summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/userspace-api/ioctl/ioctl-number.rst4
-rw-r--r--MAINTAINERS6
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/powerpc/Kconfig.debug1
-rw-r--r--arch/powerpc/Makefile25
-rw-r--r--arch/powerpc/boot/dts/fsl/t1023si-post.dtsi79
-rw-r--r--arch/powerpc/boot/dts/fsl/t1040si-post.dtsi71
-rw-r--r--arch/powerpc/configs/ppc64_defconfig1
-rw-r--r--arch/powerpc/configs/ps3_defconfig1
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h10
-rw-r--r--arch/powerpc/include/asm/book3s/64/tlbflush.h9
-rw-r--r--arch/powerpc/include/asm/ftrace.h2
-rw-r--r--arch/powerpc/include/asm/hvcall.h20
-rw-r--r--arch/powerpc/include/asm/kvm_book3s.h10
-rw-r--r--arch/powerpc/include/asm/kvm_book3s_64.h1
-rw-r--r--arch/powerpc/include/asm/linkage.h3
-rw-r--r--arch/powerpc/include/asm/mmu.h4
-rw-r--r--arch/powerpc/include/asm/mmzone.h8
-rw-r--r--arch/powerpc/include/asm/papr-sysparm.h17
-rw-r--r--arch/powerpc/include/asm/paravirt.h33
-rw-r--r--arch/powerpc/include/asm/ppc-pci.h5
-rw-r--r--arch/powerpc/include/asm/ps3.h6
-rw-r--r--arch/powerpc/include/asm/reg.h1
-rw-r--r--arch/powerpc/include/asm/reg_a2.h154
-rw-r--r--arch/powerpc/include/asm/rtas.h91
-rw-r--r--arch/powerpc/include/uapi/asm/papr-miscdev.h9
-rw-r--r--arch/powerpc/include/uapi/asm/papr-sysparm.h58
-rw-r--r--arch/powerpc/include/uapi/asm/papr-vpd.h22
-rw-r--r--arch/powerpc/kernel/cpu_specs_book3s_64.h15
-rw-r--r--arch/powerpc/kernel/cputable.c4
-rw-r--r--arch/powerpc/kernel/exceptions-64e.S1
-rw-r--r--arch/powerpc/kernel/rtas.c207
-rw-r--r--arch/powerpc/kernel/rtas_pci.c8
-rw-r--r--arch/powerpc/kernel/smp.c124
-rw-r--r--arch/powerpc/kernel/swsusp_64.c2
-rw-r--r--arch/powerpc/kernel/trace/ftrace_entry.S2
-rw-r--r--arch/powerpc/kernel/traps.c2
-rw-r--r--arch/powerpc/kernel/udbg_16550.c1
-rw-r--r--arch/powerpc/kernel/vdso/Makefile2
-rw-r--r--arch/powerpc/kexec/core.c1
-rw-r--r--arch/powerpc/kvm/book3s.c4
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c7
-rw-r--r--arch/powerpc/kvm/book3s_hv.c72
-rw-r--r--arch/powerpc/kvm/book3s_hv_nested.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv_nestedv2.c29
-rw-r--r--arch/powerpc/kvm/book3s_pr.c1
-rw-r--r--arch/powerpc/kvm/emulate_loadstore.c21
-rw-r--r--arch/powerpc/lib/Makefile2
-rw-r--r--arch/powerpc/lib/sstep.c14
-rw-r--r--arch/powerpc/mm/book3s64/hash_utils.c7
-rw-r--r--arch/powerpc/mm/book3s64/pgtable.c2
-rw-r--r--arch/powerpc/mm/book3s64/pkeys.c3
-rw-r--r--arch/powerpc/mm/init-common.c5
-rw-r--r--arch/powerpc/mm/mmu_decl.h5
-rw-r--r--arch/powerpc/perf/hv-gpci.c3
-rw-r--r--arch/powerpc/perf/imc-pmu.c6
-rw-r--r--arch/powerpc/platforms/44x/Kconfig1
-rw-r--r--arch/powerpc/platforms/44x/idle.c2
-rw-r--r--arch/powerpc/platforms/512x/mpc5121_ads_cpld.c2
-rw-r--r--arch/powerpc/platforms/512x/pdm360ng.c2
-rw-r--r--arch/powerpc/platforms/83xx/suspend.c5
-rw-r--r--arch/powerpc/platforms/85xx/mpc85xx_rdb.c2
-rw-r--r--arch/powerpc/platforms/86xx/Kconfig7
-rw-r--r--arch/powerpc/platforms/pasemi/setup.c2
-rw-r--r--arch/powerpc/platforms/powermac/smp.c4
-rw-r--r--arch/powerpc/platforms/powernv/opal-irqchip.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-powercap.c6
-rw-r--r--arch/powerpc/platforms/powernv/opal-prd.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-xscom.c5
-rw-r--r--arch/powerpc/platforms/powernv/subcore.c3
-rw-r--r--arch/powerpc/platforms/ps3/Kconfig12
-rw-r--r--arch/powerpc/platforms/ps3/Makefile2
-rw-r--r--arch/powerpc/platforms/ps3/device-init.c1
-rw-r--r--arch/powerpc/platforms/ps3/gelic_udbg.c1
-rw-r--r--arch/powerpc/platforms/pseries/Makefile1
-rw-r--r--arch/powerpc/platforms/pseries/eeh_pseries.c18
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c16
-rw-r--r--arch/powerpc/platforms/pseries/papr-sysparm.c205
-rw-r--r--arch/powerpc/platforms/pseries/papr-vpd.c541
-rw-r--r--arch/powerpc/platforms/pseries/pseries.h1
-rw-r--r--arch/powerpc/platforms/pseries/suspend.c1
-rw-r--r--arch/powerpc/sysdev/grackle.c19
-rw-r--r--arch/powerpc/sysdev/xics/icp-native.c2
-rw-r--r--drivers/misc/cxl/cxl.h3
-rw-r--r--drivers/misc/ocxl/afu_irq.c2
-rw-r--r--drivers/misc/ocxl/context.c2
-rw-r--r--drivers/misc/ocxl/link.c14
-rw-r--r--drivers/misc/ocxl/main.c2
-rw-r--r--drivers/net/ethernet/toshiba/ps3_gelic_net.h6
-rw-r--r--tools/testing/selftests/powerpc/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/math/fpu.h25
-rw-r--r--tools/testing/selftests/powerpc/math/fpu_asm.S48
-rw-r--r--tools/testing/selftests/powerpc/math/fpu_preempt.c30
-rw-r--r--tools/testing/selftests/powerpc/math/fpu_syscall.c8
-rw-r--r--tools/testing/selftests/powerpc/math/vmx_preempt.c10
-rw-r--r--tools/testing/selftests/powerpc/papr_sysparm/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/papr_sysparm/Makefile12
-rw-r--r--tools/testing/selftests/powerpc/papr_sysparm/papr_sysparm.c196
-rw-r--r--tools/testing/selftests/powerpc/papr_vpd/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/papr_vpd/Makefile12
-rw-r--r--tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c352
101 files changed, 2192 insertions, 603 deletions
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 4ea5b837399a..d8b6cb1a3636 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -349,6 +349,10 @@ Code Seq# Include File Comments
<mailto:vgo@ratio.de>
0xB1 00-1F PPPoX
<mailto:mostrows@styx.uwaterloo.ca>
+0xB2 00 arch/powerpc/include/uapi/asm/papr-vpd.h powerpc/pseries VPD API
+ <mailto:linuxppc-dev>
+0xB2 01-02 arch/powerpc/include/uapi/asm/papr-sysparm.h powerpc/pseries system parameter API
+ <mailto:linuxppc-dev>
0xB3 00 linux/mmc/ioctl.h
0xB4 00-0F linux/gpio.h <mailto:linux-gpio@vger.kernel.org>
0xB5 00-0F uapi/linux/rpmsg.h <mailto:linux-remoteproc@vger.kernel.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index 550d98cf14c6..9a48eac8b471 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12252,21 +12252,21 @@ S: Orphan
F: arch/powerpc/platforms/40x/
F: arch/powerpc/platforms/44x/
-LINUX FOR POWERPC EMBEDDED PPC83XX AND PPC85XX
+LINUX FOR POWERPC EMBEDDED PPC85XX
M: Scott Wood <oss@buserror.net>
L: linuxppc-dev@lists.ozlabs.org
S: Odd fixes
T: git git://git.kernel.org/pub/scm/linux/kernel/git/scottwood/linux.git
F: Documentation/devicetree/bindings/cache/freescale-l2cache.txt
F: Documentation/devicetree/bindings/powerpc/fsl/
-F: arch/powerpc/platforms/83xx/
F: arch/powerpc/platforms/85xx/
-LINUX FOR POWERPC EMBEDDED PPC8XX
+LINUX FOR POWERPC EMBEDDED PPC8XX AND PPC83XX
M: Christophe Leroy <christophe.leroy@csgroup.eu>
L: linuxppc-dev@lists.ozlabs.org
S: Maintained
F: arch/powerpc/platforms/8xx/
+F: arch/powerpc/platforms/83xx/
LINUX KERNEL DUMP TEST MODULE (LKDTM)
M: Kees Cook <keescook@chromium.org>
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f11a62809f2..76f05373361f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -189,6 +189,7 @@ config PPC
select EDAC_ATOMIC_SCRUB
select EDAC_SUPPORT
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+ select FUNCTION_ALIGNMENT_4B
select GENERIC_ATOMIC64 if PPC32
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select GENERIC_CMOS_UPDATE
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index ea4033abc07d..8c80b154e814 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -271,7 +271,6 @@ config PPC_EARLY_DEBUG_USBGECKO
config PPC_EARLY_DEBUG_PS3GELIC
bool "Early debugging through the PS3 Ethernet port"
depends on PPC_PS3
- select PS3GELIC_UDBG
help
Select this to enable early debugging for the PlayStation3 via
UDP broadcasts sent out through the Ethernet port.
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index f19dbaa1d541..051247027da0 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -10,15 +10,26 @@
# Rewritten by Cort Dougan and Paul Mackerras
#
+ifdef cross_compiling
+ ifeq ($(CROSS_COMPILE),)
+ # Auto detect cross compiler prefix.
+ # Look for: (powerpc(64(le)?)?)(-unknown)?-linux(-gnu)?-
+ CC_ARCHES := powerpc powerpc64 powerpc64le
+ CC_SUFFIXES := linux linux-gnu unknown-linux-gnu
+ CROSS_COMPILE := $(call cc-cross-prefix, $(foreach a,$(CC_ARCHES), \
+ $(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
+ endif
+endif
+
HAS_BIARCH := $(call cc-option-yn, -m32)
# Set default 32 bits cross compilers for vdso and boot wrapper
CROSS32_COMPILE ?=
# If we're on a ppc/ppc64/ppc64le machine use that defconfig, otherwise just use
-# ppc64_defconfig because we have nothing better to go on.
+# ppc64le_defconfig because we have nothing better to go on.
uname := $(shell uname -m)
-KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64)_defconfig
+KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64le)_defconfig
new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi)
@@ -161,7 +172,7 @@ CFLAGS-y += $(CONFIG_TUNE_CPU)
asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
-KBUILD_CPPFLAGS += -I $(srctree)/arch/$(ARCH) $(asinstr)
+KBUILD_CPPFLAGS += -I $(srctree)/arch/powerpc $(asinstr)
KBUILD_AFLAGS += $(AFLAGS-y)
KBUILD_CFLAGS += $(call cc-option,-msoft-float)
KBUILD_CFLAGS += $(CFLAGS-y)
@@ -232,7 +243,7 @@ BOOT_TARGETS2 := zImage% dtbImage% treeImage.% cuImage.% simpleImage.% uImage.%
PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2)
-boot := arch/$(ARCH)/boot
+boot := arch/powerpc/boot
$(BOOT_TARGETS1): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
@@ -336,7 +347,7 @@ PHONY += $(generated_configs)
define archhelp
echo '* zImage - Build default images selected by kernel config'
- echo ' zImage.* - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)'
+ echo ' zImage.* - Compressed kernel image (arch/powerpc/boot/zImage.*)'
echo ' uImage - U-Boot native image format'
echo ' cuImage.<dt> - Backwards compatible U-Boot image for older'
echo ' versions which do not support device trees'
@@ -347,12 +358,12 @@ define archhelp
echo ' (your) ~/bin/$(INSTALLKERNEL) or'
echo ' (distribution) /sbin/$(INSTALLKERNEL) or'
echo ' install to $$(INSTALL_PATH) and run lilo'
- echo ' *_defconfig - Select default config from arch/$(ARCH)/configs'
+ echo ' *_defconfig - Select default config from arch/powerpc/configs'
echo ''
echo ' Targets with <dt> embed a device tree blob inside the image'
echo ' These targets support board with firmware that does not'
echo ' support passing a device tree directly. Replace <dt> with the'
- echo ' name of a dts file from the arch/$(ARCH)/boot/dts/ directory'
+ echo ' name of a dts file from the arch/powerpc/boot/dts/ directory'
echo ' (minus the .dts extension).'
echo
$(foreach cfg,$(generated_configs),
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
index d552044c5afc..aa5152ca8120 100644
--- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -367,45 +367,46 @@
reg = <0xf0000 0x1000>;
interrupts = <18 2 0 0>;
fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x30061>;
- fsl,tmu-calibration = <0x00000000 0x0000000f
- 0x00000001 0x00000017
- 0x00000002 0x0000001e
- 0x00000003 0x00000026
- 0x00000004 0x0000002e
- 0x00000005 0x00000035
- 0x00000006 0x0000003d
- 0x00000007 0x00000044
- 0x00000008 0x0000004c
- 0x00000009 0x00000053
- 0x0000000a 0x0000005b
- 0x0000000b 0x00000064
-
- 0x00010000 0x00000011
- 0x00010001 0x0000001c
- 0x00010002 0x00000024
- 0x00010003 0x0000002b
- 0x00010004 0x00000034
- 0x00010005 0x00000039
- 0x00010006 0x00000042
- 0x00010007 0x0000004c
- 0x00010008 0x00000051
- 0x00010009 0x0000005a
- 0x0001000a 0x00000063
-
- 0x00020000 0x00000013
- 0x00020001 0x00000019
- 0x00020002 0x00000024
- 0x00020003 0x0000002c
- 0x00020004 0x00000035
- 0x00020005 0x0000003d
- 0x00020006 0x00000046
- 0x00020007 0x00000050
- 0x00020008 0x00000059
-
- 0x00030000 0x00000002
- 0x00030001 0x0000000d
- 0x00030002 0x00000019
- 0x00030003 0x00000024>;
+ fsl,tmu-calibration =
+ <0x00000000 0x0000000f>,
+ <0x00000001 0x00000017>,
+ <0x00000002 0x0000001e>,
+ <0x00000003 0x00000026>,
+ <0x00000004 0x0000002e>,
+ <0x00000005 0x00000035>,
+ <0x00000006 0x0000003d>,
+ <0x00000007 0x00000044>,
+ <0x00000008 0x0000004c>,
+ <0x00000009 0x00000053>,
+ <0x0000000a 0x0000005b>,
+ <0x0000000b 0x00000064>,
+
+ <0x00010000 0x00000011>,
+ <0x00010001 0x0000001c>,
+ <0x00010002 0x00000024>,
+ <0x00010003 0x0000002b>,
+ <0x00010004 0x00000034>,
+ <0x00010005 0x00000039>,
+ <0x00010006 0x00000042>,
+ <0x00010007 0x0000004c>,
+ <0x00010008 0x00000051>,
+ <0x00010009 0x0000005a>,
+ <0x0001000a 0x00000063>,
+
+ <0x00020000 0x00000013>,
+ <0x00020001 0x00000019>,
+ <0x00020002 0x00000024>,
+ <0x00020003 0x0000002c>,
+ <0x00020004 0x00000035>,
+ <0x00020005 0x0000003d>,
+ <0x00020006 0x00000046>,
+ <0x00020007 0x00000050>,
+ <0x00020008 0x00000059>,
+
+ <0x00030000 0x00000002>,
+ <0x00030001 0x0000000d>,
+ <0x00030002 0x00000019>,
+ <0x00030003 0x00000024>;
#thermal-sensor-cells = <1>;
};
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index ad0ab33336b8..776788623204 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -447,41 +447,42 @@
reg = <0xf0000 0x1000>;
interrupts = <18 2 0 0>;
fsl,tmu-range = <0xa0000 0x90026 0x8004a 0x1006a>;
- fsl,tmu-calibration = <0x00000000 0x00000025
- 0x00000001 0x00000028
- 0x00000002 0x0000002d
- 0x00000003 0x00000031
- 0x00000004 0x00000036
- 0x00000005 0x0000003a
- 0x00000006 0x00000040
- 0x00000007 0x00000044
- 0x00000008 0x0000004a
- 0x00000009 0x0000004f
- 0x0000000a 0x00000054
-
- 0x00010000 0x0000000d
- 0x00010001 0x00000013
- 0x00010002 0x00000019
- 0x00010003 0x0000001f
- 0x00010004 0x00000025
- 0x00010005 0x0000002d
- 0x00010006 0x00000033
- 0x00010007 0x00000043
- 0x00010008 0x0000004b
- 0x00010009 0x00000053
-
- 0x00020000 0x00000010
- 0x00020001 0x00000017
- 0x00020002 0x0000001f
- 0x00020003 0x00000029
- 0x00020004 0x00000031
- 0x00020005 0x0000003c
- 0x00020006 0x00000042
- 0x00020007 0x0000004d
- 0x00020008 0x00000056
-
- 0x00030000 0x00000012
- 0x00030001 0x0000001d>;
+ fsl,tmu-calibration =
+ <0x00000000 0x00000025>,
+ <0x00000001 0x00000028>,
+ <0x00000002 0x0000002d>,
+ <0x00000003 0x00000031>,
+ <0x00000004 0x00000036>,
+ <0x00000005 0x0000003a>,
+ <0x00000006 0x00000040>,
+ <0x00000007 0x00000044>,
+ <0x00000008 0x0000004a>,
+ <0x00000009 0x0000004f>,
+ <0x0000000a 0x00000054>,
+
+ <0x00010000 0x0000000d>,
+ <0x00010001 0x00000013>,
+ <0x00010002 0x00000019>,
+ <0x00010003 0x0000001f>,
+ <0x00010004 0x00000025>,
+ <0x00010005 0x0000002d>,
+ <0x00010006 0x00000033>,
+ <0x00010007 0x00000043>,
+ <0x00010008 0x0000004b>,
+ <0x00010009 0x00000053>,
+
+ <0x00020000 0x00000010>,
+ <0x00020001 0x00000017>,
+ <0x00020002 0x0000001f>,
+ <0x00020003 0x00000029>,
+ <0x00020004 0x00000031>,
+ <0x00020005 0x0000003c>,
+ <0x00020006 0x00000042>,
+ <0x00020007 0x0000004d>,
+ <0x00020008 0x00000056>,
+
+ <0x00030000 0x00000012>,
+ <0x00030001 0x0000001d>;
#thermal-sensor-cells = <1>;
};
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 6e7b9e8fd225..544a65fda77b 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -92,6 +92,7 @@ CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZONE_DEVICE=y
CONFIG_NET=y
CONFIG_PACKET=y
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 2b175ddf82f0..aa8bb0208bcc 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -24,6 +24,7 @@ CONFIG_PS3_VRAM=m
CONFIG_PS3_LPM=m
# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
CONFIG_KEXEC=y
+# CONFIG_PPC64_BIG_ENDIAN_ELF_ABI_V2 is not set
CONFIG_PPC_4K_PAGES=y
CONFIG_SCHED_SMT=y
CONFIG_PM=y
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index cb77eddca54b..927d585652bc 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -17,12 +17,6 @@
#define _PAGE_EXEC 0x00001 /* execute permission */
#define _PAGE_WRITE 0x00002 /* write access allowed */
#define _PAGE_READ 0x00004 /* read access allowed */
-#define _PAGE_NA _PAGE_PRIVILEGED
-#define _PAGE_NAX _PAGE_EXEC
-#define _PAGE_RO _PAGE_READ
-#define _PAGE_ROX (_PAGE_READ | _PAGE_EXEC)
-#define _PAGE_RW (_PAGE_READ | _PAGE_WRITE)
-#define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
#define _PAGE_PRIVILEGED 0x00008 /* kernel access only */
#define _PAGE_SAO 0x00010 /* Strong access order */
#define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */
@@ -532,8 +526,8 @@ static inline bool pte_user(pte_t pte)
static inline bool pte_access_permitted(pte_t pte, bool write)
{
/*
- * _PAGE_READ is needed for any access and will be
- * cleared for PROT_NONE
+ * _PAGE_READ is needed for any access and will be cleared for
+ * PROT_NONE. Execute-only mapping via PROT_EXEC also returns false.
*/
if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
return false;
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index 1950c1b825b4..fd642b729775 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -158,11 +158,6 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
*/
}
-static inline bool __pte_protnone(unsigned long pte)
-{
- return (pte & (pgprot_val(PAGE_NONE) | _PAGE_RWX)) == pgprot_val(PAGE_NONE);
-}
-
static inline bool __pte_flags_need_flush(unsigned long oldval,
unsigned long newval)
{
@@ -179,8 +174,8 @@ static inline bool __pte_flags_need_flush(unsigned long oldval,
/*
* We do not expect kernel mappings or non-PTEs or not-present PTEs.
*/
- VM_WARN_ON_ONCE(!__pte_protnone(oldval) && oldval & _PAGE_PRIVILEGED);
- VM_WARN_ON_ONCE(!__pte_protnone(newval) && newval & _PAGE_PRIVILEGED);
+ VM_WARN_ON_ONCE(oldval & _PAGE_PRIVILEGED);
+ VM_WARN_ON_ONCE(newval & _PAGE_PRIVILEGED);
VM_WARN_ON_ONCE(!(oldval & _PAGE_PTE));
VM_WARN_ON_ONCE(!(newval & _PAGE_PTE));
VM_WARN_ON_ONCE(!(oldval & _PAGE_PRESENT));
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 9e5a39b6a311..1ebd2ca97f12 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -25,7 +25,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
addr += MCOUNT_INSN_SIZE;
- return addr;
+ return addr;
}
unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index ddb99e982917..a41e542ba94d 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -349,7 +349,16 @@
#define H_GET_ENERGY_SCALE_INFO 0x450
#define H_PKS_SIGNED_UPDATE 0x454
#define H_WATCHDOG 0x45C
-#define MAX_HCALL_OPCODE H_WATCHDOG
+#define H_GUEST_GET_CAPABILITIES 0x460
+#define H_GUEST_SET_CAPABILITIES 0x464
+#define H_GUEST_CREATE 0x470
+#define H_GUEST_CREATE_VCPU 0x474
+#define H_GUEST_GET_STATE 0x478
+#define H_GUEST_SET_STATE 0x47C
+#define H_GUEST_RUN_VCPU 0x480
+#define H_GUEST_COPY_MEMORY 0x484
+#define H_GUEST_DELETE 0x488
+#define MAX_HCALL_OPCODE H_GUEST_DELETE
/* Scope args for H_SCM_UNBIND_ALL */
#define H_UNBIND_SCOPE_ALL (0x1)
@@ -393,15 +402,6 @@
#define H_ENTER_NESTED 0xF804
#define H_TLB_INVALIDATE 0xF808
#define H_COPY_TOFROM_GUEST 0xF80C
-#define H_GUEST_GET_CAPABILITIES 0x460
-#define H_GUEST_SET_CAPABILITIES 0x464
-#define H_GUEST_CREATE 0x470
-#define H_GUEST_CREATE_VCPU 0x474
-#define H_GUEST_GET_STATE 0x478
-#define H_GUEST_SET_STATE 0x47C
-#define H_GUEST_RUN_VCPU 0x480
-#define H_GUEST_COPY_MEMORY 0x484
-#define H_GUEST_DELETE 0x488
/* Flags for H_SVM_PAGE_IN */
#define H_PAGE_IN_SHARED 0x1
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4f527d09c92b..3e1e2a698c9e 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -302,6 +302,7 @@ void kvmhv_nested_exit(void);
void kvmhv_vm_nested_init(struct kvm *kvm);
long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu);
+void kvmhv_flush_lpid(u64 lpid);
void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1);
void kvmhv_release_all_nested(struct kvm *kvm);
long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
@@ -593,13 +594,17 @@ static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \
KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB)
-KVMPPC_BOOK3S_VCORE_ACCESSOR(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR)
KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
+
+static inline u64 kvmppc_get_tb_offset(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.vcore->tb_offset;
+}
static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
{
- WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB) < 0);
return vcpu->arch.dec_expires;
}
@@ -607,7 +612,6 @@ static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
static inline void kvmppc_set_dec_expires(struct kvm_vcpu *vcpu, u64 val)
{
vcpu->arch.dec_expires = val;
- WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB);
}
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 2477021bff54..d8729ec81ca0 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -682,6 +682,7 @@ void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *i
int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit);
int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1);
int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu);
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa);
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h
index b88d1d2cf304..b71b9582e754 100644
--- a/arch/powerpc/include/asm/linkage.h
+++ b/arch/powerpc/include/asm/linkage.h
@@ -4,9 +4,6 @@
#include <asm/types.h>
-#define __ALIGN .align 2
-#define __ALIGN_STR ".align 2"
-
#ifdef CONFIG_PPC64_ELF_ABI_V1
#define cond_syscall(x) \
asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n" \
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 52cc25864a1b..d8b7e246a32f 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -412,5 +412,9 @@ extern void *abatron_pteptrs[2];
#include <asm/nohash/mmu.h>
#endif
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
+#endif
+
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_MMU_H_ */
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 4c6c6dbd182f..da827d2d0866 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -42,14 +42,6 @@ u64 memory_hotplug_max(void);
#else
#define memory_hotplug_max() memblock_end_of_DRAM()
#endif /* CONFIG_NUMA */
-#ifdef CONFIG_FA_DUMP
-#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
-#endif
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end,
- int nid, pgprot_t prot);
-#endif
#endif /* __KERNEL__ */
#endif /* _ASM_MMZONE_H_ */
diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h
index f5fdbd8ae9db..0dbbff59101d 100644
--- a/arch/powerpc/include/asm/papr-sysparm.h
+++ b/arch/powerpc/include/asm/papr-sysparm.h
@@ -2,8 +2,10 @@
#ifndef _ASM_POWERPC_PAPR_SYSPARM_H
#define _ASM_POWERPC_PAPR_SYSPARM_H
+#include <uapi/asm/papr-sysparm.h>
+
typedef struct {
- const u32 token;
+ u32 token;
} papr_sysparm_t;
#define mk_papr_sysparm(x_) ((papr_sysparm_t){ .token = x_, })
@@ -20,11 +22,14 @@ typedef struct {
#define PAPR_SYSPARM_TLB_BLOCK_INVALIDATE_ATTRS mk_papr_sysparm(50)
#define PAPR_SYSPARM_LPAR_NAME mk_papr_sysparm(55)
-enum {
- PAPR_SYSPARM_MAX_INPUT = 1024,
- PAPR_SYSPARM_MAX_OUTPUT = 4000,
-};
-
+/**
+ * struct papr_sysparm_buf - RTAS work area layout for system parameter functions.
+ *
+ * This is the memory layout of the buffers passed to/from
+ * ibm,get-system-parameter and ibm,set-system-parameter. It is
+ * distinct from the papr_sysparm_io_block structure that is passed
+ * between user space and the kernel.
+ */
struct papr_sysparm_buf {
__be16 len;
char val[PAPR_SYSPARM_MAX_OUTPUT];
diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h
index ac4279208d63..b78b82d66057 100644
--- a/arch/powerpc/include/asm/paravirt.h
+++ b/arch/powerpc/include/asm/paravirt.h
@@ -76,6 +76,17 @@ static inline bool is_vcpu_idle(int vcpu)
{
return lppaca_of(vcpu).idle;
}
+
+static inline bool vcpu_is_dispatched(int vcpu)
+{
+ /*
+ * This is the yield_count. An "odd" value (low bit on) means that
+ * the processor is yielded (either because of an OS yield or a
+ * hypervisor preempt). An even value implies that the processor is
+ * currently executing.
+ */
+ return (!(yield_count_of(vcpu) & 1));
+}
#else
static inline bool is_shared_processor(void)
{
@@ -109,6 +120,10 @@ static inline bool is_vcpu_idle(int vcpu)
{
return false;
}
+static inline bool vcpu_is_dispatched(int vcpu)
+{
+ return true;
+}
#endif
#define vcpu_is_preempted vcpu_is_preempted
@@ -134,12 +149,12 @@ static inline bool vcpu_is_preempted(int cpu)
* If the hypervisor has dispatched the target CPU on a physical
* processor, then the target CPU is definitely not preempted.
*/
- if (!(yield_count_of(cpu) & 1))
+ if (vcpu_is_dispatched(cpu))
return false;
/*
- * If the target CPU has yielded to Hypervisor but OS has not
- * requested idle then the target CPU is definitely preempted.
+ * if the target CPU is not dispatched and the guest OS
+ * has not marked the CPU idle, then it is hypervisor preempted.
*/
if (!is_vcpu_idle(cpu))
return true;
@@ -166,7 +181,7 @@ static inline bool vcpu_is_preempted(int cpu)
/*
* The PowerVM hypervisor dispatches VMs on a whole core
- * basis. So we know that a thread sibling of the local CPU
+ * basis. So we know that a thread sibling of the executing CPU
* cannot have been preempted by the hypervisor, even if it
* has called H_CONFER, which will set the yield bit.
*/
@@ -174,15 +189,17 @@ static inline bool vcpu_is_preempted(int cpu)
return false;
/*
- * If any of the threads of the target CPU's core are not
- * preempted or ceded, then consider target CPU to be
- * non-preempted.
+ * The specific target CPU was marked by guest OS as idle, but
+ * then also check all other cpus in the core for PowerVM
+ * because it does core scheduling and one of the vcpu
+ * of the core getting preempted by hypervisor implies
+ * other vcpus can also be considered preempted.
*/
first_cpu = cpu_first_thread_sibling(cpu);
for (i = first_cpu; i < first_cpu + threads_per_core; i++) {
if (i == cpu)
continue;
- if (!(yield_count_of(i) & 1))
+ if (vcpu_is_dispatched(i))
return false;
if (!is_vcpu_idle(i))
return true;
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index d9fcff575027..ce2b1b5eebdd 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -35,6 +35,9 @@ extern void init_pci_config_tokens (void);
extern unsigned long get_phb_buid (struct device_node *);
extern int rtas_setup_phb(struct pci_controller *phb);
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val);
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val);
+
#ifdef CONFIG_EEH
void eeh_addr_cache_insert_dev(struct pci_dev *dev);
@@ -44,8 +47,6 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity);
int eeh_pci_enable(struct eeh_pe *pe, int function);
int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed);
void eeh_save_bars(struct eeh_dev *edev);
-int rtas_write_config(struct pci_dn *, int where, int size, u32 val);
-int rtas_read_config(struct pci_dn *, int where, int size, u32 *val);
void eeh_pe_state_mark(struct eeh_pe *pe, int state);
void eeh_pe_mark_isolated(struct eeh_pe *pe);
void eeh_pe_state_clear(struct eeh_pe *pe, int state, bool include_passed);
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index a5f36546a052..d13d8fdc3411 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -514,4 +514,10 @@ u64 ps3_get_spe_id(void *arg);
void ps3_early_mm_init(void);
+#ifdef CONFIG_PPC_EARLY_DEBUG_PS3GELIC
+void udbg_shutdown_ps3gelic(void);
+#else
+static inline void udbg_shutdown_ps3gelic(void) {}
+#endif
+
#endif
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4ae4ab9090a2..7fd09f25452d 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1361,6 +1361,7 @@
#define PVR_POWER8E 0x004B
#define PVR_POWER8NVL 0x004C
#define PVR_POWER8 0x004D
+#define PVR_HX_C2000 0x0066
#define PVR_POWER9 0x004E
#define PVR_POWER10 0x0080
#define PVR_BE 0x0070
diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h
deleted file mode 100644
index 74fba29e9491..000000000000
--- a/arch/powerpc/include/asm/reg_a2.h
+++ /dev/null
@@ -1,154 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Register definitions specific to the A2 core
- *
- * Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
- */
-
-#ifndef __ASM_POWERPC_REG_A2_H__
-#define __ASM_POWERPC_REG_A2_H__
-
-#include <asm/asm-const.h>
-
-#define SPRN_TENSR 0x1b5
-#define SPRN_TENS 0x1b6 /* Thread ENable Set */
-#define SPRN_TENC 0x1b7 /* Thread ENable Clear */
-
-#define SPRN_A2_CCR0 0x3f0 /* Core Configuration Register 0 */
-#define SPRN_A2_CCR1 0x3f1 /* Core Configuration Register 1 */
-#define SPRN_A2_CCR2 0x3f2 /* Core Configuration Register 2 */
-#define SPRN_MMUCR0 0x3fc /* MMU Control Register 0 */
-#define SPRN_MMUCR1 0x3fd /* MMU Control Register 1 */
-#define SPRN_MMUCR2 0x3fe /* MMU Control Register 2 */
-#define SPRN_MMUCR3 0x3ff /* MMU Control Register 3 */
-
-#define SPRN_IAR 0x372
-
-#define SPRN_IUCR0 0x3f3
-#define IUCR0_ICBI_ACK 0x1000
-
-#define SPRN_XUCR0 0x3f6 /* Execution Unit Config Register 0 */
-
-#define A2_IERAT_SIZE 16
-#define A2_DERAT_SIZE 32
-
-/* A2 MMUCR0 bits */
-#define MMUCR0_ECL 0x80000000 /* Extended Class for TLB fills */
-#define MMUCR0_TID_NZ 0x40000000 /* TID is non-zero */
-#define MMUCR0_TS 0x10000000 /* Translation space for TLB fills */
-#define MMUCR0_TGS 0x20000000 /* Guest space for TLB fills */
-#define MMUCR0_TLBSEL 0x0c000000 /* TLB or ERAT target for TLB fills */
-#define MMUCR0_TLBSEL_U 0x00000000 /* TLBSEL = UTLB */
-#define MMUCR0_TLBSEL_I 0x08000000 /* TLBSEL = I-ERAT */
-#define MMUCR0_TLBSEL_D 0x0c000000 /* TLBSEL = D-ERAT */
-#define MMUCR0_LOCKSRSH 0x02000000 /* Use TLB lock on tlbsx. */
-#define MMUCR0_TID_MASK 0x000000ff /* TID field */
-
-/* A2 MMUCR1 bits */
-#define MMUCR1_IRRE 0x80000000 /* I-ERAT round robin enable */
-#define MMUCR1_DRRE 0x40000000 /* D-ERAT round robin enable */
-#define MMUCR1_REE 0x20000000 /* Reference Exception Enable*/
-#define MMUCR1_CEE 0x10000000 /* Change exception enable */
-#define MMUCR1_CSINV_ALL 0x00000000 /* Inval ERAT on all CS evts */
-#define MMUCR1_CSINV_NISYNC 0x04000000 /* Inval ERAT on all ex isync*/
-#define MMUCR1_CSINV_NEVER 0x0c000000 /* Don't inval ERAT on CS */
-#define MMUCR1_ICTID 0x00080000 /* IERAT class field as TID */
-#define MMUCR1_ITTID 0x00040000 /* IERAT thdid field as TID */
-#define MMUCR1_DCTID 0x00020000 /* DERAT class field as TID */
-#define MMUCR1_DTTID 0x00010000 /* DERAT thdid field as TID */
-#define MMUCR1_DCCD 0x00008000 /* DERAT class ignore */
-#define MMUCR1_TLBWE_BINV 0x00004000 /* back invalidate on tlbwe */
-
-/* A2 MMUCR2 bits */
-#define MMUCR2_PSSEL_SHIFT 4
-
-/* A2 MMUCR3 bits */
-#define MMUCR3_THID 0x0000000f /* Thread ID */
-
-/* *** ERAT TLB bits definitions */
-#define TLB0_EPN_MASK ASM_CONST(0xfffffffffffff000)
-#define TLB0_CLASS_MASK ASM_CONST(0x0000000000000c00)
-#define TLB0_CLASS_00 ASM_CONST(0x0000000000000000)
-#define TLB0_CLASS_01 ASM_CONST(0x0000000000000400)
-#define TLB0_CLASS_10 ASM_CONST(0x0000000000000800)
-#define TLB0_CLASS_11 ASM_CONST(0x0000000000000c00)
-#define TLB0_V ASM_CONST(0x0000000000000200)
-#define TLB0_X ASM_CONST(0x0000000000000100)
-#define TLB0_SIZE_MASK ASM_CONST(0x00000000000000f0)
-#define TLB0_SIZE_4K ASM_CONST(0x0000000000000010)
-#define TLB0_SIZE_64K ASM_CONST(0x0000000000000030)
-#define TLB0_SIZE_1M ASM_CONST(0x0000000000000050)
-#define TLB0_SIZE_16M ASM_CONST(0x0000000000000070)
-#define TLB0_SIZE_1G ASM_CONST(0x00000000000000a0)
-#define TLB0_THDID_MASK ASM_CONST(0x000000000000000f)
-#define TLB0_THDID_0 ASM_CONST(0x0000000000000001)
-#define TLB0_THDID_1 ASM_CONST(0x0000000000000002)
-#define TLB0_THDID_2 ASM_CONST(0x0000000000000004)
-#define TLB0_THDID_3 ASM_CONST(0x0000000000000008)
-#define TLB0_THDID_ALL ASM_CONST(0x000000000000000f)
-
-#define TLB1_RESVATTR ASM_CONST(0x00f0000000000000)
-#define TLB1_U0 ASM_CONST(0x0008000000000000)
-#define TLB1_U1 ASM_CONST(0x0004000000000000)
-#define TLB1_U2 ASM_CONST(0x0002000000000000)
-#define TLB1_U3 ASM_CONST(0x0001000000000000)
-#define TLB1_R ASM_CONST(0x0000800000000000)
-#define TLB1_C ASM_CONST(0x0000400000000000)
-#define TLB1_RPN_MASK ASM_CONST(0x000003fffffff000)
-#define TLB1_W ASM_CONST(0x0000000000000800)
-#define TLB1_I ASM_CONST(0x0000000000000400)
-#define TLB1_M ASM_CONST(0x0000000000000200)
-#define TLB1_G ASM_CONST(0x0000000000000100)
-#define TLB1_E ASM_CONST(0x0000000000000080)
-#define TLB1_VF ASM_CONST(0x0000000000000040)
-#define TLB1_UX ASM_CONST(0x0000000000000020)
-#define TLB1_SX ASM_CONST(0x0000000000000010)
-#define TLB1_UW ASM_CONST(0x0000000000000008)
-#define TLB1_SW ASM_CONST(0x0000000000000004)
-#define TLB1_UR ASM_CONST(0x0000000000000002)
-#define TLB1_SR ASM_CONST(0x0000000000000001)
-
-/* A2 erativax attributes definitions */
-#define ERATIVAX_RS_IS_ALL 0x000
-#define ERATIVAX_RS_IS_TID 0x040
-#define ERATIVAX_RS_IS_CLASS 0x080
-#define ERATIVAX_RS_IS_FULLMATCH 0x0c0
-#define ERATIVAX_CLASS_00 0x000
-#define ERATIVAX_CLASS_01 0x010
-#define ERATIVAX_CLASS_10 0x020
-#define ERATIVAX_CLASS_11 0x030
-#define ERATIVAX_PSIZE_4K (TLB_PSIZE_4K >> 1)
-#define ERATIVAX_PSIZE_64K (TLB_PSIZE_64K >> 1)
-#define ERATIVAX_PSIZE_1M (TLB_PSIZE_1M >> 1)
-#define ERATIVAX_PSIZE_16M (TLB_PSIZE_16M >> 1)
-#define ERATIVAX_PSIZE_1G (TLB_PSIZE_1G >> 1)
-
-/* A2 eratilx attributes definitions */
-#define ERATILX_T_ALL 0
-#define ERATILX_T_TID 1
-#define ERATILX_T_TGS 2
-#define ERATILX_T_FULLMATCH 3
-#define ERATILX_T_CLASS0 4
-#define ERATILX_T_CLASS1 5
-#define ERATILX_T_CLASS2 6
-#define ERATILX_T_CLASS3 7
-
-/* XUCR0 bits */
-#define XUCR0_TRACE_UM_T0 0x40000000 /* Thread 0 */
-#define XUCR0_TRACE_UM_T1 0x20000000 /* Thread 1 */
-#define XUCR0_TRACE_UM_T2 0x10000000 /* Thread 2 */
-#define XUCR0_TRACE_UM_T3 0x08000000 /* Thread 3 */
-
-/* A2 CCR0 register */
-#define A2_CCR0_PME_DISABLED 0x00000000
-#define A2_CCR0_PME_SLEEP 0x40000000
-#define A2_CCR0_PME_RVW 0x80000000
-#define A2_CCR0_PME_DISABLED2 0xc0000000
-
-/* A2 CCR2 register */
-#define A2_CCR2_ERAT_ONLY_MODE 0x00000001
-#define A2_CCR2_ENABLE_ICSWX 0x00000002
-#define A2_CCR2_ENABLE_PC 0x20000000
-#define A2_CCR2_ENABLE_TRACE 0x40000000
-
-#endif /* __ASM_POWERPC_REG_A2_H__ */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index c697c3c74694..9bb2210c8d44 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -3,6 +3,7 @@
#define _POWERPC_RTAS_H
#ifdef __KERNEL__
+#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <asm/page.h>
#include <asm/rtas-types.h>
@@ -201,12 +202,25 @@ typedef struct {
/* Memory set aside for sys_rtas to use with calls that need a work area. */
#define RTAS_USER_REGION_SIZE (64 * 1024)
-/* RTAS return status codes */
-#define RTAS_HARDWARE_ERROR -1 /* Hardware Error */
-#define RTAS_BUSY -2 /* RTAS Busy */
-#define RTAS_INVALID_PARAMETER -3 /* Invalid indicator/domain/sensor etc. */
-#define RTAS_EXTENDED_DELAY_MIN 9900
-#define RTAS_EXTENDED_DELAY_MAX 9905
+/*
+ * Common RTAS function return values, derived from the table "RTAS
+ * Status Word Values" in PAPR+ v2.13 7.2.8: "Return Codes". If a
+ * function can return a value in this table then generally it has the
+ * meaning listed here. More extended commentary in the documentation
+ * for rtas_call().
+ *
+ * RTAS functions may use negative and positive numbers not in this
+ * set for function-specific error and success conditions,
+ * respectively.
+ */
+#define RTAS_SUCCESS 0 /* Success. */
+#define RTAS_HARDWARE_ERROR -1 /* Hardware or other unspecified error. */
+#define RTAS_BUSY -2 /* Retry immediately. */
+#define RTAS_INVALID_PARAMETER -3 /* Invalid indicator/domain/sensor etc. */
+#define RTAS_UNEXPECTED_STATE_CHANGE -7 /* Seems limited to EEH and slot reset. */
+#define RTAS_EXTENDED_DELAY_MIN 9900 /* Retry after delaying for ~1ms. */
+#define RTAS_EXTENDED_DELAY_MAX 9905 /* Retry after delaying for ~100s. */
+#define RTAS_ML_ISOLATION_ERROR -9000 /* Multi-level isolation error. */
/* statuses specific to ibm,suspend-me */
#define RTAS_SUSPEND_ABORTED 9000 /* Suspension aborted */
@@ -268,7 +282,7 @@ typedef struct {
#define RTAS_TYPE_DEALLOC 0xE3
#define RTAS_TYPE_DUMP 0xE4
#define RTAS_TYPE_HOTPLUG 0xE5
-/* I don't add PowerMGM events right now, this is a different topic */
+/* I don't add PowerMGM events right now, this is a different topic */
#define RTAS_TYPE_PMGM_POWER_SW_ON 0x60
#define RTAS_TYPE_PMGM_POWER_SW_OFF 0x61
#define RTAS_TYPE_PMGM_LID_OPEN 0x62
@@ -408,44 +422,41 @@ static inline bool rtas_function_implemented(const rtas_fn_handle_t handle)
{
return rtas_function_token(handle) != RTAS_UNKNOWN_SERVICE;
}
-extern int rtas_token(const char *service);
-extern int rtas_service_present(const char *service);
-extern int rtas_call(int token, int, int, int *, ...);
+int rtas_token(const char *service);
+int rtas_call(int token, int nargs, int nret, int *outputs, ...);
void rtas_call_unlocked(struct rtas_args *args, int token, int nargs,
int nret, ...);
-extern void __noreturn rtas_restart(char *cmd);
-extern void rtas_power_off(void);
-extern void __noreturn rtas_halt(void);
-extern void rtas_os_term(char *str);
+void __noreturn rtas_restart(char *cmd);
+void rtas_power_off(void);
+void __noreturn rtas_halt(void);
+void rtas_os_term(char *str);
void rtas_activate_firmware(void);
-extern int rtas_get_sensor(int sensor, int index, int *state);
-extern int rtas_get_sensor_fast(int sensor, int index, int *state);
-extern int rtas_get_power_level(int powerdomain, int *level);
-extern int rtas_set_power_level(int powerdomain, int level, int *setlevel);
-extern bool rtas_indicator_present(int token, int *maxindex);
-extern int rtas_set_indicator(int indicator, int index, int new_value);
-extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
-extern void rtas_progress(char *s, unsigned short hex);
+int rtas_get_sensor(int sensor, int index, int *state);
+int rtas_get_sensor_fast(int sensor, int index, int *state);
+int rtas_get_power_level(int powerdomain, int *level);
+int rtas_set_power_level(int powerdomain, int level, int *setlevel);
+bool rtas_indicator_present(int token, int *maxindex);
+int rtas_set_indicator(int indicator, int index, int new_value);
+int rtas_set_indicator_fast(int indicator, int index, int new_value);
+void rtas_progress(char *s, unsigned short hex);
int rtas_ibm_suspend_me(int *fw_status);
int rtas_error_rc(int rtas_rc);
struct rtc_time;
-extern time64_t rtas_get_boot_time(void);
-extern void rtas_get_rtc_time(struct rtc_time *rtc_time);
-extern int rtas_set_rtc_time(struct rtc_time *rtc_time);
+time64_t rtas_get_boot_time(void);
+void rtas_get_rtc_time(struct rtc_time *rtc_time);
+int rtas_set_rtc_time(struct rtc_time *rtc_time);
-extern unsigned int rtas_busy_delay_time(int status);
+unsigned int rtas_busy_delay_time(int status);
bool rtas_busy_delay(int status);
-extern int early_init_dt_scan_rtas(unsigned long node,
- const char *uname, int depth, void *data);
+int early_init_dt_scan_rtas(unsigned long node, const char *uname, int depth, void *data);
-extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
+void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
#ifdef CONFIG_PPC_PSERIES
extern time64_t last_rtas_event;
-extern int clobbering_unread_rtas_event(void);
-extern void post_mobility_fixup(void);
+int clobbering_unread_rtas_event(void);
int rtas_syscall_dispatch_ibm_suspend_me(u64 handle);
#else
static inline int clobbering_unread_rtas_event(void) { return 0; }
@@ -456,14 +467,14 @@ static inline int rtas_syscall_dispatch_ibm_suspend_me(u64 handle)
#endif
#ifdef CONFIG_PPC_RTAS_DAEMON
-extern void rtas_cancel_event_scan(void);
+void rtas_cancel_event_scan(void);
#else
static inline void rtas_cancel_event_scan(void) { }
#endif
/* Error types logged. */
#define ERR_FLAG_ALREADY_LOGGED 0x0
-#define ERR_FLAG_BOOT 0x1 /* log was pulled from NVRAM on boot */
+#define ERR_FLAG_BOOT 0x1 /* log was pulled from NVRAM on boot */
#define ERR_TYPE_RTAS_LOG 0x2 /* from rtas event-scan */
#define ERR_TYPE_KERNEL_PANIC 0x4 /* from die()/panic() */
#define ERR_TYPE_KERNEL_PANIC_GZ 0x8 /* ditto, compressed */
@@ -473,7 +484,7 @@ static inline void rtas_cancel_event_scan(void) { }
(ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC | ERR_TYPE_KERNEL_PANIC_GZ)
#define RTAS_DEBUG KERN_DEBUG "RTAS: "
-
+
#define RTAS_ERROR_LOG_MAX 2048
/*
@@ -481,7 +492,7 @@ static inline void rtas_cancel_event_scan(void) { }
* for all rtas calls that require an error buffer argument.
* This includes 'check-exception' and 'rtas-last-error'.
*/
-extern int rtas_get_error_log_max(void);
+int rtas_get_error_log_max(void);
/* Event Scan Parameters */
#define EVENT_SCAN_ALL_EVENTS 0xf0000000
@@ -502,6 +513,8 @@ extern char rtas_data_buf[RTAS_DATA_BUF_SIZE];
/* RMO buffer reserved for user-space RTAS use */
extern unsigned long rtas_rmo_buf;
+extern struct mutex rtas_ibm_get_vpd_lock;
+
#define GLOBAL_INTERRUPT_QUEUE 9005
/**
@@ -520,8 +533,8 @@ static inline u32 rtas_config_addr(int busno, int devfn, int reg)
(devfn << 8) | (reg & 0xff);
}
-extern void rtas_give_timebase(void);
-extern void rtas_take_timebase(void);
+void rtas_give_timebase(void);
+void rtas_take_timebase(void);
#ifdef CONFIG_PPC_RTAS
static inline int page_is_rtas_user_buf(unsigned long pfn)
@@ -534,7 +547,7 @@ static inline int page_is_rtas_user_buf(unsigned long pfn)
/* Not the best place to put pSeries_coalesce_init, will be fixed when we
* move some of the rtas suspend-me stuff to pseries */
-extern void pSeries_coalesce_init(void);
+void pSeries_coalesce_init(void);
void rtas_initialize(void);
#else
static inline int page_is_rtas_user_buf(unsigned long pfn) { return 0;}
@@ -542,8 +555,6 @@ static inline void pSeries_coalesce_init(void) { }
static inline void rtas_initialize(void) { }
#endif
-extern int call_rtas(const char *, int, int, unsigned long *, ...);
-
#ifdef CONFIG_HV_PERF_CTRS
void read_24x7_sys_info(void);
#else
diff --git a/arch/powerpc/include/uapi/asm/papr-miscdev.h b/arch/powerpc/include/uapi/asm/papr-miscdev.h
new file mode 100644
index 000000000000..49a2a270b7f3
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-miscdev.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_MISCDEV_H_
+#define _UAPI_PAPR_MISCDEV_H_
+
+enum {
+ PAPR_MISCDEV_IOC_ID = 0xb2,
+};
+
+#endif /* _UAPI_PAPR_MISCDEV_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h
new file mode 100644
index 000000000000..9f9a0f267ea5
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_SYSPARM_H_
+#define _UAPI_PAPR_SYSPARM_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+enum {
+ PAPR_SYSPARM_MAX_INPUT = 1024,
+ PAPR_SYSPARM_MAX_OUTPUT = 4000,
+};
+
+struct papr_sysparm_io_block {
+ __u32 parameter;
+ __u16 length;
+ char data[PAPR_SYSPARM_MAX_OUTPUT];
+};
+
+/**
+ * PAPR_SYSPARM_IOC_GET - Retrieve the value of a PAPR system parameter.
+ *
+ * Uses _IOWR because of one corner case: Retrieving the value of the
+ * "OS Service Entitlement Status" parameter (60) requires the caller
+ * to supply input data (a date string) in the buffer passed to
+ * firmware. So the @length and @data of the incoming
+ * papr_sysparm_io_block are always used to initialize the work area
+ * supplied to ibm,get-system-parameter. No other parameters are known
+ * to parameterize the result this way, and callers are encouraged
+ * (but not required) to zero-initialize @length and @data in the
+ * common case.
+ *
+ * On error the contents of the ioblock are indeterminate.
+ *
+ * Return:
+ * 0: Success; @length is the length of valid data in @data, not to exceed @PAPR_SYSPARM_MAX_OUTPUT.
+ * -EIO: Platform error. (-1)
+ * -EINVAL: Incorrect data length or format. (-9999)
+ * -EPERM: The calling partition is not allowed to access this parameter. (-9002)
+ * -EOPNOTSUPP: Parameter not supported on this platform (-3)
+ */
+#define PAPR_SYSPARM_IOC_GET _IOWR(PAPR_MISCDEV_IOC_ID, 1, struct papr_sysparm_io_block)
+
+/**
+ * PAPR_SYSPARM_IOC_SET - Update the value of a PAPR system parameter.
+ *
+ * The contents of the ioblock are unchanged regardless of success.
+ *
+ * Return:
+ * 0: Success; the parameter has been updated.
+ * -EIO: Platform error. (-1)
+ * -EINVAL: Incorrect data length or format. (-9999)
+ * -EPERM: The calling partition is not allowed to access this parameter. (-9002)
+ * -EOPNOTSUPP: Parameter not supported on this platform (-3)
+ */
+#define PAPR_SYSPARM_IOC_SET _IOW(PAPR_MISCDEV_IOC_ID, 2, struct papr_sysparm_io_block)
+
+#endif /* _UAPI_PAPR_SYSPARM_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-vpd.h b/arch/powerpc/include/uapi/asm/papr-vpd.h
new file mode 100644
index 000000000000..1c88e87cb420
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-vpd.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_VPD_H_
+#define _UAPI_PAPR_VPD_H_
+
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+struct papr_location_code {
+ /*
+ * PAPR+ v2.13 12.3.2.4 Converged Location Code Rules - Length
+ * Restrictions. 79 characters plus nul.
+ */
+ char str[80];
+};
+
+/*
+ * ioctl for /dev/papr-vpd. Returns a VPD handle fd corresponding to
+ * the location code.
+ */
+#define PAPR_VPD_IOC_CREATE_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 0, struct papr_location_code)
+
+#endif /* _UAPI_PAPR_VPD_H_ */
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h
index c370c1b804a9..3ff9757df4c0 100644
--- a/arch/powerpc/kernel/cpu_specs_book3s_64.h
+++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h
@@ -238,6 +238,21 @@ static struct cpu_spec cpu_specs[] __initdata = {
.machine_check_early = __machine_check_early_realmode_p8,
.platform = "power8",
},
+ { /* 2.07-compliant processor, HeXin C2000 processor */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00660000,
+ .cpu_name = "HX-C2000",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
{ /* 3.00-compliant processor, i.e. Power9 "architected" mode */
.pvr_mask = 0xffffffff,
.pvr_value = 0x0f000005,
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index e97a0fd0ae90..6f6801da9dc1 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -20,9 +20,9 @@
#include <asm/setup.h>
#include <asm/cpu_setup.h>
-static struct cpu_spec the_cpu_spec __read_mostly;
+static struct cpu_spec the_cpu_spec __ro_after_init;
-struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
+struct cpu_spec *cur_cpu_spec __ro_after_init = NULL;
EXPORT_SYMBOL(cur_cpu_spec);
/* The platform string corresponding to the real PVR */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 7ab4c8c0f1ab..dcf0591ad3c2 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -14,7 +14,6 @@
#include <asm/cputable.h>
#include <asm/setup.h>
#include <asm/thread_info.h>
-#include <asm/reg_a2.h>
#include <asm/exception-64e.h>
#include <asm/bug.h>
#include <asm/irqflags.h>
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index eddc031c4b95..7e793b503e29 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -18,6 +18,7 @@
#include <linux/kernel.h>
#include <linux/lockdep.h>
#include <linux/memblock.h>
+#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/reboot.h>
@@ -70,14 +71,33 @@ struct rtas_filter {
* ppc64le, and we want to keep it that way. It does
* not make sense for this to be set when @filter
* is NULL.
+ * @lock: Pointer to an optional dedicated per-function mutex. This
+ * should be set for functions that require multiple calls in
+ * sequence to complete a single operation, and such sequences
+ * will disrupt each other if allowed to interleave. Users of
+ * this function are required to hold the associated lock for
+ * the duration of the call sequence. Add an explanatory
+ * comment to the function table entry if setting this member.
*/
struct rtas_function {
s32 token;
const bool banned_for_syscall_on_le:1;
const char * const name;
const struct rtas_filter *filter;
+ struct mutex *lock;
};
+/*
+ * Per-function locks for sequence-based RTAS functions.
+ */
+static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock);
+static DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
+static DEFINE_MUTEX(rtas_ibm_get_indices_lock);
+static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock);
+static DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
+static DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
+DEFINE_MUTEX(rtas_ibm_get_vpd_lock);
+
static struct rtas_function rtas_function_table[] __ro_after_init = {
[RTAS_FNIDX__CHECK_EXCEPTION] = {
.name = "check-exception",
@@ -125,6 +145,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = -1, .size_idx1 = -1,
.buf_idx2 = -1, .size_idx2 = -1,
},
+ /*
+ * PAPR+ as of v2.13 doesn't explicitly impose any
+ * restriction, but this typically requires multiple
+ * calls before success, and there's no reason to
+ * allow sequences to interleave.
+ */
+ .lock = &rtas_ibm_activate_firmware_lock,
},
[RTAS_FNIDX__IBM_CBE_START_PTCAL] = {
.name = "ibm,cbe-start-ptcal",
@@ -196,6 +223,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = 1, .size_idx1 = -1,
.buf_idx2 = -1, .size_idx2 = -1,
},
+ /*
+ * PAPR+ v2.13 R1–7.3.19–3 is explicit that the OS
+ * must not call ibm,get-dynamic-sensor-state with
+ * different inputs until a non-retry status has been
+ * returned.
+ */
+ .lock = &rtas_ibm_get_dynamic_sensor_state_lock,
},
[RTAS_FNIDX__IBM_GET_INDICES] = {
.name = "ibm,get-indices",
@@ -203,6 +237,12 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = 2, .size_idx1 = 3,
.buf_idx2 = -1, .size_idx2 = -1,
},
+ /*
+ * PAPR+ v2.13 R1–7.3.17–2 says that the OS must not
+ * interleave ibm,get-indices call sequences with
+ * different inputs.
+ */
+ .lock = &rtas_ibm_get_indices_lock,
},
[RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY] = {
.name = "ibm,get-rio-topology",
@@ -220,6 +260,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = 0, .size_idx1 = -1,
.buf_idx2 = 1, .size_idx2 = 2,
},
+ /*
+ * PAPR+ v2.13 R1–7.3.20–4 indicates that sequences
+ * should not be allowed to interleave.
+ */
+ .lock = &rtas_ibm_get_vpd_lock,
},
[RTAS_FNIDX__IBM_GET_XIVE] = {
.name = "ibm,get-xive",
@@ -239,6 +284,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = 2, .size_idx1 = 3,
.buf_idx2 = -1, .size_idx2 = -1,
},
+ /*
+ * PAPR+ v2.13 R1–7.3.26–6 says the OS should allow
+ * only one call sequence in progress at a time.
+ */
+ .lock = &rtas_ibm_lpar_perftools_lock,
},
[RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE] = {
.name = "ibm,manage-flash-image",
@@ -277,6 +327,14 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = 0, .size_idx1 = 1,
.buf_idx2 = -1, .size_idx2 = -1,
},
+ /*
+ * This follows a sequence-based pattern similar to
+ * ibm,get-vpd et al. Since PAPR+ restricts
+ * interleaving call sequences for other functions of
+ * this style, assume the restriction applies here,
+ * even though it's not explicit in the spec.
+ */
+ .lock = &rtas_ibm_physical_attestation_lock,
},
[RTAS_FNIDX__IBM_PLATFORM_DUMP] = {
.name = "ibm,platform-dump",
@@ -284,6 +342,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = 4, .size_idx1 = 5,
.buf_idx2 = -1, .size_idx2 = -1,
},
+ /*
+ * PAPR+ v2.13 7.3.3.4.1 indicates that concurrent
+ * sequences of ibm,platform-dump are allowed if they
+ * are operating on different dump tags. So leave the
+ * lock pointer unset for now. This may need
+ * reconsideration if kernel-internal users appear.
+ */
},
[RTAS_FNIDX__IBM_POWER_OFF_UPS] = {
.name = "ibm,power-off-ups",
@@ -326,6 +391,12 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
.buf_idx1 = 2, .size_idx1 = -1,
.buf_idx2 = -1, .size_idx2 = -1,
},
+ /*
+ * PAPR+ v2.13 R1–7.3.18–3 says the OS must not call
+ * this function with different inputs until a
+ * non-retry status has been returned.
+ */
+ .lock = &rtas_ibm_set_dynamic_indicator_lock,
},
[RTAS_FNIDX__IBM_SET_EEH_OPTION] = {
.name = "ibm,set-eeh-option",
@@ -454,6 +525,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
},
};
+#define for_each_rtas_function(funcp) \
+ for (funcp = &rtas_function_table[0]; \
+ funcp < &rtas_function_table[ARRAY_SIZE(rtas_function_table)]; \
+ ++funcp)
+
/*
* Nearly all RTAS calls need to be serialized. All uses of the
* default rtas_args block must hold rtas_lock.
@@ -525,10 +601,10 @@ static DEFINE_XARRAY(rtas_token_to_function_xarray);
static int __init rtas_token_to_function_xarray_init(void)
{
+ const struct rtas_function *func;
int err = 0;
- for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
- const struct rtas_function *func = &rtas_function_table[i];
+ for_each_rtas_function(func) {
const s32 token = func->token;
if (token == RTAS_UNKNOWN_SERVICE)
@@ -544,6 +620,21 @@ static int __init rtas_token_to_function_xarray_init(void)
}
arch_initcall(rtas_token_to_function_xarray_init);
+/*
+ * For use by sys_rtas(), where the token value is provided by user
+ * space and we don't want to warn on failed lookups.
+ */
+static const struct rtas_function *rtas_token_to_function_untrusted(s32 token)
+{
+ return xa_load(&rtas_token_to_function_xarray, token);
+}
+
+/*
+ * Reverse lookup for deriving the function descriptor from a
+ * known-good token value in contexts where the former is not already
+ * available. @token must be valid, e.g. derived from the result of a
+ * prior lookup against the function table.
+ */
static const struct rtas_function *rtas_token_to_function(s32 token)
{
const struct rtas_function *func;
@@ -551,12 +642,22 @@ static const struct rtas_function *rtas_token_to_function(s32 token)
if (WARN_ONCE(token < 0, "invalid token %d", token))
return NULL;
- func = xa_load(&rtas_token_to_function_xarray, token);
-
- if (WARN_ONCE(!func, "unexpected failed lookup for token %d", token))
- return NULL;
+ func = rtas_token_to_function_untrusted(token);
+ if (func)
+ return func;
+ /*
+ * Fall back to linear scan in case the reverse mapping hasn't
+ * been initialized yet.
+ */
+ if (xa_empty(&rtas_token_to_function_xarray)) {
+ for_each_rtas_function(func) {
+ if (func->token == token)
+ return func;
+ }
+ }
- return func;
+ WARN_ONCE(true, "unexpected failed lookup for token %d", token);
+ return NULL;
}
/* This is here deliberately so it's only used in this file */
@@ -570,28 +671,25 @@ static void __do_enter_rtas(struct rtas_args *args)
static void __do_enter_rtas_trace(struct rtas_args *args)
{
- const char *name = NULL;
+ const struct rtas_function *func = rtas_token_to_function(be32_to_cpu(args->token));
- if (args == &rtas_args)
- lockdep_assert_held(&rtas_lock);
/*
- * If the tracepoints that consume the function name aren't
- * active, avoid the lookup.
+ * If there is a per-function lock, it must be held by the
+ * caller.
*/
- if ((trace_rtas_input_enabled() || trace_rtas_output_enabled())) {
- const s32 token = be32_to_cpu(args->token);
- const struct rtas_function *func = rtas_token_to_function(token);
+ if (func->lock)
+ lockdep_assert_held(func->lock);
- name = func->name;
- }
+ if (args == &rtas_args)
+ lockdep_assert_held(&rtas_lock);
- trace_rtas_input(args, name);
+ trace_rtas_input(args, func->name);
trace_rtas_ll_entry(args);
__do_enter_rtas(args);
trace_rtas_ll_exit(args);
- trace_rtas_output(args, name);
+ trace_rtas_output(args, func->name);
}
static void do_enter_rtas(struct rtas_args *args)
@@ -670,7 +768,7 @@ static void call_rtas_display_status_delay(char c)
static int pending_newline = 0; /* did last write end with unprinted newline? */
static int width = 16;
- if (c == '\n') {
+ if (c == '\n') {
while (width-- > 0)
call_rtas_display_status(' ');
width = 16;
@@ -680,7 +778,7 @@ static void call_rtas_display_status_delay(char c)
if (pending_newline) {
call_rtas_display_status('\r');
call_rtas_display_status('\n');
- }
+ }
pending_newline = 0;
if (width--) {
call_rtas_display_status(c);
@@ -820,7 +918,7 @@ void rtas_progress(char *s, unsigned short hex)
else
rtas_call(display_character, 1, 1, NULL, '\r');
}
-
+
if (row_width)
width = row_width[current_line];
else
@@ -840,9 +938,9 @@ void rtas_progress(char *s, unsigned short hex)
spin_unlock(&progress_lock);
return;
}
-
+
/* RTAS wants CR-LF, not just LF */
-
+
if (*os == '\n') {
rtas_call(display_character, 1, 1, NULL, '\r');
rtas_call(display_character, 1, 1, NULL, '\n');
@@ -852,7 +950,7 @@ void rtas_progress(char *s, unsigned short hex)
*/
rtas_call(display_character, 1, 1, NULL, *os);
}
-
+
if (row_width)
width = row_width[current_line];
else
@@ -861,15 +959,15 @@ void rtas_progress(char *s, unsigned short hex)
width--;
rtas_call(display_character, 1, 1, NULL, *os);
}
-
+
os++;
-
+
/* if we overwrite the screen length */
if (width <= 0)
while ((*os != 0) && (*os != '\n') && (*os != '\r'))
os++;
}
-
+
spin_unlock(&progress_lock);
}
EXPORT_SYMBOL_GPL(rtas_progress); /* needed by rtas_flash module */
@@ -900,11 +998,6 @@ int rtas_token(const char *service)
}
EXPORT_SYMBOL_GPL(rtas_token);
-int rtas_service_present(const char *service)
-{
- return rtas_token(service) != RTAS_UNKNOWN_SERVICE;
-}
-
#ifdef CONFIG_RTAS_ERROR_LOGGING
static u32 rtas_error_log_max __ro_after_init = RTAS_ERROR_LOG_MAX;
@@ -1638,10 +1731,14 @@ void rtas_activate_firmware(void)
return;
}
+ mutex_lock(&rtas_ibm_activate_firmware_lock);
+
do {
fwrc = rtas_call(token, 0, 1, NULL);
} while (rtas_busy_delay(fwrc));
+ mutex_unlock(&rtas_ibm_activate_firmware_lock);
+
if (fwrc)
pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
}
@@ -1713,24 +1810,18 @@ static bool in_rmo_buf(u32 base, u32 end)
end < (rtas_rmo_buf + RTAS_USER_REGION_SIZE);
}
-static bool block_rtas_call(int token, int nargs,
+static bool block_rtas_call(const struct rtas_function *func, int nargs,
struct rtas_args *args)
{
- const struct rtas_function *func;
const struct rtas_filter *f;
- const bool is_platform_dump = token == rtas_function_token(RTAS_FN_IBM_PLATFORM_DUMP);
- const bool is_config_conn = token == rtas_function_token(RTAS_FN_IBM_CONFIGURE_CONNECTOR);
+ const bool is_platform_dump =
+ func == &rtas_function_table[RTAS_FNIDX__IBM_PLATFORM_DUMP];
+ const bool is_config_conn =
+ func == &rtas_function_table[RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR];
u32 base, size, end;
/*
- * If this token doesn't correspond to a function the kernel
- * understands, you're not allowed to call it.
- */
- func = rtas_token_to_function(token);
- if (!func)
- goto err;
- /*
- * And only functions with filters attached are allowed.
+ * Only functions with filters attached are allowed.
*/
f = func->filter;
if (!f)
@@ -1787,14 +1878,15 @@ static bool block_rtas_call(int token, int nargs,
return false;
err:
pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n");
- pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n",
- token, nargs, current->comm);
+ pr_err_ratelimited("sys_rtas: %s nargs=%d (called by %s)\n",
+ func->name, nargs, current->comm);
return true;
}
/* We assume to be passed big endian arguments */
SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
{
+ const struct rtas_function *func;
struct pin_cookie cookie;
struct rtas_args args;
unsigned long flags;
@@ -1824,13 +1916,18 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
nargs * sizeof(rtas_arg_t)) != 0)
return -EFAULT;
- if (token == RTAS_UNKNOWN_SERVICE)
+ /*
+ * If this token doesn't correspond to a function the kernel
+ * understands, you're not allowed to call it.
+ */
+ func = rtas_token_to_function_untrusted(token);
+ if (!func)
return -EINVAL;
args.rets = &args.args[nargs];
memset(args.rets, 0, nret * sizeof(rtas_arg_t));
- if (block_rtas_call(token, nargs, &args))
+ if (block_rtas_call(func, nargs, &args))
return -EINVAL;
if (token_is_restricted_errinjct(token)) {
@@ -1863,6 +1960,15 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
buff_copy = get_errorlog_buffer();
+ /*
+ * If this function has a mutex assigned to it, we must
+ * acquire it to avoid interleaving with any kernel-based uses
+ * of the same function. Kernel-based sequences acquire the
+ * appropriate mutex explicitly.
+ */
+ if (func->lock)
+ mutex_lock(func->lock);
+
raw_spin_lock_irqsave(&rtas_lock, flags);
cookie = lockdep_pin_lock(&rtas_lock);
@@ -1878,6 +1984,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
lockdep_unpin_lock(&rtas_lock, cookie);
raw_spin_unlock_irqrestore(&rtas_lock, flags);
+ if (func->lock)
+ mutex_unlock(func->lock);
+
if (buff_copy) {
if (errbuf)
log_error(errbuf, ERR_TYPE_RTAS_LOG, 0);
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index e1fdc7473b72..fccf96e897f6 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -43,7 +43,7 @@ static inline int config_access_valid(struct pci_dn *dn, int where)
return 0;
}
-int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
{
int returnval = -1;
unsigned long buid, addr;
@@ -87,7 +87,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
pdn = pci_get_pdn_by_devfn(bus, devfn);
/* Validity of pdn is checked in here */
- ret = rtas_read_config(pdn, where, size, val);
+ ret = rtas_pci_dn_read_config(pdn, where, size, val);
if (*val == EEH_IO_ERROR_VALUE(size) &&
eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
return PCIBIOS_DEVICE_NOT_FOUND;
@@ -95,7 +95,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
return ret;
}
-int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val)
{
unsigned long buid, addr;
int ret;
@@ -134,7 +134,7 @@ static int rtas_pci_write_config(struct pci_bus *bus,
pdn = pci_get_pdn_by_devfn(bus, devfn);
/* Validity of pdn is checked in here. */
- return rtas_write_config(pdn, where, size, val);
+ return rtas_pci_dn_write_config(pdn, where, size, val);
}
static struct pci_ops rtas_pci_ops = {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ab691c89d787..693334c20d07 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -77,10 +77,10 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
#endif
struct task_struct *secondary_current;
-bool has_big_cores;
-bool coregroup_enabled;
-bool thread_group_shares_l2;
-bool thread_group_shares_l3;
+bool has_big_cores __ro_after_init;
+bool coregroup_enabled __ro_after_init;
+bool thread_group_shares_l2 __ro_after_init;
+bool thread_group_shares_l3 __ro_after_init;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -93,15 +93,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
EXPORT_SYMBOL_GPL(has_big_cores);
-enum {
-#ifdef CONFIG_SCHED_SMT
- smt_idx,
-#endif
- cache_idx,
- mc_idx,
- die_idx,
-};
-
#define MAX_THREAD_LIST_SIZE 8
#define THREAD_GROUP_SHARE_L1 1
#define THREAD_GROUP_SHARE_L2_L3 2
@@ -987,7 +978,7 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
return 0;
}
-static bool shared_caches;
+static bool shared_caches __ro_after_init;
#ifdef CONFIG_SCHED_SMT
/* cpumask of CPUs with asymmetric SMT dependency */
@@ -1004,6 +995,13 @@ static int powerpc_smt_flags(void)
#endif
/*
+ * On shared processor LPARs scheduled on a big core (which has two or more
+ * independent thread groups per core), prefer lower numbered CPUs, so
+ * that workload consolidates to lesser number of cores.
+ */
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
+
+/*
* P9 has a slightly odd architecture where pairs of cores share an L2 cache.
* This topology makes it *much* cheaper to migrate tasks between adjacent cores
* since the migrated task remains cache hot. We want to take advantage of this
@@ -1011,9 +1009,20 @@ static int powerpc_smt_flags(void)
*/
static int powerpc_shared_cache_flags(void)
{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
+
return SD_SHARE_PKG_RESOURCES;
}
+static int powerpc_shared_proc_flags(void)
+{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_ASYM_PACKING;
+
+ return 0;
+}
+
/*
* We can't just pass cpu_l2_cache_mask() directly because
* returns a non-const pointer and the compiler barfs on that.
@@ -1037,6 +1046,10 @@ static struct cpumask *cpu_coregroup_mask(int cpu)
static bool has_coregroup_support(void)
{
+ /* Coregroup identification not available on shared systems */
+ if (is_shared_processor())
+ return 0;
+
return coregroup_enabled;
}
@@ -1045,16 +1058,6 @@ static const struct cpumask *cpu_mc_mask(int cpu)
return cpu_coregroup_mask(cpu);
}
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
- { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
- { cpu_mc_mask, SD_INIT_NAME(MC) },
- { cpu_cpu_mask, SD_INIT_NAME(PKG) },
- { NULL, },
-};
-
static int __init init_big_cores(void)
{
int cpu;
@@ -1682,43 +1685,45 @@ void start_secondary(void *unused)
BUG();
}
-static void __init fixup_topology(void)
+static struct sched_domain_topology_level powerpc_topology[6];
+
+static void __init build_sched_topology(void)
{
- int i;
+ int i = 0;
+
+ if (is_shared_processor() && has_big_cores)
+ static_branch_enable(&splpar_asym_pack);
#ifdef CONFIG_SCHED_SMT
if (has_big_cores) {
pr_info("Big cores detected but using small core scheduling\n");
- powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+ };
+ } else {
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+ };
}
#endif
+ if (shared_caches) {
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE)
+ };
+ }
+ if (has_coregroup_support()) {
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC)
+ };
+ }
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG)
+ };
- if (!has_coregroup_support())
- powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
-
- /*
- * Try to consolidate topology levels here instead of
- * allowing scheduler to degenerate.
- * - Dont consolidate if masks are different.
- * - Dont consolidate if sd_flags exists and are different.
- */
- for (i = 1; i <= die_idx; i++) {
- if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
- continue;
-
- if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
- powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
- continue;
-
- if (!powerpc_topology[i - 1].sd_flags)
- powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+ /* There must be one trailing NULL entry left. */
+ BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
- powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
- powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
-#ifdef CONFIG_SCHED_DEBUG
- powerpc_topology[i].name = powerpc_topology[i + 1].name;
-#endif
- }
+ set_sched_topology(powerpc_topology);
}
void __init smp_cpus_done(unsigned int max_cpus)
@@ -1733,9 +1738,20 @@ void __init smp_cpus_done(unsigned int max_cpus)
smp_ops->bringup_done();
dump_numa_cpu_topology();
+ build_sched_topology();
+}
- fixup_topology();
- set_sched_topology(powerpc_topology);
+/*
+ * For asym packing, by default lower numbered CPU has higher priority.
+ * On shared processors, pack to lower numbered core. However avoid moving
+ * between thread_groups within the same core.
+ */
+int arch_asym_cpu_priority(int cpu)
+{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return -cpu / threads_per_core;
+
+ return -cpu;
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 16ee3baaf09a..50fa8fc9ef95 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -11,6 +11,8 @@
#include <linux/interrupt.h>
#include <linux/nmi.h>
+void do_after_copyback(void);
+
void do_after_copyback(void)
{
iommu_restore();
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 40677416d7b2..76dbe9fd2c0f 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -162,7 +162,6 @@ _GLOBAL(ftrace_regs_caller)
.globl ftrace_regs_call
ftrace_regs_call:
bl ftrace_stub
- nop
ftrace_regs_exit 1
_GLOBAL(ftrace_caller)
@@ -171,7 +170,6 @@ _GLOBAL(ftrace_caller)
.globl ftrace_call
ftrace_call:
bl ftrace_stub
- nop
ftrace_regs_exit 0
_GLOBAL(ftrace_stub)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5ea2014aff90..11e062b47d3f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1439,10 +1439,12 @@ static int emulate_instruction(struct pt_regs *regs)
return -EINVAL;
}
+#ifdef CONFIG_GENERIC_BUG
int is_valid_bugaddr(unsigned long addr)
{
return is_kernel_addr(addr);
}
+#endif
#ifdef CONFIG_MATH_EMULATION
static int emulate_math(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 74ddf836f7a2..a0467e528b70 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -7,7 +7,6 @@
#include <linux/types.h>
#include <asm/udbg.h>
#include <asm/io.h>
-#include <asm/reg_a2.h>
#include <asm/early_ioremap.h>
extern u8 real_readb(volatile u8 __iomem *addr);
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 0c7d82c270c3..1b93655c2857 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -71,7 +71,7 @@ AS64FLAGS := -D__VDSO64__
targets += vdso32.lds
CPPFLAGS_vdso32.lds += -P -C -Upowerpc
targets += vdso64.lds
-CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+CPPFLAGS_vdso64.lds += -P -C
# link rule for the .so file, .lds has to be first
$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 85846cadb9b5..27fa9098a5b7 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -75,6 +75,7 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_OFFSET(mmu_psize_def, shift);
#endif
VMCOREINFO_SYMBOL(cur_cpu_spec);
+ VMCOREINFO_OFFSET(cpu_spec, cpu_features);
VMCOREINFO_OFFSET(cpu_spec, mmu_features);
vmcoreinfo_append_str("NUMBER(RADIX_MMU)=%d\n", early_radix_enabled());
vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 6cd20ab9e94e..8acec144120e 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -302,11 +302,11 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
switch (priority) {
case BOOK3S_IRQPRIO_DECREMENTER:
- deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+ deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
vec = BOOK3S_INTERRUPT_DECREMENTER;
break;
case BOOK3S_IRQPRIO_EXTERNAL:
- deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+ deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
vec = BOOK3S_INTERRUPT_EXTERNAL;
break;
case BOOK3S_IRQPRIO_SYSTEM_RESET:
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 175a8eb2681f..4a1abb9f7c05 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -40,6 +40,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
unsigned long quadrant, ret = n;
bool is_load = !!to;
+ if (kvmhv_is_nestedv2())
+ return H_UNSUPPORTED;
+
/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
if (kvmhv_on_pseries())
return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
@@ -97,7 +100,7 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
void *to, void *from, unsigned long n)
{
int lpid = vcpu->kvm->arch.lpid;
- int pid = kvmppc_get_pid(vcpu);
+ int pid;
/* This would cause a data segment intr so don't allow the access */
if (eaddr & (0x3FFUL << 52))
@@ -110,6 +113,8 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
/* If accessing quadrant 3 then pid is expected to be 0 */
if (((eaddr >> 62) & 0x3) == 0x3)
pid = 0;
+ else
+ pid = kvmppc_get_pid(vcpu);
eaddr &= ~(0xFFFUL << 52);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1ed6ec140701..e48126a59ba7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -650,7 +650,8 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
return err;
}
-static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
+static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap,
+ struct kvmppc_vpa *old_vpap)
{
struct kvm *kvm = vcpu->kvm;
void *va;
@@ -690,9 +691,8 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
kvmppc_unpin_guest_page(kvm, va, gpa, false);
va = NULL;
}
- if (vpap->pinned_addr)
- kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
- vpap->dirty);
+ *old_vpap = *vpap;
+
vpap->gpa = gpa;
vpap->pinned_addr = va;
vpap->dirty = false;
@@ -702,6 +702,9 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvmppc_vpa old_vpa = { 0 };
+
if (!(vcpu->arch.vpa.update_pending ||
vcpu->arch.slb_shadow.update_pending ||
vcpu->arch.dtl.update_pending))
@@ -709,17 +712,34 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->arch.vpa_update_lock);
if (vcpu->arch.vpa.update_pending) {
- kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
- if (vcpu->arch.vpa.pinned_addr)
+ kvmppc_update_vpa(vcpu, &vcpu->arch.vpa, &old_vpa);
+ if (old_vpa.pinned_addr) {
+ if (kvmhv_is_nestedv2())
+ kvmhv_nestedv2_set_vpa(vcpu, ~0ull);
+ kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+ old_vpa.dirty);
+ }
+ if (vcpu->arch.vpa.pinned_addr) {
init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+ if (kvmhv_is_nestedv2())
+ kvmhv_nestedv2_set_vpa(vcpu, __pa(vcpu->arch.vpa.pinned_addr));
+ }
}
if (vcpu->arch.dtl.update_pending) {
- kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
+ kvmppc_update_vpa(vcpu, &vcpu->arch.dtl, &old_vpa);
+ if (old_vpa.pinned_addr)
+ kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+ old_vpa.dirty);
vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
vcpu->arch.dtl_index = 0;
}
- if (vcpu->arch.slb_shadow.update_pending)
- kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
+ if (vcpu->arch.slb_shadow.update_pending) {
+ kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow, &old_vpa);
+ if (old_vpa.pinned_addr)
+ kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+ old_vpa.dirty);
+ }
+
spin_unlock(&vcpu->arch.vpa_update_lock);
}
@@ -1597,7 +1617,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
* That can happen due to a bug, or due to a machine check
* occurring at just the wrong time.
*/
- if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) {
+ if (!kvmhv_is_nestedv2() && (__kvmppc_get_msr_hv(vcpu) & MSR_HV)) {
printk(KERN_EMERG "KVM trap in HV mode!\n");
printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
vcpu->arch.trap, kvmppc_get_pc(vcpu),
@@ -1688,7 +1708,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
{
int i;
- if (unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
+ if (!kvmhv_is_nestedv2() && unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
/*
* Guest userspace executed sc 1. This can only be
* reached by the P9 path because the old path
@@ -4084,6 +4104,8 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
if (rc < 0)
return -EINVAL;
+ kvmppc_gse_put_u64(io->vcpu_run_input, KVMPPC_GSID_LPCR, lpcr);
+
accumulate_time(vcpu, &vcpu->arch.in_guest);
rc = plpar_guest_run_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id,
&trap, &i);
@@ -4736,13 +4758,19 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
if (!nested) {
kvmppc_core_prepare_to_enter(vcpu);
- if (__kvmppc_get_msr_hv(vcpu) & MSR_EE) {
- if (xive_interrupt_pending(vcpu))
+ if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
+ &vcpu->arch.pending_exceptions) ||
+ xive_interrupt_pending(vcpu)) {
+ /*
+ * For nested HV, don't synthesize but always pass MER,
+ * the L0 will be able to optimise that more
+ * effectively than manipulating registers directly.
+ */
+ if (!kvmhv_on_pseries() && (__kvmppc_get_msr_hv(vcpu) & MSR_EE))
kvmppc_inject_interrupt_hv(vcpu,
- BOOK3S_INTERRUPT_EXTERNAL, 0);
- } else if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
- &vcpu->arch.pending_exceptions)) {
- lpcr |= LPCR_MER;
+ BOOK3S_INTERRUPT_EXTERNAL, 0);
+ else
+ lpcr |= LPCR_MER;
}
} else if (vcpu->arch.pending_exceptions ||
vcpu->arch.doorbell_request ||
@@ -4806,7 +4834,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
* entering a nested guest in which case the decrementer is now owned
* by L2 and the L1 decrementer is provided in hdec_expires
*/
- if (kvmppc_core_pending_dec(vcpu) &&
+ if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) &&
((tb < kvmppc_dec_expires_host_tb(vcpu)) ||
(trap == BOOK3S_INTERRUPT_SYSCALL &&
kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
@@ -4949,7 +4977,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
if (run->exit_reason == KVM_EXIT_PAPR_HCALL) {
accumulate_time(vcpu, &vcpu->arch.hcall);
- if (WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
+ if (!kvmhv_is_nestedv2() && WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
/*
* These should have been caught reflected
* into the guest by now. Final sanity check:
@@ -5691,10 +5719,12 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
}
- if (kvmhv_is_nestedv2())
+ if (kvmhv_is_nestedv2()) {
+ kvmhv_flush_lpid(kvm->arch.lpid);
plpar_guest_delete(0, kvm->arch.lpid);
- else
+ } else {
kvmppc_free_lpid(kvm->arch.lpid);
+ }
kvmppc_free_pimap(kvm);
}
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 3b658b8696bc..5c375ec1a3c6 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -503,7 +503,7 @@ void kvmhv_nested_exit(void)
}
}
-static void kvmhv_flush_lpid(u64 lpid)
+void kvmhv_flush_lpid(u64 lpid)
{
long rc;
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index fd3c4f2d9480..5378eb40b162 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -856,6 +856,35 @@ free_gsb:
EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_ptbl_entry);
/**
+ * kvmhv_nestedv2_set_vpa() - register L2 VPA with L0
+ * @vcpu: vcpu
+ * @vpa: L1 logical real address
+ */
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa)
+{
+ struct kvmhv_nestedv2_io *io;
+ struct kvmppc_gs_buff *gsb;
+ int rc = 0;
+
+ io = &vcpu->arch.nestedv2_io;
+ gsb = io->vcpu_run_input;
+
+ kvmppc_gsb_reset(gsb);
+ rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_VPA, vpa);
+ if (rc < 0)
+ goto out;
+
+ rc = kvmppc_gsb_send(gsb, 0);
+ if (rc < 0)
+ pr_err("KVM-NESTEDv2: couldn't register the L2 VPA (rc=%d)\n", rc);
+
+out:
+ kvmppc_gsb_reset(gsb);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_vpa);
+
+/**
* kvmhv_nestedv2_parse_output() - receive values from H_GUEST_RUN_VCPU output
* @vcpu: vcpu
*
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 9118242063fb..5b92619a05fd 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -604,6 +604,7 @@ static void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
case PVR_POWER8:
case PVR_POWER8E:
case PVR_POWER8NVL:
+ case PVR_HX_C2000:
case PVR_POWER9:
vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
BOOK3S_HFLAG_NEW_TLBIE;
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 077fd88a0b68..ec60c7979718 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -93,7 +93,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
emulated = EMULATE_FAIL;
vcpu->arch.regs.msr = kvmppc_get_msr(vcpu);
- kvmhv_nestedv2_reload_ptregs(vcpu, &vcpu->arch.regs);
if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
int type = op.type & INSTR_TYPE_MASK;
int size = GETSIZE(op.type);
@@ -112,7 +111,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
op.reg, size, !instr_byte_swap);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
- kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+ kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
break;
}
@@ -132,7 +131,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
KVM_MMIO_REG_FPR|op.reg, size, 1);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
- kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+ kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
break;
#endif
@@ -224,16 +223,17 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
break;
}
#endif
- case STORE:
- /* if need byte reverse, op.val has been reversed by
- * analyse_instr().
- */
- emulated = kvmppc_handle_store(vcpu, op.val, size, 1);
+ case STORE: {
+ int instr_byte_swap = op.type & BYTEREV;
+
+ emulated = kvmppc_handle_store(vcpu, kvmppc_get_gpr(vcpu, op.reg),
+ size, !instr_byte_swap);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
- kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+ kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
break;
+ }
#ifdef CONFIG_PPC_FPU
case STORE_FP:
if (kvmppc_check_fp_disabled(vcpu))
@@ -254,7 +254,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
kvmppc_get_fpr(vcpu, op.reg), size, 1);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
- kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+ kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
break;
#endif
@@ -358,7 +358,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
}
trace_kvm_ppc_instr(ppc_inst_val(inst), kvmppc_get_pc(vcpu), emulated);
- kvmhv_nestedv2_mark_dirty_ptregs(vcpu, &vcpu->arch.regs);
/* Advance past emulated instruction. */
if (emulated != EMULATE_FAIL)
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 51ad0397c17a..6eac63e79a89 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -45,7 +45,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
# so it is only needed for modules, and only for older linkers which
# do not support --save-restore-funcs
ifndef CONFIG_LD_IS_BFD
-extra-$(CONFIG_PPC64) += crtsavres.o
+always-$(CONFIG_PPC64) += crtsavres.o
endif
obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index a4ab8625061a..5766180f5380 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -586,6 +586,8 @@ static int do_fp_load(struct instruction_op *op, unsigned long ea,
} u;
nb = GETSIZE(op->type);
+ if (nb > sizeof(u))
+ return -EINVAL;
if (!address_ok(regs, ea, nb))
return -EFAULT;
rn = op->reg;
@@ -636,6 +638,8 @@ static int do_fp_store(struct instruction_op *op, unsigned long ea,
} u;
nb = GETSIZE(op->type);
+ if (nb > sizeof(u))
+ return -EINVAL;
if (!address_ok(regs, ea, nb))
return -EFAULT;
rn = op->reg;
@@ -680,6 +684,9 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
u8 b[sizeof(__vector128)];
} u = {};
+ if (size > sizeof(u))
+ return -EINVAL;
+
if (!address_ok(regs, ea & ~0xfUL, 16))
return -EFAULT;
/* align to multiple of size */
@@ -688,7 +695,7 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
if (err)
return err;
if (unlikely(cross_endian))
- do_byte_reverse(&u.b[ea & 0xf], size);
+ do_byte_reverse(&u.b[ea & 0xf], min_t(size_t, size, sizeof(u)));
preempt_disable();
if (regs->msr & MSR_VEC)
put_vr(rn, &u.v);
@@ -707,6 +714,9 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
u8 b[sizeof(__vector128)];
} u;
+ if (size > sizeof(u))
+ return -EINVAL;
+
if (!address_ok(regs, ea & ~0xfUL, 16))
return -EFAULT;
/* align to multiple of size */
@@ -719,7 +729,7 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
u.v = current->thread.vr_state.vr[rn];
preempt_enable();
if (unlikely(cross_endian))
- do_byte_reverse(&u.b[ea & 0xf], size);
+ do_byte_reverse(&u.b[ea & 0xf], min_t(size_t, size, sizeof(u)));
return copy_mem_out(&u.b[ea & 0xf], ea, size, regs);
}
#endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index ad2afa08e62e..0626a25b0d72 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -310,9 +310,16 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags
else
rflags |= 0x3;
}
+ VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request");
} else {
if (pteflags & _PAGE_RWX)
rflags |= 0x2;
+ /*
+ * We should never hit this in normal fault handling because
+ * a permission check (check_pte_access()) will bubble this
+ * to higher level linux handler even for PAGE_NONE.
+ */
+ VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request");
if (!((pteflags & _PAGE_WRITE) && (pteflags & _PAGE_DIRTY)))
rflags |= 0x1;
}
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index be229290a6a7..3438ab72c346 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -542,6 +542,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* For hash translation mode, we use the deposited table to store hash slot
* information and they are stored at PTRS_PER_PMD offset from related pmd
@@ -563,6 +564,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
return true;
}
+#endif
/*
* Does the CPU support tlbie?
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 125733962033..a974baf8f327 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -89,7 +89,8 @@ static int __init scan_pkey_feature(void)
unsigned long pvr = mfspr(SPRN_PVR);
if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E ||
- PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9)
+ PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9 ||
+ PVR_VER(pvr) == PVR_HX_C2000)
pkeys_total = 32;
}
}
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index 119ef491f797..d3a7726ecf51 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -126,7 +126,7 @@ void pgtable_cache_add(unsigned int shift)
* as to leave enough 0 bits in the address to contain it. */
unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
HUGEPD_SHIFT_MASK + 1);
- struct kmem_cache *new;
+ struct kmem_cache *new = NULL;
/* It would be nice if this was a BUILD_BUG_ON(), but at the
* moment, gcc doesn't seem to recognize is_power_of_2 as a
@@ -139,7 +139,8 @@ void pgtable_cache_add(unsigned int shift)
align = max_t(unsigned long, align, minalign);
name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
- new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
+ if (name)
+ new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
if (!new)
panic("Could not allocate pgtable cache for order %d", shift);
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 7f9ff0640124..72341b9fb552 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -181,3 +181,8 @@ static inline bool debug_pagealloc_enabled_or_kfence(void)
{
return IS_ENABLED(CONFIG_KFENCE) || debug_pagealloc_enabled();
}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int create_section_mapping(unsigned long start, unsigned long end,
+ int nid, pgprot_t prot);
+#endif
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 39dbe6b348df..27f18119fda1 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -534,6 +534,9 @@ static ssize_t affinity_domain_via_partition_show(struct device *dev, struct dev
if (!ret)
goto parse_result;
+ if (ret && (ret != H_PARAMETER))
+ goto out;
+
/*
* ret value as 'H_PARAMETER' implies that the current buffer size
* can't accommodate all the information, and a partial buffer
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 5d12ca386c1f..8664a7d297ad 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -299,6 +299,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
attr_group->attrs = attrs;
do {
ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i].value);
+ if (!ev_val_str)
+ continue;
dev_str = device_str_attr_create(pmu->events[i].name, ev_val_str);
if (!dev_str)
continue;
@@ -306,6 +308,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
attrs[j++] = dev_str;
if (pmu->events[i].scale) {
ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale", pmu->events[i].name);
+ if (!ev_scale_str)
+ continue;
dev_str = device_str_attr_create(ev_scale_str, pmu->events[i].scale);
if (!dev_str)
continue;
@@ -315,6 +319,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
if (pmu->events[i].unit) {
ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit", pmu->events[i].name);
+ if (!ev_unit_str)
+ continue;
dev_str = device_str_attr_create(ev_unit_str, pmu->events[i].unit);
if (!dev_str)
continue;
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 1624ebf95497..35a1f4b9f827 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -173,6 +173,7 @@ config ISS4xx
config CURRITUCK
bool "IBM Currituck (476fpe) Support"
depends on PPC_47x
+ select I2C
select SWIOTLB
select 476FPE
select FORCE_PCI
diff --git a/arch/powerpc/platforms/44x/idle.c b/arch/powerpc/platforms/44x/idle.c
index f533b495e7db..e2eeef8dff78 100644
--- a/arch/powerpc/platforms/44x/idle.c
+++ b/arch/powerpc/platforms/44x/idle.c
@@ -27,7 +27,7 @@ static void ppc44x_idle(void)
isync();
}
-int __init ppc44x_idle_init(void)
+static int __init ppc44x_idle_init(void)
{
if (!mode_spin) {
/* If we are not setting spin mode
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index 6f08d07aee3b..e995eb30bf09 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -17,6 +17,8 @@
#include <linux/of_address.h>
#include <linux/of_irq.h>
+#include "mpc5121_ads.h"
+
static struct device_node *cpld_pic_node;
static struct irq_domain *cpld_pic_host;
diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c
index ce51cfeeb066..8bbbf78bb42b 100644
--- a/arch/powerpc/platforms/512x/pdm360ng.c
+++ b/arch/powerpc/platforms/512x/pdm360ng.c
@@ -101,7 +101,7 @@ static inline void __init pdm360ng_touchscreen_init(void)
}
#endif /* CONFIG_TOUCHSCREEN_ADS7846 */
-void __init pdm360ng_init(void)
+static void __init pdm360ng_init(void)
{
mpc512x_init();
pdm360ng_touchscreen_init();
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 9833c36bda83..c9664e46b03d 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -261,9 +261,10 @@ static int mpc83xx_suspend_begin(suspend_state_t state)
static int agent_thread_fn(void *data)
{
+ set_freezable();
+
while (1) {
- wait_event_interruptible(agent_wq, pci_pm_state >= 2);
- try_to_freeze();
+ wait_event_freezable(agent_wq, pci_pm_state >= 2);
if (signal_pending(current) || pci_pm_state < 2)
continue;
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index ec9f60fbebc7..e0cec670d8db 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -76,7 +76,7 @@ static void __init mpc85xx_rdb_setup_arch(void)
/* P1025 has pins muxed for QE and other functions. To
* enable QE UEC mode, we need to set bit QE0 for UCC1
* in Eth mode, QE0 and QE3 for UCC5 in Eth mode, QE9
- * and QE12 for QE MII management singals in PMUXCR
+ * and QE12 for QE MII management signals in PMUXCR
* register.
*/
setbits32(&guts->pmuxcr, MPC85xx_PMUXCR_QE(0) |
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 67467cd6f34c..06b1e5c49d6f 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -52,10 +52,3 @@ config MPC8641
select MPIC
default y if GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \
|| MVME7100
-
-config MPC8610
- bool
- select HAVE_PCI
- select FSL_PCI if PCI
- select PPC_UDBG_16550
- select MPIC
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index ef985ba2bf21..0761d98e5be3 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -64,7 +64,7 @@ static void __noreturn pas_restart(char *cmd)
}
#ifdef CONFIG_PPC_PASEMI_NEMO
-void pas_shutdown(void)
+static void pas_shutdown(void)
{
/* Set the PLD bit that makes the SB600 think the power button is being pressed */
void __iomem *pld_map = ioremap(0xf5000000,4096);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index c83d1e14077e..15644be31990 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -413,7 +413,7 @@ static void __init smp_psurge_setup_cpu(int cpu_nr)
printk(KERN_ERR "Couldn't get primary IPI interrupt");
}
-void __init smp_psurge_take_timebase(void)
+static void __init smp_psurge_take_timebase(void)
{
if (psurge_type != PSURGE_DUAL)
return;
@@ -429,7 +429,7 @@ void __init smp_psurge_take_timebase(void)
set_dec(tb_ticks_per_jiffy/2);
}
-void __init smp_psurge_give_timebase(void)
+static void __init smp_psurge_give_timebase(void)
{
/* Nothing to do here */
}
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index f9a7001dacb7..56a1f7ce78d2 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -275,6 +275,8 @@ int __init opal_event_init(void)
else
name = kasprintf(GFP_KERNEL, "opal");
+ if (!name)
+ continue;
/* Install interrupt handler */
rc = request_irq(r->start, opal_interrupt, r->flags & IRQD_TRIGGER_MASK,
name, NULL);
diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c
index 7bfe4cbeb35a..ea917266aa17 100644
--- a/arch/powerpc/platforms/powernv/opal-powercap.c
+++ b/arch/powerpc/platforms/powernv/opal-powercap.c
@@ -196,6 +196,12 @@ void __init opal_powercap_init(void)
j = 0;
pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node);
+ if (!pcaps[i].pg.name) {
+ kfree(pcaps[i].pattrs);
+ kfree(pcaps[i].pg.attrs);
+ goto out_pcaps_pattrs;
+ }
+
if (has_min) {
powercap_add_attr(min, "powercap-min",
&pcaps[i].pattrs[j]);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 327e2f76905d..b66b06efcef1 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -66,6 +66,8 @@ static bool opal_prd_range_is_valid(uint64_t addr, uint64_t size)
const char *label;
addrp = of_get_address(node, 0, &range_size, NULL);
+ if (!addrp)
+ continue;
range_addr = of_read_number(addrp, 2);
range_end = range_addr + range_size;
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 262cd6fac907..748c2b97fa53 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -165,6 +165,11 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn,
ent->chip = chip;
snprintf(ent->name, 16, "%08x", chip);
ent->path.data = (void *)kasprintf(GFP_KERNEL, "%pOF", dn);
+ if (!ent->path.data) {
+ kfree(ent);
+ return -ENOMEM;
+ }
+
ent->path.size = strlen((char *)ent->path.data);
dir = debugfs_create_dir(ent->name, root);
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 191424468f10..393e747541fb 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -425,7 +425,8 @@ static int subcore_init(void)
if (pvr_ver != PVR_POWER8 &&
pvr_ver != PVR_POWER8E &&
- pvr_ver != PVR_POWER8NVL)
+ pvr_ver != PVR_POWER8NVL &&
+ pvr_ver != PVR_HX_C2000)
return 0;
/*
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index a44869e5ea70..e9c1087dd42e 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -167,16 +167,4 @@ config PS3_LPM
profiling support of the Cell processor with programs like
perfmon2, then say Y or M, otherwise say N.
-config PS3GELIC_UDBG
- bool "PS3 udbg output via UDP broadcasts on Ethernet"
- depends on PPC_PS3
- help
- Enables udbg early debugging output by sending broadcast UDP
- via the Ethernet port (UDP port number 18194).
-
- This driver uses a trivial implementation and is independent
- from the main PS3 gelic network driver.
-
- If in doubt, say N here.
-
endmenu
diff --git a/arch/powerpc/platforms/ps3/Makefile b/arch/powerpc/platforms/ps3/Makefile
index 86bf2967a8d4..bc79bb124d1e 100644
--- a/arch/powerpc/platforms/ps3/Makefile
+++ b/arch/powerpc/platforms/ps3/Makefile
@@ -3,7 +3,7 @@ obj-y += setup.o mm.o time.o hvcall.o htab.o repository.o
obj-y += interrupt.o exports.o os-area.o
obj-y += system-bus.o
-obj-$(CONFIG_PS3GELIC_UDBG) += gelic_udbg.o
+obj-$(CONFIG_PPC_EARLY_DEBUG_PS3GELIC) += gelic_udbg.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SPU_BASE) += spu.o
obj-y += device-init.o
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e87360a0fb40..878bc160246e 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -827,6 +827,7 @@ static int ps3_probe_thread(void *data)
if (res)
goto fail_free_irq;
+ set_freezable();
/* Loop here processing the requested notification events. */
do {
try_to_freeze();
diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c
index 6b298010fd84..a5202c18c236 100644
--- a/arch/powerpc/platforms/ps3/gelic_udbg.c
+++ b/arch/powerpc/platforms/ps3/gelic_udbg.c
@@ -14,6 +14,7 @@
#include <linux/ip.h>
#include <linux/udp.h>
+#include <asm/ps3.h>
#include <asm/io.h>
#include <asm/udbg.h>
#include <asm/lv1call.h>
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 1476c5e4433c..f936962a2946 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -4,6 +4,7 @@ ccflags-$(CONFIG_PPC_PSERIES_DEBUG) += -DDEBUG
obj-y := lpar.o hvCall.o nvram.o reconfig.o \
of_helpers.o rtas-work-area.o papr-sysparm.o \
+ papr-vpd.o \
setup.o iommu.o event_sources.o ras.o \
firmware.o power.o dlpar.o mobility.o rng.o \
pci.o pci_dlpar.o eeh_pseries.o msi.o \
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index def184da51cf..b1ae0c0d1187 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -252,7 +252,7 @@ static int pseries_eeh_cap_start(struct pci_dn *pdn)
if (!pdn)
return 0;
- rtas_read_config(pdn, PCI_STATUS, 2, &status);
+ rtas_pci_dn_read_config(pdn, PCI_STATUS, 2, &status);
if (!(status & PCI_STATUS_CAP_LIST))
return 0;
@@ -270,11 +270,11 @@ static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap)
return 0;
while (cnt--) {
- rtas_read_config(pdn, pos, 1, &pos);
+ rtas_pci_dn_read_config(pdn, pos, 1, &pos);
if (pos < 0x40)
break;
pos &= ~3;
- rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+ rtas_pci_dn_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
if (id == 0xff)
break;
if (id == cap)
@@ -294,7 +294,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
if (!edev || !edev->pcie_cap)
return 0;
- if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+ if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
return 0;
else if (!header)
return 0;
@@ -307,7 +307,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
if (pos < 256)
break;
- if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+ if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
break;
}
@@ -412,8 +412,8 @@ static void pseries_eeh_init_edev(struct pci_dn *pdn)
if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
edev->mode |= EEH_DEV_BRIDGE;
if (edev->pcie_cap) {
- rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
- 2, &pcie_flags);
+ rtas_pci_dn_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+ 2, &pcie_flags);
pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
edev->mode |= EEH_DEV_ROOT_PORT;
@@ -676,7 +676,7 @@ static int pseries_eeh_read_config(struct eeh_dev *edev, int where, int size, u3
{
struct pci_dn *pdn = eeh_dev_to_pdn(edev);
- return rtas_read_config(pdn, where, size, val);
+ return rtas_pci_dn_read_config(pdn, where, size, val);
}
/**
@@ -692,7 +692,7 @@ static int pseries_eeh_write_config(struct eeh_dev *edev, int where, int size, u
{
struct pci_dn *pdn = eeh_dev_to_pdn(edev);
- return rtas_write_config(pdn, where, size, val);
+ return rtas_pci_dn_write_config(pdn, where, size, val);
}
#ifdef CONFIG_PCI_IOV
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index a43bfb01720a..3fe3ddb30c04 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -208,8 +208,10 @@ static int dlpar_change_lmb_state(struct drmem_lmb *lmb, bool online)
int rc;
mem_block = lmb_to_memblock(lmb);
- if (!mem_block)
+ if (!mem_block) {
+ pr_err("Failed memory block lookup for LMB 0x%x\n", lmb->drc_index);
return -EINVAL;
+ }
if (online && mem_block->dev.offline)
rc = device_online(&mem_block->dev);
@@ -436,14 +438,15 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
}
}
- if (!lmb_found)
+ if (!lmb_found) {
+ pr_debug("Failed to look up LMB for drc index %x\n", drc_index);
rc = -EINVAL;
-
- if (rc)
+ } else if (rc) {
pr_debug("Failed to hot-remove memory at %llx\n",
lmb->base_addr);
- else
+ } else {
pr_debug("Memory at %llx was hot-removed\n", lmb->base_addr);
+ }
return rc;
}
@@ -575,6 +578,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
rc = update_lmb_associativity_index(lmb);
if (rc) {
dlpar_release_drc(lmb->drc_index);
+ pr_err("Failed to configure LMB 0x%x\n", lmb->drc_index);
return rc;
}
@@ -588,12 +592,14 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
/* Add the memory */
rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_MEMMAP_ON_MEMORY);
if (rc) {
+ pr_err("Failed to add LMB 0x%x to node %u", lmb->drc_index, nid);
invalidate_lmb_associativity_index(lmb);
return rc;
}
rc = dlpar_online_lmb(lmb);
if (rc) {
+ pr_err("Failed to online LMB 0x%x on node %u\n", lmb->drc_index, nid);
__remove_memory(lmb->base_addr, block_sz);
invalidate_lmb_associativity_index(lmb);
} else {
diff --git a/arch/powerpc/platforms/pseries/papr-sysparm.c b/arch/powerpc/platforms/pseries/papr-sysparm.c
index fedc61599e6c..7063ce8884e4 100644
--- a/arch/powerpc/platforms/pseries/papr-sysparm.c
+++ b/arch/powerpc/platforms/pseries/papr-sysparm.c
@@ -2,14 +2,20 @@
#define pr_fmt(fmt) "papr-sysparm: " fmt
+#include <linux/anon_inodes.h>
#include <linux/bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
+#include <linux/miscdevice.h>
#include <linux/printk.h>
#include <linux/slab.h>
-#include <asm/rtas.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
#include <asm/papr-sysparm.h>
#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
struct papr_sysparm_buf *papr_sysparm_buf_alloc(void)
{
@@ -23,6 +29,46 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
kfree(buf);
}
+static size_t papr_sysparm_buf_get_length(const struct papr_sysparm_buf *buf)
+{
+ return be16_to_cpu(buf->len);
+}
+
+static void papr_sysparm_buf_set_length(struct papr_sysparm_buf *buf, size_t length)
+{
+ WARN_ONCE(length > sizeof(buf->val),
+ "bogus length %zu, clamping to safe value", length);
+ length = min(sizeof(buf->val), length);
+ buf->len = cpu_to_be16(length);
+}
+
+/*
+ * For use on buffers returned from ibm,get-system-parameter before
+ * returning them to callers. Ensures the encoded length of valid data
+ * cannot overrun buf->val[].
+ */
+static void papr_sysparm_buf_clamp_length(struct papr_sysparm_buf *buf)
+{
+ papr_sysparm_buf_set_length(buf, papr_sysparm_buf_get_length(buf));
+}
+
+/*
+ * Perform some basic diligence on the system parameter buffer before
+ * submitting it to RTAS.
+ */
+static bool papr_sysparm_buf_can_submit(const struct papr_sysparm_buf *buf)
+{
+ /*
+ * Firmware ought to reject buffer lengths that exceed the
+ * maximum specified in PAPR, but there's no reason for the
+ * kernel to allow them either.
+ */
+ if (papr_sysparm_buf_get_length(buf) > sizeof(buf->val))
+ return false;
+
+ return true;
+}
+
/**
* papr_sysparm_get() - Retrieve the value of a PAPR system parameter.
* @param: PAPR system parameter token as described in
@@ -47,7 +93,6 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
*
* Return: 0 on success, -errno otherwise. @buf is unmodified on error.
*/
-
int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
{
const s32 token = rtas_function_token(RTAS_FN_IBM_GET_SYSTEM_PARAMETER);
@@ -63,6 +108,9 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
if (token == RTAS_UNKNOWN_SERVICE)
return -ENOENT;
+ if (!papr_sysparm_buf_can_submit(buf))
+ return -EINVAL;
+
work_area = rtas_work_area_alloc(sizeof(*buf));
memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -77,6 +125,7 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
case 0:
ret = 0;
memcpy(buf, rtas_work_area_raw_buf(work_area), sizeof(*buf));
+ papr_sysparm_buf_clamp_length(buf);
break;
case -3: /* parameter not implemented */
ret = -EOPNOTSUPP;
@@ -115,6 +164,9 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
if (token == RTAS_UNKNOWN_SERVICE)
return -ENOENT;
+ if (!papr_sysparm_buf_can_submit(buf))
+ return -EINVAL;
+
work_area = rtas_work_area_alloc(sizeof(*buf));
memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -149,3 +201,152 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
return ret;
}
+
+static struct papr_sysparm_buf *
+papr_sysparm_buf_from_user(const struct papr_sysparm_io_block __user *user_iob)
+{
+ struct papr_sysparm_buf *kern_spbuf;
+ long err;
+ u16 len;
+
+ /*
+ * The length of valid data that userspace claims to be in
+ * user_iob->data[].
+ */
+ if (get_user(len, &user_iob->length))
+ return ERR_PTR(-EFAULT);
+
+ static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_INPUT);
+ static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_INPUT);
+
+ if (len > PAPR_SYSPARM_MAX_INPUT)
+ return ERR_PTR(-EINVAL);
+
+ kern_spbuf = papr_sysparm_buf_alloc();
+ if (!kern_spbuf)
+ return ERR_PTR(-ENOMEM);
+
+ papr_sysparm_buf_set_length(kern_spbuf, len);
+
+ if (len > 0 && copy_from_user(kern_spbuf->val, user_iob->data, len)) {
+ err = -EFAULT;
+ goto free_sysparm_buf;
+ }
+
+ return kern_spbuf;
+
+free_sysparm_buf:
+ papr_sysparm_buf_free(kern_spbuf);
+ return ERR_PTR(err);
+}
+
+static int papr_sysparm_buf_to_user(const struct papr_sysparm_buf *kern_spbuf,
+ struct papr_sysparm_io_block __user *user_iob)
+{
+ u16 len_out = papr_sysparm_buf_get_length(kern_spbuf);
+
+ if (put_user(len_out, &user_iob->length))
+ return -EFAULT;
+
+ static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_OUTPUT);
+ static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_OUTPUT);
+
+ if (copy_to_user(user_iob->data, kern_spbuf->val, PAPR_SYSPARM_MAX_OUTPUT))
+ return -EFAULT;
+
+ return 0;
+}
+
+static long papr_sysparm_ioctl_get(struct papr_sysparm_io_block __user *user_iob)
+{
+ struct papr_sysparm_buf *kern_spbuf;
+ papr_sysparm_t param;
+ long ret;
+
+ if (get_user(param.token, &user_iob->parameter))
+ return -EFAULT;
+
+ kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+ if (IS_ERR(kern_spbuf))
+ return PTR_ERR(kern_spbuf);
+
+ ret = papr_sysparm_get(param, kern_spbuf);
+ if (ret)
+ goto free_sysparm_buf;
+
+ ret = papr_sysparm_buf_to_user(kern_spbuf, user_iob);
+ if (ret)
+ goto free_sysparm_buf;
+
+ ret = 0;
+
+free_sysparm_buf:
+ papr_sysparm_buf_free(kern_spbuf);
+ return ret;
+}
+
+
+static long papr_sysparm_ioctl_set(struct papr_sysparm_io_block __user *user_iob)
+{
+ struct papr_sysparm_buf *kern_spbuf;
+ papr_sysparm_t param;
+ long ret;
+
+ if (get_user(param.token, &user_iob->parameter))
+ return -EFAULT;
+
+ kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+ if (IS_ERR(kern_spbuf))
+ return PTR_ERR(kern_spbuf);
+
+ ret = papr_sysparm_set(param, kern_spbuf);
+ if (ret)
+ goto free_sysparm_buf;
+
+ ret = 0;
+
+free_sysparm_buf:
+ papr_sysparm_buf_free(kern_spbuf);
+ return ret;
+}
+
+static long papr_sysparm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+ void __user *argp = (__force void __user *)arg;
+ long ret;
+
+ switch (ioctl) {
+ case PAPR_SYSPARM_IOC_GET:
+ ret = papr_sysparm_ioctl_get(argp);
+ break;
+ case PAPR_SYSPARM_IOC_SET:
+ if (filp->f_mode & FMODE_WRITE)
+ ret = papr_sysparm_ioctl_set(argp);
+ else
+ ret = -EBADF;
+ break;
+ default:
+ ret = -ENOIOCTLCMD;
+ break;
+ }
+ return ret;
+}
+
+static const struct file_operations papr_sysparm_ops = {
+ .unlocked_ioctl = papr_sysparm_ioctl,
+};
+
+static struct miscdevice papr_sysparm_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "papr-sysparm",
+ .fops = &papr_sysparm_ops,
+};
+
+static __init int papr_sysparm_init(void)
+{
+ if (!rtas_function_implemented(RTAS_FN_IBM_GET_SYSTEM_PARAMETER))
+ return -ENODEV;
+
+ return misc_register(&papr_sysparm_dev);
+}
+machine_device_initcall(pseries, papr_sysparm_init);
diff --git a/arch/powerpc/platforms/pseries/papr-vpd.c b/arch/powerpc/platforms/pseries/papr-vpd.c
new file mode 100644
index 000000000000..c29e85db5f35
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-vpd.c
@@ -0,0 +1,541 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-vpd: " fmt
+
+#include <linux/anon_inodes.h>
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/papr-vpd.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-vpd.h>
+
+/*
+ * Function-specific return values for ibm,get-vpd, derived from PAPR+
+ * v2.13 7.3.20 "ibm,get-vpd RTAS Call".
+ */
+#define RTAS_IBM_GET_VPD_COMPLETE 0 /* All VPD has been retrieved. */
+#define RTAS_IBM_GET_VPD_MORE_DATA 1 /* More VPD is available. */
+#define RTAS_IBM_GET_VPD_START_OVER -4 /* VPD changed, restart call sequence. */
+
+/**
+ * struct rtas_ibm_get_vpd_params - Parameters (in and out) for ibm,get-vpd.
+ * @loc_code: In: Caller-provided location code buffer. Must be RTAS-addressable.
+ * @work_area: In: Caller-provided work area buffer for results.
+ * @sequence: In: Sequence number. Out: Next sequence number.
+ * @written: Out: Bytes written by ibm,get-vpd to @work_area.
+ * @status: Out: RTAS call status.
+ */
+struct rtas_ibm_get_vpd_params {
+ const struct papr_location_code *loc_code;
+ struct rtas_work_area *work_area;
+ u32 sequence;
+ u32 written;
+ s32 status;
+};
+
+/**
+ * rtas_ibm_get_vpd() - Call ibm,get-vpd to fill a work area buffer.
+ * @params: See &struct rtas_ibm_get_vpd_params.
+ *
+ * Calls ibm,get-vpd until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_ibm_get_vpd() multiple times
+ * to retrieve all the VPD for the provided location code. Only one
+ * sequence should be in progress at any time; starting a new sequence
+ * will disrupt any sequence already in progress. Serialization of VPD
+ * retrieval sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_ibm_get_vpd(struct rtas_ibm_get_vpd_params *params)
+{
+ const struct papr_location_code *loc_code = params->loc_code;
+ struct rtas_work_area *work_area = params->work_area;
+ u32 rets[2];
+ s32 fwrc;
+ int ret;
+
+ lockdep_assert_held(&rtas_ibm_get_vpd_lock);
+
+ do {
+ fwrc = rtas_call(rtas_function_token(RTAS_FN_IBM_GET_VPD), 4, 3,
+ rets,
+ __pa(loc_code),
+ rtas_work_area_phys(work_area),
+ rtas_work_area_size(work_area),
+ params->sequence);
+ } while (rtas_busy_delay(fwrc));
+
+ switch (fwrc) {
+ case RTAS_HARDWARE_ERROR:
+ ret = -EIO;
+ break;
+ case RTAS_INVALID_PARAMETER:
+ ret = -EINVAL;
+ break;
+ case RTAS_IBM_GET_VPD_START_OVER:
+ ret = -EAGAIN;
+ break;
+ case RTAS_IBM_GET_VPD_MORE_DATA:
+ params->sequence = rets[0];
+ fallthrough;
+ case RTAS_IBM_GET_VPD_COMPLETE:
+ params->written = rets[1];
+ /*
+ * Kernel or firmware bug, do not continue.
+ */
+ if (WARN(params->written > rtas_work_area_size(work_area),
+ "possible write beyond end of work area"))
+ ret = -EFAULT;
+ else
+ ret = 0;
+ break;
+ default:
+ ret = -EIO;
+ pr_err_ratelimited("unexpected ibm,get-vpd status %d\n", fwrc);
+ break;
+ }
+
+ params->status = fwrc;
+ return ret;
+}
+
+/*
+ * Internal VPD "blob" APIs for accumulating ibm,get-vpd results into
+ * an immutable buffer to be attached to a file descriptor.
+ */
+struct vpd_blob {
+ const char *data;
+ size_t len;
+};
+
+static bool vpd_blob_has_data(const struct vpd_blob *blob)
+{
+ return blob->data && blob->len;
+}
+
+static void vpd_blob_free(const struct vpd_blob *blob)
+{
+ if (blob) {
+ kvfree(blob->data);
+ kfree(blob);
+ }
+}
+
+/**
+ * vpd_blob_extend() - Append data to a &struct vpd_blob.
+ * @blob: The blob to extend.
+ * @data: The new data to append to @blob.
+ * @len: The length of @data.
+ *
+ * Context: May sleep.
+ * Return: -ENOMEM on allocation failure, 0 otherwise.
+ */
+static int vpd_blob_extend(struct vpd_blob *blob, const char *data, size_t len)
+{
+ const size_t new_len = blob->len + len;
+ const size_t old_len = blob->len;
+ const char *old_ptr = blob->data;
+ char *new_ptr;
+
+ new_ptr = old_ptr ?
+ kvrealloc(old_ptr, old_len, new_len, GFP_KERNEL_ACCOUNT) :
+ kvmalloc(len, GFP_KERNEL_ACCOUNT);
+
+ if (!new_ptr)
+ return -ENOMEM;
+
+ memcpy(&new_ptr[old_len], data, len);
+ blob->data = new_ptr;
+ blob->len = new_len;
+ return 0;
+}
+
+/**
+ * vpd_blob_generate() - Construct a new &struct vpd_blob.
+ * @generator: Function that supplies the blob data.
+ * @arg: Context pointer supplied by caller, passed to @generator.
+ *
+ * The @generator callback is invoked until it returns NULL. @arg is
+ * passed to @generator in its first argument on each call. When
+ * @generator returns data, it should store the data length in its
+ * second argument.
+ *
+ * Context: May sleep.
+ * Return: A completely populated &struct vpd_blob, or NULL on error.
+ */
+static const struct vpd_blob *
+vpd_blob_generate(const char * (*generator)(void *, size_t *), void *arg)
+{
+ struct vpd_blob *blob;
+ const char *buf;
+ size_t len;
+ int err = 0;
+
+ blob = kzalloc(sizeof(*blob), GFP_KERNEL_ACCOUNT);
+ if (!blob)
+ return NULL;
+
+ while (err == 0 && (buf = generator(arg, &len)))
+ err = vpd_blob_extend(blob, buf, len);
+
+ if (err != 0 || !vpd_blob_has_data(blob))
+ goto free_blob;
+
+ return blob;
+free_blob:
+ vpd_blob_free(blob);
+ return NULL;
+}
+
+/*
+ * Internal VPD sequence APIs. A VPD sequence is a series of calls to
+ * ibm,get-vpd for a given location code. The sequence ends when an
+ * error is encountered or all VPD for the location code has been
+ * returned.
+ */
+
+/**
+ * struct vpd_sequence - State for managing a VPD sequence.
+ * @error: Shall be zero as long as the sequence has not encountered an error,
+ * -ve errno otherwise. Use vpd_sequence_set_err() to update this.
+ * @params: Parameter block to pass to rtas_ibm_get_vpd().
+ */
+struct vpd_sequence {
+ int error;
+ struct rtas_ibm_get_vpd_params params;
+};
+
+/**
+ * vpd_sequence_begin() - Begin a VPD retrieval sequence.
+ * @seq: Uninitialized sequence state.
+ * @loc_code: Location code that defines the scope of the VPD to return.
+ *
+ * Initializes @seq with the resources necessary to carry out a VPD
+ * sequence. Callers must pass @seq to vpd_sequence_end() regardless
+ * of whether the sequence succeeds.
+ *
+ * Context: May sleep.
+ */
+static void vpd_sequence_begin(struct vpd_sequence *seq,
+ const struct papr_location_code *loc_code)
+{
+ /*
+ * Use a static data structure for the location code passed to
+ * RTAS to ensure it's in the RMA and avoid a separate work
+ * area allocation. Guarded by the function lock.
+ */
+ static struct papr_location_code static_loc_code;
+
+ /*
+ * We could allocate the work area before acquiring the
+ * function lock, but that would allow concurrent requests to
+ * exhaust the limited work area pool for no benefit. So
+ * allocate the work area under the lock.
+ */
+ mutex_lock(&rtas_ibm_get_vpd_lock);
+ static_loc_code = *loc_code;
+ *seq = (struct vpd_sequence) {
+ .params = {
+ .work_area = rtas_work_area_alloc(SZ_4K),
+ .loc_code = &static_loc_code,
+ .sequence = 1,
+ },
+ };
+}
+
+/**
+ * vpd_sequence_end() - Finalize a VPD retrieval sequence.
+ * @seq: Sequence state.
+ *
+ * Releases resources obtained by vpd_sequence_begin().
+ */
+static void vpd_sequence_end(struct vpd_sequence *seq)
+{
+ rtas_work_area_free(seq->params.work_area);
+ mutex_unlock(&rtas_ibm_get_vpd_lock);
+}
+
+/**
+ * vpd_sequence_should_stop() - Determine whether a VPD retrieval sequence
+ * should continue.
+ * @seq: VPD sequence state.
+ *
+ * Examines the sequence error state and outputs of the last call to
+ * ibm,get-vpd to determine whether the sequence in progress should
+ * continue or stop.
+ *
+ * Return: True if the sequence has encountered an error or if all VPD for
+ * this sequence has been retrieved. False otherwise.
+ */
+static bool vpd_sequence_should_stop(const struct vpd_sequence *seq)
+{
+ bool done;
+
+ if (seq->error)
+ return true;
+
+ switch (seq->params.status) {
+ case 0:
+ if (seq->params.written == 0)
+ done = false; /* Initial state. */
+ else
+ done = true; /* All data consumed. */
+ break;
+ case 1:
+ done = false; /* More data available. */
+ break;
+ default:
+ done = true; /* Error encountered. */
+ break;
+ }
+
+ return done;
+}
+
+static int vpd_sequence_set_err(struct vpd_sequence *seq, int err)
+{
+ /* Preserve the first error recorded. */
+ if (seq->error == 0)
+ seq->error = err;
+
+ return seq->error;
+}
+
+/*
+ * Generator function to be passed to vpd_blob_generate().
+ */
+static const char *vpd_sequence_fill_work_area(void *arg, size_t *len)
+{
+ struct vpd_sequence *seq = arg;
+ struct rtas_ibm_get_vpd_params *p = &seq->params;
+
+ if (vpd_sequence_should_stop(seq))
+ return NULL;
+ if (vpd_sequence_set_err(seq, rtas_ibm_get_vpd(p)))
+ return NULL;
+ *len = p->written;
+ return rtas_work_area_raw_buf(p->work_area);
+}
+
+/*
+ * Higher-level VPD retrieval code below. These functions use the
+ * vpd_blob_* and vpd_sequence_* APIs defined above to create fd-based
+ * VPD handles for consumption by user space.
+ */
+
+/**
+ * papr_vpd_run_sequence() - Run a single VPD retrieval sequence.
+ * @loc_code: Location code that defines the scope of VPD to return.
+ *
+ * Context: May sleep. Holds a mutex and an RTAS work area for its
+ * duration. Typically performs multiple sleepable slab
+ * allocations.
+ *
+ * Return: A populated &struct vpd_blob on success. Encoded error
+ * pointer otherwise.
+ */
+static const struct vpd_blob *papr_vpd_run_sequence(const struct papr_location_code *loc_code)
+{
+ const struct vpd_blob *blob;
+ struct vpd_sequence seq;
+
+ vpd_sequence_begin(&seq, loc_code);
+ blob = vpd_blob_generate(vpd_sequence_fill_work_area, &seq);
+ if (!blob)
+ vpd_sequence_set_err(&seq, -ENOMEM);
+ vpd_sequence_end(&seq);
+
+ if (seq.error) {
+ vpd_blob_free(blob);
+ return ERR_PTR(seq.error);
+ }
+
+ return blob;
+}
+
+/**
+ * papr_vpd_retrieve() - Return the VPD for a location code.
+ * @loc_code: Location code that defines the scope of VPD to return.
+ *
+ * Run VPD sequences against @loc_code until a blob is successfully
+ * instantiated, or a hard error is encountered, or a fatal signal is
+ * pending.
+ *
+ * Context: May sleep.
+ * Return: A fully populated VPD blob when successful. Encoded error
+ * pointer otherwise.
+ */
+static const struct vpd_blob *papr_vpd_retrieve(const struct papr_location_code *loc_code)
+{
+ const struct vpd_blob *blob;
+
+ /*
+ * EAGAIN means the sequence errored with a -4 (VPD changed)
+ * status from ibm,get-vpd, and we should attempt a new
+ * sequence. PAPR+ v2.13 R1–7.3.20–5 indicates that this
+ * should be a transient condition, not something that happens
+ * continuously. But we'll stop trying on a fatal signal.
+ */
+ do {
+ blob = papr_vpd_run_sequence(loc_code);
+ if (!IS_ERR(blob)) /* Success. */
+ break;
+ if (PTR_ERR(blob) != -EAGAIN) /* Hard error. */
+ break;
+ pr_info_ratelimited("VPD changed during retrieval, retrying\n");
+ cond_resched();
+ } while (!fatal_signal_pending(current));
+
+ return blob;
+}
+
+static ssize_t papr_vpd_handle_read(struct file *file, char __user *buf, size_t size, loff_t *off)
+{
+ const struct vpd_blob *blob = file->private_data;
+
+ /* bug: we should not instantiate a handle without any data attached. */
+ if (!vpd_blob_has_data(blob)) {
+ pr_err_once("handle without data\n");
+ return -EIO;
+ }
+
+ return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
+}
+
+static int papr_vpd_handle_release(struct inode *inode, struct file *file)
+{
+ const struct vpd_blob *blob = file->private_data;
+
+ vpd_blob_free(blob);
+
+ return 0;
+}
+
+static loff_t papr_vpd_handle_seek(struct file *file, loff_t off, int whence)
+{
+ const struct vpd_blob *blob = file->private_data;
+
+ return fixed_size_llseek(file, off, whence, blob->len);
+}
+
+
+static const struct file_operations papr_vpd_handle_ops = {
+ .read = papr_vpd_handle_read,
+ .llseek = papr_vpd_handle_seek,
+ .release = papr_vpd_handle_release,
+};
+
+/**
+ * papr_vpd_create_handle() - Create a fd-based handle for reading VPD.
+ * @ulc: Location code in user memory; defines the scope of the VPD to
+ * retrieve.
+ *
+ * Handler for PAPR_VPD_IOC_CREATE_HANDLE ioctl command. Validates
+ * @ulc and instantiates an immutable VPD "blob" for it. The blob is
+ * attached to a file descriptor for reading by user space. The memory
+ * backing the blob is freed when the file is released.
+ *
+ * The entire requested VPD is retrieved by this call and all
+ * necessary RTAS interactions are performed before returning the fd
+ * to user space. This keeps the read handler simple and ensures that
+ * the kernel can prevent interleaving of ibm,get-vpd call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_vpd_create_handle(struct papr_location_code __user *ulc)
+{
+ struct papr_location_code klc;
+ const struct vpd_blob *blob;
+ struct file *file;
+ long err;
+ int fd;
+
+ if (copy_from_user(&klc, ulc, sizeof(klc)))
+ return -EFAULT;
+
+ if (!string_is_terminated(klc.str, ARRAY_SIZE(klc.str)))
+ return -EINVAL;
+
+ blob = papr_vpd_retrieve(&klc);
+ if (IS_ERR(blob))
+ return PTR_ERR(blob);
+
+ fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
+ if (fd < 0) {
+ err = fd;
+ goto free_blob;
+ }
+
+ file = anon_inode_getfile("[papr-vpd]", &papr_vpd_handle_ops,
+ (void *)blob, O_RDONLY);
+ if (IS_ERR(file)) {
+ err = PTR_ERR(file);
+ goto put_fd;
+ }
+
+ file->f_mode |= FMODE_LSEEK | FMODE_PREAD;
+ fd_install(fd, file);
+ return fd;
+put_fd:
+ put_unused_fd(fd);
+free_blob:
+ vpd_blob_free(blob);
+ return err;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-vpd.
+ */
+static long papr_vpd_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+ void __user *argp = (__force void __user *)arg;
+ long ret;
+
+ switch (ioctl) {
+ case PAPR_VPD_IOC_CREATE_HANDLE:
+ ret = papr_vpd_create_handle(argp);
+ break;
+ default:
+ ret = -ENOIOCTLCMD;
+ break;
+ }
+ return ret;
+}
+
+static const struct file_operations papr_vpd_ops = {
+ .unlocked_ioctl = papr_vpd_dev_ioctl,
+};
+
+static struct miscdevice papr_vpd_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "papr-vpd",
+ .fops = &papr_vpd_ops,
+};
+
+static __init int papr_vpd_init(void)
+{
+ if (!rtas_function_implemented(RTAS_FN_IBM_GET_VPD))
+ return -ENODEV;
+
+ return misc_register(&papr_vpd_dev);
+}
+machine_device_initcall(pseries, papr_vpd_init);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 8376f03f932a..bba4ad192b0f 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -55,6 +55,7 @@ extern int dlpar_detach_node(struct device_node *);
extern int dlpar_acquire_drc(u32 drc_index);
extern int dlpar_release_drc(u32 drc_index);
extern int dlpar_unisolate_drc(u32 drc_index);
+extern void post_mobility_fixup(void);
void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog);
int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_errlog);
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 5c43435472cc..382003dfdb9a 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -13,6 +13,7 @@
#include <asm/mmu.h>
#include <asm/rtas.h>
#include <asm/topology.h>
+#include "pseries.h"
static struct device suspend_dev;
diff --git a/arch/powerpc/sysdev/grackle.c b/arch/powerpc/sysdev/grackle.c
index fd2f94a884f0..7dce8278b71e 100644
--- a/arch/powerpc/sysdev/grackle.c
+++ b/arch/powerpc/sysdev/grackle.c
@@ -18,24 +18,8 @@
#define GRACKLE_CFA(b, d, o) (0x80 | ((b) << 8) | ((d) << 16) \
| (((o) & ~3) << 24))
-#define GRACKLE_PICR1_STG 0x00000040
#define GRACKLE_PICR1_LOOPSNOOP 0x00000010
-/* N.B. this is called before bridges is initialized, so we can't
- use grackle_pcibios_{read,write}_config_dword. */
-static inline void grackle_set_stg(struct pci_controller* bp, int enable)
-{
- unsigned int val;
-
- out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8));
- val = in_le32(bp->cfg_data);
- val = enable? (val | GRACKLE_PICR1_STG) :
- (val & ~GRACKLE_PICR1_STG);
- out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8));
- out_le32(bp->cfg_data, val);
- (void)in_le32(bp->cfg_data);
-}
-
static inline void grackle_set_loop_snoop(struct pci_controller *bp, int enable)
{
unsigned int val;
@@ -56,7 +40,4 @@ void __init setup_grackle(struct pci_controller *hose)
pci_add_flags(PCI_REASSIGN_ALL_BUS);
if (of_machine_is_compatible("AAPL,PowerBook1998"))
grackle_set_loop_snoop(hose, 1);
-#if 0 /* Disabled for now, HW problems ??? */
- grackle_set_stg(hose, 1);
-#endif
}
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index f6ec6dba92dc..700b67476a7d 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -236,6 +236,8 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr,
rname = kasprintf(GFP_KERNEL, "CPU %d [0x%x] Interrupt Presentation",
cpu, hw_id);
+ if (!rname)
+ return -ENOMEM;
if (!request_mem_region(addr, size, rname)) {
pr_warn("icp_native: Could not reserve ICP MMIO for CPU %d, interrupt server #0x%x\n",
cpu, hw_id);
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 0562071cdd4a..6ad0ab892675 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -836,7 +836,8 @@ static inline bool cxl_is_power8(void)
{
if ((pvr_version_is(PVR_POWER8E)) ||
(pvr_version_is(PVR_POWER8NVL)) ||
- (pvr_version_is(PVR_POWER8)))
+ (pvr_version_is(PVR_POWER8)) ||
+ (pvr_version_is(PVR_HX_C2000)))
return true;
return false;
}
diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c
index a06920b7e049..36f7379b8e2d 100644
--- a/drivers/misc/ocxl/afu_irq.c
+++ b/drivers/misc/ocxl/afu_irq.c
@@ -57,7 +57,7 @@ EXPORT_SYMBOL_GPL(ocxl_irq_set_handler);
static irqreturn_t afu_irq_handler(int virq, void *data)
{
- struct afu_irq *irq = (struct afu_irq *) data;
+ struct afu_irq *irq = data;
trace_ocxl_afu_irq_receive(virq);
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index 7f83116ae11a..cded7d1caf32 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -55,7 +55,7 @@ EXPORT_SYMBOL_GPL(ocxl_context_alloc);
*/
static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
{
- struct ocxl_context *ctx = (struct ocxl_context *) data;
+ struct ocxl_context *ctx = data;
mutex_lock(&ctx->xsl_error_lock);
ctx->xsl_error.addr = addr;
diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
index c06c699c0e7b..03402203cacd 100644
--- a/drivers/misc/ocxl/link.c
+++ b/drivers/misc/ocxl/link.c
@@ -188,7 +188,7 @@ ack:
static irqreturn_t xsl_fault_handler(int irq, void *data)
{
- struct ocxl_link *link = (struct ocxl_link *) data;
+ struct ocxl_link *link = data;
struct spa *spa = link->spa;
u64 dsisr, dar, pe_handle;
struct pe_data *pe_data;
@@ -483,7 +483,7 @@ static void release_xsl(struct kref *ref)
void ocxl_link_release(struct pci_dev *dev, void *link_handle)
{
- struct ocxl_link *link = (struct ocxl_link *) link_handle;
+ struct ocxl_link *link = link_handle;
mutex_lock(&links_list_lock);
kref_put(&link->ref, release_xsl);
@@ -540,7 +540,7 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
void (*xsl_err_cb)(void *data, u64 addr, u64 dsisr),
void *xsl_err_data)
{
- struct ocxl_link *link = (struct ocxl_link *) link_handle;
+ struct ocxl_link *link = link_handle;
struct spa *spa = link->spa;
struct ocxl_process_element *pe;
int pe_handle, rc = 0;
@@ -630,7 +630,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_add_pe);
int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
{
- struct ocxl_link *link = (struct ocxl_link *) link_handle;
+ struct ocxl_link *link = link_handle;
struct spa *spa = link->spa;
struct ocxl_process_element *pe;
int pe_handle, rc;
@@ -666,7 +666,7 @@ int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
int ocxl_link_remove_pe(void *link_handle, int pasid)
{
- struct ocxl_link *link = (struct ocxl_link *) link_handle;
+ struct ocxl_link *link = link_handle;
struct spa *spa = link->spa;
struct ocxl_process_element *pe;
struct pe_data *pe_data;
@@ -752,7 +752,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_remove_pe);
int ocxl_link_irq_alloc(void *link_handle, int *hw_irq)
{
- struct ocxl_link *link = (struct ocxl_link *) link_handle;
+ struct ocxl_link *link = link_handle;
int irq;
if (atomic_dec_if_positive(&link->irq_available) < 0)
@@ -771,7 +771,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_irq_alloc);
void ocxl_link_free_irq(void *link_handle, int hw_irq)
{
- struct ocxl_link *link = (struct ocxl_link *) link_handle;
+ struct ocxl_link *link = link_handle;
xive_native_free_irq(hw_irq);
atomic_inc(&link->irq_available);
diff --git a/drivers/misc/ocxl/main.c b/drivers/misc/ocxl/main.c
index ef73cf35dda2..658974143c3c 100644
--- a/drivers/misc/ocxl/main.c
+++ b/drivers/misc/ocxl/main.c
@@ -7,7 +7,7 @@
static int __init init_ocxl(void)
{
- int rc = 0;
+ int rc;
if (!tlbie_capable)
return -EINVAL;
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h
index 0d98defb011e..0ec7412febc7 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h
@@ -346,12 +346,6 @@ static inline void *port_priv(struct gelic_port *port)
return port->priv;
}
-#ifdef CONFIG_PPC_EARLY_DEBUG_PS3GELIC
-void udbg_shutdown_ps3gelic(void);
-#else
-static inline void udbg_shutdown_ps3gelic(void) {}
-#endif
-
int gelic_card_set_irq_mask(struct gelic_card *card, u64 mask);
/* shared netdev ops */
void gelic_card_up(struct gelic_card *card);
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 7ea42fa02eab..c376151982c4 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -32,6 +32,8 @@ SUB_DIRS = alignment \
vphn \
math \
papr_attributes \
+ papr_vpd \
+ papr_sysparm \
ptrace \
security \
mce
diff --git a/tools/testing/selftests/powerpc/math/fpu.h b/tools/testing/selftests/powerpc/math/fpu.h
new file mode 100644
index 000000000000..a8ad0d42604e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2023, Michael Ellerman, IBM Corporation.
+ */
+
+#ifndef _SELFTESTS_POWERPC_FPU_H
+#define _SELFTESTS_POWERPC_FPU_H
+
+static inline void randomise_darray(double *darray, int num)
+{
+ long val;
+
+ for (int i = 0; i < num; i++) {
+ val = random();
+ if (val & 1)
+ val *= -1;
+
+ if (val & 2)
+ darray[i] = 1.0 / val;
+ else
+ darray[i] = val * val;
+ }
+}
+
+#endif /* _SELFTESTS_POWERPC_FPU_H */
diff --git a/tools/testing/selftests/powerpc/math/fpu_asm.S b/tools/testing/selftests/powerpc/math/fpu_asm.S
index 9dc0c158f871..efe1e1be4695 100644
--- a/tools/testing/selftests/powerpc/math/fpu_asm.S
+++ b/tools/testing/selftests/powerpc/math/fpu_asm.S
@@ -66,6 +66,40 @@ FUNC_START(check_fpu)
li r3,0 # Success!!!
1: blr
+
+// int check_all_fprs(double darray[32])
+FUNC_START(check_all_fprs)
+ PUSH_BASIC_STACK(8)
+ mr r4, r3 // r4 = darray
+ li r3, 1 // prepare for failure
+
+ stfd f31, STACK_FRAME_LOCAL(0, 0)(sp) // backup f31
+
+ // Check regs f0-f30, using f31 as scratch
+ .set i, 0
+ .rept 31
+ lfd f31, (8 * i)(r4) // load expected value
+ fcmpu cr0, i, f31 // compare
+ bne cr0, 1f // bail if mismatch
+ .set i, i + 1
+ .endr
+
+ lfd f31, STACK_FRAME_LOCAL(0, 0)(sp) // reload f31
+ stfd f30, STACK_FRAME_LOCAL(0, 0)(sp) // backup f30
+
+ lfd f30, (8 * 31)(r4) // load expected value of f31
+ fcmpu cr0, f30, f31 // compare
+ bne cr0, 1f // bail if mismatch
+
+ lfd f30, STACK_FRAME_LOCAL(0, 0)(sp) // reload f30
+
+ // Success
+ li r3, 0
+
+1: POP_BASIC_STACK(8)
+ blr
+FUNC_END(check_all_fprs)
+
FUNC_START(test_fpu)
# r3 holds pointer to where to put the result of fork
# r4 holds pointer to the pid
@@ -75,8 +109,9 @@ FUNC_START(test_fpu)
std r3,STACK_FRAME_PARAM(0)(sp) # Address of darray
std r4,STACK_FRAME_PARAM(1)(sp) # Address of pid
- bl load_fpu
- nop
+ // Load FPRs with expected values
+ OP_REGS lfd, 8, 0, 31, r3
+
li r0,__NR_fork
sc
@@ -85,7 +120,7 @@ FUNC_START(test_fpu)
std r3,0(r9)
ld r3,STACK_FRAME_PARAM(0)(sp)
- bl check_fpu
+ bl check_all_fprs
nop
POP_FPU(256)
@@ -104,8 +139,8 @@ FUNC_START(preempt_fpu)
std r4,STACK_FRAME_PARAM(1)(sp) # int *threads_starting
std r5,STACK_FRAME_PARAM(2)(sp) # int *running
- bl load_fpu
- nop
+ // Load FPRs with expected values
+ OP_REGS lfd, 8, 0, 31, r3
sync
# Atomic DEC
@@ -116,8 +151,7 @@ FUNC_START(preempt_fpu)
bne- 1b
2: ld r3,STACK_FRAME_PARAM(0)(sp)
- bl check_fpu
- nop
+ bl check_all_fprs
cmpdi r3,0
bne 3f
ld r4,STACK_FRAME_PARAM(2)(sp)
diff --git a/tools/testing/selftests/powerpc/math/fpu_preempt.c b/tools/testing/selftests/powerpc/math/fpu_preempt.c
index 5235bdc8c0b1..9ddede0770ed 100644
--- a/tools/testing/selftests/powerpc/math/fpu_preempt.c
+++ b/tools/testing/selftests/powerpc/math/fpu_preempt.c
@@ -1,13 +1,12 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright 2015, Cyril Bur, IBM Corp.
+ * Copyright 2023, Michael Ellerman, IBM Corp.
*
* This test attempts to see if the FPU registers change across preemption.
- * Two things should be noted here a) The check_fpu function in asm only checks
- * the non volatile registers as it is reused from the syscall test b) There is
- * no way to be sure preemption happened so this test just uses many threads
- * and a long wait. As such, a successful test doesn't mean much but a failure
- * is bad.
+ * There is no way to be sure preemption happened so this test just uses many
+ * threads and a long wait. As such, a successful test doesn't mean much but
+ * a failure is bad.
*/
#include <stdio.h>
@@ -20,9 +19,10 @@
#include <pthread.h>
#include "utils.h"
+#include "fpu.h"
/* Time to wait for workers to get preempted (seconds) */
-#define PREEMPT_TIME 20
+#define PREEMPT_TIME 60
/*
* Factor by which to multiply number of online CPUs for total number of
* worker threads
@@ -30,26 +30,22 @@
#define THREAD_FACTOR 8
-__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
- 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
- 2.1};
+__thread double darray[32];
int threads_starting;
int running;
-extern void preempt_fpu(double *darray, int *threads_starting, int *running);
+extern int preempt_fpu(double *darray, int *threads_starting, int *running);
void *preempt_fpu_c(void *p)
{
- int i;
- srand(pthread_self());
- for (i = 0; i < 21; i++)
- darray[i] = rand();
+ long rc;
- /* Test failed if it ever returns */
- preempt_fpu(darray, &threads_starting, &running);
+ srand(pthread_self());
+ randomise_darray(darray, ARRAY_SIZE(darray));
+ rc = preempt_fpu(darray, &threads_starting, &running);
- return p;
+ return (void *)rc;
}
int test_preempt_fpu(void)
diff --git a/tools/testing/selftests/powerpc/math/fpu_syscall.c b/tools/testing/selftests/powerpc/math/fpu_syscall.c
index 694f225c7e45..751d46b133fc 100644
--- a/tools/testing/selftests/powerpc/math/fpu_syscall.c
+++ b/tools/testing/selftests/powerpc/math/fpu_syscall.c
@@ -14,12 +14,11 @@
#include <stdlib.h>
#include "utils.h"
+#include "fpu.h"
extern int test_fpu(double *darray, pid_t *pid);
-double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
- 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
- 2.1};
+double darray[32];
int syscall_fpu(void)
{
@@ -27,6 +26,9 @@ int syscall_fpu(void)
int i;
int ret;
int child_ret;
+
+ randomise_darray(darray, ARRAY_SIZE(darray));
+
for (i = 0; i < 1000; i++) {
/* test_fpu will fork() */
ret = test_fpu(darray, &fork_pid);
diff --git a/tools/testing/selftests/powerpc/math/vmx_preempt.c b/tools/testing/selftests/powerpc/math/vmx_preempt.c
index 6761d6ce30ec..6f7cf400c687 100644
--- a/tools/testing/selftests/powerpc/math/vmx_preempt.c
+++ b/tools/testing/selftests/powerpc/math/vmx_preempt.c
@@ -37,19 +37,21 @@ __thread vector int varray[] = {{1, 2, 3, 4}, {5, 6, 7, 8}, {9, 10,11,12},
int threads_starting;
int running;
-extern void preempt_vmx(vector int *varray, int *threads_starting, int *running);
+extern int preempt_vmx(vector int *varray, int *threads_starting, int *running);
void *preempt_vmx_c(void *p)
{
int i, j;
+ long rc;
+
srand(pthread_self());
for (i = 0; i < 12; i++)
for (j = 0; j < 4; j++)
varray[i][j] = rand();
- /* Test fails if it ever returns */
- preempt_vmx(varray, &threads_starting, &running);
- return p;
+ rc = preempt_vmx(varray, &threads_starting, &running);
+
+ return (void *)rc;
}
int test_preempt_vmx(void)
diff --git a/tools/testing/selftests/powerpc/papr_sysparm/.gitignore b/tools/testing/selftests/powerpc/papr_sysparm/.gitignore
new file mode 100644
index 000000000000..f2a69bf59d40
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_sysparm/.gitignore
@@ -0,0 +1 @@
+/papr_sysparm
diff --git a/tools/testing/selftests/powerpc/papr_sysparm/Makefile b/tools/testing/selftests/powerpc/papr_sysparm/Makefile
new file mode 100644
index 000000000000..7f79e437634a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_sysparm/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+noarg:
+ $(MAKE) -C ../
+
+TEST_GEN_PROGS := papr_sysparm
+
+top_srcdir = ../../../../..
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
+
+$(OUTPUT)/papr_sysparm: CFLAGS += $(KHDR_INCLUDES)
diff --git a/tools/testing/selftests/powerpc/papr_sysparm/papr_sysparm.c b/tools/testing/selftests/powerpc/papr_sysparm/papr_sysparm.c
new file mode 100644
index 000000000000..f56c15a11e2f
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_sysparm/papr_sysparm.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+#include <asm/papr-sysparm.h>
+
+#include "utils.h"
+
+#define DEVPATH "/dev/papr-sysparm"
+
+static int open_close(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+ FAIL_IF(close(devfd) != 0);
+
+ return 0;
+}
+
+static int get_splpar(void)
+{
+ struct papr_sysparm_io_block sp = {
+ .parameter = 20, // SPLPAR characteristics
+ };
+ const int devfd = open(DEVPATH, O_RDONLY);
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+ FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_GET, &sp) != 0);
+ FAIL_IF(sp.length == 0);
+ FAIL_IF(sp.length > sizeof(sp.data));
+ FAIL_IF(close(devfd) != 0);
+
+ return 0;
+}
+
+static int get_bad_parameter(void)
+{
+ struct papr_sysparm_io_block sp = {
+ .parameter = UINT32_MAX, // there are only ~60 specified parameters
+ };
+ const int devfd = open(DEVPATH, O_RDONLY);
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ // Ensure expected error
+ FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_GET, &sp) != -1);
+ FAIL_IF(errno != EOPNOTSUPP);
+
+ // Ensure the buffer is unchanged
+ FAIL_IF(sp.length != 0);
+ for (size_t i = 0; i < ARRAY_SIZE(sp.data); ++i)
+ FAIL_IF(sp.data[i] != 0);
+
+ FAIL_IF(close(devfd) != 0);
+
+ return 0;
+}
+
+static int check_efault_common(unsigned long cmd)
+{
+ const int devfd = open(DEVPATH, O_RDWR);
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ // Ensure expected error
+ FAIL_IF(ioctl(devfd, cmd, NULL) != -1);
+ FAIL_IF(errno != EFAULT);
+
+ FAIL_IF(close(devfd) != 0);
+
+ return 0;
+}
+
+static int check_efault_get(void)
+{
+ return check_efault_common(PAPR_SYSPARM_IOC_GET);
+}
+
+static int check_efault_set(void)
+{
+ return check_efault_common(PAPR_SYSPARM_IOC_SET);
+}
+
+static int set_hmc0(void)
+{
+ struct papr_sysparm_io_block sp = {
+ .parameter = 0, // HMC0, not a settable parameter
+ };
+ const int devfd = open(DEVPATH, O_RDWR);
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ // Ensure expected error
+ FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_SET, &sp) != -1);
+ SKIP_IF_MSG(errno == EOPNOTSUPP, "operation not supported");
+ FAIL_IF(errno != EPERM);
+
+ FAIL_IF(close(devfd) != 0);
+
+ return 0;
+}
+
+static int set_with_ro_fd(void)
+{
+ struct papr_sysparm_io_block sp = {
+ .parameter = 0, // HMC0, not a settable parameter.
+ };
+ const int devfd = open(DEVPATH, O_RDONLY);
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ // Ensure expected error
+ FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_SET, &sp) != -1);
+ SKIP_IF_MSG(errno == EOPNOTSUPP, "operation not supported");
+
+ // HMC0 isn't a settable parameter and we would normally
+ // expect to get EPERM on attempts to modify it. However, when
+ // the file is open read-only, we expect the driver to prevent
+ // the attempt with a distinct error.
+ FAIL_IF(errno != EBADF);
+
+ FAIL_IF(close(devfd) != 0);
+
+ return 0;
+}
+
+struct sysparm_test {
+ int (*function)(void);
+ const char *description;
+};
+
+static const struct sysparm_test sysparm_tests[] = {
+ {
+ .function = open_close,
+ .description = "open and close " DEVPATH " without issuing commands",
+ },
+ {
+ .function = get_splpar,
+ .description = "retrieve SPLPAR characteristics",
+ },
+ {
+ .function = get_bad_parameter,
+ .description = "verify EOPNOTSUPP for known-bad parameter",
+ },
+ {
+ .function = check_efault_get,
+ .description = "PAPR_SYSPARM_IOC_GET returns EFAULT on bad address",
+ },
+ {
+ .function = check_efault_set,
+ .description = "PAPR_SYSPARM_IOC_SET returns EFAULT on bad address",
+ },
+ {
+ .function = set_hmc0,
+ .description = "ensure EPERM on attempt to update HMC0",
+ },
+ {
+ .function = set_with_ro_fd,
+ .description = "PAPR_IOC_SYSPARM_SET returns EACCES on read-only fd",
+ },
+};
+
+int main(void)
+{
+ size_t fails = 0;
+
+ for (size_t i = 0; i < ARRAY_SIZE(sysparm_tests); ++i) {
+ const struct sysparm_test *t = &sysparm_tests[i];
+
+ if (test_harness(t->function, t->description))
+ ++fails;
+ }
+
+ return fails == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
+}
diff --git a/tools/testing/selftests/powerpc/papr_vpd/.gitignore b/tools/testing/selftests/powerpc/papr_vpd/.gitignore
new file mode 100644
index 000000000000..49285031a656
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_vpd/.gitignore
@@ -0,0 +1 @@
+/papr_vpd
diff --git a/tools/testing/selftests/powerpc/papr_vpd/Makefile b/tools/testing/selftests/powerpc/papr_vpd/Makefile
new file mode 100644
index 000000000000..06b719703bfd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_vpd/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+noarg:
+ $(MAKE) -C ../
+
+TEST_GEN_PROGS := papr_vpd
+
+top_srcdir = ../../../../..
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
+
+$(OUTPUT)/papr_vpd: CFLAGS += $(KHDR_INCLUDES)
diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
new file mode 100644
index 000000000000..98cbb9109ee6
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+#include <asm/papr-vpd.h>
+
+#include "utils.h"
+
+#define DEVPATH "/dev/papr-vpd"
+
+static int dev_papr_vpd_open_close(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+ FAIL_IF(close(devfd) != 0);
+
+ return 0;
+}
+
+static int dev_papr_vpd_get_handle_all(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+ struct papr_location_code lc = { .str = "", };
+ off_t size;
+ int fd;
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ errno = 0;
+ fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+ FAIL_IF(errno != 0);
+ FAIL_IF(fd < 0);
+
+ FAIL_IF(close(devfd) != 0);
+
+ size = lseek(fd, 0, SEEK_END);
+ FAIL_IF(size <= 0);
+
+ void *buf = malloc((size_t)size);
+ FAIL_IF(!buf);
+
+ ssize_t consumed = pread(fd, buf, size, 0);
+ FAIL_IF(consumed != size);
+
+ /* Ensure EOF */
+ FAIL_IF(read(fd, buf, size) != 0);
+ FAIL_IF(close(fd));
+
+ /* Verify that the buffer looks like VPD */
+ static const char needle[] = "System VPD";
+ FAIL_IF(!memmem(buf, size, needle, strlen(needle)));
+
+ return 0;
+}
+
+static int dev_papr_vpd_get_handle_byte_at_a_time(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+ struct papr_location_code lc = { .str = "", };
+ int fd;
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ errno = 0;
+ fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+ FAIL_IF(errno != 0);
+ FAIL_IF(fd < 0);
+
+ FAIL_IF(close(devfd) != 0);
+
+ size_t consumed = 0;
+ while (1) {
+ ssize_t res;
+ char c;
+
+ errno = 0;
+ res = read(fd, &c, sizeof(c));
+ FAIL_IF(res > sizeof(c));
+ FAIL_IF(res < 0);
+ FAIL_IF(errno != 0);
+ consumed += res;
+ if (res == 0)
+ break;
+ }
+
+ FAIL_IF(consumed != lseek(fd, 0, SEEK_END));
+
+ FAIL_IF(close(fd));
+
+ return 0;
+}
+
+
+static int dev_papr_vpd_unterm_loc_code(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+ struct papr_location_code lc = {};
+ int fd;
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ /*
+ * Place a non-null byte in every element of loc_code; the
+ * driver should reject this input.
+ */
+ memset(lc.str, 'x', ARRAY_SIZE(lc.str));
+
+ errno = 0;
+ fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+ FAIL_IF(fd != -1);
+ FAIL_IF(errno != EINVAL);
+
+ FAIL_IF(close(devfd) != 0);
+ return 0;
+}
+
+static int dev_papr_vpd_null_handle(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+ int rc;
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ errno = 0;
+ rc = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, NULL);
+ FAIL_IF(rc != -1);
+ FAIL_IF(errno != EFAULT);
+
+ FAIL_IF(close(devfd) != 0);
+ return 0;
+}
+
+static int papr_vpd_close_handle_without_reading(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+ struct papr_location_code lc;
+ int fd;
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ errno = 0;
+ fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+ FAIL_IF(errno != 0);
+ FAIL_IF(fd < 0);
+
+ /* close the handle without reading it */
+ FAIL_IF(close(fd) != 0);
+
+ FAIL_IF(close(devfd) != 0);
+ return 0;
+}
+
+static int papr_vpd_reread(void)
+{
+ const int devfd = open(DEVPATH, O_RDONLY);
+ struct papr_location_code lc = { .str = "", };
+ int fd;
+
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ errno = 0;
+ fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+ FAIL_IF(errno != 0);
+ FAIL_IF(fd < 0);
+
+ FAIL_IF(close(devfd) != 0);
+
+ const off_t size = lseek(fd, 0, SEEK_END);
+ FAIL_IF(size <= 0);
+
+ char *bufs[2];
+
+ for (size_t i = 0; i < ARRAY_SIZE(bufs); ++i) {
+ bufs[i] = malloc(size);
+ FAIL_IF(!bufs[i]);
+ ssize_t consumed = pread(fd, bufs[i], size, 0);
+ FAIL_IF(consumed != size);
+ }
+
+ FAIL_IF(memcmp(bufs[0], bufs[1], size));
+
+ FAIL_IF(close(fd) != 0);
+
+ return 0;
+}
+
+static int get_system_loc_code(struct papr_location_code *lc)
+{
+ static const char system_id_path[] = "/sys/firmware/devicetree/base/system-id";
+ static const char model_path[] = "/sys/firmware/devicetree/base/model";
+ char *system_id;
+ char *model;
+ int err = -1;
+
+ if (read_file_alloc(model_path, &model, NULL))
+ return err;
+
+ if (read_file_alloc(system_id_path, &system_id, NULL))
+ goto free_model;
+
+ char *mtm;
+ int sscanf_ret = sscanf(model, "IBM,%ms", &mtm);
+ if (sscanf_ret != 1)
+ goto free_system_id;
+
+ char *plant_and_seq;
+ if (sscanf(system_id, "IBM,%*c%*c%ms", &plant_and_seq) != 1)
+ goto free_mtm;
+ /*
+ * Replace - with . to build location code.
+ */
+ char *sep = strchr(mtm, '-');
+ if (!sep)
+ goto free_mtm;
+ else
+ *sep = '.';
+
+ snprintf(lc->str, sizeof(lc->str),
+ "U%s.%s", mtm, plant_and_seq);
+ err = 0;
+
+ free(plant_and_seq);
+free_mtm:
+ free(mtm);
+free_system_id:
+ free(system_id);
+free_model:
+ free(model);
+ return err;
+}
+
+static int papr_vpd_system_loc_code(void)
+{
+ struct papr_location_code lc;
+ const int devfd = open(DEVPATH, O_RDONLY);
+ off_t size;
+ int fd;
+
+ SKIP_IF_MSG(get_system_loc_code(&lc),
+ "Cannot determine system location code");
+ SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+ DEVPATH " not present");
+
+ FAIL_IF(devfd < 0);
+
+ errno = 0;
+ fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+ FAIL_IF(errno != 0);
+ FAIL_IF(fd < 0);
+
+ FAIL_IF(close(devfd) != 0);
+
+ size = lseek(fd, 0, SEEK_END);
+ FAIL_IF(size <= 0);
+
+ void *buf = malloc((size_t)size);
+ FAIL_IF(!buf);
+
+ ssize_t consumed = pread(fd, buf, size, 0);
+ FAIL_IF(consumed != size);
+
+ /* Ensure EOF */
+ FAIL_IF(read(fd, buf, size) != 0);
+ FAIL_IF(close(fd));
+
+ /* Verify that the buffer looks like VPD */
+ static const char needle[] = "System VPD";
+ FAIL_IF(!memmem(buf, size, needle, strlen(needle)));
+
+ return 0;
+}
+
+struct vpd_test {
+ int (*function)(void);
+ const char *description;
+};
+
+static const struct vpd_test vpd_tests[] = {
+ {
+ .function = dev_papr_vpd_open_close,
+ .description = "open/close " DEVPATH,
+ },
+ {
+ .function = dev_papr_vpd_unterm_loc_code,
+ .description = "ensure EINVAL on unterminated location code",
+ },
+ {
+ .function = dev_papr_vpd_null_handle,
+ .description = "ensure EFAULT on bad handle addr",
+ },
+ {
+ .function = dev_papr_vpd_get_handle_all,
+ .description = "get handle for all VPD"
+ },
+ {
+ .function = papr_vpd_close_handle_without_reading,
+ .description = "close handle without consuming VPD"
+ },
+ {
+ .function = dev_papr_vpd_get_handle_byte_at_a_time,
+ .description = "read all VPD one byte at a time"
+ },
+ {
+ .function = papr_vpd_reread,
+ .description = "ensure re-read yields same results"
+ },
+ {
+ .function = papr_vpd_system_loc_code,
+ .description = "get handle for system VPD"
+ },
+};
+
+int main(void)
+{
+ size_t fails = 0;
+
+ for (size_t i = 0; i < ARRAY_SIZE(vpd_tests); ++i) {
+ const struct vpd_test *t = &vpd_tests[i];
+
+ if (test_harness(t->function, t->description))
+ ++fails;
+ }
+
+ return fails == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
+}