diff options
Diffstat (limited to 'arch/powerpc')
146 files changed, 1063 insertions, 824 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index f7a363cbc1bb..1cbadb60612d 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -126,13 +126,14 @@ config PPC select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV + select ARCH_HAS_HUGEPD if HUGETLB_PAGE select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API if PPC64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC64 - select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION) + select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION) select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE if PPC64 select ARCH_HAS_UBSAN_SANITIZE_ALL @@ -214,8 +215,7 @@ config PPC select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_RCU_TABLE_FREE if SMP - select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE + select HAVE_RCU_TABLE_FREE select HAVE_MMU_GATHER_PAGE_SIZE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN @@ -230,11 +230,13 @@ config PPC select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE select NEED_SG_DMA_LENGTH select OF + select OF_DMA_DEFAULT_COHERENT if !NOT_COHERENT_CACHE select OF_EARLY_FLATTREE select OLD_SIGACTION if PPC32 select OLD_SIGSUSPEND select PCI_DOMAINS if PCI select PCI_SYSCALL if PCI + select PPC_DAWR if PPC64 select RTC_LIB select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE @@ -371,6 +373,9 @@ config PPC_ADV_DEBUG_DAC_RANGE depends on PPC_ADV_DEBUG_REGS && 44x default y +config PPC_DAWR + bool + config ZONE_DMA bool default y if PPC_BOOK3E_64 @@ -716,6 +721,7 @@ config THREAD_SHIFT range 13 15 default "15" if PPC_256K_PAGES default "14" if PPC64 + default "14" if KASAN default "13" help Used to define the stack size. The default is almost always what you diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index c59920920ddc..b915fe658979 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -371,7 +371,7 @@ config PPC_PTDUMP config PPC_DEBUG_WX bool "Warn on W+X mappings at boot" - depends on PPC_PTDUMP + depends on PPC_PTDUMP && STRICT_KERNEL_RWX help Generate a warning if any W+X mappings are found at boot. diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index da9f9b48a63a..a120561f8433 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -91,11 +91,13 @@ MULTIPLEWORD := -mmultiple endif ifdef CONFIG_PPC64 +ifndef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mcall-aixdesc) aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2 endif +endif ifndef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align @@ -142,6 +144,7 @@ endif endif CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no) +ifndef CONFIG_CC_IS_CLANG ifdef CONFIG_CPU_LITTLE_ENDIAN CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc)) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2) @@ -150,6 +153,7 @@ CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) endif +endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink index 83f8e5ba2722..1dc88ad66867 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -17,11 +17,11 @@ quiet_cmd_head_check = CHKHEAD $@ quiet_cmd_relocs_check = CHKREL $@ ifdef CONFIG_PPC_BOOK3S_64 cmd_relocs_check = \ - $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" ; \ + $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" ; \ $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@" else cmd_relocs_check = \ - $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" + $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" endif # `@true` prevents complaint when there is nothing to be done diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c index 1699e9531552..00c4d843a023 100644 --- a/arch/powerpc/boot/4xx.c +++ b/arch/powerpc/boot/4xx.c @@ -228,7 +228,7 @@ void ibm4xx_denali_fixup_memsize(void) dpath = 8; /* 64 bits */ /* get address pins (rows) */ - val = SDRAM0_READ(DDR0_42); + val = SDRAM0_READ(DDR0_42); row = DDR_GET_VAL(val, DDR_APIN, DDR_APIN_SHIFT); if (row > max_row) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 73d1f3562978..a6fd5d43a9ba 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -122,7 +122,7 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c -src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c +src-wlib-$(CONFIG_PPC_MPC52xx) += mpc52xx-psc.c src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c ifndef CONFIG_PPC64_BOOT_WRAPPER src-wlib-y += crtsavres.S diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi index e1a961f05dcd..baa0c503e741 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi @@ -63,6 +63,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy0: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi index c288f3c6c637..93095600e808 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi @@ -60,6 +60,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy6: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi index 94f3e7175012..ff4bd38f0645 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi @@ -63,6 +63,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy1: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi index 94a76982d214..1fa38ed6f59e 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi @@ -60,6 +60,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy7: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi index b5ff5f71c6b8..a8cc9780c0c4 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy0: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi index ee44182c6348..8b8bd70c9382 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy1: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi index f05f0d775039..619c880b54d8 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe5000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy2: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi index a9114ec51075..d7ebb73a400d 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe7000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy3: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi index 44dd00ac7367..b151d696a069 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe9000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy4: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi index 5b1b84b58602..adc0ae0013a3 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xeb000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy5: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi index 0e1daaef9e74..435047e0e250 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi @@ -60,6 +60,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy14: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi index 68c5ef779266..c098657cca0a 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi @@ -60,6 +60,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy15: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi index 605363cc1117..9d06824815f3 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy8: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi index 1955dfa13634..70e947730c4b 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy9: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi index 2c1476454ee0..ad96e6529595 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe5000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy10: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi index b8b541ff5fb0..034bc4b71f7a 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe7000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy11: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi index 4b2cfddd1b15..93ca23d82b39 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe9000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy12: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi index 0a52ddf7cc17..23b3117a2fd2 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xeb000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy13: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index 2abc8e83b95e..9757d4f6331e 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -6,6 +6,8 @@ #include <string.h> #define INT_MAX ((int)(~0U>>1)) +#define UINT32_MAX ((u32)~0U) +#define INT32_MAX ((s32)(UINT32_MAX >> 1)) #include "of.h" diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index b0491b8c0199..afef4fcdea98 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -129,7 +129,7 @@ int serial_console_init(void) dt_is_compatible(devp, "fsl,cpm2-smc-uart")) rc = cpm_console_init(devp, &serial_cd); #endif -#ifdef CONFIG_PPC_MPC52XX +#ifdef CONFIG_PPC_MPC52xx else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart")) rc = mpc5200_psc_console_init(devp, &serial_cd); #endif diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h index 9c63b596e6ce..a09595f00cab 100644 --- a/arch/powerpc/include/asm/archrandom.h +++ b/arch/powerpc/include/asm/archrandom.h @@ -28,7 +28,7 @@ static inline int arch_get_random_seed_int(unsigned int *v) unsigned long val; int rc; - rc = arch_get_random_long(&val); + rc = arch_get_random_seed_long(&val); if (rc) *v = val; diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index f9dc597b0b86..6eb311eb818b 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -2,6 +2,7 @@ #ifndef _ASM_POWERPC_BOOK3S_32_KUP_H #define _ASM_POWERPC_BOOK3S_32_KUP_H +#include <asm/bug.h> #include <asm/book3s/32/mmu-hash.h> #ifdef __ASSEMBLY__ @@ -75,7 +76,7 @@ .macro kuap_check current, gpr #ifdef CONFIG_PPC_KUAP_DEBUG - lwz \gpr2, KUAP(thread) + lwz \gpr, THREAD + KUAP(\current) 999: twnei \gpr, 0 EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) #endif @@ -102,11 +103,13 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end) isync(); /* Context sync required after mtsrin() */ } -static inline void allow_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + u32 size, unsigned long dir) { u32 addr, end; - if (__builtin_constant_p(to) && to == NULL) + BUILD_BUG_ON(!__builtin_constant_p(dir)); + if (!(dir & KUAP_WRITE)) return; addr = (__force u32)to; @@ -119,11 +122,16 @@ static inline void allow_user_access(void __user *to, const void __user *from, u kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end); /* Clear Ks */ } -static inline void prevent_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline void prevent_user_access(void __user *to, const void __user *from, + u32 size, unsigned long dir) { u32 addr = (__force u32)to; u32 end = min(addr + size, TASK_SIZE); + BUILD_BUG_ON(!__builtin_constant_p(dir)); + if (!(dir & KUAP_WRITE)) + return; + if (!addr || addr >= TASK_SIZE || !size) return; @@ -131,12 +139,17 @@ static inline void prevent_user_access(void __user *to, const void __user *from, kuap_update_sr(mfsrin(addr) | SR_KS, addr, end); /* set Ks */ } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { + unsigned long begin = regs->kuap & 0xf0000000; + unsigned long end = regs->kuap << 28; + if (!is_write) return false; - return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !"); + return WARN(address < begin || address >= end, + "Bug: write fault blocked by segment registers !"); } #endif /* CONFIG_PPC_KUAP */ diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 998317702630..dc5c039eb28e 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -49,7 +49,6 @@ static inline void pgtable_free(void *table, unsigned index_size) #define get_hugepd_cache_index(x) (x) -#ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { @@ -66,13 +65,6 @@ static inline void __tlb_remove_table(void *_table) pgtable_free(table, shift); } -#else -static inline void pgtable_free_tlb(struct mmu_gather *tlb, - void *table, int shift) -{ - pgtable_free(table, shift); -} -#endif static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 8fd8599c9395..3f9ae3585ab9 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -156,6 +156,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, extern int hash__has_transparent_hugepage(void); #endif +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + BUG(); + return pmd; +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index d1d9177d9ebd..0729c034e56f 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -246,7 +246,7 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, */ static inline int hash__pmd_trans_huge(pmd_t pmd) { - return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) == + return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) == (_PAGE_PTE | H_PAGE_THP_HUGE)); } @@ -272,6 +272,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); extern int hash__has_transparent_hugepage(void); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)); +} + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index f254de956d6a..c8d1076e0ebb 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -77,25 +77,27 @@ static inline void set_kuap(unsigned long value) isync(); } -static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) { // This is written so we can resolve to a single case at build time - if (__builtin_constant_p(to) && to == NULL) + BUILD_BUG_ON(!__builtin_constant_p(dir)); + if (dir == KUAP_READ) set_kuap(AMR_KUAP_BLOCK_WRITE); - else if (__builtin_constant_p(from) && from == NULL) + else if (dir == KUAP_WRITE) set_kuap(AMR_KUAP_BLOCK_READ); else set_kuap(0); } static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) + unsigned long size, unsigned long dir) { set_kuap(AMR_KUAP_BLOCKED); } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 15b75005bc34..3fa1b962dc27 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -600,8 +600,11 @@ extern void slb_set_size(u16 size); * */ #define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) + +// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel #define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ - MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT) + MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2) + /* * For platforms that support on 65bit VA we limit the context bits */ diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index d5a44912902f..cae9e814593a 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -19,9 +19,7 @@ extern struct vmemmap_backing *vmemmap_list; extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); extern void pmd_fragment_free(unsigned long *); extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); -#ifdef CONFIG_SMP extern void __tlb_remove_table(void *_table); -#endif void pte_frag_destroy(void *pte_frag); static inline pgd_t *radix__pgd_alloc(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 ccf00a8b98c6..e8b60bc8e7b9 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -990,10 +990,25 @@ extern struct page *pgd_page(pgd_t pgd); #define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) #define pgd_page_vaddr(pgd) __va(pgd_val(pgd) & ~PGD_MASKED_BITS) -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) -#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1)) -#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) -#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) +static inline unsigned long pgd_index(unsigned long address) +{ + return (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1); +} + +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} + +static inline unsigned long pmd_index(unsigned long address) +{ + return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); +} + +static inline unsigned long pte_index(unsigned long address) +{ + return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); +} /* * Find an entry in a page-table-directory. We combine the address region @@ -1295,7 +1310,9 @@ extern void serialize_against_pte_lookup(struct mm_struct *mm); static inline pmd_t pmd_mkdevmap(pmd_t pmd) { - return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); + if (radix_enabled()) + return radix__pmd_mkdevmap(pmd); + return hash__pmd_mkdevmap(pmd); } static inline int pmd_devmap(pmd_t pmd) diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 574eca33f893..0efada5b4600 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -257,6 +257,11 @@ extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, extern int radix__has_transparent_hugepage(void); #endif +static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 3d76e1c388c2..28c3d936fdf3 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -27,12 +27,12 @@ struct drmem_lmb_info { extern struct drmem_lmb_info *drmem_info; #define for_each_drmem_lmb_in_range(lmb, start, end) \ - for ((lmb) = (start); (lmb) <= (end); (lmb)++) + for ((lmb) = (start); (lmb) < (end); (lmb)++) #define for_each_drmem_lmb(lmb) \ for_each_drmem_lmb_in_range((lmb), \ &drmem_info->lmbs[0], \ - &drmem_info->lmbs[drmem_info->n_lmbs - 1]) + &drmem_info->lmbs[drmem_info->n_lmbs]) /* * The of_drconf_cell_v1 struct defines the layout of the LMB data diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 0cfc365d814b..722289a1d000 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -77,7 +77,12 @@ enum fixed_addresses { static inline void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { - map_kernel_page(fix_to_virt(idx), phys, flags); + if (__builtin_constant_p(idx)) + BUILD_BUG_ON(idx >= __end_of_fixed_addresses); + else if (WARN_ON(idx >= __end_of_fixed_addresses)) + return; + + map_kernel_page(__fix_to_virt(idx), phys, flags); } #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index eea28ca679db..bc7d9d06a6d9 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -35,7 +35,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, { int oldval = 0, ret; - allow_write_to_user(uaddr, sizeof(*uaddr)); + allow_read_write_user(uaddr, uaddr, sizeof(*uaddr)); pagefault_disable(); switch (op) { @@ -62,7 +62,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, *oval = oldval; - prevent_write_to_user(uaddr, sizeof(*uaddr)); + prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr)); return ret; } @@ -76,7 +76,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, if (!access_ok(uaddr, sizeof(u32))) return -EFAULT; - allow_write_to_user(uaddr, sizeof(*uaddr)); + allow_read_write_user(uaddr, uaddr, sizeof(*uaddr)); + __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\ @@ -97,7 +98,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "cc", "memory"); *uval = prev; - prevent_write_to_user(uaddr, sizeof(*uaddr)); + prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr)); + return ret; } diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 78202d5fb13a..67e2da195eae 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -76,18 +76,25 @@ static inline void hw_breakpoint_disable(void) extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs); int hw_breakpoint_handler(struct die_args *args); -extern int set_dawr(struct arch_hw_breakpoint *brk); +#else /* CONFIG_HAVE_HW_BREAKPOINT */ +static inline void hw_breakpoint_disable(void) { } +static inline void thread_change_pc(struct task_struct *tsk, + struct pt_regs *regs) { } + +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ + + +#ifdef CONFIG_PPC_DAWR extern bool dawr_force_enable; static inline bool dawr_enabled(void) { return dawr_force_enable; } - -#else /* CONFIG_HAVE_HW_BREAKPOINT */ -static inline void hw_breakpoint_disable(void) { } -static inline void thread_change_pc(struct task_struct *tsk, - struct pt_regs *regs) { } +int set_dawr(struct arch_hw_breakpoint *brk); +#else static inline bool dawr_enabled(void) { return false; } -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ +static inline int set_dawr(struct arch_hw_breakpoint *brk) { return -1; } +#endif + #endif /* __KERNEL__ */ #endif /* _PPC_BOOK3S_64_HW_BREAKPOINT_H */ diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index 296e51c2f066..6db06f58deed 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -23,9 +23,7 @@ #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) -#define KASAN_SHADOW_END 0UL - -#define KASAN_SHADOW_SIZE (KASAN_SHADOW_END - KASAN_SHADOW_START) +#define KASAN_SHADOW_END (-(-KASAN_SHADOW_START >> KASAN_SHADOW_SCALE_SHIFT)) #ifdef CONFIG_KASAN void kasan_early_init(void); diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 5b5e39643a27..94f24928916a 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -2,6 +2,10 @@ #ifndef _ASM_POWERPC_KUP_H_ #define _ASM_POWERPC_KUP_H_ +#define KUAP_READ 1 +#define KUAP_WRITE 2 +#define KUAP_READ_WRITE (KUAP_READ | KUAP_WRITE) + #ifdef CONFIG_PPC64 #include <asm/book3s/64/kup-radix.h> #endif @@ -42,32 +46,48 @@ void setup_kuap(bool disabled); #else static inline void setup_kuap(bool disabled) { } static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) { } + unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) { } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) { return false; } + unsigned long size, unsigned long dir) { } +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return false; +} #endif /* CONFIG_PPC_KUAP */ static inline void allow_read_from_user(const void __user *from, unsigned long size) { - allow_user_access(NULL, from, size); + allow_user_access(NULL, from, size, KUAP_READ); } static inline void allow_write_to_user(void __user *to, unsigned long size) { - allow_user_access(to, NULL, size); + allow_user_access(to, NULL, size, KUAP_WRITE); +} + +static inline void allow_read_write_user(void __user *to, const void __user *from, + unsigned long size) +{ + allow_user_access(to, from, size, KUAP_READ_WRITE); } static inline void prevent_read_from_user(const void __user *from, unsigned long size) { - prevent_user_access(NULL, from, size); + prevent_user_access(NULL, from, size, KUAP_READ); } static inline void prevent_write_to_user(void __user *to, unsigned long size) { - prevent_user_access(to, NULL, size); + prevent_user_access(to, NULL, size, KUAP_WRITE); +} + +static inline void prevent_read_write_user(void __user *to, const void __user *from, + unsigned long size) +{ + prevent_user_access(to, from, size, KUAP_READ_WRITE); } #endif /* !__ASSEMBLY__ */ -#endif /* _ASM_POWERPC_KUP_H_ */ +#endif /* _ASM_POWERPC_KUAP_H_ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index bb7c8cc77f1a..04b2b927bb5a 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -535,7 +535,7 @@ static inline void note_hpte_modification(struct kvm *kvm, */ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm) { - return rcu_dereference_raw_notrace(kvm->memslots[0]); + return rcu_dereference_raw_check(kvm->memslots[0]); } extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 1c3133b5f86a..6fe97465e350 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -34,18 +34,19 @@ #include <asm/reg.h> static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) + unsigned long size, unsigned long dir) { mtspr(SPRN_MD_AP, MD_APG_INIT); } static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) + unsigned long size, unsigned long dir) { mtspr(SPRN_MD_AP, MD_APG_KUAP); } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000), "Bug: fault blocked by AP register !"); diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h index 332b13b4ecdb..29c43665a753 100644 --- a/arch/powerpc/include/asm/nohash/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/pgalloc.h @@ -46,7 +46,6 @@ static inline void pgtable_free(void *table, int shift) #define get_hugepd_cache_index(x) (x) -#ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { unsigned long pgf = (unsigned long)table; @@ -64,13 +63,6 @@ static inline void __tlb_remove_table(void *_table) pgtable_free(table, shift); } -#else -static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) -{ - pgtable_free(table, shift); -} -#endif - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 0d52f57fca04..f3e5b3c73432 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -285,8 +285,13 @@ static inline bool pfn_valid(unsigned long pfn) /* * Some number of bits at the level of the page table that points to * a hugepte are used to encode the size. This masks those bits. + * On 8xx, HW assistance requires 4k alignment for the hugepte. */ +#ifdef CONFIG_PPC_8xx +#define HUGEPD_SHIFT_MASK 0xfff +#else #define HUGEPD_SHIFT_MASK 0x3f +#endif #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index dce863a7635c..8e5b7d0b851c 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -10,8 +10,6 @@ #ifdef CONFIG_SMP -#include <asm/paca.h> - #define __my_cpu_offset local_paca->data_offset #endif /* CONFIG_SMP */ @@ -19,4 +17,6 @@ #include <asm-generic/percpu.h> +#include <asm/paca.h> + #endif /* _ASM_POWERPC_PERCPU_H_ */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 7426d7a90e1e..7aba3c7ea25c 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -12,6 +12,8 @@ #ifdef CONFIG_PPC_PERF_CTRS #include <asm/perf_event_server.h> +#else +static inline bool is_sier_available(void) { return false; } #endif #ifdef CONFIG_FSL_EMB_PERF_EVENT diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 64145751b2fd..f7ee707734bc 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -144,13 +144,9 @@ static inline void pte_frag_set(mm_context_t *ctx, void *p) #define is_ioremap_addr is_ioremap_addr static inline bool is_ioremap_addr(const void *x) { -#ifdef CONFIG_MMU unsigned long addr = (unsigned long)x; return addr >= IOREMAP_BASE && addr < IOREMAP_END; -#else - return false; -#endif } #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index ef573fe9873e..c92795f55ffb 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -291,7 +291,6 @@ struct thread_struct { #else #define INIT_THREAD { \ .ksp = INIT_SP, \ - .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \ .addr_limit = KERNEL_DS, \ .fpexc_mode = 0, \ .fscr = FSCR_TAR | FSCR_EBB \ diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 3c1887351c71..bd227e0eab07 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -368,8 +368,6 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value); extern void rtas_progress(char *s, unsigned short hex); extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); -extern int rtas_online_cpus_mask(cpumask_var_t cpus); -extern int rtas_offline_cpus_mask(cpumask_var_t cpus); extern int rtas_ibm_suspend_me(u64 handle); struct rtc_time; diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index ccf44c135389..7c05e95a5c44 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -9,7 +9,7 @@ #define _ASM_POWERPC_SECURITY_FEATURES_H -extern unsigned long powerpc_security_features; +extern u64 powerpc_security_features; extern bool rfi_flush; /* These are bit flags */ @@ -24,17 +24,17 @@ void setup_stf_barrier(void); void do_stf_barrier_fixups(enum stf_barrier_type types); void setup_count_cache_flush(void); -static inline void security_ftr_set(unsigned long feature) +static inline void security_ftr_set(u64 feature) { powerpc_security_features |= feature; } -static inline void security_ftr_clear(unsigned long feature) +static inline void security_ftr_clear(u64 feature) { powerpc_security_features &= ~feature; } -static inline bool security_ftr_enabled(unsigned long feature) +static inline bool security_ftr_enabled(u64 feature) { return !!(powerpc_security_features & feature); } diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h index d995061f5f86..f7d9b9f5c7ff 100644 --- a/arch/powerpc/include/asm/setjmp.h +++ b/arch/powerpc/include/asm/setjmp.h @@ -7,7 +7,9 @@ #define JMP_BUF_LEN 23 -extern long setjmp(long *); -extern void longjmp(long *, long); +typedef long jmp_buf[JMP_BUF_LEN]; + +extern int setjmp(jmp_buf env); +extern void longjmp(jmp_buf env, int val); #endif /* _ASM_POWERPC_SETJMP_H */ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index a47f827bc5f1..ff0dffb19aea 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -15,6 +15,7 @@ * * (the type definitions are in asm/spinlock_types.h) */ +#include <linux/jump_label.h> #include <linux/irqflags.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -36,10 +37,12 @@ #endif #ifdef CONFIG_PPC_PSERIES +DECLARE_STATIC_KEY_FALSE(shared_processor); + #define vcpu_is_preempted vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + if (!static_branch_unlikely(&shared_processor)) return false; return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1); } diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index b2c0be93929d..7f3a8b902325 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -26,6 +26,17 @@ #define tlb_flush tlb_flush extern void tlb_flush(struct mmu_gather *tlb); +/* + * book3s: + * Hash does not use the linux page-tables, so we can avoid + * the TLB invalidate for page-table freeing, Radix otoh does use the + * page-tables and needs the TLBI. + * + * nohash: + * We still do TLB invalidate in the __pte_free_tlb routine before we + * add the page table pages to mmu gather table batch. + */ +#define tlb_needs_table_invalidate() radix_enabled() /* Get the generic bits... */ #include <asm-generic/tlb.h> diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 8b03eb44e876..d02ac21558b4 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -313,9 +313,9 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) unsigned long ret; barrier_nospec(); - allow_user_access(to, from, n); + allow_read_write_user(to, from, n); ret = __copy_tofrom_user(to, from, n); - prevent_user_access(to, from, n); + prevent_read_write_user(to, from, n); return ret; } #endif /* __powerpc64__ */ @@ -387,7 +387,7 @@ static inline unsigned long raw_copy_to_user(void __user *to, return ret; } -extern unsigned long __clear_user(void __user *addr, unsigned long size); +unsigned long __arch_clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) { @@ -395,12 +395,17 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size) might_fault(); if (likely(access_ok(addr, size))) { allow_write_to_user(addr, size); - ret = __clear_user(addr, size); + ret = __arch_clear_user(addr, size); prevent_write_to_user(addr, size); } return ret; } +static inline unsigned long __clear_user(void __user *addr, unsigned long size) +{ + return clear_user(addr, size); +} + extern long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index c61d59ed3b45..2ccb938d8544 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -82,6 +82,7 @@ struct vdso_data { __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */ __s64 wtom_clock_sec; /* Wall to monotonic clock sec */ struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; @@ -103,6 +104,7 @@ struct vdso_data { __s32 wtom_clock_nsec; struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 dcache_block_size; /* L1 d-cache block size */ __u32 icache_block_size; /* L1 i-cache block size */ diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h index f2dfcd50a2d3..33aee7490cbb 100644 --- a/arch/powerpc/include/asm/xive-regs.h +++ b/arch/powerpc/include/asm/xive-regs.h @@ -39,6 +39,7 @@ #define XIVE_ESB_VAL_P 0x2 #define XIVE_ESB_VAL_Q 0x1 +#define XIVE_ESB_INVALID 0xFF /* * Thread Management (aka "TM") registers diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 64a7d8f693ff..447b7d935f4c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -7,9 +7,6 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' $(call cc-disable-warning, CFLAGS_ptrace.o += $(call cc-disable-warning, array-bounds) CFLAGS_syscalls.o += $(call cc-disable-warning, attribute-alias) -# Disable clang warning for using setjmp without setjmp.h header -CFLAGS_crash.o += $(call cc-disable-warning, builtin-requires-header) - ifdef CONFIG_PPC64 CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) endif @@ -59,6 +56,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o +obj-$(CONFIG_PPC_DAWR) += dawr.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 31dc7e64cbfc..31e501383125 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -385,6 +385,7 @@ int main(void) OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec); OFFSET(STAMP_XTIME, vdso_data, stamp_xtime); OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction); + OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res); OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size); OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size); OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size); @@ -415,7 +416,6 @@ int main(void) DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); - DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index bfe5f4a2886b..3b7cb01a4139 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -2191,11 +2191,13 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, * oprofile_cpu_type already has a value, then we are * possibly overriding a real PVR with a logical one, * and, in that case, keep the current value for - * oprofile_cpu_type. + * oprofile_cpu_type. Futhermore, let's ensure that the + * fix for the PMAO bug is enabled on compatibility mode. */ if (old.oprofile_cpu_type != NULL) { t->oprofile_cpu_type = old.oprofile_cpu_type; t->oprofile_type = old.oprofile_type; + t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } } diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c new file mode 100644 index 000000000000..5f66b95b6858 --- /dev/null +++ b/arch/powerpc/kernel/dawr.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * DAWR infrastructure + * + * Copyright 2019, Michael Neuling, IBM Corporation. + */ + +#include <linux/types.h> +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <asm/debugfs.h> +#include <asm/machdep.h> +#include <asm/hvcall.h> + +bool dawr_force_enable; +EXPORT_SYMBOL_GPL(dawr_force_enable); + +int set_dawr(struct arch_hw_breakpoint *brk) +{ + unsigned long dawr, dawrx, mrd; + + dawr = brk->address; + + dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) + << (63 - 58); + dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) << (63 - 59); + dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) >> 3; + /* + * DAWR length is stored in field MDR bits 48:53. Matches range in + * doublewords (64 bits) baised by -1 eg. 0b000000=1DW and + * 0b111111=64DW. + * brk->len is in bytes. + * This aligns up to double word size, shifts and does the bias. + */ + mrd = ((brk->len + 7) >> 3) - 1; + dawrx |= (mrd & 0x3f) << (63 - 53); + + if (ppc_md.set_dawr) + return ppc_md.set_dawr(dawr, dawrx); + + mtspr(SPRN_DAWR, dawr); + mtspr(SPRN_DAWRX, dawrx); + + return 0; +} + +static void set_dawr_cb(void *info) +{ + set_dawr(info); +} + +static ssize_t dawr_write_file_bool(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct arch_hw_breakpoint null_brk = {0, 0, 0}; + size_t rc; + + /* Send error to user if they hypervisor won't allow us to write DAWR */ + if (!dawr_force_enable && + firmware_has_feature(FW_FEATURE_LPAR) && + set_dawr(&null_brk) != H_SUCCESS) + return -ENODEV; + + rc = debugfs_write_file_bool(file, user_buf, count, ppos); + if (rc) + return rc; + + /* If we are clearing, make sure all CPUs have the DAWR cleared */ + if (!dawr_force_enable) + smp_call_function(set_dawr_cb, &null_brk, 0); + + return rc; +} + +static const struct file_operations dawr_enable_fops = { + .read = debugfs_read_file_bool, + .write = dawr_write_file_bool, + .open = simple_open, + .llseek = default_llseek, +}; + +static int __init dawr_force_setup(void) +{ + if (cpu_has_feature(CPU_FTR_DAWR)) { + /* Don't setup sysfs file for user control on P8 */ + dawr_force_enable = true; + return 0; + } + + if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) { + /* Turn DAWR off by default, but allow admin to turn it on */ + debugfs_create_file_unsafe("dawr_enable_dangerous", 0600, + powerpc_debugfs_root, + &dawr_force_enable, + &dawr_enable_fops); + } + return 0; +} +arch_initcall(dawr_force_setup); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 864cc55fa03c..cf55c756f829 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -139,7 +139,6 @@ static void __init cpufeatures_setup_cpu(void) /* Initialize the base environment -- clear FSCR/HFSCR. */ hv_mode = !!(mfmsr() & MSR_HV); if (hv_mode) { - /* CPU_FTR_HVMODE is used early in PACA setup */ cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE; mtspr(SPRN_HFSCR, 0); } @@ -346,6 +345,14 @@ static int __init feat_enable_dscr(struct dt_cpu_feature *f) { u64 lpcr; + /* + * Linux relies on FSCR[DSCR] being clear, so that we can take the + * facility unavailable interrupt and track the task's usage of DSCR. + * See facility_unavailable_exception(). + * Clear the bit here so that feat_enable() doesn't set it. + */ + f->fscr_bit_nr = -1; + feat_enable(f); lpcr = mfspr(SPRN_LPCR); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index fe0c32fb9f96..d147bc212405 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -540,12 +540,6 @@ static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) pci_iov_remove_virtfn(edev->physfn, pdn->vf_index); edev->pdev = NULL; - - /* - * We have to set the VF PE number to invalid one, which is - * required to plug the VF successfully. - */ - pdn->pe_number = IODA_INVALID_PE; #endif if (rmv_data) list_add(&edev->rmv_entry, &rmv_data->removed_vf_list); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 85fdb6d879f1..2c46a45f53e6 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -179,7 +179,7 @@ transfer_to_handler: 2: /* if from kernel, check interrupted DOZE/NAP mode and * check for stack overflow */ - kuap_save_and_lock r11, r12, r9, r2, r0 + kuap_save_and_lock r11, r12, r9, r2, r6 addi r2, r12, -THREAD lwz r9,KSP_LIMIT(r12) cmplw r1,r9 /* if r1 <= ksp_limit */ @@ -284,6 +284,7 @@ reenable_mmu: rlwinm r9,r9,0,~MSR_EE lwz r12,_LINK(r11) /* and return to address in LR */ kuap_restore r11, r2, r3, r4, r5 + lwz r2, GPR2(r11) b fast_exception_return #endif @@ -696,7 +697,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE) stw r10,_CCR(r1) stw r1,KSP(r3) /* Set old stack pointer */ - kuap_check r2, r4 + kuap_check r2, r0 #ifdef CONFIG_SMP /* We need a sync somewhere here to make sure that if the * previous task gets rescheduled on another CPU, it sees all diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3e564536a237..7c07c66cd80b 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -424,17 +424,19 @@ EXC_COMMON_BEGIN(machine_check_idle_common) bl machine_check_queue_event /* - * We have not used any non-volatile GPRs here, and as a rule - * most exception code including machine check does not. - * Therefore PACA_NAPSTATELOST does not need to be set. Idle - * wakeup will restore volatile registers. + * GPR-loss wakeups are relatively straightforward, because the + * idle sleep code has saved all non-volatile registers on its + * own stack, and r1 in PACAR1. * - * Load the original SRR1 into r3 for pnv_powersave_wakeup_mce. + * For no-loss wakeups the r1 and lr registers used by the + * early machine check handler have to be restored first. r2 is + * the kernel TOC, so no need to restore it. * * Then decrement MCE nesting after finishing with the stack. */ ld r3,_MSR(r1) ld r4,_LINK(r1) + ld r1,GPR1(r1) lhz r11,PACA_IN_MCE(r13) subi r11,r11,1 @@ -443,7 +445,7 @@ EXC_COMMON_BEGIN(machine_check_idle_common) mtlr r4 rlwinm r10,r3,47-31,30,31 cmpwi cr1,r10,2 - bltlr cr1 /* no state loss, return to idle caller */ + bltlr cr1 /* no state loss, return to idle caller with r3=SRR1 */ b idle_return_gpr_loss #endif /* diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b5a5c6896019..b838f08929cb 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -900,6 +900,7 @@ p_toc: .8byte __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. */ +__REF start_here_multiplatform: /* set up the TOC */ bl relative_toc @@ -943,15 +944,8 @@ start_here_multiplatform: std r0,0(r4) #endif - /* The following gets the stack set up with the regs */ - /* pointing to the real addr of the kernel stack. This is */ - /* all done to support the C function call below which sets */ - /* up the htab. This is done because we have relocated the */ - /* kernel but are still running in real mode. */ - - LOAD_REG_ADDR(r3,init_thread_union) - /* set up a stack pointer */ + LOAD_REG_ADDR(r3,init_thread_union) LOAD_REG_IMMEDIATE(r1,THREAD_SIZE) add r1,r3,r1 li r0,0 @@ -975,6 +969,7 @@ start_here_multiplatform: RFI b . /* prevent speculative execution */ + .previous /* This is where all platforms converge execution */ start_here_common: diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 5ab9178c2347..acd038b59dd3 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -288,7 +288,7 @@ InstructionTLBMiss: * set. All other Linux PTE bits control the behavior * of the MMU. */ - rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */ + rlwinm r10, r10, 0, ~0x0f00 /* Clear bits 20-23 */ rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index adf0505dbe02..519d49547e2f 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -238,6 +238,9 @@ set_ivor: bl early_init +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif #ifdef CONFIG_RELOCATABLE mr r3,r30 mr r4,r31 @@ -264,9 +267,6 @@ set_ivor: /* * Decide what sort of machine this is and initialize the MMU. */ -#ifdef CONFIG_KASAN - bl kasan_early_init -#endif mr r3,r30 mr r4,r31 bl machine_init diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 50262597c222..c8d1fa2e9d53 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -366,64 +366,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp) { /* TODO */ } - -bool dawr_force_enable; -EXPORT_SYMBOL_GPL(dawr_force_enable); - -static void set_dawr_cb(void *info) -{ - set_dawr(info); -} - -static ssize_t dawr_write_file_bool(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct arch_hw_breakpoint null_brk = {0, 0, 0}; - size_t rc; - - /* Send error to user if they hypervisor won't allow us to write DAWR */ - if ((!dawr_force_enable) && - (firmware_has_feature(FW_FEATURE_LPAR)) && - (set_dawr(&null_brk) != H_SUCCESS)) - return -1; - - rc = debugfs_write_file_bool(file, user_buf, count, ppos); - if (rc) - return rc; - - /* If we are clearing, make sure all CPUs have the DAWR cleared */ - if (!dawr_force_enable) - smp_call_function(set_dawr_cb, &null_brk, 0); - - return rc; -} - -static const struct file_operations dawr_enable_fops = { - .read = debugfs_read_file_bool, - .write = dawr_write_file_bool, - .open = simple_open, - .llseek = default_llseek, -}; - -static int __init dawr_force_setup(void) -{ - dawr_force_enable = false; - - if (cpu_has_feature(CPU_FTR_DAWR)) { - /* Don't setup sysfs file for user control on P8 */ - dawr_force_enable = true; - return 0; - } - - if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) { - /* Turn DAWR off by default, but allow admin to turn it on */ - dawr_force_enable = false; - debugfs_create_file_unsafe("dawr_enable_dangerous", 0600, - powerpc_debugfs_root, - &dawr_force_enable, - &dawr_enable_fops); - } - return 0; -} -arch_initcall(dawr_force_setup); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 5645bc9cbc09..add67498c126 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -619,8 +619,6 @@ void __do_irq(struct pt_regs *regs) trace_irq_entry(regs); - check_stack_overflow(); - /* * Query the platform PIC for the interrupt & ack it. * @@ -652,6 +650,8 @@ void do_IRQ(struct pt_regs *regs) irqsp = hardirq_ctx[raw_smp_processor_id()]; sirqsp = softirq_ctx[raw_smp_processor_id()]; + check_stack_overflow(); + /* Already there ? */ if (unlikely(cursp == irqsp || cursp == sirqsp)) { __do_irq(regs); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 2d27ec4feee4..9b340af02c38 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -264,6 +264,9 @@ int kprobe_handler(struct pt_regs *regs) if (user_mode(regs)) return 0; + if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)) + return 0; + /* * We don't want to be preempted for the entire * duration of kprobe processing diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index c4ed328a7b96..7a1c11a7cba5 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -114,11 +114,12 @@ void machine_kexec(struct kimage *image) void __init reserve_crashkernel(void) { - unsigned long long crash_size, crash_base; + unsigned long long crash_size, crash_base, total_mem_sz; int ret; + total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size(); /* use common parsing */ - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; @@ -177,6 +178,7 @@ void __init reserve_crashkernel(void) /* Crash kernel trumps memory limit */ if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; + total_mem_sz = memory_limit; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", memory_limit); } @@ -185,7 +187,7 @@ void __init reserve_crashkernel(void) "for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crashk_res.start >> 20), - (unsigned long)(memblock_phys_mem_size() >> 20)); + (unsigned long)(total_mem_sz >> 20)); if (!memblock_is_region_memory(crashk_res.start, crash_size) || memblock_reserve(crashk_res.start, crash_size)) { diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index d4d096f80f4b..19b5c4bb7d01 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -82,7 +82,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of cache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 1: dcbst 0,r6 @@ -98,7 +98,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,ICACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of Icache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 2: icbi 0,r6 diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index e3ad8aa4730d..01800e5c4118 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -134,7 +134,7 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit) struct paca_struct **paca_ptrs __read_mostly; EXPORT_SYMBOL(paca_ptrs); -void __init initialise_paca(struct paca_struct *new_paca, int cpu) +void __init __nostackprotector initialise_paca(struct paca_struct *new_paca, int cpu) { #ifdef CONFIG_PPC_PSERIES new_paca->lppaca_ptr = NULL; @@ -163,7 +163,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) } /* Put the paca pointer into r13 and SPRG_PACA */ -void setup_paca(struct paca_struct *new_paca) +void __nostackprotector setup_paca(struct paca_struct *new_paca) { /* Setup r13 */ local_paca = new_paca; @@ -172,11 +172,15 @@ void setup_paca(struct paca_struct *new_paca) /* On Book3E, initialize the TLB miss exception frames */ mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb); #else - /* In HV mode, we setup both HPACA and PACA to avoid problems + /* + * In HV mode, we setup both HPACA and PACA to avoid problems * if we do a GET_PACA() before the feature fixups have been - * applied + * applied. + * + * Normally you should test against CPU_FTR_HVMODE, but CPU features + * are not yet set up when we first reach here. */ - if (early_cpu_has_feature(CPU_FTR_HVMODE)) + if (mfmsr() & MSR_HV) mtspr(SPRN_SPRG_HPACA, local_paca); #endif mtspr(SPRN_SPRG_PACA, local_paca); diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index c4c8c237a106..eca72c460151 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -244,9 +244,22 @@ void remove_dev_pci_data(struct pci_dev *pdev) continue; #ifdef CONFIG_EEH - /* Release EEH device for the VF */ + /* + * Release EEH state for this VF. The PCI core + * has already torn down the pci_dev for this VF, but + * we're responsible to removing the eeh_dev since it + * has the same lifetime as the pci_dn that spawned it. + */ edev = pdn_to_eeh_dev(pdn); if (edev) { + /* + * We allocate pci_dn's for the totalvfs count, + * but only only the vfs that were activated + * have a configured PE. + */ + if (edev->pe) + eeh_rmv_from_parent_pe(edev); + pdn->edev = NULL; kfree(edev); } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4f9bfe9fd960..642b248ff41f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -780,34 +780,6 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk) return __set_dabr(dabr, dabrx); } -int set_dawr(struct arch_hw_breakpoint *brk) -{ - unsigned long dawr, dawrx, mrd; - - dawr = brk->address; - - dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) \ - << (63 - 58); //* read/write bits */ - dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) \ - << (63 - 59); //* translate */ - dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) \ - >> 3; //* PRIM bits */ - /* dawr length is stored in field MDR bits 48:53. Matches range in - doublewords (64 bits) baised by -1 eg. 0b000000=1DW and - 0b111111=64DW. - brk->len is in bytes. - This aligns up to double word size, shifts and does the bias. - */ - mrd = ((brk->len + 7) >> 3) - 1; - dawrx |= (mrd & 0x3f) << (63 - 53); - - if (ppc_md.set_dawr) - return ppc_md.set_dawr(dawr, dawrx); - mtspr(SPRN_DAWR, dawr); - mtspr(SPRN_DAWRX, dawrx); - return 0; -} - void __set_breakpoint(struct arch_hw_breakpoint *brk) { memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 7159e791a70d..0d1a67b3e8da 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -684,6 +684,23 @@ static void __init tm_init(void) static void tm_init(void) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +#ifdef CONFIG_PPC64 +static void __init save_fscr_to_task(void) +{ + /* + * Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we + * have configured via the device tree features or via __init_FSCR(). + * That value will then be propagated to pid 1 (init) and all future + * processes. + */ + if (early_cpu_has_feature(CPU_FTR_ARCH_207S)) + init_task.thread.fscr = mfspr(SPRN_FSCR); +} +#else +static inline void save_fscr_to_task(void) {}; +#endif + + void __init early_init_devtree(void *params) { phys_addr_t limit; @@ -769,6 +786,8 @@ void __init early_init_devtree(void *params) BUG(); } + save_fscr_to_task(); + #if defined(CONFIG_SMP) && defined(CONFIG_PPC64) /* We'll later wait for secondaries to check in; there are * NCPUS-1 non-boot CPUs :-) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 6d600c977c09..e1186a0deb23 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1037,7 +1037,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = { .reserved2 = 0, .reserved3 = 0, .subprocessors = 1, - .byte22 = OV5_FEAT(OV5_DRMEM_V2), + .byte22 = OV5_FEAT(OV5_DRMEM_V2) | OV5_FEAT(OV5_DRC_INFO), .intarch = 0, .mmu = 0, .hash_ext = 0, diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 65cd96c3b1d6..5e468938a661 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -841,97 +841,6 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } -enum rtas_cpu_state { - DOWN, - UP, -}; - -#ifndef CONFIG_SMP -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - if (!cpumask_empty(cpus)) { - cpumask_clear(cpus); - return -EINVAL; - } else - return 0; -} -#else -/* On return cpumask will be altered to indicate CPUs changed. - * CPUs with states changed will be set in the mask, - * CPUs with status unchanged will be unset in the mask. */ -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - int cpu; - int cpuret = 0; - int ret = 0; - - if (cpumask_empty(cpus)) - return 0; - - for_each_cpu(cpu, cpus) { - struct device *dev = get_cpu_device(cpu); - - switch (state) { - case DOWN: - cpuret = device_offline(dev); - break; - case UP: - cpuret = device_online(dev); - break; - } - if (cpuret < 0) { - pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", - __func__, - ((state == UP) ? "up" : "down"), - cpu, cpuret); - if (!ret) - ret = cpuret; - if (state == UP) { - /* clear bits for unchanged cpus, return */ - cpumask_shift_right(cpus, cpus, cpu); - cpumask_shift_left(cpus, cpus, cpu); - break; - } else { - /* clear bit for unchanged cpu, continue */ - cpumask_clear_cpu(cpu, cpus); - } - } - } - - return ret; -} -#endif - -int rtas_online_cpus_mask(cpumask_var_t cpus) -{ - int ret; - - ret = rtas_cpu_state_change_mask(UP, cpus); - - if (ret) { - cpumask_var_t tmp_mask; - - if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL)) - return ret; - - /* Use tmp_mask to preserve cpus mask from first failure */ - cpumask_copy(tmp_mask, cpus); - rtas_offline_cpus_mask(tmp_mask); - free_cpumask_var(tmp_mask); - } - - return ret; -} -EXPORT_SYMBOL(rtas_online_cpus_mask); - -int rtas_offline_cpus_mask(cpumask_var_t cpus) -{ - return rtas_cpu_state_change_mask(DOWN, cpus); -} -EXPORT_SYMBOL(rtas_offline_cpus_mask); - int rtas_ibm_suspend_me(u64 handle) { long state; @@ -939,8 +848,6 @@ int rtas_ibm_suspend_me(u64 handle) unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; DECLARE_COMPLETION_ONSTACK(done); - cpumask_var_t offline_mask; - int cpuret; if (!rtas_service_present("ibm,suspend-me")) return -ENOSYS; @@ -961,9 +868,6 @@ int rtas_ibm_suspend_me(u64 handle) return -EIO; } - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - atomic_set(&data.working, 0); atomic_set(&data.done, 0); atomic_set(&data.error, 0); @@ -972,24 +876,8 @@ int rtas_ibm_suspend_me(u64 handle) lock_device_hotplug(); - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); - cpuret = rtas_online_cpus_mask(offline_mask); - if (cpuret) { - pr_err("%s: Could not bring present CPUs online.\n", __func__); - atomic_set(&data.error, cpuret); - goto out; - } - cpu_hotplug_disable(); - /* Check if we raced with a CPU-Offline Operation */ - if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) { - pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__); - atomic_set(&data.error, -EAGAIN); - goto out_hotplug_enable; - } - /* Call function on all CPUs. One of us will make the * rtas call */ @@ -1001,18 +889,11 @@ int rtas_ibm_suspend_me(u64 handle) if (atomic_read(&data.error) != 0) printk(KERN_ERR "Error doing global join\n"); -out_hotplug_enable: - cpu_hotplug_enable(); - /* Take down CPUs not online prior to suspend */ - cpuret = rtas_offline_cpus_mask(offline_mask); - if (cpuret) - pr_warn("%s: Could not restore CPUs to offline state.\n", - __func__); + cpu_hotplug_enable(); -out: unlock_device_hotplug(); - free_cpumask_var(offline_mask); + return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index bd91dceb7010..1740a66cea84 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -16,7 +16,7 @@ #include <asm/setup.h> -unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; +u64 powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; enum count_cache_flush_type { COUNT_CACHE_FLUSH_NONE = 0x1, @@ -109,7 +109,7 @@ device_initcall(barrier_nospec_debugfs_init); static __init int security_feature_debugfs_init(void) { debugfs_create_x64("security_features", 0400, powerpc_debugfs_root, - (u64 *)&powerpc_security_features); + &powerpc_security_features); return 0; } device_initcall(security_feature_debugfs_init); @@ -142,32 +142,33 @@ ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, cha thread_priv = security_ftr_enabled(SEC_FTR_L1D_THREAD_PRIV); - if (rfi_flush || thread_priv) { + if (rfi_flush) { struct seq_buf s; seq_buf_init(&s, buf, PAGE_SIZE - 1); - seq_buf_printf(&s, "Mitigation: "); - - if (rfi_flush) - seq_buf_printf(&s, "RFI Flush"); - - if (rfi_flush && thread_priv) - seq_buf_printf(&s, ", "); - + seq_buf_printf(&s, "Mitigation: RFI Flush"); if (thread_priv) - seq_buf_printf(&s, "L1D private per thread"); + seq_buf_printf(&s, ", L1D private per thread"); seq_buf_printf(&s, "\n"); return s.len; } + if (thread_priv) + return sprintf(buf, "Vulnerable: L1D private per thread\n"); + if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) && !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Vulnerable\n"); } + +ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_meltdown(dev, attr, buf); +} #endif ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index c82577c4b15d..1b02d338a5f5 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -8,6 +8,12 @@ #ifndef __ARCH_POWERPC_KERNEL_SETUP_H #define __ARCH_POWERPC_KERNEL_SETUP_H +#ifdef CONFIG_CC_IS_CLANG +#define __nostackprotector +#else +#define __nostackprotector __attribute__((__optimize__("no-stack-protector"))) +#endif + void initialize_cache_info(void); void irqstack_early_init(void); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 44b4c432a273..e50fbed36651 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -284,24 +284,42 @@ void __init record_spr_defaults(void) * device-tree is not accessible via normal means at this point. */ -void __init early_setup(unsigned long dt_ptr) +void __init __nostackprotector early_setup(unsigned long dt_ptr) { static __initdata struct paca_struct boot_paca; /* -------- printk is _NOT_ safe to use here ! ------- */ - /* Try new device tree based feature discovery ... */ - if (!dt_cpu_ftrs_init(__va(dt_ptr))) - /* Otherwise use the old style CPU table */ - identify_cpu(0, mfspr(SPRN_PVR)); - - /* Assume we're on cpu 0 for now. Don't write to the paca yet! */ + /* + * Assume we're on cpu 0 for now. + * + * We need to load a PACA very early for a few reasons. + * + * The stack protector canary is stored in the paca, so as soon as we + * call any stack protected code we need r13 pointing somewhere valid. + * + * If we are using kcov it will call in_task() in its instrumentation, + * which relies on the current task from the PACA. + * + * dt_cpu_ftrs_init() calls into generic OF/fdt code, as well as + * printk(), which can trigger both stack protector and kcov. + * + * percpu variables and spin locks also use the paca. + * + * So set up a temporary paca. It will be replaced below once we know + * what CPU we are on. + */ initialise_paca(&boot_paca, 0); setup_paca(&boot_paca); fixup_boot_paca(); /* -------- printk is now safe to use ------- */ + /* Try new device tree based feature discovery ... */ + if (!dt_cpu_ftrs_init(__va(dt_ptr))) + /* Otherwise use the old style CPU table */ + identify_cpu(0, mfspr(SPRN_PVR)); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); @@ -523,6 +541,8 @@ static bool __init parse_cache_info(struct device_node *np, lsizep = of_get_property(np, propnames[3], NULL); if (bsizep == NULL) bsizep = lsizep; + if (lsizep == NULL) + lsizep = bsizep; if (lsizep != NULL) lsize = be32_to_cpu(*lsizep); if (bsizep != NULL) diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e6c30cee6abf..d215f9554553 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -200,14 +200,27 @@ unsigned long get_tm_stackpointer(struct task_struct *tsk) * normal/non-checkpointed stack pointer. */ + unsigned long ret = tsk->thread.regs->gpr[1]; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BUG_ON(tsk != current); if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) { + preempt_disable(); tm_reclaim_current(TM_CAUSE_SIGNAL); if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr)) - return tsk->thread.ckpt_regs.gpr[1]; + ret = tsk->thread.ckpt_regs.gpr[1]; + + /* + * If we treclaim, we must clear the current thread's TM bits + * before re-enabling preemption. Otherwise we might be + * preempted and have the live MSR[TS] changed behind our back + * (tm_recheckpoint_new_task() would recheckpoint). Besides, we + * enter the signal handler in non-transactional state. + */ + tsk->thread.regs->msr &= ~MSR_TS_MASK; + preempt_enable(); } #endif - return tsk->thread.regs->gpr[1]; + return ret; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index ebb78effd280..6c18d58eca11 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -489,19 +489,11 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, */ static int save_tm_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, int sigret) + struct mcontext __user *tm_frame, int sigret, + unsigned long msr) { - unsigned long msr = regs->msr; - WARN_ON(tm_suspend_disabled); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - /* Save both sets of general registers */ if (save_general_regs(¤t->thread.ckpt_regs, frame) || save_general_regs(regs, tm_frame)) @@ -912,6 +904,10 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -944,13 +940,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_frame = &rt_sf->uc_transact.uc_mcontext; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (__put_user((unsigned long)&rt_sf->uc_transact, &rt_sf->uc.uc_link) || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs)) goto badframe; - if (save_tm_user_regs(regs, frame, tm_frame, sigret)) + if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr)) goto badframe; } else @@ -1369,6 +1365,10 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -1402,9 +1402,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_mctx = &frame->mctx_transact; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact, - sigret)) + sigret, msr)) goto badframe; } else diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index bee704f32f96..a521f82a789a 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -192,7 +192,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, struct task_struct *tsk, - int signr, sigset_t *set, unsigned long handler) + int signr, sigset_t *set, unsigned long handler, + unsigned long msr) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -207,12 +208,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif struct pt_regs *regs = tsk->thread.regs; - unsigned long msr = tsk->thread.regs->msr; long err = 0; BUG_ON(tsk != current); - BUG_ON(!MSR_TM_ACTIVE(regs->msr)); + BUG_ON(!MSR_TM_ACTIVE(msr)); WARN_ON(tm_suspend_disabled); @@ -222,13 +222,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, */ msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); err |= __put_user(tm_v_regs, &tm_sc->v_regs); @@ -480,8 +473,10 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, err |= __get_user(tsk->thread.ckpt_regs.ccr, &sc->gp_regs[PT_CCR]); + /* Don't allow userspace to set the trap value */ + regs->trap = 0; + /* These regs are not checkpointed; they can go in 'regs'. */ - err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]); err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]); err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]); err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]); @@ -824,6 +819,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, unsigned long newsp = 0; long err = 0; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -841,7 +840,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= __put_user(0, &frame->uc.uc_flags); err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { /* The ucontext_t passed to userland points to the second * ucontext_t (for transactional state) with its uc_link ptr. */ @@ -849,7 +848,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, tsk, ksig->sig, NULL, - (unsigned long)ksig->ka.sa.sa_handler); + (unsigned long)ksig->ka.sa.sa_handler, + msr); } else #endif { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 694522308cd5..0e0a2227af7d 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -232,7 +232,7 @@ static u64 scan_dispatch_log(u64 stop_tb) * Accumulate stolen time by scanning the dispatch trace log. * Called on entry from user mode. */ -void accumulate_stolen_time(void) +void notrace accumulate_stolen_time(void) { u64 sst, ust; unsigned long save_irq_soft_mask = irq_soft_mask_return(); @@ -522,35 +522,6 @@ static inline void clear_irq_work_pending(void) "i" (offsetof(struct paca_struct, irq_work_pending))); } -void arch_irq_work_raise(void) -{ - preempt_disable(); - set_irq_work_pending_flag(); - /* - * Non-nmi code running with interrupts disabled will replay - * irq_happened before it re-enables interrupts, so setthe - * decrementer there instead of causing a hardware exception - * which would immediately hit the masked interrupt handler - * and have the net effect of setting the decrementer in - * irq_happened. - * - * NMI interrupts can not check this when they return, so the - * decrementer hardware exception is raised, which will fire - * when interrupts are next enabled. - * - * BookE does not support this yet, it must audit all NMI - * interrupt handlers to ensure they call nmi_enter() so this - * check would be correct. - */ - if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) { - set_dec(1); - } else { - hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_DEC; - } - preempt_enable(); -} - #else /* 32-bit */ DEFINE_PER_CPU(u8, irq_work_pending); @@ -559,16 +530,27 @@ DEFINE_PER_CPU(u8, irq_work_pending); #define test_irq_work_pending() __this_cpu_read(irq_work_pending) #define clear_irq_work_pending() __this_cpu_write(irq_work_pending, 0) +#endif /* 32 vs 64 bit */ + void arch_irq_work_raise(void) { + /* + * 64-bit code that uses irq soft-mask can just cause an immediate + * interrupt here that gets soft masked, if this is called under + * local_irq_disable(). It might be possible to prevent that happening + * by noticing interrupts are disabled and setting decrementer pending + * to be replayed when irqs are enabled. The problem there is that + * tracing can call irq_work_raise, including in code that does low + * level manipulations of irq soft-mask state (e.g., trace_hardirqs_on) + * which could get tangled up if we're messing with the same state + * here. + */ preempt_disable(); set_irq_work_pending_flag(); set_dec(1); preempt_enable(); } -#endif /* 32 vs 64 bit */ - #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 @@ -959,6 +941,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec; vdso_data->stamp_xtime = xt; vdso_data->stamp_sec_fraction = frac_sec; + vdso_data->hrtimer_res = hrtimer_resolution; smp_wmb(); ++(vdso_data->tb_update_count); } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index c8ea3a253b81..88e1c6892648 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -250,15 +250,22 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, } NOKPROBE_SYMBOL(oops_end); +static char *get_mmu_str(void) +{ + if (early_radix_enabled()) + return " MMU=Radix"; + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return " MMU=Hash"; + return ""; +} + static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); - printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n", + printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n", IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE", - PAGE_SIZE / 1024, - early_radix_enabled() ? " MMU=Radix" : "", - early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "", + PAGE_SIZE / 1024, get_mmu_str(), IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", IS_ENABLED(CONFIG_SMP) ? " SMP" : "", IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "", diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index d60598113a9f..36849b693d86 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -704,7 +704,7 @@ int vdso_getcpu_init(void) node = cpu_to_node(cpu); WARN_ON_ONCE(node > 0xffff); - val = (cpu & 0xfff) | ((node & 0xffff) << 16); + val = (cpu & 0xffff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG_VDSO_WRITE, val); get_paca()->sprg_vdso = val; diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index becd9f8767ed..a967e795b96d 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -156,12 +156,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) cror cr0*4+eq,cr0*4+eq,cr1*4+eq bne cr0,99f + mflr r12 + .cfi_register lr,r12 + bl __get_datapage@local /* get data page */ + lwz r5, CLOCK_HRTIMER_RES(r3) + mtlr r12 li r3,0 cmpli cr0,r4,0 crclr cr0*4+so beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l stw r3,TSPC32_TV_SEC(r4) stw r5,TSPC32_TV_NSEC(r4) blr diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index 3f92561a64c4..526f5ba2593e 100644 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -35,7 +35,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index 07bfe33fe874..81757f06bbd7 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -186,12 +186,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) cror cr0*4+eq,cr0*4+eq,cr1*4+eq bne cr0,99f + mflr r12 + .cfi_register lr,r12 + bl V_LOCAL_FUNC(__get_datapage) + lwz r5, CLOCK_HRTIMER_RES(r3) + mtlr r12 li r3,0 cmpldi cr0,r4,0 crclr cr0*4+so beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l std r3,TSPC64_TV_SEC(r4) std r5,TSPC64_TV_NSEC(r4) blr diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 060a1acd7c6d..4638d2863388 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -326,6 +326,12 @@ SECTIONS *(.branch_lt) } +#ifdef CONFIG_DEBUG_INFO_BTF + .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { + *(.BTF) + } +#endif + .opd : AT(ADDR(.opd) - LOAD_OFFSET) { __start_opd = .; KEEP(*(.opd)) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index f53997a8ca62..b8e13d5a4a31 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -38,6 +38,7 @@ config KVM_BOOK3S_32_HANDLER config KVM_BOOK3S_64_HANDLER bool select KVM_BOOK3S_HANDLER + select PPC_DAWR_FORCE_ENABLE config KVM_BOOK3S_PR_POSSIBLE bool diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 08b2dfbc5305..56dbc2f6e3d2 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -38,7 +38,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, /* 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, - __pa(to), __pa(from), n); + (to != NULL) ? __pa(to): 0, + (from != NULL) ? __pa(from): 0, n); quadrant = 1; if (!pid) @@ -353,7 +354,13 @@ static struct kmem_cache *kvm_pmd_cache; static pte_t *kvmppc_pte_alloc(void) { - return kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL); + pte_t *pte; + + pte = kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL); + /* pmd_populate() will only reference _pa(pte). */ + kmemleak_ignore(pte); + + return pte; } static void kvmppc_pte_free(pte_t *ptep) @@ -369,7 +376,13 @@ static inline int pmd_is_leaf(pmd_t pmd) static pmd_t *kvmppc_pmd_alloc(void) { - return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); + pmd_t *pmd; + + pmd = kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); + /* pud_populate() will only reference _pa(pmd). */ + kmemleak_ignore(pmd); + + return pmd; } static void kvmppc_pmd_free(pmd_t *pmdp) diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 446d91d6cf70..2ae6ee1d5755 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -110,6 +110,7 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, struct kvmppc_spapr_tce_iommu_table *stit, *tmp; struct iommu_table_group *table_group = NULL; + rcu_read_lock(); list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) { table_group = iommu_group_get_iommudata(grp); @@ -124,7 +125,9 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, kref_put(&stit->kref, kvm_spapr_tce_liobn_put); } } + cond_resched_rcu(); } + rcu_read_unlock(); } extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, @@ -142,12 +145,14 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, if (!f.file) return -EBADF; + rcu_read_lock(); list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) { if (stt == f.file->private_data) { found = true; break; } } + rcu_read_unlock(); fdput(f); @@ -180,6 +185,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, if (!tbl) return -EINVAL; + rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { if (tbl != stit->tbl) continue; @@ -187,14 +193,17 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, if (!kref_get_unless_zero(&stit->kref)) { /* stit is being destroyed */ iommu_tce_table_put(tbl); + rcu_read_unlock(); return -ENOTTY; } /* * The table is already known to this KVM, we just increased * its KVM reference counter and can return. */ + rcu_read_unlock(); return 0; } + rcu_read_unlock(); stit = kzalloc(sizeof(*stit), GFP_KERNEL); if (!stit) { @@ -400,18 +409,19 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, if (kvmppc_tce_to_ua(stt->kvm, tce, &ua)) return H_TOO_HARD; + rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { unsigned long hpa = 0; struct mm_iommu_table_group_mem_t *mem; long shift = stit->tbl->it_page_shift; mem = mm_iommu_lookup(stt->kvm->mm, ua, 1ULL << shift); - if (!mem) - return H_TOO_HARD; - - if (mm_iommu_ua_to_hpa(mem, ua, shift, &hpa)) + if (!mem || mm_iommu_ua_to_hpa(mem, ua, shift, &hpa)) { + rcu_read_unlock(); return H_TOO_HARD; + } } + rcu_read_unlock(); return H_SUCCESS; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index f8975c620f41..cc4279bc6da6 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2351,7 +2351,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, mutex_unlock(&kvm->lock); if (!vcore) - goto free_vcpu; + goto uninit_vcpu; spin_lock(&vcore->lock); ++vcore->num_threads; @@ -2368,6 +2368,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, return vcpu; +uninit_vcpu: + kvm_vcpu_uninit(vcpu); free_vcpu: kmem_cache_free(kvm_vcpu_cache, vcpu); out: @@ -3618,6 +3620,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { kvmppc_nested_cede(vcpu); + kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } } else { diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index cc65af8fe6f7..3f6ad3f58628 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1769,10 +1769,12 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm, err = kvmppc_mmu_init(vcpu); if (err < 0) - goto uninit_vcpu; + goto free_shared_page; return vcpu; +free_shared_page: + free_page((unsigned long)vcpu->arch.shared); uninit_vcpu: kvm_vcpu_uninit(vcpu); free_shadow_vcpu: diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index a3f9c665bb5b..baa740815b3c 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -2005,6 +2005,10 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) pr_devel("Creating xive for partition\n"); + /* Already there ? */ + if (kvm->arch.xive) + return -EEXIST; + xive = kvmppc_xive_get_device(kvm, type); if (!xive) return -ENOMEM; @@ -2014,12 +2018,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->kvm = kvm; mutex_init(&xive->lock); - /* Already there ? */ - if (kvm->arch.xive) - ret = -EEXIST; - else - kvm->arch.xive = xive; - /* We use the default queue size set by the host */ xive->q_order = xive_native_default_eq_shift(); if (xive->q_order < PAGE_SHIFT) @@ -2039,6 +2037,7 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) if (ret) return ret; + kvm->arch.xive = xive; return 0; } diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 78b906ffa0d2..235d57d6c205 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -50,6 +50,24 @@ static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio) } } +static int kvmppc_xive_native_configure_queue(u32 vp_id, struct xive_q *q, + u8 prio, __be32 *qpage, + u32 order, bool can_escalate) +{ + int rc; + __be32 *qpage_prev = q->qpage; + + rc = xive_native_configure_queue(vp_id, q, prio, qpage, order, + can_escalate); + if (rc) + return rc; + + if (qpage_prev) + put_page(virt_to_page(qpage_prev)); + + return rc; +} + void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -582,19 +600,14 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, q->guest_qaddr = 0; q->guest_qshift = 0; - rc = xive_native_configure_queue(xc->vp_id, q, priority, - NULL, 0, true); + rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority, + NULL, 0, true); if (rc) { pr_err("Failed to reset queue %d for VCPU %d: %d\n", priority, xc->server_num, rc); return rc; } - if (q->qpage) { - put_page(virt_to_page(q->qpage)); - q->qpage = NULL; - } - return 0; } @@ -624,17 +637,18 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, srcu_idx = srcu_read_lock(&kvm->srcu); gfn = gpa_to_gfn(kvm_eq.qaddr); - page = gfn_to_page(kvm, gfn); - if (is_error_page(page)) { + + page_size = kvm_host_page_size(vcpu, gfn); + if (1ull << kvm_eq.qshift > page_size) { srcu_read_unlock(&kvm->srcu, srcu_idx); - pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr); + pr_warn("Incompatible host page size %lx!\n", page_size); return -EINVAL; } - page_size = kvm_host_page_size(kvm, gfn); - if (1ull << kvm_eq.qshift > page_size) { + page = gfn_to_page(kvm, gfn); + if (is_error_page(page)) { srcu_read_unlock(&kvm->srcu, srcu_idx); - pr_warn("Incompatible host page size %lx!\n", page_size); + pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr); return -EINVAL; } @@ -653,8 +667,8 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, * OPAL level because the use of END ESBs is not supported by * Linux. */ - rc = xive_native_configure_queue(xc->vp_id, q, priority, - (__be32 *) qaddr, kvm_eq.qshift, true); + rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority, + (__be32 *) qaddr, kvm_eq.qshift, true); if (rc) { pr_err("Failed to configure queue %d for VCPU %d: %d\n", priority, xc->server_num, rc); @@ -1081,7 +1095,6 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) dev->private = xive; xive->dev = dev; xive->kvm = kvm; - kvm->arch.xive = xive; mutex_init(&xive->mapping_lock); mutex_init(&xive->lock); @@ -1102,6 +1115,7 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) if (ret) return ret; + kvm->arch.xive = xive; return 0; } diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index 9208c82ed08d..88f62cf2dbb9 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -73,7 +73,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; u32 inst; - int ra, rs, rt; enum emulation_result emulated = EMULATE_FAIL; int advance = 1; struct instruction_op op; @@ -85,10 +84,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) if (emulated != EMULATE_DONE) return emulated; - ra = get_ra(inst); - rs = get_rs(inst); - rt = get_rt(inst); - /* * if mmio_vsx_tx_sx_enabled == 0, copy data between * VSR[0..31] and memory diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S index f69a6aab7bfb..1ddb26394e8a 100644 --- a/arch/powerpc/lib/string_32.S +++ b/arch/powerpc/lib/string_32.S @@ -17,7 +17,7 @@ CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT CACHELINE_MASK = (L1_CACHE_BYTES-1) -_GLOBAL(__clear_user) +_GLOBAL(__arch_clear_user) /* * Use dcbz on the complete cache lines in the destination * to set them to zero. This requires that the destination @@ -87,4 +87,4 @@ _GLOBAL(__clear_user) EX_TABLE(8b, 91b) EX_TABLE(9b, 91b) -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index 507b18b1660e..169872bc0892 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -17,7 +17,7 @@ PPC64_CACHES: .section ".text" /** - * __clear_user: - Zero a block of memory in user space, with less checking. + * __arch_clear_user: - Zero a block of memory in user space, with less checking. * @to: Destination address, in user space. * @n: Number of bytes to zero. * @@ -58,7 +58,7 @@ err3; stb r0,0(r3) mr r3,r4 blr -_GLOBAL_TOC(__clear_user) +_GLOBAL_TOC(__arch_clear_user) cmpdi r4,32 neg r6,r3 li r0,0 @@ -181,4 +181,4 @@ err1; dcbz 0,r3 cmpdi r4,32 blt .Lshort_clear b .Lmedium_clear -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 8d68f03bf5a4..55c0208e7bfd 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -187,6 +187,7 @@ void mmu_mark_initmem_nx(void) int i; unsigned long base = (unsigned long)_stext - PAGE_OFFSET; unsigned long top = (unsigned long)_etext - PAGE_OFFSET; + unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; unsigned long size; if (cpu_has_feature(CPU_FTR_601)) @@ -201,9 +202,10 @@ void mmu_mark_initmem_nx(void) size = block_size(base, top); size = max(size, 128UL << 10); if ((top - base) > size) { - if (strict_kernel_rwx_enabled()) - pr_warn("Kernel _etext not properly aligned\n"); size <<= 1; + if (strict_kernel_rwx_enabled() && base + size > border) + pr_warn("Some RW data is getting mapped X. " + "Adjust CONFIG_DATA_SHIFT to avoid that.\n"); } setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); base += size; diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 64340fc677bb..1f46f7180363 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -297,10 +297,18 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot, HPTE_V_BOLTED, psize, psize, ssize); - + if (ret == -1) { + /* Try to remove a non bolted entry */ + ret = mmu_hash_ops.hpte_remove(hpteg); + if (ret != -1) + ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot, + HPTE_V_BOLTED, psize, psize, + ssize); + } if (ret < 0) break; + cond_resched(); #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled() && (paddr >> PAGE_SHIFT) < linear_map_hash_count) diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 01bc9663360d..c7e3cc805cef 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -354,7 +354,6 @@ static inline void pgtable_free(void *table, int index) } } -#ifdef CONFIG_SMP void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index) { unsigned long pgf = (unsigned long)table; @@ -371,12 +370,6 @@ void __tlb_remove_table(void *_table) return pgtable_free(table, index); } -#else -void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index) -{ - return pgtable_free(table, index); -} -#endif #ifdef CONFIG_PROC_FS atomic_long_t direct_pages_count[MMU_PAGE_COUNT]; diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index ae7fca40e5b3..432fd9fa8c3f 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -83,13 +83,17 @@ static int pkey_initialize(void) scan_pkey_feature(); /* - * Let's assume 32 pkeys on P8 bare metal, if its not defined by device - * tree. We make this exception since skiboot forgot to expose this - * property on power8. + * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device + * tree. We make this exception since some version of skiboot forgot to + * expose this property on power8/9. */ - if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) && - cpu_has_feature(CPU_FTRS_POWER8)) - pkeys_total = 32; + if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR)) { + 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) + pkeys_total = 32; + } /* * Adjust the upper limit, based on the number of bits supported by @@ -367,12 +371,14 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) return true; pkey_shift = pkeyshift(pkey); - if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift))) - return true; + if (execute) + return !(read_iamr() & (IAMR_EX_BIT << pkey_shift)); + + amr = read_amr(); + if (write) + return !(amr & (AMR_WR_BIT << pkey_shift)); - amr = read_amr(); /* Delay reading amr until absolutely needed */ - return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) || - (write && !(amr & (AMR_WR_BIT << pkey_shift)))); + return !(amr & (AMR_RD_BIT << pkey_shift)); } bool arch_pte_access_permitted(u64 pte, bool write, bool execute) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index ec6b7ad70659..74b3a03a578e 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -254,7 +254,7 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code, // Read/write fault in a valid region (the exception table search passed // above), but blocked by KUAP is bad, it can never succeed. - if (bad_kuap_fault(regs, is_write)) + if (bad_kuap_fault(regs, address, is_write)) return true; // What's left? Kernel fault on user in well defined regions (extable @@ -262,6 +262,9 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code, return false; } +// This comes from 64-bit struct rt_sigframe + __SIGNAL_FRAMESIZE +#define SIGFRAME_MAX_SIZE (4096 + 128) + static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, struct vm_area_struct *vma, unsigned int flags, bool *must_retry) @@ -269,7 +272,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, /* * N.B. The POWER/Open ABI allows programs to access up to * 288 bytes below the stack pointer. - * The kernel signal delivery code writes up to about 1.5kB + * The kernel signal delivery code writes a bit over 4KB * below the stack pointer (r1) before decrementing it. * The exec code can write slightly over 640kB to the stack * before setting the user r1. Thus we allow the stack to @@ -294,7 +297,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, * between the last mapped region and the stack will * expand the stack rather than segfaulting. */ - if (address + 2048 >= uregs->gpr[1]) + if (address + SIGFRAME_MAX_SIZE >= uregs->gpr[1]) return false; if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) && @@ -375,6 +378,9 @@ static void sanity_check_fault(bool is_write, bool is_user, * Userspace trying to access kernel address, we get PROTFAULT for that. */ if (is_user && address >= TASK_SIZE) { + if ((long)address == -1) + return; + pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n", current->comm, current->pid, address, from_kuid(&init_user_ns, current_uid())); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1de0f43a68e5..e8157325e089 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -53,20 +53,29 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (pshift >= pdshift) { cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + new = NULL; } else if (IS_ENABLED(CONFIG_PPC_8xx)) { - cachep = PGT_CACHE(PTE_INDEX_SIZE); + cachep = NULL; num_hugepd = 1; + new = pte_alloc_one(mm); } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; + new = NULL; } - new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + if (!cachep && !new) { + WARN_ONCE(1, "No page table cache created for hugetlb tables"); + return -ENOMEM; + } + + if (cachep) + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); - if (! new) + if (!new) return -ENOMEM; /* @@ -92,7 +101,10 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (i < num_hugepd) { for (i = i - 1 ; i >= 0; i--, hpdp--) *hpdp = __hugepd(0); - kmem_cache_free(cachep, new); + if (cachep) + kmem_cache_free(cachep, new); + else + pte_free(mm, new); } else { kmemleak_ignore(new); } @@ -319,8 +331,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else if (IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_free_tlb(tlb, hugepte, - get_hugepd_cache_index(PTE_INDEX_SIZE)); + pgtable_free_tlb(tlb, hugepte, 0); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -519,13 +530,6 @@ retry: return page; } -static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, - unsigned long sz) -{ - unsigned long __boundary = (addr + sz) & ~(sz-1); - return (__boundary - 1 < end - 1) ? __boundary : end; -} - #ifdef CONFIG_PPC_MM_SLICES unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, @@ -596,6 +600,7 @@ __setup("hugepagesz=", hugepage_setup_sz); static int __init hugetlbpage_init(void) { + bool configured = false; int psize; if (hugetlb_disabled) { @@ -640,16 +645,22 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_cache_add(PTE_INDEX_SIZE); - else if (pdshift > shift) - pgtable_cache_add(pdshift - shift); - else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx)) + if (pdshift > shift) { + if (!IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(pdshift - shift); + } else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || + IS_ENABLED(CONFIG_PPC_8xx)) { pgtable_cache_add(PTE_T_ORDER); + } + + configured = true; } - if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE)) - hugetlbpage_init_default(); + if (configured) { + if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE)) + hugetlbpage_init_default(); + } else + pr_info("Failed to initialize. Disabling HugeTLB"); return 0; } @@ -673,68 +684,3 @@ void flush_dcache_icache_hugepage(struct page *page) } } } - -static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - unsigned long pte_end; - struct page *head, *page; - pte_t pte; - int refs; - - pte_end = (addr + sz) & ~(sz-1); - if (pte_end < end) - end = pte_end; - - pte = READ_ONCE(*ptep); - - if (!pte_access_permitted(pte, write)) - return 0; - - /* hugepages are never "special" */ - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - refs = 0; - head = pte_page(pte); - - page = head + ((addr & (sz-1)) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - if (!page_cache_add_speculative(head, refs)) { - *nr -= refs; - return 0; - } - - if (unlikely(pte_val(pte) != pte_val(*ptep))) { - /* Could be optimized better */ - *nr -= refs; - while (refs--) - put_page(head); - return 0; - } - - return 1; -} - -int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift, - unsigned long end, int write, struct page **pages, int *nr) -{ - pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(hugepd); - unsigned long next; - - ptep = hugepte_offset(hugepd, addr, pdshift); - do { - next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr)) - return 0; - } while (ptep++, addr = next, addr != end); - - return 1; -} diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 0e6ed4413eea..1cfe57b51d7e 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -117,7 +117,7 @@ static void __init kasan_remap_early_shadow_ro(void) kasan_populate_pte(kasan_early_shadow_pte, prot); - for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) { + for (k_cur = k_start & PAGE_MASK; k_cur != k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur); pte_t *ptep = pte_offset_kernel(pmd, k_cur); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 2eda1ec36f55..99fcdf73f207 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -270,6 +270,14 @@ void __init mem_init(void) BUILD_BUG_ON(MMU_PAGE_COUNT > 16); #ifdef CONFIG_SWIOTLB + /* + * Some platforms (e.g. 85xx) limit DMA-able memory way below + * 4G. We force memblock to bottom-up mode to ensure that the + * memory allocated in swiotlb_init() is DMA-able. + * As it's the last memblock allocation, no need to reset it + * back to to-down. + */ + memblock_set_bottom_up(true); swiotlb_init(0); #endif diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S index 2ca407cedbe7..eaeee402f96e 100644 --- a/arch/powerpc/mm/nohash/tlb_low.S +++ b/arch/powerpc/mm/nohash/tlb_low.S @@ -397,7 +397,7 @@ _GLOBAL(set_context) * extern void loadcam_entry(unsigned int index) * * Load TLBCAM[index] entry in to the L2 CAM MMU - * Must preserve r7, r8, r9, and r10 + * Must preserve r7, r8, r9, r10 and r11 */ _GLOBAL(loadcam_entry) mflr r5 @@ -433,6 +433,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) */ _GLOBAL(loadcam_multi) mflr r8 + /* Don't switch to AS=1 if already there */ + mfmsr r11 + andi. r11,r11,MSR_IS + bne 10f /* * Set up temporary TLB entry that is the same as what we're @@ -458,6 +462,7 @@ _GLOBAL(loadcam_multi) mtmsr r6 isync +10: mr r9,r3 add r10,r3,r4 2: bl loadcam_entry @@ -466,6 +471,10 @@ _GLOBAL(loadcam_multi) mr r3,r9 blt 2b + /* Don't return to AS=0 if we were in AS=1 at function start */ + andi. r11,r11,MSR_IS + bne 3f + /* Return to AS=0 and clear the temporary entry */ mfmsr r6 rlwinm. r6,r6,0,~(MSR_IS|MSR_DS) @@ -481,6 +490,7 @@ _GLOBAL(loadcam_multi) tlbwe isync +3: mtlr r8 blr #endif diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 35cb96cfc258..5159445a21dd 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -360,7 +360,7 @@ void mark_initmem_nx(void) unsigned long numpages = PFN_UP((unsigned long)_einittext) - PFN_DOWN((unsigned long)_sinittext); - if (v_block_mapped((unsigned long)_stext + 1)) + if (v_block_mapped((unsigned long)_sinittext)) mmu_mark_initmem_nx(); else change_page_attr(page, numpages, PAGE_KERNEL); @@ -372,8 +372,9 @@ void mark_rodata_ro(void) struct page *page; unsigned long numpages; - if (v_block_mapped((unsigned long)_sinittext)) { + if (v_block_mapped((unsigned long)_stext + 1)) { mmu_mark_rodata_ro(); + ptdump_check_wx(); return; } diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c index b69912854dc3..485363358395 100644 --- a/arch/powerpc/mm/ptdump/ptdump.c +++ b/arch/powerpc/mm/ptdump/ptdump.c @@ -62,6 +62,7 @@ struct pg_state { unsigned long start_address; unsigned long start_pa; unsigned long last_pa; + unsigned long page_size; unsigned int level; u64 current_flags; bool check_wx; @@ -163,9 +164,9 @@ static void dump_addr(struct pg_state *st, unsigned long addr) #endif pt_dump_seq_printf(st->seq, REG "-" REG " ", st->start_address, addr - 1); - if (st->start_pa == st->last_pa && st->start_address + PAGE_SIZE != addr) { + if (st->start_pa == st->last_pa && st->start_address + st->page_size != addr) { pt_dump_seq_printf(st->seq, "[" REG "]", st->start_pa); - delta = PAGE_SIZE >> 10; + delta = st->page_size >> 10; } else { pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa); delta = (addr - st->start_address) >> 10; @@ -181,10 +182,12 @@ static void dump_addr(struct pg_state *st, unsigned long addr) static void note_prot_wx(struct pg_state *st, unsigned long addr) { + pte_t pte = __pte(st->current_flags); + if (!st->check_wx) return; - if (!((st->current_flags & pgprot_val(PAGE_KERNEL_X)) == pgprot_val(PAGE_KERNEL_X))) + if (!pte_write(pte) || !pte_exec(pte)) return; WARN_ONCE(1, "powerpc/mm: Found insecure W+X mapping at address %p/%pS\n", @@ -194,7 +197,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr) } static void note_page(struct pg_state *st, unsigned long addr, - unsigned int level, u64 val) + unsigned int level, u64 val, unsigned long page_size) { u64 flag = val & pg_level[level].mask; u64 pa = val & PTE_RPN_MASK; @@ -206,6 +209,7 @@ static void note_page(struct pg_state *st, unsigned long addr, st->start_address = addr; st->start_pa = pa; st->last_pa = pa; + st->page_size = page_size; pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); /* * Dump the section of virtual memory when: @@ -217,7 +221,7 @@ static void note_page(struct pg_state *st, unsigned long addr, */ } else if (flag != st->current_flags || level != st->level || addr >= st->marker[1].start_address || - (pa != st->last_pa + PAGE_SIZE && + (pa != st->last_pa + st->page_size && (pa != st->start_pa || st->start_pa != st->last_pa))) { /* Check the PTE flags */ @@ -245,6 +249,7 @@ static void note_page(struct pg_state *st, unsigned long addr, st->start_address = addr; st->start_pa = pa; st->last_pa = pa; + st->page_size = page_size; st->current_flags = flag; st->level = level; } else { @@ -260,7 +265,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) for (i = 0; i < PTRS_PER_PTE; i++, pte++) { addr = start + i * PAGE_SIZE; - note_page(st, addr, 4, pte_val(*pte)); + note_page(st, addr, 4, pte_val(*pte), PAGE_SIZE); } } @@ -277,7 +282,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) /* pmd exists */ walk_pte(st, pmd, addr); else - note_page(st, addr, 3, pmd_val(*pmd)); + note_page(st, addr, 3, pmd_val(*pmd), PMD_SIZE); } } @@ -293,7 +298,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) /* pud exists */ walk_pmd(st, pud, addr); else - note_page(st, addr, 2, pud_val(*pud)); + note_page(st, addr, 2, pud_val(*pud), PUD_SIZE); } } @@ -314,7 +319,7 @@ static void walk_pagetables(struct pg_state *st) /* pgd exists */ walk_pud(st, pgd, addr); else - note_page(st, addr, 1, pgd_val(*pgd)); + note_page(st, addr, 1, pgd_val(*pgd), PGDIR_SIZE); } } @@ -373,7 +378,7 @@ static int ptdump_show(struct seq_file *m, void *v) /* Traverse kernel page tables */ walk_pagetables(&st); - note_page(&st, 0, 0, 0); + note_page(&st, 0, 0, 0, 0); return 0; } diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c index f7ed2f187cb0..784f8df17f73 100644 --- a/arch/powerpc/mm/ptdump/shared.c +++ b/arch/powerpc/mm/ptdump/shared.c @@ -31,6 +31,11 @@ static const struct flag_info flag_array[] = { .set = "present", .clear = " ", }, { + .mask = _PAGE_COHERENT, + .val = _PAGE_COHERENT, + .set = "coherent", + .clear = " ", + }, { .mask = _PAGE_GUARDED, .val = _PAGE_GUARDED, .set = "guarded", diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 42bbcd47cc85..dffe1a45b6ed 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -50,7 +50,7 @@ static void slice_print_mask(const char *label, const struct slice_mask *mask) { #endif -static inline bool slice_addr_is_low(unsigned long addr) +static inline notrace bool slice_addr_is_low(unsigned long addr) { u64 tmp = (u64)addr; @@ -659,7 +659,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, mm_ctx_user_psize(¤t->mm->context), 1); } -unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) +unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr) { unsigned char *psizes; int index, mask_index; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index c2ee6041f02c..4d09d0a6e899 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -1112,6 +1112,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) } /* + * If we have seen a tail call, we need a second pass. + * This is because bpf_jit_emit_common_epilogue() is called + * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen. + */ + if (cgctx.seen & SEEN_TAILCALL) { + cgctx.idx = 0; + if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) { + fp = org_fp; + goto out_addrs; + } + } + + /* * Pretend to build prologue, given the features we've seen. This will * update ctgtx.idx as it pretends to output instructions, then we can * calculate total size from idx. diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index faad5b315f49..5834ac3dd474 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1400,16 +1400,6 @@ static void h_24x7_event_read(struct perf_event *event) h24x7hw = &get_cpu_var(hv_24x7_hw); h24x7hw->events[i] = event; put_cpu_var(h24x7hw); - /* - * Clear the event count so we can compute the _change_ - * in the 24x7 raw counter value at the end of the txn. - * - * Note that we could alternatively read the 24x7 value - * now and save its value in event->hw.prev_count. But - * that would require issuing a hcall, which would then - * defeat the purpose of using the txn interface. - */ - local64_set(&event->count, 0); } put_cpu_var(hv_24x7_reqb); diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c index e6e2adcc7b64..c13d64c3b019 100644 --- a/arch/powerpc/platforms/4xx/pci.c +++ b/arch/powerpc/platforms/4xx/pci.c @@ -1242,7 +1242,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) if (mbase == NULL) { printk(KERN_ERR "%pOF: Can't map internal config space !", port->node); - goto done; + return; } while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA) @@ -1252,9 +1252,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) } if (attempt) port->link = 1; -done: iounmap(mbase); - } static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = { diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 2794235e9d3e..98d824563b35 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -379,7 +379,7 @@ config PPC_KUAP config PPC_KUAP_DEBUG bool "Extra debugging for Kernel Userspace Access Protection" - depends on PPC_HAVE_KUAP && (PPC_RADIX_MMU || PPC_32) + depends on PPC_KUAP && (PPC_RADIX_MMU || PPC32) help Add extra debugging for Kernel Userspace Access Protection (KUAP) If you're unsure, say N. diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index d40253a18b1c..512c87bc20a3 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1978,8 +1978,9 @@ static ssize_t __spufs_mbox_info_read(struct spu_context *ctx, static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { - int ret; struct spu_context *ctx = file->private_data; + u32 stat, data; + int ret; if (!access_ok(buf, len)) return -EFAULT; @@ -1988,11 +1989,16 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_mbox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.prob.pu_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + /* EOF if there's no entry in the mbox */ + if (!(stat & 0x0000ff)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); } static const struct file_operations spufs_mbox_info_fops = { @@ -2019,6 +2025,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + u32 stat, data; int ret; if (!access_ok(buf, len)) @@ -2028,11 +2035,16 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_ibox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.priv2.puint_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + /* EOF if there's no entry in the ibox */ + if (!(stat & 0xff0000)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); } static const struct file_operations spufs_ibox_info_fops = { @@ -2041,6 +2053,11 @@ static const struct file_operations spufs_ibox_info_fops = { .llseek = generic_file_llseek, }; +static size_t spufs_wbox_info_cnt(struct spu_context *ctx) +{ + return (4 - ((ctx->csa.prob.mb_stat_R & 0x00ff00) >> 8)) * sizeof(u32); +} + static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { @@ -2049,7 +2066,7 @@ static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, u32 wbox_stat; wbox_stat = ctx->csa.prob.mb_stat_R; - cnt = 4 - ((wbox_stat & 0x00ff00) >> 8); + cnt = spufs_wbox_info_cnt(ctx); for (i = 0; i < cnt; i++) { data[i] = ctx->csa.spu_mailbox_data[i]; } @@ -2062,7 +2079,8 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; - int ret; + u32 data[ARRAY_SIZE(ctx->csa.spu_mailbox_data)]; + int ret, count; if (!access_ok(buf, len)) return -EFAULT; @@ -2071,11 +2089,13 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_wbox_info_read(ctx, buf, len, pos); + count = spufs_wbox_info_cnt(ctx); + memcpy(&data, &ctx->csa.spu_mailbox_data, sizeof(data)); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &data, + count * sizeof(u32)); } static const struct file_operations spufs_wbox_info_fops = { @@ -2084,27 +2104,33 @@ static const struct file_operations spufs_wbox_info_fops = { .llseek = generic_file_llseek, }; -static ssize_t __spufs_dma_info_read(struct spu_context *ctx, - char __user *buf, size_t len, loff_t *pos) +static void spufs_get_dma_info(struct spu_context *ctx, + struct spu_dma_info *info) { - struct spu_dma_info info; - struct mfc_cq_sr *qp, *spuqp; int i; - info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; - info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; - info.dma_info_status = ctx->csa.spu_chnldata_RW[24]; - info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; - info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; + info->dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; + info->dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; + info->dma_info_status = ctx->csa.spu_chnldata_RW[24]; + info->dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; + info->dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; for (i = 0; i < 16; i++) { - qp = &info.dma_info_command_data[i]; - spuqp = &ctx->csa.priv2.spuq[i]; + struct mfc_cq_sr *qp = &info->dma_info_command_data[i]; + struct mfc_cq_sr *spuqp = &ctx->csa.priv2.spuq[i]; qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW; qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW; qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW; qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW; } +} + +static ssize_t __spufs_dma_info_read(struct spu_context *ctx, + char __user *buf, size_t len, loff_t *pos) +{ + struct spu_dma_info info; + + spufs_get_dma_info(ctx, &info); return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2114,6 +2140,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_dma_info info; int ret; if (!access_ok(buf, len)) @@ -2123,11 +2150,12 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_dma_info_read(ctx, buf, len, pos); + spufs_get_dma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); } static const struct file_operations spufs_dma_info_fops = { @@ -2136,13 +2164,31 @@ static const struct file_operations spufs_dma_info_fops = { .llseek = no_llseek, }; +static void spufs_get_proxydma_info(struct spu_context *ctx, + struct spu_proxydma_info *info) +{ + int i; + + info->proxydma_info_type = ctx->csa.prob.dma_querytype_RW; + info->proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; + info->proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; + + for (i = 0; i < 8; i++) { + struct mfc_cq_sr *qp = &info->proxydma_info_command_data[i]; + struct mfc_cq_sr *puqp = &ctx->csa.priv2.puq[i]; + + qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; + qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; + qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; + qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; + } +} + static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { struct spu_proxydma_info info; - struct mfc_cq_sr *qp, *puqp; int ret = sizeof info; - int i; if (len < ret) return -EINVAL; @@ -2150,18 +2196,7 @@ static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, if (!access_ok(buf, len)) return -EFAULT; - info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW; - info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; - info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; - for (i = 0; i < 8; i++) { - qp = &info.proxydma_info_command_data[i]; - puqp = &ctx->csa.priv2.puq[i]; - - qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; - qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; - qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; - qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; - } + spufs_get_proxydma_info(ctx, &info); return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2171,17 +2206,19 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_proxydma_info info; int ret; ret = spu_acquire_saved(ctx); if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_proxydma_info_read(ctx, buf, len, pos); + spufs_get_proxydma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); } static const struct file_operations spufs_proxydma_info_fops = { diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 9cd6f3e1000b..09a0594350b6 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -294,23 +294,6 @@ static int __init maple_probe(void) return 1; } -define_machine(maple) { - .name = "Maple", - .probe = maple_probe, - .setup_arch = maple_setup_arch, - .init_IRQ = maple_init_IRQ, - .pci_irq_fixup = maple_pci_irq_fixup, - .pci_get_legacy_ide_irq = maple_pci_get_legacy_ide_irq, - .restart = maple_restart, - .halt = maple_halt, - .get_boot_time = maple_get_boot_time, - .set_rtc_time = maple_set_rtc_time, - .get_rtc_time = maple_get_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = maple_progress, - .power_save = power4_idle, -}; - #ifdef CONFIG_EDAC /* * Register a platform device for CPC925 memory controller on @@ -367,3 +350,20 @@ static int __init maple_cpc925_edac_setup(void) } machine_device_initcall(maple, maple_cpc925_edac_setup); #endif + +define_machine(maple) { + .name = "Maple", + .probe = maple_probe, + .setup_arch = maple_setup_arch, + .init_IRQ = maple_init_IRQ, + .pci_irq_fixup = maple_pci_irq_fixup, + .pci_get_legacy_ide_irq = maple_pci_get_legacy_ide_irq, + .restart = maple_restart, + .halt = maple_halt, + .get_boot_time = maple_get_boot_time, + .set_rtc_time = maple_set_rtc_time, + .get_rtc_time = maple_get_rtc_time, + .calibrate_decr = generic_calibrate_decr, + .progress = maple_progress, + .power_save = power4_idle, +}; diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index fd14a6237954..28330c150d4f 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -1155,10 +1155,10 @@ static void __init pnv_power9_idle_init(void) pnv_deepest_stop_psscr_mask); } - pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%lld\n", + pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n", pnv_first_spr_loss_level); - pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%lld\n", + pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n", pnv_first_tb_loss_level); } diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index e04b20625cb9..000b350d4060 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -59,10 +59,6 @@ static void export_imc_mode_and_cmd(struct device_node *node, imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root); - /* - * Return here, either because 'imc' directory already exists, - * Or failed to create a new one. - */ if (!imc_debugfs_parent) return; @@ -135,7 +131,6 @@ static int imc_get_mem_addr_nest(struct device_node *node, } pmu_ptr->imc_counter_mmaped = true; - export_imc_mode_and_cmd(node, pmu_ptr); kfree(base_addr_arr); kfree(chipid_arr); return 0; @@ -151,7 +146,7 @@ error: * and domain as the inputs. * Allocates memory for the struct imc_pmu, sets up its domain, size and offsets */ -static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) +static struct imc_pmu *imc_pmu_create(struct device_node *parent, int pmu_index, int domain) { int ret = 0; struct imc_pmu *pmu_ptr; @@ -159,27 +154,23 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) /* Return for unknown domain */ if (domain < 0) - return -EINVAL; + return NULL; /* memory for pmu */ pmu_ptr = kzalloc(sizeof(*pmu_ptr), GFP_KERNEL); if (!pmu_ptr) - return -ENOMEM; + return NULL; /* Set the domain */ pmu_ptr->domain = domain; ret = of_property_read_u32(parent, "size", &pmu_ptr->counter_mem_size); - if (ret) { - ret = -EINVAL; + if (ret) goto free_pmu; - } if (!of_property_read_u32(parent, "offset", &offset)) { - if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) { - ret = -EINVAL; + if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) goto free_pmu; - } } /* Function to register IMC pmu */ @@ -190,14 +181,14 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) if (pmu_ptr->domain == IMC_DOMAIN_NEST) kfree(pmu_ptr->mem_info); kfree(pmu_ptr); - return ret; + return NULL; } - return 0; + return pmu_ptr; free_pmu: kfree(pmu_ptr); - return ret; + return NULL; } static void disable_nest_pmu_counters(void) @@ -254,6 +245,7 @@ int get_max_nest_dev(void) static int opal_imc_counters_probe(struct platform_device *pdev) { struct device_node *imc_dev = pdev->dev.of_node; + struct imc_pmu *pmu; int pmu_count = 0, domain; bool core_imc_reg = false, thread_imc_reg = false; u32 type; @@ -269,6 +261,7 @@ static int opal_imc_counters_probe(struct platform_device *pdev) } for_each_compatible_node(imc_dev, NULL, IMC_DTB_UNIT_COMPAT) { + pmu = NULL; if (of_property_read_u32(imc_dev, "type", &type)) { pr_warn("IMC Device without type property\n"); continue; @@ -285,7 +278,14 @@ static int opal_imc_counters_probe(struct platform_device *pdev) domain = IMC_DOMAIN_THREAD; break; case IMC_TYPE_TRACE: - domain = IMC_DOMAIN_TRACE; + /* + * FIXME. Using trace_imc events to monitor application + * or KVM thread performance can cause a checkstop + * (system crash). + * Disable it for now. + */ + pr_info_once("IMC: disabling trace_imc PMU\n"); + domain = -1; break; default: pr_warn("IMC Unknown Device type \n"); @@ -293,9 +293,13 @@ static int opal_imc_counters_probe(struct platform_device *pdev) break; } - if (!imc_pmu_create(imc_dev, pmu_count, domain)) { - if (domain == IMC_DOMAIN_NEST) + pmu = imc_pmu_create(imc_dev, pmu_count, domain); + if (pmu != NULL) { + if (domain == IMC_DOMAIN_NEST) { + if (!imc_debugfs_parent) + export_imc_mode_and_cmd(imc_dev, pmu); pmu_count++; + } if (domain == IMC_DOMAIN_CORE) core_imc_reg = true; if (domain == IMC_DOMAIN_THREAD) @@ -303,10 +307,6 @@ static int opal_imc_counters_probe(struct platform_device *pdev) } } - /* If none of the nest units are registered, remove debugfs interface */ - if (pmu_count == 0) - debugfs_remove_recursive(imc_debugfs_parent); - /* If core imc is not registered, unregister thread-imc */ if (!core_imc_reg && thread_imc_reg) unregister_thread_imc(); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 0f72c7484824..050131e886f1 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1556,6 +1556,10 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) /* Reserve PE for each VF */ for (vf_index = 0; vf_index < num_vfs; vf_index++) { + int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index); + int vf_bus = pci_iov_virtfn_bus(pdev, vf_index); + struct pci_dn *vf_pdn; + if (pdn->m64_single_mode) pe_num = pdn->pe_num_map[vf_index]; else @@ -1568,13 +1572,11 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) pe->pbus = NULL; pe->parent_dev = pdev; pe->mve_number = -1; - pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) | - pci_iov_virtfn_devfn(pdev, vf_index); + pe->rid = (vf_bus << 8) | vf_devfn; pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n", hose->global_number, pdev->bus->number, - PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)), - PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num); + PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num); if (pnv_ioda_configure_pe(phb, pe)) { /* XXX What do we do here ? */ @@ -1588,6 +1590,15 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) list_add_tail(&pe->list, &phb->ioda.pe_list); mutex_unlock(&phb->ioda.pe_list_mutex); + /* associate this pe to it's pdn */ + list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) { + if (vf_pdn->busno == vf_bus && + vf_pdn->devfn == vf_devfn) { + vf_pdn->pe_number = pe_num; + break; + } + } + pnv_pci_ioda2_setup_dma_pe(phb, pe); #ifdef CONFIG_IOMMU_API iommu_register_group(&pe->table_group, @@ -2897,9 +2908,6 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) struct pci_dn *pdn; int mul, total_vfs; - if (!pdev->is_physfn || pci_dev_is_added(pdev)) - return; - pdn = pci_get_pdn(pdev); pdn->vfs_expanded = 0; pdn->m64_single_mode = false; @@ -2974,6 +2982,30 @@ truncate_iov: res->end = res->start - 1; } } + +static void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev) +{ + if (WARN_ON(pci_dev_is_added(pdev))) + return; + + if (pdev->is_virtfn) { + struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev); + + /* + * VF PEs are single-device PEs so their pdev pointer needs to + * be set. The pdev doesn't exist when the PE is allocated (in + * (pcibios_sriov_enable()) so we fix it up here. + */ + pe->pdev = pdev; + WARN_ON(!(pe->flags & PNV_IODA_PE_VF)); + } else if (pdev->is_physfn) { + /* + * For PFs adjust their allocated IOV resources to match what + * the PHB can support using it's M64 BAR table. + */ + pnv_pci_ioda_fixup_iov_resources(pdev); + } +} #endif /* CONFIG_PCI_IOV */ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, @@ -3870,7 +3902,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, ppc_md.pcibios_default_alignment = pnv_pci_default_alignment; #ifdef CONFIG_PCI_IOV - ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; + ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov; ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment; ppc_md.pcibios_sriov_enable = pnv_pcibios_sriov_enable; ppc_md.pcibios_sriov_disable = pnv_pcibios_sriov_disable; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index ff1a33fee8e6..2bfb72d057a7 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -814,24 +814,6 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; -#ifdef CONFIG_PCI_IOV - struct pnv_ioda_pe *pe; - struct pci_dn *pdn; - - /* Fix the VF pdn PE number */ - if (pdev->is_virtfn) { - pdn = pci_get_pdn(pdev); - WARN_ON(pdn->pe_number != IODA_INVALID_PE); - list_for_each_entry(pe, &phb->ioda.pe_list, list) { - if (pe->rid == ((pdev->bus->number << 8) | - (pdev->devfn & 0xff))) { - pdn->pe_number = pe->pe_number; - pe->pdev = pdev; - break; - } - } - } -#endif /* CONFIG_PCI_IOV */ if (phb && phb->dma_dev_setup) phb->dma_dev_setup(phb, pdev); @@ -1089,6 +1071,23 @@ void __init pnv_pci_init(void) if (!firmware_has_feature(FW_FEATURE_OPAL)) return; +#ifdef CONFIG_PCIEPORTBUS + /* + * On PowerNV PCIe devices are (currently) managed in cooperation + * with firmware. This isn't *strictly* required, but there's enough + * assumptions baked into both firmware and the platform code that + * it's unwise to allow the portbus services to be used. + * + * We need to fix this eventually, but for now set this flag to disable + * the portbus driver. The AER service isn't required since that AER + * events are handled via EEH. The pciehp hotplug driver can't work + * without kernel changes (and portbus binding breaks pnv_php). The + * other services also require some thinking about how we're going + * to integrate them. + */ + pcie_ports_disabled = true; +#endif + /* Look for IODA IO-Hubs. */ for_each_compatible_node(np, NULL, "ibm,ioda-hub") { pnv_pci_init_ioda_hub(np); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 001dfac8354a..d87981f90fdc 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -167,7 +167,6 @@ static void pnv_smp_cpu_kill_self(void) /* Standard hot unplug procedure */ idle_task_exit(); - current->active_mm = NULL; /* for sanity */ cpu = smp_processor_id(); DBG("CPU%d offline\n", cpu); generic_set_cpu_dead(cpu); diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c index 423be34f0f5f..f42fe4e86ce5 100644 --- a/arch/powerpc/platforms/ps3/mm.c +++ b/arch/powerpc/platforms/ps3/mm.c @@ -200,13 +200,14 @@ void ps3_mm_vas_destroy(void) { int result; - DBG("%s:%d: map.vas_id = %llu\n", __func__, __LINE__, map.vas_id); - if (map.vas_id) { result = lv1_select_virtual_address_space(0); - BUG_ON(result); - result = lv1_destruct_virtual_address_space(map.vas_id); - BUG_ON(result); + result += lv1_destruct_virtual_address_space(map.vas_id); + + if (result) { + lv1_panic(0); + } + map.vas_id = 0; } } @@ -304,19 +305,20 @@ static void ps3_mm_region_destroy(struct mem_region *r) int result; if (!r->destroy) { - pr_info("%s:%d: Not destroying high region: %llxh %llxh\n", - __func__, __LINE__, r->base, r->size); return; } - DBG("%s:%d: r->base = %llxh\n", __func__, __LINE__, r->base); - if (r->base) { result = lv1_release_memory(r->base); - BUG_ON(result); + + if (result) { + lv1_panic(0); + } + r->size = r->base = r->offset = 0; map.total = map.rm.size; } + ps3_mm_set_repository_highmem(NULL); } diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index b33251d75927..572651a5c87b 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -411,6 +411,10 @@ static struct bus_type cmm_subsys = { .dev_name = "cmm", }; +static void cmm_release_device(struct device *dev) +{ +} + /** * cmm_sysfs_register - Register with sysfs * @@ -426,6 +430,7 @@ static int cmm_sysfs_register(struct device *dev) dev->id = 0; dev->bus = &cmm_subsys; + dev->release = cmm_release_device; if ((rc = device_register(dev))) goto subsys_unregister; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 46d0d35b9ca4..c5de633e8436 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -27,7 +27,7 @@ static bool rtas_hp_event; unsigned long pseries_memory_block_size(void) { struct device_node *np; - unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + u64 memblock_size = MIN_MEMORY_BLOCK_SIZE; struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); @@ -223,7 +223,7 @@ static int get_lmb_range(u32 drc_index, int n_lmbs, struct drmem_lmb **end_lmb) { struct drmem_lmb *lmb, *start, *end; - struct drmem_lmb *last_lmb; + struct drmem_lmb *limit; start = NULL; for_each_drmem_lmb(lmb) { @@ -236,10 +236,10 @@ static int get_lmb_range(u32 drc_index, int n_lmbs, if (!start) return -EINVAL; - end = &start[n_lmbs - 1]; + end = &start[n_lmbs]; - last_lmb = &drmem_info->lmbs[drmem_info->n_lmbs - 1]; - if (end > last_lmb) + limit = &drmem_info->lmbs[drmem_info->n_lmbs]; + if (end > limit) return -EINVAL; *start_lmb = start; @@ -360,8 +360,10 @@ static bool lmb_is_removable(struct drmem_lmb *lmb) for (i = 0; i < scns_per_block; i++) { pfn = PFN_DOWN(phys_addr); - if (!pfn_present(pfn)) + if (!pfn_present(pfn)) { + phys_addr += MIN_MEMORY_BLOCK_SIZE; continue; + } rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION); phys_addr += MIN_MEMORY_BLOCK_SIZE; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 889dc2e44b89..3eddad5f9be0 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -132,10 +132,10 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index) return be64_to_cpu(*tcep); } -static void tce_free_pSeriesLP(struct iommu_table*, long, long); +static void tce_free_pSeriesLP(unsigned long liobn, long, long); static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long); -static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, +static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, long npages, unsigned long uaddr, enum dma_data_direction direction, unsigned long attrs) @@ -146,25 +146,25 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, int ret = 0; long tcenum_start = tcenum, npages_start = npages; - rpn = __pa(uaddr) >> TCE_SHIFT; + rpn = __pa(uaddr) >> tceshift; proto_tce = TCE_PCI_READ; if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; while (npages--) { - tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; - rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce); + tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift; + rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce); if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { ret = (int)rc; - tce_free_pSeriesLP(tbl, tcenum_start, + tce_free_pSeriesLP(liobn, tcenum_start, (npages_start - (npages + 1))); break; } if (rc && printk_ratelimit()) { printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc); - printk("\tindex = 0x%llx\n", (u64)tbl->it_index); + printk("\tindex = 0x%llx\n", (u64)liobn); printk("\ttcenum = 0x%llx\n", (u64)tcenum); printk("\ttce val = 0x%llx\n", tce ); dump_stack(); @@ -193,7 +193,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, unsigned long flags; if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) { - return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, + return tce_build_pSeriesLP(tbl->it_index, tcenum, + tbl->it_page_shift, npages, uaddr, direction, attrs); } @@ -209,8 +210,9 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, /* If allocation fails, fall back to the loop implementation */ if (!tcep) { local_irq_restore(flags); - return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, - direction, attrs); + return tce_build_pSeriesLP(tbl->it_index, tcenum, + tbl->it_page_shift, + npages, uaddr, direction, attrs); } __this_cpu_write(tce_page, tcep); } @@ -261,16 +263,16 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, return ret; } -static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages) +static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages) { u64 rc; while (npages--) { - rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, 0); + rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0); if (rc && printk_ratelimit()) { printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc); - printk("\tindex = 0x%llx\n", (u64)tbl->it_index); + printk("\tindex = 0x%llx\n", (u64)liobn); printk("\ttcenum = 0x%llx\n", (u64)tcenum); dump_stack(); } @@ -285,7 +287,7 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n u64 rc; if (!firmware_has_feature(FW_FEATURE_MULTITCE)) - return tce_free_pSeriesLP(tbl, tcenum, npages); + return tce_free_pSeriesLP(tbl->it_index, tcenum, npages); rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages); @@ -400,6 +402,19 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, u64 rc = 0; long l, limit; + if (!firmware_has_feature(FW_FEATURE_MULTITCE)) { + unsigned long tceshift = be32_to_cpu(maprange->tce_shift); + unsigned long dmastart = (start_pfn << PAGE_SHIFT) + + be64_to_cpu(maprange->dma_base); + unsigned long tcenum = dmastart >> tceshift; + unsigned long npages = num_pfn << PAGE_SHIFT >> tceshift; + void *uaddr = __va(start_pfn << PAGE_SHIFT); + + return tce_build_pSeriesLP(be32_to_cpu(maprange->liobn), + tcenum, tceshift, npages, (unsigned long) uaddr, + DMA_BIDIRECTIONAL, 0); + } + local_irq_disable(); /* to protect tcep and the page behind it */ tcep = __this_cpu_read(tce_page); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 15fe7213aa6b..aa7cc6f2a125 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1255,7 +1255,7 @@ static int __init vpa_debugfs_init(void) { char name[16]; long i; - static struct dentry *vpa_dir; + struct dentry *vpa_dir; if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index e33e8bc4b69b..38c306551f76 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -435,10 +435,10 @@ static void maxmem_data(struct seq_file *m) { unsigned long maxmem = 0; - maxmem += drmem_info->n_lmbs * drmem_info->lmb_size; + maxmem += (unsigned long)drmem_info->n_lmbs * drmem_info->lmb_size; maxmem += hugetlb_total_pages() * PAGE_SIZE; - seq_printf(m, "MaxMem=%ld\n", maxmem); + seq_printf(m, "MaxMem=%lu\n", maxmem); } static int pseries_lparcfg_data(struct seq_file *m, void *v) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 3c17fc7c2b93..8debe017c0d6 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -238,6 +238,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) p->bus = nvdimm_bus_register(NULL, &p->bus_desc); if (!p->bus) { dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn); + kfree(p->bus_desc.provider_name); return -ENXIO; } @@ -382,6 +383,7 @@ static int papr_scm_remove(struct platform_device *pdev) nvdimm_bus_unregister(p->bus); drc_pmem_unbind(p); + kfree(p->bus_desc.provider_name); kfree(p); return 0; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index f16fdd0f71f7..68eec766a5d8 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -412,10 +412,11 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) /* * Some versions of FWNMI place the buffer inside the 4kB page starting at * 0x7000. Other versions place it inside the rtas buffer. We check both. + * Minimum size of the buffer is 16 bytes. */ #define VALID_FWNMI_BUFFER(A) \ - ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ - (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) + ((((A) >= 0x7000) && ((A) <= 0x8000 - 16)) || \ + (((A) >= rtas.base) && ((A) <= (rtas.base + rtas.size - 16)))) static inline struct rtas_error_log *fwnmi_get_errlog(void) { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index cc682759feae..c0a87b1cee24 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -71,6 +71,9 @@ #include "pseries.h" #include "../../../../drivers/pci/pci.h" +DEFINE_STATIC_KEY_FALSE(shared_processor); +EXPORT_SYMBOL_GPL(shared_processor); + int CMO_PrPSP = -1; int CMO_SecPSP = -1; unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); @@ -780,6 +783,10 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); + + if (lppaca_shared_proc(get_lppaca())) + static_branch_enable(&shared_processor); + ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; #ifdef CONFIG_PCI_IOV diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 0a24a5a185f0..f789693f61f4 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -132,15 +132,11 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - stream_id = simple_strtoul(buf, NULL, 16); do { @@ -150,32 +146,16 @@ static ssize_t store_hibernate(struct device *dev, } while (rc == -EAGAIN); if (!rc) { - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, - cpu_online_mask); - rc = rtas_online_cpus_mask(offline_mask); - if (rc) { - pr_err("%s: Could not bring present CPUs online.\n", - __func__); - goto out; - } - stop_topology_update(); rc = pm_suspend(PM_SUSPEND_MEM); start_topology_update(); - - /* Take down CPUs not online prior to suspend */ - if (!rtas_offline_cpus_mask(offline_mask)) - pr_warn("%s: Could not restore CPUs to offline " - "state.\n", __func__); } stream_id = 0; if (!rc) rc = count; -out: - free_cpumask_var(offline_mask); + return rc; } diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index ba758f4be328..63c8dc080770 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1174,6 +1174,8 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) if (tbl == NULL) return NULL; + kref_init(&tbl->it_kref); + of_parse_dma_window(dev->dev.of_node, dma_window, &tbl->it_index, &offset, &size); diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index be86fce1a84e..9542394300ec 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -19,6 +19,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/msi.h> +#include <linux/vmalloc.h> #include <asm/prom.h> #include <asm/io.h> @@ -68,13 +69,6 @@ static u32 xive_ipi_irq; /* Xive state for each CPU */ static DEFINE_PER_CPU(struct xive_cpu *, xive_cpu); -/* - * A "disabled" interrupt should never fire, to catch problems - * we set its logical number to this - */ -#define XIVE_BAD_IRQ 0x7fffffff -#define XIVE_MAX_IRQ (XIVE_BAD_IRQ - 1) - /* An invalid CPU target */ #define XIVE_INVALID_TARGET (-1) @@ -937,12 +931,21 @@ static int xive_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state) { struct xive_irq_data *xd = irq_data_get_irq_handler_data(data); + u8 pq; switch (which) { case IRQCHIP_STATE_ACTIVE: - *state = !xd->stale_p && - (xd->saved_p || - !!(xive_esb_read(xd, XIVE_ESB_GET) & XIVE_ESB_VAL_P)); + pq = xive_esb_read(xd, XIVE_ESB_GET); + + /* + * The esb value being all 1's means we couldn't get + * the PQ state of the interrupt through mmio. It may + * happen, for example when querying a PHB interrupt + * while the PHB is in an error state. We consider the + * interrupt to be inactive in that case. + */ + *state = (pq != XIVE_ESB_INVALID) && !xd->stale_p && + (xd->saved_p || !!(pq & XIVE_ESB_VAL_P)); return 0; default: return -EINVAL; @@ -972,12 +975,16 @@ EXPORT_SYMBOL_GPL(is_xive_irq); void xive_cleanup_irq_data(struct xive_irq_data *xd) { if (xd->eoi_mmio) { + unmap_kernel_range((unsigned long)xd->eoi_mmio, + 1u << xd->esb_shift); iounmap(xd->eoi_mmio); if (xd->eoi_mmio == xd->trig_mmio) xd->trig_mmio = NULL; xd->eoi_mmio = NULL; } if (xd->trig_mmio) { + unmap_kernel_range((unsigned long)xd->trig_mmio, + 1u << xd->esb_shift); iounmap(xd->trig_mmio); xd->trig_mmio = NULL; } @@ -1000,6 +1007,15 @@ static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw) xd->target = XIVE_INVALID_TARGET; irq_set_handler_data(virq, xd); + /* + * Turn OFF by default the interrupt being mapped. A side + * effect of this check is the mapping the ESB page of the + * interrupt in the Linux address space. This prevents page + * fault issues in the crash handler which masks all + * interrupts. + */ + xive_esb_read(xd, XIVE_ESB_SET_PQ_01); + return 0; } @@ -1097,7 +1113,7 @@ static int xive_setup_cpu_ipi(unsigned int cpu) xc = per_cpu(xive_cpu, cpu); /* Check if we are already setup */ - if (xc->hw_ipi != 0) + if (xc->hw_ipi != XIVE_BAD_IRQ) return 0; /* Grab an IPI from the backend, this will populate xc->hw_ipi */ @@ -1134,7 +1150,7 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc) /* Disable the IPI and free the IRQ data */ /* Already cleaned up ? */ - if (xc->hw_ipi == 0) + if (xc->hw_ipi == XIVE_BAD_IRQ) return; /* Mask the IPI */ @@ -1290,6 +1306,7 @@ static int xive_prepare_cpu(unsigned int cpu) if (np) xc->chip_id = of_get_ibm_chip_id(np); of_node_put(np); + xc->hw_ipi = XIVE_BAD_IRQ; per_cpu(xive_cpu, cpu) = xc; } diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index ad8ee7dd7f57..43f1f587a956 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -298,7 +298,7 @@ static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc) s64 rc; /* Free the IPI */ - if (!xc->hw_ipi) + if (xc->hw_ipi == XIVE_BAD_IRQ) return; for (;;) { rc = opal_xive_free_irq(xc->hw_ipi); @@ -306,7 +306,7 @@ static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc) msleep(OPAL_BUSY_DELAY_MS); continue; } - xc->hw_ipi = 0; + xc->hw_ipi = XIVE_BAD_IRQ; break; } } diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index 8ef9cf4ebb1c..ce756997054f 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -356,20 +356,28 @@ static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data) data->esb_shift = esb_shift; data->trig_page = trig_page; + data->hw_irq = hw_irq; + /* * No chip-id for the sPAPR backend. This has an impact how we * pick a target. See xive_pick_irq_target(). */ data->src_chip = XIVE_INVALID_CHIP_ID; + /* + * When the H_INT_ESB flag is set, the H_INT_ESB hcall should + * be used for interrupt management. Skip the remapping of the + * ESB pages which are not available. + */ + if (data->flags & XIVE_IRQ_FLAG_H_INT_ESB) + return 0; + data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift); if (!data->eoi_mmio) { pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq); return -ENOMEM; } - data->hw_irq = hw_irq; - /* Full function page supports trigger */ if (flags & XIVE_SRC_TRIGGER) { data->trig_mmio = data->eoi_mmio; @@ -498,11 +506,11 @@ static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc) static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc) { - if (!xc->hw_ipi) + if (xc->hw_ipi == XIVE_BAD_IRQ) return; xive_irq_bitmap_free(xc->hw_ipi); - xc->hw_ipi = 0; + xc->hw_ipi = XIVE_BAD_IRQ; } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h index 211725dbf364..a2f8d9361e6e 100644 --- a/arch/powerpc/sysdev/xive/xive-internal.h +++ b/arch/powerpc/sysdev/xive/xive-internal.h @@ -5,6 +5,13 @@ #ifndef __XIVE_INTERNAL_H #define __XIVE_INTERNAL_H +/* + * A "disabled" interrupt should never fire, to catch problems + * we set its logical number to this + */ +#define XIVE_BAD_IRQ 0x7fffffff +#define XIVE_MAX_IRQ (XIVE_BAD_IRQ - 1) + /* Each CPU carry one of these with various per-CPU state */ struct xive_cpu { #ifdef CONFIG_SMP diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh index 2b4e959caa36..014e00e74d2b 100755 --- a/arch/powerpc/tools/relocs_check.sh +++ b/arch/powerpc/tools/relocs_check.sh @@ -10,24 +10,29 @@ # based on relocs_check.pl # Copyright © 2009 IBM Corporation -if [ $# -lt 2 ]; then - echo "$0 [path to objdump] [path to vmlinux]" 1>&2 +if [ $# -lt 3 ]; then + echo "$0 [path to objdump] [path to nm] [path to vmlinux]" 1>&2 exit 1 fi -# Have Kbuild supply the path to objdump so we handle cross compilation. +# Have Kbuild supply the path to objdump and nm so we handle cross compilation. objdump="$1" -vmlinux="$2" +nm="$2" +vmlinux="$3" + +# Remove from the bad relocations those that match an undefined weak symbol +# which will result in an absolute relocation to 0. +# Weak unresolved symbols are of that form in nm output: +# " w _binary__btf_vmlinux_bin_end" +undef_weak_symbols=$($nm "$vmlinux" | awk '$1 ~ /w/ { print $2 }') bad_relocs=$( -"$objdump" -R "$vmlinux" | +$objdump -R "$vmlinux" | # Only look at relocation lines. grep -E '\<R_' | # These relocations are okay # On PPC64: # R_PPC64_RELATIVE, R_PPC64_NONE - # R_PPC64_ADDR64 mach_<name> - # R_PPC64_ADDR64 __crc_<name> # On PPC: # R_PPC_RELATIVE, R_PPC_ADDR16_HI, # R_PPC_ADDR16_HA,R_PPC_ADDR16_LO, @@ -39,8 +44,7 @@ R_PPC_ADDR16_HI R_PPC_ADDR16_HA R_PPC_RELATIVE R_PPC_NONE' | - grep -E -v '\<R_PPC64_ADDR64[[:space:]]+mach_' | - grep -E -v '\<R_PPC64_ADDR64[[:space:]]+__crc_' + ([ "$undef_weak_symbols" ] && grep -F -w -v "$undef_weak_symbols" || cat) ) if [ -z "$bad_relocs" ]; then diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 1e972df3107e..77114755dc6f 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -18,14 +18,14 @@ vmlinux="$2" #__end_interrupts should be located within the first 64K end_intr=0x$( -"$objdump" -R "$vmlinux" -d --start-address=0xc000000000000000 \ +$objdump -R "$vmlinux" -d --start-address=0xc000000000000000 \ --stop-address=0xc000000000010000 | grep '\<__end_interrupts>:' | awk '{print $1}' ) BRANCHES=$( -"$objdump" -R "$vmlinux" -D --start-address=0xc000000000000000 \ +$objdump -R "$vmlinux" -D --start-address=0xc000000000000000 \ --stop-address=${end_intr} | grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | grep -v '\<__start_initialization_multiplatform>' | diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index f142570ad860..6f9cccea54f3 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -1,9 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for xmon -# Disable clang warning for using setjmp without setjmp.h header -subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header) - GCOV_PROFILE := n KCOV_INSTRUMENT := n UBSAN_SANITIZE := n diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index e15ccf19c153..79ac87f4d87b 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1894,15 +1894,14 @@ static void dump_300_sprs(void) printf("pidr = %.16lx tidr = %.16lx\n", mfspr(SPRN_PID), mfspr(SPRN_TIDR)); - printf("asdr = %.16lx psscr = %.16lx\n", - mfspr(SPRN_ASDR), hv ? mfspr(SPRN_PSSCR) - : mfspr(SPRN_PSSCR_PR)); + printf("psscr = %.16lx\n", + hv ? mfspr(SPRN_PSSCR) : mfspr(SPRN_PSSCR_PR)); if (!hv) return; - printf("ptcr = %.16lx\n", - mfspr(SPRN_PTCR)); + printf("ptcr = %.16lx asdr = %.16lx\n", + mfspr(SPRN_PTCR), mfspr(SPRN_ASDR)); #endif } |