diff options
author | Stefan Agner <stefan.agner@toradex.com> | 2016-09-16 13:17:18 -0700 |
---|---|---|
committer | Stefan Agner <stefan.agner@toradex.com> | 2016-09-29 13:58:03 -0700 |
commit | cd89f007101ad44dc318b2aca826b5754c5ccfa9 (patch) | |
tree | 75cddcca3c07f8c06e053398eeb618f3da458169 /arch | |
parent | 45de59e3f1511606433c294e9ec85c5b9d4f637f (diff) | |
parent | 1d074db69c46d62ce82b331c2080e2fcb710bf4a (diff) |
Merge tag 'v4.4.21' into toradex_vf_4.4-next
This is the 4.4.21 stable release
Diffstat (limited to 'arch')
93 files changed, 1007 insertions, 538 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6312f607932f..2d785f5a3041 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -387,7 +387,7 @@ config ARC_HAS_LLSC config ARC_STAR_9000923308 bool "Workaround for llock/scond livelock" - default y + default n depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC config ARC_HAS_SWAPE diff --git a/arch/arc/Makefile b/arch/arc/Makefile index aeb19021099e..c05ea2b54276 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -18,6 +18,20 @@ cflags-y += -fno-common -pipe -fno-builtin -D__linux__ cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 cflags-$(CONFIG_ISA_ARCV2) += -mcpu=archs +is_700 = $(shell $(CC) -dM -E - < /dev/null | grep -q "ARC700" && echo 1 || echo 0) + +ifdef CONFIG_ISA_ARCOMPACT +ifeq ($(is_700), 0) + $(error Toolchain not configured for ARCompact builds) +endif +endif + +ifdef CONFIG_ISA_ARCV2 +ifeq ($(is_700), 1) + $(error Toolchain not configured for ARCv2 builds) +endif +endif + ifdef CONFIG_ARC_CURR_IN_REG # For a global register defintion, make sure it gets passed to every file # We had a customer reported bug where some code built in kernel was NOT using @@ -48,8 +62,6 @@ endif endif -cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables - # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok ifeq ($(atleast_gcc48),y) cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 7fac7d85ed6a..2c30a016cf15 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -374,12 +374,6 @@ static inline int is_isa_arcompact(void) return IS_ENABLED(CONFIG_ISA_ARCOMPACT); } -#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7) -#error "Toolchain not configured for ARCompact builds" -#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS) -#error "Toolchain not configured for ARCv2 builds" -#endif - #endif /* __ASEMBLY__ */ #endif /* _ASM_ARC_ARCREGS_H */ diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index ad7860c5ce15..51597f344a62 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -142,7 +142,7 @@ #ifdef CONFIG_ARC_CURR_IN_REG ; Retrieve orig r25 and save it with rest of callee_regs - ld.as r12, [r12, PT_user_r25] + ld r12, [r12, PT_user_r25] PUSH r12 #else PUSH r25 @@ -198,7 +198,7 @@ ; SP is back to start of pt_regs #ifdef CONFIG_ARC_CURR_IN_REG - st.as r12, [sp, PT_user_r25] + st r12, [sp, PT_user_r25] #endif .endm diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index c1d36458bfb7..4c6eed80cd8b 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void) .endm .macro IRQ_ENABLE scratch + TRACE_ASM_IRQ_ENABLE lr \scratch, [status32] or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch - TRACE_ASM_IRQ_ENABLE .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 57af2f05ae84..3cab04255ae0 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -110,7 +110,7 @@ #define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE) /* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) +#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL) /* More Abbrevaited helpers */ #define PAGE_U_NONE __pgprot(___DEF) diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index e1b87444ea9a..05131805aa33 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -332,10 +332,6 @@ static void arc_chk_core_config(void) pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n"); else if (!cpu->extn.fpu_dp && fpu_enabled) panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n"); - - if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic && - !IS_ENABLED(CONFIG_ARC_STAR_9000923308)) - panic("llock/scond livelock workaround missing\n"); } /* diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index 001de4ce711e..11b50959f20e 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, * prelogue is setup (callee regs saved and then fp set and not other * way around */ - pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); + pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); return 0; #endif diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index ff7ff6cbb811..aaf1e2d1d900 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -914,6 +914,15 @@ void arc_cache_init(void) printk(arc_cache_mumbojumbo(0, str, sizeof(str))); + /* + * Only master CPU needs to execute rest of function: + * - Assume SMP so all cores will have same cache config so + * any geomtry checks will be same for all + * - IOC setup / dma callbacks only need to be setup once + */ + if (cpu) + return; + if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) { struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 8450944b28e6..22f7a13e20b4 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -58,8 +58,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0xf1100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0xf1110000 0x10000>; + MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>; internal-regs { diff --git a/arch/arm/boot/dts/sun4i-a10-a1000.dts b/arch/arm/boot/dts/sun4i-a10-a1000.dts index 97570cb7f2fc..1d23527d4ecf 100644 --- a/arch/arm/boot/dts/sun4i-a10-a1000.dts +++ b/arch/arm/boot/dts/sun4i-a10-a1000.dts @@ -84,6 +84,7 @@ regulator-name = "emac-3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + startup-delay-us = <20000>; enable-active-high; gpio = <&pio 7 15 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/arch/arm/boot/dts/sun4i-a10-hackberry.dts index 2b17c5199151..6de83a6187d0 100644 --- a/arch/arm/boot/dts/sun4i-a10-hackberry.dts +++ b/arch/arm/boot/dts/sun4i-a10-hackberry.dts @@ -66,6 +66,7 @@ regulator-name = "emac-3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + startup-delay-us = <20000>; enable-active-high; gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts index 7afc7a64eef1..e28f080b1fd5 100644 --- a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts +++ b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts @@ -80,6 +80,7 @@ regulator-name = "emac-3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + startup-delay-us = <20000>; enable-active-high; gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>; /* PH19 */ }; diff --git a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts index 9fea918f949e..39731a78f087 100644 --- a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts +++ b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts @@ -79,6 +79,7 @@ regulator-name = "emac-3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + startup-delay-us = <20000>; enable-active-high; gpio = <&pio 0 2 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts index 530ab28e9ca2..d21f50ba3172 100644 --- a/arch/arm/boot/dts/sun5i-r8-chip.dts +++ b/arch/arm/boot/dts/sun5i-r8-chip.dts @@ -52,7 +52,7 @@ / { model = "NextThing C.H.I.P."; - compatible = "nextthing,chip", "allwinner,sun5i-r8"; + compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13"; aliases { i2c0 = &i2c0; diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index aeddd28b3595..92fd2c8a9af0 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) +#define pmd_present(pmd) (pmd_val(pmd)) #define copy_pmd(pmdpd,pmdps) \ do { \ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a745a2a53853..fd929b5ded9e 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -212,6 +212,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) : !!(pmd_val(pmd) & (val))) #define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val))) +#define pmd_present(pmd) (pmd_isset((pmd), L_PMD_SECT_VALID)) #define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF)) #define pte_special(pte) (pte_isset((pte), L_PTE_SPECIAL)) static inline pte_t pte_mkspecial(pte_t pte) @@ -257,10 +258,10 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) -/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */ +/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */ static inline pmd_t pmd_mknotpresent(pmd_t pmd) { - return __pmd(0); + return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 348caabb7625..d62204060cbe 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; #define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) static inline pte_t *pmd_page_vaddr(pmd_t pmd) { diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 087acb569b63..5f221acd21ae 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd, mm_segment_t fs; long ret, err, i; - if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event))) + if (maxevents <= 0 || + maxevents > (INT_MAX/sizeof(*kbuf)) || + maxevents > (INT_MAX/sizeof(*events))) return -EINVAL; + if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents)) + return -EFAULT; kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL); if (!kbuf) return -ENOMEM; @@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid, if (nsops < 1 || nsops > SEMOPM) return -EINVAL; + if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops)) + return -EFAULT; sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL); if (!sops) return -ENOMEM; diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c index acaf7056efa5..e08d02667c81 100644 --- a/arch/arm/mach-imx/mach-imx6ul.c +++ b/arch/arm/mach-imx/mach-imx6ul.c @@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev) static void __init imx6ul_enet_phy_init(void) { if (IS_BUILTIN(CONFIG_PHYLIB)) - phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff, + phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK, ksz8081_phy_fixup); } diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 55348ee5a352..feed36b32ff6 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -162,22 +162,16 @@ exit: } /* - * This ioremap hook is used on Armada 375/38x to ensure that PCIe - * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This - * is needed as a workaround for a deadlock issue between the PCIe - * interface and the cache controller. + * This ioremap hook is used on Armada 375/38x to ensure that all MMIO + * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is + * needed for the HW I/O coherency mechanism to work properly without + * deadlock. */ static void __iomem * -armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, - unsigned int mtype, void *caller) +armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, + unsigned int mtype, void *caller) { - struct resource pcie_mem; - - mvebu_mbus_get_pcie_mem_aperture(&pcie_mem); - - if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end) - mtype = MT_UNCACHED; - + mtype = MT_UNCACHED; return __arm_ioremap_caller(phys_addr, size, mtype, caller); } @@ -186,7 +180,7 @@ static void __init armada_375_380_coherency_init(struct device_node *np) struct device_node *cache_dn; coherency_cpu_base = of_iomap(np, 0); - arch_ioremap_caller = armada_pcie_wa_ioremap_caller; + arch_ioremap_caller = armada_wa_ioremap_caller; /* * We should switch the PL310 to I/O coherency mode only if diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 871f21783866..14cdc6dea493 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -391,6 +391,15 @@ config CAVIUM_ERRATUM_22375 If unsure, say Y. +config CAVIUM_ERRATUM_23144 + bool "Cavium erratum 23144: ITS SYNC hang on dual socket system" + depends on NUMA + default y + help + ITS SYNC command hang for cross node io and collections/cpu mapping. + + If unsure, say Y. + config CAVIUM_ERRATUM_23154 bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed" default y @@ -401,6 +410,17 @@ config CAVIUM_ERRATUM_23154 If unsure, say Y. +config CAVIUM_ERRATUM_27456 + bool "Cavium erratum 27456: Broadcast TLBI instructions may cause icache corruption" + default y + help + On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI + instructions may cause the icache to become corrupted if it + contains data for a non-current ASID. The fix is to + invalidate the icache when changing the mm context. + + If unsure, say Y. + endmenu diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index cc093a482aa4..e0ee2b00d573 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -262,6 +262,8 @@ #io-channel-cells = <1>; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; @@ -517,7 +519,7 @@ #address-cells = <0>; reg = <0x0 0xffb71000 0x0 0x1000>, - <0x0 0xffb72000 0x0 0x1000>, + <0x0 0xffb72000 0x0 0x2000>, <0x0 0xffb74000 0x0 0x2000>, <0x0 0xffb76000 0x0 0x2000>; interrupts = <GIC_PPI 9 diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 2731d3b25ed2..8ec88e5b290f 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void) u64 irqstat; asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat)); + dsb(sy); return irqstat; } diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 8f271b83f910..8136afc9df0d 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -30,8 +30,9 @@ #define ARM64_HAS_LSE_ATOMICS 5 #define ARM64_WORKAROUND_CAVIUM_23154 6 #define ARM64_WORKAROUND_834220 7 +#define ARM64_WORKAROUND_CAVIUM_27456 8 -#define ARM64_NCAPS 8 +#define ARM64_NCAPS 9 #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index bc6492b9a924..44dd892a4bbe 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -136,6 +136,7 @@ typedef struct user_fpsimd_state elf_fpregset_t; #define SET_PERSONALITY(ex) clear_thread_flag(TIF_32BIT); +/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #define ARCH_DLINFO \ do { \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 5e6857b6bdc4..2d960f8588b0 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -107,8 +107,6 @@ #define TCR_EL2_MASK (TCR_EL2_TG0 | TCR_EL2_SH0 | \ TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ) -#define TCR_EL2_FLAGS (TCR_EL2_RES1 | TCR_EL2_PS_40B) - /* VTCR_EL2 Registers bits */ #define VTCR_EL2_RES1 (1 << 31) #define VTCR_EL2_PS_MASK (7 << 16) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index e9e5467e0bf4..7f94755089e2 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -58,6 +58,7 @@ #define COMPAT_PSR_Z_BIT 0x40000000 #define COMPAT_PSR_N_BIT 0x80000000 #define COMPAT_PSR_IT_MASK 0x0600fc00 /* If-Then execution state mask */ +#define COMPAT_PSR_GE_MASK 0x000f0000 #ifdef CONFIG_CPU_BIG_ENDIAN #define COMPAT_PSR_ENDSTATE COMPAT_PSR_E_BIT @@ -116,6 +117,8 @@ struct pt_regs { }; u64 orig_x0; u64 syscallno; + u64 orig_addr_limit; + u64 unused; // maintain 16 byte alignment }; #define arch_has_single_step() (1) @@ -151,35 +154,9 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->regs[0]; } -/* - * Are the current registers suitable for user mode? (used to maintain - * security in signal handlers) - */ -static inline int valid_user_regs(struct user_pt_regs *regs) -{ - if (user_mode(regs) && (regs->pstate & PSR_I_BIT) == 0) { - regs->pstate &= ~(PSR_F_BIT | PSR_A_BIT); - - /* The T bit is reserved for AArch64 */ - if (!(regs->pstate & PSR_MODE32_BIT)) - regs->pstate &= ~COMPAT_PSR_T_BIT; - - return 1; - } - - /* - * Force PSR to something logical... - */ - regs->pstate &= PSR_f | PSR_s | (PSR_x & ~PSR_A_BIT) | \ - COMPAT_PSR_T_BIT | PSR_MODE32_BIT; - - if (!(regs->pstate & PSR_MODE32_BIT)) { - regs->pstate &= ~COMPAT_PSR_T_BIT; - regs->pstate |= PSR_MODE_EL0t; - } - - return 0; -} +/* We must avoid circular header include via sched.h */ +struct task_struct; +int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task); #define instruction_pointer(regs) ((unsigned long)(regs)->pc) diff --git a/arch/arm64/include/uapi/asm/auxvec.h b/arch/arm64/include/uapi/asm/auxvec.h index 22d6d8885854..4cf0c17787a8 100644 --- a/arch/arm64/include/uapi/asm/auxvec.h +++ b/arch/arm64/include/uapi/asm/auxvec.h @@ -19,4 +19,6 @@ /* vDSO location */ #define AT_SYSINFO_EHDR 33 +#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */ + #endif diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 25de8b244961..087cf9a65359 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -58,6 +58,7 @@ int main(void) DEFINE(S_PC, offsetof(struct pt_regs, pc)); DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); + DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index feb6b4efa641..a3e846a28b05 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -100,6 +100,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01), }, #endif +#ifdef CONFIG_CAVIUM_ERRATUM_27456 + { + /* Cavium ThunderX, T88 pass 1.x - 2.1 */ + .desc = "Cavium erratum 27456", + .capability = ARM64_WORKAROUND_CAVIUM_27456, + MIDR_RANGE(MIDR_THUNDERX, 0x00, + (1 << MIDR_VARIANT_SHIFT) | 1), + }, +#endif { } }; diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index c1492ba1f6d1..e51f27ac13fd 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -152,7 +152,6 @@ static int debug_monitors_init(void) /* Clear the OS lock. */ on_each_cpu(clear_os_lock, NULL, 1); isb(); - local_dbg_enable(); /* Register hotplug handler. */ __register_cpu_notifier(&os_lock_nb); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 7ed3d75f6304..5a3753d09e20 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -27,6 +27,7 @@ #include <asm/cpufeature.h> #include <asm/errno.h> #include <asm/esr.h> +#include <asm/memory.h> #include <asm/thread_info.h> #include <asm/unistd.h> @@ -93,7 +94,13 @@ disable_step_tsk x19, x20 // exceptions when scheduling. .else add x21, sp, #S_FRAME_SIZE - .endif + get_thread_info tsk + /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ + ldr x20, [tsk, #TI_ADDR_LIMIT] + str x20, [sp, #S_ORIG_ADDR_LIMIT] + mov x20, #TASK_SIZE_64 + str x20, [tsk, #TI_ADDR_LIMIT] + .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 stp lr, x21, [sp, #S_LR] @@ -117,6 +124,12 @@ .endm .macro kernel_exit, el + .if \el != 0 + /* Restore the task's original addr_limit. */ + ldr x20, [sp, #S_ORIG_ADDR_LIMIT] + str x20, [tsk, #TI_ADDR_LIMIT] + .endif + ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 ct_user_enter diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index ff7f13239515..fc779ec6f051 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -39,6 +39,7 @@ #include <linux/elf.h> #include <asm/compat.h> +#include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/pgtable.h> #include <asm/syscall.h> @@ -500,7 +501,7 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - if (!valid_user_regs(&newregs)) + if (!valid_user_regs(&newregs, target)) return -EINVAL; task_pt_regs(target)->user_regs = newregs; @@ -770,7 +771,7 @@ static int compat_gpr_set(struct task_struct *target, } - if (valid_user_regs(&newregs.user_regs)) + if (valid_user_regs(&newregs.user_regs, target)) *task_pt_regs(target) = newregs; else ret = -EINVAL; @@ -1272,3 +1273,79 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs) if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); } + +/* + * Bits which are always architecturally RES0 per ARM DDI 0487A.h + * Userspace cannot use these until they have an architectural meaning. + * We also reserve IL for the kernel; SS is handled dynamically. + */ +#define SPSR_EL1_AARCH64_RES0_BITS \ + (GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \ + GENMASK_ULL(5, 5)) +#define SPSR_EL1_AARCH32_RES0_BITS \ + (GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20)) + +static int valid_compat_regs(struct user_pt_regs *regs) +{ + regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS; + + if (!system_supports_mixed_endian_el0()) { + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + regs->pstate |= COMPAT_PSR_E_BIT; + else + regs->pstate &= ~COMPAT_PSR_E_BIT; + } + + if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) && + (regs->pstate & COMPAT_PSR_A_BIT) == 0 && + (regs->pstate & COMPAT_PSR_I_BIT) == 0 && + (regs->pstate & COMPAT_PSR_F_BIT) == 0) { + return 1; + } + + /* + * Force PSR to a valid 32-bit EL0t, preserving the same bits as + * arch/arm. + */ + regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT | + COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT | + COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK | + COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT | + COMPAT_PSR_T_BIT; + regs->pstate |= PSR_MODE32_BIT; + + return 0; +} + +static int valid_native_regs(struct user_pt_regs *regs) +{ + regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS; + + if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) && + (regs->pstate & PSR_D_BIT) == 0 && + (regs->pstate & PSR_A_BIT) == 0 && + (regs->pstate & PSR_I_BIT) == 0 && + (regs->pstate & PSR_F_BIT) == 0) { + return 1; + } + + /* Force PSR to a valid 64-bit EL0t */ + regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT; + + return 0; +} + +/* + * Are the current registers suitable for user mode? (used to maintain + * security in signal handlers) + */ +int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) +{ + if (!test_tsk_thread_flag(task, TIF_SINGLESTEP)) + regs->pstate &= ~DBG_SPSR_SS; + + if (is_compat_thread(task_thread_info(task))) + return valid_compat_regs(regs); + else + return valid_native_regs(regs); +} diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e18c48cb6db1..a8eafdbc7cb8 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -115,7 +115,7 @@ static int restore_sigframe(struct pt_regs *regs, */ regs->syscallno = ~0UL; - err |= !valid_user_regs(®s->user_regs); + err |= !valid_user_regs(®s->user_regs, current); if (err == 0) { struct fpsimd_context *fpsimd_ctx = @@ -307,7 +307,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Check that the resulting registers are actually sane. */ - ret |= !valid_user_regs(®s->user_regs); + ret |= !valid_user_regs(®s->user_regs, current); /* * Fast forward the stepping logic so we step into the signal diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 71ef6dc89ae5..107335637390 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -356,7 +356,7 @@ static int compat_restore_sigframe(struct pt_regs *regs, */ regs->syscallno = ~0UL; - err |= !valid_user_regs(®s->user_regs); + err |= !valid_user_regs(®s->user_regs, current); aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace; if (err == 0) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index b1adc51b2c2e..f3c3d8fee5ba 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -188,7 +188,6 @@ asmlinkage void secondary_start_kernel(void) set_cpu_online(cpu, true); complete(&cpu_running); - local_dbg_enable(); local_irq_enable(); local_async_enable(); @@ -334,8 +333,8 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_boot_cpu(void) { - cpuinfo_store_boot_cpu(); set_my_cpu_offset(per_cpu_offset(smp_processor_id())); + cpuinfo_store_boot_cpu(); } static u64 __init of_get_cpu_mpidr(struct device_node *dn) diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 178ba2248a98..84c338f017b2 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -64,7 +64,7 @@ __do_hyp_init: mrs x4, tcr_el1 ldr x5, =TCR_EL2_MASK and x4, x4, x5 - ldr x5, =TCR_EL2_FLAGS + mov x5, #TCR_EL2_RES1 orr x4, x4, x5 #ifndef CONFIG_ARM64_VA_BITS_48 @@ -85,15 +85,18 @@ __do_hyp_init: ldr_l x5, idmap_t0sz bfi x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH #endif - msr tcr_el2, x4 - - ldr x4, =VTCR_EL2_FLAGS /* * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in - * VTCR_EL2. + * TCR_EL2 and VTCR_EL2. */ mrs x5, ID_AA64MMFR0_EL1 bfi x4, x5, #16, #3 + + msr tcr_el2, x4 + + ldr x4, =VTCR_EL2_FLAGS + bfi x4, x5, #16, #3 + msr vtcr_el2, x4 mrs x4, mair_el1 diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 116ad654dd59..653735a8c58a 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -652,9 +652,9 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) /* * Check whether the physical FDT address is set and meets the minimum * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be - * at least 8 bytes so that we can always access the size field of the - * FDT header after mapping the first chunk, double check here if that - * is indeed the case. + * at least 8 bytes so that we can always access the magic and size + * fields of the FDT header after mapping the first chunk, double check + * here if that is indeed the case. */ BUILD_BUG_ON(MIN_FDT_ALIGN < 8); if (!dt_phys || dt_phys % MIN_FDT_ALIGN) @@ -682,7 +682,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, SWAPPER_BLOCK_SIZE, prot); - if (fdt_check_header(dt_virt) != 0) + if (fdt_magic(dt_virt) != FDT_MAGIC) return NULL; size = fdt_totalsize(dt_virt); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index b8f04b3f2786..18201e9e8cc7 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -25,6 +25,8 @@ #include <asm/hwcap.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable.h> +#include <asm/cpufeature.h> +#include <asm/alternative.h> #include "proc-macros.S" @@ -137,7 +139,17 @@ ENTRY(cpu_do_switch_mm) bfi x0, x1, #48, #16 // set the ASID msr ttbr0_el1, x0 // set TTBR0 isb +alternative_if_not ARM64_WORKAROUND_CAVIUM_27456 ret + nop + nop + nop +alternative_else + ic iallu + dsb nsh + isb + ret +alternative_endif ENDPROC(cpu_do_switch_mm) .section ".text.init", #alloc, #execinstr @@ -156,6 +168,8 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 + isb // Unmask debug exceptions now, + enable_dbg // since this is per-cpu reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h index a62581815624..88fa25fae8bd 100644 --- a/arch/metag/include/asm/atomic_lnkget.h +++ b/arch/metag/include/asm/atomic_lnkget.h @@ -61,7 +61,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ " CMPT %0, #HI(0x02000000)\n" \ " BNZ 1b\n" \ : "=&d" (temp), "=&da" (result) \ - : "da" (&v->counter), "bd" (i) \ + : "da" (&v->counter), "br" (i) \ : "cc"); \ \ smp_mb(); \ diff --git a/arch/metag/include/asm/cmpxchg_lnkget.h b/arch/metag/include/asm/cmpxchg_lnkget.h index 0154e2807ebb..2369ad394876 100644 --- a/arch/metag/include/asm/cmpxchg_lnkget.h +++ b/arch/metag/include/asm/cmpxchg_lnkget.h @@ -73,7 +73,7 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old, " DCACHE [%2], %0\n" #endif "2:\n" - : "=&d" (temp), "=&da" (retval) + : "=&d" (temp), "=&d" (retval) : "da" (m), "bd" (old), "da" (new) : "cc" ); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 4e956b3e16f5..dd7cee795709 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -372,6 +372,7 @@ struct kvm_mips_tlb { #define KVM_MIPS_GUEST_TLB_SIZE 64 struct kvm_vcpu_arch { void *host_ebase, *guest_ebase; + int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); unsigned long host_stack; unsigned long host_gp; diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c index 1f910563fdf6..d76275da54cb 100644 --- a/arch/mips/kernel/csrc-r4k.c +++ b/arch/mips/kernel/csrc-r4k.c @@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static u64 notrace r4k_read_sched_clock(void) +static u64 __maybe_unused notrace r4k_read_sched_clock(void) { return read_c0_count(); } @@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void) clocksource_register_hz(&clocksource_mips, mips_hpt_frequency); +#ifndef CONFIG_CPU_FREQ sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency); +#endif return 0; } diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 5a69eb48d0a8..ee93d5fe61d7 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -344,7 +344,7 @@ EXPORT(sysn32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key PTR sys_request_key - PTR sys_keyctl /* 6245 */ + PTR compat_sys_keyctl /* 6245 */ PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index e4b6d7c97822..b77052ec6fb2 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -500,7 +500,7 @@ EXPORT(sys32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key /* 4280 */ PTR sys_request_key - PTR sys_keyctl + PTR compat_sys_keyctl PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch /* 4285 */ diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index dc10c77b7500..d6476d11212e 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1629,8 +1629,14 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, preempt_disable(); if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) { - if (kvm_mips_host_tlb_lookup(vcpu, va) < 0) - kvm_mips_handle_kseg0_tlb_fault(va, vcpu); + if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 && + kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) { + kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n", + __func__, va, vcpu, read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; + } } else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) || KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) { int index; @@ -1665,14 +1671,19 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, run, vcpu); preempt_enable(); goto dont_update_pc; - } else { - /* - * We fault an entry from the guest tlb to the - * shadow host TLB - */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, - NULL, - NULL); + } + /* + * We fault an entry from the guest tlb to the + * shadow host TLB + */ + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, + NULL, NULL)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; } } } else { @@ -2633,8 +2644,13 @@ enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause, * OK we have a Guest TLB entry, now inject it into the * shadow host TLB */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL, - NULL); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, + NULL, NULL)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + } } } diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h index 4ab4bdfad703..2143884709e4 100644 --- a/arch/mips/kvm/interrupt.h +++ b/arch/mips/kvm/interrupt.h @@ -28,6 +28,7 @@ #define MIPS_EXC_MAX 12 /* XXXSL More to follow */ +extern char __kvm_mips_vcpu_run_end[]; extern char mips32_exception[], mips32_exceptionEnd[]; extern char mips32_GuestException[], mips32_GuestExceptionEnd[]; diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 7e2210846b8b..77706433651b 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -227,6 +227,7 @@ FEXPORT(__kvm_mips_load_k0k1) /* Jump to guest */ eret +EXPORT(__kvm_mips_vcpu_run_end) VECTOR(MIPSX(exception), unknown) /* Find out what mode we came from and jump to the proper handler. */ diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 2683d04fdda5..e86b7499921a 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -314,6 +314,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) memcpy(gebase + offset, mips32_GuestException, mips32_GuestExceptionEnd - mips32_GuestException); +#ifdef MODULE + offset += mips32_GuestExceptionEnd - mips32_GuestException; + memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run, + __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run); + vcpu->arch.vcpu_run = gebase + offset; +#else + vcpu->arch.vcpu_run = __kvm_mips_vcpu_run; +#endif + /* Invalidate the icache for these ranges */ local_flush_icache_range((unsigned long)gebase, (unsigned long)gebase + ALIGN(size, PAGE_SIZE)); @@ -403,7 +412,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Disable hardware page table walking while in guest */ htw_stop(); - r = __kvm_mips_vcpu_run(run, vcpu); + r = vcpu->arch.vcpu_run(run, vcpu); /* Re-enable HTW before enabling interrupts */ htw_start(); diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index aed0ac2a4972..7a7ed9ca01bb 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -276,7 +276,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, } gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT); - if (gfn >= kvm->arch.guest_pmap_npages) { + if ((gfn | 1) >= kvm->arch.guest_pmap_npages) { kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__, gfn, badvaddr); kvm_mips_dump_host_tlbs(); @@ -361,25 +361,39 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; pfn_t pfn0, pfn1; - - if ((tlb->tlb_hi & VPN2_MASK) == 0) { - pfn0 = 0; - pfn1 = 0; - } else { - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0) - >> PAGE_SHIFT) < 0) - return -1; - - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1) - >> PAGE_SHIFT) < 0) - return -1; - - pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0) - >> PAGE_SHIFT]; - pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1) - >> PAGE_SHIFT]; + gfn_t gfn0, gfn1; + long tlb_lo[2]; + + tlb_lo[0] = tlb->tlb_lo0; + tlb_lo[1] = tlb->tlb_lo1; + + /* + * The commpage address must not be mapped to anything else if the guest + * TLB contains entries nearby, or commpage accesses will break. + */ + if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) & + VPN2_MASK & (PAGE_MASK << 1))) + tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0; + + gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT; + gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT; + if (gfn0 >= kvm->arch.guest_pmap_npages || + gfn1 >= kvm->arch.guest_pmap_npages) { + kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n", + __func__, gfn0, gfn1, tlb->tlb_hi); + kvm_mips_dump_guest_tlbs(vcpu); + return -1; } + if (kvm_mips_map_page(kvm, gfn0) < 0) + return -1; + + if (kvm_mips_map_page(kvm, gfn1) < 0) + return -1; + + pfn0 = kvm->arch.guest_pmap[gfn0]; + pfn1 = kvm->arch.guest_pmap[gfn1]; + if (hpa0) *hpa0 = pfn0 << PAGE_SHIFT; @@ -391,9 +405,9 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, kvm_mips_get_kernel_asid(vcpu) : kvm_mips_get_user_asid(vcpu)); entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) | - (tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V); + (tlb_lo[0] & MIPS3_PG_D) | (tlb_lo[0] & MIPS3_PG_V); entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) | - (tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V); + (tlb_lo[1] & MIPS3_PG_D) | (tlb_lo[1] & MIPS3_PG_V); kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc, tlb->tlb_lo0, tlb->tlb_lo1); @@ -794,10 +808,16 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu) local_irq_restore(flags); return KVM_INVALID_INST; } - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, - &vcpu->arch. - guest_tlb[index], - NULL, NULL); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, + &vcpu->arch.guest_tlb[index], + NULL, NULL)) { + kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, opc, index, vcpu, + read_c0_entryhi()); + kvm_mips_dump_guest_tlbs(vcpu); + local_irq_restore(flags); + return KVM_INVALID_INST; + } inst = *(opc); } local_irq_restore(flags); diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c index a2631a52ca99..444802e78554 100644 --- a/arch/mips/loongson64/loongson-3/hpet.c +++ b/arch/mips/loongson64/loongson-3/hpet.c @@ -13,8 +13,8 @@ #define SMBUS_PCI_REG64 0x64 #define SMBUS_PCI_REGB4 0xb4 -#define HPET_MIN_CYCLES 64 -#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) +#define HPET_MIN_CYCLES 16 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES * 12) static DEFINE_SPINLOCK(hpet_lock); DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device); @@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt) static int hpet_next_event(unsigned long delta, struct clock_event_device *evt) { - unsigned int cnt; - int res; + u32 cnt; + s32 res; cnt = hpet_read(HPET_COUNTER); - cnt += delta; + cnt += (u32) delta; hpet_write(HPET_T0_CMP, cnt); - res = (int)(cnt - hpet_read(HPET_COUNTER)); + res = (s32)(cnt - hpet_read(HPET_COUNTER)); return res < HPET_MIN_CYCLES ? -ETIME : 0; } @@ -230,7 +230,7 @@ void __init setup_hpet_timer(void) cd = &per_cpu(hpet_clockevent_device, cpu); cd->name = "hpet"; - cd->rating = 320; + cd->rating = 100; cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; cd->set_state_shutdown = hpet_set_state_shutdown; cd->set_state_periodic = hpet_set_state_periodic; diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index b4a837893562..5abe51cad899 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -65,7 +65,7 @@ static struct insn insn_table[] = { #ifndef CONFIG_CPU_MIPSR6 { insn_cache, M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, #else - { insn_cache, M6(cache_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, + { insn_cache, M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, #endif { insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD }, diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h index c0ae62520d15..274d5bc6ecce 100644 --- a/arch/parisc/include/uapi/asm/errno.h +++ b/arch/parisc/include/uapi/asm/errno.h @@ -97,10 +97,10 @@ #define ENOTCONN 235 /* Transport endpoint is not connected */ #define ESHUTDOWN 236 /* Cannot send after transport endpoint shutdown */ #define ETOOMANYREFS 237 /* Too many references: cannot splice */ -#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ #define ETIMEDOUT 238 /* Connection timed out */ #define ECONNREFUSED 239 /* Connection refused */ -#define EREMOTERELEASE 240 /* Remote peer released connection */ +#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ +#define EREMOTERELEASE 240 /* Remote peer released connection */ #define EHOSTDOWN 241 /* Host is down */ #define EHOSTUNREACH 242 /* No route to host */ diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h index 9f8402b35115..27e588f6c72e 100644 --- a/arch/powerpc/include/asm/icswx.h +++ b/arch/powerpc/include/asm/icswx.h @@ -164,6 +164,7 @@ struct coprocessor_request_block { #define ICSWX_INITIATED (0x8) #define ICSWX_BUSY (0x4) #define ICSWX_REJECTED (0x2) +#define ICSWX_XERS0 (0x1) /* undefined or set from XERSO. */ static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb) { diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index b34e8a54f7db..98949b0df00a 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -677,7 +677,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) /* Check if the request is finished successfully */ if (active_flag) { rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc <= 0) + if (rc < 0) return rc; if (rc & active_flag) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 646bf4d222c1..cf788d7d7e56 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1239,6 +1239,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index e52b82b71d79..b7e86e00048f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -718,7 +718,7 @@ unsigned char ibm_architecture_vec[] = { * must match by the macro below. Update the definition if * the structure layout changes. */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 125 +#define IBM_ARCH_VEC_NRCORES_OFFSET 133 W(NR_CPUS), /* number of cores supported */ 0, 0, diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index bf8f34a58670..b7019b559ddb 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 463af88c95a2..974f73df00bb 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -655,112 +655,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BEGIN_FTR_SECTION - b skip_tm -END_FTR_SECTION_IFCLR(CPU_FTR_TM) - - /* Turn on TM/FP/VSX/VMX so we can restore them. */ - mfmsr r5 - li r6, MSR_TM >> 32 - sldi r6, r6, 32 - or r5, r5, r6 - ori r5, r5, MSR_FP - oris r5, r5, (MSR_VEC | MSR_VSX)@h - mtmsrd r5 - - /* - * The user may change these outside of a transaction, so they must - * always be context switched. - */ - ld r5, VCPU_TFHAR(r4) - ld r6, VCPU_TFIAR(r4) - ld r7, VCPU_TEXASR(r4) - mtspr SPRN_TFHAR, r5 - mtspr SPRN_TFIAR, r6 - mtspr SPRN_TEXASR, r7 - - ld r5, VCPU_MSR(r4) - rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 - beq skip_tm /* TM not active in guest */ - - /* Make sure the failure summary is set, otherwise we'll program check - * when we trechkpt. It's possible that this might have been not set - * on a kvmppc_set_one_reg() call but we shouldn't let this crash the - * host. - */ - oris r7, r7, (TEXASR_FS)@h - mtspr SPRN_TEXASR, r7 - - /* - * We need to load up the checkpointed state for the guest. - * We need to do this early as it will blow away any GPRs, VSRs and - * some SPRs. - */ - - mr r31, r4 - addi r3, r31, VCPU_FPRS_TM - bl load_fp_state - addi r3, r31, VCPU_VRS_TM - bl load_vr_state - mr r4, r31 - lwz r7, VCPU_VRSAVE_TM(r4) - mtspr SPRN_VRSAVE, r7 - - ld r5, VCPU_LR_TM(r4) - lwz r6, VCPU_CR_TM(r4) - ld r7, VCPU_CTR_TM(r4) - ld r8, VCPU_AMR_TM(r4) - ld r9, VCPU_TAR_TM(r4) - mtlr r5 - mtcr r6 - mtctr r7 - mtspr SPRN_AMR, r8 - mtspr SPRN_TAR, r9 - - /* - * Load up PPR and DSCR values but don't put them in the actual SPRs - * till the last moment to avoid running with userspace PPR and DSCR for - * too long. - */ - ld r29, VCPU_DSCR_TM(r4) - ld r30, VCPU_PPR_TM(r4) - - std r2, PACATMSCRATCH(r13) /* Save TOC */ - - /* Clear the MSR RI since r1, r13 are all going to be foobar. */ - li r5, 0 - mtmsrd r5, 1 - - /* Load GPRs r0-r28 */ - reg = 0 - .rept 29 - ld reg, VCPU_GPRS_TM(reg)(r31) - reg = reg + 1 - .endr - - mtspr SPRN_DSCR, r29 - mtspr SPRN_PPR, r30 - - /* Load final GPRs */ - ld 29, VCPU_GPRS_TM(29)(r31) - ld 30, VCPU_GPRS_TM(30)(r31) - ld 31, VCPU_GPRS_TM(31)(r31) - - /* TM checkpointed state is now setup. All GPRs are now volatile. */ - TRECHKPT - - /* Now let's get back the state we need. */ - HMT_MEDIUM - GET_PACA(r13) - ld r29, HSTATE_DSCR(r13) - mtspr SPRN_DSCR, r29 - ld r4, HSTATE_KVM_VCPU(r13) - ld r1, HSTATE_HOST_R1(r13) - ld r2, PACATMSCRATCH(r13) - - /* Set the MSR RI since we have our registers back. */ - li r5, MSR_RI - mtmsrd r5, 1 -skip_tm: + bl kvmppc_restore_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif /* Load guest PMU registers */ @@ -841,12 +737,6 @@ BEGIN_FTR_SECTION /* Skip next section on POWER7 */ b 8f END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) - /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ - mfmsr r8 - li r0, 1 - rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r8 - /* Load up POWER8-specific registers */ ld r5, VCPU_IAMR(r4) lwz r6, VCPU_PSPB(r4) @@ -1436,106 +1326,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BEGIN_FTR_SECTION - b 2f -END_FTR_SECTION_IFCLR(CPU_FTR_TM) - /* Turn on TM. */ - mfmsr r8 - li r0, 1 - rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r8 - - ld r5, VCPU_MSR(r9) - rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 - beq 1f /* TM not active in guest. */ - - li r3, TM_CAUSE_KVM_RESCHED - - /* Clear the MSR RI since r1, r13 are all going to be foobar. */ - li r5, 0 - mtmsrd r5, 1 - - /* All GPRs are volatile at this point. */ - TRECLAIM(R3) - - /* Temporarily store r13 and r9 so we have some regs to play with */ - SET_SCRATCH0(r13) - GET_PACA(r13) - std r9, PACATMSCRATCH(r13) - ld r9, HSTATE_KVM_VCPU(r13) - - /* Get a few more GPRs free. */ - std r29, VCPU_GPRS_TM(29)(r9) - std r30, VCPU_GPRS_TM(30)(r9) - std r31, VCPU_GPRS_TM(31)(r9) - - /* Save away PPR and DSCR soon so don't run with user values. */ - mfspr r31, SPRN_PPR - HMT_MEDIUM - mfspr r30, SPRN_DSCR - ld r29, HSTATE_DSCR(r13) - mtspr SPRN_DSCR, r29 - - /* Save all but r9, r13 & r29-r31 */ - reg = 0 - .rept 29 - .if (reg != 9) && (reg != 13) - std reg, VCPU_GPRS_TM(reg)(r9) - .endif - reg = reg + 1 - .endr - /* ... now save r13 */ - GET_SCRATCH0(r4) - std r4, VCPU_GPRS_TM(13)(r9) - /* ... and save r9 */ - ld r4, PACATMSCRATCH(r13) - std r4, VCPU_GPRS_TM(9)(r9) - - /* Reload stack pointer and TOC. */ - ld r1, HSTATE_HOST_R1(r13) - ld r2, PACATOC(r13) - - /* Set MSR RI now we have r1 and r13 back. */ - li r5, MSR_RI - mtmsrd r5, 1 - - /* Save away checkpinted SPRs. */ - std r31, VCPU_PPR_TM(r9) - std r30, VCPU_DSCR_TM(r9) - mflr r5 - mfcr r6 - mfctr r7 - mfspr r8, SPRN_AMR - mfspr r10, SPRN_TAR - std r5, VCPU_LR_TM(r9) - stw r6, VCPU_CR_TM(r9) - std r7, VCPU_CTR_TM(r9) - std r8, VCPU_AMR_TM(r9) - std r10, VCPU_TAR_TM(r9) - - /* Restore r12 as trap number. */ - lwz r12, VCPU_TRAP(r9) - - /* Save FP/VSX. */ - addi r3, r9, VCPU_FPRS_TM - bl store_fp_state - addi r3, r9, VCPU_VRS_TM - bl store_vr_state - mfspr r6, SPRN_VRSAVE - stw r6, VCPU_VRSAVE_TM(r9) -1: - /* - * We need to save these SPRs after the treclaim so that the software - * error code is recorded correctly in the TEXASR. Also the user may - * change these outside of a transaction, so they must always be - * context switched. - */ - mfspr r5, SPRN_TFHAR - mfspr r6, SPRN_TFIAR - mfspr r7, SPRN_TEXASR - std r5, VCPU_TFHAR(r9) - std r6, VCPU_TFIAR(r9) - std r7, VCPU_TEXASR(r9) -2: + bl kvmppc_save_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif /* Increment yield count if they have a VPA */ @@ -2245,6 +2037,13 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */ /* save FP state */ bl kvmppc_save_fp +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + ld r9, HSTATE_KVM_VCPU(r13) + bl kvmppc_save_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) +#endif + /* * Set DEC to the smaller of DEC and HDEC, so that we wake * no later than the end of our timeslice (HDEC interrupts @@ -2321,6 +2120,12 @@ kvm_end_cede: bl kvmhv_accumulate_time #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + bl kvmppc_restore_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) +#endif + /* load up FP state */ bl kvmppc_load_fp @@ -2629,6 +2434,239 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mr r4,r31 blr +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +/* + * Save transactional state and TM-related registers. + * Called with r9 pointing to the vcpu struct. + * This can modify all checkpointed registers, but + * restores r1, r2 and r9 (vcpu pointer) before exit. + */ +kvmppc_save_tm: + mflr r0 + std r0, PPC_LR_STKOFF(r1) + + /* Turn on TM. */ + mfmsr r8 + li r0, 1 + rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG + mtmsrd r8 + + ld r5, VCPU_MSR(r9) + rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 + beq 1f /* TM not active in guest. */ + + std r1, HSTATE_HOST_R1(r13) + li r3, TM_CAUSE_KVM_RESCHED + + /* Clear the MSR RI since r1, r13 are all going to be foobar. */ + li r5, 0 + mtmsrd r5, 1 + + /* All GPRs are volatile at this point. */ + TRECLAIM(R3) + + /* Temporarily store r13 and r9 so we have some regs to play with */ + SET_SCRATCH0(r13) + GET_PACA(r13) + std r9, PACATMSCRATCH(r13) + ld r9, HSTATE_KVM_VCPU(r13) + + /* Get a few more GPRs free. */ + std r29, VCPU_GPRS_TM(29)(r9) + std r30, VCPU_GPRS_TM(30)(r9) + std r31, VCPU_GPRS_TM(31)(r9) + + /* Save away PPR and DSCR soon so don't run with user values. */ + mfspr r31, SPRN_PPR + HMT_MEDIUM + mfspr r30, SPRN_DSCR + ld r29, HSTATE_DSCR(r13) + mtspr SPRN_DSCR, r29 + + /* Save all but r9, r13 & r29-r31 */ + reg = 0 + .rept 29 + .if (reg != 9) && (reg != 13) + std reg, VCPU_GPRS_TM(reg)(r9) + .endif + reg = reg + 1 + .endr + /* ... now save r13 */ + GET_SCRATCH0(r4) + std r4, VCPU_GPRS_TM(13)(r9) + /* ... and save r9 */ + ld r4, PACATMSCRATCH(r13) + std r4, VCPU_GPRS_TM(9)(r9) + + /* Reload stack pointer and TOC. */ + ld r1, HSTATE_HOST_R1(r13) + ld r2, PACATOC(r13) + + /* Set MSR RI now we have r1 and r13 back. */ + li r5, MSR_RI + mtmsrd r5, 1 + + /* Save away checkpinted SPRs. */ + std r31, VCPU_PPR_TM(r9) + std r30, VCPU_DSCR_TM(r9) + mflr r5 + mfcr r6 + mfctr r7 + mfspr r8, SPRN_AMR + mfspr r10, SPRN_TAR + std r5, VCPU_LR_TM(r9) + stw r6, VCPU_CR_TM(r9) + std r7, VCPU_CTR_TM(r9) + std r8, VCPU_AMR_TM(r9) + std r10, VCPU_TAR_TM(r9) + + /* Restore r12 as trap number. */ + lwz r12, VCPU_TRAP(r9) + + /* Save FP/VSX. */ + addi r3, r9, VCPU_FPRS_TM + bl store_fp_state + addi r3, r9, VCPU_VRS_TM + bl store_vr_state + mfspr r6, SPRN_VRSAVE + stw r6, VCPU_VRSAVE_TM(r9) +1: + /* + * We need to save these SPRs after the treclaim so that the software + * error code is recorded correctly in the TEXASR. Also the user may + * change these outside of a transaction, so they must always be + * context switched. + */ + mfspr r5, SPRN_TFHAR + mfspr r6, SPRN_TFIAR + mfspr r7, SPRN_TEXASR + std r5, VCPU_TFHAR(r9) + std r6, VCPU_TFIAR(r9) + std r7, VCPU_TEXASR(r9) + + ld r0, PPC_LR_STKOFF(r1) + mtlr r0 + blr + +/* + * Restore transactional state and TM-related registers. + * Called with r4 pointing to the vcpu struct. + * This potentially modifies all checkpointed registers. + * It restores r1, r2, r4 from the PACA. + */ +kvmppc_restore_tm: + mflr r0 + std r0, PPC_LR_STKOFF(r1) + + /* Turn on TM/FP/VSX/VMX so we can restore them. */ + mfmsr r5 + li r6, MSR_TM >> 32 + sldi r6, r6, 32 + or r5, r5, r6 + ori r5, r5, MSR_FP + oris r5, r5, (MSR_VEC | MSR_VSX)@h + mtmsrd r5 + + /* + * The user may change these outside of a transaction, so they must + * always be context switched. + */ + ld r5, VCPU_TFHAR(r4) + ld r6, VCPU_TFIAR(r4) + ld r7, VCPU_TEXASR(r4) + mtspr SPRN_TFHAR, r5 + mtspr SPRN_TFIAR, r6 + mtspr SPRN_TEXASR, r7 + + ld r5, VCPU_MSR(r4) + rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 + beqlr /* TM not active in guest */ + std r1, HSTATE_HOST_R1(r13) + + /* Make sure the failure summary is set, otherwise we'll program check + * when we trechkpt. It's possible that this might have been not set + * on a kvmppc_set_one_reg() call but we shouldn't let this crash the + * host. + */ + oris r7, r7, (TEXASR_FS)@h + mtspr SPRN_TEXASR, r7 + + /* + * We need to load up the checkpointed state for the guest. + * We need to do this early as it will blow away any GPRs, VSRs and + * some SPRs. + */ + + mr r31, r4 + addi r3, r31, VCPU_FPRS_TM + bl load_fp_state + addi r3, r31, VCPU_VRS_TM + bl load_vr_state + mr r4, r31 + lwz r7, VCPU_VRSAVE_TM(r4) + mtspr SPRN_VRSAVE, r7 + + ld r5, VCPU_LR_TM(r4) + lwz r6, VCPU_CR_TM(r4) + ld r7, VCPU_CTR_TM(r4) + ld r8, VCPU_AMR_TM(r4) + ld r9, VCPU_TAR_TM(r4) + mtlr r5 + mtcr r6 + mtctr r7 + mtspr SPRN_AMR, r8 + mtspr SPRN_TAR, r9 + + /* + * Load up PPR and DSCR values but don't put them in the actual SPRs + * till the last moment to avoid running with userspace PPR and DSCR for + * too long. + */ + ld r29, VCPU_DSCR_TM(r4) + ld r30, VCPU_PPR_TM(r4) + + std r2, PACATMSCRATCH(r13) /* Save TOC */ + + /* Clear the MSR RI since r1, r13 are all going to be foobar. */ + li r5, 0 + mtmsrd r5, 1 + + /* Load GPRs r0-r28 */ + reg = 0 + .rept 29 + ld reg, VCPU_GPRS_TM(reg)(r31) + reg = reg + 1 + .endr + + mtspr SPRN_DSCR, r29 + mtspr SPRN_PPR, r30 + + /* Load final GPRs */ + ld 29, VCPU_GPRS_TM(29)(r31) + ld 30, VCPU_GPRS_TM(30)(r31) + ld 31, VCPU_GPRS_TM(31)(r31) + + /* TM checkpointed state is now setup. All GPRs are now volatile. */ + TRECHKPT + + /* Now let's get back the state we need. */ + HMT_MEDIUM + GET_PACA(r13) + ld r29, HSTATE_DSCR(r13) + mtspr SPRN_DSCR, r29 + ld r4, HSTATE_KVM_VCPU(r13) + ld r1, HSTATE_HOST_R1(r13) + ld r2, PACATMSCRATCH(r13) + + /* Set the MSR RI since we have our registers back. */ + li r5, MSR_RI + mtmsrd r5, 1 + + ld r0, PPC_LR_STKOFF(r1) + mtlr r0 + blr +#endif + /* * We come here if we get any exception or interrupt while we are * executing host real mode code while in guest MMU context. diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index bd98ce2be17b..3e8865b187de 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -912,7 +912,8 @@ machine_arch_initcall(pseries, find_existing_ddw_windows); static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_query_response *query) { - struct eeh_dev *edev; + struct device_node *dn; + struct pci_dn *pdn; u32 cfg_addr; u64 buid; int ret; @@ -923,11 +924,10 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - edev = pci_dev_to_eeh_dev(dev); - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, cfg_addr, BUID_HI(buid), BUID_LO(buid)); @@ -941,7 +941,8 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_create_response *create, int page_shift, int window_shift) { - struct eeh_dev *edev; + struct device_node *dn; + struct pci_dn *pdn; u32 cfg_addr; u64 buid; int ret; @@ -952,11 +953,10 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - edev = pci_dev_to_eeh_dev(dev); - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index b8045b97f4fb..d750cc0dfe30 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -669,11 +669,13 @@ static const struct file_operations prng_tdes_fops = { static struct miscdevice prng_sha512_dev = { .name = "prandom", .minor = MISC_DYNAMIC_MINOR, + .mode = 0644, .fops = &prng_sha512_fops, }; static struct miscdevice prng_tdes_dev = { .name = "prandom", .minor = MISC_DYNAMIC_MINOR, + .mode = 0644, .fops = &prng_tdes_fops, }; diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index 5e04f3cbd320..8ae236b0f80b 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc) " la %0,0\n" "1:\n" EX_TABLE(0b,1b) - : "=d" (rc), "=d" (orig_fpc) + : "=d" (rc), "=&d" (orig_fpc) : "d" (fpc), "0" (-EINVAL)); return rc; } diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h index 1aac41e83ea1..92df3eb8d14e 100644 --- a/arch/s390/include/asm/pci_dma.h +++ b/arch/s390/include/asm/pci_dma.h @@ -23,6 +23,8 @@ enum zpci_ioat_dtype { #define ZPCI_IOTA_FS_2G 2 #define ZPCI_KEY (PAGE_DEFAULT_KEY << 5) +#define ZPCI_TABLE_SIZE_RT (1UL << 42) + #define ZPCI_IOTA_STO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST) #define ZPCI_IOTA_RTTO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT) #define ZPCI_IOTA_RSTO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index b1f0a90f933b..42570d8fb265 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2070,13 +2070,6 @@ void s390_reset_system(void (*fn_pre)(void), S390_lowcore.program_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; - /* - * Clear subchannel ID and number to signal new kernel that no CCW or - * SCSI IPL has been done (for kexec and kdump) - */ - S390_lowcore.subchannel_id = 0; - S390_lowcore.subchannel_nr = 0; - /* Store status at absolute zero */ store_status(); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 19442395f413..f2f6720a3331 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -701,8 +701,7 @@ static int zpci_restore(struct device *dev) goto out; zpci_map_resources(pdev); - zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET, - zdev->start_dma + zdev->iommu_size - 1, + zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, (u64) zdev->dma_table); out: diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index d348f2c09a1e..3a40f718baef 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -458,7 +458,19 @@ int zpci_dma_init_device(struct zpci_dev *zdev) goto out_clean; } - zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET; + /* + * Restrict the iommu bitmap size to the minimum of the following: + * - main memory size + * - 3-level pagetable address limit minus start_dma offset + * - DMA address range allowed by the hardware (clp query pci fn) + * + * Also set zdev->end_dma to the actual end address of the usable + * range, instead of the theoretical maximum as reported by hardware. + */ + zdev->iommu_size = min3((u64) high_memory, + ZPCI_TABLE_SIZE_RT - zdev->start_dma, + zdev->end_dma - zdev->start_dma + 1); + zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1; zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT; zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); if (!zdev->iommu_bitmap) { @@ -466,10 +478,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) goto out_reg; } - rc = zpci_register_ioat(zdev, - 0, - zdev->start_dma + PAGE_OFFSET, - zdev->start_dma + zdev->iommu_size - 1, + rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, (u64) zdev->dma_table); if (rc) goto out_reg; diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S index 1dd5bd8a8c59..133055311dce 100644 --- a/arch/um/include/asm/common.lds.S +++ b/arch/um/include/asm/common.lds.S @@ -81,7 +81,7 @@ .altinstr_replacement : { *(.altinstr_replacement) } /* .exit.text is discard at runtime, not link time, to deal with references from .altinstructions and .eh_frame */ - .exit.text : { *(.exit.text) } + .exit.text : { EXIT_TEXT } .exit.data : { *(.exit.data) } .preinit_array : { diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 2ee62dba0373..c0cc2a6be0bf 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage for i in lib lib64 share end ; do \ if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \ cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \ + if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \ + cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \ + fi ; \ break ; \ fi ; \ if [ $$i = end ] ; then exit 1 ; fi ; \ diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index f17705e1332c..e62f4401e792 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -294,7 +294,7 @@ # 285 sys_setaltroot 286 i386 add_key sys_add_key 287 i386 request_key sys_request_key -288 i386 keyctl sys_keyctl +288 i386 keyctl sys_keyctl compat_sys_keyctl 289 i386 ioprio_set sys_ioprio_set 290 i386 ioprio_get sys_ioprio_get 291 i386 inotify_init sys_inotify_init diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index b94f6f64e23d..dbff1456d215 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -24,6 +24,7 @@ #define _ASM_X86_MTRR_H #include <uapi/asm/mtrr.h> +#include <asm/pat.h> /* @@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } +static inline void mtrr_bp_init(void) +{ + pat_disable("MTRRs disabled, skipping PAT initialization too."); +} #define mtrr_ap_init() do {} while (0) -#define mtrr_bp_init() do {} while (0) #define set_mtrr_aps_delayed_init() do {} while (0) #define mtrr_aps_init() do {} while (0) #define mtrr_bp_restore() do {} while (0) diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index ca6c228d5e62..0b1ff4c1c14e 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -5,8 +5,8 @@ #include <asm/pgtable_types.h> bool pat_enabled(void); +void pat_disable(const char *reason); extern void pat_init(void); -void pat_init_cache_modes(u64); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7a6bed5c08bc..baad72e4c100 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -76,6 +76,8 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u8 ret_flags; version = src->version; + /* Make the latest version visible */ + smp_rmb(); offset = pvclock_get_nsec_offset(src); ret = src->system_time + offset; diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6df2029405a3..3142218e546f 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -86,7 +86,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) static inline void __native_flush_tlb(void) { + /* + * If current->mm == NULL then we borrow a mm which may change during a + * task switch and therefore we must not be preempted while we write CR3 + * back: + */ + preempt_disable(); native_write_cr3(native_read_cr3()); + preempt_enable(); } static inline void __native_flush_tlb_global_irq_disabled(void) diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 29fa475ec518..c986d0b3bc35 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2f69e3b184f6..a3e1f8497f8c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1587,6 +1587,9 @@ void __init enable_IR_x2apic(void) unsigned long flags; int ret, ir_stat; + if (skip_ioapic_setup) + return; + ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) return; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 20e242ea1bc4..cfc4a966e2b9 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -152,6 +152,11 @@ static struct clocksource hyperv_cs = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +static unsigned char hv_get_nmi_reason(void) +{ + return 0; +} + static void __init ms_hyperv_init_platform(void) { /* @@ -191,6 +196,13 @@ static void __init ms_hyperv_init_platform(void) machine_ops.crash_shutdown = hv_machine_crash_shutdown; #endif mark_tsc_unstable("running on Hyper-V"); + + /* + * Generation 2 instances don't support reading the NMI status from + * 0x61 port. + */ + if (efi_enabled(EFI_BOOT)) + x86_platform.get_nmi_reason = hv_get_nmi_reason; } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3b533cf37c74..b5624fafa44a 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -444,11 +444,24 @@ static void __init print_mtrr_state(void) pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } +/* PAT setup for BP. We need to go through sync steps here */ +void __init mtrr_bp_pat_init(void) +{ + unsigned long flags; + + local_irq_save(flags); + prepare_set(); + + pat_init(); + + post_set(); + local_irq_restore(flags); +} + /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; - unsigned long flags; unsigned lo, dummy; unsigned int i; @@ -481,15 +494,6 @@ bool __init get_mtrr_state(void) mtrr_state_set = 1; - /* PAT setup for BP. We need to go through sync steps here */ - local_irq_save(flags); - prepare_set(); - - pat_init(); - - post_set(); - local_irq_restore(flags); - return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f891b4750f04..fa77ac8291f0 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -752,6 +752,9 @@ void __init mtrr_bp_init(void) /* BIOS may override */ __mtrr_enabled = get_mtrr_state(); + if (mtrr_enabled()) + mtrr_bp_pat_init(); + if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; mtrr_if->set_all(); @@ -759,8 +762,16 @@ void __init mtrr_bp_init(void) } } - if (!mtrr_enabled()) + if (!mtrr_enabled()) { pr_info("MTRR: Disabled\n"); + + /* + * PAT initialization relies on MTRR's rendezvous handler. + * Skip PAT init until the handler can initialize both + * features independently. + */ + pat_disable("MTRRs disabled, skipping PAT initialization too."); + } } void mtrr_ap_init(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 951884dcc433..6c7ced07d16d 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); +void mtrr_bp_pat_init(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 078de2e86b7a..5f82cd59f0e5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -3601,7 +3601,7 @@ __init int intel_pmu_init(void) c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } c->idxmsk64 &= - ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); + ~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); c->weight = hweight64(c->idxmsk64); } } diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index a316ca96f1b6..fc704ed587e8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -211,6 +211,20 @@ static void __put_rmid(u32 rmid) list_add_tail(&entry->list, &cqm_rmid_limbo_lru); } +static void cqm_cleanup(void) +{ + int i; + + if (!cqm_rmid_ptrs) + return; + + for (i = 0; i < cqm_max_rmid; i++) + kfree(cqm_rmid_ptrs[i]); + + kfree(cqm_rmid_ptrs); + cqm_rmid_ptrs = NULL; +} + static int intel_cqm_setup_rmid_cache(void) { struct cqm_rmid_entry *entry; @@ -218,7 +232,7 @@ static int intel_cqm_setup_rmid_cache(void) int r = 0; nr_rmids = cqm_max_rmid + 1; - cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) * + cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) * nr_rmids, GFP_KERNEL); if (!cqm_rmid_ptrs) return -ENOMEM; @@ -249,11 +263,9 @@ static int intel_cqm_setup_rmid_cache(void) mutex_unlock(&cache_mutex); return 0; -fail: - while (r--) - kfree(cqm_rmid_ptrs[r]); - kfree(cqm_rmid_ptrs); +fail: + cqm_cleanup(); return -ENOMEM; } @@ -281,9 +293,13 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) /* * Events that target same task are placed into the same cache group. + * Mark it as a multi event group, so that we update ->count + * for every event rather than just the group leader later. */ - if (a->hw.target == b->hw.target) + if (a->hw.target == b->hw.target) { + b->hw.is_group_event = true; return true; + } /* * Are we an inherited event? @@ -849,6 +865,7 @@ static void intel_cqm_setup_event(struct perf_event *event, bool conflict = false; u32 rmid; + event->hw.is_group_event = false; list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { rmid = iter->hw.cqm_rmid; @@ -940,7 +957,9 @@ static u64 intel_cqm_event_count(struct perf_event *event) return __perf_event_count(event); /* - * Only the group leader gets to report values. This stops us + * Only the group leader gets to report values except in case of + * multiple events in the same group, we still need to read the + * other events.This stops us * reporting duplicate values to userspace, and gives us a clear * rule for which task gets to report the values. * @@ -948,7 +967,7 @@ static u64 intel_cqm_event_count(struct perf_event *event) * specific packages - we forfeit that ability when we create * task events. */ - if (!cqm_group_leader(event)) + if (!cqm_group_leader(event) && !event->hw.is_group_event) return 0; /* @@ -1315,7 +1334,7 @@ static const struct x86_cpu_id intel_cqm_match[] = { static int __init intel_cqm_init(void) { - char *str, scale[20]; + char *str = NULL, scale[20]; int i, cpu, ret; if (!x86_match_cpu(intel_cqm_match)) @@ -1375,16 +1394,25 @@ static int __init intel_cqm_init(void) cqm_pick_event_reader(i); } - __perf_cpu_notifier(intel_cqm_cpu_notifier); - ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1); - if (ret) + if (ret) { pr_err("Intel CQM perf registration failed: %d\n", ret); - else - pr_info("Intel CQM monitoring enabled\n"); + goto out; + } + + pr_info("Intel CQM monitoring enabled\n"); + /* + * Register the hot cpu notifier once we are sure cqm + * is enabled to avoid notifier leak. + */ + __perf_cpu_notifier(intel_cqm_cpu_notifier); out: cpu_notifier_register_done(); + if (ret) { + kfree(str); + cqm_cleanup(); + } return ret; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 7abb2b88572e..1e7de3cefc9c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -1110,6 +1110,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) void *at; u64 pebs_status; + /* + * fmt0 does not have a status bitfield (does not use + * perf_record_nhm format) + */ + if (x86_pmu.intel_cap.pebs_format < 1) + return base; + if (base == NULL) return NULL; @@ -1195,7 +1202,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = (top - at) / x86_pmu.pebs_record_size; + n = top - at; if (n <= 0) return; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index db9a675e751b..9fdf1d330727 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include <linux/pci.h> #include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/dmi.h> #include <linux/pci_ids.h> +#include <linux/bcma/bcma.h> +#include <linux/bcma/bcma_regs.h> #include <drm/i915_drm.h> #include <asm/pci-direct.h> #include <asm/dma.h> @@ -21,6 +25,9 @@ #include <asm/iommu.h> #include <asm/gart.h> #include <asm/irq_remapping.h> +#include <asm/early_ioremap.h> + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func) #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC /* + * Only applies to Nvidia root ports (bus 0) and not to + * Nvidia graphics cards with PCI ports on secondary buses. + */ + if (num) + return; + + /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. * Unfortunately that's not true on many Asus boards. @@ -589,6 +603,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -602,12 +671,6 @@ struct chipset { void (*f)(int num, int slot, int func); }; -/* - * Only works for devices on the root bus. If you add any devices - * not on bus 0 readd another loop level in early_quirks(). But - * be careful because at least the Nvidia quirk here relies on - * only matching on bus 0. - */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -637,9 +700,13 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; +static void __init early_pci_scan_bus(int bus); + /** * check_dev_quirk - apply early quirks to a given PCI device * @num: bus number @@ -648,7 +715,7 @@ static struct chipset early_qrk[] __initdata = { * * Check the vendor & device ID against the early quirks table. * - * If the device is single function, let early_quirks() know so we don't + * If the device is single function, let early_pci_scan_bus() know so we don't * poke at this device again. */ static int __init check_dev_quirk(int num, int slot, int func) @@ -657,6 +724,7 @@ static int __init check_dev_quirk(int num, int slot, int func) u16 vendor; u16 device; u8 type; + u8 sec; int i; class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); @@ -684,25 +752,36 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); + + if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); + if (sec > num) + early_pci_scan_bus(sec); + } + if (!(type & 0x80)) return -1; return 0; } -void __init early_quirks(void) +static void __init early_pci_scan_bus(int bus) { int slot, func; - if (!early_pci_allowed()) - return; - /* Poor man's PCI discovery */ - /* Only scan the root bus */ for (slot = 0; slot < 32; slot++) for (func = 0; func < 8; func++) { /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(0, slot, func)) + if (check_dev_quirk(bus, slot, func)) break; } } + +void __init early_quirks(void) +{ + if (!early_pci_allowed()) + return; + + early_pci_scan_bus(0); +} diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 1deffe6cc873..023c442c33bb 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -959,7 +959,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * normal page fault. */ regs->ip = (unsigned long)cur->addr; + /* + * Trap flag (TF) has been set here because this fault + * happened where the single stepping will be done. + * So clear it by resetting the current kprobe: + */ + regs->flags &= ~X86_EFLAGS_TF; + + /* + * If the TF flag was set before the kprobe hit, + * don't touch it: + */ regs->flags |= kcb->kprobe_old_flags; + if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..bf0ce75735b0 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -66,6 +66,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); return flags & valid_flags; @@ -80,6 +82,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index bf4db6eaec8f..c6aace2bbe08 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) *cursor &= 0xfe; } /* - * Similar treatment for VEX3 prefix. - * TODO: add XOP/EVEX treatment when insn decoder supports them + * Similar treatment for VEX3/EVEX prefix. + * TODO: add XOP treatment when insn decoder supports them */ - if (insn->vex_prefix.nbytes == 3) { + if (insn->vex_prefix.nbytes >= 3) { /* * vex2: c5 rvvvvLpp (has no b bit) * vex3/xop: c4/8f rxbmmmmm wvvvvLpp * evex: 62 rxbR00mm wvvvv1pp zllBVaaa - * (evex will need setting of both b and x since - * in non-sib encoding evex.x is 4th bit of MODRM.rm) - * Setting VEX3.b (setting because it has inverted meaning): + * Setting VEX3.b (setting because it has inverted meaning). + * Setting EVEX.x since (in non-SIB encoding) EVEX.x + * is the 4th bit of MODRM.rm, and needs the same treatment. + * For VEX3-encoded insns, VEX3.x value has no effect in + * non-SIB encoding, the change is superfluous but harmless. */ cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1; - *cursor |= 0x20; + *cursor |= 0x60; } /* @@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) reg = MODRM_REG(insn); /* Fetch modrm.reg */ reg2 = 0xff; /* Fetch vex.vvvv */ - if (insn->vex_prefix.nbytes == 2) - reg2 = insn->vex_prefix.bytes[1]; - else if (insn->vex_prefix.nbytes == 3) + if (insn->vex_prefix.nbytes) reg2 = insn->vex_prefix.bytes[2]; /* - * TODO: add XOP, EXEV vvvv reading. + * TODO: add XOP vvvv reading. * * vex.vvvv field is in bits 6-3, bits are inverted. * But in 32-bit mode, high-order bit may be ignored. diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index c146f3c262c3..0149ac59c273 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -539,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter) iter->fixed = false; iter->start_max = iter->start; + iter->range = NULL; iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node); __mtrr_lookup_var_next(iter); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f314e9b9660b..4589b6feeb7b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6579,7 +6579,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6596,17 +6602,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); @@ -8125,6 +8124,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason != EXIT_REASON_EXCEPTION_NMI && exit_reason != EXIT_REASON_EPT_VIOLATION && + exit_reason != EXIT_REASON_PML_FULL && exit_reason != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; @@ -8737,6 +8737,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu) put_cpu(); } +/* + * Ensure that the current vmcs of the logical processor is the + * vmcs01 of the vcpu before calling free_nested(). + */ +static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int r; + + r = vcpu_load(vcpu); + BUG_ON(r); + vmx_load_vmcs01(vcpu); + free_nested(vmx); + vcpu_put(vcpu); +} + static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8745,8 +8761,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) vmx_destroy_pml_buffer(vmx); free_vpid(vmx->vpid); leave_guest_mode(vcpu); - vmx_load_vmcs01(vcpu); - free_nested(vmx); + vmx_free_vcpu_nested(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 844b06d67df4..307f60ecfc6d 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -94,18 +94,6 @@ static unsigned long mmap_base(unsigned long rnd) } /* - * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 - * does, but not when emulating X86_32 - */ -static unsigned long mmap_legacy_base(unsigned long rnd) -{ - if (mmap_is_ia32()) - return TASK_UNMAPPED_BASE; - else - return TASK_UNMAPPED_BASE + rnd; -} - -/* * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: */ @@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); - mm->mmap_legacy_base = mmap_legacy_base(random_factor); + mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor; if (mmap_is_legacy()) { mm->mmap_base = mm->mmap_legacy_base; diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 188e3e07eeeb..6ad687d104ca 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -39,11 +39,22 @@ static bool boot_cpu_done; static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); +static void init_cache_modes(void); -static inline void pat_disable(const char *reason) +void pat_disable(const char *reason) { + if (!__pat_enabled) + return; + + if (boot_cpu_done) { + WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); + return; + } + __pat_enabled = 0; pr_info("x86/PAT: %s\n", reason); + + init_cache_modes(); } static int __init nopat(char *str) @@ -180,7 +191,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(u64 pat) +static void __init_cache_modes(u64 pat) { enum page_cache_mode cache; char pat_msg[33]; @@ -201,14 +212,11 @@ static void pat_bsp_init(u64 pat) { u64 tmp_pat; - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { pat_disable("PAT not supported by CPU."); return; } - if (!pat_enabled()) - goto done; - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { pat_disable("PAT MSR is 0, disabled."); @@ -217,16 +225,12 @@ static void pat_bsp_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); -done: - pat_init_cache_modes(pat); + __init_cache_modes(pat); } static void pat_ap_init(u64 pat) { - if (!pat_enabled()) - return; - - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { /* * If this happens we are on a secondary CPU, but switched to * PAT on the boot CPU. We have no way to undo PAT. @@ -237,18 +241,32 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void pat_init(void) +static void init_cache_modes(void) { - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; + u64 pat = 0; + static int init_cm_done; - if (!pat_enabled()) { + if (init_cm_done) + return; + + if (boot_cpu_has(X86_FEATURE_PAT)) { + /* + * CPU supports PAT. Set PAT table to be consistent with + * PAT MSR. This case supports "nopat" boot option, and + * virtual machine environments which support PAT without + * MTRRs. In specific, Xen has unique setup to PAT MSR. + * + * If PAT MSR returns 0, it is considered invalid and emulates + * as No PAT. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + } + + if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two - * cache bits, PWT (Write Through) and PCD (Cache Disable). This - * setup is the same as the BIOS default setup when the system - * has PAT but the "nopat" boot option has been specified. This - * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * cache bits, PWT (Write Through) and PCD (Cache Disable). + * This setup is also the same as the BIOS default setup. * * PTE encoding: * @@ -265,10 +283,36 @@ void pat_init(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } + + __init_cache_modes(pat); + + init_cm_done = 1; +} + +/** + * pat_init - Initialize PAT MSR and PAT table + * + * This function initializes PAT MSR and PAT table with an OS-defined value + * to enable additional cache attributes, WC and WT. + * + * This function must be called on all CPUs using the specific sequence of + * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this + * procedure for PAT. + */ +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + init_cache_modes(); + return; + } - } else if ((c->x86_vendor == X86_VENDOR_INTEL) && - (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || - ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { /* * PAT support with the lower four entries. Intel Pentium 2, * 3, M, and 4 are affected by PAT errata, which makes the @@ -733,25 +777,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (file->f_flags & O_DSYNC) pcm = _PAGE_CACHE_MODE_UC_MINUS; -#ifdef CONFIG_X86_32 - /* - * On the PPro and successors, the MTRRs are used to set - * memory types for physical addresses outside main memory, - * so blindly setting UC or PWT on those pages is wrong. - * For Pentiums and earlier, the surround logic should disable - * caching for the high addresses through the KEN pin, but - * we maintain the tradition of paranoia in this code. - */ - if (!pat_enabled() && - !(boot_cpu_has(X86_FEATURE_MTRR) || - boot_cpu_has(X86_FEATURE_K6_MTRR) || - boot_cpu_has(X86_FEATURE_CYRIX_ARR) || - boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) && - (pfn << PAGE_SHIFT) >= __pa(high_memory)) { - pcm = _PAGE_CACHE_MODE_UC; - } -#endif - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | cachemode2protval(pcm)); return 1; diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 8b93e634af84..ae97f24a4371 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -37,6 +37,7 @@ /* Quirks for the listed devices */ #define PCI_DEVICE_ID_INTEL_MRFL_MMC 0x1190 +#define PCI_DEVICE_ID_INTEL_MRFL_HSU 0x1191 /* Fixed BAR fields */ #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00 /* Fixed BAR (TBD) */ @@ -225,13 +226,20 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) /* Special treatment for IRQ0 */ if (dev->irq == 0) { /* + * Skip HS UART common registers device since it has + * IRQ0 assigned and not used by the kernel. + */ + if (dev->device == PCI_DEVICE_ID_INTEL_MRFL_HSU) + return -EBUSY; + /* * TNG has IRQ0 assigned to eMMC controller. But there * are also other devices with bogus PCI configuration * that have IRQ0 assigned. This check ensures that - * eMMC gets it. + * eMMC gets it. The rest of devices still could be + * enabled without interrupt line being allocated. */ if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC) - return -EBUSY; + return 0; } break; default: diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index beab8c706ac9..ffa41591bff9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -74,7 +74,6 @@ #include <asm/mach_traps.h> #include <asm/mwait.h> #include <asm/pci_x86.h> -#include <asm/pat.h> #include <asm/cpu.h> #ifdef CONFIG_ACPI @@ -1519,7 +1518,6 @@ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; - u64 pat; int rc; if (!xen_start_info) @@ -1627,13 +1625,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->nr_pages); xen_reserve_special_pages(); - /* - * Modify the cache mode translation tables to match Xen's PAT - * configuration. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - pat_init_cache_modes(pat); - /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 |