ .destroy = user_destroy,
+ .describe = cert_store_key_describe,
+ .read = user_read,
+};
+
+/* Logging functions. */
+static void pr_dbf_vcb(const struct vcb *b)
+{
+ pr_dbf_msg("VCB Header:");
+ pr_dbf_msg("vcb_input_length: %d", b->vcb_hdr.vcb_input_length);
+ pr_dbf_msg("first_vc_index: %d", b->vcb_hdr.first_vc_index);
+ pr_dbf_msg("last_vc_index: %d", b->vcb_hdr.last_vc_index);
+ pr_dbf_msg("cs_token: %d", b->vcb_hdr.cs_token);
+ pr_dbf_msg("vcb_output_length: %d", b->vcb_hdr.vcb_output_length);
+ pr_dbf_msg("version: %d", b->vcb_hdr.version);
+ pr_dbf_msg("stored_vc_count: %d", b->vcb_hdr.stored_vc_count);
+ pr_dbf_msg("remaining_vc_count: %d", b->vcb_hdr.remaining_vc_count);
+}
+
+static void pr_dbf_vce(const struct vce *e)
+{
+ unsigned char vc_name[VC_NAME_LEN_BYTES + 1];
+ char log_string[VC_NAME_LEN_BYTES + 40];
+
+ pr_dbf_msg("VCE Header:");
+ pr_dbf_msg("vce_hdr.vce_length: %d", e->vce_hdr.vce_length);
+ pr_dbf_msg("vce_hdr.flags: %d", e->vce_hdr.flags);
+ pr_dbf_msg("vce_hdr.key_type: %d", e->vce_hdr.key_type);
+ pr_dbf_msg("vce_hdr.vc_index: %d", e->vce_hdr.vc_index);
+ pr_dbf_msg("vce_hdr.vc_format: %d", e->vce_hdr.vc_format);
+ pr_dbf_msg("vce_hdr.key_id_length: %d", e->vce_hdr.key_id_length);
+ pr_dbf_msg("vce_hdr.vc_hash_type: %d", e->vce_hdr.vc_hash_type);
+ pr_dbf_msg("vce_hdr.vc_hash_length: %d", e->vce_hdr.vc_hash_length);
+ pr_dbf_msg("vce_hdr.vc_hash_offset: %d", e->vce_hdr.vc_hash_offset);
+ pr_dbf_msg("vce_hdr.vc_length: %d", e->vce_hdr.vc_length);
+ pr_dbf_msg("vce_hdr.vc_offset: %d", e->vce_hdr.vc_offset);
+
+ /* Certificate name in ASCII. */
+ memcpy(vc_name, e->vce_hdr.vc_name, VC_NAME_LEN_BYTES);
+ EBCASC_500(vc_name, VC_NAME_LEN_BYTES);
+ vc_name[VC_NAME_LEN_BYTES] = '\0';
+
+ snprintf(log_string, sizeof(log_string),
+ "index: %d vce_hdr.vc_name (ASCII): %s",
+ e->vce_hdr.vc_index, vc_name);
+ debug_text_event(cert_store_hexdump, 3, log_string);
+
+ /* Certificate data. */
+ debug_text_event(cert_store_hexdump, 3, "VCE: Certificate data start");
+ debug_event(cert_store_hexdump, 3, (u8 *)e->cert_data_buf, 128);
+ debug_text_event(cert_store_hexdump, 3, "VCE: Certificate data end");
+ debug_event(cert_store_hexdump, 3,
+ (u8 *)e->cert_data_buf + e->vce_hdr.vce_length - 128, 128);
+}
+
+static void pr_dbf_vcssb(const struct vcssb *s)
+{
+ debug_text_event(cert_store_hexdump, 3, "DIAG320 Subcode1");
+ debug_event(cert_store_hexdump, 3, (u8 *)s, VCSSB_LEN_BYTES);
+
+ pr_dbf_msg("VCSSB:");
+ pr_dbf_msg("vcssb_length: %u", s->vcssb_length);
+ pr_dbf_msg("version: %u", s->version);
+ pr_dbf_msg("cs_token: %u", s->cs_token);
+ pr_dbf_msg("total_vc_index_count: %u", s->total_vc_index_count);
+ pr_dbf_msg("max_vc_index_count: %u", s->max_vc_index_count);
+ pr_dbf_msg("max_vce_length: %u", s->max_vce_length);
+ pr_dbf_msg("max_vcxe_length: %u", s->max_vce_length);
+ pr_dbf_msg("max_single_vcb_length: %u", s->max_single_vcb_length);
+ pr_dbf_msg("total_vcb_length: %u", s->total_vcb_length);
+ pr_dbf_msg("max_single_vcxb_length: %u", s->max_single_vcxb_length);
+ pr_dbf_msg("total_vcxb_length: %u", s->total_vcxb_length);
+}
+
+static int __diag320(unsigned long subcode, void *addr)
+{
+ union register_pair rp = { .even = (unsigned long)addr, };
+
+ asm volatile(
+ " diag %[rp],%[subcode],0x320\n"
+ "0: nopr %%r7\n"
+ EX_TABLE(0b, 0b)
+ : [rp] "+d" (rp.pair)
+ : [subcode] "d" (subcode)
+ : "cc", "memory");
+
+ return rp.odd;
+}
+
+static int diag320(unsigned long subcode, void *addr)
+{
+ diag_stat_inc(DIAG_STAT_X320);
+
+ return __diag320(subcode, addr);
+}
+
+/*
+ * Calculate SHA256 hash of the VCE certificate and compare it to hash stored in
+ * VCE. Return -EINVAL if hashes don't match.
+ */
+static int check_certificate_hash(const struct vce *vce)
+{
+ u8 hash[SHA256_DIGEST_SIZE];
+ u16 vc_hash_length;
+ u8 *vce_hash;
+
+ vce_hash = (u8 *)vce + vce->vce_hdr.vc_hash_offset;
+ vc_hash_length = vce->vce_hdr.vc_hash_length;
+ sha256((u8 *)vce + vce->vce_hdr.vc_offset, vce->vce_hdr.vc_length, hash);
+ if (memcmp(vce_hash, hash, vc_hash_length) == 0)
+ return 0;
+
+ pr_dbf_msg("SHA256 hash of received certificate does not match");
+ debug_text_event(cert_store_hexdump, 3, "VCE hash:");
+ debug_event(cert_store_hexdump, 3, vce_hash, SHA256_DIGEST_SIZE);
+ debug_text_event(cert_store_hexdump, 3, "Calculated hash:");
+ debug_event(cert_store_hexdump, 3, hash, SHA256_DIGEST_SIZE);
+
+ return -EINVAL;
+}
+
+static int check_certificate_valid(const struct vce *vce)
+{
+ if (!(vce->vce_hdr.flags & VCE_FLAGS_VALID_MASK)) {
+ pr_dbf_msg("Certificate entry is invalid");
+ return -EINVAL;
+ }
+ if (vce->vce_hdr.vc_format != 1) {
+ pr_dbf_msg("Certificate format is not supported");
+ return -EINVAL;
+ }
+ if (vce->vce_hdr.vc_hash_type != 1) {
+ pr_dbf_msg("Hash type is not supported");
+ return -EINVAL;
+ }
+
+ return check_certificate_hash(vce);
+}
+
+static struct key *get_user_session_keyring(void)
+{
+ key_ref_t us_keyring_ref;
+
+ us_keyring_ref = lookup_user_key(KEY_SPEC_USER_SESSION_KEYRING,
+ KEY_LOOKUP_CREATE, KEY_NEED_LINK);
+ if (IS_ERR(us_keyring_ref)) {
+ pr_dbf_msg("Couldn't get user session keyring: %ld",
+ PTR_ERR(us_keyring_ref));
+ return ERR_PTR(-ENOKEY);
+ }
+ key_ref_put(us_keyring_ref);
+ return key_ref_to_ptr(us_keyring_ref);
+}
+
+/* Invalidate all keys from cert_store keyring. */
+static int invalidate_keyring_keys(struct key *keyring)
+{
+ unsigned long num_keys, key_index;
+ size_t keyring_payload_len;
+ key_serial_t *key_array;
+ struct key *current_key;
+ int rc;
+
+ keyring_payload_len = key_type_keyring.read(keyring, NULL, 0);
+ num_keys = keyring_payload_len / sizeof(key_serial_t);
+ key_array = kcalloc(num_keys, sizeof(key_serial_t), GFP_KERNEL);
+ if (!key_array)
+ return -ENOMEM;
+
+ rc = key_type_keyring.read(keyring, (char *)key_array, keyring_payload_len);
+ if (rc != keyring_payload_len) {
+ pr_dbf_msg("Couldn't read keyring payload");
+ goto out;
+ }
+
+ for (key_index = 0; key_index < num_keys; key_index++) {
+ current_key = key_lookup(key_array[key_index]);
+ pr_dbf_msg("Invalidating key %08x", current_key->serial);
+
+ key_invalidate(current_key);
+ key_put(current_key);
+ rc = key_unlink(keyring, current_key);
+ if (rc) {
+ pr_dbf_msg("Couldn't unlink key %08x: %d", current_key->serial, rc);
+ break;
+ }
+ }
+out:
+ kfree(key_array);
+ return rc;
+}
+
+static struct key *find_cs_keyring(void)
+{
+ key_ref_t cs_keyring_ref;
+ struct key *cs_keyring;
+
+ cs_keyring_ref = keyring_search(make_key_ref(get_user_session_keyring(), true),
+ &key_type_keyring, CERT_STORE_KEYRING_NAME,
+ false);
+ if (!IS_ERR(cs_keyring_ref)) {
+ cs_keyring = key_ref_to_ptr(cs_keyring_ref);
+ key_ref_put(cs_keyring_ref);
+ goto found;
+ }
+ /* Search default locations: thread, process, session keyrings */
+ cs_keyring = request_key(&key_type_keyring, CERT_STORE_KEYRING_NAME, NULL);
+ if (IS_ERR(cs_keyring))
+ return NULL;
+ key_put(cs_keyring);
+found:
+ return cs_keyring;
+}
+
+static void cleanup_cs_keys(void)
+{
+ struct key *cs_keyring;
+
+ cs_keyring = find_cs_keyring();
+ if (!cs_keyring)
+ return;
+
+ pr_dbf_msg("Found cert_store keyring. Purging...");
+ /*
+ * Remove cert_store_key_type in case invalidation
+ * of old cert_store keys failed (= severe error).
+ */
+ if (invalidate_keyring_keys(cs_keyring))
+ unregister_key_type(&key_type_cert_store_key);
+
+ keyring_clear(cs_keyring);
+ key_invalidate(cs_keyring);
+ key_put(cs_keyring);
+ key_unlink(get_user_session_keyring(), cs_keyring);
+}
+
+static struct key *create_cs_keyring(void)
+{
+ static struct key *cs_keyring;
+
+ /* Cleanup previous cs_keyring and all associated keys if any. */
+ cleanup_cs_keys();
+ cs_keyring = keyring_alloc(CERT_STORE_KEYRING_NAME, GLOBAL_ROOT_UID,
+ GLOBAL_ROOT_GID, current_cred(),
+ (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ,
+ KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_SET_KEEP,
+ NULL, get_user_session_keyring());
+ if (IS_ERR(cs_keyring)) {
+ pr_dbf_msg("Can't allocate cert_store keyring");
+ return NULL;
+ }
+
+ pr_dbf_msg("Successfully allocated cert_store keyring: %08x", cs_keyring->serial);
+
+ /*
+ * In case a previous clean-up ran into an
+ * error and unregistered key type.
+ */
+ register_key_type(&key_type_cert_store_key);
+
+ return cs_keyring;
+}
+
+/*
+ * Allocate memory and create key description in format
+ * [key name in EBCDIC]:[VCE index]:[CS token].
+ * Return a pointer to key description or NULL if memory
+ * allocation failed. Memory should be freed by caller.
+ */
+static char *get_key_description(struct vcssb *vcssb, const struct vce *vce)
+{
+ size_t len, name_len;
+ u32 cs_token;
+ char *desc;
+
+ cs_token = vcssb->cs_token;
+ /* Description string contains "%64s:%04u:%08u\0". */
+ name_len = sizeof(vce->vce_hdr.vc_name);
+ len = name_len + 1 + 4 + 1 + 8 + 1;
+ desc = kmalloc(len, GFP_KERNEL);
+ if (!desc)
+ return NULL;
+
+ memcpy(desc, vce->vce_hdr.vc_name, name_len);
+ sprintf(desc + name_len, ":%04u:%08u", vce->vce_hdr.vc_index, cs_token);
+
+ return desc;
+}
+
+/*
+ * Create a key of type "cert_store_key" using the data from VCE for key
+ * payload and key description. Link the key to "cert_store" keyring.
+ */
+static int create_key_from_vce(struct vcssb *vcssb, struct vce *vce,
+ struct key *keyring)
+{
+ key_ref_t newkey;
+ char *desc;
+ int rc;
+
+ desc = get_key_description(vcssb, vce);
+ if (!desc)
+ return -ENOMEM;
+
+ newkey = key_create_or_update(
+ make_key_ref(keyring, true), CERT_STORE_KEY_TYPE_NAME,
+ desc, (u8 *)vce + vce->vce_hdr.vc_offset,
+ vce->vce_hdr.vc_length,
+ (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ,
+ KEY_ALLOC_NOT_IN_QUOTA);
+
+ rc = PTR_ERR_OR_ZERO(newkey);
+ if (rc) {
+ pr_dbf_msg("Couldn't create a key from Certificate Entry (%d)", rc);
+ rc = -ENOKEY;
+ goto out;
+ }
+
+ key_ref_put(newkey);
+out:
+ kfree(desc);
+ return rc;
+}
+
+/* Get Verification Certificate Storage Size block with DIAG320 subcode2. */
+static int get_vcssb(struct vcssb *vcssb)
+{
+ int diag320_rc;
+
+ memset(vcssb, 0, sizeof(*vcssb));
+ vcssb->vcssb_length = VCSSB_LEN_BYTES;
+ diag320_rc = diag320(DIAG320_STORAGE, vcssb);
+ pr_dbf_vcssb(vcssb);
+
+ if (diag320_rc != DIAG320_RC_OK) {
+ pr_dbf_msg("Diag 320 Subcode 1 returned bad RC: %04x", diag320_rc);
+ return -EIO;
+ }
+ if (vcssb->vcssb_length == VCSSB_LEN_NO_CERTS) {
+ pr_dbf_msg("No certificates available for current configuration");
+ return -ENOKEY;
+ }
+
+ return 0;
+}
+
+static u32 get_4k_mult_vcb_size(struct vcssb *vcssb)
+{
+ return round_up(vcssb->max_single_vcb_length, PAGE_SIZE);
+}
+
+/* Fill input fields of single-entry VCB that will be read by LPAR. */
+static void fill_vcb_input(struct vcssb *vcssb, struct vcb *vcb, u16 index)
+{
+ memset(vcb, 0, sizeof(*vcb));
+ vcb->vcb_hdr.vcb_input_length = get_4k_mult_vcb_size(vcssb);
+ vcb->vcb_hdr.cs_token = vcssb->cs_token;
+
+ /* Request single entry. */
+ vcb->vcb_hdr.first_vc_index = index;
+ vcb->vcb_hdr.last_vc_index = index;
+}
+
+static void extract_vce_from_sevcb(struct vcb *vcb, struct vce *vce)
+{
+ struct vce *extracted_vce;
+
+ extracted_vce = (struct vce *)vcb->vcb_buf;
+ memcpy(vce, vcb->vcb_buf, extracted_vce->vce_hdr.vce_length);
+ pr_dbf_vce(vce);
+}
+
+static int get_sevcb(struct vcssb *vcssb, u16 index, struct vcb *vcb)
+{
+ int rc, diag320_rc;
+
+ fill_vcb_input(vcssb, vcb, index);
+
+ diag320_rc = diag320(DIAG320_CERT_BLOCK, vcb);
+ pr_dbf_msg("Diag 320 Subcode2 RC %2x", diag320_rc);
+ pr_dbf_vcb(vcb);
+
+ switch (diag320_rc) {
+ case DIAG320_RC_OK:
+ rc = 0;
+ if (vcb->vcb_hdr.vcb_output_length == VCB_LEN_NO_CERTS) {
+ pr_dbf_msg("No certificate entry for index %u", index);
+ rc = -ENOKEY;
+ } else if (vcb->vcb_hdr.remaining_vc_count != 0) {
+ /* Retry on insufficient space. */
+ pr_dbf_msg("Couldn't get all requested certificates");
+ rc = -EAGAIN;
+ }
+ break;
+ case DIAG320_RC_CS_NOMATCH:
+ pr_dbf_msg("Certificate Store token mismatch");
+ rc = -EAGAIN;
+ break;
+ default:
+ pr_dbf_msg("Diag 320 Subcode2 returned bad rc (0x%4x)", diag320_rc);
+ rc = -EINVAL;
+ break;
+ }
+
+ return rc;
+}
+
+/*
+ * Allocate memory for single-entry VCB, get VCB via DIAG320 subcode 2 call,
+ * extract VCE and create a key from its' certificate.
+ */
+static int create_key_from_sevcb(struct vcssb *vcssb, u16 index,
+ struct key *keyring)
+{
+ struct vcb *vcb;
+ struct vce *vce;
+ int rc;
+
+ rc = -ENOMEM;
+ vcb = vmalloc(get_4k_mult_vcb_size(vcssb));
+ vce = vmalloc(vcssb->max_single_vcb_length - sizeof(vcb->vcb_hdr));
+ if (!vcb || !vce)
+ goto out;
+
+ rc = get_sevcb(vcssb, index, vcb);
+ if (rc)
+ goto out;
+
+ extract_vce_from_sevcb(vcb, vce);
+ rc = check_certificate_valid(vce);
+ if (rc)
+ goto out;
+
+ rc = create_key_from_vce(vcssb, vce, keyring);
+ if (rc)
+ goto out;
+
+ pr_dbf_msg("Successfully created key from Certificate Entry %d", index);
+out:
+ vfree(vce);
+ vfree(vcb);
+ return rc;
+}
+
+/*
+ * Request a single-entry VCB for each VCE available for the partition.
+ * Create a key from it and link it to cert_store keyring. If no keys
+ * could be created (i.e. VCEs were invalid) return -ENOKEY.
+ */
+static int add_certificates_to_keyring(struct vcssb *vcssb, struct key *keyring)
+{
+ int rc, index, count, added;
+
+ count = 0;
+ added = 0;
+ /* Certificate Store entries indices start with 1 and have no gaps. */
+ for (index = 1; index < vcssb->total_vc_index_count + 1; index++) {
+ pr_dbf_msg("Creating key from VCE %u", index);
+ rc = create_key_from_sevcb(vcssb, index, keyring);
+ count++;
+
+ if (rc == -EAGAIN)
+ return rc;
+
+ if (rc)
+ pr_dbf_msg("Creating key from VCE %u failed (%d)", index, rc);
+ else
+ added++;
+ }
+
+ if (added == 0) {
+ pr_dbf_msg("Processed %d entries. No keys created", count);
+ return -ENOKEY;
+ }
+
+ pr_info("Added %d of %d keys to cert_store keyring", added, count);
+
+ /*
+ * Do not allow to link more keys to certificate store keyring after all
+ * the VCEs were processed.
+ */
+ rc = keyring_restrict(make_key_ref(keyring, true), NULL, NULL);
+ if (rc)
+ pr_dbf_msg("Failed to set restriction to cert_store keyring (%d)", rc);
+
+ return 0;
+}
+
+/*
+ * Check which DIAG320 subcodes are installed.
+ * Return -ENOENT if subcodes 1 or 2 are not available.
+ */
+static int query_diag320_subcodes(void)
+{
+ unsigned long ism[ISM_LEN_DWORDS];
+ int rc;
+
+ rc = diag320(0, ism);
+ if (rc != DIAG320_RC_OK) {
+ pr_dbf_msg("DIAG320 subcode query returned %04x", rc);
+ return -ENOENT;
+ }
+
+ debug_text_event(cert_store_hexdump, 3, "DIAG320 Subcode 0");
+ debug_event(cert_store_hexdump, 3, ism, sizeof(ism));
+
+ if (!test_bit_inv(1, ism) || !test_bit_inv(2, ism)) {
+ pr_dbf_msg("Not all required DIAG320 subcodes are installed");
+ return -ENOENT;
+ }
+
+ return 0;
+}
+
+/*
+ * Check if Certificate Store is supported by the firmware and DIAG320 subcodes
+ * 1 and 2 are installed. Create cert_store keyring and link all certificates
+ * available for the current partition to it as "cert_store_key" type
+ * keys. On refresh or error invalidate cert_store keyring and destroy
+ * all keys of "cert_store_key" type.
+ */
+static int fill_cs_keyring(void)
+{
+ struct key *cs_keyring;
+ struct vcssb *vcssb;
+ int rc;
+
+ rc = -ENOMEM;
+ vcssb = kmalloc(VCSSB_LEN_BYTES, GFP_KERNEL);
+ if (!vcssb)
+ goto cleanup_keys;
+
+ rc = -ENOENT;
+ if (!sclp.has_diag320) {
+ pr_dbf_msg("Certificate Store is not supported");
+ goto cleanup_keys;
+ }
+
+ rc = query_diag320_subcodes();
+ if (rc)
+ goto cleanup_keys;
+
+ rc = get_vcssb(vcssb);
+ if (rc)
+ goto cleanup_keys;
+
+ rc = -ENOMEM;
+ cs_keyring = create_cs_keyring();
+ if (!cs_keyring)
+ goto cleanup_keys;
+
+ rc = add_certificates_to_keyring(vcssb, cs_keyring);
+ if (rc)
+ goto cleanup_cs_keyring;
+
+ goto out;
+
+cleanup_cs_keyring:
+ key_put(cs_keyring);
+cleanup_keys:
+ cleanup_cs_keys();
+out:
+ kfree(vcssb);
+ return rc;
+}
+
+static DEFINE_MUTEX(cs_refresh_lock);
+static int cs_status_val = -1;
+
+static ssize_t cs_status_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ if (cs_status_val == -1)
+ return sysfs_emit(buf, "uninitialized\n");
+ else if (cs_status_val == 0)
+ return sysfs_emit(buf, "ok\n");
+
+ return sysfs_emit(buf, "failed (%d)\n", cs_status_val);
+}
+
+static struct kobj_attribute cs_status_attr = __ATTR_RO(cs_status);
+
+static ssize_t refresh_store(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int rc, retries;
+
+ pr_dbf_msg("Refresh certificate store information requested");
+ rc = mutex_lock_interruptible(&cs_refresh_lock);
+ if (rc)
+ return rc;
+
+ for (retries = 0; retries < DIAG_MAX_RETRIES; retries++) {
+ /* Request certificates from certificate store. */
+ rc = fill_cs_keyring();
+ if (rc)
+ pr_dbf_msg("Failed to refresh certificate store information (%d)", rc);
+ if (rc != -EAGAIN)
+ break;
+ }
+ cs_status_val = rc;
+ mutex_unlock(&cs_refresh_lock);
+
+ return rc ?: count;
+}
+
+static struct kobj_attribute refresh_attr = __ATTR_WO(refresh);
+
+static const struct attribute *cert_store_attrs[] __initconst = {
+ &cs_status_attr.attr,
+ &refresh_attr.attr,
+ NULL,
+};
+
+static struct kobject *cert_store_kobj;
+
+static int __init cert_store_init(void)
+{
+ int rc = -ENOMEM;
+
+ cert_store_dbf = debug_register("cert_store_msg", 10, 1, 64);
+ if (!cert_store_dbf)
+ goto cleanup_dbf;
+
+ cert_store_hexdump = debug_register("cert_store_hexdump", 3, 1, 128);
+ if (!cert_store_hexdump)
+ goto cleanup_dbf;
+
+ debug_register_view(cert_store_hexdump, &debug_hex_ascii_view);
+ debug_register_view(cert_store_dbf, &debug_sprintf_view);
+
+ /* Create directory /sys/firmware/cert_store. */
+ cert_store_kobj = kobject_create_and_add("cert_store", firmware_kobj);
+ if (!cert_store_kobj)
+ goto cleanup_dbf;
+
+ rc = sysfs_create_files(cert_store_kobj, cert_store_attrs);
+ if (rc)
+ goto cleanup_kobj;
+
+ register_key_type(&key_type_cert_store_key);
+
+ return rc;
+
+cleanup_kobj:
+ kobject_put(cert_store_kobj);
+cleanup_dbf:
+ debug_unregister(cert_store_dbf);
+ debug_unregister(cert_store_hexdump);
+
+ return rc;
+}
+device_initcall(cert_store_init);
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index 82079f2d8583..f9f06cd8fcee 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -11,6 +11,7 @@
#include <linux/cpu.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
+#include <linux/vmalloc.h>
#include <asm/asm-extable.h>
#include <asm/diag.h>
#include <asm/trace/diag.h>
@@ -50,6 +51,7 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = {
[DIAG_STAT_X304] = { .code = 0x304, .name = "Partition-Resource Service" },
[DIAG_STAT_X308] = { .code = 0x308, .name = "List-Directed IPL" },
[DIAG_STAT_X318] = { .code = 0x318, .name = "CP Name and Version Codes" },
+ [DIAG_STAT_X320] = { .code = 0x320, .name = "Certificate Store" },
[DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" },
};
@@ -167,8 +169,29 @@ static inline int __diag204(unsigned long *subcode, unsigned long size, void *ad
return rp.odd;
}
+/**
+ * diag204() - Issue diagnose 204 call.
+ * @subcode: Subcode of diagnose 204 to be executed.
+ * @size: Size of area in pages which @area points to, if given.
+ * @addr: Vmalloc'ed memory area where the result is written to.
+ *
+ * Execute diagnose 204 with the given subcode and write the result to the
+ * memory area specified with @addr. For subcodes which do not write a
+ * result to memory both @size and @addr must be zero. If @addr is
+ * specified it must be page aligned and must have been allocated with
+ * vmalloc(). Conversion to real / physical addresses will be handled by
+ * this function if required.
+ */
int diag204(unsigned long subcode, unsigned long size, void *addr)
{
+ if (addr) {
+ if (WARN_ON_ONCE(!is_vmalloc_addr(addr)))
+ return -1;
+ if (WARN_ON_ONCE(!IS_ALIGNED((unsigned long)addr, PAGE_SIZE)))
+ return -1;
+ }
+ if ((subcode & DIAG204_SUBCODE_MASK) == DIAG204_SUBC_STIB4)
+ addr = (void *)pfn_to_phys(vmalloc_to_pfn(addr));
diag_stat_inc(DIAG_STAT_X204);
size = __diag204(&subcode, size, addr);
if (subcode)
@@ -200,7 +223,7 @@ int diag210(struct diag210 *addr)
EXPORT_SYMBOL(diag210);
/*
- * Diagnose 210: Get information about a virtual device
+ * Diagnose 8C: Access 3270 Display Device Information
*/
int diag8c(struct diag8c *addr, struct ccw_dev_id *devno)
{
diff --git a/arch/s390/kernel/ebcdic.c b/arch/s390/kernel/ebcdic.c
index 7f8246c9be08..0e51fa537262 100644
--- a/arch/s390/kernel/ebcdic.c
+++ b/arch/s390/kernel/ebcdic.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * ECBDIC -> ASCII, ASCII -> ECBDIC,
+ * EBCDIC -> ASCII, ASCII -> EBCDIC,
* upper to lower case (EBCDIC) conversion tables.
*
* S390 version
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index a660f4b6d654..49a11f6dd7ae 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -8,6 +8,7 @@
* Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
*/
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/asm-extable.h>
@@ -26,7 +27,6 @@
#include <asm/vx-insn.h>
#include <asm/setup.h>
#include <asm/nmi.h>
-#include <asm/export.h>
#include <asm/nospec-insn.h>
_LPP_OFFSET = __LC_LPP
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 85a00d97a314..05e51666db03 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -266,7 +266,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \
struct kobj_attribute *attr, \
const char *buf, size_t len) \
{ \
- strncpy(_value, buf, sizeof(_value) - 1); \
+ strscpy(_value, buf, sizeof(_value)); \
strim(_value); \
return len; \
} \
@@ -557,15 +557,12 @@ static struct kobj_attribute sys_ipl_ccw_loadparm_attr =
__ATTR(loadparm, 0444, ipl_ccw_loadparm_show, NULL);
static struct attribute *ipl_fcp_attrs[] = {
- &sys_ipl_type_attr.attr,
&sys_ipl_device_attr.attr,
&sys_ipl_fcp_wwpn_attr.attr,
&sys_ipl_fcp_lun_attr.attr,
&sys_ipl_fcp_bootprog_attr.attr,
&sys_ipl_fcp_br_lba_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
- &sys_ipl_secure_attr.attr,
- &sys_ipl_has_secure_attr.attr,
NULL,
};
@@ -575,14 +572,11 @@ static struct attribute_group ipl_fcp_attr_group = {
};
static struct attribute *ipl_nvme_attrs[] = {
- &sys_ipl_type_attr.attr,
&sys_ipl_nvme_fid_attr.attr,
&sys_ipl_nvme_nsid_attr.attr,
&sys_ipl_nvme_bootprog_attr.attr,
&sys_ipl_nvme_br_lba_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
- &sys_ipl_secure_attr.attr,
- &sys_ipl_has_secure_attr.attr,
NULL,
};
@@ -592,13 +586,10 @@ static struct attribute_group ipl_nvme_attr_group = {
};
static struct attribute *ipl_eckd_attrs[] = {
- &sys_ipl_type_attr.attr,
&sys_ipl_eckd_bootprog_attr.attr,
&sys_ipl_eckd_br_chr_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
&sys_ipl_device_attr.attr,
- &sys_ipl_secure_attr.attr,
- &sys_ipl_has_secure_attr.attr,
NULL,
};
@@ -610,21 +601,15 @@ static struct attribute_group ipl_eckd_attr_group = {
/* CCW ipl device attributes */
static struct attribute *ipl_ccw_attrs_vm[] = {
- &sys_ipl_type_attr.attr,
&sys_ipl_device_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
&sys_ipl_vm_parm_attr.attr,
- &sys_ipl_secure_attr.attr,
- &sys_ipl_has_secure_attr.attr,
NULL,
};
static struct attribute *ipl_ccw_attrs_lpar[] = {
- &sys_ipl_type_attr.attr,
&sys_ipl_device_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
- &sys_ipl_secure_attr.attr,
- &sys_ipl_has_secure_attr.attr,
NULL,
};
@@ -636,15 +621,15 @@ static struct attribute_group ipl_ccw_attr_group_lpar = {
.attrs = ipl_ccw_attrs_lpar
};
-/* UNKNOWN ipl device attributes */
-
-static struct attribute *ipl_unknown_attrs[] = {
+static struct attribute *ipl_common_attrs[] = {
&sys_ipl_type_attr.attr,
+ &sys_ipl_secure_attr.attr,
+ &sys_ipl_has_secure_attr.attr,
NULL,
};
-static struct attribute_group ipl_unknown_attr_group = {
- .attrs = ipl_unknown_attrs,
+static struct attribute_group ipl_common_attr_group = {
+ .attrs = ipl_common_attrs,
};
static struct kset *ipl_kset;
@@ -668,6 +653,9 @@ static int __init ipl_init(void)
rc = -ENOMEM;
goto out;
}
+ rc = sysfs_create_group(&ipl_kset->kobj, &ipl_common_attr_group);
+ if (rc)
+ goto out;
switch (ipl_info.type) {
case IPL_TYPE_CCW:
if (MACHINE_IS_VM)
@@ -689,8 +677,6 @@ static int __init ipl_init(void)
rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nvme_attr_group);
break;
default:
- rc = sysfs_create_group(&ipl_kset->kobj,
- &ipl_unknown_attr_group);
break;
}
out:
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 6d9276c096a6..12a2bd4fc88c 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -13,6 +13,7 @@
#include <linux/reboot.h>
#include <linux/ftrace.h>
#include <linux/debug_locks.h>
+#include <asm/pfault.h>
#include <asm/cio.h>
#include <asm/setup.h>
#include <asm/smp.h>
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 2df94d32140c..8d207b82d9fe 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -188,7 +188,7 @@ static int kexec_file_add_ipl_report(struct kimage *image,
data->memsz = ALIGN(data->memsz, PAGE_SIZE);
buf.mem = data->memsz;
- ptr = (void *)ipl_cert_list_addr;
+ ptr = __va(ipl_cert_list_addr);
end = ptr + ipl_cert_list_size;
ncerts = 0;
while (ptr < end) {
@@ -200,7 +200,7 @@ static int kexec_file_add_ipl_report(struct kimage *image,
addr = data->memsz + data->report->size;
addr += ncerts * sizeof(struct ipl_rb_certificate_entry);
- ptr = (void *)ipl_cert_list_addr;
+ ptr = __va(ipl_cert_list_addr);
while (ptr < end) {
len = *(unsigned int *)ptr;
ptr += sizeof(len);
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index dbece2803c50..ae4d4fd9afcd 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -9,15 +9,20 @@
#include <asm/ftrace.h>
#include <asm/nospec-insn.h>
#include <asm/ptrace.h>
-#include <asm/export.h>
+#define STACK_FRAME_SIZE_PTREGS (STACK_FRAME_OVERHEAD + __PT_SIZE)
+#define STACK_PTREGS (STACK_FRAME_OVERHEAD)
+#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
+#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW)
+
+#define STACK_FRAME_SIZE_FREGS (STACK_FRAME_OVERHEAD + __FTRACE_REGS_SIZE)
+#define STACK_FREGS (STACK_FRAME_OVERHEAD)
+#define STACK_FREGS_PTREGS (STACK_FRAME_OVERHEAD + __FTRACE_REGS_PT_REGS)
+#define STACK_FREGS_PTREGS_GPRS (STACK_FREGS_PTREGS + __PT_GPRS)
+#define STACK_FREGS_PTREGS_PSW (STACK_FREGS_PTREGS + __PT_PSW)
+#define STACK_FREGS_PTREGS_ORIG_GPR2 (STACK_FREGS_PTREGS + __PT_ORIG_GPR2)
+#define STACK_FREGS_PTREGS_FLAGS (STACK_FREGS_PTREGS + __PT_FLAGS)
-#define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE)
-#define STACK_PTREGS (STACK_FRAME_OVERHEAD)
-#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
-#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW)
-#define STACK_PTREGS_ORIG_GPR2 (STACK_PTREGS + __PT_ORIG_GPR2)
-#define STACK_PTREGS_FLAGS (STACK_PTREGS + __PT_FLAGS)
/* packed stack: allocate just enough for r14, r15 and backchain */
#define TRACED_FUNC_FRAME_SIZE 24
@@ -53,23 +58,23 @@ SYM_CODE_END(ftrace_stub_direct_tramp)
stg %r1,__SF_BACKCHAIN(%r15)
stg %r0,(__SF_GPRS+8*8)(%r15)
stg %r15,(__SF_GPRS+9*8)(%r15)
- # allocate pt_regs and stack frame for ftrace_trace_function
- aghi %r15,-STACK_FRAME_SIZE
- stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15)
- xc STACK_PTREGS_ORIG_GPR2(8,%r15),STACK_PTREGS_ORIG_GPR2(%r15)
+ # allocate ftrace_regs and stack frame for ftrace_trace_function
+ aghi %r15,-STACK_FRAME_SIZE_FREGS
+ stg %r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15)
+ xc STACK_FREGS_PTREGS_ORIG_GPR2(8,%r15),STACK_FREGS_PTREGS_ORIG_GPR2(%r15)
.if \allregs == 1
- stg %r14,(STACK_PTREGS_PSW)(%r15)
- mvghi STACK_PTREGS_FLAGS(%r15),_PIF_FTRACE_FULL_REGS
+ stg %r14,(STACK_FREGS_PTREGS_PSW)(%r15)
+ mvghi STACK_FREGS_PTREGS_FLAGS(%r15),_PIF_FTRACE_FULL_REGS
.else
- xc STACK_PTREGS_FLAGS(8,%r15),STACK_PTREGS_FLAGS(%r15)
+ xc STACK_FREGS_PTREGS_FLAGS(8,%r15),STACK_FREGS_PTREGS_FLAGS(%r15)
.endif
lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address
aghi %r1,-TRACED_FUNC_FRAME_SIZE
stg %r1,__SF_BACKCHAIN(%r15)
- stg %r0,(STACK_PTREGS_PSW+8)(%r15)
- stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15)
+ stg %r0,(STACK_FREGS_PTREGS_PSW+8)(%r15)
+ stmg %r2,%r14,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15)
.endm
SYM_CODE_START(ftrace_regs_caller)
@@ -96,30 +101,30 @@ SYM_CODE_START(ftrace_common)
lg %r1,0(%r1)
#endif
lgr %r3,%r14
- la %r5,STACK_PTREGS(%r15)
+ la %r5,STACK_FREGS(%r15)
BASR_EX %r14,%r1
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
# The j instruction gets runtime patched to a nop instruction.
# See ftrace_enable_ftrace_graph_caller.
SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL)
j .Lftrace_graph_caller_end
- lmg %r2,%r3,(STACK_PTREGS_GPRS+14*8)(%r15)
- lg %r4,(STACK_PTREGS_PSW+8)(%r15)
+ lmg %r2,%r3,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15)
+ lg %r4,(STACK_FREGS_PTREGS_PSW+8)(%r15)
brasl %r14,prepare_ftrace_return
- stg %r2,(STACK_PTREGS_GPRS+14*8)(%r15)
+ stg %r2,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15)
.Lftrace_graph_caller_end:
#endif
- lg %r0,(STACK_PTREGS_PSW+8)(%r15)
+ lg %r0,(STACK_FREGS_PTREGS_PSW+8)(%r15)
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
- ltg %r1,STACK_PTREGS_ORIG_GPR2(%r15)
+ ltg %r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15)
locgrz %r1,%r0
#else
- lg %r1,STACK_PTREGS_ORIG_GPR2(%r15)
+ lg %r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15)
ltgr %r1,%r1
jnz 0f
lgr %r1,%r0
#endif
-0: lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
+0: lmg %r2,%r15,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15)
BR_EX %r1
SYM_CODE_END(ftrace_common)
@@ -128,10 +133,14 @@ SYM_CODE_END(ftrace_common)
SYM_FUNC_START(return_to_handler)
stmg %r2,%r5,32(%r15)
lgr %r1,%r15
- aghi %r15,-STACK_FRAME_OVERHEAD
+ aghi %r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE)
stg %r1,__SF_BACKCHAIN(%r15)
+ la %r3,STACK_FRAME_OVERHEAD(%r15)
+ stg %r1,__FGRAPH_RET_FP(%r3)
+ stg %r2,__FGRAPH_RET_GPR2(%r3)
+ lgr %r2,%r3
brasl %r14,ftrace_return_to_handler
- aghi %r15,STACK_FRAME_OVERHEAD
+ aghi %r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE
lgr %r14,%r2
lmg %r2,%r5,32(%r15)
BR_EX %r14
@@ -160,11 +169,11 @@ SYM_CODE_END(ftrace_shared_hotpatch_trampoline_exrl)
SYM_CODE_START(arch_rethook_trampoline)
stg %r14,(__SF_GPRS+8*8)(%r15)
- lay %r15,-STACK_FRAME_SIZE(%r15)
+ lay %r15,-STACK_FRAME_SIZE_PTREGS(%r15)
stmg %r0,%r14,STACK_PTREGS_GPRS(%r15)
# store original stack pointer in backchain and pt_regs
- lay %r7,STACK_FRAME_SIZE(%r15)
+ lay %r7,STACK_FRAME_SIZE_PTREGS(%r15)
stg %r7,__SF_BACKCHAIN(%r15)
stg %r7,STACK_PTREGS_GPRS+(15*8)(%r15)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 00d76448319d..c744104e4a9c 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -146,6 +146,7 @@ static u32 __amode31_ref *__ctl_linkage_stack = __ctl_linkage_stack_amode31;
static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31;
int __bootdata(noexec_disabled);
+unsigned long __bootdata_preserved(max_mappable);
unsigned long __bootdata(ident_map_size);
struct physmem_info __bootdata(physmem_info);
@@ -874,7 +875,7 @@ static void __init log_component_list(void)
pr_info("Linux is running with Secure-IPL enabled\n");
else
pr_info("Linux is running with Secure-IPL disabled\n");
- ptr = (void *) early_ipl_comp_list_addr;
+ ptr = __va(early_ipl_comp_list_addr);
end = (void *) ptr + early_ipl_comp_list_size;
pr_info("The IPL report contains the following components:\n");
while (ptr < end) {
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index f9a2b755f510..a4edb7ea66ea 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -37,6 +37,7 @@
#include <linux/crash_dump.h>
#include <linux/kprobes.h>
#include <asm/asm-offsets.h>
+#include <asm/pfault.h>
#include <asm/diag.h>
#include <asm/switch_to.h>
#include <asm/facility.h>
@@ -252,8 +253,9 @@ static void pcpu_free_lowcore(struct pcpu *pcpu)
static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
{
- struct lowcore *lc = lowcore_ptr[cpu];
+ struct lowcore *lc, *abs_lc;
+ lc = lowcore_ptr[cpu];
cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
lc->cpu_nr = cpu;
@@ -266,7 +268,9 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
lc->machine_flags = S390_lowcore.machine_flags;
lc->user_timer = lc->system_timer =
lc->steal_timer = lc->avg_steal_timer = 0;
- __ctl_store(lc->cregs_save_area, 0, 15);
+ abs_lc = get_abs_lowcore();
+ memcpy(lc->cregs_save_area, abs_lc->cregs_save_area, sizeof(lc->cregs_save_area));
+ put_abs_lowcore(abs_lc);
lc->cregs_save_area[1] = lc->kernel_asce;
lc->cregs_save_area[7] = lc->user_asce;
save_access_regs((unsigned int *) lc->access_regs_save_area);
@@ -606,8 +610,8 @@ void smp_ctl_set_clear_bit(int cr, int bit, bool set)
ctlreg = (ctlreg & parms.andval) | parms.orval;
abs_lc->cregs_save_area[cr] = ctlreg;
put_abs_lowcore(abs_lc);
- spin_unlock(&ctl_lock);
on_each_cpu(smp_ctl_bit_callback, &parms, 1);
+ spin_unlock(&ctl_lock);
}
EXPORT_SYMBOL(smp_ctl_set_clear_bit);
@@ -927,12 +931,18 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
rc = pcpu_alloc_lowcore(pcpu, cpu);
if (rc)
return rc;
+ /*
+ * Make sure global control register contents do not change
+ * until new CPU has initialized control registers.
+ */
+ spin_lock(&ctl_lock);
pcpu_prepare_secondary(pcpu, cpu);
pcpu_attach_task(pcpu, tidle);
pcpu_start_fn(pcpu, smp_start_secondary, NULL);
/* Wait until cpu puts itself in the online & active maps */
while (!cpu_online(cpu))
cpu_relax();
+ spin_unlock(&ctl_lock);
return 0;
}
diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c
index 4d141e2c132e..30bb20461db4 100644
--- a/arch/s390/kernel/sthyi.c
+++ b/arch/s390/kernel/sthyi.c
@@ -317,7 +317,9 @@ static void fill_diag(struct sthyi_sctns *sctns)
if (pages <= 0)
return;
- diag204_buf = vmalloc(array_size(pages, PAGE_SIZE));
+ diag204_buf = __vmalloc_node(array_size(pages, PAGE_SIZE),
+ PAGE_SIZE, GFP_KERNEL, NUMA_NO_NODE,
+ __builtin_return_address(0));
if (!diag204_buf)
return;
@@ -459,9 +461,9 @@ static int sthyi_update_cache(u64 *rc)
*
* Fills the destination with system information returned by the STHYI
* instruction. The data is generated by emulation or execution of STHYI,
- * if available. The return value is the condition code that would be
- * returned, the rc parameter is the return code which is passed in
- * register R2 + 1.
+ * if available. The return value is either a negative error value or
+ * the condition code that would be returned, the rc parameter is the
+ * return code which is passed in register R2 + 1.
*/
int sthyi_fill(void *dst, u64 *rc)
{
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index a6935af2235c..0122cc156952 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -454,3 +454,4 @@
449 common futex_waitv sys_futex_waitv sys_futex_waitv
450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat sys_cachestat
+452 common fchmodat2 sys_fchmodat2 sys_fchmodat2
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 66f0eb1c872b..b771f1b4cdd1 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -88,7 +88,7 @@ fail:
* Requests the Ultravisor to pin the page in the shared state. This will
* cause an intercept when the guest attempts to unshare the pinned page.
*/
-static int uv_pin_shared(unsigned long paddr)
+int uv_pin_shared(unsigned long paddr)
{
struct uv_cb_cfs uvcb = {
.header.cmd = UVC_CMD_PIN_PAGE_SHARED,
@@ -100,6 +100,7 @@ static int uv_pin_shared(unsigned long paddr)
return -EINVAL;
return 0;
}
+EXPORT_SYMBOL_GPL(uv_pin_shared);
/*
* Requests the Ultravisor to destroy a guest page and make it
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 954d39adf85c..341abafb96e4 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -389,8 +389,8 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
*/
int handle_sthyi(struct kvm_vcpu *vcpu)
{
- int reg1, reg2, r = 0;
- u64 code, addr, cc = 0, rc = 0;
+ int reg1, reg2, cc = 0, r = 0;
+ u64 code, addr, rc = 0;
struct sthyi_sctns *sctns = NULL;
if (!test_kvm_facility(vcpu->kvm, 74))
@@ -421,7 +421,10 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
return -ENOMEM;
cc = sthyi_fill(sctns, &rc);
-
+ if (cc < 0) {
+ free_page((unsigned long)sctns);
+ return cc;
+ }
out:
if (!cc) {
if (kvm_s390_pv_cpu_is_protected(vcpu)) {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 0261d42c7d01..a7ea80cfa445 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -270,18 +270,6 @@ static inline u64 kvm_s390_pv_cpu_get_handle(struct kvm_vcpu *vcpu)
return vcpu->arch.pv.handle;
}
-static inline bool kvm_s390_pv_is_protected(struct kvm *kvm)
-{
- lockdep_assert_held(&kvm->lock);
- return !!kvm_s390_pv_get_handle(kvm);
-}
-
-static inline bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu)
-{
- lockdep_assert_held(&vcpu->mutex);
- return !!kvm_s390_pv_cpu_get_handle(vcpu);
-}
-
/* implemented in interrupt.c */
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 2f34c7c3c5ab..8d3f39a8a11e 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -18,6 +18,20 @@
#include <linux/mmu_notifier.h>
#include "kvm-s390.h"
+bool kvm_s390_pv_is_protected(struct kvm *kvm)
+{
+ lockdep_assert_held(&kvm->lock);
+ return !!kvm_s390_pv_get_handle(kvm);
+}
+EXPORT_SYMBOL_GPL(kvm_s390_pv_is_protected);
+
+bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu)
+{
+ lockdep_assert_held(&vcpu->mutex);
+ return !!kvm_s390_pv_cpu_get_handle(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_s390_pv_cpu_is_protected);
+
/**
* struct pv_vm_to_be_destroyed - Represents a protected VM that needs to
* be destroyed
@@ -411,8 +425,12 @@ int kvm_s390_pv_deinit_cleanup_all(struct kvm *kvm, u16 *rc, u16 *rrc)
u16 _rc, _rrc;
int cc = 0;
- /* Make sure the counter does not reach 0 before calling s390_uv_destroy_range */
- atomic_inc(&kvm->mm->context.protected_count);
+ /*
+ * Nothing to do if the counter was already 0. Otherwise make sure
+ * the counter does not reach 0 before calling s390_uv_destroy_range.
+ */
+ if (!atomic_inc_not_zero(&kvm->mm->context.protected_count))
+ return 0;
*rc = 1;
/* If the current VM is protected, destroy it */
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 5a9a55de2e10..08f60a42b9a6 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -5,8 +5,8 @@
* Copyright IBM Corp. 2012
*/
+#include <linux/export.h>
#include <linux/linkage.h>
-#include <asm/export.h>
#include <asm/nospec-insn.h>
GEN_BR_THUNK %r14
diff --git a/arch/s390/lib/tishift.S b/arch/s390/lib/tishift.S
index de33cf02cfd2..96214f51f49b 100644
--- a/arch/s390/lib/tishift.S
+++ b/arch/s390/lib/tishift.S
@@ -1,8 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/nospec-insn.h>
-#include <asm/export.h>
.section .noinstr.text, "ax"
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index d90db06a8af5..352ff520fd94 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_CMM) += cmm.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o
obj-$(CONFIG_PGSTE) += gmap.o
+obj-$(CONFIG_PFAULT) += pfault.o
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 5300c6867d5e..f47515313226 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -90,7 +90,7 @@ static long cmm_alloc_pages(long nr, long *counter,
} else
free_page((unsigned long) npa);
}
- diag10_range(virt_to_pfn(addr), 1);
+ diag10_range(virt_to_pfn((void *)addr), 1);
pa->pages[pa->index++] = addr;
(*counter)++;
spin_unlock(&cmm_lock);
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index ba5f80268878..afa5db750d92 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -297,7 +297,7 @@ static int pt_dump_init(void)
address_markers[ABS_LOWCORE_NR].start_address = __abs_lowcore;
address_markers[ABS_LOWCORE_END_NR].start_address = __abs_lowcore + ABS_LOWCORE_MAP_SIZE;
address_markers[MEMCPY_REAL_NR].start_address = __memcpy_real_area;
- address_markers[MEMCPY_REAL_END_NR].start_address = __memcpy_real_area + PAGE_SIZE;
+ address_markers[MEMCPY_REAL_END_NR].start_address = __memcpy_real_area + MEMCPY_REAL_SIZE;
address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap;
address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size;
address_markers[VMALLOC_NR].start_address = VMALLOC_START;
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 1bc42ce26599..e41869f5cc95 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -640,10 +640,13 @@ void segment_warning(int rc, char *seg_name)
pr_err("There is not enough memory to load or query "
"DCSS %s\n", seg_name);
break;
- case -ERANGE:
- pr_err("DCSS %s exceeds the kernel mapping range (%lu) "
- "and cannot be loaded\n", seg_name, VMEM_MAX_PHYS);
+ case -ERANGE: {
+ struct range mhp_range = arch_get_mappable_range();
+
+ pr_err("DCSS %s exceeds the kernel mapping range (%llu) "
+ "and cannot be loaded\n", seg_name, mhp_range.end + 1);
break;
+ }
default:
break;
}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index dbe8394234e2..099c4824dd8a 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -43,8 +43,6 @@
#include "../kernel/entry.h"
#define __FAIL_ADDR_MASK -4096L
-#define __SUBCODE_MASK 0x0600
-#define __PF_RES_FIELD 0x8000000000000000ULL
/*
* Allocate private vm_fault_reason from top. Please make sure it won't
@@ -407,7 +405,6 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
access = VM_WRITE;
if (access == VM_WRITE)
flags |= FAULT_FLAG_WRITE;
-#ifdef CONFIG_PER_VMA_LOCK
if (!(flags & FAULT_FLAG_USER))
goto lock_mmap;
vma = lock_vma_under_rcu(mm, address);
@@ -418,9 +415,12 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
goto lock_mmap;
}
fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
- vma_end_read(vma);
+ if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+ vma_end_read(vma);
if (!(fault & VM_FAULT_RETRY)) {
count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ if (likely(!(fault & VM_FAULT_ERROR)))
+ fault = 0;
goto out;
}
count_vm_vma_lock_event(VMA_LOCK_RETRY);
@@ -430,7 +430,6 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
goto out;
}
lock_mmap:
-#endif /* CONFIG_PER_VMA_LOCK */
mmap_read_lock(mm);
gmap = NULL;
@@ -581,232 +580,6 @@ void do_dat_exception(struct pt_regs *regs)
}
NOKPROBE_SYMBOL(do_dat_exception);
-#ifdef CONFIG_PFAULT
-/*
- * 'pfault' pseudo page faults routines.
- */
-static int pfault_disable;
-
-static int __init nopfault(char *str)
-{
- pfault_disable = 1;
- return 1;
-}
-
-__setup("nopfault", nopfault);
-
-struct pfault_refbk {
- u16 refdiagc;
- u16 reffcode;
- u16 refdwlen;
- u16 refversn;
- u64 refgaddr;
- u64 refselmk;
- u64 refcmpmk;
- u64 reserved;
-} __attribute__ ((packed, aligned(8)));
-
-static struct pfault_refbk pfault_init_refbk = {
- .refdiagc = 0x258,
- .reffcode = 0,
- .refdwlen = 5,
- .refversn = 2,
- .refgaddr = __LC_LPP,
- .refselmk = 1ULL << 48,
- .refcmpmk = 1ULL << 48,
- .reserved = __PF_RES_FIELD
-};
-
-int pfault_init(void)
-{
- int rc;
-
- if (pfault_disable)
- return -1;
- diag_stat_inc(DIAG_STAT_X258);
- asm volatile(
- " diag %1,%0,0x258\n"
- "0: j 2f\n"
- "1: la %0,8\n"
- "2:\n"
- EX_TABLE(0b,1b)
- : "=d" (rc)
- : "a" (&pfault_init_refbk), "m" (pfault_init_refbk) : "cc");
- return rc;
-}
-
-static struct pfault_refbk pfault_fini_refbk = {
- .refdiagc = 0x258,
- .reffcode = 1,
- .refdwlen = 5,
- .refversn = 2,
-};
-
-void pfault_fini(void)
-{
-
- if (pfault_disable)
- return;
- diag_stat_inc(DIAG_STAT_X258);
- asm volatile(
- " diag %0,0,0x258\n"
- "0: nopr %%r7\n"
- EX_TABLE(0b,0b)
- : : "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk) : "cc");
-}
-
-static DEFINE_SPINLOCK(pfault_lock);
-static LIST_HEAD(pfault_list);
-
-#define PF_COMPLETE 0x0080
-
-/*
- * The mechanism of our pfault code: if Linux is running as guest, runs a user
- * space process and the user space process accesses a page that the host has
- * paged out we get a pfault interrupt.
- *
- * This allows us, within the guest, to schedule a different process. Without
- * this mechanism the host would have to suspend the whole virtual cpu until
- * the page has been paged in.
- *
- * So when we get such an interrupt then we set the state of the current task
- * to uninterruptible and also set the need_resched flag. Both happens within
- * interrupt context(!). If we later on want to return to user space we
- * recognize the need_resched flag and then call schedule(). It's not very
- * obvious how this works...
- *
- * Of course we have a lot of additional fun with the completion interrupt (->
- * host signals that a page of a process has been paged in and the process can
- * continue to run). This interrupt can arrive on any cpu and, since we have
- * virtual cpus, actually appear before the interrupt that signals that a page
- * is missing.
- */
-static void pfault_interrupt(struct ext_code ext_code,
- unsigned int param32, unsigned long param64)
-{
- struct task_struct *tsk;
- __u16 subcode;
- pid_t pid;
-
- /*
- * Get the external interruption subcode & pfault initial/completion
- * signal bit. VM stores this in the 'cpu address' field associated
- * with the external interrupt.
- */
- subcode = ext_code.subcode;
- if ((subcode & 0xff00) != __SUBCODE_MASK)
- return;
- inc_irq_stat(IRQEXT_PFL);
- /* Get the token (= pid of the affected task). */
- pid = param64 & LPP_PID_MASK;
- rcu_read_lock();
- tsk = find_task_by_pid_ns(pid, &init_pid_ns);
- if (tsk)
- get_task_struct(tsk);
- rcu_read_unlock();
- if (!tsk)
- return;
- spin_lock(&pfault_lock);
- if (subcode & PF_COMPLETE) {
- /* signal bit is set -> a page has been swapped in by VM */
- if (tsk->thread.pfault_wait == 1) {
- /* Initial interrupt was faster than the completion
- * interrupt. pfault_wait is valid. Set pfault_wait
- * back to zero and wake up the process. This can
- * safely be done because the task is still sleeping
- * and can't produce new pfaults. */
- tsk->thread.pfault_wait = 0;
- list_del(&tsk->thread.list);
- wake_up_process(tsk);
- put_task_struct(tsk);
- } else {
- /* Completion interrupt was faster than initial
- * interrupt. Set pfault_wait to -1 so the initial
- * interrupt doesn't put the task to sleep.
- * If the task is not running, ignore the completion
- * interrupt since it must be a leftover of a PFAULT
- * CANCEL operation which didn't remove all pending
- * completion interrupts. */
- if (task_is_running(tsk))
- tsk->thread.pfault_wait = -1;
- }
- } else {
- /* signal bit not set -> a real page is missing. */
- if (WARN_ON_ONCE(tsk != current))
- goto out;
- if (tsk->thread.pfault_wait == 1) {
- /* Already on the list with a reference: put to sleep */
- goto block;
- } else if (tsk->thread.pfault_wait == -1) {
- /* Completion interrupt was faster than the initial
- * interrupt (pfault_wait == -1). Set pfault_wait
- * back to zero and exit. */
- tsk->thread.pfault_wait = 0;
- } else {
- /* Initial interrupt arrived before completion
- * interrupt. Let the task sleep.
- * An extra task reference is needed since a different
- * cpu may set the task state to TASK_RUNNING again
- * before the scheduler is reached. */
- get_task_struct(tsk);
- tsk->thread.pfault_wait = 1;
- list_add(&tsk->thread.list, &pfault_list);
-block:
- /* Since this must be a userspace fault, there
- * is no kernel task state to trample. Rely on the
- * return to userspace schedule() to block. */
- __set_current_state(TASK_UNINTERRUPTIBLE);
- set_tsk_need_resched(tsk);
- set_preempt_need_resched();
- }
- }
-out:
- spin_unlock(&pfault_lock);
- put_task_struct(tsk);
-}
-
-static int pfault_cpu_dead(unsigned int cpu)
-{
- struct thread_struct *thread, *next;
- struct task_struct *tsk;
-
- spin_lock_irq(&pfault_lock);
- list_for_each_entry_safe(thread, next, &pfault_list, list) {
- thread->pfault_wait = 0;
- list_del(&thread->list);
- tsk = container_of(thread, struct task_struct, thread);
- wake_up_process(tsk);
- put_task_struct(tsk);
- }
- spin_unlock_irq(&pfault_lock);
- return 0;
-}
-
-static int __init pfault_irq_init(void)
-{
- int rc;
-
- rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
- if (rc)
- goto out_extint;
- rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
- if (rc)
- goto out_pfault;
- irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
- cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead",
- NULL, pfault_cpu_dead);
- return 0;
-
-out_pfault:
- unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
-out_extint:
- pfault_disable = 1;
- return rc;
-}
-early_initcall(pfault_irq_init);
-
-#endif /* CONFIG_PFAULT */
-
#if IS_ENABLED(CONFIG_PGSTE)
void do_secure_storage_access(struct pt_regs *regs)
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 989ebd0912b4..906a7bfc2a78 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2514,6 +2514,7 @@ static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
static const struct mm_walk_ops thp_split_walk_ops = {
.pmd_entry = thp_split_walk_pmd_entry,
+ .walk_lock = PGWALK_WRLOCK_VERIFY,
};
static inline void thp_split_mm(struct mm_struct *mm)
@@ -2565,6 +2566,7 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
static const struct mm_walk_ops zap_zero_walk_ops = {
.pmd_entry = __zap_zero_pages,
+ .walk_lock = PGWALK_WRLOCK,
};
/*
@@ -2655,6 +2657,7 @@ static const struct mm_walk_ops enable_skey_walk_ops = {
.hugetlb_entry = __s390_enable_skey_hugetlb,
.pte_entry = __s390_enable_skey_pte,
.pmd_entry = __s390_enable_skey_pmd,
+ .walk_lock = PGWALK_WRLOCK,
};
int s390_enable_skey(void)
@@ -2692,6 +2695,7 @@ static int __s390_reset_cmma(pte_t *pte, unsigned long addr,
static const struct mm_walk_ops reset_cmma_walk_ops = {
.pte_entry = __s390_reset_cmma,
+ .walk_lock = PGWALK_WRLOCK,
};
void s390_reset_cmma(struct mm_struct *mm)
@@ -2728,6 +2732,7 @@ static int s390_gather_pages(pte_t *ptep, unsigned long addr,
static const struct mm_walk_ops gather_pages_ops = {
.pte_entry = s390_gather_pages,
+ .walk_lock = PGWALK_RDLOCK,
};
/*
@@ -2853,6 +2858,7 @@ int s390_replace_asce(struct gmap *gmap)
page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
if (!page)
return -ENOMEM;
+ page->index = 0;
table = page_to_virt(page);
memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index cbe1df1e9c18..c805b3e2592b 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -86,11 +86,12 @@ size_t memcpy_real_iter(struct iov_iter *iter, unsigned long src, size_t count)
void *chunk;
pte_t pte;
+ BUILD_BUG_ON(MEMCPY_REAL_SIZE != PAGE_SIZE);
while (count) {
- phys = src & PAGE_MASK;
- offset = src & ~PAGE_MASK;
+ phys = src & MEMCPY_REAL_MASK;
+ offset = src & ~MEMCPY_REAL_MASK;
chunk = (void *)(__memcpy_real_area + offset);
- len = min(count, PAGE_SIZE - offset);
+ len = min(count, MEMCPY_REAL_SIZE - offset);
pte = mk_pte_phys(phys, PAGE_KERNEL_RO);
mutex_lock(&memcpy_real_mutex);
diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
new file mode 100644
index 000000000000..1aac13bb8f53
--- /dev/null
+++ b/arch/s390/mm/pfault.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 1999, 2023
+ */
+
+#include <linux/cpuhotplug.h>
+#include <linux/sched/task.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <asm/asm-extable.h>
+#include <asm/pfault.h>
+#include <asm/diag.h>
+
+#define __SUBCODE_MASK 0x0600
+#define __PF_RES_FIELD 0x8000000000000000UL
+
+/*
+ * 'pfault' pseudo page faults routines.
+ */
+static int pfault_disable;
+
+static int __init nopfault(char *str)
+{
+ pfault_disable = 1;
+ return 1;
+}
+early_param("nopfault", nopfault);
+
+struct pfault_refbk {
+ u16 refdiagc;
+ u16 reffcode;
+ u16 refdwlen;
+ u16 refversn;
+ u64 refgaddr;
+ u64 refselmk;
+ u64 refcmpmk;
+ u64 reserved;
+};
+
+static struct pfault_refbk pfault_init_refbk = {
+ .refdiagc = 0x258,
+ .reffcode = 0,
+ .refdwlen = 5,
+ .refversn = 2,
+ .refgaddr = __LC_LPP,
+ .refselmk = 1UL << 48,
+ .refcmpmk = 1UL << 48,
+ .reserved = __PF_RES_FIELD
+};
+
+int __pfault_init(void)
+{
+ int rc = -EOPNOTSUPP;
+
+ if (pfault_disable)
+ return rc;
+ diag_stat_inc(DIAG_STAT_X258);
+ asm volatile(
+ " diag %[refbk],%[rc],0x258\n"
+ "0: nopr %%r7\n"
+ EX_TABLE(0b, 0b)
+ : [rc] "+d" (rc)
+ : [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk)
+ : "cc");
+ return rc;
+}
+
+static struct pfault_refbk pfault_fini_refbk = {
+ .refdiagc = 0x258,
+ .reffcode = 1,
+ .refdwlen = 5,
+ .refversn = 2,
+};
+
+void __pfault_fini(void)
+{
+ if (pfault_disable)
+ return;
+ diag_stat_inc(DIAG_STAT_X258);
+ asm volatile(
+ " diag %[refbk],0,0x258\n"
+ "0: nopr %%r7\n"
+ EX_TABLE(0b, 0b)
+ :
+ : [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk)
+ : "cc");
+}
+
+static DEFINE_SPINLOCK(pfault_lock);
+static LIST_HEAD(pfault_list);
+
+#define PF_COMPLETE 0x0080
+
+/*
+ * The mechanism of our pfault code: if Linux is running as guest, runs a user
+ * space process and the user space process accesses a page that the host has
+ * paged out we get a pfault interrupt.
+ *
+ * This allows us, within the guest, to schedule a different process. Without
+ * this mechanism the host would have to suspend the whole virtual cpu until
+ * the page has been paged in.
+ *
+ * So when we get such an interrupt then we set the state of the current task
+ * to uninterruptible and also set the need_resched flag. Both happens within
+ * interrupt context(!). If we later on want to return to user space we
+ * recognize the need_resched flag and then call schedule(). It's not very
+ * obvious how this works...
+ *
+ * Of course we have a lot of additional fun with the completion interrupt (->
+ * host signals that a page of a process has been paged in and the process can
+ * continue to run). This interrupt can arrive on any cpu and, since we have
+ * virtual cpus, actually appear before the interrupt that signals that a page
+ * is missing.
+ */
+static void pfault_interrupt(struct ext_code ext_code,
+ unsigned int param32, unsigned long param64)
+{
+ struct task_struct *tsk;
+ __u16 subcode;
+ pid_t pid;
+
+ /*
+ * Get the external interruption subcode & pfault initial/completion
+ * signal bit. VM stores this in the 'cpu address' field associated
+ * with the external interrupt.
+ */
+ subcode = ext_code.subcode;
+ if ((subcode & 0xff00) != __SUBCODE_MASK)
+ return;
+ inc_irq_stat(IRQEXT_PFL);
+ /* Get the token (= pid of the affected task). */
+ pid = param64 & LPP_PID_MASK;
+ rcu_read_lock();
+ tsk = find_task_by_pid_ns(pid, &init_pid_ns);
+ if (tsk)
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ if (!tsk)
+ return;
+ spin_lock(&pfault_lock);
+ if (subcode & PF_COMPLETE) {
+ /* signal bit is set -> a page has been swapped in by VM */
+ if (tsk->thread.pfault_wait == 1) {
+ /*
+ * Initial interrupt was faster than the completion
+ * interrupt. pfault_wait is valid. Set pfault_wait
+ * back to zero and wake up the process. This can
+ * safely be done because the task is still sleeping
+ * and can't produce new pfaults.
+ */
+ tsk->thread.pfault_wait = 0;
+ list_del(&tsk->thread.list);
+ wake_up_process(tsk);
+ put_task_struct(tsk);
+ } else {
+ /*
+ * Completion interrupt was faster than initial
+ * interrupt. Set pfault_wait to -1 so the initial
+ * interrupt doesn't put the task to sleep.
+ * If the task is not running, ignore the completion
+ * interrupt since it must be a leftover of a PFAULT
+ * CANCEL operation which didn't remove all pending
+ * completion interrupts.
+ */
+ if (task_is_running(tsk))
+ tsk->thread.pfault_wait = -1;
+ }
+ } else {
+ /* signal bit not set -> a real page is missing. */
+ if (WARN_ON_ONCE(tsk != current))
+ goto out;
+ if (tsk->thread.pfault_wait == 1) {
+ /* Already on the list with a reference: put to sleep */
+ goto block;
+ } else if (tsk->thread.pfault_wait == -1) {
+ /*
+ * Completion interrupt was faster than the initial
+ * interrupt (pfault_wait == -1). Set pfault_wait
+ * back to zero and exit.
+ */
+ tsk->thread.pfault_wait = 0;
+ } else {
+ /*
+ * Initial interrupt arrived before completion
+ * interrupt. Let the task sleep.
+ * An extra task reference is needed since a different
+ * cpu may set the task state to TASK_RUNNING again
+ * before the scheduler is reached.
+ */
+ get_task_struct(tsk);
+ tsk->thread.pfault_wait = 1;
+ list_add(&tsk->thread.list, &pfault_list);
+block:
+ /*
+ * Since this must be a userspace fault, there
+ * is no kernel task state to trample. Rely on the
+ * return to userspace schedule() to block.
+ */
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ set_tsk_need_resched(tsk);
+ set_preempt_need_resched();
+ }
+ }
+out:
+ spin_unlock(&pfault_lock);
+ put_task_struct(tsk);
+}
+
+static int pfault_cpu_dead(unsigned int cpu)
+{
+ struct thread_struct *thread, *next;
+ struct task_struct *tsk;
+
+ spin_lock_irq(&pfault_lock);
+ list_for_each_entry_safe(thread, next, &pfault_list, list) {
+ thread->pfault_wait = 0;
+ list_del(&thread->list);
+ tsk = container_of(thread, struct task_struct, thread);
+ wake_up_process(tsk);
+ put_task_struct(tsk);
+ }
+ spin_unlock_irq(&pfault_lock);
+ return 0;
+}
+
+static int __init pfault_irq_init(void)
+{
+ int rc;
+
+ rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
+ if (rc)
+ goto out_extint;
+ rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
+ if (rc)
+ goto out_pfault;
+ irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
+ cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead",
+ NULL, pfault_cpu_dead);
+ return 0;
+
+out_pfault:
+ unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
+out_extint:
+ pfault_disable = 1;
+ return rc;
+}
+early_initcall(pfault_irq_init);
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 66ab68db9842..07fc660a24aa 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -43,17 +43,17 @@ __initcall(page_table_register_sysctl);
unsigned long *crst_table_alloc(struct mm_struct *mm)
{
- struct page *page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
+ struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, CRST_ALLOC_ORDER);
- if (!page)
+ if (!ptdesc)
return NULL;
- arch_set_page_dat(page, CRST_ALLOC_ORDER);
- return (unsigned long *) page_to_virt(page);
+ arch_set_page_dat(ptdesc_page(ptdesc), CRST_ALLOC_ORDER);
+ return (unsigned long *) ptdesc_to_virt(ptdesc);
}
void crst_table_free(struct mm_struct *mm, unsigned long *table)
{
- free_pages((unsigned long)table, CRST_ALLOC_ORDER);
+ pagetable_free(virt_to_ptdesc(table));
}
static void __crst_table_upgrade(void *arg)
@@ -140,21 +140,21 @@ static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
struct page *page_table_alloc_pgste(struct mm_struct *mm)
{
- struct page *page;
+ struct ptdesc *ptdesc;
u64 *table;
- page = alloc_page(GFP_KERNEL);
- if (page) {
- table = (u64 *)page_to_virt(page);
+ ptdesc = pagetable_alloc(GFP_KERNEL, 0);
+ if (ptdesc) {
+ table = (u64 *)ptdesc_to_virt(ptdesc);
memset64(table, _PAGE_INVALID, PTRS_PER_PTE);
memset64(table + PTRS_PER_PTE, 0, PTRS_PER_PTE);
}
- return page;
+ return ptdesc_page(ptdesc);
}
void page_table_free_pgste(struct page *page)
{
- __free_page(page);
+ pagetable_free(page_ptdesc(page));
}
#endif /* CONFIG_PGSTE */
@@ -229,11 +229,20 @@ void page_table_free_pgste(struct page *page)
* logic described above. Both AA bits are set to 1 to denote a 4KB-pgtable
* while the PP bits are never used, nor such a page is added to or removed
* from mm_context_t::pgtable_list.
+ *
+ * pte_free_defer() overrides those rules: it takes the page off pgtable_list,
+ * and prevents both 2K fragments from being reused. pte_free_defer() has to
+ * guarantee that its pgtable cannot be reused before the RCU grace period
+ * has elapsed (which page_table_free_rcu() does not actually guarantee).
+ * But for simplicity, because page->rcu_head overlays page->lru, and because
+ * the RCU callback might not be called before the mm_context_t has been freed,
+ * pte_free_defer() in this implementation prevents both fragments from being
+ * reused, and delays making the call to RCU until both fragments are freed.
*/
unsigned long *page_table_alloc(struct mm_struct *mm)
{
unsigned long *table;
- struct page *page;
+ struct ptdesc *ptdesc;
unsigned int mask, bit;
/* Try to get a fragment of a 4K page as a 2K page table */
@@ -241,9 +250,9 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
table = NULL;
spin_lock_bh(&mm->context.lock);
if (!list_empty(&mm->context.pgtable_list)) {
- page = list_first_entry(&mm->context.pgtable_list,
- struct page, lru);
- mask = atomic_read(&page->_refcount) >> 24;
+ ptdesc = list_first_entry(&mm->context.pgtable_list,
+ struct ptdesc, pt_list);
+ mask = atomic_read(&ptdesc->_refcount) >> 24;
/*
* The pending removal bits must also be checked.
* Failure to do so might lead to an impossible
@@ -255,13 +264,13 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
*/
mask = (mask | (mask >> 4)) & 0x03U;
if (mask != 0x03U) {
- table = (unsigned long *) page_to_virt(page);
+ table = (unsigned long *) ptdesc_to_virt(ptdesc);
bit = mask & 1; /* =1 -> second 2K */
if (bit)
table += PTRS_PER_PTE;
- atomic_xor_bits(&page->_refcount,
+ atomic_xor_bits(&ptdesc->_refcount,
0x01U << (bit + 24));
- list_del(&page->lru);
+ list_del_init(&ptdesc->pt_list);
}
}
spin_unlock_bh(&mm->context.lock);
@@ -269,27 +278,28 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
return table;
}
/* Allocate a fresh page */
- page = alloc_page(GFP_KERNEL);
- if (!page)
+ ptdesc = pagetable_alloc(GFP_KERNEL, 0);
+ if (!ptdesc)
return NULL;
- if (!pgtable_pte_page_ctor(page)) {
- __free_page(page);
+ if (!pagetable_pte_ctor(ptdesc)) {
+ pagetable_free(ptdesc);
return NULL;
}
- arch_set_page_dat(page, 0);
+ arch_set_page_dat(ptdesc_page(ptdesc), 0);
/* Initialize page table */
- table = (unsigned long *) page_to_virt(page);
+ table = (unsigned long *) ptdesc_to_virt(ptdesc);
if (mm_alloc_pgste(mm)) {
/* Return 4K page table with PGSTEs */
- atomic_xor_bits(&page->_refcount, 0x03U << 24);
+ INIT_LIST_HEAD(&ptdesc->pt_list);
+ atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24);
memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE);
memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE);
} else {
/* Return the first 2K fragment of the page */
- atomic_xor_bits(&page->_refcount, 0x01U << 24);
+ atomic_xor_bits(&ptdesc->_refcount, 0x01U << 24);
memset64((u64 *)table, _PAGE_INVALID, 2 * PTRS_PER_PTE);
spin_lock_bh(&mm->context.lock);
- list_add(&page->lru, &mm->context.pgtable_list);
+ list_add(&ptdesc->pt_list, &mm->context.pgtable_list);
spin_unlock_bh(&mm->context.lock);
}
return table;
@@ -300,7 +310,9 @@ static void page_table_release_check(struct page *page, void *table,
{
char msg[128];
- if (!IS_ENABLED(CONFIG_DEBUG_VM) || !mask)
+ if (!IS_ENABLED(CONFIG_DEBUG_VM))
+ return;
+ if (!mask && list_empty(&page->lru))
return;
snprintf(msg, sizeof(msg),
"Invalid pgtable %p release half 0x%02x mask 0x%02x",
@@ -308,12 +320,20 @@ static void page_table_release_check(struct page *page, void *table,
dump_page(page, msg);
}
+static void pte_free_now(struct rcu_head *head)
+{
+ struct ptdesc *ptdesc;
+
+ ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
+ pagetable_pte_dtor(ptdesc);
+ pagetable_free(ptdesc);
+}
+
void page_table_free(struct mm_struct *mm, unsigned long *table)
{
unsigned int mask, bit, half;
- struct page *page;
+ struct ptdesc *ptdesc = virt_to_ptdesc(table);
- page = virt_to_page(table);
if (!mm_alloc_pgste(mm)) {
/* Free 2K page table fragment of a 4K page */
bit = ((unsigned long) table & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
@@ -323,42 +343,50 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
* will happen outside of the critical section from this
* function or from __tlb_remove_table()
*/
- mask = atomic_xor_bits(&page->_refcount, 0x11U << (bit + 24));
+ mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24));
mask >>= 24;
- if (mask & 0x03U)
- list_add(&page->lru, &mm->context.pgtable_list);
- else
- list_del(&page->lru);
+ if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) {
+ /*
+ * Other half is allocated, and neither half has had
+ * its free deferred: add page to head of list, to make
+ * this freed half available for immediate reuse.
+ */
+ list_add(&ptdesc->pt_list, &mm->context.pgtable_list);
+ } else {
+ /* If page is on list, now remove it. */
+ list_del_init(&ptdesc->pt_list);
+ }
spin_unlock_bh(&mm->context.lock);
- mask = atomic_xor_bits(&page->_refcount, 0x10U << (bit + 24));
+ mask = atomic_xor_bits(&ptdesc->_refcount, 0x10U << (bit + 24));
mask >>= 24;
if (mask != 0x00U)
return;
half = 0x01U << bit;
} else {
half = 0x03U;
- mask = atomic_xor_bits(&page->_refcount, 0x03U << 24);
+ mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24);
mask >>= 24;
}
- page_table_release_check(page, table, half, mask);
- pgtable_pte_page_dtor(page);
- __free_page(page);
+ page_table_release_check(ptdesc_page(ptdesc), table, half, mask);
+ if (folio_test_clear_active(ptdesc_folio(ptdesc)))
+ call_rcu(&ptdesc->pt_rcu_head, pte_free_now);
+ else
+ pte_free_now(&ptdesc->pt_rcu_head);
}
void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
unsigned long vmaddr)
{
struct mm_struct *mm;
- struct page *page;
unsigned int bit, mask;
+ struct ptdesc *ptdesc = virt_to_ptdesc(table);
mm = tlb->mm;
- page = virt_to_page(table);
if (mm_alloc_pgste(mm)) {
gmap_unlink(mm, table, vmaddr);
table = (unsigned long *) ((unsigned long)table | 0x03U);
- tlb_remove_table(tlb, table);
+ tlb_remove_ptdesc(tlb, table);
return;
}
bit = ((unsigned long) table & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
@@ -368,12 +396,20 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
* outside of the critical section from __tlb_remove_table() or from
* page_table_free()
*/
- mask = atomic_xor_bits(&page->_refcount, 0x11U << (bit + 24));
+ mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24));
mask >>= 24;
- if (mask & 0x03U)
- list_add_tail(&page->lru, &mm->context.pgtable_list);
- else
- list_del(&page->lru);
+ if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) {
+ /*
+ * Other half is allocated, and neither half has had
+ * its free deferred: add page to end of list, to make
+ * this freed half available for reuse once its pending
+ * bit has been cleared by __tlb_remove_table().
+ */
+ list_add_tail(&ptdesc->pt_list, &mm->context.pgtable_list);
+ } else {
+ /* If page is on list, now remove it. */
+ list_del_init(&ptdesc->pt_list);
+ }
spin_unlock_bh(&mm->context.lock);
table = (unsigned long *) ((unsigned long) table | (0x01U << bit));
tlb_remove_table(tlb, table);
@@ -383,30 +419,48 @@ void __tlb_remove_table(void *_table)
{
unsigned int mask = (unsigned long) _table & 0x03U, half = mask;
void *table = (void *)((unsigned long) _table ^ mask);
- struct page *page = virt_to_page(table);
+ struct ptdesc *ptdesc = virt_to_ptdesc(table);
switch (half) {
case 0x00U: /* pmd, pud, or p4d */
- free_pages((unsigned long)table, CRST_ALLOC_ORDER);
+ pagetable_free(ptdesc);
return;
case 0x01U: /* lower 2K of a 4K page table */
case 0x02U: /* higher 2K of a 4K page table */
- mask = atomic_xor_bits(&page->_refcount, mask << (4 + 24));
+ mask = atomic_xor_bits(&ptdesc->_refcount, mask << (4 + 24));
mask >>= 24;
if (mask != 0x00U)
return;
break;
case 0x03U: /* 4K page table with pgstes */
- mask = atomic_xor_bits(&page->_refcount, 0x03U << 24);
+ mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24);
mask >>= 24;
break;
}
- page_table_release_check(page, table, half, mask);
- pgtable_pte_page_dtor(page);
- __free_page(page);
+ page_table_release_check(ptdesc_page(ptdesc), table, half, mask);
+ if (folio_test_clear_active(ptdesc_folio(ptdesc)))
+ call_rcu(&ptdesc->pt_rcu_head, pte_free_now);
+ else
+ pte_free_now(&ptdesc->pt_rcu_head);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+ struct page *page;
+
+ page = virt_to_page(pgtable);
+ SetPageActive(page);
+ page_table_free(mm, (unsigned long *)pgtable);
+ /*
+ * page_table_free() does not do the pgste gmap_unlink() which
+ * page_table_free_rcu() does: warn us if pgste ever reaches here.
+ */
+ WARN_ON_ONCE(mm_has_pgste(mm));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
/*
* Base infrastructure required to generate basic asces, region, segment,
* and page tables that do not make use of enhanced features like EDAT1.
@@ -432,16 +486,20 @@ static void base_pgt_free(unsigned long *table)
static unsigned long *base_crst_alloc(unsigned long val)
{
unsigned long *table;
+ struct ptdesc *ptdesc;
- table = (unsigned long *)__get_free_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
- if (table)
- crst_table_init(table, val);
+ ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, CRST_ALLOC_ORDER);
+ if (!ptdesc)
+ return NULL;
+ table = ptdesc_address(ptdesc);
+
+ crst_table_init(table, val);
return table;
}
static void base_crst_free(unsigned long *table)
{
- free_pages((unsigned long)table, CRST_ALLOC_ORDER);
+ pagetable_free(virt_to_ptdesc(table));
}
#define BASE_ADDR_END_FUNC(NAME, SIZE) \
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index b26649233d12..e44243b9c0a4 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -36,7 +36,7 @@ static void vmem_free_pages(unsigned long addr, int order)
{
/* We don't expect boot memory to be removed ever. */
if (!slab_is_available() ||
- WARN_ON_ONCE(PageReserved(virt_to_page(addr))))
+ WARN_ON_ONCE(PageReserved(virt_to_page((void *)addr))))
return;
free_pages(addr, order);
}
@@ -531,7 +531,7 @@ struct range arch_get_mappable_range(void)
struct range mhp_range;
mhp_range.start = 0;
- mhp_range.end = VMEM_MAX_PHYS - 1;
+ mhp_range.end = max_mappable - 1;
return mhp_range;
}
@@ -763,6 +763,8 @@ void __init vmem_map_init(void)
if (static_key_enabled(&cpu_has_bear))
set_memory_nx(0, 1);
set_memory_nx(PAGE_SIZE, 1);
+ if (debug_pagealloc_enabled())
+ set_memory_4k(0, ident_map_size >> PAGE_SHIFT);
pr_info("Write protected kernel read-only data: %luk\n",
(unsigned long)(__end_rodata - _stext) >> 10);
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index afc3f33788da..d34d5813d006 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -244,62 +244,25 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
zpci_memcpy_toio(to, from, count);
}
-static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot)
+void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
+ unsigned long prot)
{
- unsigned long offset, vaddr;
- struct vm_struct *area;
- phys_addr_t last_addr;
-
- last_addr = addr + size - 1;
- if (!size || last_addr < addr)
- return NULL;
-
+ /*
+ * When PCI MIO instructions are unavailable the "physical" address
+ * encodes a hint for accessing the PCI memory space it represents.
+ * Just pass it unchanged such that ioread/iowrite can decode it.
+ */
if (!static_branch_unlikely(&have_mio))
- return (void __iomem *) addr;
+ return (void __iomem *)phys_addr;
- offset = addr & ~PAGE_MASK;
- addr &= PAGE_MASK;
- size = PAGE_ALIGN(size + offset);
- area = get_vm_area(size, VM_IOREMAP);
- if (!area)
- return NULL;
-
- vaddr = (unsigned long) area->addr;
- if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) {
- free_vm_area(area);
- return NULL;
- }
- return (void __iomem *) ((unsigned long) area->addr + offset);
-}
-
-void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
-{
- return __ioremap(addr, size, __pgprot(prot));
+ return generic_ioremap_prot(phys_addr, size, __pgprot(prot));
}
EXPORT_SYMBOL(ioremap_prot);
-void __iomem *ioremap(phys_addr_t addr, size_t size)
-{
- return __ioremap(addr, size, PAGE_KERNEL);
-}
-EXPORT_SYMBOL(ioremap);
-
-void __iomem *ioremap_wc(phys_addr_t addr, size_t size)
-{
- return __ioremap(addr, size, pgprot_writecombine(PAGE_KERNEL));
-}
-EXPORT_SYMBOL(ioremap_wc);
-
-void __iomem *ioremap_wt(phys_addr_t addr, size_t size)
-{
- return __ioremap(addr, size, pgprot_writethrough(PAGE_KERNEL));
-}
-EXPORT_SYMBOL(ioremap_wt);
-
void iounmap(volatile void __iomem *addr)
{
if (static_branch_likely(&have_mio))
- vunmap((__force void *) ((unsigned long) addr & PAGE_MASK));
+ generic_iounmap(addr);
}
EXPORT_SYMBOL(iounmap);
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index ee367798e388..ee90a91ed888 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -666,9 +666,4 @@ static struct miscdevice clp_misc_device = {
.fops = &clp_misc_fops,
};
-static int __init clp_misc_init(void)
-{
- return misc_register(&clp_misc_device);
-}
-
-device_initcall(clp_misc_init);
+builtin_misc_device(clp_misc_device);