diff options
Diffstat (limited to 'arch/powerpc')
246 files changed, 7139 insertions, 2500 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 54b9387c3691..b9fc064d38d2 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 @@ -237,6 +238,7 @@ config PPC select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1 select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER @@ -255,7 +257,7 @@ config PPC select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES - select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT + select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT && (!ARCH_USING_PATCHABLE_FUNCTION_ENTRY || (!CC_IS_GCC || GCC_VERSION >= 110100)) select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) @@ -607,10 +609,10 @@ config ARCH_SUPPORTS_KEXEC def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP) config ARCH_SUPPORTS_KEXEC_FILE - def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y + def_bool PPC64 config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -857,6 +859,7 @@ config THREAD_SHIFT int "Thread shift" if EXPERT range 13 15 default "15" if PPC_256K_PAGES + default "15" if PPC_PSERIES || PPC_POWERNV default "14" if PPC64 default "13" help @@ -910,11 +913,11 @@ config ARCH_FORCE_MAX_ORDER default "6" if PPC32 && PPC_64K_PAGES range 4 10 if PPC32 && PPC_256K_PAGES default "4" if PPC32 && PPC_256K_PAGES - range 10 10 + range 10 12 default "10" help The kernel page allocator limits the size of maximal physically - contiguous allocations. The limit is called MAX_ORDER and it + contiguous allocations. The limit is called MAX_PAGE_ORDER and it defines the maximal power of two of number of pages that can be allocated as a single contiguous block. This option allows overriding the default setting when ability to allocate very diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 2a54fadbeaf5..8c80b154e814 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -82,6 +82,18 @@ config MSI_BITMAP_SELFTEST bool "Run self-tests of the MSI bitmap code" depends on DEBUG_KERNEL +config GUEST_STATE_BUFFER_TEST + def_tristate n + prompt "Enable Guest State Buffer unit tests" + depends on KUNIT + depends on KVM_BOOK3S_HV_POSSIBLE + default KUNIT_ALL_TESTS + help + The Guest State Buffer is a data format specified in the PAPR. + It is by hcalls to communicate the state of L2 guests between + the L1 and L0 hypervisors. Enable unit tests for the library + used to create and use guest state buffers. + config PPC_IRQ_SOFT_MASK_DEBUG bool "Include extra checks for powerpc irq soft masking" depends on PPC64 @@ -147,6 +159,8 @@ config BDI_SWITCH config BOOTX_TEXT bool "Support for early boot text console (BootX or OpenFirmware only)" depends on PPC_BOOK3S + select FONT_SUN8x16 + select FONT_SUPPORT help Say Y here to see progress messages from the boot firmware in text mode. Requires either BootX or Open Firmware. @@ -257,7 +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/Makefile.postlink b/arch/powerpc/Makefile.postlink index 1f860b3c9bec..ae5a4256b03d 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -35,9 +35,6 @@ ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) endif -%.ko: FORCE - @true - clean: rm -f .tmp_symbols.txt 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/boot/install.sh b/arch/powerpc/boot/install.sh index 461902c8a46d..101fcb397a0f 100755 --- a/arch/powerpc/boot/install.sh +++ b/arch/powerpc/boot/install.sh @@ -21,13 +21,17 @@ set -e # this should work for both the pSeries zImage and the iSeries vmlinux.sm image_name=`basename $2` -if [ -f $4/$image_name ]; then - mv $4/$image_name $4/$image_name.old + +echo "Warning: '${INSTALLKERNEL}' command not available... Copying" \ + "directly to $4/$image_name-$1" >&2 + +if [ -f $4/$image_name-$1 ]; then + mv $4/$image_name-$1 $4/$image_name-$1.old fi -if [ -f $4/System.map ]; then - mv $4/System.map $4/System.old +if [ -f $4/System.map-$1 ]; then + mv $4/System.map-$1 $4/System-$1.old fi -cat $2 > $4/$image_name -cp $3 $4/System.map +cat $2 > $4/$image_name-$1 +cp $3 $4/System.map-$1 diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig index 51499ee6366b..2479ab62d12f 100644 --- a/arch/powerpc/configs/44x/sam440ep_defconfig +++ b/arch/powerpc/configs/44x/sam440ep_defconfig @@ -78,7 +78,6 @@ CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y -CONFIG_REISERFS_FS=y CONFIG_AUTOFS_FS=y CONFIG_ISO9660_FS=y CONFIG_JOLIET=y diff --git a/arch/powerpc/configs/debug.config b/arch/powerpc/configs/debug.config index a14ae1f20d60..bcc1fcf25e10 100644 --- a/arch/powerpc/configs/debug.config +++ b/arch/powerpc/configs/debug.config @@ -1 +1,5 @@ +CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG=y +CONFIG_PPC_IRQ_SOFT_MASK_DEBUG=y +CONFIG_PPC_KUAP_DEBUG=y +CONFIG_PPC_RFI_SRR_DEBUG=y CONFIG_SCOM_DEBUGFS=y diff --git a/arch/powerpc/configs/disable-werror.config b/arch/powerpc/configs/disable-werror.config index 6ea12a12432c..7776b91da37f 100644 --- a/arch/powerpc/configs/disable-werror.config +++ b/arch/powerpc/configs/disable-werror.config @@ -1 +1,2 @@ +# Help: Disable -Werror CONFIG_PPC_DISABLE_WERROR=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index 71d9d112c0b6..9215bed53291 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -202,10 +202,6 @@ CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_REISERFS_FS=y -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -CONFIG_REISERFS_FS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_POSIX_ACL=y CONFIG_FS_DAX=y diff --git a/arch/powerpc/configs/hardening.config b/arch/powerpc/configs/hardening.config new file mode 100644 index 000000000000..4e9bba327e8f --- /dev/null +++ b/arch/powerpc/configs/hardening.config @@ -0,0 +1,10 @@ +# PowerPC specific hardening options + +# Block kernel from unexpectedly reading userspace memory. +CONFIG_PPC_KUAP=y + +# Attack surface reduction. +# CONFIG_SCOM_DEBUGFS is not set + +# Disable internal kernel debugger. +# CONFIG_XMON is not set diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index a205da9ee5f2..57ded82c2840 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -138,7 +138,6 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_MIRROR=m CONFIG_DM_ZERO=m CONFIG_ADB=y -CONFIG_ADB_CUDA=y CONFIG_ADB_PMU=y CONFIG_ADB_PMU_LED=y CONFIG_ADB_PMU_LED_DISK=y @@ -181,6 +180,7 @@ CONFIG_SERIAL_PMACZILOG_TTYS=y CONFIG_SERIAL_PMACZILOG_CONSOLE=y CONFIG_NVRAM=y CONFIG_I2C_CHARDEV=m +CONFIG_POWER_RESET=y CONFIG_APM_POWER=y CONFIG_BATTERY_PMU=y CONFIG_HWMON=m 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/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 624c371ffcc3..4c05f4e4d505 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -175,10 +175,6 @@ CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_REISERFS_FS=y -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -CONFIG_REISERFS_FS_SECURITY=y CONFIG_JFS_FS=y CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index eaf3273372a9..66c7b28d7450 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -274,7 +274,6 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -954,11 +953,6 @@ CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y CONFIG_JBD2_DEBUG=y -CONFIG_REISERFS_FS=m -CONFIG_REISERFS_PROC_INFO=y -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -CONFIG_REISERFS_FS_SECURITY=y CONFIG_JFS_FS=m CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=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/configs/security.config b/arch/powerpc/configs/security.config index 1c91a35c6a73..0d54e29e2cdf 100644 --- a/arch/powerpc/configs/security.config +++ b/arch/powerpc/configs/security.config @@ -1,3 +1,5 @@ +# Help: Common security options for PowerPC builds + # This is the equivalent of booting with lockdown=integrity CONFIG_SECURITY=y CONFIG_SECURITYFS=y @@ -12,4 +14,4 @@ CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y # UBSAN bounds checking is very cheap and good for hardening CONFIG_UBSAN=y -# CONFIG_UBSAN_MISC is not set
\ No newline at end of file +# CONFIG_UBSAN_MISC is not set diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 8d3eacb50d56..9d44e6630908 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_DEBUG_CREDENTIALS=y # CONFIG_FTRACE is not set CONFIG_XMON=y # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c index 4b6e899895e7..f62ee54076c0 100644 --- a/arch/powerpc/crypto/aes-gcm-p10-glue.c +++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c @@ -37,7 +37,7 @@ asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len, void *rkey, u8 *iv, void *Xi); asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len, void *rkey, u8 *iv, void *Xi); -asmlinkage void gcm_init_htable(unsigned char htable[256], unsigned char Xi[16]); +asmlinkage void gcm_init_htable(unsigned char htable[], unsigned char Xi[]); asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable, unsigned char *aad, unsigned int alen); diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 7e0f0322912b..671ecc6711e3 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -233,35 +233,24 @@ static inline int arch_test_and_change_bit(unsigned long nr, return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0; } -#ifdef CONFIG_PPC64 -static inline unsigned long -clear_bit_unlock_return_word(int nr, volatile unsigned long *addr) +static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *p) { unsigned long old, t; - unsigned long *p = (unsigned long *)addr + BIT_WORD(nr); - unsigned long mask = BIT_MASK(nr); __asm__ __volatile__ ( PPC_RELEASE_BARRIER "1:" PPC_LLARX "%0,0,%3,0\n" - "andc %1,%0,%2\n" + "xor %1,%0,%2\n" PPC_STLCX "%1,0,%3\n" "bne- 1b\n" : "=&r" (old), "=&r" (t) : "r" (mask), "r" (p) : "cc", "memory"); - return old; + return (old & BIT_MASK(7)) != 0; } - -/* - * This is a special function for mm/filemap.c - * Bit 7 corresponds to PG_waiters. - */ -#define arch_clear_bit_unlock_is_negative_byte(nr, addr) \ - (clear_bit_unlock_return_word(nr, addr) & BIT_MASK(7)) - -#endif /* CONFIG_PPC64 */ +#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte #include <asm-generic/bitops/non-atomic.h> diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 9b13eb14e21b..52971ee30717 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -20,7 +20,7 @@ #define _PAGE_PRESENT 0x001 /* software: pte contains a translation */ #define _PAGE_HASHPTE 0x002 /* hash_page has made an HPTE for this pte */ -#define _PAGE_USER 0x004 /* usermode access allowed */ +#define _PAGE_READ 0x004 /* software: read access allowed */ #define _PAGE_GUARDED 0x008 /* G: prohibit speculative access */ #define _PAGE_COHERENT 0x010 /* M: enforce memory coherence (SMP systems) */ #define _PAGE_NO_CACHE 0x020 /* I: cache inhibit */ @@ -28,7 +28,7 @@ #define _PAGE_DIRTY 0x080 /* C: page changed */ #define _PAGE_ACCESSED 0x100 /* R: page referenced */ #define _PAGE_EXEC 0x200 /* software: exec allowed */ -#define _PAGE_RW 0x400 /* software: user write access allowed */ +#define _PAGE_WRITE 0x400 /* software: user write access allowed */ #define _PAGE_SPECIAL 0x800 /* software: Special page */ #ifdef CONFIG_PTE_64BIT @@ -42,26 +42,13 @@ #define _PMD_PRESENT_MASK (PAGE_MASK) #define _PMD_BAD (~PAGE_MASK) -/* We borrow the _PAGE_USER bit to store the exclusive marker in swap PTEs. */ -#define _PAGE_SWP_EXCLUSIVE _PAGE_USER +/* We borrow the _PAGE_READ bit to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_READ /* And here we include common definitions */ -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX (_PAGE_EXEC) -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) - #define _PAGE_HPTEFLAGS _PAGE_HASHPTE -#ifndef __ASSEMBLY__ - -static inline bool pte_user(pte_t pte) -{ - return pte_val(pte) & _PAGE_USER; -} -#endif /* __ASSEMBLY__ */ - /* * Location of the PFN in the PTE. Most 32-bit platforms use the same * as _PAGE_SHIFT here (ie, naturally aligned). @@ -97,20 +84,7 @@ static inline bool pte_user(pte_t pte) #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) -/* - * Permission masks used to generate the __P and __S table. - * - * Note:__pgprot is defined in arch/powerpc/include/asm/page.h - * - * Write permissions imply read permissions for now. - */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) @@ -170,7 +144,14 @@ void unmap_kernel_page(unsigned long va); * value (for now) on others, from where we can start layout kernel * virtual space that goes below PKMAP and FIXMAP */ -#include <asm/fixmap.h> + +#define FIXADDR_SIZE 0 +#ifdef CONFIG_KASAN +#include <asm/kasan.h> +#define FIXADDR_TOP (KASAN_SHADOW_START - PAGE_SIZE) +#else +#define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) +#endif /* * ioremap_bot starts at that address. Early ioremaps move down from there, @@ -224,9 +205,6 @@ void unmap_kernel_page(unsigned long va); /* Bits to mask out from a PGD to get to the PUD page */ #define PGD_MASKED_BITS 0 -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ - (unsigned long long)pte_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) /* @@ -343,7 +321,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); } static inline void __ptep_set_access_flags(struct vm_area_struct *vma, @@ -402,8 +380,16 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) } /* Generic accessors to PTE bits */ -static inline int pte_write(pte_t pte) { return !!(pte_val(pte) & _PAGE_RW);} -static inline int pte_read(pte_t pte) { return 1; } +static inline bool pte_read(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_READ); +} + +static inline bool pte_write(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_WRITE); +} + static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); } static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } @@ -438,10 +424,10 @@ static inline bool pte_ci(pte_t pte) static inline bool pte_access_permitted(pte_t pte, bool write) { /* - * A read-only access is controlled by _PAGE_USER bit. - * We have _PAGE_READ set for WRITE and EXECUTE + * A read-only access is controlled by _PAGE_READ bit. + * We have _PAGE_READ set for WRITE */ - if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) + if (!pte_present(pte) || !pte_read(pte)) return false; if (write && !pte_write(pte)) @@ -465,7 +451,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_RW); + return __pte(pte_val(pte) & ~_PAGE_WRITE); } static inline pte_t pte_exprotect(pte_t pte) @@ -495,6 +481,9 @@ static inline pte_t pte_mkpte(pte_t pte) static inline pte_t pte_mkwrite_novma(pte_t pte) { + /* + * write implies read, hence set both + */ return __pte(pte_val(pte) | _PAGE_RW); } @@ -518,16 +507,6 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_USER); -} - -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_USER); -} - static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); diff --git a/arch/powerpc/include/asm/book3s/32/tlbflush.h b/arch/powerpc/include/asm/book3s/32/tlbflush.h index 4be572908124..e43534da5207 100644 --- a/arch/powerpc/include/asm/book3s/32/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/32/tlbflush.h @@ -80,7 +80,7 @@ static inline void local_flush_tlb_page(struct vm_area_struct *vma, static inline void local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize) { - BUILD_BUG(); + flush_range(mm, vmaddr, vmaddr); } static inline void local_flush_tlb_mm(struct mm_struct *mm) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 5c497c862d75..927d585652bc 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -17,8 +17,6 @@ #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ #define _PAGE_READ 0x00004 /* read access allowed */ -#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 */ @@ -136,23 +134,7 @@ #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC) -/* Permission masks used to generate the __P and __S table, - * - * Note:__pgprot is defined in arch/powerpc/include/asm/page.h - * - * Write permissions imply read permissions for now (we could make write-only - * pages on BookE but we don't bother for now). Execute permission control is - * possible on platforms that define _PAGE_EXEC - */ -#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_PRIVILEGED) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_READ) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_READ) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) -/* Radix only, Hash uses PAGE_READONLY_X + execute-only pkey instead */ -#define PAGE_EXECONLY __pgprot(_PAGE_BASE | _PAGE_EXEC) +#include <asm/pgtable-masks.h> /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) @@ -316,6 +298,7 @@ extern unsigned long pci_io_base; #define IOREMAP_START (ioremap_bot) #define IOREMAP_END (KERN_IO_END - FIXADDR_SIZE) #define FIXADDR_SIZE SZ_32M +#define FIXADDR_TOP (IOREMAP_END + FIXADDR_SIZE) #ifndef __ASSEMBLY__ @@ -543,8 +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; @@ -629,16 +612,6 @@ static inline pte_t pte_mkdevmap(pte_t pte) return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL | _PAGE_DEVMAP)); } -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); -} - -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); -} - /* * This is potentially called with a pmd as the argument, in which case it's not * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set. @@ -647,7 +620,7 @@ static inline pte_t pte_mkuser(pte_t pte) */ static inline int pte_devmap(pte_t pte) { - u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); + __be64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); return (pte_raw(pte) & mask) == mask; } @@ -1014,8 +987,6 @@ static inline pmd_t *pud_pgtable(pud_t pud) return (pmd_t *)__va(pud_val(pud) & ~PUD_MASKED_BITS); } -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_ERROR(e) \ 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/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index 3b7bd36a2321..f42d68c6b314 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -8,37 +8,4 @@ #include <asm/book3s/32/pgtable.h> #endif -#ifndef __ASSEMBLY__ -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, pte_t entry, int dirty); - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - -void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); - -/* - * This gets called at the end of handling a page fault, when - * the kernel has put a new PTE into the page table for the process. - * We use it to ensure coherency between the i-cache and d-cache - * for the page which has just been mapped in. - * On machines which use an MMU hash table, we use this to put a - * corresponding HPTE into the hash table ahead of time, instead of - * waiting for the inevitable extra hash-table miss exception. - */ -static inline void update_mmu_cache_range(struct vm_fault *vmf, - struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, unsigned int nr) -{ - if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE)) - return; - if (radix_enabled()) - return; - __update_mmu_cache(vma, address, ptep); -} - -#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 3f881548fb61..0e29ccf903d0 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -74,6 +74,7 @@ int create_cond_branch(ppc_inst_t *instr, const u32 *addr, int patch_branch(u32 *addr, unsigned long target, int flags); int patch_instruction(u32 *addr, ppc_inst_t instr); int raw_patch_instruction(u32 *addr, ppc_inst_t instr); +int patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr); static inline unsigned long patch_site_addr(s32 *site) { diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h index 3bdd74739cb8..e3c6969853ef 100644 --- a/arch/powerpc/include/asm/cpm1.h +++ b/arch/powerpc/include/asm/cpm1.h @@ -49,11 +49,6 @@ */ extern cpm8xx_t __iomem *cpmp; /* Pointer to comm processor */ -#define cpm_dpalloc cpm_muram_alloc -#define cpm_dpfree cpm_muram_free -#define cpm_dpram_addr cpm_muram_addr -#define cpm_dpram_phys cpm_muram_dma - extern void cpm_setbrg(uint brg, uint rate); extern void __init cpm_load_patch(cpm8xx_t *cp); diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h index 249d43cc6427..a22acc36eb9b 100644 --- a/arch/powerpc/include/asm/cpm2.h +++ b/arch/powerpc/include/asm/cpm2.h @@ -87,10 +87,6 @@ */ extern cpm_cpm2_t __iomem *cpmp; /* Pointer to comm processor */ -#define cpm_dpalloc cpm_muram_alloc -#define cpm_dpfree cpm_muram_free -#define cpm_dpram_addr cpm_muram_addr - extern void cpm2_reset(void); /* Baud rate generators. diff --git a/arch/powerpc/include/asm/fb.h b/arch/powerpc/include/asm/fb.h index 5f1a2e5f7654..c0c5d1df7ad1 100644 --- a/arch/powerpc/include/asm/fb.h +++ b/arch/powerpc/include/asm/fb.h @@ -2,18 +2,15 @@ #ifndef _ASM_FB_H_ #define _ASM_FB_H_ -#include <linux/fs.h> - #include <asm/page.h> -static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, - unsigned long off) +static inline pgprot_t pgprot_framebuffer(pgprot_t prot, + unsigned long vm_start, unsigned long vm_end, + unsigned long offset) { - vma->vm_page_prot = phys_mem_access_prot(file, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot); + return __phys_mem_access_prot(PHYS_PFN(offset), vm_end - vm_start, prot); } -#define fb_pgprotect fb_pgprotect +#define pgprot_framebuffer pgprot_framebuffer #include <asm-generic/fb.h> diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index a832aeafe560..f9068dd8dfce 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -23,18 +23,6 @@ #include <asm/kmap_size.h> #endif -#ifdef CONFIG_PPC64 -#define FIXADDR_TOP (IOREMAP_END + FIXADDR_SIZE) -#else -#define FIXADDR_SIZE 0 -#ifdef CONFIG_KASAN -#include <asm/kasan.h> -#define FIXADDR_TOP (KASAN_SHADOW_START - PAGE_SIZE) -#else -#define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) -#endif -#endif - /* * Here we define all the compile-time 'special' virtual * addresses. The point is to have a constant address at @@ -119,5 +107,9 @@ static inline void __set_fixmap(enum fixed_addresses idx, #define __early_set_fixmap __set_fixmap +#ifdef CONFIG_PPC_8xx +#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE)) +#endif + #endif /* !__ASSEMBLY__ */ #endif 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/guest-state-buffer.h b/arch/powerpc/include/asm/guest-state-buffer.h new file mode 100644 index 000000000000..808149f31576 --- /dev/null +++ b/arch/powerpc/include/asm/guest-state-buffer.h @@ -0,0 +1,995 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Interface based on include/net/netlink.h + */ +#ifndef _ASM_POWERPC_GUEST_STATE_BUFFER_H +#define _ASM_POWERPC_GUEST_STATE_BUFFER_H + +#include "asm/hvcall.h" +#include <linux/gfp.h> +#include <linux/bitmap.h> +#include <asm/plpar_wrappers.h> + +/************************************************************************** + * Guest State Buffer Constants + **************************************************************************/ +/* Element without a value and any length */ +#define KVMPPC_GSID_BLANK 0x0000 +/* Size required for the L0's internal VCPU representation */ +#define KVMPPC_GSID_HOST_STATE_SIZE 0x0001 + /* Minimum size for the H_GUEST_RUN_VCPU output buffer */ +#define KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE 0x0002 + /* "Logical" PVR value as defined in the PAPR */ +#define KVMPPC_GSID_LOGICAL_PVR 0x0003 + /* L0 relative timebase offset */ +#define KVMPPC_GSID_TB_OFFSET 0x0004 + /* Partition Scoped Page Table Info */ +#define KVMPPC_GSID_PARTITION_TABLE 0x0005 + /* Process Table Info */ +#define KVMPPC_GSID_PROCESS_TABLE 0x0006 + +/* H_GUEST_RUN_VCPU input buffer Info */ +#define KVMPPC_GSID_RUN_INPUT 0x0C00 +/* H_GUEST_RUN_VCPU output buffer Info */ +#define KVMPPC_GSID_RUN_OUTPUT 0x0C01 +#define KVMPPC_GSID_VPA 0x0C02 + +#define KVMPPC_GSID_GPR(x) (0x1000 + (x)) +#define KVMPPC_GSID_HDEC_EXPIRY_TB 0x1020 +#define KVMPPC_GSID_NIA 0x1021 +#define KVMPPC_GSID_MSR 0x1022 +#define KVMPPC_GSID_LR 0x1023 +#define KVMPPC_GSID_XER 0x1024 +#define KVMPPC_GSID_CTR 0x1025 +#define KVMPPC_GSID_CFAR 0x1026 +#define KVMPPC_GSID_SRR0 0x1027 +#define KVMPPC_GSID_SRR1 0x1028 +#define KVMPPC_GSID_DAR 0x1029 +#define KVMPPC_GSID_DEC_EXPIRY_TB 0x102A +#define KVMPPC_GSID_VTB 0x102B +#define KVMPPC_GSID_LPCR 0x102C +#define KVMPPC_GSID_HFSCR 0x102D +#define KVMPPC_GSID_FSCR 0x102E +#define KVMPPC_GSID_FPSCR 0x102F +#define KVMPPC_GSID_DAWR0 0x1030 +#define KVMPPC_GSID_DAWR1 0x1031 +#define KVMPPC_GSID_CIABR 0x1032 +#define KVMPPC_GSID_PURR 0x1033 +#define KVMPPC_GSID_SPURR 0x1034 +#define KVMPPC_GSID_IC 0x1035 +#define KVMPPC_GSID_SPRG0 0x1036 +#define KVMPPC_GSID_SPRG1 0x1037 +#define KVMPPC_GSID_SPRG2 0x1038 +#define KVMPPC_GSID_SPRG3 0x1039 +#define KVMPPC_GSID_PPR 0x103A +#define KVMPPC_GSID_MMCR(x) (0x103B + (x)) +#define KVMPPC_GSID_MMCRA 0x103F +#define KVMPPC_GSID_SIER(x) (0x1040 + (x)) +#define KVMPPC_GSID_BESCR 0x1043 +#define KVMPPC_GSID_EBBHR 0x1044 +#define KVMPPC_GSID_EBBRR 0x1045 +#define KVMPPC_GSID_AMR 0x1046 +#define KVMPPC_GSID_IAMR 0x1047 +#define KVMPPC_GSID_AMOR 0x1048 +#define KVMPPC_GSID_UAMOR 0x1049 +#define KVMPPC_GSID_SDAR 0x104A +#define KVMPPC_GSID_SIAR 0x104B +#define KVMPPC_GSID_DSCR 0x104C +#define KVMPPC_GSID_TAR 0x104D +#define KVMPPC_GSID_DEXCR 0x104E +#define KVMPPC_GSID_HDEXCR 0x104F +#define KVMPPC_GSID_HASHKEYR 0x1050 +#define KVMPPC_GSID_HASHPKEYR 0x1051 +#define KVMPPC_GSID_CTRL 0x1052 + +#define KVMPPC_GSID_CR 0x2000 +#define KVMPPC_GSID_PIDR 0x2001 +#define KVMPPC_GSID_DSISR 0x2002 +#define KVMPPC_GSID_VSCR 0x2003 +#define KVMPPC_GSID_VRSAVE 0x2004 +#define KVMPPC_GSID_DAWRX0 0x2005 +#define KVMPPC_GSID_DAWRX1 0x2006 +#define KVMPPC_GSID_PMC(x) (0x2007 + (x)) +#define KVMPPC_GSID_WORT 0x200D +#define KVMPPC_GSID_PSPB 0x200E + +#define KVMPPC_GSID_VSRS(x) (0x3000 + (x)) + +#define KVMPPC_GSID_HDAR 0xF000 +#define KVMPPC_GSID_HDSISR 0xF001 +#define KVMPPC_GSID_HEIR 0xF002 +#define KVMPPC_GSID_ASDR 0xF003 + +#define KVMPPC_GSE_GUESTWIDE_START KVMPPC_GSID_BLANK +#define KVMPPC_GSE_GUESTWIDE_END KVMPPC_GSID_PROCESS_TABLE +#define KVMPPC_GSE_GUESTWIDE_COUNT \ + (KVMPPC_GSE_GUESTWIDE_END - KVMPPC_GSE_GUESTWIDE_START + 1) + +#define KVMPPC_GSE_META_START KVMPPC_GSID_RUN_INPUT +#define KVMPPC_GSE_META_END KVMPPC_GSID_VPA +#define KVMPPC_GSE_META_COUNT (KVMPPC_GSE_META_END - KVMPPC_GSE_META_START + 1) + +#define KVMPPC_GSE_DW_REGS_START KVMPPC_GSID_GPR(0) +#define KVMPPC_GSE_DW_REGS_END KVMPPC_GSID_CTRL +#define KVMPPC_GSE_DW_REGS_COUNT \ + (KVMPPC_GSE_DW_REGS_END - KVMPPC_GSE_DW_REGS_START + 1) + +#define KVMPPC_GSE_W_REGS_START KVMPPC_GSID_CR +#define KVMPPC_GSE_W_REGS_END KVMPPC_GSID_PSPB +#define KVMPPC_GSE_W_REGS_COUNT \ + (KVMPPC_GSE_W_REGS_END - KVMPPC_GSE_W_REGS_START + 1) + +#define KVMPPC_GSE_VSRS_START KVMPPC_GSID_VSRS(0) +#define KVMPPC_GSE_VSRS_END KVMPPC_GSID_VSRS(63) +#define KVMPPC_GSE_VSRS_COUNT (KVMPPC_GSE_VSRS_END - KVMPPC_GSE_VSRS_START + 1) + +#define KVMPPC_GSE_INTR_REGS_START KVMPPC_GSID_HDAR +#define KVMPPC_GSE_INTR_REGS_END KVMPPC_GSID_ASDR +#define KVMPPC_GSE_INTR_REGS_COUNT \ + (KVMPPC_GSE_INTR_REGS_END - KVMPPC_GSE_INTR_REGS_START + 1) + +#define KVMPPC_GSE_IDEN_COUNT \ + (KVMPPC_GSE_GUESTWIDE_COUNT + KVMPPC_GSE_META_COUNT + \ + KVMPPC_GSE_DW_REGS_COUNT + KVMPPC_GSE_W_REGS_COUNT + \ + KVMPPC_GSE_VSRS_COUNT + KVMPPC_GSE_INTR_REGS_COUNT) + +/** + * Ranges of guest state buffer elements + */ +enum { + KVMPPC_GS_CLASS_GUESTWIDE = 0x01, + KVMPPC_GS_CLASS_META = 0x02, + KVMPPC_GS_CLASS_DWORD_REG = 0x04, + KVMPPC_GS_CLASS_WORD_REG = 0x08, + KVMPPC_GS_CLASS_VECTOR = 0x10, + KVMPPC_GS_CLASS_INTR = 0x20, +}; + +/** + * Types of guest state buffer elements + */ +enum { + KVMPPC_GSE_BE32, + KVMPPC_GSE_BE64, + KVMPPC_GSE_VEC128, + KVMPPC_GSE_PARTITION_TABLE, + KVMPPC_GSE_PROCESS_TABLE, + KVMPPC_GSE_BUFFER, + __KVMPPC_GSE_TYPE_MAX, +}; + +/** + * Flags for guest state elements + */ +enum { + KVMPPC_GS_FLAGS_WIDE = 0x01, +}; + +/** + * struct kvmppc_gs_part_table - deserialized partition table information + * element + * @address: start of the partition table + * @ea_bits: number of bits in the effective address + * @gpd_size: root page directory size + */ +struct kvmppc_gs_part_table { + u64 address; + u64 ea_bits; + u64 gpd_size; +}; + +/** + * struct kvmppc_gs_proc_table - deserialized process table information element + * @address: start of the process table + * @gpd_size: process table size + */ +struct kvmppc_gs_proc_table { + u64 address; + u64 gpd_size; +}; + +/** + * struct kvmppc_gs_buff_info - deserialized meta guest state buffer information + * @address: start of the guest state buffer + * @size: size of the guest state buffer + */ +struct kvmppc_gs_buff_info { + u64 address; + u64 size; +}; + +/** + * struct kvmppc_gs_header - serialized guest state buffer header + * @nelem: count of guest state elements in the buffer + * @data: start of the stream of elements in the buffer + */ +struct kvmppc_gs_header { + __be32 nelems; + char data[]; +} __packed; + +/** + * struct kvmppc_gs_elem - serialized guest state buffer element + * @iden: Guest State ID + * @len: length of data + * @data: the guest state buffer element's value + */ +struct kvmppc_gs_elem { + __be16 iden; + __be16 len; + char data[]; +} __packed; + +/** + * struct kvmppc_gs_buff - a guest state buffer with metadata. + * @capacity: total length of the buffer + * @len: current length of the elements and header + * @guest_id: guest id associated with the buffer + * @vcpu_id: vcpu_id associated with the buffer + * @hdr: the serialised guest state buffer + */ +struct kvmppc_gs_buff { + size_t capacity; + size_t len; + unsigned long guest_id; + unsigned long vcpu_id; + struct kvmppc_gs_header *hdr; +}; + +/** + * struct kvmppc_gs_bitmap - a bitmap for element ids + * @bitmap: a bitmap large enough for all Guest State IDs + */ +struct kvmppc_gs_bitmap { + /* private: */ + DECLARE_BITMAP(bitmap, KVMPPC_GSE_IDEN_COUNT); +}; + +/** + * struct kvmppc_gs_parser - a map of element ids to locations in a buffer + * @iterator: bitmap used for iterating + * @gses: contains the pointers to elements + * + * A guest state parser is used for deserialising a guest state buffer. + * Given a buffer, it then allows looking up guest state elements using + * a guest state id. + */ +struct kvmppc_gs_parser { + /* private: */ + struct kvmppc_gs_bitmap iterator; + struct kvmppc_gs_elem *gses[KVMPPC_GSE_IDEN_COUNT]; +}; + +enum { + GSM_GUEST_WIDE = 0x1, + GSM_SEND = 0x2, + GSM_RECEIVE = 0x4, + GSM_GSB_OWNER = 0x8, +}; + +struct kvmppc_gs_msg; + +/** + * struct kvmppc_gs_msg_ops - guest state message behavior + * @get_size: maximum size required for the message data + * @fill_info: serializes to the guest state buffer format + * @refresh_info: dserializes from the guest state buffer format + */ +struct kvmppc_gs_msg_ops { + size_t (*get_size)(struct kvmppc_gs_msg *gsm); + int (*fill_info)(struct kvmppc_gs_buff *gsb, struct kvmppc_gs_msg *gsm); + int (*refresh_info)(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb); +}; + +/** + * struct kvmppc_gs_msg - a guest state message + * @bitmap: the guest state ids that should be included + * @ops: modify message behavior for reading and writing to buffers + * @flags: guest wide or thread wide + * @data: location where buffer data will be written to or from. + * + * A guest state message is allows flexibility in sending in receiving data + * in a guest state buffer format. + */ +struct kvmppc_gs_msg { + struct kvmppc_gs_bitmap bitmap; + struct kvmppc_gs_msg_ops *ops; + unsigned long flags; + void *data; +}; + +/************************************************************************** + * Guest State IDs + **************************************************************************/ + +u16 kvmppc_gsid_size(u16 iden); +unsigned long kvmppc_gsid_flags(u16 iden); +u64 kvmppc_gsid_mask(u16 iden); + +/************************************************************************** + * Guest State Buffers + **************************************************************************/ +struct kvmppc_gs_buff *kvmppc_gsb_new(size_t size, unsigned long guest_id, + unsigned long vcpu_id, gfp_t flags); +void kvmppc_gsb_free(struct kvmppc_gs_buff *gsb); +void *kvmppc_gsb_put(struct kvmppc_gs_buff *gsb, size_t size); +int kvmppc_gsb_send(struct kvmppc_gs_buff *gsb, unsigned long flags); +int kvmppc_gsb_recv(struct kvmppc_gs_buff *gsb, unsigned long flags); + +/** + * kvmppc_gsb_header() - the header of a guest state buffer + * @gsb: guest state buffer + * + * Returns a pointer to the buffer header. + */ +static inline struct kvmppc_gs_header * +kvmppc_gsb_header(struct kvmppc_gs_buff *gsb) +{ + return gsb->hdr; +} + +/** + * kvmppc_gsb_data() - the elements of a guest state buffer + * @gsb: guest state buffer + * + * Returns a pointer to the first element of the buffer data. + */ +static inline struct kvmppc_gs_elem *kvmppc_gsb_data(struct kvmppc_gs_buff *gsb) +{ + return (struct kvmppc_gs_elem *)kvmppc_gsb_header(gsb)->data; +} + +/** + * kvmppc_gsb_len() - the current length of a guest state buffer + * @gsb: guest state buffer + * + * Returns the length including the header of a buffer. + */ +static inline size_t kvmppc_gsb_len(struct kvmppc_gs_buff *gsb) +{ + return gsb->len; +} + +/** + * kvmppc_gsb_capacity() - the capacity of a guest state buffer + * @gsb: guest state buffer + * + * Returns the capacity of a buffer. + */ +static inline size_t kvmppc_gsb_capacity(struct kvmppc_gs_buff *gsb) +{ + return gsb->capacity; +} + +/** + * kvmppc_gsb_paddress() - the physical address of buffer + * @gsb: guest state buffer + * + * Returns the physical address of the buffer. + */ +static inline u64 kvmppc_gsb_paddress(struct kvmppc_gs_buff *gsb) +{ + return __pa(kvmppc_gsb_header(gsb)); +} + +/** + * kvmppc_gsb_nelems() - the number of elements in a buffer + * @gsb: guest state buffer + * + * Returns the number of elements in a buffer + */ +static inline u32 kvmppc_gsb_nelems(struct kvmppc_gs_buff *gsb) +{ + return be32_to_cpu(kvmppc_gsb_header(gsb)->nelems); +} + +/** + * kvmppc_gsb_reset() - empty a guest state buffer + * @gsb: guest state buffer + * + * Reset the number of elements and length of buffer to empty. + */ +static inline void kvmppc_gsb_reset(struct kvmppc_gs_buff *gsb) +{ + kvmppc_gsb_header(gsb)->nelems = cpu_to_be32(0); + gsb->len = sizeof(struct kvmppc_gs_header); +} + +/** + * kvmppc_gsb_data_len() - the length of a buffer excluding the header + * @gsb: guest state buffer + * + * Returns the length of a buffer excluding the header + */ +static inline size_t kvmppc_gsb_data_len(struct kvmppc_gs_buff *gsb) +{ + return gsb->len - sizeof(struct kvmppc_gs_header); +} + +/** + * kvmppc_gsb_data_cap() - the capacity of a buffer excluding the header + * @gsb: guest state buffer + * + * Returns the capacity of a buffer excluding the header + */ +static inline size_t kvmppc_gsb_data_cap(struct kvmppc_gs_buff *gsb) +{ + return gsb->capacity - sizeof(struct kvmppc_gs_header); +} + +/** + * kvmppc_gsb_for_each_elem - iterate over the elements in a buffer + * @i: loop counter + * @pos: set to current element + * @gsb: guest state buffer + * @rem: initialized to buffer capacity, holds bytes currently remaining in + * stream + */ +#define kvmppc_gsb_for_each_elem(i, pos, gsb, rem) \ + kvmppc_gse_for_each_elem(i, kvmppc_gsb_nelems(gsb), pos, \ + kvmppc_gsb_data(gsb), \ + kvmppc_gsb_data_cap(gsb), rem) + +/************************************************************************** + * Guest State Elements + **************************************************************************/ + +/** + * kvmppc_gse_iden() - guest state ID of element + * @gse: guest state element + * + * Return the guest state ID in host endianness. + */ +static inline u16 kvmppc_gse_iden(const struct kvmppc_gs_elem *gse) +{ + return be16_to_cpu(gse->iden); +} + +/** + * kvmppc_gse_len() - length of guest state element data + * @gse: guest state element + * + * Returns the length of guest state element data + */ +static inline u16 kvmppc_gse_len(const struct kvmppc_gs_elem *gse) +{ + return be16_to_cpu(gse->len); +} + +/** + * kvmppc_gse_total_len() - total length of guest state element + * @gse: guest state element + * + * Returns the length of the data plus the ID and size header. + */ +static inline u16 kvmppc_gse_total_len(const struct kvmppc_gs_elem *gse) +{ + return be16_to_cpu(gse->len) + sizeof(*gse); +} + +/** + * kvmppc_gse_total_size() - space needed for a given data length + * @size: data length + * + * Returns size plus the space needed for the ID and size header. + */ +static inline u16 kvmppc_gse_total_size(u16 size) +{ + return sizeof(struct kvmppc_gs_elem) + size; +} + +/** + * kvmppc_gse_data() - pointer to data of a guest state element + * @gse: guest state element + * + * Returns a pointer to the beginning of guest state element data. + */ +static inline void *kvmppc_gse_data(const struct kvmppc_gs_elem *gse) +{ + return (void *)gse->data; +} + +/** + * kvmppc_gse_ok() - checks space exists for guest state element + * @gse: guest state element + * @remaining: bytes of space remaining + * + * Returns true if the guest state element can fit in remaining space. + */ +static inline bool kvmppc_gse_ok(const struct kvmppc_gs_elem *gse, + int remaining) +{ + return remaining >= kvmppc_gse_total_len(gse); +} + +/** + * kvmppc_gse_next() - iterate to the next guest state element in a stream + * @gse: stream of guest state elements + * @remaining: length of the guest element stream + * + * Returns the next guest state element in a stream of elements. The length of + * the stream is updated in remaining. + */ +static inline struct kvmppc_gs_elem * +kvmppc_gse_next(const struct kvmppc_gs_elem *gse, int *remaining) +{ + int len = sizeof(*gse) + kvmppc_gse_len(gse); + + *remaining -= len; + return (struct kvmppc_gs_elem *)(gse->data + kvmppc_gse_len(gse)); +} + +/** + * kvmppc_gse_for_each_elem - iterate over a stream of guest state elements + * @i: loop counter + * @max: number of elements + * @pos: set to current element + * @head: head of elements + * @len: length of the stream + * @rem: initialized to len, holds bytes currently remaining elements + */ +#define kvmppc_gse_for_each_elem(i, max, pos, head, len, rem) \ + for (i = 0, pos = head, rem = len; kvmppc_gse_ok(pos, rem) && i < max; \ + pos = kvmppc_gse_next(pos, &(rem)), i++) + +int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size, + const void *data); +int kvmppc_gse_parse(struct kvmppc_gs_parser *gsp, struct kvmppc_gs_buff *gsb); + +/** + * kvmppc_gse_put_be32() - add a be32 guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: big endian value + */ +static inline int kvmppc_gse_put_be32(struct kvmppc_gs_buff *gsb, u16 iden, + __be32 val) +{ + __be32 tmp; + + tmp = val; + return __kvmppc_gse_put(gsb, iden, sizeof(__be32), &tmp); +} + +/** + * kvmppc_gse_put_u32() - add a host endian 32bit int guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: host endian value + */ +static inline int kvmppc_gse_put_u32(struct kvmppc_gs_buff *gsb, u16 iden, + u32 val) +{ + __be32 tmp; + + val &= kvmppc_gsid_mask(iden); + tmp = cpu_to_be32(val); + return kvmppc_gse_put_be32(gsb, iden, tmp); +} + +/** + * kvmppc_gse_put_be64() - add a be64 guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: big endian value + */ +static inline int kvmppc_gse_put_be64(struct kvmppc_gs_buff *gsb, u16 iden, + __be64 val) +{ + __be64 tmp; + + tmp = val; + return __kvmppc_gse_put(gsb, iden, sizeof(__be64), &tmp); +} + +/** + * kvmppc_gse_put_u64() - add a host endian 64bit guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: host endian value + */ +static inline int kvmppc_gse_put_u64(struct kvmppc_gs_buff *gsb, u16 iden, + u64 val) +{ + __be64 tmp; + + val &= kvmppc_gsid_mask(iden); + tmp = cpu_to_be64(val); + return kvmppc_gse_put_be64(gsb, iden, tmp); +} + +/** + * __kvmppc_gse_put_reg() - add a register type guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: host endian value + * + * Adds a register type guest state element. Uses the guest state ID for + * determining the length of the guest element. If the guest state ID has + * bits that can not be set they will be cleared. + */ +static inline int __kvmppc_gse_put_reg(struct kvmppc_gs_buff *gsb, u16 iden, + u64 val) +{ + val &= kvmppc_gsid_mask(iden); + if (kvmppc_gsid_size(iden) == sizeof(u64)) + return kvmppc_gse_put_u64(gsb, iden, val); + + if (kvmppc_gsid_size(iden) == sizeof(u32)) { + u32 tmp; + + tmp = (u32)val; + if (tmp != val) + return -EINVAL; + + return kvmppc_gse_put_u32(gsb, iden, tmp); + } + return -EINVAL; +} + +/** + * kvmppc_gse_put_vector128() - add a vector guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: 16 byte vector value + */ +static inline int kvmppc_gse_put_vector128(struct kvmppc_gs_buff *gsb, u16 iden, + vector128 *val) +{ + __be64 tmp[2] = { 0 }; + union { + __vector128 v; + u64 dw[2]; + } u; + + u.v = *val; + tmp[0] = cpu_to_be64(u.dw[TS_FPROFFSET]); +#ifdef CONFIG_VSX + tmp[1] = cpu_to_be64(u.dw[TS_VSRLOWOFFSET]); +#endif + return __kvmppc_gse_put(gsb, iden, sizeof(tmp), &tmp); +} + +/** + * kvmppc_gse_put_part_table() - add a partition table guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: partition table value + */ +static inline int kvmppc_gse_put_part_table(struct kvmppc_gs_buff *gsb, + u16 iden, + struct kvmppc_gs_part_table val) +{ + __be64 tmp[3]; + + tmp[0] = cpu_to_be64(val.address); + tmp[1] = cpu_to_be64(val.ea_bits); + tmp[2] = cpu_to_be64(val.gpd_size); + return __kvmppc_gse_put(gsb, KVMPPC_GSID_PARTITION_TABLE, sizeof(tmp), + &tmp); +} + +/** + * kvmppc_gse_put_proc_table() - add a process table guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: process table value + */ +static inline int kvmppc_gse_put_proc_table(struct kvmppc_gs_buff *gsb, + u16 iden, + struct kvmppc_gs_proc_table val) +{ + __be64 tmp[2]; + + tmp[0] = cpu_to_be64(val.address); + tmp[1] = cpu_to_be64(val.gpd_size); + return __kvmppc_gse_put(gsb, KVMPPC_GSID_PROCESS_TABLE, sizeof(tmp), + &tmp); +} + +/** + * kvmppc_gse_put_buff_info() - adds a GSB description guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: guest state buffer description value + */ +static inline int kvmppc_gse_put_buff_info(struct kvmppc_gs_buff *gsb, u16 iden, + struct kvmppc_gs_buff_info val) +{ + __be64 tmp[2]; + + tmp[0] = cpu_to_be64(val.address); + tmp[1] = cpu_to_be64(val.size); + return __kvmppc_gse_put(gsb, iden, sizeof(tmp), &tmp); +} + +int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size, + const void *data); + +/** + * kvmppc_gse_get_be32() - return the data of a be32 element + * @gse: guest state element + */ +static inline __be32 kvmppc_gse_get_be32(const struct kvmppc_gs_elem *gse) +{ + if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__be32))) + return 0; + return *(__be32 *)kvmppc_gse_data(gse); +} + +/** + * kvmppc_gse_get_u32() - return the data of a be32 element in host endianness + * @gse: guest state element + */ +static inline u32 kvmppc_gse_get_u32(const struct kvmppc_gs_elem *gse) +{ + return be32_to_cpu(kvmppc_gse_get_be32(gse)); +} + +/** + * kvmppc_gse_get_be64() - return the data of a be64 element + * @gse: guest state element + */ +static inline __be64 kvmppc_gse_get_be64(const struct kvmppc_gs_elem *gse) +{ + if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__be64))) + return 0; + return *(__be64 *)kvmppc_gse_data(gse); +} + +/** + * kvmppc_gse_get_u64() - return the data of a be64 element in host endianness + * @gse: guest state element + */ +static inline u64 kvmppc_gse_get_u64(const struct kvmppc_gs_elem *gse) +{ + return be64_to_cpu(kvmppc_gse_get_be64(gse)); +} + +/** + * kvmppc_gse_get_vector128() - return the data of a vector element + * @gse: guest state element + */ +static inline void kvmppc_gse_get_vector128(const struct kvmppc_gs_elem *gse, + vector128 *v) +{ + union { + __vector128 v; + u64 dw[2]; + } u = { 0 }; + __be64 *src; + + if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__vector128))) + *v = u.v; + + src = (__be64 *)kvmppc_gse_data(gse); + u.dw[TS_FPROFFSET] = be64_to_cpu(src[0]); +#ifdef CONFIG_VSX + u.dw[TS_VSRLOWOFFSET] = be64_to_cpu(src[1]); +#endif + *v = u.v; +} + +/************************************************************************** + * Guest State Bitmap + **************************************************************************/ + +bool kvmppc_gsbm_test(struct kvmppc_gs_bitmap *gsbm, u16 iden); +void kvmppc_gsbm_set(struct kvmppc_gs_bitmap *gsbm, u16 iden); +void kvmppc_gsbm_clear(struct kvmppc_gs_bitmap *gsbm, u16 iden); +u16 kvmppc_gsbm_next(struct kvmppc_gs_bitmap *gsbm, u16 prev); + +/** + * kvmppc_gsbm_zero - zero the entire bitmap + * @gsbm: guest state buffer bitmap + */ +static inline void kvmppc_gsbm_zero(struct kvmppc_gs_bitmap *gsbm) +{ + bitmap_zero(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT); +} + +/** + * kvmppc_gsbm_fill - fill the entire bitmap + * @gsbm: guest state buffer bitmap + */ +static inline void kvmppc_gsbm_fill(struct kvmppc_gs_bitmap *gsbm) +{ + bitmap_fill(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT); + clear_bit(0, gsbm->bitmap); +} + +/** + * kvmppc_gsbm_for_each - iterate the present guest state IDs + * @gsbm: guest state buffer bitmap + * @iden: current guest state ID + */ +#define kvmppc_gsbm_for_each(gsbm, iden) \ + for (iden = kvmppc_gsbm_next(gsbm, 0); iden != 0; \ + iden = kvmppc_gsbm_next(gsbm, iden)) + +/************************************************************************** + * Guest State Parser + **************************************************************************/ + +void kvmppc_gsp_insert(struct kvmppc_gs_parser *gsp, u16 iden, + struct kvmppc_gs_elem *gse); +struct kvmppc_gs_elem *kvmppc_gsp_lookup(struct kvmppc_gs_parser *gsp, + u16 iden); + +/** + * kvmppc_gsp_for_each - iterate the <guest state IDs, guest state element> + * pairs + * @gsp: guest state buffer bitmap + * @iden: current guest state ID + * @gse: guest state element + */ +#define kvmppc_gsp_for_each(gsp, iden, gse) \ + for (iden = kvmppc_gsbm_next(&(gsp)->iterator, 0), \ + gse = kvmppc_gsp_lookup((gsp), iden); \ + iden != 0; iden = kvmppc_gsbm_next(&(gsp)->iterator, iden), \ + gse = kvmppc_gsp_lookup((gsp), iden)) + +/************************************************************************** + * Guest State Message + **************************************************************************/ + +/** + * kvmppc_gsm_for_each - iterate the guest state IDs included in a guest state + * message + * @gsp: guest state buffer bitmap + * @iden: current guest state ID + * @gse: guest state element + */ +#define kvmppc_gsm_for_each(gsm, iden) \ + for (iden = kvmppc_gsbm_next(&gsm->bitmap, 0); iden != 0; \ + iden = kvmppc_gsbm_next(&gsm->bitmap, iden)) + +int kvmppc_gsm_init(struct kvmppc_gs_msg *mgs, struct kvmppc_gs_msg_ops *ops, + void *data, unsigned long flags); + +struct kvmppc_gs_msg *kvmppc_gsm_new(struct kvmppc_gs_msg_ops *ops, void *data, + unsigned long flags, gfp_t gfp_flags); +void kvmppc_gsm_free(struct kvmppc_gs_msg *gsm); +size_t kvmppc_gsm_size(struct kvmppc_gs_msg *gsm); +int kvmppc_gsm_fill_info(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_buff *gsb); +int kvmppc_gsm_refresh_info(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb); + +/** + * kvmppc_gsm_include - indicate a guest state ID should be included when + * serializing + * @gsm: guest state message + * @iden: guest state ID + */ +static inline void kvmppc_gsm_include(struct kvmppc_gs_msg *gsm, u16 iden) +{ + kvmppc_gsbm_set(&gsm->bitmap, iden); +} + +/** + * kvmppc_gsm_includes - check if a guest state ID will be included when + * serializing + * @gsm: guest state message + * @iden: guest state ID + */ +static inline bool kvmppc_gsm_includes(struct kvmppc_gs_msg *gsm, u16 iden) +{ + return kvmppc_gsbm_test(&gsm->bitmap, iden); +} + +/** + * kvmppc_gsm_includes - indicate all guest state IDs should be included when + * serializing + * @gsm: guest state message + * @iden: guest state ID + */ +static inline void kvmppc_gsm_include_all(struct kvmppc_gs_msg *gsm) +{ + kvmppc_gsbm_fill(&gsm->bitmap); +} + +/** + * kvmppc_gsm_include - clear the guest state IDs that should be included when + * serializing + * @gsm: guest state message + */ +static inline void kvmppc_gsm_reset(struct kvmppc_gs_msg *gsm) +{ + kvmppc_gsbm_zero(&gsm->bitmap); +} + +/** + * kvmppc_gsb_receive_data - flexibly update values from a guest state buffer + * @gsb: guest state buffer + * @gsm: guest state message + * + * Requests updated values for the guest state values included in the guest + * state message. The guest state message will then deserialize the guest state + * buffer. + */ +static inline int kvmppc_gsb_receive_data(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + int rc; + + kvmppc_gsb_reset(gsb); + rc = kvmppc_gsm_fill_info(gsm, gsb); + if (rc < 0) + return rc; + + rc = kvmppc_gsb_recv(gsb, gsm->flags); + if (rc < 0) + return rc; + + rc = kvmppc_gsm_refresh_info(gsm, gsb); + if (rc < 0) + return rc; + return 0; +} + +/** + * kvmppc_gsb_recv - receive a single guest state ID + * @gsb: guest state buffer + * @gsm: guest state message + * @iden: guest state identity + */ +static inline int kvmppc_gsb_receive_datum(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm, u16 iden) +{ + int rc; + + kvmppc_gsm_include(gsm, iden); + rc = kvmppc_gsb_receive_data(gsb, gsm); + if (rc < 0) + return rc; + kvmppc_gsm_reset(gsm); + return 0; +} + +/** + * kvmppc_gsb_send_data - flexibly send values from a guest state buffer + * @gsb: guest state buffer + * @gsm: guest state message + * + * Sends the guest state values included in the guest state message. + */ +static inline int kvmppc_gsb_send_data(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + int rc; + + kvmppc_gsb_reset(gsb); + rc = kvmppc_gsm_fill_info(gsm, gsb); + if (rc < 0) + return rc; + rc = kvmppc_gsb_send(gsb, gsm->flags); + + return rc; +} + +/** + * kvmppc_gsb_recv - send a single guest state ID + * @gsb: guest state buffer + * @gsm: guest state message + * @iden: guest state identity + */ +static inline int kvmppc_gsb_send_datum(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm, u16 iden) +{ + int rc; + + kvmppc_gsm_include(gsm, iden); + rc = kvmppc_gsb_send_data(gsb, gsm); + if (rc < 0) + return rc; + kvmppc_gsm_reset(gsm); + return 0; +} + +#endif /* _ASM_POWERPC_GUEST_STATE_BUFFER_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index c099780385dd..a41e542ba94d 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -100,6 +100,18 @@ #define H_COP_HW -74 #define H_STATE -75 #define H_IN_USE -77 + +#define H_INVALID_ELEMENT_ID -79 +#define H_INVALID_ELEMENT_SIZE -80 +#define H_INVALID_ELEMENT_VALUE -81 +#define H_INPUT_BUFFER_NOT_DEFINED -82 +#define H_INPUT_BUFFER_TOO_SMALL -83 +#define H_OUTPUT_BUFFER_NOT_DEFINED -84 +#define H_OUTPUT_BUFFER_TOO_SMALL -85 +#define H_PARTITION_PAGE_TABLE_NOT_DEFINED -86 +#define H_GUEST_VCPU_STATE_NOT_HV_OWNED -87 + + #define H_UNSUPPORTED_FLAG_START -256 #define H_UNSUPPORTED_FLAG_END -511 #define H_MULTI_THREADS_ACTIVE -9005 @@ -337,7 +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) @@ -467,6 +488,15 @@ #define H_RPTI_PAGE_1G 0x08 #define H_RPTI_PAGE_ALL (-1UL) +/* Flags for H_GUEST_{S,G}_STATE */ +#define H_GUEST_FLAGS_WIDE (1UL<<(63-0)) + +/* Flag values used for H_{S,G}SET_GUEST_CAPABILITIES */ +#define H_GUEST_CAP_COPY_MEM (1UL<<(63-0)) +#define H_GUEST_CAP_POWER9 (1UL<<(63-1)) +#define H_GUEST_CAP_POWER10 (1UL<<(63-2)) +#define H_GUEST_CAP_BITMAP2 (1UL<<(63-63)) + #ifndef __ASSEMBLY__ #include <linux/types.h> diff --git a/arch/powerpc/include/asm/hvconsole.h b/arch/powerpc/include/asm/hvconsole.h index ccb2034506f0..d841a97010a0 100644 --- a/arch/powerpc/include/asm/hvconsole.h +++ b/arch/powerpc/include/asm/hvconsole.h @@ -21,8 +21,8 @@ * Vio firmware always attempts to fetch MAX_VIO_GET_CHARS chars. The 'count' * parm is included to conform to put_chars() function pointer template */ -extern int hvc_get_chars(uint32_t vtermno, char *buf, int count); -extern int hvc_put_chars(uint32_t vtermno, const char *buf, int count); +extern ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count); +extern ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count); /* Provided by HVC VIO */ void hvc_vio_init_early(void); diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h index 464a7519ed64..9058edcb632b 100644 --- a/arch/powerpc/include/asm/hvsi.h +++ b/arch/powerpc/include/asm/hvsi.h @@ -64,7 +64,7 @@ struct hvsi_priv { unsigned int inbuf_len; /* data in input buffer */ unsigned char inbuf[HVSI_INBUF_SIZE]; unsigned int inbuf_cur; /* Cursor in input buffer */ - unsigned int inbuf_pktlen; /* packet length from cursor */ + size_t inbuf_pktlen; /* packet length from cursor */ atomic_t seqno; /* packet sequence number */ unsigned int opened:1; /* driver opened */ unsigned int established:1; /* protocol established */ @@ -72,24 +72,26 @@ struct hvsi_priv { unsigned int mctrl_update:1; /* modem control updated */ unsigned short mctrl; /* modem control */ struct tty_struct *tty; /* tty structure */ - int (*get_chars)(uint32_t termno, char *buf, int count); - int (*put_chars)(uint32_t termno, const char *buf, int count); + ssize_t (*get_chars)(uint32_t termno, u8 *buf, size_t count); + ssize_t (*put_chars)(uint32_t termno, const u8 *buf, size_t count); uint32_t termno; }; /* hvsi lib functions */ struct hvc_struct; extern void hvsilib_init(struct hvsi_priv *pv, - int (*get_chars)(uint32_t termno, char *buf, int count), - int (*put_chars)(uint32_t termno, const char *buf, - int count), + ssize_t (*get_chars)(uint32_t termno, u8 *buf, + size_t count), + ssize_t (*put_chars)(uint32_t termno, const u8 *buf, + size_t count), int termno, int is_console); extern int hvsilib_open(struct hvsi_priv *pv, struct hvc_struct *hp); extern void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp); extern int hvsilib_read_mctrl(struct hvsi_priv *pv); extern int hvsilib_write_mctrl(struct hvsi_priv *pv, int dtr); extern void hvsilib_establish(struct hvsi_priv *pv); -extern int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count); -extern int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count); +extern ssize_t hvsilib_get_chars(struct hvsi_priv *pv, u8 *buf, size_t count); +extern ssize_t hvsilib_put_chars(struct hvsi_priv *pv, const u8 *buf, + size_t count); #endif /* _HVSI_H */ diff --git a/arch/powerpc/include/asm/ide.h b/arch/powerpc/include/asm/ide.h deleted file mode 100644 index ce87a4441ca3..000000000000 --- a/arch/powerpc/include/asm/ide.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 1994-1996 Linus Torvalds & authors - * - * This file contains the powerpc architecture specific IDE code. - */ -#ifndef _ASM_POWERPC_IDE_H -#define _ASM_POWERPC_IDE_H - -#include <linux/compiler.h> -#include <asm/io.h> - -#define __ide_mm_insw(p, a, c) readsw((void __iomem *)(p), (a), (c)) -#define __ide_mm_insl(p, a, c) readsl((void __iomem *)(p), (a), (c)) -#define __ide_mm_outsw(p, a, c) writesw((void __iomem *)(p), (a), (c)) -#define __ide_mm_outsl(p, a, c) writesl((void __iomem *)(p), (a), (c)) - -#endif /* _ASM_POWERPC_IDE_H */ diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 699a88584ae1..a656635df386 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -74,14 +74,14 @@ struct imc_events { * The following is the data structure to hold trace imc data. */ struct trace_imc_data { - u64 tb1; - u64 ip; - u64 val; - u64 cpmc1; - u64 cpmc2; - u64 cpmc3; - u64 cpmc4; - u64 tb2; + __be64 tb1; + __be64 ip; + __be64 val; + __be64 cpmc1; + __be64 cpmc2; + __be64 cpmc3; + __be64 cpmc4; + __be64 tb2; }; /* Event attribute array index */ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 0732b743e099..08c550ed49be 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -710,12 +710,6 @@ static inline void name at \ #define memcpy_toio memcpy_toio /* - * Convert a physical pointer to a virtual kernel pointer for /dev/mem - * access - */ -#define xlate_dev_mem_ptr(p) __va(p) - -/* * We don't do relaxed operations yet, at least not with this semantic */ #define readb_relaxed(addr) readb(addr) @@ -900,7 +894,6 @@ void __iomem *ioremap_wt(phys_addr_t address, unsigned long size); #endif void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size); -#define ioremap_uc(addr, size) ioremap((addr), (size)) #define ioremap_cache(addr, size) \ ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) @@ -950,7 +943,7 @@ extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size, * almost all conceivable cases a device driver should not be using * this function */ -static inline unsigned long virt_to_phys(volatile void * address) +static inline unsigned long virt_to_phys(const volatile void * address) { WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !virt_addr_valid(address)); diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h index b8b0be8f1a07..c6d3078bd8c3 100644 --- a/arch/powerpc/include/asm/irq_work.h +++ b/arch/powerpc/include/asm/irq_work.h @@ -6,6 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return true; } -extern void arch_irq_work_raise(void); #endif /* _ASM_POWERPC_IRQ_WORK_H */ diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 93ce3ec25387..2f2a86ed2280 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" @@ -32,7 +32,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index a1ddba01e7d1..e1b43aa12175 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -99,10 +99,14 @@ void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_co void kexec_copy_flush(struct kimage *image); -#if defined(CONFIG_CRASH_DUMP) && defined(CONFIG_PPC_RTAS) +#if defined(CONFIG_CRASH_DUMP) +bool is_kdump_kernel(void); +#define is_kdump_kernel is_kdump_kernel +#if defined(CONFIG_PPC_RTAS) void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); #define crash_free_reserved_phys_range crash_free_reserved_phys_range -#endif +#endif /* CONFIG_PPC_RTAS */ +#endif /* CONFIG_CRASH_DUMP */ #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops kexec_elf64_ops; diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index c8e4b4fd4e33..4525a9c68260 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -84,8 +84,6 @@ struct arch_optimized_insn { kprobe_opcode_t *insn; }; -extern int kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data); extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index bbf5e2c5fe09..3e1e2a698c9e 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -12,6 +12,7 @@ #include <linux/types.h> #include <linux/kvm_host.h> #include <asm/kvm_book3s_asm.h> +#include <asm/guest-state-buffer.h> struct kvmppc_bat { u64 raw; @@ -191,14 +192,14 @@ extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *gpte, bool data, bool iswrite); extern void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, - unsigned int pshift, unsigned int lpid); + unsigned int pshift, u64 lpid); extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa, unsigned int shift, const struct kvm_memory_slot *memslot, - unsigned int lpid); + u64 lpid); extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing, unsigned long gpa, - unsigned int lpid); + u64 lpid); extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, unsigned long gpa, struct kvm_memory_slot *memslot, @@ -207,7 +208,7 @@ extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, extern int kvmppc_init_vm_radix(struct kvm *kvm); extern void kvmppc_free_radix(struct kvm *kvm); extern void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, - unsigned int lpid); + u64 lpid); extern int kvmppc_radix_init(void); extern void kvmppc_radix_exit(void); extern void kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -295,12 +296,14 @@ static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {} static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {} #endif +extern unsigned long nested_capabilities; long kvmhv_nested_init(void); 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_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1); +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); long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu); @@ -316,6 +319,69 @@ long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu); void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac); + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + +extern struct static_key_false __kvmhv_is_nestedv2; + +static inline bool kvmhv_is_nestedv2(void) +{ + return static_branch_unlikely(&__kvmhv_is_nestedv2); +} + +static inline bool kvmhv_is_nestedv1(void) +{ + return !static_branch_likely(&__kvmhv_is_nestedv2); +} + +#else + +static inline bool kvmhv_is_nestedv2(void) +{ + return false; +} + +static inline bool kvmhv_is_nestedv1(void) +{ + return false; +} + +#endif + +int __kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs); +int __kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs); +int __kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden); +int __kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden); + +static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_reload_ptregs(vcpu, regs); + return 0; +} +static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_mark_dirty_ptregs(vcpu, regs); + return 0; +} + +static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_mark_dirty(vcpu, iden); + return 0; +} + +static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_cached_reload(vcpu, iden); + return 0; +} + extern int kvm_irq_bypass; static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) @@ -335,60 +401,72 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { vcpu->arch.regs.gpr[num] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_GPR(num)); } static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_GPR(num)) < 0); return vcpu->arch.regs.gpr[num]; } static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) { vcpu->arch.regs.ccr = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CR); } static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CR) < 0); return vcpu->arch.regs.ccr; } static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.xer = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_XER); } static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_XER) < 0); return vcpu->arch.regs.xer; } static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.ctr = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CTR); } static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CTR) < 0); return vcpu->arch.regs.ctr; } static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.link = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LR); } static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_LR) < 0); return vcpu->arch.regs.link; } static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.nip = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_NIA); } static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_NIA) < 0); return vcpu->arch.regs.nip; } @@ -403,10 +481,144 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return vcpu->arch.fault_dar; } +static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0); + return vcpu->arch.fp.fpr[i][TS_FPROFFSET]; +} + +static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val) +{ + vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i)); +} + +static inline u64 kvmppc_get_fpscr(struct kvm_vcpu *vcpu) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_FPSCR) < 0); + return vcpu->arch.fp.fpscr; +} + +static inline void kvmppc_set_fpscr(struct kvm_vcpu *vcpu, u64 val) +{ + vcpu->arch.fp.fpscr = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_FPSCR); +} + + +static inline u64 kvmppc_get_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0); + return vcpu->arch.fp.fpr[i][j]; +} + +static inline void kvmppc_set_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j, + u64 val) +{ + vcpu->arch.fp.fpr[i][j] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i)); +} + +#ifdef CONFIG_ALTIVEC +static inline void kvmppc_get_vsx_vr(struct kvm_vcpu *vcpu, int i, vector128 *v) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(32 + i)) < 0); + *v = vcpu->arch.vr.vr[i]; +} + +static inline void kvmppc_set_vsx_vr(struct kvm_vcpu *vcpu, int i, + vector128 *val) +{ + vcpu->arch.vr.vr[i] = *val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(32 + i)); +} + +static inline u32 kvmppc_get_vscr(struct kvm_vcpu *vcpu) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSCR) < 0); + return vcpu->arch.vr.vscr.u[3]; +} + +static inline void kvmppc_set_vscr(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.vr.vscr.u[3] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSCR); +} +#endif + +#define KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden) \ +static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val) \ +{ \ + \ + vcpu->arch.reg = val; \ + kvmhv_nestedv2_mark_dirty(vcpu, iden); \ +} + +#define KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden) \ +static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ +{ \ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0); \ + return vcpu->arch.reg; \ +} + +#define KVMPPC_BOOK3S_VCPU_ACCESSOR(reg, size, iden) \ + KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden) \ + KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden) \ + +KVMPPC_BOOK3S_VCPU_ACCESSOR(pid, 32, KVMPPC_GSID_PIDR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(tar, 64, KVMPPC_GSID_TAR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbhr, 64, KVMPPC_GSID_EBBHR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbrr, 64, KVMPPC_GSID_EBBRR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(bescr, 64, KVMPPC_GSID_BESCR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(ic, 64, KVMPPC_GSID_IC) +KVMPPC_BOOK3S_VCPU_ACCESSOR(vrsave, 64, KVMPPC_GSID_VRSAVE) + + +#define KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden) \ +static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val) \ +{ \ + vcpu->arch.vcore->reg = val; \ + kvmhv_nestedv2_mark_dirty(vcpu, iden); \ +} + +#define KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden) \ +static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ +{ \ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0); \ + return vcpu->arch.vcore->reg; \ +} + +#define KVMPPC_BOOK3S_VCORE_ACCESSOR(reg, size, iden) \ + KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden) \ + KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden) \ + + +KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB) +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_DEC_EXPIRY_TB) < 0); + return vcpu->arch.dec_expires; +} + +static inline void kvmppc_set_dec_expires(struct kvm_vcpu *vcpu, u64 val) +{ + vcpu->arch.dec_expires = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB); +} + /* Expiry time of vcpu DEC relative to host TB */ static inline u64 kvmppc_dec_expires_host_tb(struct kvm_vcpu *vcpu) { - return vcpu->arch.dec_expires - vcpu->arch.vcore->tb_offset; + return kvmppc_get_dec_expires(vcpu) - kvmppc_get_tb_offset(vcpu); } static inline bool is_kvmppc_resume_guest(int r) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index d49065af08e9..d8729ec81ca0 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -624,7 +624,7 @@ static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu) extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte, unsigned long gpa, unsigned int level, - unsigned long mmu_seq, unsigned int lpid, + unsigned long mmu_seq, u64 lpid, unsigned long *rmapp, struct rmap_nested **n_rmap); extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp, struct rmap_nested **n_rmap); @@ -677,6 +677,13 @@ static inline pte_t *find_kvm_host_pte(struct kvm *kvm, unsigned long mmu_seq, extern pte_t *find_kvm_nested_guest_pte(struct kvm *kvm, unsigned long lpid, unsigned long ea, unsigned *hshift); +int kvmhv_nestedv2_vcpu_create(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io); +void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io); +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 */ #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index 0c3401b2e19e..7c3291aa8922 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -89,6 +89,16 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) return vcpu->arch.regs.nip; } +static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val) +{ + vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val; +} + +static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i) +{ + return vcpu->arch.fp.fpr[i][TS_FPROFFSET]; +} + #ifdef CONFIG_BOOKE static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 14ee0dece853..8abac532146e 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -25,6 +25,7 @@ #include <asm/cacheflush.h> #include <asm/hvcall.h> #include <asm/mce.h> +#include <asm/guest-state-buffer.h> #define __KVM_HAVE_ARCH_VCPU_DEBUGFS @@ -62,8 +63,6 @@ #include <linux/mmu_notifier.h> -#define KVM_ARCH_WANT_MMU_NOTIFIER - #define HPTEG_CACHE_NUM (1 << 15) #define HPTEG_HASH_BITS_PTE 13 #define HPTEG_HASH_BITS_PTE_LONG 12 @@ -276,7 +275,7 @@ struct kvm_resize_hpt; #define KVMPPC_SECURE_INIT_ABORT 0x4 /* H_SVM_INIT_ABORT issued */ struct kvm_arch { - unsigned int lpid; + u64 lpid; unsigned int smt_mode; /* # vcpus per virtual core */ unsigned int emul_smt_mode; /* emualted SMT mode, on P9 */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -509,6 +508,23 @@ union xive_tma_w01 { __be64 w01; }; + /* Nestedv2 H_GUEST_RUN_VCPU configuration */ +struct kvmhv_nestedv2_config { + struct kvmppc_gs_buff_info vcpu_run_output_cfg; + struct kvmppc_gs_buff_info vcpu_run_input_cfg; + u64 vcpu_run_output_size; +}; + + /* Nestedv2 L1<->L0 communication state */ +struct kvmhv_nestedv2_io { + struct kvmhv_nestedv2_config cfg; + struct kvmppc_gs_buff *vcpu_run_output; + struct kvmppc_gs_buff *vcpu_run_input; + struct kvmppc_gs_msg *vcpu_message; + struct kvmppc_gs_msg *vcore_message; + struct kvmppc_gs_bitmap valids; +}; + struct kvm_vcpu_arch { ulong host_stack; u32 host_pid; @@ -829,6 +845,8 @@ struct kvm_vcpu_arch { u64 nested_hfscr; /* HFSCR that the L1 requested for the nested guest */ u32 nested_vcpu_id; gpa_t nested_io_gpr; + /* For nested APIv2 guests*/ + struct kvmhv_nestedv2_io nestedv2_io; #endif #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index b4da8514af43..3281215097cc 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -615,6 +615,42 @@ static inline bool kvmhv_on_pseries(void) { return false; } + +#endif + +#ifndef CONFIG_PPC_BOOK3S + +static inline bool kvmhv_is_nestedv2(void) +{ + return false; +} + +static inline bool kvmhv_is_nestedv1(void) +{ + return false; +} + +static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + return 0; +} +static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + return 0; +} + +static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden) +{ + return 0; +} + +static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden) +{ + return 0; +} + #endif #ifdef CONFIG_KVM_XICS @@ -927,79 +963,85 @@ static inline bool kvmppc_shared_big_endian(struct kvm_vcpu *vcpu) #endif } -#define SPRNG_WRAPPER_GET(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr) \ static inline ulong kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ { \ return mfspr(bookehv_spr); \ } \ -#define SPRNG_WRAPPER_SET(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr) \ static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, ulong val) \ { \ mtspr(bookehv_spr, val); \ } \ -#define SHARED_WRAPPER_GET(reg, size) \ +#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden) \ static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ { \ + if (iden) \ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0); \ if (kvmppc_shared_big_endian(vcpu)) \ - return be##size##_to_cpu(vcpu->arch.shared->reg); \ + return be##size##_to_cpu((__be##size __force)vcpu->arch.shared->reg); \ else \ - return le##size##_to_cpu(vcpu->arch.shared->reg); \ + return le##size##_to_cpu((__le##size __force)vcpu->arch.shared->reg); \ } \ -#define SHARED_WRAPPER_SET(reg, size) \ +#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden) \ static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val) \ { \ if (kvmppc_shared_big_endian(vcpu)) \ - vcpu->arch.shared->reg = cpu_to_be##size(val); \ + vcpu->arch.shared->reg = (u##size __force)cpu_to_be##size(val); \ else \ - vcpu->arch.shared->reg = cpu_to_le##size(val); \ + vcpu->arch.shared->reg = (u##size __force)cpu_to_le##size(val); \ + \ + if (iden) \ + kvmhv_nestedv2_mark_dirty(vcpu, iden); \ } \ -#define SHARED_WRAPPER(reg, size) \ - SHARED_WRAPPER_GET(reg, size) \ - SHARED_WRAPPER_SET(reg, size) \ +#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden) \ + KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden) \ + KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden) \ -#define SPRNG_WRAPPER(reg, bookehv_spr) \ - SPRNG_WRAPPER_GET(reg, bookehv_spr) \ - SPRNG_WRAPPER_SET(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr) \ + KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr) \ + KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr) \ #ifdef CONFIG_KVM_BOOKE_HV -#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr) \ - SPRNG_WRAPPER(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden) \ + KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr) \ #else -#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr) \ - SHARED_WRAPPER(reg, size) \ +#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden) \ + KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden) \ #endif -SHARED_WRAPPER(critical, 64) -SHARED_SPRNG_WRAPPER(sprg0, 64, SPRN_GSPRG0) -SHARED_SPRNG_WRAPPER(sprg1, 64, SPRN_GSPRG1) -SHARED_SPRNG_WRAPPER(sprg2, 64, SPRN_GSPRG2) -SHARED_SPRNG_WRAPPER(sprg3, 64, SPRN_GSPRG3) -SHARED_SPRNG_WRAPPER(srr0, 64, SPRN_GSRR0) -SHARED_SPRNG_WRAPPER(srr1, 64, SPRN_GSRR1) -SHARED_SPRNG_WRAPPER(dar, 64, SPRN_GDEAR) -SHARED_SPRNG_WRAPPER(esr, 64, SPRN_GESR) -SHARED_WRAPPER_GET(msr, 64) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(critical, 64, 0) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg0, 64, SPRN_GSPRG0, KVMPPC_GSID_SPRG0) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg1, 64, SPRN_GSPRG1, KVMPPC_GSID_SPRG1) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg2, 64, SPRN_GSPRG2, KVMPPC_GSID_SPRG2) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg3, 64, SPRN_GSPRG3, KVMPPC_GSID_SPRG3) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr0, 64, SPRN_GSRR0, KVMPPC_GSID_SRR0) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr1, 64, SPRN_GSRR1, KVMPPC_GSID_SRR1) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(dar, 64, SPRN_GDEAR, KVMPPC_GSID_DAR) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(esr, 64, SPRN_GESR, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(msr, 64, KVMPPC_GSID_MSR) static inline void kvmppc_set_msr_fast(struct kvm_vcpu *vcpu, u64 val) { if (kvmppc_shared_big_endian(vcpu)) vcpu->arch.shared->msr = cpu_to_be64(val); else vcpu->arch.shared->msr = cpu_to_le64(val); + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_MSR); } -SHARED_WRAPPER(dsisr, 32) -SHARED_WRAPPER(int_pending, 32) -SHARED_WRAPPER(sprg4, 64) -SHARED_WRAPPER(sprg5, 64) -SHARED_WRAPPER(sprg6, 64) -SHARED_WRAPPER(sprg7, 64) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(dsisr, 32, KVMPPC_GSID_DSISR) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(int_pending, 32, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg4, 64, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg5, 64, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg6, 64, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg7, 64, 0) static inline u32 kvmppc_get_sr(struct kvm_vcpu *vcpu, int nr) { 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/local.h b/arch/powerpc/include/asm/local.h index 45492fb5bf22..ec6ced6d7ced 100644 --- a/arch/powerpc/include/asm/local.h +++ b/arch/powerpc/include/asm/local.h @@ -115,23 +115,23 @@ static __inline__ long local_xchg(local_t *l, long n) } /** - * local_add_unless - add unless the number is a given value + * local_add_unless - add unless the number is already a given value * @l: pointer of type local_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * Atomically adds @a to @l, so long as it was not @u. - * Returns non-zero if @l was not @u, and zero otherwise. + * Atomically adds @a to @l, if @v was not already @u. + * Returns true if the addition was done. */ -static __inline__ int local_add_unless(local_t *l, long a, long u) +static __inline__ bool local_add_unless(local_t *l, long a, long u) { unsigned long flags; - int ret = 0; + bool ret = false; powerpc_local_irq_pmu_save(flags); if (l->v != u) { l->v += a; - ret = 1; + ret = true; } powerpc_local_irq_pmu_restore(flags); diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 4f6e7d7ee388..d31a5ec1550d 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -10,7 +10,7 @@ #include <linux/export.h> struct pt_regs; -struct pci_bus; +struct pci_bus; struct device_node; struct iommu_table; struct rtc_time; @@ -78,8 +78,8 @@ struct machdep_calls { unsigned char (*nvram_read_val)(int addr); void (*nvram_write_val)(int addr, unsigned char val); ssize_t (*nvram_write)(char *buf, size_t count, loff_t *index); - ssize_t (*nvram_read)(char *buf, size_t count, loff_t *index); - ssize_t (*nvram_size)(void); + ssize_t (*nvram_read)(char *buf, size_t count, loff_t *index); + ssize_t (*nvram_size)(void); void (*nvram_sync)(void); /* Exception handlers */ @@ -102,12 +102,11 @@ struct machdep_calls { */ long (*feature_call)(unsigned int feature, ...); - /* Get legacy PCI/IDE interrupt mapping */ + /* Get legacy PCI/IDE interrupt mapping */ int (*pci_get_legacy_ide_irq)(struct pci_dev *dev, int channel); - + /* Get access protection for /dev/mem */ - pgprot_t (*phys_mem_access_prot)(struct file *file, - unsigned long pfn, + pgprot_t (*phys_mem_access_prot)(unsigned long pfn, unsigned long size, pgprot_t vma_prot); 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/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h index de092b04ee1a..92df40c6cc6b 100644 --- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h @@ -46,7 +46,8 @@ static inline int check_and_get_huge_psize(int shift) } #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned long sz); #define __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h index 0e93a4728c9e..141d82e249a8 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -188,7 +188,6 @@ typedef struct { } mm_context_t; #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000) -#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE)) /* Page size definitions, common between 32 and 64-bit * diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index f99c53a5f184..9164a9e41b02 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -9,10 +9,6 @@ #include <linux/threads.h> #include <asm/mmu.h> /* For sub-arch specific PPC_PIN_SIZE */ -#ifdef CONFIG_44x -extern int icache_44x_need_flush; -#endif - #endif /* __ASSEMBLY__ */ #define PTE_INDEX_SIZE PTE_SHIFT @@ -55,26 +51,22 @@ extern int icache_44x_need_flush; #define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ - (unsigned long long)pte_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) -#ifndef __ASSEMBLY__ - -int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); -void unmap_kernel_page(unsigned long va); - -#endif /* !__ASSEMBLY__ */ - - /* * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary * value (for now) on others, from where we can start layout kernel * virtual space that goes below PKMAP and FIXMAP */ -#include <asm/fixmap.h> + +#define FIXADDR_SIZE 0 +#ifdef CONFIG_KASAN +#include <asm/kasan.h> +#define FIXADDR_TOP (KASAN_SHADOW_START - PAGE_SIZE) +#else +#define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) +#endif /* * ioremap_bot starts at that address. Early ioremaps move down from there, @@ -151,7 +143,7 @@ void unmap_kernel_page(unsigned long va); * The mask covered by the RPN must be a ULL on 32-bit platforms with * 64-bit PTEs. */ -#if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) +#ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) #define MAX_POSSIBLE_PHYSMEM_BITS 36 #else @@ -159,48 +151,8 @@ void unmap_kernel_page(unsigned long va); #define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif -/* - * _PAGE_CHG_MASK masks of bits that are to be preserved across - * pgprot changes. - */ -#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) - #ifndef __ASSEMBLY__ -#define pte_clear(mm, addr, ptep) \ - do { pte_update(mm, addr, ptep, ~0, 0, 0); } while (0) - -#ifndef pte_mkwrite_novma -static inline pte_t pte_mkwrite_novma(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_RW); -} -#endif - -static inline pte_t pte_mkdirty(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_DIRTY); -} - -static inline pte_t pte_mkyoung(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_ACCESSED); -} - -#ifndef pte_wrprotect -static inline pte_t pte_wrprotect(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_RW); -} -#endif - -#ifndef pte_mkexec -static inline pte_t pte_mkexec(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_EXEC); -} -#endif - #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) #define pmd_present(pmd) (pmd_val(pmd) & _PMD_PRESENT_MASK) @@ -210,141 +162,6 @@ static inline void pmd_clear(pmd_t *pmdp) } /* - * PTE updates. This function is called whenever an existing - * valid PTE is updated. This does -not- include set_pte_at() - * which nowadays only sets a new PTE. - * - * Depending on the type of MMU, we may need to use atomic updates - * and the PTE may be either 32 or 64 bit wide. In the later case, - * when using atomic updates, only the low part of the PTE is - * accessed atomically. - * - * In addition, on 44x, we also maintain a global flag indicating - * that an executable user mapping was modified, which is needed - * to properly flush the virtually tagged instruction cache of - * those implementations. - * - * On the 8xx, the page tables are a bit special. For 16k pages, we have - * 4 identical entries. For 512k pages, we have 128 entries as if it was - * 4k pages, but they are flagged as 512k pages for the hardware. - * For other page sizes, we have a single entry in the table. - */ -#ifdef CONFIG_PPC_8xx -static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); -static int hugepd_ok(hugepd_t hpd); - -static int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) -{ - if (!huge) - return PAGE_SIZE / SZ_4K; - else if (hugepd_ok(*((hugepd_t *)pmd))) - return 1; - else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE)) - return SZ_16K / SZ_4K; - else - return SZ_512K / SZ_4K; -} - -static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, - unsigned long clr, unsigned long set, int huge) -{ - pte_basic_t *entry = (pte_basic_t *)p; - pte_basic_t old = pte_val(*p); - pte_basic_t new = (old & ~(pte_basic_t)clr) | set; - int num, i; - pmd_t *pmd = pmd_off(mm, addr); - - num = number_of_cells_per_pte(pmd, new, huge); - - for (i = 0; i < num; i += PAGE_SIZE / SZ_4K, new += PAGE_SIZE) { - *entry++ = new; - if (IS_ENABLED(CONFIG_PPC_16K_PAGES) && num != 1) { - *entry++ = new; - *entry++ = new; - *entry++ = new; - } - } - - return old; -} - -#ifdef CONFIG_PPC_16K_PAGES -#define ptep_get ptep_get -static inline pte_t ptep_get(pte_t *ptep) -{ - pte_basic_t val = READ_ONCE(ptep->pte); - pte_t pte = {val, val, val, val}; - - return pte; -} -#endif /* CONFIG_PPC_16K_PAGES */ - -#else -static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, - unsigned long clr, unsigned long set, int huge) -{ - pte_basic_t old = pte_val(*p); - pte_basic_t new = (old & ~(pte_basic_t)clr) | set; - - *p = __pte(new); - -#ifdef CONFIG_44x - if ((old & _PAGE_USER) && (old & _PAGE_EXEC)) - icache_44x_need_flush = 1; -#endif - return old; -} -#endif - -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int __ptep_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - unsigned long old; - old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); - return (old & _PAGE_ACCESSED) != 0; -} -#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ - __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep) - -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - return __pte(pte_update(mm, addr, ptep, ~0, 0, 0)); -} - -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -#ifndef ptep_set_wrprotect -static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); -} -#endif - -#ifndef __ptep_set_access_flags -static inline void __ptep_set_access_flags(struct vm_area_struct *vma, - pte_t *ptep, pte_t entry, - unsigned long address, - int psize) -{ - unsigned long set = pte_val(entry) & - (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - int huge = psize > mmu_virtual_psize ? 1 : 0; - - pte_update(vma->vm_mm, address, ptep, 0, set, huge); - - flush_tlb_page(vma, address); -} -#endif - -static inline int pte_young(pte_t pte) -{ - return pte_val(pte) & _PAGE_ACCESSED; -} - -/* * Note that on Book E processors, the pmd contains the kernel virtual * (lowmem) address of the pte page. The physical address is less useful * because everything runs with translation enabled (even the TLB miss diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h index 6fe46e754556..d759cfd74754 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-40x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -42,10 +42,10 @@ #define _PAGE_PRESENT 0x002 /* software: PTE contains a translation */ #define _PAGE_NO_CACHE 0x004 /* I: caching is inhibited */ #define _PAGE_WRITETHRU 0x008 /* W: caching is write-through */ -#define _PAGE_USER 0x010 /* matches one of the zone permission bits */ +#define _PAGE_READ 0x010 /* software: read permission */ #define _PAGE_SPECIAL 0x020 /* software: Special page */ #define _PAGE_DIRTY 0x080 /* software: dirty page */ -#define _PAGE_RW 0x100 /* hardware: WR, anded with dirty in exception */ +#define _PAGE_WRITE 0x100 /* hardware: WR, anded with dirty in exception */ #define _PAGE_EXEC 0x200 /* hardware: EX permission */ #define _PAGE_ACCESSED 0x400 /* software: R: page referenced */ @@ -55,11 +55,6 @@ /* cache related flags non existing on 40x */ #define _PAGE_COHERENT 0 -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX _PAGE_EXEC -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) - #define _PMD_PRESENT 0x400 /* PMD points to page of PTEs */ #define _PMD_PRESENT_MASK _PMD_PRESENT #define _PMD_BAD 0x802 @@ -69,20 +64,10 @@ #define _PTE_NONE_MASK 0 -/* Until my rework is finished, 40x still needs atomic PTE updates */ -#define PTE_ATOMIC_UPDATES 1 - #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC) -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_40x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h index b7ed13cee137..851813725237 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-44x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h @@ -63,12 +63,12 @@ */ #define _PAGE_PRESENT 0x00000001 /* S: PTE valid */ -#define _PAGE_RW 0x00000002 /* S: Write permission */ +#define _PAGE_WRITE 0x00000002 /* S: Write permission */ #define _PAGE_EXEC 0x00000004 /* H: Execute permission */ -#define _PAGE_ACCESSED 0x00000008 /* S: Page referenced */ +#define _PAGE_READ 0x00000008 /* S: Read permission */ #define _PAGE_DIRTY 0x00000010 /* S: Page dirty */ #define _PAGE_SPECIAL 0x00000020 /* S: Special page */ -#define _PAGE_USER 0x00000040 /* S: User page */ +#define _PAGE_ACCESSED 0x00000040 /* S: Page referenced */ #define _PAGE_ENDIAN 0x00000080 /* H: E bit */ #define _PAGE_GUARDED 0x00000100 /* H: G bit */ #define _PAGE_COHERENT 0x00000200 /* H: M bit */ @@ -78,11 +78,6 @@ /* No page size encoding in the linux PTE */ #define _PAGE_PSIZE 0 -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX _PAGE_EXEC -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) - /* TODO: Add large page lowmem mapping support */ #define _PMD_PRESENT 0 #define _PMD_PRESENT_MASK (PAGE_MASK) @@ -105,14 +100,7 @@ #define _PAGE_BASE (_PAGE_BASE_NC) #endif -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_44x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h index 16451df5ddb0..653a342d3b25 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-85xx.h @@ -17,9 +17,9 @@ */ /* Definitions for FSL Book-E Cores */ -#define _PAGE_PRESENT 0x00001 /* S: PTE contains a translation */ -#define _PAGE_USER 0x00002 /* S: User page (maps to UR) */ -#define _PAGE_RW 0x00004 /* S: Write permission (SW) */ +#define _PAGE_READ 0x00001 /* H: Read permission (SR) */ +#define _PAGE_PRESENT 0x00002 /* S: PTE contains a translation */ +#define _PAGE_WRITE 0x00004 /* S: Write permission (SW) */ #define _PAGE_DIRTY 0x00008 /* S: Page dirty */ #define _PAGE_EXEC 0x00010 /* H: SX permission */ #define _PAGE_ACCESSED 0x00020 /* S: Page referenced */ @@ -31,11 +31,6 @@ #define _PAGE_WRITETHRU 0x00400 /* H: W bit */ #define _PAGE_SPECIAL 0x00800 /* S: Special page */ -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX _PAGE_EXEC -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) - /* No page size encoding in the linux PTE */ #define _PAGE_PSIZE 0 @@ -61,14 +56,7 @@ #define _PAGE_BASE (_PAGE_BASE_NC) #endif -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 21f681ee535a..137dc3c84e45 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -48,6 +48,11 @@ #define _PAGE_HUGE 0x0800 /* Copied to L1 PS bit 29 */ +#define _PAGE_NAX (_PAGE_NA | _PAGE_EXEC) +#define _PAGE_ROX (_PAGE_RO | _PAGE_EXEC) +#define _PAGE_RW 0 +#define _PAGE_RWX _PAGE_EXEC + /* cache related flags non existing on 8xx */ #define _PAGE_COHERENT 0 #define _PAGE_WRITETHRU 0 @@ -77,14 +82,7 @@ #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE) #define _PAGE_BASE (_PAGE_BASE_NC) -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_NA) -#define PAGE_SHARED __pgprot(_PAGE_BASE) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_RO) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_RO) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #ifndef __ASSEMBLY__ static inline pte_t pte_wrprotect(pte_t pte) @@ -94,6 +92,13 @@ static inline pte_t pte_wrprotect(pte_t pte) #define pte_wrprotect pte_wrprotect +static inline int pte_read(pte_t pte) +{ + return (pte_val(pte) & _PAGE_RO) != _PAGE_NA; +} + +#define pte_read pte_read + static inline int pte_write(pte_t pte) { return !(pte_val(pte) & _PAGE_RO); @@ -108,27 +113,6 @@ static inline pte_t pte_mkwrite_novma(pte_t pte) #define pte_mkwrite_novma pte_mkwrite_novma -static inline bool pte_user(pte_t pte) -{ - return !(pte_val(pte) & _PAGE_SH); -} - -#define pte_user pte_user - -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_SH); -} - -#define pte_mkprivileged pte_mkprivileged - -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_SH); -} - -#define pte_mkuser pte_mkuser - static inline pte_t pte_mkhuge(pte_t pte) { return __pte(pte_val(pte) | _PAGE_SPS | _PAGE_HUGE); @@ -180,6 +164,63 @@ static inline unsigned long pte_leaf_size(pte_t pte) #define pte_leaf_size pte_leaf_size +/* + * On the 8xx, the page tables are a bit special. For 16k pages, we have + * 4 identical entries. For 512k pages, we have 128 entries as if it was + * 4k pages, but they are flagged as 512k pages for the hardware. + * For other page sizes, we have a single entry in the table. + */ +static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); +static int hugepd_ok(hugepd_t hpd); + +static inline int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) +{ + if (!huge) + return PAGE_SIZE / SZ_4K; + else if (hugepd_ok(*((hugepd_t *)pmd))) + return 1; + else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE)) + return SZ_16K / SZ_4K; + else + return SZ_512K / SZ_4K; +} + +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge) +{ + pte_basic_t *entry = (pte_basic_t *)p; + pte_basic_t old = pte_val(*p); + pte_basic_t new = (old & ~(pte_basic_t)clr) | set; + int num, i; + pmd_t *pmd = pmd_off(mm, addr); + + num = number_of_cells_per_pte(pmd, new, huge); + + for (i = 0; i < num; i += PAGE_SIZE / SZ_4K, new += PAGE_SIZE) { + *entry++ = new; + if (IS_ENABLED(CONFIG_PPC_16K_PAGES) && num != 1) { + *entry++ = new; + *entry++ = new; + *entry++ = new; + } + } + + return old; +} + +#define pte_update pte_update + +#ifdef CONFIG_PPC_16K_PAGES +#define ptep_get ptep_get +static inline pte_t ptep_get(pte_t *ptep) +{ + pte_basic_t val = READ_ONCE(ptep->pte); + pte_t pte = {val, val, val, val}; + + return pte; +} +#endif /* CONFIG_PPC_16K_PAGES */ + #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 5cd9acf58a7d..2202c78730e8 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -57,6 +57,7 @@ #define IOREMAP_START (ioremap_bot) #define IOREMAP_END (KERN_IO_START + KERN_IO_SIZE - FIXADDR_SIZE) #define FIXADDR_SIZE SZ_32M +#define FIXADDR_TOP (IOREMAP_END + FIXADDR_SIZE) /* * Defines the address of the vmemap area, in its own region on @@ -74,37 +75,11 @@ #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) -/* - * _PAGE_CHG_MASK masks of bits that are to be preserved across - * pgprot changes. - */ -#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) - #define H_PAGE_4K_PFN 0 #ifndef __ASSEMBLY__ /* pte_clear moved to later in this file */ -static inline pte_t pte_mkwrite_novma(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_RW); -} - -static inline pte_t pte_mkdirty(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_DIRTY); -} - -static inline pte_t pte_mkyoung(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_ACCESSED); -} - -static inline pte_t pte_wrprotect(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_RW); -} - #define PMD_BAD_BITS (PTE_TABLE_SIZE-1) #define PUD_BAD_BITS (PMD_TABLE_SIZE-1) @@ -170,107 +145,20 @@ static inline void p4d_set(p4d_t *p4dp, unsigned long val) *p4dp = __p4d(val); } -/* Atomic PTE updates */ -static inline unsigned long pte_update(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, unsigned long clr, - unsigned long set, - int huge) -{ - unsigned long old = pte_val(*ptep); - *ptep = __pte((old & ~clr) | set); - - /* huge pages use the old page table lock */ - if (!huge) - assert_pte_locked(mm, addr); - - return old; -} - -static inline int pte_young(pte_t pte) -{ - return pte_val(pte) & _PAGE_ACCESSED; -} - -static inline int __ptep_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - unsigned long old; - - if (pte_young(*ptep)) - return 0; - old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); - return (old & _PAGE_ACCESSED) != 0; -} -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ -({ \ - int __r; \ - __r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ - __r; \ -}) - -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - - if ((pte_val(*ptep) & _PAGE_RW) == 0) - return; - - pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); -} - #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - if ((pte_val(*ptep) & _PAGE_RW) == 0) - return; - - pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young(__vma, __address, __ptep) \ ({ \ - int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \ - __ptep); \ + int __young = ptep_test_and_clear_young(__vma, __address, __ptep);\ __young; \ }) -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); - return __pte(old); -} - -static inline void pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t * ptep) -{ - pte_update(mm, addr, ptep, ~0UL, 0, 0); -} - - -/* Set the dirty and/or accessed bits atomically in a linux PTE */ -static inline void __ptep_set_access_flags(struct vm_area_struct *vma, - pte_t *ptep, pte_t entry, - unsigned long address, - int psize) -{ - unsigned long bits = pte_val(entry) & - (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - - unsigned long old = pte_val(*ptep); - *ptep = __pte(old | bits); - - flush_tlb_page(vma, address); -} - -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) #define pgd_ERROR(e) \ @@ -310,8 +198,6 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, /* We borrow MSB 56 (LSB 7) to store the exclusive marker in swap PTEs. */ #define _PAGE_SWP_EXCLUSIVE 0x80 -int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); -void unmap_kernel_page(unsigned long va); extern int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 56ea48276356..427db14292c9 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -2,12 +2,23 @@ #ifndef _ASM_POWERPC_NOHASH_PGTABLE_H #define _ASM_POWERPC_NOHASH_PGTABLE_H +#ifndef __ASSEMBLY__ +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge); +#endif + #if defined(CONFIG_PPC64) #include <asm/nohash/64/pgtable.h> #else #include <asm/nohash/32/pgtable.h> #endif +/* + * _PAGE_CHG_MASK masks of bits that are to be preserved across + * pgprot changes. + */ +#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) + /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) #define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE) @@ -18,14 +29,136 @@ #ifndef __ASSEMBLY__ +extern int icache_44x_need_flush; + +/* + * PTE updates. This function is called whenever an existing + * valid PTE is updated. This does -not- include set_pte_at() + * which nowadays only sets a new PTE. + * + * Depending on the type of MMU, we may need to use atomic updates + * and the PTE may be either 32 or 64 bit wide. In the later case, + * when using atomic updates, only the low part of the PTE is + * accessed atomically. + * + * In addition, on 44x, we also maintain a global flag indicating + * that an executable user mapping was modified, which is needed + * to properly flush the virtually tagged instruction cache of + * those implementations. + */ +#ifndef pte_update +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge) +{ + pte_basic_t old = pte_val(*p); + pte_basic_t new = (old & ~(pte_basic_t)clr) | set; + + if (new == old) + return old; + + *p = __pte(new); + + if (IS_ENABLED(CONFIG_44x) && !is_kernel_addr(addr) && (old & _PAGE_EXEC)) + icache_44x_need_flush = 1; + + /* huge pages use the old page table lock */ + if (!huge) + assert_pte_locked(mm, addr); + + return old; +} +#endif + +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + unsigned long old; + + old = pte_update(vma->vm_mm, addr, ptep, _PAGE_ACCESSED, 0, 0); + + return (old & _PAGE_ACCESSED) != 0; +} +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG + +#ifndef ptep_set_wrprotect +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); +} +#endif +#define __HAVE_ARCH_PTEP_SET_WRPROTECT + +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 0)); +} +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR + +static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + pte_update(mm, addr, ptep, ~0UL, 0, 0); +} + +/* Set the dirty and/or accessed bits atomically in a linux PTE */ +#ifndef __ptep_set_access_flags +static inline void __ptep_set_access_flags(struct vm_area_struct *vma, + pte_t *ptep, pte_t entry, + unsigned long address, + int psize) +{ + unsigned long set = pte_val(entry) & + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); + int huge = psize > mmu_virtual_psize ? 1 : 0; + + pte_update(vma->vm_mm, address, ptep, 0, set, huge); + + flush_tlb_page(vma, address); +} +#endif + /* Generic accessors to PTE bits */ +#ifndef pte_mkwrite_novma +static inline pte_t pte_mkwrite_novma(pte_t pte) +{ + /* + * write implies read, hence set both + */ + return __pte(pte_val(pte) | _PAGE_RW); +} +#endif + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +#ifndef pte_wrprotect +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_WRITE); +} +#endif + +#ifndef pte_mkexec +static inline pte_t pte_mkexec(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_EXEC); +} +#endif + #ifndef pte_write static inline int pte_write(pte_t pte) { - return pte_val(pte) & _PAGE_RW; + return pte_val(pte) & _PAGE_WRITE; } #endif -static inline int pte_read(pte_t pte) { return 1; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } @@ -33,23 +166,6 @@ static inline bool pte_hashpte(pte_t pte) { return false; } static inline bool pte_ci(pte_t pte) { return pte_val(pte) & _PAGE_NO_CACHE; } static inline bool pte_exec(pte_t pte) { return pte_val(pte) & _PAGE_EXEC; } -#ifdef CONFIG_NUMA_BALANCING -/* - * These work without NUMA balancing but the kernel does not care. See the - * comment in include/linux/pgtable.h . On powerpc, this will only - * work for user pages and always return true for kernel pages. - */ -static inline int pte_protnone(pte_t pte) -{ - return pte_present(pte) && !pte_user(pte); -} - -static inline int pmd_protnone(pmd_t pmd) -{ - return pte_protnone(pmd_pte(pmd)); -} -#endif /* CONFIG_NUMA_BALANCING */ - static inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_PRESENT; @@ -60,15 +176,20 @@ static inline bool pte_hw_valid(pte_t pte) return pte_val(pte) & _PAGE_PRESENT; } +static inline int pte_young(pte_t pte) +{ + return pte_val(pte) & _PAGE_ACCESSED; +} + /* - * Don't just check for any non zero bits in __PAGE_USER, since for book3e + * Don't just check for any non zero bits in __PAGE_READ, since for book3e * and PTE_64BIT, PAGE_KERNEL_X contains _PAGE_BAP_SR which is also in - * _PAGE_USER. Need to explicitly match _PAGE_BAP_UR bit in that case too. + * _PAGE_READ. Need to explicitly match _PAGE_BAP_UR bit in that case too. */ -#ifndef pte_user -static inline bool pte_user(pte_t pte) +#ifndef pte_read +static inline bool pte_read(pte_t pte) { - return (pte_val(pte) & _PAGE_USER) == _PAGE_USER; + return (pte_val(pte) & _PAGE_READ) == _PAGE_READ; } #endif @@ -80,10 +201,10 @@ static inline bool pte_user(pte_t pte) static inline bool pte_access_permitted(pte_t pte, bool write) { /* - * A read-only access is controlled by _PAGE_USER bit. - * We have _PAGE_READ set for WRITE and EXECUTE + * A read-only access is controlled by _PAGE_READ bit. + * We have _PAGE_READ set for WRITE */ - if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) + if (!pte_present(pte) || !pte_read(pte)) return false; if (write && !pte_write(pte)) @@ -130,20 +251,6 @@ static inline pte_t pte_mkhuge(pte_t pte) } #endif -#ifndef pte_mkprivileged -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_USER); -} -#endif - -#ifndef pte_mkuser -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_USER); -} -#endif - static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); @@ -205,11 +312,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, mb(); } - -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, pte_t entry, int dirty); - /* * Macro to mark a page protection value as "uncacheable". */ @@ -238,11 +340,6 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre #define pgprot_writecombine pgprot_noncached_wc -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - #ifdef CONFIG_HUGETLB_PAGE static inline int hugepd_ok(hugepd_t hpd) { @@ -267,20 +364,8 @@ static inline int pud_huge(pud_t pud) #define is_hugepd(hpd) (hugepd_ok(hpd)) #endif -/* - * This gets called at the end of handling a page fault, when - * the kernel has put a new PTE into the page table for the process. - * We use it to ensure coherency between the i-cache and d-cache - * for the page which has just been mapped in. - */ -#if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE) -void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, unsigned int nr); -#else -static inline void update_mmu_cache_range(struct vm_fault *vmf, - struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, unsigned int nr) {} -#endif +int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/nohash/pte-e500.h b/arch/powerpc/include/asm/nohash/pte-e500.h index d8924cbd61e4..f516f0b5b7a8 100644 --- a/arch/powerpc/include/asm/nohash/pte-e500.h +++ b/arch/powerpc/include/asm/nohash/pte-e500.h @@ -48,13 +48,20 @@ /* "Higher level" linux bit combinations */ #define _PAGE_EXEC (_PAGE_BAP_SX | _PAGE_BAP_UX) /* .. and was cache cleaned */ -#define _PAGE_RW (_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */ +#define _PAGE_READ (_PAGE_BAP_SR | _PAGE_BAP_UR) /* User read permission */ +#define _PAGE_WRITE (_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */ + #define _PAGE_KERNEL_RW (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY) #define _PAGE_KERNEL_RO (_PAGE_BAP_SR) #define _PAGE_KERNEL_RWX (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY | _PAGE_BAP_SX) #define _PAGE_KERNEL_ROX (_PAGE_BAP_SR | _PAGE_BAP_SX) -#define _PAGE_USER (_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */ -#define _PAGE_PRIVILEGED (_PAGE_BAP_SR) + +#define _PAGE_NA 0 +#define _PAGE_NAX _PAGE_BAP_UX +#define _PAGE_RO _PAGE_READ +#define _PAGE_ROX (_PAGE_READ | _PAGE_BAP_UX) +#define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) +#define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_BAP_UX) #define _PAGE_SPECIAL _PAGE_SW0 @@ -89,36 +96,12 @@ #define _PAGE_BASE (_PAGE_BASE_NC) #endif -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_BAP_UX) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_BAP_UX) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_BAP_UX) +#include <asm/pgtable-masks.h> #ifndef __ASSEMBLY__ -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte((pte_val(pte) & ~_PAGE_USER) | _PAGE_PRIVILEGED); -} - -#define pte_mkprivileged pte_mkprivileged - -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte((pte_val(pte) & ~_PAGE_PRIVILEGED) | _PAGE_USER); -} - -#define pte_mkuser pte_mkuser - static inline pte_t pte_mkexec(pte_t pte) { - if (pte_val(pte) & _PAGE_BAP_UR) - return __pte((pte_val(pte) & ~_PAGE_BAP_SX) | _PAGE_BAP_UX); - else - return __pte((pte_val(pte) & ~_PAGE_BAP_UX) | _PAGE_BAP_SX); + return __pte((pte_val(pte) & ~_PAGE_BAP_SX) | _PAGE_BAP_UX); } #define pte_mkexec pte_mkexec diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index a9b31cc258fc..af304e6cb486 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -227,7 +227,7 @@ int64_t opal_pci_set_power_state(uint64_t async_token, uint64_t id, uint64_t data); int64_t opal_pci_poll2(uint64_t id, uint64_t data); -int64_t opal_int_get_xirr(uint32_t *out_xirr, bool just_poll); +int64_t opal_int_get_xirr(__be32 *out_xirr, bool just_poll); int64_t opal_int_set_cppr(uint8_t cppr); int64_t opal_int_eoi(uint32_t xirr); int64_t opal_int_set_mfrr(uint32_t cpu, uint8_t mfrr); @@ -313,9 +313,11 @@ extern int early_init_dt_scan_recoverable_ranges(unsigned long node, const char *uname, int depth, void *data); void __init opal_configure_cores(void); -extern int opal_get_chars(uint32_t vtermno, char *buf, int count); -extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len); -extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len); +extern ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count); +extern ssize_t opal_put_chars(uint32_t vtermno, const u8 *buf, + size_t total_len); +extern ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *buf, + size_t total_len); extern int opal_flush_chars(uint32_t vtermno, bool wait); extern int opal_flush_console(uint32_t vtermno); 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 e08513d73119..b78b82d66057 100644 --- a/arch/powerpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -71,6 +71,22 @@ static inline void yield_to_any(void) { plpar_hcall_norets_notrace(H_CONFER, -1, 0); } + +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) { @@ -100,6 +116,14 @@ static inline void prod_cpu(int cpu) ___bad_prod_cpu(); /* This would be a bug */ } +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 @@ -121,9 +145,23 @@ static inline bool vcpu_is_preempted(int cpu) if (!is_shared_processor()) return false; + /* + * If the hypervisor has dispatched the target CPU on a physical + * processor, then the target CPU is definitely not preempted. + */ + if (vcpu_is_dispatched(cpu)) + return false; + + /* + * 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; + #ifdef CONFIG_PPC_SPLPAR if (!is_kvm_guest()) { - int first_cpu; + int first_cpu, i; /* * The result of vcpu_is_preempted() is used in a @@ -143,17 +181,37 @@ 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. */ if (cpu_first_thread_sibling(cpu) == first_cpu) return false; + + /* + * 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 (vcpu_is_dispatched(i)) + return false; + if (!is_vcpu_idle(i)) + return true; + } } #endif - if (yield_count_of(cpu) & 1) - return true; + /* + * None of the threads in target CPU's core are running but none of + * them were preempted too. Hence assume the target CPU to be + * non-preempted. + */ return false; } diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index f5078a7dd85a..46a9c4491ed0 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -105,9 +105,7 @@ extern void of_scan_pci_bridge(struct pci_dev *dev); extern void of_scan_bus(struct device_node *node, struct pci_bus *bus); extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus); -struct file; -extern pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, +extern pgprot_t pci_phys_mem_access_prot(unsigned long pfn, unsigned long size, pgprot_t prot); diff --git a/arch/powerpc/include/asm/pgtable-masks.h b/arch/powerpc/include/asm/pgtable-masks.h new file mode 100644 index 000000000000..6e8e2db26a5a --- /dev/null +++ b/arch/powerpc/include/asm/pgtable-masks.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_PGTABLE_MASKS_H +#define _ASM_POWERPC_PGTABLE_MASKS_H + +#ifndef _PAGE_NA +#define _PAGE_NA 0 +#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) +#endif + +/* Permission flags for kernel mappings */ +#ifndef _PAGE_KERNEL_RO +#define _PAGE_KERNEL_RO _PAGE_RO +#define _PAGE_KERNEL_ROX _PAGE_ROX +#define _PAGE_KERNEL_RW (_PAGE_RW | _PAGE_DIRTY) +#define _PAGE_KERNEL_RWX (_PAGE_RWX | _PAGE_DIRTY) +#endif + +/* Permission masks used to generate the __P and __S table */ +#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_NA) +#define PAGE_EXECONLY_X __pgprot(_PAGE_BASE | _PAGE_NAX) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_RWX) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_RO) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_ROX) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_RO) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_ROX) + +#endif /* _ASM_POWERPC_PGTABLE_MASKS_H */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index d0ee46de248e..9224f23065ff 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -71,6 +71,12 @@ static inline pgprot_t pte_pgprot(pte_t pte) return __pgprot(pte_flags); } +static inline pgprot_t pgprot_nx(pgprot_t prot) +{ + return pte_pgprot(pte_exprotect(__pte(pgprot_val(prot)))); +} +#define pgprot_nx pgprot_nx + #ifndef pmd_page_vaddr static inline const void *pmd_page_vaddr(pmd_t pmd) { @@ -110,6 +116,41 @@ void mark_initmem_nx(void); static inline void mark_initmem_nx(void) { } #endif +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); + +pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size, + pgprot_t vma_prot); + +struct file; +static inline pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + return __phys_mem_access_prot(pfn, size, vma_prot); +} +#define __HAVE_PHYS_MEM_ACCESS_PROT + +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); + +/* + * This gets called at the end of handling a page fault, when + * the kernel has put a new PTE into the page table for the process. + * We use it to ensure coherency between the i-cache and d-cache + * for the page which has just been mapped in. + * On machines which use an MMU hash table, we use this to put a + * corresponding HPTE into the hash table ahead of time, instead of + * waiting for the inevitable extra hash-table miss exception. + */ +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, unsigned int nr) +{ + if ((mmu_has_feature(MMU_FTR_HPTE_TABLE) && !radix_enabled()) || + (IS_ENABLED(CONFIG_PPC_E500) && IS_ENABLED(CONFIG_HUGETLB_PAGE))) + __update_mmu_cache(vma, address, ptep); +} + /* * When used, PTE_FRAG_NR is defined in subarch pgtable.h * so we are sure it is included when arriving here. diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index fe3d0ea0058a..b3ee44a40c2f 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -6,6 +6,7 @@ #include <linux/string.h> #include <linux/irqflags.h> +#include <linux/delay.h> #include <asm/hvcall.h> #include <asm/paca.h> @@ -343,6 +344,212 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) return rc; } +static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + unsigned long token; + long rc; + + token = -1UL; + do { + rc = plpar_hcall(H_GUEST_CREATE, retbuf, flags, token); + if (rc == H_SUCCESS) + *guest_id = retbuf[0]; + + if (rc == H_BUSY) { + token = retbuf[0]; + cond_resched(); + } + + if (H_IS_LONG_BUSY(rc)) { + token = retbuf[0]; + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_create_vcpu(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id) +{ + long rc; + + do { + rc = plpar_hcall_norets(H_GUEST_CREATE_VCPU, 0, guest_id, vcpu_id); + + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_set_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + while (true) { + rc = plpar_hcall(H_GUEST_SET_STATE, retbuf, flags, guest_id, + vcpu_id, data_buffer, data_size); + + if (rc == H_BUSY) { + cpu_relax(); + continue; + } + + if (H_IS_LONG_BUSY(rc)) { + mdelay(get_longbusy_msecs(rc)); + continue; + } + + if (rc == H_INVALID_ELEMENT_ID) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_SIZE) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_VALUE) + *failed_index = retbuf[0]; + + break; + } + + return rc; +} + +static inline long plpar_guest_get_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + while (true) { + rc = plpar_hcall(H_GUEST_GET_STATE, retbuf, flags, guest_id, + vcpu_id, data_buffer, data_size); + + if (rc == H_BUSY) { + cpu_relax(); + continue; + } + + if (H_IS_LONG_BUSY(rc)) { + mdelay(get_longbusy_msecs(rc)); + continue; + } + + if (rc == H_INVALID_ELEMENT_ID) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_SIZE) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_VALUE) + *failed_index = retbuf[0]; + + break; + } + + return rc; +} + +static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id, + unsigned long vcpu_id, int *trap, + unsigned long *failed_index) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_GUEST_RUN_VCPU, retbuf, flags, guest_id, vcpu_id); + if (rc == H_SUCCESS) + *trap = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_ID) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_SIZE) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_VALUE) + *failed_index = retbuf[0]; + + return rc; +} + +static inline long plpar_guest_delete(unsigned long flags, u64 guest_id) +{ + long rc; + + do { + rc = plpar_hcall_norets(H_GUEST_DELETE, flags, guest_id); + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_set_capabilities(unsigned long flags, + unsigned long capabilities) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + do { + rc = plpar_hcall(H_GUEST_SET_CAPABILITIES, retbuf, flags, capabilities); + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_get_capabilities(unsigned long flags, + unsigned long *capabilities) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + do { + rc = plpar_hcall(H_GUEST_GET_CAPABILITIES, retbuf, flags); + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + } while (rc == H_BUSY); + + if (rc == H_SUCCESS) + *capabilities = retbuf[0]; + + return rc; +} + /* * Wrapper to H_RPT_INVALIDATE hcall that handles return values appropriately * @@ -355,7 +562,7 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) * error recovery of killing the process/guest will be eventually * needed. */ -static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type, +static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type, u64 page_sizes, u64 start, u64 end) { long rc; @@ -401,12 +608,68 @@ static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex, return 0; } -static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type, +static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type, u64 page_sizes, u64 start, u64 end) { return 0; } +static inline long plpar_guest_create_vcpu(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id) +{ + return 0; +} + +static inline long plpar_guest_get_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + return 0; +} + +static inline long plpar_guest_set_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + return 0; +} + +static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id, + unsigned long vcpu_id, int *trap, + unsigned long *failed_index) +{ + return 0; +} + +static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id) +{ + return 0; +} + +static inline long plpar_guest_delete(unsigned long flags, u64 guest_id) +{ + return 0; +} + +static inline long plpar_guest_get_capabilities(unsigned long flags, + unsigned long *capabilities) +{ + return 0; +} + +static inline long plpar_guest_set_capabilities(unsigned long flags, + unsigned long capabilities) +{ + return 0; +} + #endif /* CONFIG_PPC_PSERIES */ #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ 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/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 9db8b16567e2..ea8f91fbc62f 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -397,6 +397,23 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, return 0; } +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * We support up to 8 arguments and assume they are sent in through the GPRs. + * This will fail for fp/vector arguments, but those aren't usually found in + * kernel code. This is expected to be called from kprobes or ftrace with regs. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) +{ +#define NR_REG_ARGUMENTS 8 + if (n < NR_REG_ARGUMENTS) + return regs_get_register(regs, offsetof(struct pt_regs, gpr[3 + n])); + return 0; +} + #endif /* __ASSEMBLY__ */ #ifndef __powerpc64__ 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/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index fb725ec77926..de10437fd206 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -74,7 +74,7 @@ __pu_failed: \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op " %0,0(%1) # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -83,7 +83,7 @@ __pu_failed: \ : label) #else #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -97,7 +97,7 @@ __pu_failed: \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ @@ -146,7 +146,7 @@ do { \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op" %0,0(%1) # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -155,7 +155,7 @@ do { \ : label) #else #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -169,7 +169,7 @@ do { \ __get_user_asm_goto(x, addr, label, "ld") #else /* __powerpc64__ */ #define __get_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: lwz%X1 %0, %1\n" \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ @@ -374,7 +374,7 @@ copy_mc_to_user(void __user *to, const void *from, unsigned long n) if (check_copy_size(from, n, true)) { if (access_ok(to, n)) { allow_write_to_user(to, n); - n = copy_mc_generic((void *)to, from, n); + n = copy_mc_generic((void __force *)to, from, n); prevent_write_to_user(to, n); } } 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/btext.c b/arch/powerpc/kernel/btext.c index 19e46fd623b0..7f63f1cdc6c3 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -8,6 +8,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/font.h> #include <linux/memblock.h> #include <linux/pgtable.h> #include <linux/of.h> @@ -41,10 +42,6 @@ static unsigned char *logicalDisplayBase __force_data; unsigned long disp_BAT[2] __initdata = {0, 0}; -#define cmapsz (16*256) - -static unsigned char vga_font[cmapsz]; - static int boot_text_mapped __force_data; extern void rmci_on(void); @@ -407,7 +404,7 @@ static unsigned int expand_bits_16[4] = { }; -static void draw_byte_32(unsigned char *font, unsigned int *base, int rb) +static void draw_byte_32(const unsigned char *font, unsigned int *base, int rb) { int l, bits; int fg = 0xFFFFFFFFUL; @@ -428,7 +425,7 @@ static void draw_byte_32(unsigned char *font, unsigned int *base, int rb) } } -static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb) +static inline void draw_byte_16(const unsigned char *font, unsigned int *base, int rb) { int l, bits; int fg = 0xFFFFFFFFUL; @@ -446,7 +443,7 @@ static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb) } } -static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb) +static inline void draw_byte_8(const unsigned char *font, unsigned int *base, int rb) { int l, bits; int fg = 0x0F0F0F0FUL; @@ -465,7 +462,8 @@ static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb) static noinline void draw_byte(unsigned char c, long locX, long locY) { unsigned char *base = calc_base(locX << 3, locY << 4); - unsigned char *font = &vga_font[((unsigned int)c) * 16]; + unsigned int font_index = c * 16; + const unsigned char *font = font_sun_8x16.data + font_index; int rb = dispDeviceRowBytes; rmci_maybe_on(); @@ -583,349 +581,3 @@ void __init udbg_init_btext(void) */ udbg_putc = btext_drawchar; } - -static unsigned char vga_font[cmapsz] = { -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x81, 0xa5, 0x81, 0x81, 0xbd, -0x99, 0x81, 0x81, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xff, -0xdb, 0xff, 0xff, 0xc3, 0xe7, 0xff, 0xff, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x6c, 0xfe, 0xfe, 0xfe, 0xfe, 0x7c, 0x38, 0x10, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x7c, 0xfe, -0x7c, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, -0x3c, 0x3c, 0xe7, 0xe7, 0xe7, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x18, 0x3c, 0x7e, 0xff, 0xff, 0x7e, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, -0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, -0xff, 0xff, 0xe7, 0xc3, 0xc3, 0xe7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x42, 0x42, 0x66, 0x3c, 0x00, -0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc3, 0x99, 0xbd, -0xbd, 0x99, 0xc3, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x1e, 0x0e, -0x1a, 0x32, 0x78, 0xcc, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x3c, 0x66, 0x66, 0x66, 0x66, 0x3c, 0x18, 0x7e, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x33, 0x3f, 0x30, 0x30, 0x30, -0x30, 0x70, 0xf0, 0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0x63, -0x7f, 0x63, 0x63, 0x63, 0x63, 0x67, 0xe7, 0xe6, 0xc0, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x18, 0x18, 0xdb, 0x3c, 0xe7, 0x3c, 0xdb, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfe, 0xf8, -0xf0, 0xe0, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x06, 0x0e, -0x1e, 0x3e, 0xfe, 0x3e, 0x1e, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, -0x66, 0x00, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xdb, -0xdb, 0xdb, 0x7b, 0x1b, 0x1b, 0x1b, 0x1b, 0x1b, 0x00, 0x00, 0x00, 0x00, -0x00, 0x7c, 0xc6, 0x60, 0x38, 0x6c, 0xc6, 0xc6, 0x6c, 0x38, 0x0c, 0xc6, -0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0xfe, 0xfe, 0xfe, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, -0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x7e, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x18, 0x0c, 0xfe, 0x0c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x60, 0xfe, 0x60, 0x30, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0xc0, -0xc0, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x24, 0x66, 0xff, 0x66, 0x24, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x38, 0x7c, 0x7c, 0xfe, 0xfe, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xfe, 0x7c, 0x7c, -0x38, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x24, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6c, -0x6c, 0xfe, 0x6c, 0x6c, 0x6c, 0xfe, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, -0x18, 0x18, 0x7c, 0xc6, 0xc2, 0xc0, 0x7c, 0x06, 0x06, 0x86, 0xc6, 0x7c, -0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc2, 0xc6, 0x0c, 0x18, -0x30, 0x60, 0xc6, 0x86, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, -0x6c, 0x38, 0x76, 0xdc, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x30, 0x30, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x30, 0x30, 0x30, -0x30, 0x30, 0x18, 0x0c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x18, -0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x3c, 0xff, 0x3c, 0x66, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, -0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x02, 0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xce, 0xde, 0xf6, 0xe6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x38, 0x78, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, -0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0x06, 0x06, 0x3c, 0x06, 0x06, 0x06, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x1c, 0x3c, 0x6c, 0xcc, 0xfe, -0x0c, 0x0c, 0x0c, 0x1e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0, -0xc0, 0xc0, 0xfc, 0x06, 0x06, 0x06, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x60, 0xc0, 0xc0, 0xfc, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0x06, 0x06, 0x0c, 0x18, -0x30, 0x30, 0x30, 0x30, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, -0xc6, 0xc6, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x06, 0x06, 0x0c, 0x78, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, -0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x18, 0x18, 0x00, 0x00, 0x00, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x06, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, -0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, -0x30, 0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0x0c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xde, 0xde, -0xde, 0xdc, 0xc0, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, -0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x66, 0x66, 0x66, 0x66, 0xfc, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0xc2, 0xc0, 0xc0, 0xc0, -0xc0, 0xc2, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x6c, -0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x6c, 0xf8, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, 0x60, 0x62, 0x66, 0xfe, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, -0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, -0xc2, 0xc0, 0xc0, 0xde, 0xc6, 0xc6, 0x66, 0x3a, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x0c, -0x0c, 0x0c, 0x0c, 0x0c, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xe6, 0x66, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0x66, 0xe6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x60, 0x60, 0x60, 0x60, 0x60, -0x60, 0x62, 0x66, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xe7, -0xff, 0xff, 0xdb, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, 0xc6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, -0x66, 0x66, 0x7c, 0x60, 0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xd6, 0xde, 0x7c, -0x0c, 0x0e, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x6c, -0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, -0xc6, 0x60, 0x38, 0x0c, 0x06, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xff, 0xdb, 0x99, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, -0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x66, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x18, -0x3c, 0x66, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, -0xc3, 0x66, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xff, 0xc3, 0x86, 0x0c, 0x18, 0x30, 0x60, 0xc1, 0xc3, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x30, 0x30, 0x30, 0x30, 0x30, -0x30, 0x30, 0x30, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, -0xc0, 0xe0, 0x70, 0x38, 0x1c, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x3c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00, -0x30, 0x30, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x78, 0x0c, 0x7c, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe0, 0x60, -0x60, 0x78, 0x6c, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc0, 0xc0, 0xc0, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x0c, 0x0c, 0x3c, 0x6c, 0xcc, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xf0, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xcc, 0xcc, -0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0xcc, 0x78, 0x00, 0x00, 0x00, 0xe0, 0x60, -0x60, 0x6c, 0x76, 0x66, 0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x06, 0x00, 0x0e, 0x06, 0x06, -0x06, 0x06, 0x06, 0x06, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0xe0, 0x60, -0x60, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe6, 0xff, 0xdb, -0xdb, 0xdb, 0xdb, 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x66, 0x66, -0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x76, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0x0c, 0x1e, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x76, 0x66, 0x60, 0x60, 0x60, 0xf0, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0x60, -0x38, 0x0c, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x30, -0x30, 0xfc, 0x30, 0x30, 0x30, 0x30, 0x36, 0x1c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0xc3, -0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0x3c, 0x66, 0xc3, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xfe, 0xcc, 0x18, 0x30, 0x60, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x0e, 0x18, 0x18, 0x18, 0x70, 0x18, 0x18, 0x18, 0x18, 0x0e, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x00, 0x18, -0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x18, -0x18, 0x18, 0x0e, 0x18, 0x18, 0x18, 0x18, 0x70, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, -0xc6, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, -0xc2, 0xc0, 0xc0, 0xc0, 0xc2, 0x66, 0x3c, 0x0c, 0x06, 0x7c, 0x00, 0x00, -0x00, 0x00, 0xcc, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x00, 0x7c, 0xc6, 0xfe, -0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, -0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xcc, 0x00, 0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0x78, 0x0c, 0x7c, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, -0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x60, 0x60, 0x66, 0x3c, 0x0c, 0x06, -0x3c, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xfe, -0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, -0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x60, 0x30, 0x18, 0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x00, 0x00, 0x38, 0x18, 0x18, -0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, 0x66, -0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x60, 0x30, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0xc6, -0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, 0x00, -0x38, 0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x18, 0x30, 0x60, 0x00, 0xfe, 0x66, 0x60, 0x7c, 0x60, 0x60, 0x66, 0xfe, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6e, 0x3b, 0x1b, -0x7e, 0xd8, 0xdc, 0x77, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3e, 0x6c, -0xcc, 0xcc, 0xfe, 0xcc, 0xcc, 0xcc, 0xcc, 0xce, 0x00, 0x00, 0x00, 0x00, -0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x00, 0x7c, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, -0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x30, 0x78, 0xcc, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0xcc, 0xcc, 0xcc, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, -0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0x78, 0x00, -0x00, 0xc6, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, -0xc3, 0xc0, 0xc0, 0xc0, 0xc3, 0x7e, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, -0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xe6, 0xfc, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0xff, 0x18, -0xff, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, -0x7c, 0x62, 0x66, 0x6f, 0x66, 0x66, 0x66, 0xf3, 0x00, 0x00, 0x00, 0x00, -0x00, 0x0e, 0x1b, 0x18, 0x18, 0x18, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, -0xd8, 0x70, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0x78, 0x0c, 0x7c, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, -0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x18, 0x30, 0x60, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0xcc, 0xcc, 0xcc, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, -0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, -0x76, 0xdc, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x6c, 0x6c, 0x3e, 0x00, 0x7e, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c, -0x38, 0x00, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x30, 0x30, 0x00, 0x30, 0x30, 0x60, 0xc0, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0, -0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xfe, 0x06, 0x06, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, 0x60, 0xce, 0x9b, 0x06, -0x0c, 0x1f, 0x00, 0x00, 0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, -0x66, 0xce, 0x96, 0x3e, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, -0x00, 0x18, 0x18, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x6c, 0xd8, 0x6c, 0x36, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, 0x6c, 0x36, -0x6c, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x44, 0x11, 0x44, -0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, -0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, -0x55, 0xaa, 0x55, 0xaa, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, -0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x18, 0xf8, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, -0x36, 0xf6, 0x06, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x06, 0xf6, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0xf6, 0x06, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xfe, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0xf8, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x37, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x37, 0x30, 0x3f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xf7, 0x00, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xff, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x37, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, -0x36, 0xf7, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xff, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x3f, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, -0x18, 0x1f, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0xff, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x1f, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, -0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, -0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf0, 0xf0, 0xf0, 0xf0, -0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, -0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, -0x0f, 0x0f, 0x0f, 0x0f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x76, 0xdc, 0xd8, 0xd8, 0xd8, 0xdc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x78, 0xcc, 0xcc, 0xcc, 0xd8, 0xcc, 0xc6, 0xc6, 0xc6, 0xcc, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0xc6, 0xc0, 0xc0, 0xc0, -0xc0, 0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0xfe, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0xfe, 0xc6, 0x60, 0x30, 0x18, 0x30, 0x60, 0xc6, 0xfe, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xd8, 0xd8, -0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x66, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xc0, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x18, 0x3c, 0x66, 0x66, -0x66, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, -0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0x6c, 0x38, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x6c, 0xc6, 0xc6, 0xc6, 0x6c, 0x6c, 0x6c, 0x6c, 0xee, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x30, 0x18, 0x0c, 0x3e, 0x66, -0x66, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x7e, 0xdb, 0xdb, 0xdb, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x03, 0x06, 0x7e, 0xdb, 0xdb, 0xf3, 0x7e, 0x60, 0xc0, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x30, 0x60, 0x60, 0x7c, 0x60, -0x60, 0x60, 0x30, 0x1c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, -0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, 0x18, -0x18, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, -0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x00, 0x7e, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0x1b, 0x1b, 0x1b, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x7e, 0x00, 0x18, 0x18, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x00, -0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c, -0x38, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0f, 0x0c, 0x0c, -0x0c, 0x0c, 0x0c, 0xec, 0x6c, 0x6c, 0x3c, 0x1c, 0x00, 0x00, 0x00, 0x00, -0x00, 0xd8, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0xd8, 0x30, 0x60, 0xc8, 0xf8, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, -}; - 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/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 9a3b85bfc83f..2086fa6cdc25 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -19,6 +19,7 @@ #include <linux/uio.h> #include <asm/rtas.h> #include <asm/inst.h> +#include <asm/fadump.h> #ifdef DEBUG #include <asm/udbg.h> @@ -92,6 +93,17 @@ ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, return csize; } +/* + * Return true only when kexec based kernel dump capturing method is used. + * This ensures all restritions applied for kdump case are not automatically + * applied for fadump case. + */ +bool is_kdump_kernel(void) +{ + return !is_fadump_active() && elfcorehdr_addr != ELFCORE_ADDR_MAX; +} +EXPORT_SYMBOL_GPL(is_kdump_kernel); + #ifdef CONFIG_PPC_RTAS /* * The crashkernel region will almost always overlap the RTAS region, so diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 438568a472d0..48773d2d9be3 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -39,7 +39,7 @@ static int eeh_result_priority(enum pci_ers_result result) case PCI_ERS_RESULT_NEED_RESET: return 6; default: - WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", (int)result); + WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", result); return 0; } }; @@ -60,7 +60,7 @@ static const char *pci_ers_result_name(enum pci_ers_result result) case PCI_ERS_RESULT_NO_AER_DRIVER: return "no AER driver"; default: - WARN_ONCE(1, "Unknown result type: %d\n", (int)result); + WARN_ONCE(1, "Unknown result type: %d\n", result); return "unknown"; } }; diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 9692acb0361f..7eda33a24bb4 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -137,8 +137,9 @@ ret_from_syscall: lis r4,icache_44x_need_flush@ha lwz r5,icache_44x_need_flush@l(r4) cmplwi cr0,r5,0 - bne- 2f + bne- .L44x_icache_flush #endif /* CONFIG_PPC_47x */ +.L44x_icache_flush_return: kuep_unlock lwz r4,_LINK(r1) lwz r5,_CCR(r1) @@ -172,10 +173,11 @@ syscall_exit_finish: b 1b #ifdef CONFIG_44x -2: li r7,0 +.L44x_icache_flush: + li r7,0 iccci r0,r0 stw r7,icache_44x_need_flush@l(r4) - b 1b + b .L44x_icache_flush_return #endif /* CONFIG_44x */ .globl ret_from_fork 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/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index c33c8ebf8641..eaf2f167c342 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -893,7 +893,7 @@ __start_interrupts: * * Call convention: * - * syscall register convention is in Documentation/powerpc/syscall64-abi.rst + * syscall register convention is in Documentation/arch/powerpc/syscall64-abi.rst */ EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000) /* SCV 0 */ @@ -1952,8 +1952,8 @@ EXC_VIRT_NONE(0x4b00, 0x100) * Call convention: * * syscall and hypercalls register conventions are documented in - * Documentation/powerpc/syscall64-abi.rst and - * Documentation/powerpc/papr_hcalls.rst respectively. + * Documentation/arch/powerpc/syscall64-abi.rst and + * Documentation/arch/powerpc/papr_hcalls.rst respectively. * * The intersection of volatile registers that don't contain possible * inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 3ff2da7b120b..d14eda1e8589 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -313,7 +313,7 @@ static __init u64 fadump_calculate_reserve_size(void) * memory at a predefined offset. */ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), - &size, &base); + &size, &base, NULL, NULL); if (ret == 0 && size > 0) { unsigned long max_size; diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c index 20328f72f9f2..8987eee33dc8 100644 --- a/arch/powerpc/kernel/firmware.c +++ b/arch/powerpc/kernel/firmware.c @@ -23,6 +23,8 @@ EXPORT_SYMBOL_GPL(powerpc_firmware_features); #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST) DEFINE_STATIC_KEY_FALSE(kvm_guest); +EXPORT_SYMBOL_GPL(kvm_guest); + int __init check_kvm_guest(void) { struct device_node *hyper_node; diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 6a9acfb690c9..2f8f3f93cbb6 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -23,6 +23,15 @@ #include <asm/feature-fixups.h> #ifdef CONFIG_VSX +#define __REST_1FPVSR(n,c,base) \ +BEGIN_FTR_SECTION \ + b 2f; \ +END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ + REST_FPR(n,base); \ + b 3f; \ +2: REST_VSR(n,c,base); \ +3: + #define __REST_32FPVSRS(n,c,base) \ BEGIN_FTR_SECTION \ b 2f; \ @@ -41,9 +50,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ 2: SAVE_32VSRS(n,c,base); \ 3: #else +#define __REST_1FPVSR(n,b,base) REST_FPR(n, base) #define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base) #define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base) #endif +#define REST_1FPVSR(n,c,base) __REST_1FPVSR(n,__REG_##c,__REG_##base) #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base) #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base) @@ -67,6 +78,7 @@ _GLOBAL(store_fp_state) SAVE_32FPVSRS(0, R4, R3) mffs fr0 stfd fr0,FPSTATE_FPSCR(r3) + REST_1FPVSR(0, R4, R3) blr EXPORT_SYMBOL(store_fp_state) @@ -138,4 +150,5 @@ _GLOBAL(save_fpu) 2: SAVE_32FPVSRS(0, R4, R6) mffs fr0 stfd fr0,FPSTATE_FPSCR(r6) + REST_1FPVSR(0, R4, R6) blr diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index b32e7b2ebdcf..9fc90410b385 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -312,13 +312,13 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt) rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */ lwz r11, 0(r11) /* Get Linux PTE */ - li r9, _PAGE_PRESENT | _PAGE_ACCESSED + li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_READ andc. r9, r9, r11 /* Check permission */ bne 5f - rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */ - and r9, r9, r11 /* hwwrite = dirty & rw */ - rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */ + rlwinm r9, r11, 1, _PAGE_WRITE /* dirty => w */ + and r9, r9, r11 /* hwwrite = dirty & w */ + rlwimi r11, r9, 0, _PAGE_WRITE /* replace w by hwwrite */ /* Create TLB tag. This is the faulting address plus a static * set of bits. These are size, valid, E, U0. @@ -400,9 +400,9 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt) andc. r9, r9, r11 /* Check permission */ bne 5f - rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */ - and r9, r9, r11 /* hwwrite = dirty & rw */ - rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */ + rlwinm r9, r11, 1, _PAGE_WRITE /* dirty => w */ + and r9, r9, r11 /* hwwrite = dirty & w */ + rlwimi r11, r9, 0, _PAGE_WRITE /* replace w by hwwrite */ /* Create TLB tag. This is the faulting address plus a static * set of bits. These are size, valid, E, U0. @@ -561,10 +561,11 @@ finish_tlb_load: /* * Clear out the software-only bits in the PTE to generate the * TLB_DATA value. These are the bottom 2 bits of the RPM, the - * top 3 bits of the zone field, and M. + * 4 bits of the zone field, and M. */ - li r9, 0x0ce2 + li r9, 0x0cf2 andc r11, r11, r9 + rlwimi r11, r10, 8, 24, 27 /* Copy 4 upper address bit into zone */ /* load the next available TLB index. */ lwz r9, tlb_4xx_index@l(0) diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index a3197c9f721c..25642e802ed3 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -314,8 +314,8 @@ interrupt_base: * kernel page tables. */ lis r11, PAGE_OFFSET@h - cmplw r10, r11 - blt+ 3f + cmplw cr7, r10, r11 + blt+ cr7, 3f lis r11, swapper_pg_dir@h ori r11, r11, swapper_pg_dir@l @@ -342,7 +342,7 @@ interrupt_base: mtspr SPRN_MMUCR,r12 /* Mask of required permission bits. Note that while we - * do copy ESR:ST to _PAGE_RW position as trying to write + * do copy ESR:ST to _PAGE_WRITE position as trying to write * to an RO page is pretty common, we don't do it with * _PAGE_DIRTY. We could do it, but it's a fairly rare * event so I'd rather take the overhead when it happens @@ -355,7 +355,7 @@ interrupt_base: * place or can we save a couple of instructions here ? */ mfspr r12,SPRN_ESR - li r13,_PAGE_PRESENT|_PAGE_ACCESSED + li r13,_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_READ rlwimi r13,r12,10,30,30 /* Load the PTE */ @@ -428,8 +428,8 @@ interrupt_base: * kernel page tables. */ lis r11, PAGE_OFFSET@h - cmplw r10, r11 - blt+ 3f + cmplw cr7, r10, r11 + blt+ cr7, 3f lis r11, swapper_pg_dir@h ori r11, r11, swapper_pg_dir@l @@ -515,6 +515,7 @@ interrupt_base: * r11 - PTE high word value * r12 - PTE low word value * r13 - TLB index + * cr7 - Result of comparison with PAGE_OFFSET * MMUCR - loaded with proper value when we get here * Upon exit, we reload everything and RFI. */ @@ -533,11 +534,10 @@ finish_tlb_load_44x: tlbwe r10,r13,PPC44x_TLB_PAGEID /* Write PAGEID */ /* And WS 2 */ - li r10,0xf85 /* Mask to apply from PTE */ - rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */ + li r10,0xf84 /* Mask to apply from PTE */ + rlwimi r10,r12,29,30,31 /* DIRTY,READ -> SW,SR position */ and r11,r12,r10 /* Mask PTE bits to keep */ - andi. r10,r12,_PAGE_USER /* User page ? */ - beq 1f /* nope, leave U bits empty */ + bge cr7,1f /* User page ? no, leave U bits empty */ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */ rlwinm r11,r11,0,~PPC44x_TLB_SX /* Clear SX if User page */ 1: tlbwe r11,r13,PPC44x_TLB_ATTRIB /* Write ATTRIB */ @@ -568,8 +568,8 @@ finish_tlb_load_44x: * kernel page tables. */ lis r11,PAGE_OFFSET@h - cmplw cr0,r10,r11 - blt+ 3f + cmplw cr7,r10,r11 + blt+ cr7,3f lis r11,swapper_pg_dir@h ori r11,r11, swapper_pg_dir@l li r12,0 /* MMUCR = 0 */ @@ -586,7 +586,7 @@ finish_tlb_load_44x: 4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */ /* Mask of required permission bits. Note that while we - * do copy ESR:ST to _PAGE_RW position as trying to write + * do copy ESR:ST to _PAGE_WRITE position as trying to write * to an RO page is pretty common, we don't do it with * _PAGE_DIRTY. We could do it, but it's a fairly rare * event so I'd rather take the overhead when it happens @@ -599,7 +599,7 @@ finish_tlb_load_44x: * place or can we save a couple of instructions here ? */ mfspr r12,SPRN_ESR - li r13,_PAGE_PRESENT|_PAGE_ACCESSED + li r13,_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_READ rlwimi r13,r12,10,30,30 /* Load the PTE */ @@ -669,8 +669,8 @@ finish_tlb_load_44x: * kernel page tables. */ lis r11,PAGE_OFFSET@h - cmplw cr0,r10,r11 - blt+ 3f + cmplw cr7,r10,r11 + blt+ cr7,3f lis r11,swapper_pg_dir@h ori r11,r11, swapper_pg_dir@l li r12,0 /* MMUCR = 0 */ @@ -744,6 +744,7 @@ finish_tlb_load_44x: * r11 - PTE high word value * r12 - PTE low word value * r13 - free to use + * cr7 - Result of comparison with PAGE_OFFSET * MMUCR - loaded with proper value when we get here * Upon exit, we reload everything and RFI. */ @@ -753,11 +754,10 @@ finish_tlb_load_47x: tlbwe r11,r13,1 /* And make up word 2 */ - li r10,0xf85 /* Mask to apply from PTE */ - rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */ + li r10,0xf84 /* Mask to apply from PTE */ + rlwimi r10,r12,29,30,31 /* DIRTY,READ -> SW,SR position */ and r11,r12,r10 /* Mask PTE bits to keep */ - andi. r10,r12,_PAGE_USER /* User page ? */ - beq 1f /* nope, leave U bits empty */ + bge cr7,1f /* User page ? no, leave U bits empty */ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */ rlwinm r11,r11,0,~PPC47x_TLB2_SX /* Clear SX if User page */ 1: tlbwe r11,r13,2 diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index 97e9ea0c7297..39724ff5ae1f 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -395,7 +395,7 @@ interrupt_base: #ifdef CONFIG_PPC_FPU FP_UNAVAILABLE_EXCEPTION #else - EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, unknown_exception) + EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, emulation_assist_interrupt) #endif /* System Call Interrupt */ @@ -471,7 +471,7 @@ END_BTB_FLUSH_SECTION 4: /* Mask of required permission bits. Note that while we - * do copy ESR:ST to _PAGE_RW position as trying to write + * do copy ESR:ST to _PAGE_WRITE position as trying to write * to an RO page is pretty common, we don't do it with * _PAGE_DIRTY. We could do it, but it's a fairly rare * event so I'd rather take the overhead when it happens @@ -485,10 +485,10 @@ END_BTB_FLUSH_SECTION */ mfspr r12,SPRN_ESR #ifdef CONFIG_PTE_64BIT - li r13,_PAGE_PRESENT + li r13,_PAGE_PRESENT|_PAGE_BAP_SR oris r13,r13,_PAGE_ACCESSED@h #else - li r13,_PAGE_PRESENT|_PAGE_ACCESSED + li r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED #endif rlwimi r13,r12,11,29,29 @@ -783,15 +783,15 @@ BEGIN_MMU_FTR_SECTION mtspr SPRN_MAS7, r10 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) #else - li r10, (_PAGE_EXEC | _PAGE_PRESENT) + li r10, (_PAGE_EXEC | _PAGE_READ) mr r13, r11 rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */ and r12, r11, r10 - andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */ + mcrf cr0, cr5 /* Test for user page */ slwi r10, r12, 1 or r10, r10, r12 rlwinm r10, r10, 0, ~_PAGE_EXEC /* Clear SX on user pages */ - iseleq r12, r12, r10 + isellt r12, r10, r12 rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */ mtspr SPRN_MAS3, r13 #endif diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 6764b98ca360..c1d89764dd22 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -412,10 +412,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE) . = INTERRUPT_INST_TLB_MISS_603 InstructionTLBMiss: /* - * r0: scratch + * r0: userspace flag (later scratch) * r1: linux style pte ( later becomes ppc hardware pte ) * r2: ptr to linux-style pte - * r3: scratch + * r3: fault address */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_IMISS @@ -424,12 +424,13 @@ InstructionTLBMiss: cmplw 0,r1,r3 #endif mfspr r2, SPRN_SDR1 - li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER + li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC rlwinm r2, r2, 28, 0xfffff000 #ifdef CONFIG_MODULES + li r0, 3 bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ - li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC + li r0, 0 addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ #endif 112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ @@ -437,13 +438,15 @@ InstructionTLBMiss: rlwinm. r2,r2,0,0,19 /* extract address of pte page */ beq- InstructionAddressInvalid /* return if no mapping */ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ - lwz r0,0(r2) /* get linux-style pte */ - andc. r1,r1,r0 /* check access & ~permission */ + lwz r2,0(r2) /* get linux-style pte */ + andc. r1,r1,r2 /* check access & ~permission */ bne- InstructionAddressInvalid /* return if access not permitted */ /* Convert linux-style PTE to low word of PPC-style PTE */ - rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */ +#ifdef CONFIG_MODULES + rlwimi r2, r0, 0, 31, 31 /* userspace ? -> PP lsb */ +#endif ori r1, r1, 0xe06 /* clear out reserved bits */ - andc r1, r0, r1 /* PP = user? 1 : 0 */ + andc r1, r2, r1 /* PP = user? 1 : 0 */ BEGIN_FTR_SECTION rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) @@ -478,38 +481,38 @@ InstructionAddressInvalid: . = INTERRUPT_DATA_LOAD_TLB_MISS_603 DataLoadTLBMiss: /* - * r0: scratch + * r0: userspace flag (later scratch) * r1: linux style pte ( later becomes ppc hardware pte ) * r2: ptr to linux-style pte - * r3: scratch + * r3: fault address */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_DMISS lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SDR1 - li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER + li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_READ rlwinm r2, r2, 28, 0xfffff000 + li r0, 3 bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ - li r1, _PAGE_PRESENT | _PAGE_ACCESSED + li r0, 0 addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ 112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ lwz r2,0(r2) /* get pmd entry */ rlwinm. r2,r2,0,0,19 /* extract address of pte page */ beq- DataAddressInvalid /* return if no mapping */ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ - lwz r0,0(r2) /* get linux-style pte */ - andc. r1,r1,r0 /* check access & ~permission */ + lwz r2,0(r2) /* get linux-style pte */ + andc. r1,r1,r2 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ /* Convert linux-style PTE to low word of PPC-style PTE */ - rlwinm r1,r0,32-9,30,30 /* _PAGE_RW -> PP msb */ - rlwimi r0,r0,32-1,30,30 /* _PAGE_USER -> PP msb */ - rlwimi r1,r0,32-3,24,24 /* _PAGE_RW -> _PAGE_DIRTY */ - rlwimi r0,r0,32-1,31,31 /* _PAGE_USER -> PP lsb */ + rlwinm r1,r2,32-9,30,30 /* _PAGE_WRITE -> PP msb */ + rlwimi r2,r0,0,30,31 /* userspace ? -> PP */ + rlwimi r1,r2,32-3,24,24 /* _PAGE_WRITE -> _PAGE_DIRTY */ xori r1,r1,_PAGE_DIRTY /* clear dirty when not rw */ ori r1,r1,0xe04 /* clear out reserved bits */ - andc r1,r0,r1 /* PP = user? rw? 1: 3: 0 */ + andc r1,r2,r1 /* PP = user? rw? 1: 3: 0 */ BEGIN_FTR_SECTION rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) @@ -558,34 +561,35 @@ DataAddressInvalid: . = INTERRUPT_DATA_STORE_TLB_MISS_603 DataStoreTLBMiss: /* - * r0: scratch + * r0: userspace flag (later scratch) * r1: linux style pte ( later becomes ppc hardware pte ) * r2: ptr to linux-style pte - * r3: scratch + * r3: fault address */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_DMISS lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SDR1 - li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER + li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED rlwinm r2, r2, 28, 0xfffff000 + li r0, 3 bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ - li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED + li r0, 0 addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ 112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ lwz r2,0(r2) /* get pmd entry */ rlwinm. r2,r2,0,0,19 /* extract address of pte page */ beq- DataAddressInvalid /* return if no mapping */ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ - lwz r0,0(r2) /* get linux-style pte */ - andc. r1,r1,r0 /* check access & ~permission */ + lwz r2,0(r2) /* get linux-style pte */ + andc. r1,r1,r2 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ /* Convert linux-style PTE to low word of PPC-style PTE */ - rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */ + rlwimi r2,r0,0,31,31 /* userspace ? -> PP lsb */ li r1,0xe06 /* clear out reserved bits & PP msb */ - andc r1,r0,r1 /* PP = user? 1: 0 */ + andc r1,r2,r1 /* PP = user? 1: 0 */ BEGIN_FTR_SECTION rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) @@ -689,7 +693,8 @@ hash_page_dsi: mfdar r4 mfsrr0 r5 mfsrr1 r9 - rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */ + rlwinm r3, r3, 32 - 15, _PAGE_WRITE /* DSISR_STORE -> _PAGE_WRITE */ + ori r3, r3, _PAGE_PRESENT | _PAGE_READ bl hash_page mfspr r10, SPRN_SPRG_THREAD restore_regs_thread r10 @@ -699,7 +704,7 @@ hash_page_isi: mr r11, r10 mfspr r10, SPRN_SPRG_THREAD save_regs_thread r10 - li r3, 0 + li r3, _PAGE_PRESENT | _PAGE_EXEC lwz r4, SRR0(r10) lwz r9, SRR1(r10) bl hash_page diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index b8513dc3e53a..a1318ce18d0e 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -230,13 +230,15 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) struct arch_hw_breakpoint *info; int i; + preempt_disable(); + for (i = 0; i < nr_wp_slots(); i++) { struct perf_event *bp = __this_cpu_read(bp_per_reg[i]); if (unlikely(bp && counter_arch_bp(bp)->perf_single_step)) goto reset; } - return; + goto out; reset: regs_set_return_msr(regs, regs->msr & ~MSR_SE); @@ -245,6 +247,9 @@ reset: __set_breakpoint(i, info); info->perf_single_step = false; } + +out: + preempt_enable(); } static bool is_larx_stcx_instr(int type) @@ -363,6 +368,11 @@ static void handle_p10dd1_spurious_exception(struct perf_event **bp, } } +/* + * Handle a DABR or DAWR exception. + * + * Called in atomic context. + */ int hw_breakpoint_handler(struct die_args *args) { bool err = false; @@ -490,6 +500,8 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler); /* * Handle single-step exceptions following a DABR hit. + * + * Called in atomic context. */ static int single_step_dabr_instruction(struct die_args *args) { @@ -541,6 +553,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction); /* * Handle debug exception notifications. + * + * Called in atomic context. */ int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c index a74623025f3a..9e51801c4915 100644 --- a/arch/powerpc/kernel/hw_breakpoint_constraints.c +++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c @@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr, int *type, int *size, unsigned long *ea) { struct instruction_op op; + int err; - if (__get_user_instr(*instr, (void __user *)regs->nip)) + pagefault_disable(); + err = __get_user_instr(*instr, (void __user *)regs->nip); + pagefault_enable(); + + if (err) return; analyse_instr(&op, regs, *instr); diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index b1c0418b25c8..30b56c67fa61 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -105,7 +105,6 @@ static struct ctl_table powersave_nap_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - {} }; static int __init diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index c4f6d3c69ba9..eca293794a1e 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -3,6 +3,7 @@ #include <linux/context_tracking.h> #include <linux/err.h> #include <linux/compat.h> +#include <linux/rseq.h> #include <linux/sched/debug.h> /* for show_regs */ #include <asm/kup.h> diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c index 2f29b7d432de..6af535905984 100644 --- a/arch/powerpc/kernel/io.c +++ b/arch/powerpc/kernel/io.c @@ -33,7 +33,7 @@ void _insb(const volatile u8 __iomem *port, void *buf, long count) return; asm volatile("sync"); do { - tmp = *port; + tmp = *(const volatile u8 __force *)port; eieio(); *tbuf++ = tmp; } while (--count != 0); @@ -49,7 +49,7 @@ void _outsb(volatile u8 __iomem *port, const void *buf, long count) return; asm volatile("sync"); do { - *port = *tbuf++; + *(volatile u8 __force *)port = *tbuf++; } while (--count != 0); asm volatile("sync"); } @@ -64,7 +64,7 @@ void _insw_ns(const volatile u16 __iomem *port, void *buf, long count) return; asm volatile("sync"); do { - tmp = *port; + tmp = *(const volatile u16 __force *)port; eieio(); *tbuf++ = tmp; } while (--count != 0); @@ -80,7 +80,7 @@ void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count) return; asm volatile("sync"); do { - *port = *tbuf++; + *(volatile u16 __force *)port = *tbuf++; } while (--count != 0); asm volatile("sync"); } @@ -95,7 +95,7 @@ void _insl_ns(const volatile u32 __iomem *port, void *buf, long count) return; asm volatile("sync"); do { - tmp = *port; + tmp = *(const volatile u32 __force *)port; eieio(); *tbuf++ = tmp; } while (--count != 0); @@ -111,7 +111,7 @@ void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count) return; asm volatile("sync"); do { - *port = *tbuf++; + *(volatile u32 __force *)port = *tbuf++; } while (--count != 0); asm volatile("sync"); } diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 14251bc5219e..d71eac3b2887 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1074,10 +1074,10 @@ int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa) } EXPORT_SYMBOL_GPL(iommu_tce_check_gpa); -extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, - struct iommu_table *tbl, - unsigned long entry, unsigned long *hpa, - enum dma_data_direction *direction) +long iommu_tce_xchg_no_kill(struct mm_struct *mm, + struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction) { long ret; unsigned long size = 0; @@ -1280,34 +1280,64 @@ struct iommu_table_group_ops spapr_tce_table_group_ops = { /* * A simple iommu_ops to allow less cruft in generic VFIO code. */ -static int spapr_tce_blocking_iommu_attach_dev(struct iommu_domain *dom, - struct device *dev) +static int +spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, + struct device *dev) { + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct iommu_group *grp = iommu_group_get(dev); struct iommu_table_group *table_group; - int ret = -EINVAL; - if (!grp) - return -ENODEV; + /* At first attach the ownership is already set */ + if (!domain) + return 0; table_group = iommu_group_get_iommudata(grp); - ret = table_group->ops->take_ownership(table_group); + /* + * The domain being set to PLATFORM from earlier + * BLOCKED. The table_group ownership has to be released. + */ + table_group->ops->release_ownership(table_group); iommu_group_put(grp); - return ret; + return 0; } -static void spapr_tce_blocking_iommu_set_platform_dma(struct device *dev) +static const struct iommu_domain_ops spapr_tce_platform_domain_ops = { + .attach_dev = spapr_tce_platform_iommu_attach_dev, +}; + +static struct iommu_domain spapr_tce_platform_domain = { + .type = IOMMU_DOMAIN_PLATFORM, + .ops = &spapr_tce_platform_domain_ops, +}; + +static int +spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain, + struct device *dev) { struct iommu_group *grp = iommu_group_get(dev); struct iommu_table_group *table_group; + int ret = -EINVAL; + /* + * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain + * also sets the dma_api ops + */ table_group = iommu_group_get_iommudata(grp); - table_group->ops->release_ownership(table_group); + ret = table_group->ops->take_ownership(table_group); + iommu_group_put(grp); + + return ret; } -static const struct iommu_domain_ops spapr_tce_blocking_domain_ops = { - .attach_dev = spapr_tce_blocking_iommu_attach_dev, +static const struct iommu_domain_ops spapr_tce_blocked_domain_ops = { + .attach_dev = spapr_tce_blocked_iommu_attach_dev, +}; + +static struct iommu_domain spapr_tce_blocked_domain = { + .type = IOMMU_DOMAIN_BLOCKED, + .ops = &spapr_tce_blocked_domain_ops, }; static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap) @@ -1322,22 +1352,6 @@ static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } -static struct iommu_domain *spapr_tce_iommu_domain_alloc(unsigned int type) -{ - struct iommu_domain *dom; - - if (type != IOMMU_DOMAIN_BLOCKED) - return NULL; - - dom = kzalloc(sizeof(*dom), GFP_KERNEL); - if (!dom) - return NULL; - - dom->ops = &spapr_tce_blocking_domain_ops; - - return dom; -} - static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev) { struct pci_dev *pdev; @@ -1371,12 +1385,12 @@ static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev) } static const struct iommu_ops spapr_tce_iommu_ops = { + .default_domain = &spapr_tce_platform_domain, + .blocked_domain = &spapr_tce_blocked_domain, .capable = spapr_tce_iommu_capable, - .domain_alloc = spapr_tce_iommu_domain_alloc, .probe_device = spapr_tce_iommu_probe_device, .release_device = spapr_tce_iommu_release_device, .device_group = spapr_tce_iommu_device_group, - .set_platform_dma_ops = spapr_tce_blocking_iommu_set_platform_dma, }; static struct attribute *spapr_tce_iommu_attrs[] = { diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 938e66829eae..d5c48d1b0a31 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -230,7 +230,7 @@ again: * This allows interrupts to be unmasked without hard disabling, and * also without new hard interrupts coming in ahead of pending ones. */ - asm_volatile_goto( + asm goto( "1: \n" " lbz 9,%0(13) \n" " cmpwi 9,0 \n" diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index cda4e00b67c1..7502066c3c53 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -68,7 +68,7 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit, memblock_set_bottom_up(true); /* - * See Documentation/powerpc/ultravisor.rst for more details. + * See Documentation/arch/powerpc/ultravisor.rst for more details. * * UV/HV data sharing is in PAGE_SIZE granularity. In order to * minimize the number of pages shared, align the allocation to diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 040255ddb569..d95a48eff412 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -521,8 +521,7 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma) * PCI device, it tries to find the PCI device first and calls the * above routine */ -pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, +pgprot_t pci_phys_mem_access_prot(unsigned long pfn, unsigned long size, pgprot_t prot) { diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b68898ac07e1..9452a54d356c 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1198,11 +1198,11 @@ void kvmppc_save_user_regs(void) usermsr = current->thread.regs->msr; + /* Caller has enabled FP/VEC/VSX/TM in MSR */ if (usermsr & MSR_FP) - save_fpu(current); - + __giveup_fpu(current); if (usermsr & MSR_VEC) - save_altivec(current); + __giveup_altivec(current); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (usermsr & MSR_TM) { @@ -2258,6 +2258,22 @@ unsigned long __get_wchan(struct task_struct *p) return ret; } +static bool empty_user_regs(struct pt_regs *regs, struct task_struct *tsk) +{ + unsigned long stack_page; + + // A non-empty pt_regs should never have a zero MSR or TRAP value. + if (regs->msr || regs->trap) + return false; + + // Check it sits at the very base of the stack + stack_page = (unsigned long)task_stack_page(tsk); + if ((unsigned long)(regs + 1) != stack_page + THREAD_SIZE) + return false; + + return true; +} + static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH; void __no_sanitize_address show_stack(struct task_struct *tsk, @@ -2322,9 +2338,13 @@ void __no_sanitize_address show_stack(struct task_struct *tsk, lr = regs->link; printk("%s--- interrupt: %lx at %pS\n", loglvl, regs->trap, (void *)regs->nip); - __show_regs(regs); - printk("%s--- interrupt: %lx\n", - loglvl, regs->trap); + + // Detect the case of an empty pt_regs at the very base + // of the stack and suppress showing it in full. + if (!empty_user_regs(regs, tsk)) { + __show_regs(regs); + printk("%s--- interrupt: %lx\n", loglvl, regs->trap); + } firstframe = 1; } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index d464ba412084..e67effdba85c 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -947,7 +947,7 @@ struct option_vector7 { } __packed; struct ibm_arch_vec { - struct { u32 mask, val; } pvrs[14]; + struct { __be32 mask, val; } pvrs[14]; u8 num_vectors; diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c index 5d7a72b41ae7..727ed4a14545 100644 --- a/arch/powerpc/kernel/ptrace/ptrace.c +++ b/arch/powerpc/kernel/ptrace/ptrace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * PowerPC version * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) @@ -9,10 +10,6 @@ * * Modified by Cort Dougan (cort@hq.fsmlabs.com) * and Paul Mackerras (paulus@samba.org). - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file README.legal in the main directory of - * this archive for more details. */ #include <linux/regset.h> diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index 9454b8395b6a..f38df72e64b8 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -752,6 +752,8 @@ static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v) /** * ppc_rtas_rmo_buf_show() - Describe RTAS-addressable region for user space. + * @m: seq_file output target. + * @v: Unused. * * Base + size description of a range of RTAS-addressable memory set * aside for user space to use as work area(s) for certain RTAS 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/setup-common.c b/arch/powerpc/kernel/setup-common.c index 2f1026fba00d..9b142b9d5187 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -22,7 +22,6 @@ #include <linux/seq_file.h> #include <linux/ioport.h> #include <linux/console.h> -#include <linux/screen_info.h> #include <linux/root_dev.h> #include <linux/cpu.h> #include <linux/unistd.h> @@ -98,21 +97,6 @@ int boot_cpu_hwid = -1; int dcache_bsize; int icache_bsize; -/* - * This still seems to be needed... -- paulus - */ -struct screen_info screen_info = { - .orig_x = 0, - .orig_y = 25, - .orig_video_cols = 80, - .orig_video_lines = 25, - .orig_video_isVGA = 1, - .orig_video_points = 16 -}; -#if defined(CONFIG_FB_VGA16_MODULE) -EXPORT_SYMBOL(screen_info); -#endif - /* Variables required to store legacy IO irq routing */ int of_i8042_kbd_irq; EXPORT_SYMBOL_GPL(of_i8042_kbd_irq); @@ -601,7 +585,6 @@ struct seq_buf ppc_hw_desc __initdata = { .buffer = ppc_hw_desc_buf, .size = sizeof(ppc_hw_desc_buf), .len = 0, - .readpos = 0, }; static __init void probe_machine(void) @@ -948,6 +931,8 @@ void __init setup_arch(char **cmdline_p) /* Parse memory topology */ mem_topology_setup(); + /* Set max_mapnr before paging_init() */ + set_max_mapnr(max_pfn); /* * Release secondary cpus out of their spinloops at 0x60 now that diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 246201d0d879..2f19d5e94485 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -364,7 +364,7 @@ void __init early_setup(unsigned long dt_ptr) */ initialise_paca(&boot_paca, 0); fixup_boot_paca(&boot_paca); - WARN_ON(local_paca != 0); + WARN_ON(local_paca); setup_paca(&boot_paca); /* install the paca into registers */ /* -------- printk is now safe to use ------- */ diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 68a91e553e14..aa17e62f3754 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Common signal handling code for both 32 and 64 bits * * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation * Extracted from signal_32.c and signal_64.c - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file README.legal in the main directory of - * this archive for more details. */ #include <linux/resume_user_mode.h> diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index a429c57ed433..58ecea1cdc27 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -1,10 +1,7 @@ -/* +/* SPDX-License-Identifier: GPL-2.0-or-later + * * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation * Extracted from signal_32.c and signal_64.c - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file README.legal in the main directory of - * this archive for more details. */ #ifndef _POWERPC_ARCH_SIGNAL_H diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5826f5108a12..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(DIE) }, - { NULL, }, -}; - static int __init init_big_cores(void) { int cpu; @@ -1595,7 +1598,7 @@ static void add_cpu_to_masks(int cpu) /* Skip all CPUs already part of current CPU core mask */ cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu)); - /* If chip_id is -1; limit the cpu_core_mask to within DIE*/ + /* If chip_id is -1; limit the cpu_core_mask to within PKG */ if (chip_id == -1) cpumask_and(mask, mask, cpu_cpu_mask(cpu)); @@ -1629,7 +1632,7 @@ void start_secondary(void *unused) smp_store_cpu_info(cpu); set_dec(tb_ticks_per_jiffy); - rcu_cpu_starting(cpu); + rcutree_report_cpu_starting(cpu); cpu_callin_map[cpu] = 1; if (smp_ops->setup_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/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index b15f15dcacb5..e6a958a5da27 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -73,29 +73,12 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum bool firstframe; stack_end = stack_page + THREAD_SIZE; - if (!is_idle_task(task)) { - /* - * For user tasks, this is the SP value loaded on - * kernel entry, see "PACAKSAVE(r13)" in _switch() and - * system_call_common(). - * - * Likewise for non-swapper kernel threads, - * this also happens to be the top of the stack - * as setup by copy_thread(). - * - * Note that stack backlinks are not properly setup by - * copy_thread() and thus, a forked task() will have - * an unreliable stack trace until it's been - * _switch()'ed to for the first time. - */ - stack_end -= STACK_USER_INT_FRAME_SIZE; - } else { - /* - * idle tasks have a custom stack layout, - * c.f. cpu_idle_thread_init(). - */ + + // See copy_thread() for details. + if (task->flags & PF_KTHREAD) stack_end -= STACK_FRAME_MIN_SIZE; - } + else + stack_end -= STACK_USER_INT_FRAME_SIZE; if (task == current) sp = current_stack_frame(); 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/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 20e50586e8a2..17173b82ca21 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -294,7 +294,7 @@ 233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 233 64 fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group -235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +235 nospu lookup_dcookie sys_ni_syscall 236 common epoll_create sys_epoll_create 237 common epoll_ctl sys_epoll_ctl 238 common epoll_wait sys_epoll_wait @@ -539,3 +539,12 @@ 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_ni_syscall +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S index 90701885762c..76dbe9fd2c0f 100644 --- a/arch/powerpc/kernel/trace/ftrace_entry.S +++ b/arch/powerpc/kernel/trace/ftrace_entry.S @@ -62,7 +62,7 @@ .endif /* Save previous stack pointer (r1) */ - addi r8, r1, SWITCH_FRAME_SIZE + addi r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE PPC_STL r8, GPR1(r1) .if \allregs == 1 @@ -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) @@ -182,7 +180,7 @@ ftrace_no_trace: mflr r3 mtctr r3 REST_GPR(3, r1) - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE mtlr r0 bctr #endif diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index eeff136b83d9..11e062b47d3f 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -157,7 +157,7 @@ static int die_owner = -1; static unsigned int die_nest_count; static int die_counter; -extern void panic_flush_kmsg_start(void) +void panic_flush_kmsg_start(void) { /* * These are mostly taken from kernel/panic.c, but tries to do @@ -170,7 +170,7 @@ extern void panic_flush_kmsg_start(void) bust_spinlocks(1); } -extern void panic_flush_kmsg_end(void) +void panic_flush_kmsg_end(void) { kmsg_dump(KMSG_DUMP_PANIC); bust_spinlocks(0); @@ -1164,6 +1164,7 @@ void emulate_single_step(struct pt_regs *regs) __single_step_exception(regs); } +#ifdef CONFIG_PPC_FPU_REGS static inline int __parse_fpscr(unsigned long fpscr) { int ret = FPE_FLTUNK; @@ -1190,6 +1191,7 @@ static inline int __parse_fpscr(unsigned long fpscr) return ret; } +#endif static void parse_fpe(struct pt_regs *regs) { @@ -1437,10 +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) @@ -1512,23 +1516,11 @@ static void do_program_check(struct pt_regs *regs) return; } - if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && user_mode(regs)) { - ppc_inst_t insn; - - if (get_user_instr(insn, (void __user *)regs->nip)) { - _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); - return; - } - - if (ppc_inst_primary_opcode(insn) == 31 && - get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) { - _exception(SIGILL, regs, ILL_ILLOPN, regs->nip); - return; - } + /* User mode considers other cases after enabling IRQs */ + if (!user_mode(regs)) { + _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); + return; } - - _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); - return; } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (reason & REASON_TM) { @@ -1561,16 +1553,44 @@ static void do_program_check(struct pt_regs *regs) /* * If we took the program check in the kernel skip down to sending a - * SIGILL. The subsequent cases all relate to emulating instructions - * which we should only do for userspace. We also do not want to enable - * interrupts for kernel faults because that might lead to further - * faults, and loose the context of the original exception. + * SIGILL. The subsequent cases all relate to user space, such as + * emulating instructions which we should only do for user space. We + * also do not want to enable interrupts for kernel faults because that + * might lead to further faults, and loose the context of the original + * exception. */ if (!user_mode(regs)) goto sigill; interrupt_cond_local_irq_enable(regs); + /* + * (reason & REASON_TRAP) is mostly handled before enabling IRQs, + * except get_user_instr() can sleep so we cannot reliably inspect the + * current instruction in that context. Now that we know we are + * handling a user space trap and can sleep, we can check if the trap + * was a hashchk failure. + */ + if (reason & REASON_TRAP) { + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) { + ppc_inst_t insn; + + if (get_user_instr(insn, (void __user *)regs->nip)) { + _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); + return; + } + + if (ppc_inst_primary_opcode(insn) == 31 && + get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) { + _exception(SIGILL, regs, ILL_ILLOPN, regs->nip); + return; + } + } + + _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); + return; + } + /* (reason & REASON_ILLEGAL) would be the obvious thing here, * but there seems to be a hardware bug on the 405GP (RevD) * that means ESR is sometimes set incorrectly - either to 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/kernel/vector.S b/arch/powerpc/kernel/vector.S index 4094e4c4c77a..80b3f6e476b6 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -33,6 +33,7 @@ _GLOBAL(store_vr_state) mfvscr v0 li r4, VRSTATE_VSCR stvx v0, r4, r3 + lvx v0, 0, r3 blr EXPORT_SYMBOL(store_vr_state) @@ -109,6 +110,7 @@ _GLOBAL(save_altivec) mfvscr v0 li r4,VRSTATE_VSCR stvx v0,r4,r7 + lvx v0,0,r7 blr #ifdef CONFIG_VSX diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index de64c7962991..27fa9098a5b7 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -74,6 +74,10 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_STRUCT_SIZE(mmu_psize_def); 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()); } @@ -109,7 +113,7 @@ void __init reserve_crashkernel(void) total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size(); /* use common parsing */ ret = parse_crashkernel(boot_command_line, total_mem_sz, - &crash_size, &crash_base); + &crash_size, &crash_base, NULL, NULL); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index a79e28c91e2b..762e4d09aacf 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -283,8 +283,7 @@ static void kexec_prepare_cpus(void) * We could use a smaller stack if we don't care about anything using * current, but that audit has not been performed. */ -static union thread_union kexec_stack __init_task_data = - { }; +static union thread_union kexec_stack = { }; /* * For similar reasons to the stack above, the kexecing CPU needs to be on a @@ -379,8 +378,8 @@ void default_machine_kexec(struct kimage *image) #ifdef CONFIG_PPC_64S_HASH_MMU /* Values we need to export to the second kernel via the device tree. */ -static unsigned long htab_base; -static unsigned long htab_size; +static __be64 htab_base; +static __be64 htab_size; static struct property htab_base_prop = { .name = "linux,htab-base", diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c index eeb258002d1e..904016cf89ea 100644 --- a/arch/powerpc/kexec/elf_64.c +++ b/arch/powerpc/kexec/elf_64.c @@ -59,7 +59,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, if (ret) goto out; - pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr); + kexec_dprintk("Loaded the kernel at 0x%lx\n", kernel_load_addr); ret = kexec_load_purgatory(image, &pbuf); if (ret) { @@ -67,7 +67,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, goto out; } - pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); + kexec_dprintk("Loaded purgatory at 0x%lx\n", pbuf.mem); /* Load additional segments needed for panic kernel */ if (image->type == KEXEC_TYPE_CRASH) { @@ -99,7 +99,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, goto out; initrd_load_addr = kbuf.mem; - pr_debug("Loaded initrd at 0x%lx\n", initrd_load_addr); + kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_load_addr); } fdt = of_kexec_alloc_and_setup_fdt(image, initrd_load_addr, @@ -132,7 +132,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, fdt_load_addr = kbuf.mem; - pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr); + kexec_dprintk("Loaded device tree at 0x%lx\n", fdt_load_addr); slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset; ret = setup_purgatory_ppc64(image, slave_code, fdt, kernel_load_addr, diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index a3de5369d22c..5b4c5cb23354 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -32,7 +32,7 @@ #include <asm/plpks.h> struct umem_info { - u64 *buf; /* data buffer for usable-memory property */ + __be64 *buf; /* data buffer for usable-memory property */ u32 size; /* size allocated for the data buffer */ u32 max_entries; /* maximum no. of entries */ u32 idx; /* index of current entry */ @@ -443,10 +443,10 @@ static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf, * * Returns buffer on success, NULL on error. */ -static u64 *check_realloc_usable_mem(struct umem_info *um_info, int cnt) +static __be64 *check_realloc_usable_mem(struct umem_info *um_info, int cnt) { u32 new_size; - u64 *tbuf; + __be64 *tbuf; if ((um_info->idx + cnt) <= um_info->max_entries) return um_info->buf; @@ -577,7 +577,7 @@ static int add_usable_mem_property(void *fdt, struct device_node *dn, NODE_PATH_LEN, dn); return -EOVERFLOW; } - pr_debug("Memory node path: %s\n", path); + kexec_dprintk("Memory node path: %s\n", path); /* Now that we know the path, find its offset in kdump kernel's fdt */ node = fdt_path_offset(fdt, path); @@ -590,8 +590,8 @@ static int add_usable_mem_property(void *fdt, struct device_node *dn, /* Get the address & size cells */ n_mem_addr_cells = of_n_addr_cells(dn); n_mem_size_cells = of_n_size_cells(dn); - pr_debug("address cells: %d, size cells: %d\n", n_mem_addr_cells, - n_mem_size_cells); + kexec_dprintk("address cells: %d, size cells: %d\n", n_mem_addr_cells, + n_mem_size_cells); um_info->idx = 0; if (!check_realloc_usable_mem(um_info, 2)) { @@ -664,7 +664,7 @@ static int update_usable_mem_fdt(void *fdt, struct crash_mem *usable_mem) node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory"); if (node == -FDT_ERR_NOTFOUND) - pr_debug("No dynamic reconfiguration memory found\n"); + kexec_dprintk("No dynamic reconfiguration memory found\n"); else if (node < 0) { pr_err("Malformed device tree: error reading /ibm,dynamic-reconfiguration-memory.\n"); return -EINVAL; @@ -776,8 +776,8 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) for (i = 0; i < ehdr->e_phnum; i++) { if (phdr->p_paddr == BACKUP_SRC_START) { phdr->p_offset = image->arch.backup_start; - pr_debug("Backup region offset updated to 0x%lx\n", - image->arch.backup_start); + kexec_dprintk("Backup region offset updated to 0x%lx\n", + image->arch.backup_start); return; } } @@ -850,7 +850,7 @@ int load_crashdump_segments_ppc64(struct kimage *image, pr_err("Failed to load backup segment\n"); return ret; } - pr_debug("Loaded the backup region at 0x%lx\n", kbuf->mem); + kexec_dprintk("Loaded the backup region at 0x%lx\n", kbuf->mem); /* Load elfcorehdr segment - to export crashing kernel's vmcore */ ret = load_elfcorehdr_segment(image, kbuf); @@ -858,8 +858,8 @@ int load_crashdump_segments_ppc64(struct kimage *image, pr_err("Failed to load elfcorehdr segment\n"); return ret; } - pr_debug("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n", - image->elf_load_addr, kbuf->bufsz, kbuf->memsz); + kexec_dprintk("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf->bufsz, kbuf->memsz); return 0; } @@ -1138,11 +1138,15 @@ static int update_pci_dma_nodes(void *fdt, const char *dmapropname) continue; ret = copy_property(fdt, pci_offset, dn, "ibm,dma-window"); - if (ret < 0) + if (ret < 0) { + of_node_put(dn); break; + } ret = copy_property(fdt, pci_offset, dn, dmapropname); - if (ret < 0) + if (ret < 0) { + of_node_put(dn); break; + } } return ret; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 902611954200..074263429faf 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -19,13 +19,11 @@ if VIRTUALIZATION config KVM bool - select PREEMPT_NOTIFIERS - select HAVE_KVM_EVENTFD + select KVM_COMMON select HAVE_KVM_VCPU_ASYNC_IOCTL select KVM_VFIO select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS - select INTERVAL_TREE config KVM_BOOK3S_HANDLER bool @@ -42,7 +40,7 @@ config KVM_BOOK3S_64_HANDLER config KVM_BOOK3S_PR_POSSIBLE bool select KVM_MMIO - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER config KVM_BOOK3S_HV_POSSIBLE bool @@ -85,7 +83,7 @@ config KVM_BOOK3S_64_HV tristate "KVM for POWER7 and later using hypervisor mode in host" depends on KVM_BOOK3S_64 && PPC_POWERNV select KVM_BOOK3S_HV_POSSIBLE - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER select CMA help Support running unmodified book3s_64 guest kernels in @@ -194,7 +192,7 @@ config KVM_E500V2 depends on !CONTEXT_TRACKING_USER select KVM select KVM_MMIO - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500 guest kernels in virtual machines on E500v2 host processors. @@ -211,7 +209,7 @@ config KVM_E500MC select KVM select KVM_MMIO select KVM_BOOKE_HV - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500MC/E5500/E6500 guest kernels in virtual machines on E500MC/E5500/E6500 host processors. @@ -225,7 +223,6 @@ config KVM_MPIC bool "KVM in-kernel MPIC emulation" depends on KVM && PPC_E500 select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_MSI help @@ -238,7 +235,6 @@ config KVM_XICS bool "KVM in-kernel XICS emulation" depends on KVM_BOOK3S_64 && !KVM_MPIC select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQFD default y help Include support for the XICS (eXternal Interrupt Controller diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 5319d889b184..4bd9d1230869 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -87,8 +87,12 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_hv_ras.o \ book3s_hv_builtin.o \ book3s_hv_p9_perf.o \ + book3s_hv_nestedv2.o \ + guest-state-buffer.o \ $(kvm-book3s_64-builtin-tm-objs-y) \ $(kvm-book3s_64-builtin-xics-objs-y) + +obj-$(CONFIG_GUEST_STATE_BUFFER_TEST) += test-guest-state-buffer.o endif kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 686d8d9eda3e..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: @@ -565,7 +565,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) regs->msr = kvmppc_get_msr(vcpu); regs->srr0 = kvmppc_get_srr0(vcpu); regs->srr1 = kvmppc_get_srr1(vcpu); - regs->pid = vcpu->arch.pid; + regs->pid = kvmppc_get_pid(vcpu); regs->sprg0 = kvmppc_get_sprg0(vcpu); regs->sprg1 = kvmppc_get_sprg1(vcpu); regs->sprg2 = kvmppc_get_sprg2(vcpu); @@ -636,17 +636,17 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, break; case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: i = id - KVM_REG_PPC_FPR0; - *val = get_reg_val(id, VCPU_FPR(vcpu, i)); + *val = get_reg_val(id, kvmppc_get_fpr(vcpu, i)); break; case KVM_REG_PPC_FPSCR: - *val = get_reg_val(id, vcpu->arch.fp.fpscr); + *val = get_reg_val(id, kvmppc_get_fpscr(vcpu)); break; #ifdef CONFIG_VSX case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: if (cpu_has_feature(CPU_FTR_VSX)) { i = id - KVM_REG_PPC_VSR0; - val->vsxval[0] = vcpu->arch.fp.fpr[i][0]; - val->vsxval[1] = vcpu->arch.fp.fpr[i][1]; + val->vsxval[0] = kvmppc_get_vsx_fpr(vcpu, i, 0); + val->vsxval[1] = kvmppc_get_vsx_fpr(vcpu, i, 1); } else { r = -ENXIO; } @@ -683,19 +683,19 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.fscr); break; case KVM_REG_PPC_TAR: - *val = get_reg_val(id, vcpu->arch.tar); + *val = get_reg_val(id, kvmppc_get_tar(vcpu)); break; case KVM_REG_PPC_EBBHR: - *val = get_reg_val(id, vcpu->arch.ebbhr); + *val = get_reg_val(id, kvmppc_get_ebbhr(vcpu)); break; case KVM_REG_PPC_EBBRR: - *val = get_reg_val(id, vcpu->arch.ebbrr); + *val = get_reg_val(id, kvmppc_get_ebbrr(vcpu)); break; case KVM_REG_PPC_BESCR: - *val = get_reg_val(id, vcpu->arch.bescr); + *val = get_reg_val(id, kvmppc_get_bescr(vcpu)); break; case KVM_REG_PPC_IC: - *val = get_reg_val(id, vcpu->arch.ic); + *val = get_reg_val(id, kvmppc_get_ic(vcpu)); break; default: r = -EINVAL; @@ -724,7 +724,7 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, break; case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: i = id - KVM_REG_PPC_FPR0; - VCPU_FPR(vcpu, i) = set_reg_val(id, *val); + kvmppc_set_fpr(vcpu, i, set_reg_val(id, *val)); break; case KVM_REG_PPC_FPSCR: vcpu->arch.fp.fpscr = set_reg_val(id, *val); @@ -733,8 +733,8 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: if (cpu_has_feature(CPU_FTR_VSX)) { i = id - KVM_REG_PPC_VSR0; - vcpu->arch.fp.fpr[i][0] = val->vsxval[0]; - vcpu->arch.fp.fpr[i][1] = val->vsxval[1]; + kvmppc_set_vsx_fpr(vcpu, i, 0, val->vsxval[0]); + kvmppc_set_vsx_fpr(vcpu, i, 1, val->vsxval[1]); } else { r = -ENXIO; } @@ -765,22 +765,22 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, break; #endif /* CONFIG_KVM_XIVE */ case KVM_REG_PPC_FSCR: - vcpu->arch.fscr = set_reg_val(id, *val); + kvmppc_set_fpscr(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_TAR: - vcpu->arch.tar = set_reg_val(id, *val); + kvmppc_set_tar(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_EBBHR: - vcpu->arch.ebbhr = set_reg_val(id, *val); + kvmppc_set_ebbhr(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_EBBRR: - vcpu->arch.ebbrr = set_reg_val(id, *val); + kvmppc_set_ebbrr(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_BESCR: - vcpu->arch.bescr = set_reg_val(id, *val); + kvmppc_set_bescr(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_IC: - vcpu->arch.ic = set_reg_val(id, *val); + kvmppc_set_ic(vcpu, set_reg_val(id, *val)); break; default: r = -EINVAL; diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 3b361af87313..a9ab92abffe8 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -19,7 +19,7 @@ /* * This is a hcall, so register convention is as - * Documentation/powerpc/papr_hcalls.rst. + * Documentation/arch/powerpc/papr_hcalls.rst. * * This may also be a syscall from PR-KVM userspace that is to be * reflected to the PR guest kernel, so registers may be set up for diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index efd0ebf70a5e..2b1f0cdd8c18 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -28,6 +28,7 @@ #include <asm/pte-walk.h> #include "book3s.h" +#include "book3s_hv.h" #include "trace_hv.h" //#define DEBUG_RESIZE_HPT 1 @@ -120,7 +121,7 @@ void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info) kvm->arch.hpt = *info; kvm->arch.sdr1 = __pa(info->virt) | (info->order - 18); - pr_debug("KVM guest htab at %lx (order %ld), LPID %x\n", + pr_debug("KVM guest htab at %lx (order %ld), LPID %llx\n", info->virt, (long)info->order, kvm->arch.lpid); } @@ -347,7 +348,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long v, orig_v, gr; __be64 *hptep; long int index; - int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); + int virtmode = __kvmppc_get_msr_hv(vcpu) & (data ? MSR_DR : MSR_IR); if (kvm_is_radix(vcpu->kvm)) return kvmppc_mmu_radix_xlate(vcpu, eaddr, gpte, data, iswrite); @@ -385,7 +386,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, /* Get PP bits and key for permission check */ pp = gr & (HPTE_R_PP0 | HPTE_R_PP); - key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS; + key = (__kvmppc_get_msr_hv(vcpu) & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS; key &= slb_v; /* Calculate permissions */ diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 572707858d65..4a1abb9f7c05 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -15,6 +15,7 @@ #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> +#include "book3s_hv.h" #include <asm/page.h> #include <asm/mmu.h> #include <asm/pgalloc.h> @@ -39,6 +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, @@ -96,7 +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 = vcpu->arch.pid; + int pid; /* This would cause a data segment intr so don't allow the access */ if (eaddr & (0x3FFUL << 52)) @@ -109,6 +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); @@ -270,7 +276,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, /* Work out effective PID */ switch (eaddr >> 62) { case 0: - pid = vcpu->arch.pid; + pid = kvmppc_get_pid(vcpu); break; case 3: pid = 0; @@ -294,9 +300,9 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, } else { if (!(pte & _PAGE_PRIVILEGED)) { /* Check AMR/IAMR to see if strict mode is in force */ - if (vcpu->arch.amr & (1ul << 62)) + if (kvmppc_get_amr_hv(vcpu) & (1ul << 62)) gpte->may_read = 0; - if (vcpu->arch.amr & (1ul << 63)) + if (kvmppc_get_amr_hv(vcpu) & (1ul << 63)) gpte->may_write = 0; if (vcpu->arch.iamr & (1ul << 62)) gpte->may_execute = 0; @@ -307,7 +313,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, } void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, - unsigned int pshift, unsigned int lpid) + unsigned int pshift, u64 lpid) { unsigned long psize = PAGE_SIZE; int psi; @@ -344,7 +350,7 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc); } -static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid) +static void kvmppc_radix_flush_pwc(struct kvm *kvm, u64 lpid) { long rc; @@ -417,7 +423,7 @@ static void kvmppc_pmd_free(pmd_t *pmdp) void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa, unsigned int shift, const struct kvm_memory_slot *memslot, - unsigned int lpid) + u64 lpid) { unsigned long old; @@ -468,7 +474,7 @@ void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa, * (or 4kB) mappings (of sub-pages of the same 2MB page). */ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full, - unsigned int lpid) + u64 lpid) { if (full) { memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE); @@ -489,7 +495,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full, } static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full, - unsigned int lpid) + u64 lpid) { unsigned long im; pmd_t *p = pmd; @@ -518,7 +524,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full, } static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud, - unsigned int lpid) + u64 lpid) { unsigned long iu; pud_t *p = pud; @@ -539,7 +545,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud, pud_free(kvm->mm, pud); } -void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid) +void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, u64 lpid) { unsigned long ig; @@ -566,7 +572,7 @@ void kvmppc_free_radix(struct kvm *kvm) } static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd, - unsigned long gpa, unsigned int lpid) + unsigned long gpa, u64 lpid) { pte_t *pte = pte_offset_kernel(pmd, 0); @@ -582,7 +588,7 @@ static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd, } static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud, - unsigned long gpa, unsigned int lpid) + unsigned long gpa, u64 lpid) { pmd_t *pmd = pmd_offset(pud, 0); @@ -608,7 +614,7 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud, int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte, unsigned long gpa, unsigned int level, - unsigned long mmu_seq, unsigned int lpid, + unsigned long mmu_seq, u64 lpid, unsigned long *rmapp, struct rmap_nested **n_rmap) { pgd_t *pgd; @@ -785,7 +791,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte, } bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing, - unsigned long gpa, unsigned int lpid) + unsigned long gpa, u64 lpid) { unsigned long pgflags; unsigned int shift; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 93b695b289e9..b569ebaa590e 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -20,6 +20,7 @@ #include <linux/iommu.h> #include <linux/file.h> #include <linux/mm.h> +#include <linux/rcupdate_wait.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> @@ -77,8 +78,8 @@ static void kvm_spapr_tce_liobn_put(struct kref *kref) call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free); } -extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, - struct iommu_group *grp) +void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, + struct iommu_group *grp) { int i; struct kvmppc_spapr_tce_table *stt; @@ -105,8 +106,8 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, rcu_read_unlock(); } -extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, - struct iommu_group *grp) +long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, + struct iommu_group *grp) { struct kvmppc_spapr_tce_table *stt = NULL; bool found = false; @@ -786,12 +787,12 @@ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, idx = (ioba >> stt->page_shift) - stt->offset; page = stt->pages[idx / TCES_PER_PAGE]; if (!page) { - vcpu->arch.regs.gpr[4] = 0; + kvmppc_set_gpr(vcpu, 4, 0); return H_SUCCESS; } tbl = (u64 *)page_address(page); - vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE]; + kvmppc_set_gpr(vcpu, 4, tbl[idx % TCES_PER_PAGE]); return H_SUCCESS; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 130bafdb1430..52427fc2a33f 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -393,7 +393,7 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) { - unsigned long host_pcr_bit = 0, guest_pcr_bit = 0; + unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0; struct kvmppc_vcore *vc = vcpu->arch.vcore; /* We can (emulate) our own architecture version and anything older */ @@ -424,9 +424,11 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) break; case PVR_ARCH_300: guest_pcr_bit = PCR_ARCH_300; + cap = H_GUEST_CAP_POWER9; break; case PVR_ARCH_31: guest_pcr_bit = PCR_ARCH_31; + cap = H_GUEST_CAP_POWER10; break; default: return -EINVAL; @@ -437,8 +439,14 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) if (guest_pcr_bit > host_pcr_bit) return -EINVAL; + if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) { + if (!(cap & nested_capabilities)) + return -EINVAL; + } + spin_lock(&vc->lock); vc->arch_compat = arch_compat; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LOGICAL_PVR); /* * Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit * Also set all reserved PCR bits @@ -642,7 +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; @@ -682,9 +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; @@ -694,6 +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)) @@ -701,17 +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); } @@ -794,7 +822,7 @@ static void kvmppc_update_vpa_dispatch(struct kvm_vcpu *vcpu, vpa->enqueue_dispatch_tb = cpu_to_be64(be64_to_cpu(vpa->enqueue_dispatch_tb) + stolen); - __kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now + vc->tb_offset, stolen); + __kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now + kvmppc_get_tb_offset(vcpu), stolen); vcpu->arch.vpa.dirty = true; } @@ -845,9 +873,9 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu) { - if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207) + if (kvmppc_get_arch_compat(vcpu) >= PVR_ARCH_207) return true; - if ((!vcpu->arch.vcore->arch_compat) && + if ((!kvmppc_get_arch_compat(vcpu)) && cpu_has_feature(CPU_FTR_ARCH_207S)) return true; return false; @@ -868,7 +896,7 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, /* Guests can't breakpoint the hypervisor */ if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER) return H_P3; - vcpu->arch.ciabr = value1; + kvmppc_set_ciabr_hv(vcpu, value1); return H_SUCCESS; case H_SET_MODE_RESOURCE_SET_DAWR0: if (!kvmppc_power8_compatible(vcpu)) @@ -879,8 +907,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, return H_UNSUPPORTED_FLAG_START; if (value2 & DABRX_HYP) return H_P4; - vcpu->arch.dawr0 = value1; - vcpu->arch.dawrx0 = value2; + kvmppc_set_dawr0_hv(vcpu, value1); + kvmppc_set_dawrx0_hv(vcpu, value2); return H_SUCCESS; case H_SET_MODE_RESOURCE_SET_DAWR1: if (!kvmppc_power8_compatible(vcpu)) @@ -895,8 +923,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, return H_UNSUPPORTED_FLAG_START; if (value2 & DABRX_HYP) return H_P4; - vcpu->arch.dawr1 = value1; - vcpu->arch.dawrx1 = value2; + kvmppc_set_dawr1_hv(vcpu, value1); + kvmppc_set_dawrx1_hv(vcpu, value2); return H_SUCCESS; case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE: /* @@ -1267,10 +1295,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) return RESUME_HOST; break; #endif - case H_RANDOM: - if (!arch_get_random_seed_longs(&vcpu->arch.regs.gpr[4], 1)) + case H_RANDOM: { + unsigned long rand; + + if (!arch_get_random_seed_longs(&rand, 1)) ret = H_HARDWARE; + kvmppc_set_gpr(vcpu, 4, rand); break; + } case H_RPT_INVALIDATE: ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5), @@ -1370,7 +1402,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) */ static void kvmppc_cede(struct kvm_vcpu *vcpu) { - vcpu->arch.shregs.msr |= MSR_EE; + __kvmppc_set_msr_hv(vcpu, __kvmppc_get_msr_hv(vcpu) | MSR_EE); vcpu->arch.ceded = 1; smp_mb(); if (vcpu->arch.prodded) { @@ -1544,7 +1576,7 @@ static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu) if (!(vcpu->arch.hfscr_permitted & HFSCR_PM)) return EMULATE_FAIL; - vcpu->arch.hfscr |= HFSCR_PM; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PM); return RESUME_GUEST; } @@ -1554,7 +1586,7 @@ static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu) if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB)) return EMULATE_FAIL; - vcpu->arch.hfscr |= HFSCR_EBB; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_EBB); return RESUME_GUEST; } @@ -1564,7 +1596,7 @@ static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu) if (!(vcpu->arch.hfscr_permitted & HFSCR_TM)) return EMULATE_FAIL; - vcpu->arch.hfscr |= HFSCR_TM; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM); return RESUME_GUEST; } @@ -1585,7 +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 (vcpu->arch.shregs.msr & 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), @@ -1636,7 +1668,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * so that it knows that the machine check occurred. */ if (!vcpu->kvm->arch.fwnmi_enabled) { - ulong flags = (vcpu->arch.shregs.msr & 0x083c0000) | + ulong flags = (__kvmppc_get_msr_hv(vcpu) & 0x083c0000) | (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_machine_check(vcpu, flags); r = RESUME_GUEST; @@ -1666,7 +1698,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * as a result of a hypervisor emulation interrupt * (e40) getting turned into a 700 by BML RTAS. */ - flags = (vcpu->arch.shregs.msr & 0x1f0000ull) | + flags = (__kvmppc_get_msr_hv(vcpu) & 0x1f0000ull) | (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; @@ -1676,7 +1708,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, { int i; - if (unlikely(vcpu->arch.shregs.msr & 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 @@ -1754,7 +1786,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, break; } - if (!(vcpu->arch.shregs.msr & MSR_DR)) + if (!(__kvmppc_get_msr_hv(vcpu) & MSR_DR)) vsid = vcpu->kvm->arch.vrma_slb_v; else vsid = vcpu->arch.fault_gpa; @@ -1778,7 +1810,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, long err; vcpu->arch.fault_dar = kvmppc_get_pc(vcpu); - vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr & + vcpu->arch.fault_dsisr = __kvmppc_get_msr_hv(vcpu) & DSISR_SRR1_MATCH_64S; if (kvm_is_radix(vcpu->kvm) || !cpu_has_feature(CPU_FTR_ARCH_300)) { /* @@ -1787,7 +1819,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * hash fault handling below is v3 only (it uses ASDR * via fault_gpa). */ - if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) + if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE) vcpu->arch.fault_dsisr |= DSISR_ISSTORE; r = RESUME_PAGE_FAULT; break; @@ -1801,7 +1833,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, break; } - if (!(vcpu->arch.shregs.msr & MSR_IR)) + if (!(__kvmppc_get_msr_hv(vcpu) & MSR_IR)) vsid = vcpu->kvm->arch.vrma_slb_v; else vsid = vcpu->arch.fault_gpa; @@ -1863,7 +1895,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * Otherwise, we just generate a program interrupt to the guest. */ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: { - u64 cause = vcpu->arch.hfscr >> 56; + u64 cause = kvmppc_get_hfscr_hv(vcpu) >> 56; r = EMULATE_FAIL; if (cpu_has_feature(CPU_FTR_ARCH_300)) { @@ -1891,7 +1923,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, kvmppc_dump_regs(vcpu); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), - vcpu->arch.shregs.msr); + __kvmppc_get_msr_hv(vcpu)); run->hw.hardware_exit_reason = vcpu->arch.trap; r = RESUME_HOST; break; @@ -1915,11 +1947,11 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) * That can happen due to a bug, or due to a machine check * occurring at just the wrong time. */ - if (vcpu->arch.shregs.msr & MSR_HV) { + if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) { pr_emerg("KVM trap in HV mode while nested!\n"); pr_emerg("trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), - vcpu->arch.shregs.msr); + __kvmppc_get_msr_hv(vcpu)); kvmppc_dump_regs(vcpu); return RESUME_HOST; } @@ -1976,7 +2008,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) vcpu->arch.fault_dar = kvmppc_get_pc(vcpu); vcpu->arch.fault_dsisr = kvmppc_get_msr(vcpu) & DSISR_SRR1_MATCH_64S; - if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) + if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE) vcpu->arch.fault_dsisr |= DSISR_ISSTORE; srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmhv_nested_page_fault(vcpu); @@ -2183,6 +2215,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, } vc->lpcr = new_lpcr; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LPCR); spin_unlock(&vc->lock); } @@ -2207,64 +2240,64 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.dabrx); break; case KVM_REG_PPC_DSCR: - *val = get_reg_val(id, vcpu->arch.dscr); + *val = get_reg_val(id, kvmppc_get_dscr_hv(vcpu)); break; case KVM_REG_PPC_PURR: - *val = get_reg_val(id, vcpu->arch.purr); + *val = get_reg_val(id, kvmppc_get_purr_hv(vcpu)); break; case KVM_REG_PPC_SPURR: - *val = get_reg_val(id, vcpu->arch.spurr); + *val = get_reg_val(id, kvmppc_get_spurr_hv(vcpu)); break; case KVM_REG_PPC_AMR: - *val = get_reg_val(id, vcpu->arch.amr); + *val = get_reg_val(id, kvmppc_get_amr_hv(vcpu)); break; case KVM_REG_PPC_UAMOR: - *val = get_reg_val(id, vcpu->arch.uamor); + *val = get_reg_val(id, kvmppc_get_uamor_hv(vcpu)); break; case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; - *val = get_reg_val(id, vcpu->arch.mmcr[i]); + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, i)); break; case KVM_REG_PPC_MMCR2: - *val = get_reg_val(id, vcpu->arch.mmcr[2]); + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 2)); break; case KVM_REG_PPC_MMCRA: - *val = get_reg_val(id, vcpu->arch.mmcra); + *val = get_reg_val(id, kvmppc_get_mmcra_hv(vcpu)); break; case KVM_REG_PPC_MMCRS: *val = get_reg_val(id, vcpu->arch.mmcrs); break; case KVM_REG_PPC_MMCR3: - *val = get_reg_val(id, vcpu->arch.mmcr[3]); + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 3)); break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; - *val = get_reg_val(id, vcpu->arch.pmc[i]); + *val = get_reg_val(id, kvmppc_get_pmc_hv(vcpu, i)); break; case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: i = id - KVM_REG_PPC_SPMC1; *val = get_reg_val(id, vcpu->arch.spmc[i]); break; case KVM_REG_PPC_SIAR: - *val = get_reg_val(id, vcpu->arch.siar); + *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu)); break; case KVM_REG_PPC_SDAR: - *val = get_reg_val(id, vcpu->arch.sdar); + *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu)); break; case KVM_REG_PPC_SIER: - *val = get_reg_val(id, vcpu->arch.sier[0]); + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 0)); break; case KVM_REG_PPC_SIER2: - *val = get_reg_val(id, vcpu->arch.sier[1]); + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 1)); break; case KVM_REG_PPC_SIER3: - *val = get_reg_val(id, vcpu->arch.sier[2]); + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 2)); break; case KVM_REG_PPC_IAMR: - *val = get_reg_val(id, vcpu->arch.iamr); + *val = get_reg_val(id, kvmppc_get_iamr_hv(vcpu)); break; case KVM_REG_PPC_PSPB: - *val = get_reg_val(id, vcpu->arch.pspb); + *val = get_reg_val(id, kvmppc_get_pspb_hv(vcpu)); break; case KVM_REG_PPC_DPDES: /* @@ -2279,22 +2312,22 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.vcore->dpdes); break; case KVM_REG_PPC_VTB: - *val = get_reg_val(id, vcpu->arch.vcore->vtb); + *val = get_reg_val(id, kvmppc_get_vtb(vcpu)); break; case KVM_REG_PPC_DAWR: - *val = get_reg_val(id, vcpu->arch.dawr0); + *val = get_reg_val(id, kvmppc_get_dawr0_hv(vcpu)); break; case KVM_REG_PPC_DAWRX: - *val = get_reg_val(id, vcpu->arch.dawrx0); + *val = get_reg_val(id, kvmppc_get_dawrx0_hv(vcpu)); break; case KVM_REG_PPC_DAWR1: - *val = get_reg_val(id, vcpu->arch.dawr1); + *val = get_reg_val(id, kvmppc_get_dawr1_hv(vcpu)); break; case KVM_REG_PPC_DAWRX1: - *val = get_reg_val(id, vcpu->arch.dawrx1); + *val = get_reg_val(id, kvmppc_get_dawrx1_hv(vcpu)); break; case KVM_REG_PPC_CIABR: - *val = get_reg_val(id, vcpu->arch.ciabr); + *val = get_reg_val(id, kvmppc_get_ciabr_hv(vcpu)); break; case KVM_REG_PPC_CSIGR: *val = get_reg_val(id, vcpu->arch.csigr); @@ -2306,13 +2339,13 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.tcscr); break; case KVM_REG_PPC_PID: - *val = get_reg_val(id, vcpu->arch.pid); + *val = get_reg_val(id, kvmppc_get_pid(vcpu)); break; case KVM_REG_PPC_ACOP: *val = get_reg_val(id, vcpu->arch.acop); break; case KVM_REG_PPC_WORT: - *val = get_reg_val(id, vcpu->arch.wort); + *val = get_reg_val(id, kvmppc_get_wort_hv(vcpu)); break; case KVM_REG_PPC_TIDR: *val = get_reg_val(id, vcpu->arch.tid); @@ -2338,14 +2371,14 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, spin_unlock(&vcpu->arch.vpa_update_lock); break; case KVM_REG_PPC_TB_OFFSET: - *val = get_reg_val(id, vcpu->arch.vcore->tb_offset); + *val = get_reg_val(id, kvmppc_get_tb_offset(vcpu)); break; case KVM_REG_PPC_LPCR: case KVM_REG_PPC_LPCR_64: - *val = get_reg_val(id, vcpu->arch.vcore->lpcr); + *val = get_reg_val(id, kvmppc_get_lpcr(vcpu)); break; case KVM_REG_PPC_PPR: - *val = get_reg_val(id, vcpu->arch.ppr); + *val = get_reg_val(id, kvmppc_get_ppr_hv(vcpu)); break; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM case KVM_REG_PPC_TFHAR: @@ -2414,10 +2447,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, break; #endif case KVM_REG_PPC_ARCH_COMPAT: - *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); + *val = get_reg_val(id, kvmppc_get_arch_compat(vcpu)); break; case KVM_REG_PPC_DEC_EXPIRY: - *val = get_reg_val(id, vcpu->arch.dec_expires); + *val = get_reg_val(id, kvmppc_get_dec_expires(vcpu)); break; case KVM_REG_PPC_ONLINE: *val = get_reg_val(id, vcpu->arch.online); @@ -2425,6 +2458,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_PTCR: *val = get_reg_val(id, vcpu->kvm->arch.l1_ptcr); break; + case KVM_REG_PPC_FSCR: + *val = get_reg_val(id, kvmppc_get_fscr_hv(vcpu)); + break; default: r = -EINVAL; break; @@ -2453,29 +2489,29 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP; break; case KVM_REG_PPC_DSCR: - vcpu->arch.dscr = set_reg_val(id, *val); + kvmppc_set_dscr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_PURR: - vcpu->arch.purr = set_reg_val(id, *val); + kvmppc_set_purr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SPURR: - vcpu->arch.spurr = set_reg_val(id, *val); + kvmppc_set_spurr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_AMR: - vcpu->arch.amr = set_reg_val(id, *val); + kvmppc_set_amr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_UAMOR: - vcpu->arch.uamor = set_reg_val(id, *val); + kvmppc_set_uamor_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; - vcpu->arch.mmcr[i] = set_reg_val(id, *val); + kvmppc_set_mmcr_hv(vcpu, i, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCR2: - vcpu->arch.mmcr[2] = set_reg_val(id, *val); + kvmppc_set_mmcr_hv(vcpu, 2, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCRA: - vcpu->arch.mmcra = set_reg_val(id, *val); + kvmppc_set_mmcra_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCRS: vcpu->arch.mmcrs = set_reg_val(id, *val); @@ -2485,32 +2521,32 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; - vcpu->arch.pmc[i] = set_reg_val(id, *val); + kvmppc_set_pmc_hv(vcpu, i, set_reg_val(id, *val)); break; case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: i = id - KVM_REG_PPC_SPMC1; vcpu->arch.spmc[i] = set_reg_val(id, *val); break; case KVM_REG_PPC_SIAR: - vcpu->arch.siar = set_reg_val(id, *val); + kvmppc_set_siar_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SDAR: - vcpu->arch.sdar = set_reg_val(id, *val); + kvmppc_set_sdar_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SIER: - vcpu->arch.sier[0] = set_reg_val(id, *val); + kvmppc_set_sier_hv(vcpu, 0, set_reg_val(id, *val)); break; case KVM_REG_PPC_SIER2: - vcpu->arch.sier[1] = set_reg_val(id, *val); + kvmppc_set_sier_hv(vcpu, 1, set_reg_val(id, *val)); break; case KVM_REG_PPC_SIER3: - vcpu->arch.sier[2] = set_reg_val(id, *val); + kvmppc_set_sier_hv(vcpu, 2, set_reg_val(id, *val)); break; case KVM_REG_PPC_IAMR: - vcpu->arch.iamr = set_reg_val(id, *val); + kvmppc_set_iamr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_PSPB: - vcpu->arch.pspb = set_reg_val(id, *val); + kvmppc_set_pspb_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DPDES: if (cpu_has_feature(CPU_FTR_ARCH_300)) @@ -2519,25 +2555,25 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.vcore->dpdes = set_reg_val(id, *val); break; case KVM_REG_PPC_VTB: - vcpu->arch.vcore->vtb = set_reg_val(id, *val); + kvmppc_set_vtb(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DAWR: - vcpu->arch.dawr0 = set_reg_val(id, *val); + kvmppc_set_dawr0_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DAWRX: - vcpu->arch.dawrx0 = set_reg_val(id, *val) & ~DAWRX_HYP; + kvmppc_set_dawrx0_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP); break; case KVM_REG_PPC_DAWR1: - vcpu->arch.dawr1 = set_reg_val(id, *val); + kvmppc_set_dawr1_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DAWRX1: - vcpu->arch.dawrx1 = set_reg_val(id, *val) & ~DAWRX_HYP; + kvmppc_set_dawrx1_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP); break; case KVM_REG_PPC_CIABR: - vcpu->arch.ciabr = set_reg_val(id, *val); + kvmppc_set_ciabr_hv(vcpu, set_reg_val(id, *val)); /* Don't allow setting breakpoints in hypervisor code */ - if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER) - vcpu->arch.ciabr &= ~CIABR_PRIV; /* disable */ + if ((kvmppc_get_ciabr_hv(vcpu) & CIABR_PRIV) == CIABR_PRIV_HYPER) + kvmppc_set_ciabr_hv(vcpu, kvmppc_get_ciabr_hv(vcpu) & ~CIABR_PRIV); break; case KVM_REG_PPC_CSIGR: vcpu->arch.csigr = set_reg_val(id, *val); @@ -2549,13 +2585,13 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.tcscr = set_reg_val(id, *val); break; case KVM_REG_PPC_PID: - vcpu->arch.pid = set_reg_val(id, *val); + kvmppc_set_pid(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_ACOP: vcpu->arch.acop = set_reg_val(id, *val); break; case KVM_REG_PPC_WORT: - vcpu->arch.wort = set_reg_val(id, *val); + kvmppc_set_wort_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_TIDR: vcpu->arch.tid = set_reg_val(id, *val); @@ -2602,10 +2638,11 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, * decrementer, which is better than a large one that * causes a hang. */ - if (!vcpu->arch.dec_expires && tb_offset) - vcpu->arch.dec_expires = get_tb() + tb_offset; + kvmppc_set_tb_offset(vcpu, tb_offset); + if (!kvmppc_get_dec_expires(vcpu) && tb_offset) + kvmppc_set_dec_expires(vcpu, get_tb() + tb_offset); - vcpu->arch.vcore->tb_offset = tb_offset; + kvmppc_set_tb_offset(vcpu, tb_offset); break; } case KVM_REG_PPC_LPCR: @@ -2615,7 +2652,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false); break; case KVM_REG_PPC_PPR: - vcpu->arch.ppr = set_reg_val(id, *val); + kvmppc_set_ppr_hv(vcpu, set_reg_val(id, *val)); break; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM case KVM_REG_PPC_TFHAR: @@ -2686,7 +2723,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DEC_EXPIRY: - vcpu->arch.dec_expires = set_reg_val(id, *val); + kvmppc_set_dec_expires(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_ONLINE: i = set_reg_val(id, *val); @@ -2699,6 +2736,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_PTCR: vcpu->kvm->arch.l1_ptcr = set_reg_val(id, *val); break; + case KVM_REG_PPC_FSCR: + kvmppc_set_fscr_hv(vcpu, set_reg_val(id, *val)); + break; default: r = -EINVAL; break; @@ -2916,19 +2956,26 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) vcpu->arch.shared_big_endian = false; #endif #endif - vcpu->arch.mmcr[0] = MMCR0_FC; + + if (kvmhv_is_nestedv2()) { + err = kvmhv_nestedv2_vcpu_create(vcpu, &vcpu->arch.nestedv2_io); + if (err < 0) + return err; + } + + kvmppc_set_mmcr_hv(vcpu, 0, MMCR0_FC); if (cpu_has_feature(CPU_FTR_ARCH_31)) { - vcpu->arch.mmcr[0] |= MMCR0_PMCCEXT; - vcpu->arch.mmcra = MMCRA_BHRB_DISABLE; + kvmppc_set_mmcr_hv(vcpu, 0, kvmppc_get_mmcr_hv(vcpu, 0) | MMCR0_PMCCEXT); + kvmppc_set_mmcra_hv(vcpu, MMCRA_BHRB_DISABLE); } - vcpu->arch.ctrl = CTRL_RUNLATCH; + kvmppc_set_ctrl_hv(vcpu, CTRL_RUNLATCH); /* default to host PVR, since we can't spoof it */ kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR)); spin_lock_init(&vcpu->arch.vpa_update_lock); spin_lock_init(&vcpu->arch.tbacct_lock); vcpu->arch.busy_preempt = TB_NIL; - vcpu->arch.shregs.msr = MSR_ME; + __kvmppc_set_msr_hv(vcpu, MSR_ME); vcpu->arch.intr_msr = MSR_SF | MSR_ME; /* @@ -2938,29 +2985,30 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) * don't set the HFSCR_MSGP bit, and that causes those instructions * to trap and then we emulate them. */ - vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | - HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP; + kvmppc_set_hfscr_hv(vcpu, HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | + HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP); /* On POWER10 and later, allow prefixed instructions */ if (cpu_has_feature(CPU_FTR_ARCH_31)) - vcpu->arch.hfscr |= HFSCR_PREFIX; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PREFIX); if (cpu_has_feature(CPU_FTR_HVMODE)) { - vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & mfspr(SPRN_HFSCR)); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - vcpu->arch.hfscr |= HFSCR_TM; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM); #endif } if (cpu_has_feature(CPU_FTR_TM_COMP)) vcpu->arch.hfscr |= HFSCR_TM; - vcpu->arch.hfscr_permitted = vcpu->arch.hfscr; + vcpu->arch.hfscr_permitted = kvmppc_get_hfscr_hv(vcpu); /* * PM, EBB, TM are demand-faulted so start with it clear. */ - vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM); + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM)); kvmppc_mmu_book3s_hv_init(vcpu); @@ -3071,6 +3119,8 @@ static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu) unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow); unpin_vpa(vcpu->kvm, &vcpu->arch.vpa); spin_unlock(&vcpu->arch.vpa_update_lock); + if (kvmhv_is_nestedv2()) + kvmhv_nestedv2_vcpu_free(vcpu, &vcpu->arch.nestedv2_io); } static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu) @@ -4035,10 +4085,60 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) } } +static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, + unsigned long lpcr, u64 *tb) +{ + struct kvmhv_nestedv2_io *io; + unsigned long msr, i; + int trap; + long rc; + + io = &vcpu->arch.nestedv2_io; + + msr = mfmsr(); + kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) + return 0; + + rc = kvmhv_nestedv2_flush_vcpu(vcpu, 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); + + if (rc != H_SUCCESS) { + pr_err("KVM Guest Run VCPU hcall failed\n"); + if (rc == H_INVALID_ELEMENT_ID) + pr_err("KVM: Guest Run VCPU invalid element id at %ld\n", i); + else if (rc == H_INVALID_ELEMENT_SIZE) + pr_err("KVM: Guest Run VCPU invalid element size at %ld\n", i); + else if (rc == H_INVALID_ELEMENT_VALUE) + pr_err("KVM: Guest Run VCPU invalid element value at %ld\n", i); + return -EINVAL; + } + accumulate_time(vcpu, &vcpu->arch.guest_exit); + + *tb = mftb(); + kvmppc_gsm_reset(io->vcpu_message); + kvmppc_gsm_reset(io->vcore_message); + kvmppc_gsbm_zero(&io->valids); + + rc = kvmhv_nestedv2_parse_output(vcpu); + if (rc < 0) + return -EINVAL; + + timer_rearm_host_dec(*tb); + + return trap; +} + /* call our hypervisor to load up HV regs and go */ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) { - struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long host_psscr; unsigned long msr; struct hv_guest_state hvregs; @@ -4118,7 +4218,7 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ dec = (s32) dec; *tb = mftb(); - vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset); + vcpu->arch.dec_expires = dec + (*tb + kvmppc_get_tb_offset(vcpu)); timer_rearm_host_dec(*tb); @@ -4153,7 +4253,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu_vpa_increment_dispatch(vcpu); if (kvmhv_on_pseries()) { - trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb); + if (kvmhv_is_nestedv1()) + trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb); + else + trap = kvmhv_vcpu_entry_nestedv2(vcpu, time_limit, lpcr, tb); /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !nested && @@ -4176,7 +4279,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, __this_cpu_write(cpu_in_guest, NULL); if (trap == BOOK3S_INTERRUPT_SYSCALL && - !(vcpu->arch.shregs.msr & MSR_PR)) { + !(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) { unsigned long req = kvmppc_get_gpr(vcpu, 3); /* @@ -4655,13 +4758,19 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (!nested) { kvmppc_core_prepare_to_enter(vcpu); - if (vcpu->arch.shregs.msr & 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 || @@ -4677,7 +4786,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - kvmppc_update_vpa_dispatch_p9(vcpu, vc, tb + vc->tb_offset); + kvmppc_update_vpa_dispatch_p9(vcpu, vc, tb + kvmppc_get_tb_offset(vcpu)); trace_kvm_guest_enter(vcpu); @@ -4725,7 +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))) @@ -4844,7 +4953,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) msr |= MSR_VSX; if ((cpu_has_feature(CPU_FTR_TM) || cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && - (vcpu->arch.hfscr & HFSCR_TM)) + (kvmppc_get_hfscr_hv(vcpu) & HFSCR_TM)) msr |= MSR_TM; msr = msr_check_and_set(msr); @@ -4868,7 +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(vcpu->arch.shregs.msr & 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: @@ -5133,6 +5242,14 @@ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask) if (++cores_done >= kvm->arch.online_vcores) break; } + + if (kvmhv_is_nestedv2()) { + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LPCR); + } + } } void kvmppc_setup_partition_table(struct kvm *kvm) @@ -5399,15 +5516,43 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) /* Allocate the guest's logical partition ID */ - lpid = kvmppc_alloc_lpid(); - if ((long)lpid < 0) - return -ENOMEM; - kvm->arch.lpid = lpid; + if (!kvmhv_is_nestedv2()) { + lpid = kvmppc_alloc_lpid(); + if ((long)lpid < 0) + return -ENOMEM; + kvm->arch.lpid = lpid; + } kvmppc_alloc_host_rm_ops(); kvmhv_vm_nested_init(kvm); + if (kvmhv_is_nestedv2()) { + long rc; + unsigned long guest_id; + + rc = plpar_guest_create(0, &guest_id); + + if (rc != H_SUCCESS) + pr_err("KVM: Create Guest hcall failed, rc=%ld\n", rc); + + switch (rc) { + case H_PARAMETER: + case H_FUNCTION: + case H_STATE: + return -EINVAL; + case H_NOT_ENOUGH_RESOURCES: + case H_ABORTED: + return -ENOMEM; + case H_AUTHORITY: + return -EPERM; + case H_NOT_AVAILABLE: + return -EBUSY; + } + kvm->arch.lpid = guest_id; + } + + /* * Since we don't flush the TLB when tearing down a VM, * and this lpid might have previously been used, @@ -5477,7 +5622,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) lpcr |= LPCR_HAIL; ret = kvmppc_init_vm_radix(kvm); if (ret) { - kvmppc_free_lpid(kvm->arch.lpid); + if (kvmhv_is_nestedv2()) + plpar_guest_delete(0, kvm->arch.lpid); + else + kvmppc_free_lpid(kvm->arch.lpid); return ret; } kvmppc_setup_partition_table(kvm); @@ -5567,10 +5715,16 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) kvm->arch.process_table = 0; if (kvm->arch.secure_guest) uv_svm_terminate(kvm->arch.lpid); - kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); + if (!kvmhv_is_nestedv2()) + kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); } - kvmppc_free_lpid(kvm->arch.lpid); + if (kvmhv_is_nestedv2()) { + kvmhv_flush_lpid(kvm->arch.lpid); + plpar_guest_delete(0, kvm->arch.lpid); + } else { + kvmppc_free_lpid(kvm->arch.lpid); + } kvmppc_free_pimap(kvm); } @@ -5982,6 +6136,8 @@ static int kvmhv_enable_nested(struct kvm *kvm) return -ENODEV; if (!radix_enabled()) return -ENODEV; + if (kvmhv_is_nestedv2()) + return -ENODEV; /* kvm == NULL means the caller is testing if the capability exists */ if (kvm) @@ -6084,7 +6240,7 @@ static int kvmhv_svm_off(struct kvm *kvm) } srcu_idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct kvm_memory_slot *memslot; struct kvm_memslots *slots = __kvm_memslots(kvm, i); int bkt; diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h index 2f2e59d7d433..47b2c815641e 100644 --- a/arch/powerpc/kvm/book3s_hv.h +++ b/arch/powerpc/kvm/book3s_hv.h @@ -3,6 +3,8 @@ /* * Privileged (non-hypervisor) host registers to save. */ +#include "asm/guest-state-buffer.h" + struct p9_host_os_sprs { unsigned long iamr; unsigned long amr; @@ -50,3 +52,77 @@ void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next); #define start_timing(vcpu, next) do {} while (0) #define end_timing(vcpu) do {} while (0) #endif + +static inline void __kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 val) +{ + vcpu->arch.shregs.msr = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_MSR); +} + +static inline u64 __kvmppc_get_msr_hv(struct kvm_vcpu *vcpu) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_MSR) < 0); + return vcpu->arch.shregs.msr; +} + +#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size, iden) \ +static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, u##size val) \ +{ \ + vcpu->arch.reg = val; \ + kvmhv_nestedv2_mark_dirty(vcpu, iden); \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size, iden) \ +static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu) \ +{ \ + kvmhv_nestedv2_cached_reload(vcpu, iden); \ + return vcpu->arch.reg; \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(reg, size, iden) \ + KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size, iden) \ + KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size, iden) \ + +#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size, iden) \ +static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, int i, u##size val) \ +{ \ + vcpu->arch.reg[i] = val; \ + kvmhv_nestedv2_mark_dirty(vcpu, iden(i)); \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size, iden) \ +static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu, int i) \ +{ \ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden(i)) < 0); \ + return vcpu->arch.reg[i]; \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(reg, size, iden) \ + KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size, iden) \ + KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size, iden) \ + +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(mmcra, 64, KVMPPC_GSID_MMCRA) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hfscr, 64, KVMPPC_GSID_HFSCR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(fscr, 64, KVMPPC_GSID_FSCR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dscr, 64, KVMPPC_GSID_DSCR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(purr, 64, KVMPPC_GSID_PURR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(spurr, 64, KVMPPC_GSID_SPURR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(amr, 64, KVMPPC_GSID_AMR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(uamor, 64, KVMPPC_GSID_UAMOR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(siar, 64, KVMPPC_GSID_SIAR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(sdar, 64, KVMPPC_GSID_SDAR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(iamr, 64, KVMPPC_GSID_IAMR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr0, 64, KVMPPC_GSID_DAWR0) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr1, 64, KVMPPC_GSID_DAWR1) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx0, 64, KVMPPC_GSID_DAWRX0) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx1, 64, KVMPPC_GSID_DAWRX1) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ciabr, 64, KVMPPC_GSID_CIABR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(wort, 64, KVMPPC_GSID_WORT) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ppr, 64, KVMPPC_GSID_PPR) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ctrl, 64, KVMPPC_GSID_CTRL); + +KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(mmcr, 64, KVMPPC_GSID_MMCR) +KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(sier, 64, KVMPPC_GSID_SIER) +KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(pmc, 32, KVMPPC_GSID_PMC) + +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(pspb, 32, KVMPPC_GSID_PSPB) diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 0f5b021fa559..fa0e3a22cac0 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -32,6 +32,7 @@ #include "book3s_xics.h" #include "book3s_xive.h" +#include "book3s_hv.h" /* * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206) @@ -182,9 +183,13 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present); long kvmppc_rm_h_random(struct kvm_vcpu *vcpu) { + unsigned long rand; + if (ppc_md.get_random_seed && - ppc_md.get_random_seed(&vcpu->arch.regs.gpr[4])) + ppc_md.get_random_seed(&rand)) { + kvmppc_set_gpr(vcpu, 4, rand); return H_SUCCESS; + } return H_HARDWARE; } @@ -510,7 +515,7 @@ void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) */ if ((msr & MSR_TS_MASK) == MSR_TS_MASK) msr &= ~MSR_TS_MASK; - vcpu->arch.shregs.msr = msr; + __kvmppc_set_msr_hv(vcpu, msr); kvmppc_end_cede(vcpu); } EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv); @@ -548,7 +553,7 @@ static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) kvmppc_set_srr0(vcpu, pc); kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags); kvmppc_set_pc(vcpu, new_pc); - vcpu->arch.shregs.msr = new_msr; + __kvmppc_set_msr_hv(vcpu, new_msr); } void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 377d0b4a05ee..5c375ec1a3c6 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -428,10 +428,12 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) return vcpu->arch.trap; } +unsigned long nested_capabilities; + long kvmhv_nested_init(void) { long int ptb_order; - unsigned long ptcr; + unsigned long ptcr, host_capabilities; long rc; if (!kvmhv_on_pseries()) @@ -439,6 +441,29 @@ long kvmhv_nested_init(void) if (!radix_enabled()) return -ENODEV; + rc = plpar_guest_get_capabilities(0, &host_capabilities); + if (rc == H_SUCCESS) { + unsigned long capabilities = 0; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + capabilities |= H_GUEST_CAP_POWER10; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + capabilities |= H_GUEST_CAP_POWER9; + + nested_capabilities = capabilities & host_capabilities; + rc = plpar_guest_set_capabilities(0, nested_capabilities); + if (rc != H_SUCCESS) { + pr_err("kvm-hv: Could not configure parent hypervisor capabilities (rc=%ld)", + rc); + return -ENODEV; + } + + static_branch_enable(&__kvmhv_is_nestedv2); + return 0; + } + + pr_info("kvm-hv: nestedv2 get capabilities hcall failed, falling back to nestedv1 (rc=%ld)\n", + rc); /* Partition table entry is 1<<4 bytes in size, hence the 4. */ ptb_order = KVM_MAX_NESTED_GUESTS_SHIFT + 4; /* Minimum partition table size is 1<<12 bytes */ @@ -478,7 +503,7 @@ void kvmhv_nested_exit(void) } } -static void kvmhv_flush_lpid(unsigned int lpid) +void kvmhv_flush_lpid(u64 lpid) { long rc; @@ -500,17 +525,22 @@ static void kvmhv_flush_lpid(unsigned int lpid) pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc); } -void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1) +void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1) { if (!kvmhv_on_pseries()) { mmu_partition_table_set_entry(lpid, dw0, dw1, true); return; } - pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0); - pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1); - /* L0 will do the necessary barriers */ - kvmhv_flush_lpid(lpid); + if (kvmhv_is_nestedv1()) { + pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0); + pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1); + /* L0 will do the necessary barriers */ + kvmhv_flush_lpid(lpid); + } + + if (kvmhv_is_nestedv2()) + kvmhv_nestedv2_set_ptbl_entry(lpid, dw0, dw1); } static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp) diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c new file mode 100644 index 000000000000..5378eb40b162 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c @@ -0,0 +1,1023 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2023 Jordan Niethe, IBM Corp. <jniethe5@gmail.com> + * + * Authors: + * Jordan Niethe <jniethe5@gmail.com> + * + * Description: KVM functions specific to running on Book 3S + * processors as a NESTEDv2 guest. + * + */ + +#include "linux/blk-mq.h" +#include "linux/console.h" +#include "linux/gfp_types.h" +#include "linux/signal.h" +#include <linux/kernel.h> +#include <linux/kvm_host.h> +#include <linux/pgtable.h> + +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/hvcall.h> +#include <asm/pgalloc.h> +#include <asm/reg.h> +#include <asm/plpar_wrappers.h> +#include <asm/guest-state-buffer.h> +#include "trace_hv.h" + +struct static_key_false __kvmhv_is_nestedv2 __read_mostly; +EXPORT_SYMBOL_GPL(__kvmhv_is_nestedv2); + + +static size_t +gs_msg_ops_kvmhv_nestedv2_config_get_size(struct kvmppc_gs_msg *gsm) +{ + u16 ids[] = { + KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE, + KVMPPC_GSID_RUN_INPUT, + KVMPPC_GSID_RUN_OUTPUT, + + }; + size_t size = 0; + + for (int i = 0; i < ARRAY_SIZE(ids); i++) + size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i])); + return size; +} + +static int +gs_msg_ops_kvmhv_nestedv2_config_fill_info(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + struct kvmhv_nestedv2_config *cfg; + int rc; + + cfg = gsm->data; + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE)) { + rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE, + cfg->vcpu_run_output_size); + if (rc < 0) + return rc; + } + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_INPUT)) { + rc = kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_INPUT, + cfg->vcpu_run_input_cfg); + if (rc < 0) + return rc; + } + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_OUTPUT)) { + kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT, + cfg->vcpu_run_output_cfg); + if (rc < 0) + return rc; + } + + return 0; +} + +static int +gs_msg_ops_kvmhv_nestedv2_config_refresh_info(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb) +{ + struct kvmhv_nestedv2_config *cfg; + struct kvmppc_gs_parser gsp = { 0 }; + struct kvmppc_gs_elem *gse; + int rc; + + cfg = gsm->data; + + rc = kvmppc_gse_parse(&gsp, gsb); + if (rc < 0) + return rc; + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE); + if (gse) + cfg->vcpu_run_output_size = kvmppc_gse_get_u64(gse); + return 0; +} + +static struct kvmppc_gs_msg_ops config_msg_ops = { + .get_size = gs_msg_ops_kvmhv_nestedv2_config_get_size, + .fill_info = gs_msg_ops_kvmhv_nestedv2_config_fill_info, + .refresh_info = gs_msg_ops_kvmhv_nestedv2_config_refresh_info, +}; + +static size_t gs_msg_ops_vcpu_get_size(struct kvmppc_gs_msg *gsm) +{ + struct kvmppc_gs_bitmap gsbm = { 0 }; + size_t size = 0; + u16 iden; + + kvmppc_gsbm_fill(&gsbm); + kvmppc_gsbm_for_each(&gsbm, iden) + { + switch (iden) { + case KVMPPC_GSID_HOST_STATE_SIZE: + case KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE: + case KVMPPC_GSID_PARTITION_TABLE: + case KVMPPC_GSID_PROCESS_TABLE: + case KVMPPC_GSID_RUN_INPUT: + case KVMPPC_GSID_RUN_OUTPUT: + break; + default: + size += kvmppc_gse_total_size(kvmppc_gsid_size(iden)); + } + } + return size; +} + +static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + struct kvm_vcpu *vcpu; + vector128 v; + int rc, i; + u16 iden; + + vcpu = gsm->data; + + kvmppc_gsm_for_each(gsm, iden) + { + rc = 0; + + if ((gsm->flags & KVMPPC_GS_FLAGS_WIDE) != + (kvmppc_gsid_flags(iden) & KVMPPC_GS_FLAGS_WIDE)) + continue; + + switch (iden) { + case KVMPPC_GSID_DSCR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dscr); + break; + case KVMPPC_GSID_MMCRA: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.mmcra); + break; + case KVMPPC_GSID_HFSCR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.hfscr); + break; + case KVMPPC_GSID_PURR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.purr); + break; + case KVMPPC_GSID_SPURR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.spurr); + break; + case KVMPPC_GSID_AMR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.amr); + break; + case KVMPPC_GSID_UAMOR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.uamor); + break; + case KVMPPC_GSID_SIAR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.siar); + break; + case KVMPPC_GSID_SDAR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.sdar); + break; + case KVMPPC_GSID_IAMR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.iamr); + break; + case KVMPPC_GSID_DAWR0: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dawr0); + break; + case KVMPPC_GSID_DAWR1: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dawr1); + break; + case KVMPPC_GSID_DAWRX0: + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.dawrx0); + break; + case KVMPPC_GSID_DAWRX1: + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.dawrx1); + break; + case KVMPPC_GSID_CIABR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ciabr); + break; + case KVMPPC_GSID_WORT: + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.wort); + break; + case KVMPPC_GSID_PPR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ppr); + break; + case KVMPPC_GSID_PSPB: + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.pspb); + break; + case KVMPPC_GSID_TAR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.tar); + break; + case KVMPPC_GSID_FSCR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.fscr); + break; + case KVMPPC_GSID_EBBHR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ebbhr); + break; + case KVMPPC_GSID_EBBRR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ebbrr); + break; + case KVMPPC_GSID_BESCR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.bescr); + break; + case KVMPPC_GSID_IC: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ic); + break; + case KVMPPC_GSID_CTRL: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ctrl); + break; + case KVMPPC_GSID_PIDR: + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.pid); + break; + case KVMPPC_GSID_AMOR: { + u64 amor = ~0; + + rc = kvmppc_gse_put_u64(gsb, iden, amor); + break; + } + case KVMPPC_GSID_VRSAVE: + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.vrsave); + break; + case KVMPPC_GSID_MMCR(0)... KVMPPC_GSID_MMCR(3): + i = iden - KVMPPC_GSID_MMCR(0); + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.mmcr[i]); + break; + case KVMPPC_GSID_SIER(0)... KVMPPC_GSID_SIER(2): + i = iden - KVMPPC_GSID_SIER(0); + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.sier[i]); + break; + case KVMPPC_GSID_PMC(0)... KVMPPC_GSID_PMC(5): + i = iden - KVMPPC_GSID_PMC(0); + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.pmc[i]); + break; + case KVMPPC_GSID_GPR(0)... KVMPPC_GSID_GPR(31): + i = iden - KVMPPC_GSID_GPR(0); + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.regs.gpr[i]); + break; + case KVMPPC_GSID_CR: + rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.regs.ccr); + break; + case KVMPPC_GSID_XER: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.regs.xer); + break; + case KVMPPC_GSID_CTR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.regs.ctr); + break; + case KVMPPC_GSID_LR: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.regs.link); + break; + case KVMPPC_GSID_NIA: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.regs.nip); + break; + case KVMPPC_GSID_SRR0: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.srr0); + break; + case KVMPPC_GSID_SRR1: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.srr1); + break; + case KVMPPC_GSID_SPRG0: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.sprg0); + break; + case KVMPPC_GSID_SPRG1: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.sprg1); + break; + case KVMPPC_GSID_SPRG2: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.sprg2); + break; + case KVMPPC_GSID_SPRG3: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.sprg3); + break; + case KVMPPC_GSID_DAR: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.dar); + break; + case KVMPPC_GSID_DSISR: + rc = kvmppc_gse_put_u32(gsb, iden, + vcpu->arch.shregs.dsisr); + break; + case KVMPPC_GSID_MSR: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.shregs.msr); + break; + case KVMPPC_GSID_VTB: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.vcore->vtb); + break; + case KVMPPC_GSID_LPCR: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.vcore->lpcr); + break; + case KVMPPC_GSID_TB_OFFSET: + rc = kvmppc_gse_put_u64(gsb, iden, + vcpu->arch.vcore->tb_offset); + break; + case KVMPPC_GSID_FPSCR: + rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.fp.fpscr); + break; + case KVMPPC_GSID_VSRS(0)... KVMPPC_GSID_VSRS(31): + i = iden - KVMPPC_GSID_VSRS(0); + memcpy(&v, &vcpu->arch.fp.fpr[i], + sizeof(vcpu->arch.fp.fpr[i])); + rc = kvmppc_gse_put_vector128(gsb, iden, &v); + break; +#ifdef CONFIG_VSX + case KVMPPC_GSID_VSCR: + rc = kvmppc_gse_put_u32(gsb, iden, + vcpu->arch.vr.vscr.u[3]); + break; + case KVMPPC_GSID_VSRS(32)... KVMPPC_GSID_VSRS(63): + i = iden - KVMPPC_GSID_VSRS(32); + rc = kvmppc_gse_put_vector128(gsb, iden, + &vcpu->arch.vr.vr[i]); + break; +#endif + case KVMPPC_GSID_DEC_EXPIRY_TB: { + u64 dw; + + dw = vcpu->arch.dec_expires - + vcpu->arch.vcore->tb_offset; + rc = kvmppc_gse_put_u64(gsb, iden, dw); + break; + } + case KVMPPC_GSID_LOGICAL_PVR: + rc = kvmppc_gse_put_u32(gsb, iden, + vcpu->arch.vcore->arch_compat); + break; + } + + if (rc < 0) + return rc; + } + + return 0; +} + +static int gs_msg_ops_vcpu_refresh_info(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb) +{ + struct kvmppc_gs_parser gsp = { 0 }; + struct kvmhv_nestedv2_io *io; + struct kvmppc_gs_bitmap *valids; + struct kvm_vcpu *vcpu; + struct kvmppc_gs_elem *gse; + vector128 v; + int rc, i; + u16 iden; + + vcpu = gsm->data; + + rc = kvmppc_gse_parse(&gsp, gsb); + if (rc < 0) + return rc; + + io = &vcpu->arch.nestedv2_io; + valids = &io->valids; + + kvmppc_gsp_for_each(&gsp, iden, gse) + { + switch (iden) { + case KVMPPC_GSID_DSCR: + vcpu->arch.dscr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_MMCRA: + vcpu->arch.mmcra = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_HFSCR: + vcpu->arch.hfscr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_PURR: + vcpu->arch.purr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SPURR: + vcpu->arch.spurr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_AMR: + vcpu->arch.amr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_UAMOR: + vcpu->arch.uamor = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SIAR: + vcpu->arch.siar = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SDAR: + vcpu->arch.sdar = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_IAMR: + vcpu->arch.iamr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_DAWR0: + vcpu->arch.dawr0 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_DAWR1: + vcpu->arch.dawr1 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_DAWRX0: + vcpu->arch.dawrx0 = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_DAWRX1: + vcpu->arch.dawrx1 = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_CIABR: + vcpu->arch.ciabr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_WORT: + vcpu->arch.wort = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_PPR: + vcpu->arch.ppr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_PSPB: + vcpu->arch.pspb = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_TAR: + vcpu->arch.tar = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_FSCR: + vcpu->arch.fscr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_EBBHR: + vcpu->arch.ebbhr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_EBBRR: + vcpu->arch.ebbrr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_BESCR: + vcpu->arch.bescr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_IC: + vcpu->arch.ic = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_CTRL: + vcpu->arch.ctrl = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_PIDR: + vcpu->arch.pid = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_AMOR: + break; + case KVMPPC_GSID_VRSAVE: + vcpu->arch.vrsave = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_MMCR(0)... KVMPPC_GSID_MMCR(3): + i = iden - KVMPPC_GSID_MMCR(0); + vcpu->arch.mmcr[i] = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SIER(0)... KVMPPC_GSID_SIER(2): + i = iden - KVMPPC_GSID_SIER(0); + vcpu->arch.sier[i] = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_PMC(0)... KVMPPC_GSID_PMC(5): + i = iden - KVMPPC_GSID_PMC(0); + vcpu->arch.pmc[i] = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_GPR(0)... KVMPPC_GSID_GPR(31): + i = iden - KVMPPC_GSID_GPR(0); + vcpu->arch.regs.gpr[i] = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_CR: + vcpu->arch.regs.ccr = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_XER: + vcpu->arch.regs.xer = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_CTR: + vcpu->arch.regs.ctr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_LR: + vcpu->arch.regs.link = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_NIA: + vcpu->arch.regs.nip = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SRR0: + vcpu->arch.shregs.srr0 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SRR1: + vcpu->arch.shregs.srr1 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SPRG0: + vcpu->arch.shregs.sprg0 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SPRG1: + vcpu->arch.shregs.sprg1 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SPRG2: + vcpu->arch.shregs.sprg2 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_SPRG3: + vcpu->arch.shregs.sprg3 = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_DAR: + vcpu->arch.shregs.dar = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_DSISR: + vcpu->arch.shregs.dsisr = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_MSR: + vcpu->arch.shregs.msr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_VTB: + vcpu->arch.vcore->vtb = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_LPCR: + vcpu->arch.vcore->lpcr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_TB_OFFSET: + vcpu->arch.vcore->tb_offset = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_FPSCR: + vcpu->arch.fp.fpscr = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_VSRS(0)... KVMPPC_GSID_VSRS(31): + kvmppc_gse_get_vector128(gse, &v); + i = iden - KVMPPC_GSID_VSRS(0); + memcpy(&vcpu->arch.fp.fpr[i], &v, + sizeof(vcpu->arch.fp.fpr[i])); + break; +#ifdef CONFIG_VSX + case KVMPPC_GSID_VSCR: + vcpu->arch.vr.vscr.u[3] = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_VSRS(32)... KVMPPC_GSID_VSRS(63): + i = iden - KVMPPC_GSID_VSRS(32); + kvmppc_gse_get_vector128(gse, &vcpu->arch.vr.vr[i]); + break; +#endif + case KVMPPC_GSID_HDAR: + vcpu->arch.fault_dar = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_HDSISR: + vcpu->arch.fault_dsisr = kvmppc_gse_get_u32(gse); + break; + case KVMPPC_GSID_ASDR: + vcpu->arch.fault_gpa = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_HEIR: + vcpu->arch.emul_inst = kvmppc_gse_get_u64(gse); + break; + case KVMPPC_GSID_DEC_EXPIRY_TB: { + u64 dw; + + dw = kvmppc_gse_get_u64(gse); + vcpu->arch.dec_expires = + dw + vcpu->arch.vcore->tb_offset; + break; + } + case KVMPPC_GSID_LOGICAL_PVR: + vcpu->arch.vcore->arch_compat = kvmppc_gse_get_u32(gse); + break; + default: + continue; + } + kvmppc_gsbm_set(valids, iden); + } + + return 0; +} + +static struct kvmppc_gs_msg_ops vcpu_message_ops = { + .get_size = gs_msg_ops_vcpu_get_size, + .fill_info = gs_msg_ops_vcpu_fill_info, + .refresh_info = gs_msg_ops_vcpu_refresh_info, +}; + +static int kvmhv_nestedv2_host_create(struct kvm_vcpu *vcpu, + struct kvmhv_nestedv2_io *io) +{ + struct kvmhv_nestedv2_config *cfg; + struct kvmppc_gs_buff *gsb, *vcpu_run_output, *vcpu_run_input; + unsigned long guest_id, vcpu_id; + struct kvmppc_gs_msg *gsm, *vcpu_message, *vcore_message; + int rc; + + cfg = &io->cfg; + guest_id = vcpu->kvm->arch.lpid; + vcpu_id = vcpu->vcpu_id; + + gsm = kvmppc_gsm_new(&config_msg_ops, cfg, KVMPPC_GS_FLAGS_WIDE, + GFP_KERNEL); + if (!gsm) { + rc = -ENOMEM; + goto err; + } + + gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), guest_id, vcpu_id, + GFP_KERNEL); + if (!gsb) { + rc = -ENOMEM; + goto free_gsm; + } + + rc = kvmppc_gsb_receive_datum(gsb, gsm, + KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE); + if (rc < 0) { + pr_err("KVM-NESTEDv2: couldn't get vcpu run output buffer minimum size\n"); + goto free_gsb; + } + + vcpu_run_output = kvmppc_gsb_new(cfg->vcpu_run_output_size, guest_id, + vcpu_id, GFP_KERNEL); + if (!vcpu_run_output) { + rc = -ENOMEM; + goto free_gsb; + } + + cfg->vcpu_run_output_cfg.address = kvmppc_gsb_paddress(vcpu_run_output); + cfg->vcpu_run_output_cfg.size = kvmppc_gsb_capacity(vcpu_run_output); + io->vcpu_run_output = vcpu_run_output; + + gsm->flags = 0; + rc = kvmppc_gsb_send_datum(gsb, gsm, KVMPPC_GSID_RUN_OUTPUT); + if (rc < 0) { + pr_err("KVM-NESTEDv2: couldn't set vcpu run output buffer\n"); + goto free_gs_out; + } + + vcpu_message = kvmppc_gsm_new(&vcpu_message_ops, vcpu, 0, GFP_KERNEL); + if (!vcpu_message) { + rc = -ENOMEM; + goto free_gs_out; + } + kvmppc_gsm_include_all(vcpu_message); + + io->vcpu_message = vcpu_message; + + vcpu_run_input = kvmppc_gsb_new(kvmppc_gsm_size(vcpu_message), guest_id, + vcpu_id, GFP_KERNEL); + if (!vcpu_run_input) { + rc = -ENOMEM; + goto free_vcpu_message; + } + + io->vcpu_run_input = vcpu_run_input; + cfg->vcpu_run_input_cfg.address = kvmppc_gsb_paddress(vcpu_run_input); + cfg->vcpu_run_input_cfg.size = kvmppc_gsb_capacity(vcpu_run_input); + rc = kvmppc_gsb_send_datum(gsb, gsm, KVMPPC_GSID_RUN_INPUT); + if (rc < 0) { + pr_err("KVM-NESTEDv2: couldn't set vcpu run input buffer\n"); + goto free_vcpu_run_input; + } + + vcore_message = kvmppc_gsm_new(&vcpu_message_ops, vcpu, + KVMPPC_GS_FLAGS_WIDE, GFP_KERNEL); + if (!vcore_message) { + rc = -ENOMEM; + goto free_vcpu_run_input; + } + + kvmppc_gsm_include_all(vcore_message); + kvmppc_gsbm_clear(&vcore_message->bitmap, KVMPPC_GSID_LOGICAL_PVR); + io->vcore_message = vcore_message; + + kvmppc_gsbm_fill(&io->valids); + kvmppc_gsm_free(gsm); + kvmppc_gsb_free(gsb); + return 0; + +free_vcpu_run_input: + kvmppc_gsb_free(vcpu_run_input); +free_vcpu_message: + kvmppc_gsm_free(vcpu_message); +free_gs_out: + kvmppc_gsb_free(vcpu_run_output); +free_gsb: + kvmppc_gsb_free(gsb); +free_gsm: + kvmppc_gsm_free(gsm); +err: + return rc; +} + +/** + * __kvmhv_nestedv2_mark_dirty() - mark a Guest State ID to be sent to the host + * @vcpu: vcpu + * @iden: guest state ID + * + * Mark a guest state ID as having been changed by the L1 host and thus + * the new value must be sent to the L0 hypervisor. See kvmhv_nestedv2_flush_vcpu() + */ +int __kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden) +{ + struct kvmhv_nestedv2_io *io; + struct kvmppc_gs_bitmap *valids; + struct kvmppc_gs_msg *gsm; + + if (!iden) + return 0; + + io = &vcpu->arch.nestedv2_io; + valids = &io->valids; + gsm = io->vcpu_message; + kvmppc_gsm_include(gsm, iden); + gsm = io->vcore_message; + kvmppc_gsm_include(gsm, iden); + kvmppc_gsbm_set(valids, iden); + return 0; +} +EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_mark_dirty); + +/** + * __kvmhv_nestedv2_cached_reload() - reload a Guest State ID from the host + * @vcpu: vcpu + * @iden: guest state ID + * + * Reload the value for the guest state ID from the L0 host into the L1 host. + * This is cached so that going out to the L0 host only happens if necessary. + */ +int __kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden) +{ + struct kvmhv_nestedv2_io *io; + struct kvmppc_gs_bitmap *valids; + struct kvmppc_gs_buff *gsb; + struct kvmppc_gs_msg gsm; + int rc; + + if (!iden) + return 0; + + io = &vcpu->arch.nestedv2_io; + valids = &io->valids; + if (kvmppc_gsbm_test(valids, iden)) + return 0; + + gsb = io->vcpu_run_input; + kvmppc_gsm_init(&gsm, &vcpu_message_ops, vcpu, kvmppc_gsid_flags(iden)); + rc = kvmppc_gsb_receive_datum(gsb, &gsm, iden); + if (rc < 0) { + pr_err("KVM-NESTEDv2: couldn't get GSID: 0x%x\n", iden); + return rc; + } + return 0; +} +EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_cached_reload); + +/** + * kvmhv_nestedv2_flush_vcpu() - send modified Guest State IDs to the host + * @vcpu: vcpu + * @time_limit: hdec expiry tb + * + * Send the values marked by __kvmhv_nestedv2_mark_dirty() to the L0 host. + * Thread wide values are copied to the H_GUEST_RUN_VCPU input buffer. Guest + * wide values need to be sent with H_GUEST_SET first. + * + * The hdec tb offset is always sent to L0 host. + */ +int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit) +{ + struct kvmhv_nestedv2_io *io; + struct kvmppc_gs_buff *gsb; + struct kvmppc_gs_msg *gsm; + int rc; + + io = &vcpu->arch.nestedv2_io; + gsb = io->vcpu_run_input; + gsm = io->vcore_message; + rc = kvmppc_gsb_send_data(gsb, gsm); + if (rc < 0) { + pr_err("KVM-NESTEDv2: couldn't set guest wide elements\n"); + return rc; + } + + gsm = io->vcpu_message; + kvmppc_gsb_reset(gsb); + rc = kvmppc_gsm_fill_info(gsm, gsb); + if (rc < 0) { + pr_err("KVM-NESTEDv2: couldn't fill vcpu run input buffer\n"); + return rc; + } + + rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_HDEC_EXPIRY_TB, time_limit); + if (rc < 0) + return rc; + return 0; +} +EXPORT_SYMBOL_GPL(kvmhv_nestedv2_flush_vcpu); + +/** + * kvmhv_nestedv2_set_ptbl_entry() - send partition and process table state to + * L0 host + * @lpid: guest id + * @dw0: partition table double word + * @dw1: process table double word + */ +int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1) +{ + struct kvmppc_gs_part_table patbl; + struct kvmppc_gs_proc_table prtbl; + struct kvmppc_gs_buff *gsb; + size_t size; + int rc; + + size = kvmppc_gse_total_size( + kvmppc_gsid_size(KVMPPC_GSID_PARTITION_TABLE)) + + kvmppc_gse_total_size( + kvmppc_gsid_size(KVMPPC_GSID_PROCESS_TABLE)) + + sizeof(struct kvmppc_gs_header); + gsb = kvmppc_gsb_new(size, lpid, 0, GFP_KERNEL); + if (!gsb) + return -ENOMEM; + + patbl.address = dw0 & RPDB_MASK; + patbl.ea_bits = ((((dw0 & RTS1_MASK) >> (RTS1_SHIFT - 3)) | + ((dw0 & RTS2_MASK) >> RTS2_SHIFT)) + + 31); + patbl.gpd_size = 1ul << ((dw0 & RPDS_MASK) + 3); + rc = kvmppc_gse_put_part_table(gsb, KVMPPC_GSID_PARTITION_TABLE, patbl); + if (rc < 0) + goto free_gsb; + + prtbl.address = dw1 & PRTB_MASK; + prtbl.gpd_size = 1ul << ((dw1 & PRTS_MASK) + 12); + rc = kvmppc_gse_put_proc_table(gsb, KVMPPC_GSID_PROCESS_TABLE, prtbl); + if (rc < 0) + goto free_gsb; + + rc = kvmppc_gsb_send(gsb, KVMPPC_GS_FLAGS_WIDE); + if (rc < 0) { + pr_err("KVM-NESTEDv2: couldn't set the PATE\n"); + goto free_gsb; + } + + kvmppc_gsb_free(gsb); + return 0; + +free_gsb: + kvmppc_gsb_free(gsb); + return rc; +} +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 + * + * Parse the output buffer from H_GUEST_RUN_VCPU to update vcpu. + */ +int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu) +{ + struct kvmhv_nestedv2_io *io; + struct kvmppc_gs_buff *gsb; + struct kvmppc_gs_msg gsm; + + io = &vcpu->arch.nestedv2_io; + gsb = io->vcpu_run_output; + + vcpu->arch.fault_dar = 0; + vcpu->arch.fault_dsisr = 0; + vcpu->arch.fault_gpa = 0; + vcpu->arch.emul_inst = KVM_INST_FETCH_FAILED; + + kvmppc_gsm_init(&gsm, &vcpu_message_ops, vcpu, 0); + return kvmppc_gsm_refresh_info(&gsm, gsb); +} +EXPORT_SYMBOL_GPL(kvmhv_nestedv2_parse_output); + +static void kvmhv_nestedv2_host_free(struct kvm_vcpu *vcpu, + struct kvmhv_nestedv2_io *io) +{ + kvmppc_gsm_free(io->vcpu_message); + kvmppc_gsm_free(io->vcore_message); + kvmppc_gsb_free(io->vcpu_run_input); + kvmppc_gsb_free(io->vcpu_run_output); +} + +int __kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs) +{ + struct kvmhv_nestedv2_io *io; + struct kvmppc_gs_bitmap *valids; + struct kvmppc_gs_buff *gsb; + struct kvmppc_gs_msg gsm; + int rc = 0; + + + io = &vcpu->arch.nestedv2_io; + valids = &io->valids; + + gsb = io->vcpu_run_input; + kvmppc_gsm_init(&gsm, &vcpu_message_ops, vcpu, 0); + + for (int i = 0; i < 32; i++) { + if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_GPR(i))) + kvmppc_gsm_include(&gsm, KVMPPC_GSID_GPR(i)); + } + + if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_CR)) + kvmppc_gsm_include(&gsm, KVMPPC_GSID_CR); + + if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_XER)) + kvmppc_gsm_include(&gsm, KVMPPC_GSID_XER); + + if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_CTR)) + kvmppc_gsm_include(&gsm, KVMPPC_GSID_CTR); + + if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_LR)) + kvmppc_gsm_include(&gsm, KVMPPC_GSID_LR); + + if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_NIA)) + kvmppc_gsm_include(&gsm, KVMPPC_GSID_NIA); + + rc = kvmppc_gsb_receive_data(gsb, &gsm); + if (rc < 0) + pr_err("KVM-NESTEDv2: couldn't reload ptregs\n"); + + return rc; +} +EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_reload_ptregs); + +int __kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + for (int i = 0; i < 32; i++) + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_GPR(i)); + + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CR); + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_XER); + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CTR); + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LR); + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_NIA); + + return 0; +} +EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_mark_dirty_ptregs); + +/** + * kvmhv_nestedv2_vcpu_create() - create nested vcpu for the NESTEDv2 API + * @vcpu: vcpu + * @io: NESTEDv2 nested io state + * + * Parse the output buffer from H_GUEST_RUN_VCPU to update vcpu. + */ +int kvmhv_nestedv2_vcpu_create(struct kvm_vcpu *vcpu, + struct kvmhv_nestedv2_io *io) +{ + long rc; + + rc = plpar_guest_create_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id); + + if (rc != H_SUCCESS) { + pr_err("KVM: Create Guest vcpu hcall failed, rc=%ld\n", rc); + switch (rc) { + case H_NOT_ENOUGH_RESOURCES: + case H_ABORTED: + return -ENOMEM; + case H_AUTHORITY: + return -EPERM; + default: + return -EINVAL; + } + } + + rc = kvmhv_nestedv2_host_create(vcpu, io); + + return rc; +} +EXPORT_SYMBOL_GPL(kvmhv_nestedv2_vcpu_create); + +/** + * kvmhv_nestedv2_vcpu_free() - free the NESTEDv2 state + * @vcpu: vcpu + * @io: NESTEDv2 nested io state + */ +void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, + struct kvmhv_nestedv2_io *io) +{ + kvmhv_nestedv2_host_free(vcpu, io); +} +EXPORT_SYMBOL_GPL(kvmhv_nestedv2_vcpu_free); diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c index 34f1db212824..34bc0a8a1288 100644 --- a/arch/powerpc/kvm/book3s_hv_p9_entry.c +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -305,7 +305,7 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6 u32 pid; lpid = nested ? nested->shadow_lpid : kvm->arch.lpid; - pid = vcpu->arch.pid; + pid = kvmppc_get_pid(vcpu); /* * Prior memory accesses to host PID Q3 must be completed before we @@ -330,7 +330,7 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 int i; lpid = kvm->arch.lpid; - pid = vcpu->arch.pid; + pid = kvmppc_get_pid(vcpu); /* * See switch_mmu_to_guest_radix. ptesync should not be required here diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index 82be6d87514b..9012acadbca8 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -174,14 +174,14 @@ long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu) ppc_md.hmi_exception_early(NULL); out: - if (vc->tb_offset) { + if (kvmppc_get_tb_offset(vcpu)) { u64 new_tb = mftb() + vc->tb_offset; mtspr(SPRN_TBU40, new_tb); if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { new_tb += 0x1000000; mtspr(SPRN_TBU40, new_tb); } - vc->tb_offset_applied = vc->tb_offset; + vc->tb_offset_applied = kvmppc_get_tb_offset(vcpu); } return ret; diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 9182324dbef9..17cb75a127b0 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -776,8 +776,8 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C)); r &= ~HPTE_GR_RESERVED; } - vcpu->arch.regs.gpr[4 + i * 2] = v; - vcpu->arch.regs.gpr[5 + i * 2] = r; + kvmppc_set_gpr(vcpu, 4 + i * 2, v); + kvmppc_set_gpr(vcpu, 5 + i * 2, r); } return H_SUCCESS; } @@ -824,7 +824,7 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags, } } } - vcpu->arch.regs.gpr[4] = gr; + kvmppc_set_gpr(vcpu, 4, gr); ret = H_SUCCESS; out: unlock_hpte(hpte, v & ~HPTE_V_HVLOCK); @@ -872,7 +872,7 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags, kvmppc_set_dirty_from_hpte(kvm, v, gr); } } - vcpu->arch.regs.gpr[4] = gr; + kvmppc_set_gpr(vcpu, 4, gr); ret = H_SUCCESS; out: unlock_hpte(hpte, v & ~HPTE_V_HVLOCK); diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index e165bfa842bf..e42984878503 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -481,7 +481,7 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp, unsigned long xics_rm_h_xirr_x(struct kvm_vcpu *vcpu) { - vcpu->arch.regs.gpr[5] = get_tb(); + kvmppc_set_gpr(vcpu, 5, get_tb()); return xics_rm_h_xirr(vcpu); } @@ -518,7 +518,7 @@ unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu) } while (!icp_rm_try_update(icp, old_state, new_state)); /* Return the result in GPR4 */ - vcpu->arch.regs.gpr[4] = xirr; + kvmppc_set_gpr(vcpu, 4, xirr); return check_too_hard(xics, icp); } diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index e2d6f9327f77..92f33115144b 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -858,7 +858,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) } kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE; - pr_info("LPID %d went secure\n", kvm->arch.lpid); + pr_info("LPID %lld went secure\n", kvm->arch.lpid); out: srcu_read_unlock(&kvm->srcu, srcu_idx); 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/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index f4115819e738..29a382249770 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -328,7 +328,7 @@ static unsigned long xive_vm_h_xirr(struct kvm_vcpu *vcpu) */ /* Return interrupt and old CPPR in GPR4 */ - vcpu->arch.regs.gpr[4] = hirq | (old_cppr << 24); + kvmppc_set_gpr(vcpu, 4, hirq | (old_cppr << 24)); return H_SUCCESS; } @@ -364,7 +364,7 @@ static unsigned long xive_vm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server hirq = xive_vm_scan_interrupts(xc, pending, scan_poll); /* Return interrupt and old CPPR in GPR4 */ - vcpu->arch.regs.gpr[4] = hirq | (xc->cppr << 24); + kvmppc_set_gpr(vcpu, 4, hirq | (xc->cppr << 24)); return H_SUCCESS; } @@ -884,10 +884,10 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio, } if (single_escalation) - name = kasprintf(GFP_KERNEL, "kvm-%d-%d", + name = kasprintf(GFP_KERNEL, "kvm-%lld-%d", vcpu->kvm->arch.lpid, xc->server_num); else - name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d", + name = kasprintf(GFP_KERNEL, "kvm-%lld-%d-%d", vcpu->kvm->arch.lpid, xc->server_num, prio); if (!name) { pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n", @@ -2779,8 +2779,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req) { - struct kvmppc_vcore *vc = vcpu->arch.vcore; - /* The VM should have configured XICS mode before doing XICS hcalls. */ if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; @@ -2799,7 +2797,7 @@ int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req) return xive_vm_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4)); case H_XIRR_X: xive_vm_h_xirr(vcpu); - kvmppc_set_gpr(vcpu, 5, get_tb() + vc->tb_offset); + kvmppc_set_gpr(vcpu, 5, get_tb() + kvmppc_get_tb_offset(vcpu)); return H_SUCCESS; } diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 712ab91ced39..6e2ebbd8aaac 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -567,7 +567,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, u8 priority; struct kvm_ppc_xive_eq kvm_eq; int rc; - __be32 *qaddr = 0; + __be32 *qaddr = NULL; struct page *page; struct xive_q *q; gfn_t gfn; diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index 059c08ae0340..ec60c7979718 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -92,7 +92,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) vcpu->arch.mmio_host_swabbed = 0; emulated = EMULATE_FAIL; - vcpu->arch.regs.msr = vcpu->arch.shared->msr; + vcpu->arch.regs.msr = kvmppc_get_msr(vcpu); if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) { int type = op.type & INSTR_TYPE_MASK; int size = GETSIZE(op.type); @@ -111,7 +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; } @@ -131,7 +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 @@ -223,16 +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)) @@ -250,10 +251,10 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) vcpu->arch.mmio_sp64_extend = 1; emulated = kvmppc_handle_store(vcpu, - VCPU_FPR(vcpu, op.reg), size, 1); + 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 diff --git a/arch/powerpc/kvm/guest-state-buffer.c b/arch/powerpc/kvm/guest-state-buffer.c new file mode 100644 index 000000000000..b80dbc58621f --- /dev/null +++ b/arch/powerpc/kvm/guest-state-buffer.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "asm/hvcall.h" +#include <linux/log2.h> +#include <asm/pgalloc.h> +#include <asm/guest-state-buffer.h> + +static const u16 kvmppc_gse_iden_len[__KVMPPC_GSE_TYPE_MAX] = { + [KVMPPC_GSE_BE32] = sizeof(__be32), + [KVMPPC_GSE_BE64] = sizeof(__be64), + [KVMPPC_GSE_VEC128] = sizeof(vector128), + [KVMPPC_GSE_PARTITION_TABLE] = sizeof(struct kvmppc_gs_part_table), + [KVMPPC_GSE_PROCESS_TABLE] = sizeof(struct kvmppc_gs_proc_table), + [KVMPPC_GSE_BUFFER] = sizeof(struct kvmppc_gs_buff_info), +}; + +/** + * kvmppc_gsb_new() - create a new guest state buffer + * @size: total size of the guest state buffer (includes header) + * @guest_id: guest_id + * @vcpu_id: vcpu_id + * @flags: GFP flags + * + * Returns a guest state buffer. + */ +struct kvmppc_gs_buff *kvmppc_gsb_new(size_t size, unsigned long guest_id, + unsigned long vcpu_id, gfp_t flags) +{ + struct kvmppc_gs_buff *gsb; + + gsb = kzalloc(sizeof(*gsb), flags); + if (!gsb) + return NULL; + + size = roundup_pow_of_two(size); + gsb->hdr = kzalloc(size, GFP_KERNEL); + if (!gsb->hdr) + goto free; + + gsb->capacity = size; + gsb->len = sizeof(struct kvmppc_gs_header); + gsb->vcpu_id = vcpu_id; + gsb->guest_id = guest_id; + + gsb->hdr->nelems = cpu_to_be32(0); + + return gsb; + +free: + kfree(gsb); + return NULL; +} +EXPORT_SYMBOL_GPL(kvmppc_gsb_new); + +/** + * kvmppc_gsb_free() - free a guest state buffer + * @gsb: guest state buffer + */ +void kvmppc_gsb_free(struct kvmppc_gs_buff *gsb) +{ + kfree(gsb->hdr); + kfree(gsb); +} +EXPORT_SYMBOL_GPL(kvmppc_gsb_free); + +/** + * kvmppc_gsb_put() - allocate space in a guest state buffer + * @gsb: buffer to allocate in + * @size: amount of space to allocate + * + * Returns a pointer to the amount of space requested within the buffer and + * increments the count of elements in the buffer. + * + * Does not check if there is enough space in the buffer. + */ +void *kvmppc_gsb_put(struct kvmppc_gs_buff *gsb, size_t size) +{ + u32 nelems = kvmppc_gsb_nelems(gsb); + void *p; + + p = (void *)kvmppc_gsb_header(gsb) + kvmppc_gsb_len(gsb); + gsb->len += size; + + kvmppc_gsb_header(gsb)->nelems = cpu_to_be32(nelems + 1); + return p; +} +EXPORT_SYMBOL_GPL(kvmppc_gsb_put); + +static int kvmppc_gsid_class(u16 iden) +{ + if ((iden >= KVMPPC_GSE_GUESTWIDE_START) && + (iden <= KVMPPC_GSE_GUESTWIDE_END)) + return KVMPPC_GS_CLASS_GUESTWIDE; + + if ((iden >= KVMPPC_GSE_META_START) && (iden <= KVMPPC_GSE_META_END)) + return KVMPPC_GS_CLASS_META; + + if ((iden >= KVMPPC_GSE_DW_REGS_START) && + (iden <= KVMPPC_GSE_DW_REGS_END)) + return KVMPPC_GS_CLASS_DWORD_REG; + + if ((iden >= KVMPPC_GSE_W_REGS_START) && + (iden <= KVMPPC_GSE_W_REGS_END)) + return KVMPPC_GS_CLASS_WORD_REG; + + if ((iden >= KVMPPC_GSE_VSRS_START) && (iden <= KVMPPC_GSE_VSRS_END)) + return KVMPPC_GS_CLASS_VECTOR; + + if ((iden >= KVMPPC_GSE_INTR_REGS_START) && + (iden <= KVMPPC_GSE_INTR_REGS_END)) + return KVMPPC_GS_CLASS_INTR; + + return -1; +} + +static int kvmppc_gsid_type(u16 iden) +{ + int type = -1; + + switch (kvmppc_gsid_class(iden)) { + case KVMPPC_GS_CLASS_GUESTWIDE: + switch (iden) { + case KVMPPC_GSID_HOST_STATE_SIZE: + case KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE: + case KVMPPC_GSID_TB_OFFSET: + type = KVMPPC_GSE_BE64; + break; + case KVMPPC_GSID_PARTITION_TABLE: + type = KVMPPC_GSE_PARTITION_TABLE; + break; + case KVMPPC_GSID_PROCESS_TABLE: + type = KVMPPC_GSE_PROCESS_TABLE; + break; + case KVMPPC_GSID_LOGICAL_PVR: + type = KVMPPC_GSE_BE32; + break; + } + break; + case KVMPPC_GS_CLASS_META: + switch (iden) { + case KVMPPC_GSID_RUN_INPUT: + case KVMPPC_GSID_RUN_OUTPUT: + type = KVMPPC_GSE_BUFFER; + break; + case KVMPPC_GSID_VPA: + type = KVMPPC_GSE_BE64; + break; + } + break; + case KVMPPC_GS_CLASS_DWORD_REG: + type = KVMPPC_GSE_BE64; + break; + case KVMPPC_GS_CLASS_WORD_REG: + type = KVMPPC_GSE_BE32; + break; + case KVMPPC_GS_CLASS_VECTOR: + type = KVMPPC_GSE_VEC128; + break; + case KVMPPC_GS_CLASS_INTR: + switch (iden) { + case KVMPPC_GSID_HDAR: + case KVMPPC_GSID_ASDR: + case KVMPPC_GSID_HEIR: + type = KVMPPC_GSE_BE64; + break; + case KVMPPC_GSID_HDSISR: + type = KVMPPC_GSE_BE32; + break; + } + break; + } + + return type; +} + +/** + * kvmppc_gsid_flags() - the flags for a guest state ID + * @iden: guest state ID + * + * Returns any flags for the guest state ID. + */ +unsigned long kvmppc_gsid_flags(u16 iden) +{ + unsigned long flags = 0; + + switch (kvmppc_gsid_class(iden)) { + case KVMPPC_GS_CLASS_GUESTWIDE: + flags = KVMPPC_GS_FLAGS_WIDE; + break; + case KVMPPC_GS_CLASS_META: + case KVMPPC_GS_CLASS_DWORD_REG: + case KVMPPC_GS_CLASS_WORD_REG: + case KVMPPC_GS_CLASS_VECTOR: + case KVMPPC_GS_CLASS_INTR: + break; + } + + return flags; +} +EXPORT_SYMBOL_GPL(kvmppc_gsid_flags); + +/** + * kvmppc_gsid_size() - the size of a guest state ID + * @iden: guest state ID + * + * Returns the size of guest state ID. + */ +u16 kvmppc_gsid_size(u16 iden) +{ + int type; + + type = kvmppc_gsid_type(iden); + if (type == -1) + return 0; + + if (type >= __KVMPPC_GSE_TYPE_MAX) + return 0; + + return kvmppc_gse_iden_len[type]; +} +EXPORT_SYMBOL_GPL(kvmppc_gsid_size); + +/** + * kvmppc_gsid_mask() - the settable bits of a guest state ID + * @iden: guest state ID + * + * Returns a mask of settable bits for a guest state ID. + */ +u64 kvmppc_gsid_mask(u16 iden) +{ + u64 mask = ~0ull; + + switch (iden) { + case KVMPPC_GSID_LPCR: + mask = LPCR_DPFD | LPCR_ILE | LPCR_AIL | LPCR_LD | LPCR_MER | + LPCR_GTSE; + break; + case KVMPPC_GSID_MSR: + mask = ~(MSR_HV | MSR_S | MSR_ME); + break; + } + + return mask; +} +EXPORT_SYMBOL_GPL(kvmppc_gsid_mask); + +/** + * __kvmppc_gse_put() - add a guest state element to a buffer + * @gsb: buffer to the element to + * @iden: guest state ID + * @size: length of data + * @data: pointer to data + */ +int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size, + const void *data) +{ + struct kvmppc_gs_elem *gse; + u16 total_size; + + total_size = sizeof(*gse) + size; + if (total_size + kvmppc_gsb_len(gsb) > kvmppc_gsb_capacity(gsb)) + return -ENOMEM; + + if (kvmppc_gsid_size(iden) != size) + return -EINVAL; + + gse = kvmppc_gsb_put(gsb, total_size); + gse->iden = cpu_to_be16(iden); + gse->len = cpu_to_be16(size); + memcpy(gse->data, data, size); + + return 0; +} +EXPORT_SYMBOL_GPL(__kvmppc_gse_put); + +/** + * kvmppc_gse_parse() - create a parse map from a guest state buffer + * @gsp: guest state parser + * @gsb: guest state buffer + */ +int kvmppc_gse_parse(struct kvmppc_gs_parser *gsp, struct kvmppc_gs_buff *gsb) +{ + struct kvmppc_gs_elem *curr; + int rem, i; + + kvmppc_gsb_for_each_elem(i, curr, gsb, rem) { + if (kvmppc_gse_len(curr) != + kvmppc_gsid_size(kvmppc_gse_iden(curr))) + return -EINVAL; + kvmppc_gsp_insert(gsp, kvmppc_gse_iden(curr), curr); + } + + if (kvmppc_gsb_nelems(gsb) != i) + return -EINVAL; + return 0; +} +EXPORT_SYMBOL_GPL(kvmppc_gse_parse); + +static inline int kvmppc_gse_flatten_iden(u16 iden) +{ + int bit = 0; + int class; + + class = kvmppc_gsid_class(iden); + + if (class == KVMPPC_GS_CLASS_GUESTWIDE) { + bit += iden - KVMPPC_GSE_GUESTWIDE_START; + return bit; + } + + bit += KVMPPC_GSE_GUESTWIDE_COUNT; + + if (class == KVMPPC_GS_CLASS_META) { + bit += iden - KVMPPC_GSE_META_START; + return bit; + } + + bit += KVMPPC_GSE_META_COUNT; + + if (class == KVMPPC_GS_CLASS_DWORD_REG) { + bit += iden - KVMPPC_GSE_DW_REGS_START; + return bit; + } + + bit += KVMPPC_GSE_DW_REGS_COUNT; + + if (class == KVMPPC_GS_CLASS_WORD_REG) { + bit += iden - KVMPPC_GSE_W_REGS_START; + return bit; + } + + bit += KVMPPC_GSE_W_REGS_COUNT; + + if (class == KVMPPC_GS_CLASS_VECTOR) { + bit += iden - KVMPPC_GSE_VSRS_START; + return bit; + } + + bit += KVMPPC_GSE_VSRS_COUNT; + + if (class == KVMPPC_GS_CLASS_INTR) { + bit += iden - KVMPPC_GSE_INTR_REGS_START; + return bit; + } + + return 0; +} + +static inline u16 kvmppc_gse_unflatten_iden(int bit) +{ + u16 iden; + + if (bit < KVMPPC_GSE_GUESTWIDE_COUNT) { + iden = KVMPPC_GSE_GUESTWIDE_START + bit; + return iden; + } + bit -= KVMPPC_GSE_GUESTWIDE_COUNT; + + if (bit < KVMPPC_GSE_META_COUNT) { + iden = KVMPPC_GSE_META_START + bit; + return iden; + } + bit -= KVMPPC_GSE_META_COUNT; + + if (bit < KVMPPC_GSE_DW_REGS_COUNT) { + iden = KVMPPC_GSE_DW_REGS_START + bit; + return iden; + } + bit -= KVMPPC_GSE_DW_REGS_COUNT; + + if (bit < KVMPPC_GSE_W_REGS_COUNT) { + iden = KVMPPC_GSE_W_REGS_START + bit; + return iden; + } + bit -= KVMPPC_GSE_W_REGS_COUNT; + + if (bit < KVMPPC_GSE_VSRS_COUNT) { + iden = KVMPPC_GSE_VSRS_START + bit; + return iden; + } + bit -= KVMPPC_GSE_VSRS_COUNT; + + if (bit < KVMPPC_GSE_IDEN_COUNT) { + iden = KVMPPC_GSE_INTR_REGS_START + bit; + return iden; + } + + return 0; +} + +/** + * kvmppc_gsp_insert() - add a mapping from an guest state ID to an element + * @gsp: guest state parser + * @iden: guest state id (key) + * @gse: guest state element (value) + */ +void kvmppc_gsp_insert(struct kvmppc_gs_parser *gsp, u16 iden, + struct kvmppc_gs_elem *gse) +{ + int i; + + i = kvmppc_gse_flatten_iden(iden); + kvmppc_gsbm_set(&gsp->iterator, iden); + gsp->gses[i] = gse; +} +EXPORT_SYMBOL_GPL(kvmppc_gsp_insert); + +/** + * kvmppc_gsp_lookup() - lookup an element from a guest state ID + * @gsp: guest state parser + * @iden: guest state ID (key) + * + * Returns the guest state element if present. + */ +struct kvmppc_gs_elem *kvmppc_gsp_lookup(struct kvmppc_gs_parser *gsp, u16 iden) +{ + int i; + + i = kvmppc_gse_flatten_iden(iden); + return gsp->gses[i]; +} +EXPORT_SYMBOL_GPL(kvmppc_gsp_lookup); + +/** + * kvmppc_gsbm_set() - set the guest state ID + * @gsbm: guest state bitmap + * @iden: guest state ID + */ +void kvmppc_gsbm_set(struct kvmppc_gs_bitmap *gsbm, u16 iden) +{ + set_bit(kvmppc_gse_flatten_iden(iden), gsbm->bitmap); +} +EXPORT_SYMBOL_GPL(kvmppc_gsbm_set); + +/** + * kvmppc_gsbm_clear() - clear the guest state ID + * @gsbm: guest state bitmap + * @iden: guest state ID + */ +void kvmppc_gsbm_clear(struct kvmppc_gs_bitmap *gsbm, u16 iden) +{ + clear_bit(kvmppc_gse_flatten_iden(iden), gsbm->bitmap); +} +EXPORT_SYMBOL_GPL(kvmppc_gsbm_clear); + +/** + * kvmppc_gsbm_test() - test the guest state ID + * @gsbm: guest state bitmap + * @iden: guest state ID + */ +bool kvmppc_gsbm_test(struct kvmppc_gs_bitmap *gsbm, u16 iden) +{ + return test_bit(kvmppc_gse_flatten_iden(iden), gsbm->bitmap); +} +EXPORT_SYMBOL_GPL(kvmppc_gsbm_test); + +/** + * kvmppc_gsbm_next() - return the next set guest state ID + * @gsbm: guest state bitmap + * @prev: last guest state ID + */ +u16 kvmppc_gsbm_next(struct kvmppc_gs_bitmap *gsbm, u16 prev) +{ + int bit, pbit; + + pbit = prev ? kvmppc_gse_flatten_iden(prev) + 1 : 0; + bit = find_next_bit(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT, pbit); + + if (bit < KVMPPC_GSE_IDEN_COUNT) + return kvmppc_gse_unflatten_iden(bit); + return 0; +} +EXPORT_SYMBOL_GPL(kvmppc_gsbm_next); + +/** + * kvmppc_gsm_init() - initialize a guest state message + * @gsm: guest state message + * @ops: callbacks + * @data: private data + * @flags: guest wide or thread wide + */ +int kvmppc_gsm_init(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_msg_ops *ops, + void *data, unsigned long flags) +{ + memset(gsm, 0, sizeof(*gsm)); + gsm->ops = ops; + gsm->data = data; + gsm->flags = flags; + + return 0; +} +EXPORT_SYMBOL_GPL(kvmppc_gsm_init); + +/** + * kvmppc_gsm_new() - creates a new guest state message + * @ops: callbacks + * @data: private data + * @flags: guest wide or thread wide + * @gfp_flags: GFP allocation flags + * + * Returns an initialized guest state message. + */ +struct kvmppc_gs_msg *kvmppc_gsm_new(struct kvmppc_gs_msg_ops *ops, void *data, + unsigned long flags, gfp_t gfp_flags) +{ + struct kvmppc_gs_msg *gsm; + + gsm = kzalloc(sizeof(*gsm), gfp_flags); + if (!gsm) + return NULL; + + kvmppc_gsm_init(gsm, ops, data, flags); + + return gsm; +} +EXPORT_SYMBOL_GPL(kvmppc_gsm_new); + +/** + * kvmppc_gsm_size() - creates a new guest state message + * @gsm: self + * + * Returns the size required for the message. + */ +size_t kvmppc_gsm_size(struct kvmppc_gs_msg *gsm) +{ + if (gsm->ops->get_size) + return gsm->ops->get_size(gsm); + return 0; +} +EXPORT_SYMBOL_GPL(kvmppc_gsm_size); + +/** + * kvmppc_gsm_free() - free guest state message + * @gsm: guest state message + * + * Returns the size required for the message. + */ +void kvmppc_gsm_free(struct kvmppc_gs_msg *gsm) +{ + kfree(gsm); +} +EXPORT_SYMBOL_GPL(kvmppc_gsm_free); + +/** + * kvmppc_gsm_fill_info() - serialises message to guest state buffer format + * @gsm: self + * @gsb: buffer to serialise into + */ +int kvmppc_gsm_fill_info(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_buff *gsb) +{ + if (!gsm->ops->fill_info) + return -EINVAL; + + return gsm->ops->fill_info(gsb, gsm); +} +EXPORT_SYMBOL_GPL(kvmppc_gsm_fill_info); + +/** + * kvmppc_gsm_refresh_info() - deserialises from guest state buffer + * @gsm: self + * @gsb: buffer to serialise from + */ +int kvmppc_gsm_refresh_info(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb) +{ + if (!gsm->ops->fill_info) + return -EINVAL; + + return gsm->ops->refresh_info(gsm, gsb); +} +EXPORT_SYMBOL_GPL(kvmppc_gsm_refresh_info); + +/** + * kvmppc_gsb_send - send all elements in the buffer to the hypervisor. + * @gsb: guest state buffer + * @flags: guest wide or thread wide + * + * Performs the H_GUEST_SET_STATE hcall for the guest state buffer. + */ +int kvmppc_gsb_send(struct kvmppc_gs_buff *gsb, unsigned long flags) +{ + unsigned long hflags = 0; + unsigned long i; + int rc; + + if (kvmppc_gsb_nelems(gsb) == 0) + return 0; + + if (flags & KVMPPC_GS_FLAGS_WIDE) + hflags |= H_GUEST_FLAGS_WIDE; + + rc = plpar_guest_set_state(hflags, gsb->guest_id, gsb->vcpu_id, + __pa(gsb->hdr), gsb->capacity, &i); + return rc; +} +EXPORT_SYMBOL_GPL(kvmppc_gsb_send); + +/** + * kvmppc_gsb_recv - request all elements in the buffer have their value + * updated. + * @gsb: guest state buffer + * @flags: guest wide or thread wide + * + * Performs the H_GUEST_GET_STATE hcall for the guest state buffer. + * After returning from the hcall the guest state elements that were + * present in the buffer will have updated values from the hypervisor. + */ +int kvmppc_gsb_recv(struct kvmppc_gs_buff *gsb, unsigned long flags) +{ + unsigned long hflags = 0; + unsigned long i; + int rc; + + if (flags & KVMPPC_GS_FLAGS_WIDE) + hflags |= H_GUEST_FLAGS_WIDE; + + rc = plpar_guest_get_state(hflags, gsb->guest_id, gsb->vcpu_id, + __pa(gsb->hdr), gsb->capacity, &i); + return rc; +} +EXPORT_SYMBOL_GPL(kvmppc_gsb_recv); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 7197c8256668..23407fbd73c9 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -528,7 +528,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_ONE_REG: case KVM_CAP_IOEVENTFD: - case KVM_CAP_DEVICE_CTRL: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_SET_GUEST_DEBUG: r = 1; @@ -578,7 +577,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif -#ifdef CONFIG_HAVE_KVM_IRQFD +#ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQFD_RESAMPLE: r = !xive_enabled(); break; @@ -632,13 +631,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif case KVM_CAP_SYNC_MMU: -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - r = hv_enabled; -#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER) + BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER)); r = 1; -#else - r = 0; -#endif break; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_HTAB_FD: @@ -934,11 +928,11 @@ static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu, return; if (index >= 32) { - val.vval = VCPU_VSX_VR(vcpu, index - 32); + kvmppc_get_vsx_vr(vcpu, index - 32, &val.vval); val.vsxval[offset] = gpr; - VCPU_VSX_VR(vcpu, index - 32) = val.vval; + kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval); } else { - VCPU_VSX_FPR(vcpu, index, offset) = gpr; + kvmppc_set_vsx_fpr(vcpu, index, offset, gpr); } } @@ -949,13 +943,13 @@ static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu, int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK; if (index >= 32) { - val.vval = VCPU_VSX_VR(vcpu, index - 32); + kvmppc_get_vsx_vr(vcpu, index - 32, &val.vval); val.vsxval[0] = gpr; val.vsxval[1] = gpr; - VCPU_VSX_VR(vcpu, index - 32) = val.vval; + kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval); } else { - VCPU_VSX_FPR(vcpu, index, 0) = gpr; - VCPU_VSX_FPR(vcpu, index, 1) = gpr; + kvmppc_set_vsx_fpr(vcpu, index, 0, gpr); + kvmppc_set_vsx_fpr(vcpu, index, 1, gpr); } } @@ -970,12 +964,12 @@ static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu, val.vsx32val[1] = gpr; val.vsx32val[2] = gpr; val.vsx32val[3] = gpr; - VCPU_VSX_VR(vcpu, index - 32) = val.vval; + kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval); } else { val.vsx32val[0] = gpr; val.vsx32val[1] = gpr; - VCPU_VSX_FPR(vcpu, index, 0) = val.vsxval[0]; - VCPU_VSX_FPR(vcpu, index, 1) = val.vsxval[0]; + kvmppc_set_vsx_fpr(vcpu, index, 0, val.vsxval[0]); + kvmppc_set_vsx_fpr(vcpu, index, 1, val.vsxval[0]); } } @@ -991,15 +985,15 @@ static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu, return; if (index >= 32) { - val.vval = VCPU_VSX_VR(vcpu, index - 32); + kvmppc_get_vsx_vr(vcpu, index - 32, &val.vval); val.vsx32val[offset] = gpr32; - VCPU_VSX_VR(vcpu, index - 32) = val.vval; + kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval); } else { dword_offset = offset / 2; word_offset = offset % 2; - val.vsxval[0] = VCPU_VSX_FPR(vcpu, index, dword_offset); + val.vsxval[0] = kvmppc_get_vsx_fpr(vcpu, index, dword_offset); val.vsx32val[word_offset] = gpr32; - VCPU_VSX_FPR(vcpu, index, dword_offset) = val.vsxval[0]; + kvmppc_set_vsx_fpr(vcpu, index, dword_offset, val.vsxval[0]); } } #endif /* CONFIG_VSX */ @@ -1058,9 +1052,9 @@ static inline void kvmppc_set_vmx_dword(struct kvm_vcpu *vcpu, if (offset == -1) return; - val.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, &val.vval); val.vsxval[offset] = gpr; - VCPU_VSX_VR(vcpu, index) = val.vval; + kvmppc_set_vsx_vr(vcpu, index, &val.vval); } static inline void kvmppc_set_vmx_word(struct kvm_vcpu *vcpu, @@ -1074,9 +1068,9 @@ static inline void kvmppc_set_vmx_word(struct kvm_vcpu *vcpu, if (offset == -1) return; - val.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, &val.vval); val.vsx32val[offset] = gpr32; - VCPU_VSX_VR(vcpu, index) = val.vval; + kvmppc_set_vsx_vr(vcpu, index, &val.vval); } static inline void kvmppc_set_vmx_hword(struct kvm_vcpu *vcpu, @@ -1090,9 +1084,9 @@ static inline void kvmppc_set_vmx_hword(struct kvm_vcpu *vcpu, if (offset == -1) return; - val.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, &val.vval); val.vsx16val[offset] = gpr16; - VCPU_VSX_VR(vcpu, index) = val.vval; + kvmppc_set_vsx_vr(vcpu, index, &val.vval); } static inline void kvmppc_set_vmx_byte(struct kvm_vcpu *vcpu, @@ -1106,9 +1100,9 @@ static inline void kvmppc_set_vmx_byte(struct kvm_vcpu *vcpu, if (offset == -1) return; - val.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, &val.vval); val.vsx8val[offset] = gpr8; - VCPU_VSX_VR(vcpu, index) = val.vval; + kvmppc_set_vsx_vr(vcpu, index, &val.vval); } #endif /* CONFIG_ALTIVEC */ @@ -1194,14 +1188,14 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.kvm_ops->giveup_ext) vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_FP); - VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr; + kvmppc_set_fpr(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK, gpr); break; #ifdef CONFIG_PPC_BOOK3S case KVM_MMIO_REG_QPR: vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr; break; case KVM_MMIO_REG_FQPR: - VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr; + kvmppc_set_fpr(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK, gpr); vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr; break; #endif @@ -1419,9 +1413,9 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val) } if (rs < 32) { - *val = VCPU_VSX_FPR(vcpu, rs, vsx_offset); + *val = kvmppc_get_vsx_fpr(vcpu, rs, vsx_offset); } else { - reg.vval = VCPU_VSX_VR(vcpu, rs - 32); + kvmppc_get_vsx_vr(vcpu, rs - 32, ®.vval); *val = reg.vsxval[vsx_offset]; } break; @@ -1438,10 +1432,10 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val) if (rs < 32) { dword_offset = vsx_offset / 2; word_offset = vsx_offset % 2; - reg.vsxval[0] = VCPU_VSX_FPR(vcpu, rs, dword_offset); + reg.vsxval[0] = kvmppc_get_vsx_fpr(vcpu, rs, dword_offset); *val = reg.vsx32val[word_offset]; } else { - reg.vval = VCPU_VSX_VR(vcpu, rs - 32); + kvmppc_get_vsx_vr(vcpu, rs - 32, ®.vval); *val = reg.vsx32val[vsx_offset]; } break; @@ -1556,7 +1550,7 @@ static int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val) if (vmx_offset == -1) return -1; - reg.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, ®.vval); *val = reg.vsxval[vmx_offset]; return result; @@ -1574,7 +1568,7 @@ static int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val) if (vmx_offset == -1) return -1; - reg.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, ®.vval); *val = reg.vsx32val[vmx_offset]; return result; @@ -1592,7 +1586,7 @@ static int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val) if (vmx_offset == -1) return -1; - reg.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, ®.vval); *val = reg.vsx16val[vmx_offset]; return result; @@ -1610,7 +1604,7 @@ static int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val) if (vmx_offset == -1) return -1; - reg.vval = VCPU_VSX_VR(vcpu, index); + kvmppc_get_vsx_vr(vcpu, index, ®.vval); *val = reg.vsx8val[vmx_offset]; return result; @@ -1719,17 +1713,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + kvmppc_get_vsx_vr(vcpu, reg->id - KVM_REG_PPC_VR0, &val.vval); break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + val = get_reg_val(reg->id, kvmppc_get_vscr(vcpu)); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + val = get_reg_val(reg->id, kvmppc_get_vrsave(vcpu)); break; #endif /* CONFIG_ALTIVEC */ default: @@ -1770,21 +1764,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + kvmppc_set_vsx_vr(vcpu, reg->id - KVM_REG_PPC_VR0, &val.vval); break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + kvmppc_set_vscr(vcpu, set_reg_val(reg->id, val)); break; case KVM_REG_PPC_VRSAVE: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + kvmppc_set_vrsave(vcpu, set_reg_val(reg->id, val)); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/kvm/test-guest-state-buffer.c b/arch/powerpc/kvm/test-guest-state-buffer.c new file mode 100644 index 000000000000..4720b8dc8837 --- /dev/null +++ b/arch/powerpc/kvm/test-guest-state-buffer.c @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/init.h> +#include <linux/log2.h> +#include <kunit/test.h> + +#include <asm/guest-state-buffer.h> + +static void test_creating_buffer(struct kunit *test) +{ + struct kvmppc_gs_buff *gsb; + size_t size = 0x100; + + gsb = kvmppc_gsb_new(size, 0, 0, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb->hdr); + + KUNIT_EXPECT_EQ(test, gsb->capacity, roundup_pow_of_two(size)); + KUNIT_EXPECT_EQ(test, gsb->len, sizeof(__be32)); + + kvmppc_gsb_free(gsb); +} + +static void test_adding_element(struct kunit *test) +{ + const struct kvmppc_gs_elem *head, *curr; + union { + __vector128 v; + u64 dw[2]; + } u; + int rem; + struct kvmppc_gs_buff *gsb; + size_t size = 0x1000; + int i, rc; + u64 data; + + gsb = kvmppc_gsb_new(size, 0, 0, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb); + + /* Single elements, direct use of __kvmppc_gse_put() */ + data = 0xdeadbeef; + rc = __kvmppc_gse_put(gsb, KVMPPC_GSID_GPR(0), 8, &data); + KUNIT_EXPECT_GE(test, rc, 0); + + head = kvmppc_gsb_data(gsb); + KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(head), KVMPPC_GSID_GPR(0)); + KUNIT_EXPECT_EQ(test, kvmppc_gse_len(head), 8); + data = 0; + memcpy(&data, kvmppc_gse_data(head), 8); + KUNIT_EXPECT_EQ(test, data, 0xdeadbeef); + + /* Multiple elements, simple wrapper */ + rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_GPR(1), 0xcafef00d); + KUNIT_EXPECT_GE(test, rc, 0); + + u.dw[0] = 0x1; + u.dw[1] = 0x2; + rc = kvmppc_gse_put_vector128(gsb, KVMPPC_GSID_VSRS(0), &u.v); + KUNIT_EXPECT_GE(test, rc, 0); + u.dw[0] = 0x0; + u.dw[1] = 0x0; + + kvmppc_gsb_for_each_elem(i, curr, gsb, rem) { + switch (i) { + case 0: + KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(curr), + KVMPPC_GSID_GPR(0)); + KUNIT_EXPECT_EQ(test, kvmppc_gse_len(curr), 8); + KUNIT_EXPECT_EQ(test, kvmppc_gse_get_be64(curr), + 0xdeadbeef); + break; + case 1: + KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(curr), + KVMPPC_GSID_GPR(1)); + KUNIT_EXPECT_EQ(test, kvmppc_gse_len(curr), 8); + KUNIT_EXPECT_EQ(test, kvmppc_gse_get_u64(curr), + 0xcafef00d); + break; + case 2: + KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(curr), + KVMPPC_GSID_VSRS(0)); + KUNIT_EXPECT_EQ(test, kvmppc_gse_len(curr), 16); + kvmppc_gse_get_vector128(curr, &u.v); + KUNIT_EXPECT_EQ(test, u.dw[0], 0x1); + KUNIT_EXPECT_EQ(test, u.dw[1], 0x2); + break; + } + } + KUNIT_EXPECT_EQ(test, i, 3); + + kvmppc_gsb_reset(gsb); + KUNIT_EXPECT_EQ(test, kvmppc_gsb_nelems(gsb), 0); + KUNIT_EXPECT_EQ(test, kvmppc_gsb_len(gsb), + sizeof(struct kvmppc_gs_header)); + + kvmppc_gsb_free(gsb); +} + +static void test_gs_parsing(struct kunit *test) +{ + struct kvmppc_gs_elem *gse; + struct kvmppc_gs_parser gsp = { 0 }; + struct kvmppc_gs_buff *gsb; + size_t size = 0x1000; + u64 tmp1, tmp2; + + gsb = kvmppc_gsb_new(size, 0, 0, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb); + + tmp1 = 0xdeadbeefull; + kvmppc_gse_put_u64(gsb, KVMPPC_GSID_GPR(0), tmp1); + + KUNIT_EXPECT_GE(test, kvmppc_gse_parse(&gsp, gsb), 0); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_GPR(0)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gse); + + tmp2 = kvmppc_gse_get_u64(gse); + KUNIT_EXPECT_EQ(test, tmp2, 0xdeadbeefull); + + kvmppc_gsb_free(gsb); +} + +static void test_gs_bitmap(struct kunit *test) +{ + struct kvmppc_gs_bitmap gsbm = { 0 }; + struct kvmppc_gs_bitmap gsbm1 = { 0 }; + struct kvmppc_gs_bitmap gsbm2 = { 0 }; + u16 iden; + int i, j; + + i = 0; + for (u16 iden = KVMPPC_GSID_HOST_STATE_SIZE; + iden <= KVMPPC_GSID_PROCESS_TABLE; iden++) { + kvmppc_gsbm_set(&gsbm, iden); + kvmppc_gsbm_set(&gsbm1, iden); + KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden)); + kvmppc_gsbm_clear(&gsbm, iden); + KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden)); + i++; + } + + for (u16 iden = KVMPPC_GSID_RUN_INPUT; iden <= KVMPPC_GSID_VPA; + iden++) { + kvmppc_gsbm_set(&gsbm, iden); + kvmppc_gsbm_set(&gsbm1, iden); + KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden)); + kvmppc_gsbm_clear(&gsbm, iden); + KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden)); + i++; + } + + for (u16 iden = KVMPPC_GSID_GPR(0); iden <= KVMPPC_GSID_CTRL; iden++) { + kvmppc_gsbm_set(&gsbm, iden); + kvmppc_gsbm_set(&gsbm1, iden); + KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden)); + kvmppc_gsbm_clear(&gsbm, iden); + KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden)); + i++; + } + + for (u16 iden = KVMPPC_GSID_CR; iden <= KVMPPC_GSID_PSPB; iden++) { + kvmppc_gsbm_set(&gsbm, iden); + kvmppc_gsbm_set(&gsbm1, iden); + KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden)); + kvmppc_gsbm_clear(&gsbm, iden); + KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden)); + i++; + } + + for (u16 iden = KVMPPC_GSID_VSRS(0); iden <= KVMPPC_GSID_VSRS(63); + iden++) { + kvmppc_gsbm_set(&gsbm, iden); + kvmppc_gsbm_set(&gsbm1, iden); + KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden)); + kvmppc_gsbm_clear(&gsbm, iden); + KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden)); + i++; + } + + for (u16 iden = KVMPPC_GSID_HDAR; iden <= KVMPPC_GSID_ASDR; iden++) { + kvmppc_gsbm_set(&gsbm, iden); + kvmppc_gsbm_set(&gsbm1, iden); + KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden)); + kvmppc_gsbm_clear(&gsbm, iden); + KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden)); + i++; + } + + j = 0; + kvmppc_gsbm_for_each(&gsbm1, iden) + { + kvmppc_gsbm_set(&gsbm2, iden); + j++; + } + KUNIT_EXPECT_EQ(test, i, j); + KUNIT_EXPECT_MEMEQ(test, &gsbm1, &gsbm2, sizeof(gsbm1)); +} + +struct kvmppc_gs_msg_test1_data { + u64 a; + u32 b; + struct kvmppc_gs_part_table c; + struct kvmppc_gs_proc_table d; + struct kvmppc_gs_buff_info e; +}; + +static size_t test1_get_size(struct kvmppc_gs_msg *gsm) +{ + size_t size = 0; + u16 ids[] = { + KVMPPC_GSID_PARTITION_TABLE, + KVMPPC_GSID_PROCESS_TABLE, + KVMPPC_GSID_RUN_INPUT, + KVMPPC_GSID_GPR(0), + KVMPPC_GSID_CR, + }; + + for (int i = 0; i < ARRAY_SIZE(ids); i++) + size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i])); + return size; +} + +static int test1_fill_info(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + struct kvmppc_gs_msg_test1_data *data = gsm->data; + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_GPR(0))) + kvmppc_gse_put_u64(gsb, KVMPPC_GSID_GPR(0), data->a); + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_CR)) + kvmppc_gse_put_u32(gsb, KVMPPC_GSID_CR, data->b); + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_PARTITION_TABLE)) + kvmppc_gse_put_part_table(gsb, KVMPPC_GSID_PARTITION_TABLE, + data->c); + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_PROCESS_TABLE)) + kvmppc_gse_put_proc_table(gsb, KVMPPC_GSID_PARTITION_TABLE, + data->d); + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_INPUT)) + kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_INPUT, data->e); + + return 0; +} + +static int test1_refresh_info(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb) +{ + struct kvmppc_gs_parser gsp = { 0 }; + struct kvmppc_gs_msg_test1_data *data = gsm->data; + struct kvmppc_gs_elem *gse; + int rc; + + rc = kvmppc_gse_parse(&gsp, gsb); + if (rc < 0) + return rc; + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_GPR(0)); + if (gse) + data->a = kvmppc_gse_get_u64(gse); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_CR); + if (gse) + data->b = kvmppc_gse_get_u32(gse); + + return 0; +} + +static struct kvmppc_gs_msg_ops gs_msg_test1_ops = { + .get_size = test1_get_size, + .fill_info = test1_fill_info, + .refresh_info = test1_refresh_info, +}; + +static void test_gs_msg(struct kunit *test) +{ + struct kvmppc_gs_msg_test1_data test1_data = { + .a = 0xdeadbeef, + .b = 0x1, + }; + struct kvmppc_gs_msg *gsm; + struct kvmppc_gs_buff *gsb; + + gsm = kvmppc_gsm_new(&gs_msg_test1_ops, &test1_data, GSM_SEND, + GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm); + + gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb); + + kvmppc_gsm_include(gsm, KVMPPC_GSID_PARTITION_TABLE); + kvmppc_gsm_include(gsm, KVMPPC_GSID_PROCESS_TABLE); + kvmppc_gsm_include(gsm, KVMPPC_GSID_RUN_INPUT); + kvmppc_gsm_include(gsm, KVMPPC_GSID_GPR(0)); + kvmppc_gsm_include(gsm, KVMPPC_GSID_CR); + + kvmppc_gsm_fill_info(gsm, gsb); + + memset(&test1_data, 0, sizeof(test1_data)); + + kvmppc_gsm_refresh_info(gsm, gsb); + KUNIT_EXPECT_EQ(test, test1_data.a, 0xdeadbeef); + KUNIT_EXPECT_EQ(test, test1_data.b, 0x1); + + kvmppc_gsm_free(gsm); +} + +static struct kunit_case guest_state_buffer_testcases[] = { + KUNIT_CASE(test_creating_buffer), + KUNIT_CASE(test_adding_element), + KUNIT_CASE(test_gs_bitmap), + KUNIT_CASE(test_gs_parsing), + KUNIT_CASE(test_gs_msg), + {} +}; + +static struct kunit_suite guest_state_buffer_test_suite = { + .name = "guest_state_buffer_test", + .test_cases = guest_state_buffer_testcases, +}; + +kunit_test_suites(&guest_state_buffer_test_suite); + +MODULE_LICENSE("GPL"); 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/code-patching.c b/arch/powerpc/lib/code-patching.c index b00112d7ad46..c6ab46156cda 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -38,6 +38,7 @@ static int __patch_instruction(u32 *exec_addr, ppc_inst_t instr, u32 *patch_addr return 0; failed: + mb(); /* sync */ return -EPERM; } @@ -204,9 +205,6 @@ void __init poking_init(void) { int ret; - if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) - return; - if (mm_patch_enabled()) ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/text_poke_mm:online", @@ -309,10 +307,6 @@ static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr) err = __patch_instruction(addr, instr, patch_addr); - /* hwsync performed by __patch_instruction (sync) if successful */ - if (err) - mb(); /* sync */ - /* context synchronisation performed by __patch_instruction (isync or exception) */ stop_using_temp_mm(patching_mm, orig_mm); @@ -378,6 +372,144 @@ int patch_instruction(u32 *addr, ppc_inst_t instr) } NOKPROBE_SYMBOL(patch_instruction); +static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool repeat_instr) +{ + unsigned long start = (unsigned long)patch_addr; + + /* Repeat instruction */ + if (repeat_instr) { + ppc_inst_t instr = ppc_inst_read(code); + + if (ppc_inst_prefixed(instr)) { + u64 val = ppc_inst_as_ulong(instr); + + memset64((u64 *)patch_addr, val, len / 8); + } else { + u32 val = ppc_inst_val(instr); + + memset32(patch_addr, val, len / 4); + } + } else { + memcpy(patch_addr, code, len); + } + + smp_wmb(); /* smp write barrier */ + flush_icache_range(start, start + len); + return 0; +} + +/* + * A page is mapped and instructions that fit the page are patched. + * Assumes 'len' to be (PAGE_SIZE - offset_in_page(addr)) or below. + */ +static int __do_patch_instructions_mm(u32 *addr, u32 *code, size_t len, bool repeat_instr) +{ + struct mm_struct *patching_mm, *orig_mm; + unsigned long pfn = get_patch_pfn(addr); + unsigned long text_poke_addr; + spinlock_t *ptl; + u32 *patch_addr; + pte_t *pte; + int err; + + patching_mm = __this_cpu_read(cpu_patching_context.mm); + text_poke_addr = __this_cpu_read(cpu_patching_context.addr); + patch_addr = (u32 *)(text_poke_addr + offset_in_page(addr)); + + pte = get_locked_pte(patching_mm, text_poke_addr, &ptl); + if (!pte) + return -ENOMEM; + + __set_pte_at(patching_mm, text_poke_addr, pte, pfn_pte(pfn, PAGE_KERNEL), 0); + + /* order PTE update before use, also serves as the hwsync */ + asm volatile("ptesync" ::: "memory"); + + /* order context switch after arbitrary prior code */ + isync(); + + orig_mm = start_using_temp_mm(patching_mm); + + err = __patch_instructions(patch_addr, code, len, repeat_instr); + + /* context synchronisation performed by __patch_instructions */ + stop_using_temp_mm(patching_mm, orig_mm); + + pte_clear(patching_mm, text_poke_addr, pte); + /* + * ptesync to order PTE update before TLB invalidation done + * by radix__local_flush_tlb_page_psize (in _tlbiel_va) + */ + local_flush_tlb_page_psize(patching_mm, text_poke_addr, mmu_virtual_psize); + + pte_unmap_unlock(pte, ptl); + + return err; +} + +/* + * A page is mapped and instructions that fit the page are patched. + * Assumes 'len' to be (PAGE_SIZE - offset_in_page(addr)) or below. + */ +static int __do_patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr) +{ + unsigned long pfn = get_patch_pfn(addr); + unsigned long text_poke_addr; + u32 *patch_addr; + pte_t *pte; + int err; + + text_poke_addr = (unsigned long)__this_cpu_read(cpu_patching_context.addr) & PAGE_MASK; + patch_addr = (u32 *)(text_poke_addr + offset_in_page(addr)); + + pte = __this_cpu_read(cpu_patching_context.pte); + __set_pte_at(&init_mm, text_poke_addr, pte, pfn_pte(pfn, PAGE_KERNEL), 0); + /* See ptesync comment in radix__set_pte_at() */ + if (radix_enabled()) + asm volatile("ptesync" ::: "memory"); + + err = __patch_instructions(patch_addr, code, len, repeat_instr); + + pte_clear(&init_mm, text_poke_addr, pte); + flush_tlb_kernel_range(text_poke_addr, text_poke_addr + PAGE_SIZE); + + return err; +} + +/* + * Patch 'addr' with 'len' bytes of instructions from 'code'. + * + * If repeat_instr is true, the same instruction is filled for + * 'len' bytes. + */ +int patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr) +{ + while (len > 0) { + unsigned long flags; + size_t plen; + int err; + + plen = min_t(size_t, PAGE_SIZE - offset_in_page(addr), len); + + local_irq_save(flags); + if (mm_patch_enabled()) + err = __do_patch_instructions_mm(addr, code, plen, repeat_instr); + else + err = __do_patch_instructions(addr, code, plen, repeat_instr); + local_irq_restore(flags); + if (err) + return err; + + len -= plen; + addr = (u32 *)((unsigned long)addr + plen); + if (!repeat_instr) + code = (u32 *)((unsigned long)code + plen); + } + + return 0; +} +NOKPROBE_SYMBOL(patch_instructions); + int patch_branch(u32 *addr, unsigned long target, int flags) { ppc_inst_t instr; diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c index 253620979d0c..5de4dd549f6e 100644 --- a/arch/powerpc/lib/qspinlock.c +++ b/arch/powerpc/lib/qspinlock.c @@ -16,7 +16,8 @@ struct qnode { struct qnode *next; struct qspinlock *lock; int cpu; - int yield_cpu; + u8 sleepy; /* 1 if the previous vCPU was preempted or + * if the previous node was sleepy */ u8 locked; /* 1 if lock acquired */ }; @@ -43,7 +44,7 @@ static bool pv_sleepy_lock_sticky __read_mostly = false; static u64 pv_sleepy_lock_interval_ns __read_mostly = 0; static int pv_sleepy_lock_factor __read_mostly = 256; static bool pv_yield_prev __read_mostly = true; -static bool pv_yield_propagate_owner __read_mostly = true; +static bool pv_yield_sleepy_owner __read_mostly = true; static bool pv_prod_head __read_mostly = false; static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes); @@ -247,22 +248,18 @@ static __always_inline void seen_sleepy_lock(void) this_cpu_write(sleepy_lock_seen_clock, sched_clock()); } -static __always_inline void seen_sleepy_node(struct qspinlock *lock, u32 val) +static __always_inline void seen_sleepy_node(void) { if (pv_sleepy_lock) { if (pv_sleepy_lock_interval_ns) this_cpu_write(sleepy_lock_seen_clock, sched_clock()); - if (val & _Q_LOCKED_VAL) { - if (!(val & _Q_SLEEPY_VAL)) - try_set_sleepy(lock, val); - } + /* Don't set sleepy because we likely have a stale val */ } } -static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val) +static struct qnode *get_tail_qnode(struct qspinlock *lock, int prev_cpu) { - int cpu = decode_tail_cpu(val); - struct qnodes *qnodesp = per_cpu_ptr(&qnodes, cpu); + struct qnodes *qnodesp = per_cpu_ptr(&qnodes, prev_cpu); int idx; /* @@ -353,74 +350,66 @@ static __always_inline bool yield_head_to_locked_owner(struct qspinlock *lock, u return __yield_to_locked_owner(lock, val, paravirt, mustq); } -static __always_inline void propagate_yield_cpu(struct qnode *node, u32 val, int *set_yield_cpu, bool paravirt) +static __always_inline void propagate_sleepy(struct qnode *node, u32 val, bool paravirt) { struct qnode *next; int owner; if (!paravirt) return; - if (!pv_yield_propagate_owner) - return; - - owner = get_owner_cpu(val); - if (*set_yield_cpu == owner) + if (!pv_yield_sleepy_owner) return; next = READ_ONCE(node->next); if (!next) return; - if (vcpu_is_preempted(owner)) { - next->yield_cpu = owner; - *set_yield_cpu = owner; - } else if (*set_yield_cpu != -1) { - next->yield_cpu = owner; - *set_yield_cpu = owner; - } + if (next->sleepy) + return; + + owner = get_owner_cpu(val); + if (vcpu_is_preempted(owner)) + next->sleepy = 1; } /* Called inside spin_begin() */ -static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode *node, u32 val, bool paravirt) +static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode *node, int prev_cpu, bool paravirt) { - int prev_cpu = decode_tail_cpu(val); u32 yield_count; - int yield_cpu; bool preempted = false; if (!paravirt) goto relax; - if (!pv_yield_propagate_owner) - goto yield_prev; - - yield_cpu = READ_ONCE(node->yield_cpu); - if (yield_cpu == -1) { - /* Propagate back the -1 CPU */ - if (node->next && node->next->yield_cpu != -1) - node->next->yield_cpu = yield_cpu; + if (!pv_yield_sleepy_owner) goto yield_prev; - } - - yield_count = yield_count_of(yield_cpu); - if ((yield_count & 1) == 0) - goto yield_prev; /* owner vcpu is running */ - spin_end(); - - preempted = true; - seen_sleepy_node(lock, val); + /* + * If the previous waiter was preempted it might not be able to + * propagate sleepy to us, so check the lock in that case too. + */ + if (node->sleepy || vcpu_is_preempted(prev_cpu)) { + u32 val = READ_ONCE(lock->val); - smp_rmb(); + if (val & _Q_LOCKED_VAL) { + if (node->next && !node->next->sleepy) { + /* + * Propagate sleepy to next waiter. Only if + * owner is preempted, which allows the queue + * to become "non-sleepy" if vCPU preemption + * ceases to occur, even if the lock remains + * highly contended. + */ + if (vcpu_is_preempted(get_owner_cpu(val))) + node->next->sleepy = 1; + } - if (yield_cpu == node->yield_cpu) { - if (node->next && node->next->yield_cpu != yield_cpu) - node->next->yield_cpu = yield_cpu; - yield_to_preempted(yield_cpu, yield_count); - spin_begin(); - return preempted; + preempted = yield_to_locked_owner(lock, val, paravirt); + if (preempted) + return preempted; + } + node->sleepy = false; } - spin_begin(); yield_prev: if (!pv_yield_prev) @@ -433,7 +422,7 @@ yield_prev: spin_end(); preempted = true; - seen_sleepy_node(lock, val); + seen_sleepy_node(); smp_rmb(); /* See __yield_to_locked_owner comment */ @@ -543,7 +532,6 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b bool sleepy = false; bool mustq = false; int idx; - int set_yield_cpu = -1; int iters = 0; BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS)); @@ -567,7 +555,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b node->next = NULL; node->lock = lock; node->cpu = smp_processor_id(); - node->yield_cpu = -1; + node->sleepy = 0; node->locked = 0; tail = encode_tail_cpu(node->cpu); @@ -584,7 +572,8 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b * head of the waitqueue. */ if (old & _Q_TAIL_CPU_MASK) { - struct qnode *prev = get_tail_qnode(lock, old); + int prev_cpu = decode_tail_cpu(old); + struct qnode *prev = get_tail_qnode(lock, prev_cpu); /* Link @node into the waitqueue. */ WRITE_ONCE(prev->next, node); @@ -594,16 +583,12 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b while (!READ_ONCE(node->locked)) { spec_barrier(); - if (yield_to_prev(lock, node, old, paravirt)) + if (yield_to_prev(lock, node, prev_cpu, paravirt)) seen_preempted = true; } spec_barrier(); spin_end(); - /* Clear out stale propagated yield_cpu */ - if (paravirt && pv_yield_propagate_owner && node->yield_cpu != -1) - node->yield_cpu = -1; - smp_rmb(); /* acquire barrier for the mcs lock */ /* @@ -645,7 +630,7 @@ again: } } - propagate_yield_cpu(node, val, &set_yield_cpu, paravirt); + propagate_sleepy(node, val, paravirt); preempted = yield_head_to_locked_owner(lock, val, paravirt); if (!maybe_stealers) continue; @@ -949,21 +934,21 @@ static int pv_yield_prev_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_prev, pv_yield_prev_get, pv_yield_prev_set, "%llu\n"); -static int pv_yield_propagate_owner_set(void *data, u64 val) +static int pv_yield_sleepy_owner_set(void *data, u64 val) { - pv_yield_propagate_owner = !!val; + pv_yield_sleepy_owner = !!val; return 0; } -static int pv_yield_propagate_owner_get(void *data, u64 *val) +static int pv_yield_sleepy_owner_get(void *data, u64 *val) { - *val = pv_yield_propagate_owner; + *val = pv_yield_sleepy_owner; return 0; } -DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_propagate_owner, pv_yield_propagate_owner_get, pv_yield_propagate_owner_set, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_sleepy_owner, pv_yield_sleepy_owner_get, pv_yield_sleepy_owner_set, "%llu\n"); static int pv_prod_head_set(void *data, u64 val) { @@ -995,7 +980,7 @@ static __init int spinlock_debugfs_init(void) debugfs_create_file("qspl_pv_sleepy_lock_interval_ns", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock_interval_ns); debugfs_create_file("qspl_pv_sleepy_lock_factor", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock_factor); debugfs_create_file("qspl_pv_yield_prev", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_prev); - debugfs_create_file("qspl_pv_yield_propagate_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_propagate_owner); + debugfs_create_file("qspl_pv_yield_sleepy_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_sleepy_owner); debugfs_create_file("qspl_pv_prod_head", 0600, arch_debugfs_dir, NULL, &fops_pv_prod_head); } 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/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index 8b804e1a9fa4..4ed0efd03db5 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -36,8 +36,9 @@ /* * Load a PTE into the hash table, if possible. - * The address is in r4, and r3 contains an access flag: - * _PAGE_RW (0x400) if a write. + * The address is in r4, and r3 contains required access flags: + * - For ISI: _PAGE_PRESENT | _PAGE_EXEC + * - For DSI: _PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE if a write. * r9 contains the SRR1 value, from which we use the MSR_PR bit. * SPRG_THREAD contains the physical address of the current task's thread. * @@ -67,12 +68,16 @@ _GLOBAL(hash_page) lis r0, TASK_SIZE@h /* check if kernel address */ cmplw 0,r4,r0 mfspr r8,SPRN_SPRG_THREAD /* current task's THREAD (phys) */ - ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */ lwz r5,PGDIR(r8) /* virt page-table root */ blt+ 112f /* assume user more likely */ lis r5,swapper_pg_dir@ha /* if kernel address, use */ + andi. r0,r9,MSR_PR /* Check usermode */ addi r5,r5,swapper_pg_dir@l /* kernel page table */ - rlwimi r3,r9,32-12,29,29 /* MSR_PR -> _PAGE_USER */ +#ifdef CONFIG_SMP + bne- .Lhash_page_out /* return if usermode */ +#else + bnelr- +#endif 112: tophys(r5, r5) #ifndef CONFIG_PTE_64BIT rlwimi r5,r4,12,20,29 /* insert top 10 bits of address */ @@ -113,15 +118,15 @@ _GLOBAL(hash_page) lwarx r6,0,r8 /* get linux-style pte, flag word */ #ifdef CONFIG_PPC_KUAP mfsrin r5,r4 - rlwinm r0,r9,28,_PAGE_RW /* MSR[PR] => _PAGE_RW */ - rlwinm r5,r5,12,_PAGE_RW /* Ks => _PAGE_RW */ + rlwinm r0,r9,28,_PAGE_WRITE /* MSR[PR] => _PAGE_WRITE */ + rlwinm r5,r5,12,_PAGE_WRITE /* Ks => _PAGE_WRITE */ andc r5,r5,r0 /* Ks & ~MSR[PR] */ - andc r5,r6,r5 /* Clear _PAGE_RW when Ks = 1 && MSR[PR] = 0 */ + andc r5,r6,r5 /* Clear _PAGE_WRITE when Ks = 1 && MSR[PR] = 0 */ andc. r5,r3,r5 /* check access & ~permission */ #else andc. r5,r3,r6 /* check access & ~permission */ #endif - rlwinm r0,r3,32-3,24,24 /* _PAGE_RW access -> _PAGE_DIRTY */ + rlwinm r0,r3,32-3,24,24 /* _PAGE_WRITE access -> _PAGE_DIRTY */ ori r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE #ifdef CONFIG_SMP bne- .Lhash_page_out /* return if access not permitted */ @@ -307,12 +312,15 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64) __REF _GLOBAL(create_hpte) /* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */ - rlwinm r8,r5,32-9,30,30 /* _PAGE_RW -> PP msb */ + lis r0, TASK_SIZE@h + rlwinm r5,r5,0,~3 /* Clear PP bits */ + cmplw r4,r0 + rlwinm r8,r5,32-9,30,30 /* _PAGE_WRITE -> PP msb */ rlwinm r0,r5,32-6,30,30 /* _PAGE_DIRTY -> PP msb */ and r8,r8,r0 /* writable if _RW & _DIRTY */ - rlwimi r5,r5,32-1,30,30 /* _PAGE_USER -> PP msb */ - rlwimi r5,r5,32-2,31,31 /* _PAGE_USER -> PP lsb */ - ori r8,r8,0xe04 /* clear out reserved bits */ + bge- 1f /* Kernelspace ? Skip */ + ori r5,r5,3 /* Userspace ? PP = 3 */ +1: ori r8,r8,0xe04 /* clear out reserved bits */ andc r8,r5,r8 /* PP = user? (rw&dirty? 1: 3): 0 */ BEGIN_FTR_SECTION rlwinm r8,r8,0,~_PAGE_COHERENT /* clear M (coherence not required) */ diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 850783cfa9c7..5445587bfe84 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -127,7 +127,7 @@ static void setibat(int index, unsigned long virt, phys_addr_t phys, wimgxpp = (flags & _PAGE_COHERENT) | (_PAGE_EXEC ? BPP_RX : BPP_XX); bat[0].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */ bat[0].batl = BAT_PHYS_ADDR(phys) | wimgxpp; - if (flags & _PAGE_USER) + if (!is_kernel_addr(virt)) bat[0].batu |= 1; /* Vp = 1 */ } @@ -277,10 +277,10 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, /* Do DBAT first */ wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED); - wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX; + wimgxpp |= (flags & _PAGE_WRITE) ? BPP_RW : BPP_RX; bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */ bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp; - if (flags & _PAGE_USER) + if (!is_kernel_addr(virt)) bat[1].batu |= 1; /* Vp = 1 */ if (flags & _PAGE_GUARDED) { /* G bit must be zero in IBATs */ 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/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c index 3bc0eb21b2a0..5a2e512e96db 100644 --- a/arch/powerpc/mm/book3s64/hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/hugetlbpage.c @@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { + unsigned long psize; if (radix_enabled()) return radix__huge_ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + + psize = huge_page_size(hstate_vma(vma)); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } void __init hugetlbpage_init_defaultsize(void) diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c index d19fb1f3007d..c0e8d597e4cb 100644 --- a/arch/powerpc/mm/book3s64/iommu_api.c +++ b/arch/powerpc/mm/book3s64/iommu_api.c @@ -97,7 +97,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } mmap_read_lock(mm); - chunk = (1UL << (PAGE_SHIFT + MAX_ORDER)) / + chunk = (1UL << (PAGE_SHIFT + MAX_PAGE_ORDER)) / sizeof(struct vm_area_struct *); chunk = min(chunk, entries); for (entry = 0; entry < entries; entry += chunk) { diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 8f8a62d3ff4d..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? @@ -635,12 +637,10 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags) unsigned long prot; /* Radix supports execute-only, but protection_map maps X -> RX */ - if (radix_enabled() && ((vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)) { - prot = pgprot_val(PAGE_EXECONLY); - } else { - prot = pgprot_val(protection_map[vm_flags & - (VM_ACCESS_FLAGS | VM_SHARED)]); - } + if (!radix_enabled() && ((vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)) + vm_flags |= VM_READ; + + prot = pgprot_val(protection_map[vm_flags & (VM_ACCESS_FLAGS | VM_SHARED)]); if (vm_flags & VM_SAO) prot |= _PAGE_SAO; 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/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index 17075c78d4bc..35fd2a95be24 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -47,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, pte_t old_pte, pte_t pte) { struct mm_struct *mm = vma->vm_mm; + unsigned long psize = huge_page_size(hstate_vma(vma)); /* * POWER9 NMMU must flush the TLB after clearing the PTE before @@ -58,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, atomic_read(&mm->context.copros) > 0) radix__flush_hugetlb_page(vma, addr); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 39acc2cbab4c..9e1f6558d026 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -1212,14 +1212,7 @@ void radix__tlb_flush(struct mmu_gather *tlb) smp_mb(); /* see radix__flush_tlb_mm */ exit_flush_lazy_tlbs(mm); - _tlbiel_pid(mm->context.id, RIC_FLUSH_ALL); - - /* - * It should not be possible to have coprocessors still - * attached here. - */ - if (WARN_ON_ONCE(atomic_read(&mm->context.copros) > 0)) - __flush_all_mm(mm, true); + __flush_all_mm(mm, true); preempt_enable(); } else { diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 2369d1bf2411..fde7790277f7 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -67,7 +67,7 @@ static int drmem_update_dt_v1(struct device_node *memory, struct property *new_prop; struct of_drconf_cell_v1 *dr_cell; struct drmem_lmb *lmb; - u32 *p; + __be32 *p; new_prop = clone_property(prop, prop->length); if (!new_prop) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index b1723094d464..53335ae21a40 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -266,14 +266,15 @@ static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *vma } /* - * VM_READ, VM_WRITE and VM_EXEC all imply read permissions, as - * defined in protection_map[]. Read faults can only be caused by - * a PROT_NONE mapping, or with a PROT_EXEC-only mapping on Radix. + * VM_READ, VM_WRITE and VM_EXEC may imply read permissions, as + * defined in protection_map[]. In that case Read faults can only be + * caused by a PROT_NONE mapping. However a non exec access on a + * VM_EXEC only mapping is invalid anyway, so report it as such. */ if (unlikely(!vma_is_accessible(vma))) return true; - if (unlikely(radix_enabled() && ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_EXEC))) + if ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_EXEC) return true; /* @@ -496,6 +497,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index f7c683b672c1..0a540b37aab6 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -615,7 +615,7 @@ void __init gigantic_hugetlb_cma_reserve(void) order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT; if (order) { - VM_WARN_ON(order <= MAX_ORDER); + VM_WARN_ON(order <= MAX_PAGE_ORDER); hugetlb_cma_reserve(order); } } 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/init_32.c b/arch/powerpc/mm/init_32.c index d8adc452f431..4e71dfe7d026 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -39,6 +39,7 @@ #include <asm/hugetlb.h> #include <asm/kup.h> #include <asm/kasan.h> +#include <asm/fixmap.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c index 705e8e8ffde4..7b0afcabd89f 100644 --- a/arch/powerpc/mm/ioremap.c +++ b/arch/powerpc/mm/ioremap.c @@ -50,10 +50,6 @@ void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long flags) if (pte_write(pte)) pte = pte_mkdirty(pte); - /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */ - pte = pte_exprotect(pte); - pte = pte_mkprivileged(pte); - if (iowa_is_active()) return iowa_ioremap(addr, size, pte_pgprot(pte), caller); return __ioremap_caller(addr, size, pte_pgprot(pte), caller); @@ -66,7 +62,7 @@ int early_ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long i; for (i = 0; i < size; i += PAGE_SIZE) { - int err = map_kernel_page(ea + i, pa + i, prot); + int err = map_kernel_page(ea + i, pa + i, pgprot_nx(prot)); if (WARN_ON_ONCE(err)) /* Should clean up */ return err; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8b121df7b08f..3a440004b97d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -26,6 +26,7 @@ #include <asm/ftrace.h> #include <asm/code-patching.h> #include <asm/setup.h> +#include <asm/fixmap.h> #include <mm/mmu_decl.h> @@ -34,18 +35,18 @@ unsigned long long memory_limit; unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); -pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot) +pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size, + pgprot_t vma_prot) { if (ppc_md.phys_mem_access_prot) - return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot); + return ppc_md.phys_mem_access_prot(pfn, size, vma_prot); if (!page_is_ram(pfn)) vma_prot = pgprot_noncached(vma_prot); return vma_prot; } -EXPORT_SYMBOL(phys_mem_access_prot); +EXPORT_SYMBOL(__phys_mem_access_prot); #ifdef CONFIG_MEMORY_HOTPLUG static DEFINE_MUTEX(linear_mapping_mutex); @@ -288,7 +289,6 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_pfn); kasan_late_init(); 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/mm/nohash/40x.c b/arch/powerpc/mm/nohash/40x.c index 3684d6e570fb..e835e80c09db 100644 --- a/arch/powerpc/mm/nohash/40x.c +++ b/arch/powerpc/mm/nohash/40x.c @@ -48,20 +48,25 @@ */ void __init MMU_init_hw(void) { + int i; + unsigned long zpr; + /* * The Zone Protection Register (ZPR) defines how protection will - * be applied to every page which is a member of a given zone. At - * present, we utilize only two of the 4xx's zones. + * be applied to every page which is a member of a given zone. * The zone index bits (of ZSEL) in the PTE are used for software - * indicators, except the LSB. For user access, zone 1 is used, - * for kernel access, zone 0 is used. We set all but zone 1 - * to zero, allowing only kernel access as indicated in the PTE. - * For zone 1, we set a 01 binary (a value of 10 will not work) + * indicators. We use the 4 upper bits of virtual address to select + * the zone. We set all zones above TASK_SIZE to zero, allowing + * only kernel access as indicated in the PTE. For zones below + * TASK_SIZE, we set a 01 binary (a value of 10 will not work) * to allow user access as indicated in the PTE. This also allows * kernel access as indicated in the PTE. */ - mtspr(SPRN_ZPR, 0x10000000); + for (i = 0, zpr = 0; i < TASK_SIZE >> 28; i++) + zpr |= 1 << (30 - i * 2); + + mtspr(SPRN_ZPR, zpr); flush_instruction_cache(); diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index dbbfe897455d..6be6421086ed 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -10,6 +10,8 @@ #include <linux/memblock.h> #include <linux/hugetlb.h> +#include <asm/fixmap.h> + #include <mm/mmu_decl.h> #define IMMR_SIZE (FIX_IMMR_SIZE << PAGE_SHIFT) @@ -91,7 +93,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa, if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot))) return -EINVAL; - set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot))); + set_huge_pte_at(&init_mm, va, ptep, + pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize); return 0; } diff --git a/arch/powerpc/mm/nohash/book3e_pgtable.c b/arch/powerpc/mm/nohash/book3e_pgtable.c index b80fc4a91a53..1c5e4ecbebeb 100644 --- a/arch/powerpc/mm/nohash/book3e_pgtable.c +++ b/arch/powerpc/mm/nohash/book3e_pgtable.c @@ -71,7 +71,7 @@ static void __init *early_alloc_pgtable(unsigned long size) * map_kernel_page adds an entry to the ioremap page table * and adds an entry to the HPT, possibly bolting it */ -int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot) +int __ref map_kernel_page(unsigned long ea, phys_addr_t pa, pgprot_t prot) { pgd_t *pgdp; p4d_t *p4dp; diff --git a/arch/powerpc/mm/nohash/e500.c b/arch/powerpc/mm/nohash/e500.c index 40a4e69ae1a9..921c3521ec11 100644 --- a/arch/powerpc/mm/nohash/e500.c +++ b/arch/powerpc/mm/nohash/e500.c @@ -117,15 +117,15 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys, TLBCAM[index].MAS2 |= (flags & _PAGE_ENDIAN) ? MAS2_E : 0; TLBCAM[index].MAS3 = (phys & MAS3_RPN) | MAS3_SR; - TLBCAM[index].MAS3 |= (flags & _PAGE_RW) ? MAS3_SW : 0; + TLBCAM[index].MAS3 |= (flags & _PAGE_WRITE) ? MAS3_SW : 0; if (mmu_has_feature(MMU_FTR_BIG_PHYS)) TLBCAM[index].MAS7 = (u64)phys >> 32; /* Below is unlikely -- only for large user pages or similar */ - if (pte_user(__pte(flags))) { + if (!is_kernel_addr(virt)) { TLBCAM[index].MAS3 |= MAS3_UR; TLBCAM[index].MAS3 |= (flags & _PAGE_EXEC) ? MAS3_UX : 0; - TLBCAM[index].MAS3 |= (flags & _PAGE_RW) ? MAS3_UW : 0; + TLBCAM[index].MAS3 |= (flags & _PAGE_WRITE) ? MAS3_UW : 0; } else { TLBCAM[index].MAS3 |= (flags & _PAGE_EXEC) ? MAS3_SX : 0; } diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c index 6b30e40d4590..a134d28a0e4d 100644 --- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c +++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c @@ -178,8 +178,7 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte) * * This must always be called with the pte lock held. */ -void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, unsigned int nr) +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { if (is_vm_hugetlb_page(vma)) book3e_hugetlb_preload(vma, address, *ptep); diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 2fb3edafe9ab..b4f2786a7d2b 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -178,7 +178,7 @@ static void __init get_crash_kernel(void *fdt, unsigned long size) int ret; ret = parse_crashkernel(boot_command_line, size, &crash_size, - &crash_base); + &crash_base, NULL, NULL); if (ret != 0 || crash_size == 0) return; if (crash_base == 0) diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 3f86fd217690..a04ae4449a02 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -46,13 +46,13 @@ static inline int is_exec_fault(void) * and we avoid _PAGE_SPECIAL and cache inhibited pte. We also only do that * on userspace PTEs */ -static inline int pte_looks_normal(pte_t pte) +static inline int pte_looks_normal(pte_t pte, unsigned long addr) { if (pte_present(pte) && !pte_special(pte)) { if (pte_ci(pte)) return 0; - if (pte_user(pte)) + if (!is_kernel_addr(addr)) return 1; } return 0; @@ -79,11 +79,11 @@ static struct folio *maybe_pte_to_folio(pte_t pte) * support falls into the same category. */ -static pte_t set_pte_filter_hash(pte_t pte) +static pte_t set_pte_filter_hash(pte_t pte, unsigned long addr) { pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS); - if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) || - cpu_has_feature(CPU_FTR_NOEXECUTE))) { + if (pte_looks_normal(pte, addr) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) || + cpu_has_feature(CPU_FTR_NOEXECUTE))) { struct folio *folio = maybe_pte_to_folio(pte); if (!folio) return pte; @@ -97,15 +97,17 @@ static pte_t set_pte_filter_hash(pte_t pte) #else /* CONFIG_PPC_BOOK3S */ -static pte_t set_pte_filter_hash(pte_t pte) { return pte; } +static pte_t set_pte_filter_hash(pte_t pte, unsigned long addr) { return pte; } #endif /* CONFIG_PPC_BOOK3S */ /* Embedded type MMU with HW exec support. This is a bit more complicated * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so * instead we "filter out" the exec permission for non clean pages. + * + * This is also called once for the folio. So only work with folio->flags here. */ -static inline pte_t set_pte_filter(pte_t pte) +static inline pte_t set_pte_filter(pte_t pte, unsigned long addr) { struct folio *folio; @@ -113,10 +115,10 @@ static inline pte_t set_pte_filter(pte_t pte) return pte; if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) - return set_pte_filter_hash(pte); + return set_pte_filter_hash(pte, addr); /* No exec permission in the first place, move on */ - if (!pte_exec(pte) || !pte_looks_normal(pte)) + if (!pte_exec(pte) || !pte_looks_normal(pte, addr)) return pte; /* If you set _PAGE_EXEC on weird pages you're on your own */ @@ -190,29 +192,39 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { - /* - * Make sure hardware valid bit is not set. We don't do - * tlb flush for this update. - */ - VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep)); /* Note: mm->context.id might not yet have been assigned as * this context might not have been activated yet when this - * is called. + * is called. Filter the pte value and use the filtered value + * to setup all the ptes in the range. */ - pte = set_pte_filter(pte); + pte = set_pte_filter(pte, addr); - /* Perform the setting of the PTE */ - arch_enter_lazy_mmu_mode(); + /* + * We don't need to call arch_enter/leave_lazy_mmu_mode() + * because we expect set_ptes to be only be used on not present + * and not hw_valid ptes. Hence there is no translation cache flush + * involved that need to be batched. + */ for (;;) { + + /* + * Make sure hardware valid bit is not set. We don't do + * tlb flush for this update. + */ + VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep)); + + /* Perform the setting of the PTE */ __set_pte_at(mm, addr, ptep, pte, 0); if (--nr == 0) break; ptep++; - pte = __pte(pte_val(pte) + (1UL << PTE_RPN_SHIFT)); addr += PAGE_SIZE; + /* + * increment the pfn. + */ + pte = pfn_pte(pte_pfn(pte) + 1, pte_pgprot((pte))); } - arch_leave_lazy_mmu_mode(); } void unmap_kernel_page(unsigned long va) @@ -288,7 +300,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, } #if defined(CONFIG_PPC_8xx) -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned long sz) { pmd_t *pmd = pmd_off(mm, addr); pte_basic_t val; @@ -301,7 +314,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_ */ VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep)); - pte = set_pte_filter(pte); + pte = set_pte_filter(pte, addr); val = pte_val(pte); @@ -492,7 +505,7 @@ const pgprot_t protection_map[16] = { [VM_READ] = PAGE_READONLY, [VM_WRITE] = PAGE_COPY, [VM_WRITE | VM_READ] = PAGE_COPY, - [VM_EXEC] = PAGE_READONLY_X, + [VM_EXEC] = PAGE_EXECONLY_X, [VM_EXEC | VM_READ] = PAGE_READONLY_X, [VM_EXEC | VM_WRITE] = PAGE_COPY_X, [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_X, @@ -500,7 +513,7 @@ const pgprot_t protection_map[16] = { [VM_SHARED | VM_READ] = PAGE_READONLY, [VM_SHARED | VM_WRITE] = PAGE_SHARED, [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, - [VM_SHARED | VM_EXEC] = PAGE_READONLY_X, + [VM_SHARED | VM_EXEC] = PAGE_EXECONLY_X, [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_X, [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_X, [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_X diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c index fac932eb8f9a..b5c79b11ea3c 100644 --- a/arch/powerpc/mm/ptdump/8xx.c +++ b/arch/powerpc/mm/ptdump/8xx.c @@ -21,11 +21,6 @@ static const struct flag_info flag_array[] = { .set = "huge", .clear = " ", }, { - .mask = _PAGE_SH, - .val = 0, - .set = "user", - .clear = " ", - }, { .mask = _PAGE_RO | _PAGE_NA, .val = 0, .set = "rw", diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c index f884760ca5cf..39c30c62b7ea 100644 --- a/arch/powerpc/mm/ptdump/shared.c +++ b/arch/powerpc/mm/ptdump/shared.c @@ -11,15 +11,15 @@ static const struct flag_info flag_array[] = { { - .mask = _PAGE_USER, - .val = _PAGE_USER, - .set = "user", - .clear = " ", + .mask = _PAGE_READ, + .val = 0, + .set = " ", + .clear = "r", }, { - .mask = _PAGE_RW, + .mask = _PAGE_WRITE, .val = 0, - .set = "r ", - .clear = "rw", + .set = " ", + .clear = "w", }, { .mask = _PAGE_EXEC, .val = _PAGE_EXEC, diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 72b7bb34fade..cdea5dccaefe 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -36,9 +36,6 @@ EMIT(PPC_RAW_BRANCH(offset)); \ } while (0) -/* bl (unconditional 'branch' with link) */ -#define PPC_BL(dest) EMIT(PPC_RAW_BL((dest) - (unsigned long)(image + ctx->idx))) - /* "cond" here covers BO:BI fields. */ #define PPC_BCC_SHORT(cond, dest) \ do { \ @@ -147,12 +144,6 @@ struct codegen_context { #define BPF_FIXUP_LEN 2 /* Two instructions => 8 bytes */ #endif -static inline void bpf_flush_icache(void *start, void *end) -{ - smp_wmb(); /* smp write barrier */ - flush_icache_range((unsigned long)start, (unsigned long)end); -} - static inline bool bpf_is_seen_register(struct codegen_context *ctx, int i) { return ctx->seen & (1 << (31 - i)); @@ -169,16 +160,17 @@ static inline void bpf_clear_seen_register(struct codegen_context *ctx, int i) } void bpf_jit_init_reg_mapping(struct codegen_context *ctx); -int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func); -int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, +int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func); +int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx, u32 *addrs, int pass, bool extra_pass); void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx); void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx); void bpf_jit_realloc_regs(struct codegen_context *ctx); int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr); -int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx, - int insn_idx, int jmp_off, int dst_reg); +int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass, + struct codegen_context *ctx, int insn_idx, + int jmp_off, int dst_reg); #endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 37043dfc1add..0f9a21783329 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -13,9 +13,13 @@ #include <linux/netdevice.h> #include <linux/filter.h> #include <linux/if_vlan.h> -#include <asm/kprobes.h> +#include <linux/kernel.h> +#include <linux/memory.h> #include <linux/bpf.h> +#include <asm/kprobes.h> +#include <asm/code-patching.h> + #include "bpf_jit.h" static void bpf_jit_fill_ill_insns(void *area, unsigned int size) @@ -39,10 +43,13 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, return 0; } -struct powerpc64_jit_data { - struct bpf_binary_header *header; +struct powerpc_jit_data { + /* address of rw header */ + struct bpf_binary_header *hdr; + /* address of ro final header */ + struct bpf_binary_header *fhdr; u32 *addrs; - u8 *image; + u8 *fimage; u32 proglen; struct codegen_context ctx; }; @@ -59,15 +66,18 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) u8 *image = NULL; u32 *code_base; u32 *addrs; - struct powerpc64_jit_data *jit_data; + struct powerpc_jit_data *jit_data; struct codegen_context cgctx; int pass; int flen; - struct bpf_binary_header *bpf_hdr; + struct bpf_binary_header *fhdr = NULL; + struct bpf_binary_header *hdr = NULL; struct bpf_prog *org_fp = fp; struct bpf_prog *tmp_fp; bool bpf_blinded = false; bool extra_pass = false; + u8 *fimage = NULL; + u32 *fcode_base; u32 extable_len; u32 fixup_len; @@ -97,9 +107,16 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) addrs = jit_data->addrs; if (addrs) { cgctx = jit_data->ctx; - image = jit_data->image; - bpf_hdr = jit_data->header; + /* + * JIT compiled to a writable location (image/code_base) first. + * It is then moved to the readonly final location (fimage/fcode_base) + * using instruction patching. + */ + fimage = jit_data->fimage; + fhdr = jit_data->fhdr; proglen = jit_data->proglen; + hdr = jit_data->hdr; + image = (void *)hdr + ((void *)fimage - (void *)fhdr); extra_pass = true; /* During extra pass, ensure index is reset before repopulating extable entries */ cgctx.exentry_idx = 0; @@ -119,7 +136,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) cgctx.stack_size = round_up(fp->aux->stack_depth, 16); /* Scouting faux-generate pass 0 */ - if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0, false)) { + if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) { /* We hit something illegal or unsupported. */ fp = org_fp; goto out_addrs; @@ -134,7 +151,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) */ if (cgctx.seen & SEEN_TAILCALL || !is_offset_in_branch_range((long)cgctx.idx * 4)) { cgctx.idx = 0; - if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0, false)) { + if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) { fp = org_fp; goto out_addrs; } @@ -146,9 +163,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) * update ctgtx.idx as it pretends to output instructions, then we can * calculate total size from idx. */ - bpf_jit_build_prologue(0, &cgctx); + bpf_jit_build_prologue(NULL, &cgctx); addrs[fp->len] = cgctx.idx * 4; - bpf_jit_build_epilogue(0, &cgctx); + bpf_jit_build_epilogue(NULL, &cgctx); fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4; extable_len = fp->aux->num_exentries * sizeof(struct exception_table_entry); @@ -156,17 +173,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) proglen = cgctx.idx * 4; alloclen = proglen + FUNCTION_DESCR_SIZE + fixup_len + extable_len; - bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4, bpf_jit_fill_ill_insns); - if (!bpf_hdr) { + fhdr = bpf_jit_binary_pack_alloc(alloclen, &fimage, 4, &hdr, &image, + bpf_jit_fill_ill_insns); + if (!fhdr) { fp = org_fp; goto out_addrs; } if (extable_len) - fp->aux->extable = (void *)image + FUNCTION_DESCR_SIZE + proglen + fixup_len; + fp->aux->extable = (void *)fimage + FUNCTION_DESCR_SIZE + proglen + fixup_len; skip_init_ctx: code_base = (u32 *)(image + FUNCTION_DESCR_SIZE); + fcode_base = (u32 *)(fimage + FUNCTION_DESCR_SIZE); /* Code generation passes 1-2 */ for (pass = 1; pass < 3; pass++) { @@ -174,8 +193,10 @@ skip_init_ctx: cgctx.idx = 0; cgctx.alt_exit_addr = 0; bpf_jit_build_prologue(code_base, &cgctx); - if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, pass, extra_pass)) { - bpf_jit_binary_free(bpf_hdr); + if (bpf_jit_build_body(fp, code_base, fcode_base, &cgctx, addrs, pass, + extra_pass)) { + bpf_arch_text_copy(&fhdr->size, &hdr->size, sizeof(hdr->size)); + bpf_jit_binary_pack_free(fhdr, hdr); fp = org_fp; goto out_addrs; } @@ -195,17 +216,19 @@ skip_init_ctx: #ifdef CONFIG_PPC64_ELF_ABI_V1 /* Function descriptor nastiness: Address + TOC */ - ((u64 *)image)[0] = (u64)code_base; + ((u64 *)image)[0] = (u64)fcode_base; ((u64 *)image)[1] = local_paca->kernel_toc; #endif - fp->bpf_func = (void *)image; + fp->bpf_func = (void *)fimage; fp->jited = 1; fp->jited_len = proglen + FUNCTION_DESCR_SIZE; - bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + bpf_hdr->size); if (!fp->is_func || extra_pass) { - bpf_jit_binary_lock_ro(bpf_hdr); + if (bpf_jit_binary_pack_finalize(fp, fhdr, hdr)) { + fp = org_fp; + goto out_addrs; + } bpf_prog_fill_jited_linfo(fp, addrs); out_addrs: kfree(addrs); @@ -215,8 +238,9 @@ out_addrs: jit_data->addrs = addrs; jit_data->ctx = cgctx; jit_data->proglen = proglen; - jit_data->image = image; - jit_data->header = bpf_hdr; + jit_data->fimage = fimage; + jit_data->fhdr = fhdr; + jit_data->hdr = hdr; } out: @@ -230,12 +254,13 @@ out: * The caller should check for (BPF_MODE(code) == BPF_PROBE_MEM) before calling * this function, as this only applies to BPF_PROBE_MEM, for now. */ -int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx, - int insn_idx, int jmp_off, int dst_reg) +int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass, + struct codegen_context *ctx, int insn_idx, int jmp_off, + int dst_reg) { off_t offset; unsigned long pc; - struct exception_table_entry *ex; + struct exception_table_entry *ex, *ex_entry; u32 *fixup; /* Populate extable entries only in the last pass */ @@ -246,9 +271,16 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct code WARN_ON_ONCE(ctx->exentry_idx >= fp->aux->num_exentries)) return -EINVAL; + /* + * Program is first written to image before copying to the + * final location (fimage). Accordingly, update in the image first. + * As all offsets used are relative, copying as is to the + * final location should be alright. + */ pc = (unsigned long)&image[insn_idx]; + ex = (void *)fp->aux->extable - (void *)fimage + (void *)image; - fixup = (void *)fp->aux->extable - + fixup = (void *)ex - (fp->aux->num_exentries * BPF_FIXUP_LEN * 4) + (ctx->exentry_idx * BPF_FIXUP_LEN * 4); @@ -259,18 +291,71 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct code fixup[BPF_FIXUP_LEN - 1] = PPC_RAW_BRANCH((long)(pc + jmp_off) - (long)&fixup[BPF_FIXUP_LEN - 1]); - ex = &fp->aux->extable[ctx->exentry_idx]; + ex_entry = &ex[ctx->exentry_idx]; - offset = pc - (long)&ex->insn; + offset = pc - (long)&ex_entry->insn; if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN)) return -ERANGE; - ex->insn = offset; + ex_entry->insn = offset; - offset = (long)fixup - (long)&ex->fixup; + offset = (long)fixup - (long)&ex_entry->fixup; if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN)) return -ERANGE; - ex->fixup = offset; + ex_entry->fixup = offset; ctx->exentry_idx++; return 0; } + +void *bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + int err; + + if (WARN_ON_ONCE(core_kernel_text((unsigned long)dst))) + return ERR_PTR(-EINVAL); + + mutex_lock(&text_mutex); + err = patch_instructions(dst, src, len, false); + mutex_unlock(&text_mutex); + + return err ? ERR_PTR(err) : dst; +} + +int bpf_arch_text_invalidate(void *dst, size_t len) +{ + u32 insn = BREAKPOINT_INSTRUCTION; + int ret; + + if (WARN_ON_ONCE(core_kernel_text((unsigned long)dst))) + return -EINVAL; + + mutex_lock(&text_mutex); + ret = patch_instructions(dst, &insn, len, true); + mutex_unlock(&text_mutex); + + return ret; +} + +void bpf_jit_free(struct bpf_prog *fp) +{ + if (fp->jited) { + struct powerpc_jit_data *jit_data = fp->aux->jit_data; + struct bpf_binary_header *hdr; + + /* + * If we fail the final pass of JIT (from jit_subprogs), + * the program may not be finalized yet. Call finalize here + * before freeing it. + */ + if (jit_data) { + bpf_jit_binary_pack_finalize(fp, jit_data->fhdr, jit_data->hdr); + kvfree(jit_data->addrs); + kfree(jit_data); + } + hdr = bpf_jit_binary_pack_hdr(fp); + bpf_jit_binary_pack_free(hdr, NULL); + WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); + } + + bpf_prog_unlock_free(fp); +} diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 7f91ea064c08..2f39c50ca729 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -200,12 +200,13 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); } -int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func) +/* Relative offset needs to be calculated based on final image location */ +int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func) { - s32 rel = (s32)func - (s32)(image + ctx->idx); + s32 rel = (s32)func - (s32)(fimage + ctx->idx); if (image && rel < 0x2000000 && rel >= -0x2000000) { - PPC_BL(func); + EMIT(PPC_RAW_BL(rel)); } else { /* Load function address into r0 */ EMIT(PPC_RAW_LIS(_R0, IMM_H(func))); @@ -278,7 +279,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o } /* Assemble the body code between the prologue & epilogue */ -int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, +int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx, u32 *addrs, int pass, bool extra_pass) { const struct bpf_insn *insn = fp->insnsi; @@ -940,7 +941,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * * !fp->aux->verifier_zext. Emit NOP otherwise. * * Note that "li reg_h,0" is emitted for BPF_B/H/W case, - * if necessary. So, jump there insted of emitting an + * if necessary. So, jump there instead of emitting an * additional "li reg_h,0" instruction. */ if (size == BPF_DW && !fp->aux->verifier_zext) @@ -997,7 +998,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * jmp_off += 4; } - ret = bpf_add_extable_entry(fp, image, pass, ctx, insn_idx, + ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, insn_idx, jmp_off, dst_reg); if (ret) return ret; @@ -1053,7 +1054,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_5), _R1, 12)); } - ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr); if (ret) return ret; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0f8048f6dad6..79f23974a320 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -240,7 +240,7 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u return 0; } -int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func) +int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func) { unsigned int i, ctx_idx = ctx->idx; @@ -361,7 +361,7 @@ asm ( ); /* Assemble the body code between the prologue & epilogue */ -int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, +int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx, u32 *addrs, int pass, bool extra_pass) { enum stf_barrier_type stf_barrier = stf_barrier_type_get(); @@ -940,8 +940,8 @@ emit_clear: addrs[++i] = ctx->idx * 4; if (BPF_MODE(code) == BPF_PROBE_MEM) { - ret = bpf_add_extable_entry(fp, image, pass, ctx, ctx->idx - 1, - 4, dst_reg); + ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, + ctx->idx - 1, 4, dst_reg); if (ret) return ret; } @@ -995,7 +995,7 @@ emit_clear: if (func_addr_fixed) ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr); else - ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr); if (ret) return ret; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 8c1f7def596e..b7ff680cde96 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1371,8 +1371,7 @@ static void power_pmu_disable(struct pmu *pmu) /* * Disable instruction sampling if it was enabled */ - if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE) - val &= ~MMCRA_SAMPLE_ENABLE; + val &= ~MMCRA_SAMPLE_ENABLE; /* Disable BHRB via mmcra (BHRBRD) for p10 */ if (ppmu->flags & PPMU_ARCH_31) @@ -1383,7 +1382,7 @@ static void power_pmu_disable(struct pmu *pmu) * instruction sampling or BHRB. */ if (val != mmcra) { - mtspr(SPRN_MMCRA, mmcra); + mtspr(SPRN_MMCRA, val); mb(); isync(); } @@ -2313,7 +2312,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, struct cpu_hw_events *cpuhw; cpuhw = this_cpu_ptr(&cpu_hw_events); power_pmu_bhrb_read(event, cpuhw); - perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack); + perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack, NULL); } if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC && diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 317175791d23..057ec2e3451d 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1338,7 +1338,7 @@ static int get_count_from_result(struct perf_event *event, for (i = count = 0, element_data = res->elements + data_offset; i < num_elements; i++, element_data += data_size + data_offset) - count += be64_to_cpu(*((u64 *) element_data)); + count += be64_to_cpu(*((__be64 *)element_data)); *countp = count; @@ -1418,7 +1418,7 @@ static int h_24x7_event_init(struct perf_event *event) } domain = event_get_domain(event); - if (domain >= HV_PERF_DOMAIN_MAX) { + if (domain == 0 || domain >= HV_PERF_DOMAIN_MAX) { pr_devel("invalid domain %d\n", domain); return -EINVAL; } 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 9d229ef7f86e..8664a7d297ad 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -51,7 +51,7 @@ static int trace_imc_mem_size; * core and trace-imc */ static struct imc_pmu_ref imc_global_refc = { - .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock), + .lock = __SPIN_LOCK_UNLOCKED(imc_global_refc.lock), .id = 0, .refc = 0, }; @@ -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; @@ -544,7 +550,7 @@ static int nest_imc_event_init(struct perf_event *event) break; } pcni++; - } while (pcni->vbase != 0); + } while (pcni->vbase); if (!flag) return -ENODEV; @@ -1025,16 +1031,16 @@ static bool is_thread_imc_pmu(struct perf_event *event) return false; } -static u64 * get_event_base_addr(struct perf_event *event) +static __be64 *get_event_base_addr(struct perf_event *event) { u64 addr; if (is_thread_imc_pmu(event)) { addr = (u64)per_cpu(thread_imc_mem, smp_processor_id()); - return (u64 *)(addr + (event->attr.config & IMC_EVENT_OFFSET_MASK)); + return (__be64 *)(addr + (event->attr.config & IMC_EVENT_OFFSET_MASK)); } - return (u64 *)event->hw.event_base; + return (__be64 *)event->hw.event_base; } static void thread_imc_pmu_start_txn(struct pmu *pmu, @@ -1058,7 +1064,8 @@ static int thread_imc_pmu_commit_txn(struct pmu *pmu) static u64 imc_read_counter(struct perf_event *event) { - u64 *addr, data; + __be64 *addr; + u64 data; /* * In-Memory Collection (IMC) counters are free flowing counters. diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c index 5729b6e059de..9f720b522e17 100644 --- a/arch/powerpc/perf/power6-pmu.c +++ b/arch/powerpc/perf/power6-pmu.c @@ -335,26 +335,38 @@ static const unsigned int event_alternatives[][MAX_ALT] = { { 0x3000fe, 0x400056 }, /* PM_DATA_FROM_L3MISS */ }; -/* - * This could be made more efficient with a binary search on - * a presorted list, if necessary - */ static int find_alternatives_list(u64 event) { - int i, j; - unsigned int alt; - - for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { - if (event < event_alternatives[i][0]) - return -1; - for (j = 0; j < MAX_ALT; ++j) { - alt = event_alternatives[i][j]; - if (!alt || event < alt) - break; - if (event == alt) - return i; - } + const unsigned int presorted_event_table[] = { + 0x0130e8, 0x080080, 0x080088, 0x10000a, 0x10000b, 0x10000d, 0x10000e, + 0x100010, 0x10001a, 0x100026, 0x100054, 0x100056, 0x1000f0, 0x1000f8, + 0x1000fc, 0x200008, 0x20000e, 0x200010, 0x200012, 0x200054, 0x2000f0, + 0x2000f2, 0x2000f4, 0x2000f5, 0x2000f6, 0x2000f8, 0x2000fc, 0x2000fe, + 0x2d0030, 0x30000a, 0x30000c, 0x300010, 0x300012, 0x30001a, 0x300056, + 0x3000f0, 0x3000f2, 0x3000f6, 0x3000f8, 0x3000fc, 0x3000fe, 0x400006, + 0x400007, 0x40000a, 0x40000e, 0x400010, 0x400018, 0x400056, 0x4000f0, + 0x4000f8, 0x600005 + }; + const unsigned int event_index_table[] = { + 0, 1, 2, 3, 4, 1, 5, 6, 7, 8, 9, 10, 11, 12, 13, 12, 14, + 7, 15, 2, 9, 16, 3, 4, 0, 17, 10, 18, 19, 20, 1, 17, 15, 19, + 18, 2, 16, 21, 8, 0, 22, 13, 14, 11, 21, 5, 20, 22, 1, 6, 3 + }; + int hi = ARRAY_SIZE(presorted_event_table) - 1; + int lo = 0; + + while (lo <= hi) { + int mid = lo + (hi - lo) / 2; + unsigned int alt = presorted_event_table[mid]; + + if (alt < event) + lo = mid + 1; + else if (alt > event) + hi = mid - 1; + else + return event_index_table[mid]; } + return -1; } 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/4xx/soc.c b/arch/powerpc/platforms/4xx/soc.c index b2d940437a66..5412e6b21e10 100644 --- a/arch/powerpc/platforms/4xx/soc.c +++ b/arch/powerpc/platforms/4xx/soc.c @@ -112,7 +112,7 @@ static int __init ppc4xx_l2c_probe(void) } /* Install error handler */ - if (request_irq(irq, l2c_error_handler, 0, "L2C", 0) < 0) { + if (request_irq(irq, l2c_error_handler, 0, "L2C", NULL) < 0) { printk(KERN_ERR "Cannot install L2C error handler" ", cache is not enabled\n"); of_node_put(np); 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/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index d9f1a2a83158..1824536cf6f2 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -2,6 +2,7 @@ menuconfig PPC_82xx bool "82xx-based boards (PQ II)" depends on PPC_BOOK3S_32 + select FSL_SOC if PPC_82xx @@ -9,7 +10,6 @@ config EP8248E bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)" select CPM2 select PPC_INDIRECT_PCI if PCI - select FSL_SOC select PHYLIB if NETDEVICES select MDIO_BITBANG if PHYLIB help @@ -22,7 +22,6 @@ config MGCOGE bool "Keymile MGCOGE" select CPM2 select PPC_INDIRECT_PCI if PCI - select FSL_SOC help This enables support for the Keymile MGCOGE board. diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c index 2fb2a85d131f..1135c1ab923c 100644 --- a/arch/powerpc/platforms/83xx/misc.c +++ b/arch/powerpc/platforms/83xx/misc.c @@ -14,6 +14,8 @@ #include <asm/io.h> #include <asm/hw_irq.h> #include <asm/ipic.h> +#include <asm/fixmap.h> + #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> 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/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index ebb5f6a27dbf..b24d4102fbf6 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -40,6 +40,7 @@ #include <asm/io.h> #include <asm/rheap.h> #include <asm/cpm.h> +#include <asm/fixmap.h> #include <sysdev/fsl_soc.h> diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index 77ea9335fd04..f381b177ea06 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -4,6 +4,8 @@ * Copyright (C) 2019 Haren Myneni, IBM Corp */ +#define pr_fmt(fmt) "vas-api: " fmt + #include <linux/kernel.h> #include <linux/device.h> #include <linux/cdev.h> @@ -78,7 +80,7 @@ int get_vas_user_win_ref(struct vas_user_win_ref *task_ref) task_ref->mm = get_task_mm(current); if (!task_ref->mm) { put_pid(task_ref->pid); - pr_err("VAS: pid(%d): mm_struct is not found\n", + pr_err("pid(%d): mm_struct is not found\n", current->pid); return -EPERM; } @@ -235,8 +237,7 @@ void vas_update_csb(struct coprocessor_request_block *crb, rc = kill_pid_info(SIGSEGV, &info, pid); rcu_read_unlock(); - pr_devel("%s(): pid %d kill_proc_info() rc %d\n", __func__, - pid_vnr(pid), rc); + pr_devel("pid %d kill_proc_info() rc %d\n", pid_vnr(pid), rc); } void vas_dump_crb(struct coprocessor_request_block *crb) @@ -294,7 +295,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg) rc = copy_from_user(&uattr, uptr, sizeof(uattr)); if (rc) { - pr_err("%s(): copy_from_user() returns %d\n", __func__, rc); + pr_err("copy_from_user() returns %d\n", rc); return -EFAULT; } @@ -311,7 +312,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg) txwin = cp_inst->coproc->vops->open_win(uattr.vas_id, uattr.flags, cp_inst->coproc->cop_type); if (IS_ERR(txwin)) { - pr_err("%s() VAS window open failed, %ld\n", __func__, + pr_err_ratelimited("VAS window open failed rc=%ld\n", PTR_ERR(txwin)); return PTR_ERR(txwin); } @@ -405,8 +406,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) * window is not opened. Shouldn't expect this error. */ if (!cp_inst || !cp_inst->txwin) { - pr_err("%s(): Unexpected fault on paste address with TX window closed\n", - __func__); + pr_err("Unexpected fault on paste address with TX window closed\n"); return VM_FAULT_SIGBUS; } @@ -421,8 +421,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) * issue NX request. */ if (txwin->task_ref.vma != vmf->vma) { - pr_err("%s(): No previous mapping with paste address\n", - __func__); + pr_err("No previous mapping with paste address\n"); return VM_FAULT_SIGBUS; } @@ -481,19 +480,19 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) txwin = cp_inst->txwin; if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) { - pr_debug("%s(): size 0x%zx, PAGE_SIZE 0x%zx\n", __func__, + pr_debug("size 0x%zx, PAGE_SIZE 0x%zx\n", (vma->vm_end - vma->vm_start), PAGE_SIZE); return -EINVAL; } /* Ensure instance has an open send window */ if (!txwin) { - pr_err("%s(): No send window open?\n", __func__); + pr_err("No send window open?\n"); return -EINVAL; } if (!cp_inst->coproc->vops || !cp_inst->coproc->vops->paste_addr) { - pr_err("%s(): VAS API is not registered\n", __func__); + pr_err("VAS API is not registered\n"); return -EACCES; } @@ -510,14 +509,14 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) */ mutex_lock(&txwin->task_ref.mmap_mutex); if (txwin->status != VAS_WIN_ACTIVE) { - pr_err("%s(): Window is not active\n", __func__); + pr_err("Window is not active\n"); rc = -EACCES; goto out; } paste_addr = cp_inst->coproc->vops->paste_addr(txwin); if (!paste_addr) { - pr_err("%s(): Window paste address failed\n", __func__); + pr_err("Window paste address failed\n"); rc = -EINVAL; goto out; } @@ -533,8 +532,8 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) rc = remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, vma->vm_end - vma->vm_start, prot); - pr_devel("%s(): paste addr %llx at %lx, rc %d\n", __func__, - paste_addr, vma->vm_start, rc); + pr_devel("paste addr %llx at %lx, rc %d\n", paste_addr, + vma->vm_start, rc); txwin->task_ref.vma = vma; vma->vm_ops = &vas_vm_ops; @@ -609,8 +608,7 @@ int vas_register_coproc_api(struct module *mod, enum vas_cop_type cop_type, goto err; } - pr_devel("%s: Added dev [%d,%d]\n", __func__, MAJOR(devno), - MINOR(devno)); + pr_devel("Added dev [%d,%d]\n", MAJOR(devno), MINOR(devno)); return 0; diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 1a587618015c..18daafbe2e65 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -66,7 +66,7 @@ static int match_context(const void *v, struct file *file, unsigned fd) */ static struct spu_context *coredump_next_context(int *fd) { - struct spu_context *ctx; + struct spu_context *ctx = NULL; struct file *file; int n = iterate_fd(current->files, *fd, match_context, NULL); if (!n) @@ -74,10 +74,13 @@ static struct spu_context *coredump_next_context(int *fd) *fd = n - 1; rcu_read_lock(); - file = lookup_fd_rcu(*fd); - ctx = SPUFS_I(file_inode(file))->i_ctx; - get_spu_context(ctx); + file = lookup_fdget_rcu(*fd); rcu_read_unlock(); + if (file) { + ctx = SPUFS_I(file_inode(file))->i_ctx; + get_spu_context(ctx); + fput(file); + } return ctx; } diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 38c5be34c895..030de2b8c145 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -86,7 +86,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); out: return inode; } @@ -145,10 +145,11 @@ spufs_evict_inode(struct inode *inode) static void spufs_prune_dir(struct dentry *dir) { - struct dentry *dentry, *tmp; + struct dentry *dentry; + struct hlist_node *n; inode_lock(d_inode(dir)); - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { + hlist_for_each_entry_safe(dentry, n, &dir->d_children, d_sib) { spin_lock(&dentry->d_lock); if (simple_positive(dentry)) { dget_dlock(dentry); 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/Kconfig b/arch/powerpc/platforms/powermac/Kconfig index 130707ec9f99..8bdae0caf21e 100644 --- a/arch/powerpc/platforms/powermac/Kconfig +++ b/arch/powerpc/platforms/powermac/Kconfig @@ -2,6 +2,7 @@ config PPC_PMAC bool "Apple PowerMac based machines" depends on PPC_BOOK3S && CPU_BIG_ENDIAN + select ADB_CUDA if POWER_RESET && PPC32 select MPIC select FORCE_PCI select PPC_INDIRECT_PCI if PPC32 diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index ae62d432db8b..81c9fbae88b1 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -2614,7 +2614,8 @@ static void __init probe_one_macio(const char *name, const char *compat, int typ struct device_node* node; int i; volatile u32 __iomem *base; - const u32 *addrp, *revp; + const __be32 *addrp; + const u32 *revp; phys_addr_t addr; u64 size; diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index 40f3aa432fba..c097d591670e 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -925,8 +925,10 @@ static void __init smu_i2c_probe(void) sz = sizeof(struct pmac_i2c_bus) + sizeof(struct smu_i2c_cmd); bus = kzalloc(sz, GFP_KERNEL); - if (bus == NULL) + if (bus == NULL) { + of_node_put(busnode); return; + } bus->controller = controller; bus->busnode = of_node_get(busnode); diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 8be71920e63c..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 */ } @@ -598,8 +598,10 @@ static void __init smp_core99_setup_i2c_hwsync(int ncpus) name = "Pulsar"; break; } - if (pmac_tb_freeze != NULL) + if (pmac_tb_freeze != NULL) { + of_node_put(cc); break; + } } if (pmac_tb_freeze != NULL) { /* Open i2c bus for synchronous access */ diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h index 3f715efb0aa6..5eeb794b5eb1 100644 --- a/arch/powerpc/platforms/powernv/opal-fadump.h +++ b/arch/powerpc/platforms/powernv/opal-fadump.h @@ -135,7 +135,7 @@ static inline void opal_fadump_read_regs(char *bufp, unsigned int regs_cnt, for (i = 0; i < regs_cnt; i++, bufp += reg_entry_size) { reg_entry = (struct hdat_fadump_reg_entry *)bufp; val = (cpu_endian ? be64_to_cpu(reg_entry->reg_val) : - (u64)(reg_entry->reg_val)); + (u64 __force)(reg_entry->reg_val)); opal_fadump_set_regval_regnum(regs, be32_to_cpu(reg_entry->reg_type), be32_to_cpu(reg_entry->reg_num), 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/opal.c b/arch/powerpc/platforms/powernv/opal.c index cdf3838f08d3..45dd77e3ccf6 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -424,7 +424,7 @@ static int __init opal_message_init(struct device_node *opal_node) return 0; } -int opal_get_chars(uint32_t vtermno, char *buf, int count) +ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count) { s64 rc; __be64 evt, len; @@ -441,10 +441,11 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count) return 0; } -static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, bool atomic) +static ssize_t __opal_put_chars(uint32_t vtermno, const u8 *data, + size_t total_len, bool atomic) { unsigned long flags = 0 /* shut up gcc */; - int written; + ssize_t written; __be64 olen; s64 rc; @@ -484,7 +485,7 @@ static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, b if (atomic) { /* Should not happen */ pr_warn("atomic console write returned partial " - "len=%d written=%d\n", total_len, written); + "len=%zu written=%zd\n", total_len, written); } if (!written) written = -EAGAIN; @@ -497,7 +498,7 @@ out: return written; } -int opal_put_chars(uint32_t vtermno, const char *data, int total_len) +ssize_t opal_put_chars(uint32_t vtermno, const u8 *data, size_t total_len) { return __opal_put_chars(vtermno, data, total_len, false); } @@ -508,7 +509,8 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) * true at the moment because console space can race with OPAL's console * writes. */ -int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len) +ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *data, + size_t total_len) { return __opal_put_chars(vtermno, data, total_len, true); } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 28fac4770073..23f5b5093ec1 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1389,7 +1389,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) * DMA window can be larger than available memory, which will * cause errors later. */ - const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER); + const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_PAGE_ORDER); /* * We create the default window as big as we can. The constraint is 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-$(CONFIG_SPU_BASE) += spu.o obj-y += device-init.o diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index e87360a0fb40..878bc160246e 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -827,6 +827,7 @@ static int ps3_probe_thread(void *data) if (res) goto fail_free_irq; + set_freezable(); /* Loop here processing the requested notification events. */ do { try_to_freeze(); diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c index 6b298010fd84..a5202c18c236 100644 --- a/arch/powerpc/platforms/ps3/gelic_udbg.c +++ b/arch/powerpc/platforms/ps3/gelic_udbg.c @@ -14,6 +14,7 @@ #include <linux/ip.h> #include <linux/udp.h> +#include <asm/ps3.h> #include <asm/io.h> #include <asm/udbg.h> #include <asm/lv1call.h> diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 4ebf2ef2845d..afc0f6a61337 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -164,6 +164,12 @@ config PSERIES_PLPKS # This option is selected by in-kernel consumers that require # access to the PKS. +config PSERIES_PLPKS_SED + depends on PPC_PSERIES + bool + # This option is selected by in-kernel consumers that require + # access to the SED PKS keystore. + config PAPR_SCM depends on PPC_PSERIES && MEMORY_HOTPLUG && LIBNVDIMM tristate "Support for the PAPR Storage Class Memory interface" diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 53c3b91af2f7..f936962a2946 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -4,6 +4,7 @@ ccflags-$(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 \ @@ -29,6 +30,7 @@ obj-$(CONFIG_PPC_SVM) += svm.o obj-$(CONFIG_FA_DUMP) += rtas-fadump.o obj-$(CONFIG_PSERIES_PLPKS) += plpks.o obj-$(CONFIG_PPC_SECURE_BOOT) += plpks-secvar.o +obj-$(CONFIG_PSERIES_PLPKS_SED) += plpks_sed_ops.o obj-$(CONFIG_SUSPEND) += suspend.o obj-$(CONFIG_PPC_VAS) += vas.o vas-sysfs.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 aa4042dcd6d4..3fe3ddb30c04 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -55,7 +55,8 @@ static bool find_aa_index(struct device_node *dr_node, struct property *ala_prop, const u32 *lmb_assoc, u32 *aa_index) { - u32 *assoc_arrays, new_prop_size; + __be32 *assoc_arrays; + u32 new_prop_size; struct property *new_prop; int aa_arrays, aa_array_entries, aa_array_sz; int i, index; @@ -207,8 +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); @@ -435,14 +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; } @@ -574,6 +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; } @@ -587,12 +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/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index bae45b358a09..2b0cac6fb61f 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -184,9 +184,6 @@ _GLOBAL_TOC(plpar_hcall) plpar_hcall_trace: HCALL_INST_PRECALL(R5) - std r4,STK_PARAM(R4)(r1) - mr r0,r4 - mr r4,r5 mr r5,r6 mr r6,r7 @@ -196,7 +193,7 @@ plpar_hcall_trace: HVSC - ld r12,STK_PARAM(R4)(r1) + ld r12,STACK_FRAME_MIN_SIZE+STK_PARAM(R4)(r1) std r4,0(r12) std r5,8(r12) std r6,16(r12) @@ -296,9 +293,6 @@ _GLOBAL_TOC(plpar_hcall9) plpar_hcall9_trace: HCALL_INST_PRECALL(R5) - std r4,STK_PARAM(R4)(r1) - mr r0,r4 - mr r4,r5 mr r5,r6 mr r6,r7 diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c index 1ac52963e08b..8803c947998e 100644 --- a/arch/powerpc/platforms/pseries/hvconsole.c +++ b/arch/powerpc/platforms/pseries/hvconsole.c @@ -25,7 +25,7 @@ * firmware. * @count: not used? */ -int hvc_get_chars(uint32_t vtermno, char *buf, int count) +ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count) { long ret; unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; @@ -52,7 +52,7 @@ EXPORT_SYMBOL(hvc_get_chars); * firmware. Must be at least 16 bytes, even if count is less than 16. * @count: Send this number of characters. */ -int hvc_put_chars(uint32_t vtermno, const char *buf, int count) +ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count) { unsigned long *lbuf = (unsigned long *) buf; long ret; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 16d93b580f61..496e16c588aa 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -914,7 +914,8 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_ return 0; } -static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift) +static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift, + bool *direct_mapping) { struct dma_win *window; const struct dynamic_dma_window_prop *dma64; @@ -927,6 +928,7 @@ static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *windo dma64 = window->prop; *dma_addr = be64_to_cpu(dma64->dma_base); *window_shift = be32_to_cpu(dma64->window_shift); + *direct_mapping = window->direct; found = true; break; } @@ -1270,10 +1272,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) mutex_lock(&dma_win_init_mutex); - if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) { - direct_mapping = (len >= max_ram_len); + if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len, &direct_mapping)) goto out_unlock; - } /* * If we already went through this for a previous function of diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f2cb62148f36..4561667832ed 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -192,9 +192,9 @@ static void free_dtl_buffers(unsigned long *time_limit) continue; kmem_cache_free(dtl_cache, pp->dispatch_log); pp->dtl_ridx = 0; - pp->dispatch_log = 0; - pp->dispatch_log_end = 0; - pp->dtl_curr = 0; + pp->dispatch_log = NULL; + pp->dispatch_log_end = NULL; + pp->dtl_curr = NULL; if (time_limit && time_after(jiffies, *time_limit)) { cond_resched(); @@ -223,7 +223,7 @@ static void destroy_cpu_associativity(void) { kfree(vcpu_associativity); kfree(pcpu_associativity); - vcpu_associativity = pcpu_associativity = 0; + vcpu_associativity = pcpu_associativity = NULL; } static __be32 *__get_cpu_associativity(int cpu, __be32 *cpu_assoc, int flag) @@ -526,8 +526,10 @@ static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p, if (cmd) { rc = init_cpu_associativity(); - if (rc) + if (rc) { + destroy_cpu_associativity(); goto out; + } for_each_possible_cpu(cpu) { disp = per_cpu_ptr(&vcpu_disp_data, cpu); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 0161226d8fec..1798f0f14d58 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -61,7 +61,6 @@ static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { .mode = 0644, .proc_handler = proc_douintvec_minmax, }, - {} }; static int __init register_nmi_wd_lpm_factor_sysctl(void) 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/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index 2d40304eb6c1..febe18f251d0 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -150,7 +150,7 @@ static int plpks_gen_password(void) ospasswordlength = maxpwsize; ospassword = kzalloc(maxpwsize, GFP_KERNEL); if (!ospassword) { - kfree(password); + kfree_sensitive(password); return -ENOMEM; } memcpy(ospassword, password, ospasswordlength); @@ -163,7 +163,7 @@ static int plpks_gen_password(void) } } out: - kfree(password); + kfree_sensitive(password); return pseries_status_to_err(rc); } diff --git a/arch/powerpc/platforms/pseries/plpks_sed_ops.c b/arch/powerpc/platforms/pseries/plpks_sed_ops.c new file mode 100644 index 000000000000..7c873c9589ef --- /dev/null +++ b/arch/powerpc/platforms/pseries/plpks_sed_ops.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * POWER Platform specific code for non-volatile SED key access + * Copyright (C) 2022 IBM Corporation + * + * Define operations for SED Opal to read/write keys + * from POWER LPAR Platform KeyStore(PLPKS). + * + * Self Encrypting Drives(SED) key storage using PLPKS + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/ioctl.h> +#include <linux/sed-opal-key.h> +#include <asm/plpks.h> + +static bool plpks_sed_initialized = false; +static bool plpks_sed_available = false; + +/* + * structure that contains all SED data + */ +struct plpks_sed_object_data { + u_char version; + u_char pad1[7]; + u_long authority; + u_long range; + u_int key_len; + u_char key[32]; +}; + +#define PLPKS_SED_OBJECT_DATA_V0 0 +#define PLPKS_SED_MANGLED_LABEL "/default/pri" +#define PLPKS_SED_COMPONENT "sed-opal" +#define PLPKS_SED_KEY "opal-boot-pin" + +/* + * authority is admin1 and range is global + */ +#define PLPKS_SED_AUTHORITY 0x0000000900010001 +#define PLPKS_SED_RANGE 0x0000080200000001 + +static void plpks_init_var(struct plpks_var *var, char *keyname) +{ + if (!plpks_sed_initialized) { + plpks_sed_initialized = true; + plpks_sed_available = plpks_is_available(); + if (!plpks_sed_available) + pr_err("SED: plpks not available\n"); + } + + var->name = keyname; + var->namelen = strlen(keyname); + if (strcmp(PLPKS_SED_KEY, keyname) == 0) { + var->name = PLPKS_SED_MANGLED_LABEL; + var->namelen = strlen(keyname); + } + var->policy = PLPKS_WORLDREADABLE; + var->os = PLPKS_VAR_COMMON; + var->data = NULL; + var->datalen = 0; + var->component = PLPKS_SED_COMPONENT; +} + +/* + * Read the SED Opal key from PLPKS given the label + */ +int sed_read_key(char *keyname, char *key, u_int *keylen) +{ + struct plpks_var var; + struct plpks_sed_object_data data; + int ret; + u_int len; + + plpks_init_var(&var, keyname); + + if (!plpks_sed_available) + return -EOPNOTSUPP; + + var.data = (u8 *)&data; + var.datalen = sizeof(data); + + ret = plpks_read_os_var(&var); + if (ret != 0) + return ret; + + len = min_t(u16, be32_to_cpu(data.key_len), var.datalen); + memcpy(key, data.key, len); + key[len] = '\0'; + *keylen = len; + + return 0; +} + +/* + * Write the SED Opal key to PLPKS given the label + */ +int sed_write_key(char *keyname, char *key, u_int keylen) +{ + struct plpks_var var; + struct plpks_sed_object_data data; + struct plpks_var_name vname; + + plpks_init_var(&var, keyname); + + if (!plpks_sed_available) + return -EOPNOTSUPP; + + var.datalen = sizeof(struct plpks_sed_object_data); + var.data = (u8 *)&data; + + /* initialize SED object */ + data.version = PLPKS_SED_OBJECT_DATA_V0; + data.authority = cpu_to_be64(PLPKS_SED_AUTHORITY); + data.range = cpu_to_be64(PLPKS_SED_RANGE); + memset(&data.pad1, '\0', sizeof(data.pad1)); + data.key_len = cpu_to_be32(keylen); + memcpy(data.key, (char *)key, keylen); + + /* + * Key update requires remove first. The return value + * is ignored since it's okay if the key doesn't exist. + */ + vname.namelen = var.namelen; + vname.name = var.name; + plpks_remove_var(var.component, var.os, vname); + + return plpks_write_var(var); +} 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/rtas-work-area.c b/arch/powerpc/platforms/pseries/rtas-work-area.c index b37d52f40360..7fe34bee84d8 100644 --- a/arch/powerpc/platforms/pseries/rtas-work-area.c +++ b/arch/powerpc/platforms/pseries/rtas-work-area.c @@ -184,6 +184,7 @@ machine_arch_initcall(pseries, rtas_work_area_allocator_init); /** * rtas_work_area_reserve_arena() - Reserve memory suitable for RTAS work areas. + * @limit: Upper limit for memblock allocation. */ void __init rtas_work_area_reserve_arena(const phys_addr_t limit) { 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/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index e25ac52acf50..71d52a670d95 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -341,7 +341,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, if (atomic_inc_return(&cop_feat_caps->nr_used_credits) > atomic_read(&cop_feat_caps->nr_total_credits)) { - pr_err("Credits are not available to allocate window\n"); + pr_err_ratelimited("Credits are not available to allocate window\n"); rc = -EINVAL; goto out; } @@ -385,11 +385,15 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * same fault IRQ is not freed by the OS before. */ mutex_lock(&vas_pseries_mutex); - if (migration_in_progress) + if (migration_in_progress) { rc = -EBUSY; - else + } else { rc = allocate_setup_window(txwin, (u64 *)&domain[0], cop_feat_caps->win_type); + if (!rc) + caps->nr_open_wins_progress++; + } + mutex_unlock(&vas_pseries_mutex); if (rc) goto out; @@ -404,8 +408,17 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, goto out_free; txwin->win_type = cop_feat_caps->win_type; - mutex_lock(&vas_pseries_mutex); + /* + * The migration SUSPEND thread sets migration_in_progress and + * closes all open windows from the list. But the window is + * added to the list after open and modify HCALLs. So possible + * that migration_in_progress is set before modify HCALL which + * may cause some windows are still open when the hypervisor + * initiates the migration. + * So checks the migration_in_progress flag again and close all + * open windows. + * * Possible to lose the acquired credit with DLPAR core * removal after the window is opened. So if there are any * closed windows (means with lost credits), do not give new @@ -413,9 +426,11 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * after the existing windows are reopened when credits are * available. */ - if (!caps->nr_close_wins) { + mutex_lock(&vas_pseries_mutex); + if (!caps->nr_close_wins && !migration_in_progress) { list_add(&txwin->win_list, &caps->list); caps->nr_open_windows++; + caps->nr_open_wins_progress--; mutex_unlock(&vas_pseries_mutex); vas_user_win_add_mm_context(&txwin->vas_win.task_ref); return &txwin->vas_win; @@ -424,7 +439,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, put_vas_user_win_ref(&txwin->vas_win.task_ref); rc = -EBUSY; - pr_err("No credit is available to allocate window\n"); + pr_err_ratelimited("No credit is available to allocate window\n"); out_free: /* @@ -433,6 +448,12 @@ out_free: */ free_irq_setup(txwin); h_deallocate_vas_window(txwin->vas_win.winid); + /* + * Hold mutex and reduce nr_open_wins_progress counter. + */ + mutex_lock(&vas_pseries_mutex); + caps->nr_open_wins_progress--; + mutex_unlock(&vas_pseries_mutex); out: atomic_dec(&cop_feat_caps->nr_used_credits); kfree(txwin); @@ -937,14 +958,14 @@ int vas_migration_handler(int action) struct vas_caps *vcaps; int i, rc = 0; + pr_info("VAS migration event %d\n", action); + /* * NX-GZIP is not enabled. Nothing to do for migration. */ if (!copypaste_feat) return rc; - mutex_lock(&vas_pseries_mutex); - if (action == VAS_SUSPEND) migration_in_progress = true; else @@ -990,12 +1011,27 @@ int vas_migration_handler(int action) switch (action) { case VAS_SUSPEND: + mutex_lock(&vas_pseries_mutex); rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows, true); + /* + * Windows are included in the list after successful + * open. So wait for closing these in-progress open + * windows in vas_allocate_window() which will be + * done if the migration_in_progress is set. + */ + while (vcaps->nr_open_wins_progress) { + mutex_unlock(&vas_pseries_mutex); + msleep(10); + mutex_lock(&vas_pseries_mutex); + } + mutex_unlock(&vas_pseries_mutex); break; case VAS_RESUME: + mutex_lock(&vas_pseries_mutex); atomic_set(&caps->nr_total_credits, new_nr_creds); rc = reconfig_open_windows(vcaps, new_nr_creds, true); + mutex_unlock(&vas_pseries_mutex); break; default: /* should not happen */ @@ -1011,8 +1047,9 @@ int vas_migration_handler(int action) goto out; } + pr_info("VAS migration event (%d) successful\n", action); + out: - mutex_unlock(&vas_pseries_mutex); return rc; } diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 7115043ec488..45567cd13178 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -91,6 +91,8 @@ struct vas_cop_feat_caps { struct vas_caps { struct vas_cop_feat_caps caps; struct list_head list; /* List of open windows */ + int nr_open_wins_progress; /* Number of open windows in */ + /* progress. Used in migration */ int nr_close_wins; /* closed windows in the hypervisor for DLPAR */ int nr_open_windows; /* Number of successful open windows */ u8 feat; /* Feature type */ diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 57978a44d55b..558ec68d768e 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -11,9 +11,11 @@ #include <linux/msi.h> #include <linux/pci.h> #include <linux/slab.h> +#include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/property.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/seq_file.h> @@ -392,7 +394,6 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev, static const struct of_device_id fsl_of_msi_ids[]; static int fsl_of_msi_probe(struct platform_device *dev) { - const struct of_device_id *match; struct fsl_msi *msi; struct resource res, msiir; int err, i, j, irq_index, count; @@ -402,10 +403,7 @@ static int fsl_of_msi_probe(struct platform_device *dev) u32 offset; struct pci_controller *phb; - match = of_match_device(fsl_of_msi_ids, &dev->dev); - if (!match) - return -EINVAL; - features = match->data; + features = device_get_match_data(&dev->dev); printk(KERN_DEBUG "Setting up Freescale MSI support\n"); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 3868483fbe29..ef7707ea0db7 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -54,7 +54,7 @@ static void quirk_fsl_pcie_early(struct pci_dev *dev) /* if we aren't in host mode don't bother */ pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type); - if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE) + if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE) return; dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; @@ -581,7 +581,7 @@ static int fsl_add_bridge(struct platform_device *pdev, int is_primary) hose->ops = &fsl_indirect_pcie_ops; /* For PCIE read HEADER_TYPE to identify controller mode */ early_read_config_byte(hose, 0, 0, PCI_HEADER_TYPE, &hdr_type); - if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE) + if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE) goto no_bridge; } else { 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/mpic.c b/arch/powerpc/sysdev/mpic.c index ba287abcb008..dabbdd356664 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -355,7 +355,7 @@ static void __init mpic_test_broken_ipi(struct mpic *mpic) mpic_write(mpic->gregs, MPIC_INFO(GREG_IPI_VECTOR_PRI_0), MPIC_VECPRI_MASK); r = mpic_read(mpic->gregs, MPIC_INFO(GREG_IPI_VECTOR_PRI_0)); - if (r == le32_to_cpu(MPIC_VECPRI_MASK)) { + if (r == swab32(MPIC_VECPRI_MASK)) { printk(KERN_INFO "mpic: Detected reversed IPI registers\n"); mpic->flags |= MPIC_BROKEN_IPI; } 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/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 9f0af4d795d8..f1c0fa6ece21 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -802,7 +802,7 @@ int xive_native_get_queue_info(u32 vp_id, u32 prio, if (out_qpage) *out_qpage = be64_to_cpu(qpage); if (out_qsize) - *out_qsize = be32_to_cpu(qsize); + *out_qsize = be64_to_cpu(qsize); if (out_qeoi_page) *out_qeoi_page = be64_to_cpu(qeoi_page); if (out_escalate_irq) diff --git a/arch/powerpc/tools/gcc-check-mprofile-kernel.sh b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh index a31a56016c09..73e331e7660e 100755 --- a/arch/powerpc/tools/gcc-check-mprofile-kernel.sh +++ b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh @@ -7,21 +7,20 @@ set -o pipefail # To debug, uncomment the following line # set -x -# -mprofile-kernel is only supported on 64-bit, so this should not be invoked -# for 32-bit. We pass in -m64 explicitly, and -mbig-endian and -mlittle-endian -# are passed in from Kconfig, which takes care of toolchains defaulting to -# other targets. +# -mprofile-kernel is only supported on 64-bit with ELFv2, so this should not +# be invoked for other targets. Therefore we can pass in -m64 and -mabi +# explicitly, to take care of toolchains defaulting to other targets. # Test whether the compile option -mprofile-kernel exists and generates # profiling code (ie. a call to _mcount()). echo "int func() { return 0; }" | \ - $* -m64 -S -x c -O2 -p -mprofile-kernel - -o - \ + $* -m64 -mabi=elfv2 -S -x c -O2 -p -mprofile-kernel - -o - \ 2> /dev/null | grep -q "_mcount" # Test whether the notrace attribute correctly suppresses calls to _mcount(). echo -e "#include <linux/compiler.h>\nnotrace int func() { return 0; }" | \ - $* -m64 -S -x c -O2 -p -mprofile-kernel - -o - \ + $* -m64 -mabi=elfv2 -S -x c -O2 -p -mprofile-kernel - -o - \ 2> /dev/null | grep -q "_mcount" && \ exit 1 |