diff options
| author | Ingo Molnar <mingo@kernel.org> | 2018-02-26 10:39:26 +0300 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2018-02-26 10:41:15 +0300 |
| commit | 3f7df3efeb415610d27aecc282ff96d4a22f0168 (patch) | |
| tree | 0f66382746a1311043a25320243ff5f4b10c282e /arch | |
| parent | 39b9552281abfcdfc54162897018890dafe7ffef (diff) | |
| parent | 4a3928c6f8a53fa1aed28ccba227742486e8ddcb (diff) | |
| download | linux-3f7df3efeb415610d27aecc282ff96d4a22f0168.tar.xz | |
Merge tag 'v4.16-rc3' into x86/mm, to pick up fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch')
155 files changed, 1430 insertions, 990 deletions
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h index 46ebf14aed4e..8a2b331e43fe 100644 --- a/arch/alpha/include/asm/cmpxchg.h +++ b/arch/alpha/include/asm/cmpxchg.h @@ -6,7 +6,6 @@ * Atomic exchange routines. */ -#define __ASM__MB #define ____xchg(type, args...) __xchg ## type ## _local(args) #define ____cmpxchg(type, args...) __cmpxchg ## type ## _local(args) #include <asm/xchg.h> @@ -33,10 +32,6 @@ cmpxchg_local((ptr), (o), (n)); \ }) -#ifdef CONFIG_SMP -#undef __ASM__MB -#define __ASM__MB "\tmb\n" -#endif #undef ____xchg #undef ____cmpxchg #define ____xchg(type, args...) __xchg ##type(args) @@ -64,7 +59,6 @@ cmpxchg((ptr), (o), (n)); \ }) -#undef __ASM__MB #undef ____cmpxchg #endif /* _ALPHA_CMPXCHG_H */ diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h index 68dfb3cb7145..e2b59fac5257 100644 --- a/arch/alpha/include/asm/xchg.h +++ b/arch/alpha/include/asm/xchg.h @@ -12,6 +12,10 @@ * Atomic exchange. * Since it can be used to implement critical sections * it must clobber "memory" (also for interrupts in UP). + * + * The leading and the trailing memory barriers guarantee that these + * operations are fully ordered. + * */ static inline unsigned long @@ -19,6 +23,7 @@ ____xchg(_u8, volatile char *m, unsigned long val) { unsigned long ret, tmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %4,7,%3\n" " insbl %1,%4,%1\n" @@ -28,12 +33,12 @@ ____xchg(_u8, volatile char *m, unsigned long val) " or %1,%2,%2\n" " stq_c %2,0(%3)\n" " beq %2,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) : "r" ((long)m), "1" (val) : "memory"); + smp_mb(); return ret; } @@ -43,6 +48,7 @@ ____xchg(_u16, volatile short *m, unsigned long val) { unsigned long ret, tmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %4,7,%3\n" " inswl %1,%4,%1\n" @@ -52,12 +58,12 @@ ____xchg(_u16, volatile short *m, unsigned long val) " or %1,%2,%2\n" " stq_c %2,0(%3)\n" " beq %2,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) : "r" ((long)m), "1" (val) : "memory"); + smp_mb(); return ret; } @@ -67,17 +73,18 @@ ____xchg(_u32, volatile int *m, unsigned long val) { unsigned long dummy; + smp_mb(); __asm__ __volatile__( "1: ldl_l %0,%4\n" " bis $31,%3,%1\n" " stl_c %1,%2\n" " beq %1,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (val), "=&r" (dummy), "=m" (*m) : "rI" (val), "m" (*m) : "memory"); + smp_mb(); return val; } @@ -87,17 +94,18 @@ ____xchg(_u64, volatile long *m, unsigned long val) { unsigned long dummy; + smp_mb(); __asm__ __volatile__( "1: ldq_l %0,%4\n" " bis $31,%3,%1\n" " stq_c %1,%2\n" " beq %1,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (val), "=&r" (dummy), "=m" (*m) : "rI" (val), "m" (*m) : "memory"); + smp_mb(); return val; } @@ -128,10 +136,12 @@ ____xchg(, volatile void *ptr, unsigned long x, int size) * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. * - * The memory barrier should be placed in SMP only when we actually - * make the change. If we don't change anything (so if the returned - * prev is equal to old) then we aren't acquiring anything new and - * we don't need any memory barrier as far I can tell. + * The leading and the trailing memory barriers guarantee that these + * operations are fully ordered. + * + * The trailing memory barrier is placed in SMP unconditionally, in + * order to guarantee that dependency ordering is preserved when a + * dependency is headed by an unsuccessful operation. */ static inline unsigned long @@ -139,6 +149,7 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) { unsigned long prev, tmp, cmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %5,7,%4\n" " insbl %1,%5,%1\n" @@ -150,13 +161,13 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) " or %1,%2,%2\n" " stq_c %2,0(%4)\n" " beq %2,3f\n" - __ASM__MB "2:\n" ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); + smp_mb(); return prev; } @@ -166,6 +177,7 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) { unsigned long prev, tmp, cmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %5,7,%4\n" " inswl %1,%5,%1\n" @@ -177,13 +189,13 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) " or %1,%2,%2\n" " stq_c %2,0(%4)\n" " beq %2,3f\n" - __ASM__MB "2:\n" ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); + smp_mb(); return prev; } @@ -193,6 +205,7 @@ ____cmpxchg(_u32, volatile int *m, int old, int new) { unsigned long prev, cmp; + smp_mb(); __asm__ __volatile__( "1: ldl_l %0,%5\n" " cmpeq %0,%3,%1\n" @@ -200,13 +213,13 @@ ____cmpxchg(_u32, volatile int *m, int old, int new) " mov %4,%1\n" " stl_c %1,%2\n" " beq %1,3f\n" - __ASM__MB "2:\n" ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r"(prev), "=&r"(cmp), "=m"(*m) : "r"((long) old), "r"(new), "m"(*m) : "memory"); + smp_mb(); return prev; } @@ -216,6 +229,7 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) { unsigned long prev, cmp; + smp_mb(); __asm__ __volatile__( "1: ldq_l %0,%5\n" " cmpeq %0,%3,%1\n" @@ -223,13 +237,13 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) " mov %4,%1\n" " stq_c %1,%2\n" " beq %1,3f\n" - __ASM__MB "2:\n" ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r"(prev), "=&r"(cmp), "=m"(*m) : "r"((long) old), "r"(new), "m"(*m) : "memory"); + smp_mb(); return prev; } diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h index ea022d47896c..21ec82466d62 100644 --- a/arch/arc/include/asm/bug.h +++ b/arch/arc/include/asm/bug.h @@ -23,7 +23,8 @@ void die(const char *str, struct pt_regs *regs, unsigned long address); #define BUG() do { \ pr_warn("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \ - dump_stack(); \ + barrier_before_unreachable(); \ + __builtin_trap(); \ } while (0) #define HAVE_ARCH_BUG diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 9d27331fe69a..ec12fe1c2f07 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -373,7 +373,7 @@ static void arc_chk_core_config(void) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; int saved = 0, present = 0; - char *opt_nm = NULL;; + char *opt_nm = NULL; if (!cpu->extn.timer0) panic("Timer0 is not present!\n"); diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 333daab7def0..183391d4d33a 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -366,7 +366,7 @@ static void init_unwind_hdr(struct unwind_table *table, return; ret_err: - panic("Attention !!! Dwarf FDE parsing errors\n");; + panic("Attention !!! Dwarf FDE parsing errors\n"); } #ifdef CONFIG_MODULES diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index 629f8e9981f1..cf2701cb0de8 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -83,7 +83,7 @@ static void dummy_clock_access(struct timespec64 *ts) } static clock_access_fn __read_persistent_clock = dummy_clock_access; -static clock_access_fn __read_boot_clock = dummy_clock_access;; +static clock_access_fn __read_boot_clock = dummy_clock_access; void read_persistent_clock64(struct timespec64 *ts) { diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 57058ac46f49..7e5d7a083707 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -23,7 +23,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_platform.h> -#include <linux/perf/arm_pmu.h> #include <linux/regulator/machine.h> #include <asm/outercache.h> @@ -112,37 +111,6 @@ static void ux500_restart(enum reboot_mode mode, const char *cmd) prcmu_system_reset(0); } -/* - * The PMU IRQ lines of two cores are wired together into a single interrupt. - * Bounce the interrupt to the other core if it's not ours. - */ -static irqreturn_t db8500_pmu_handler(int irq, void *dev, irq_handler_t handler) -{ - irqreturn_t ret = handler(irq, dev); - int other = !smp_processor_id(); - - if (ret == IRQ_NONE && cpu_online(other)) - irq_set_affinity(irq, cpumask_of(other)); - - /* - * We should be able to get away with the amount of IRQ_NONEs we give, - * while still having the spurious IRQ detection code kick in if the - * interrupt really starts hitting spuriously. - */ - return ret; -} - -static struct arm_pmu_platdata db8500_pmu_platdata = { - .handle_irq = db8500_pmu_handler, - .irq_flags = IRQF_NOBALANCING | IRQF_NO_THREAD, -}; - -static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = { - /* Requires call-back bindings. */ - OF_DEV_AUXDATA("arm,cortex-a9-pmu", 0, "arm-pmu", &db8500_pmu_platdata), - {}, -}; - static struct of_dev_auxdata u8540_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu", NULL), {}, @@ -165,9 +133,6 @@ static void __init u8500_init_machine(void) if (of_machine_is_compatible("st-ericsson,u8540")) of_platform_populate(NULL, u8500_local_bus_nodes, u8540_auxdata_lookup, NULL); - else - of_platform_populate(NULL, u8500_local_bus_nodes, - u8500_auxdata_lookup, NULL); } static const char * stericsson_dt_platform_compat[] = { diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index be7bd19c87ec..350c76a1d15b 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -20,7 +20,7 @@ #define MPIDR_UP_BITMASK (0x1 << 30) #define MPIDR_MT_BITMASK (0x1 << 24) -#define MPIDR_HWID_BITMASK 0xff00ffffff +#define MPIDR_HWID_BITMASK UL(0xff00ffffff) #define MPIDR_LEVEL_BITS_SHIFT 3 #define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT) diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 1dca41bea16a..e73f68569624 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -22,7 +22,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep) { - return *ptep; + return READ_ONCE(*ptep); } diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 9679067a1574..7faed6e48b46 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -185,42 +185,42 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) return pmd; } -static inline void kvm_set_s2pte_readonly(pte_t *pte) +static inline void kvm_set_s2pte_readonly(pte_t *ptep) { pteval_t old_pteval, pteval; - pteval = READ_ONCE(pte_val(*pte)); + pteval = READ_ONCE(pte_val(*ptep)); do { old_pteval = pteval; pteval &= ~PTE_S2_RDWR; pteval |= PTE_S2_RDONLY; - pteval = cmpxchg_relaxed(&pte_val(*pte), old_pteval, pteval); + pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); } -static inline bool kvm_s2pte_readonly(pte_t *pte) +static inline bool kvm_s2pte_readonly(pte_t *ptep) { - return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY; + return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY; } -static inline bool kvm_s2pte_exec(pte_t *pte) +static inline bool kvm_s2pte_exec(pte_t *ptep) { - return !(pte_val(*pte) & PTE_S2_XN); + return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN); } -static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) +static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp) { - kvm_set_s2pte_readonly((pte_t *)pmd); + kvm_set_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_readonly(pmd_t *pmd) +static inline bool kvm_s2pmd_readonly(pmd_t *pmdp) { - return kvm_s2pte_readonly((pte_t *)pmd); + return kvm_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_exec(pmd_t *pmd) +static inline bool kvm_s2pmd_exec(pmd_t *pmdp) { - return !(pmd_val(*pmd) & PMD_S2_XN); + return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN); } static inline bool kvm_page_empty(void *ptr) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 8d3331985d2e..39ec0b8a689e 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -141,13 +141,13 @@ static inline void cpu_install_idmap(void) * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -static inline void cpu_replace_ttbr1(pgd_t *pgd) +static inline void cpu_replace_ttbr1(pgd_t *pgdp) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; ttbr_replace_func *replace_phys; - phys_addr_t pgd_phys = virt_to_phys(pgd); + phys_addr_t pgd_phys = virt_to_phys(pgdp); replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index e9d9f1b006ef..2e05bcd944c8 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -36,23 +36,23 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) return (pmd_t *)__get_free_page(PGALLOC_GFP); } -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp) { - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); + BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1)); + free_page((unsigned long)pmdp); } -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { - set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot)); + set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot)); } -static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp) { - __pud_populate(pud, __pa(pmd), PMD_TYPE_TABLE); + __pud_populate(pudp, __pa(pmdp), PMD_TYPE_TABLE); } #else -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { BUILD_BUG(); } @@ -65,30 +65,30 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) return (pud_t *)__get_free_page(PGALLOC_GFP); } -static inline void pud_free(struct mm_struct *mm, pud_t *pud) +static inline void pud_free(struct mm_struct *mm, pud_t *pudp) { - BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); + BUG_ON((unsigned long)pudp & (PAGE_SIZE-1)); + free_page((unsigned long)pudp); } -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { - set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot)); + set_pgd(pgdp, __pgd(__phys_to_pgd_val(pudp) | prot)); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, pud_t *pudp) { - __pgd_populate(pgd, __pa(pud), PUD_TYPE_TABLE); + __pgd_populate(pgdp, __pa(pudp), PUD_TYPE_TABLE); } #else -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { BUILD_BUG(); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ extern pgd_t *pgd_alloc(struct mm_struct *mm); -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); +extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr) @@ -114,10 +114,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) /* * Free a PTE table. */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep) { - if (pte) - free_page((unsigned long)pte); + if (ptep) + free_page((unsigned long)ptep); } static inline void pte_free(struct mm_struct *mm, pgtable_t pte) @@ -126,10 +126,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte) __free_page(pte); } -static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, +static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { - set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot)); + set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot)); } /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 094374c82db0..7e2c27e63cd8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -218,7 +218,7 @@ static inline pmd_t pmd_mkcont(pmd_t pmd) static inline void set_pte(pte_t *ptep, pte_t pte) { - *ptep = pte; + WRITE_ONCE(*ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance @@ -250,6 +250,8 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { + pte_t old_pte; + if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte, addr); @@ -258,14 +260,15 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) && + old_pte = READ_ONCE(*ptep); + if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) && (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) { VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); - VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + __func__, pte_val(old_pte), pte_val(pte)); + VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); + __func__, pte_val(old_pte), pte_val(pte)); } set_pte(ptep, pte); @@ -431,7 +434,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); dsb(ishst); isb(); } @@ -482,7 +485,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) static inline void set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); dsb(ishst); isb(); } @@ -500,7 +503,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) /* Find an entry in the second-level page table. */ #define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) -#define pmd_offset_phys(dir, addr) (pud_page_paddr(*(dir)) + pmd_index(addr) * sizeof(pmd_t)) +#define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_offset(dir, addr) ((pmd_t *)__va(pmd_offset_phys((dir), (addr)))) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) @@ -535,7 +538,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pgd; + WRITE_ONCE(*pgdp, pgd); dsb(ishst); } @@ -552,7 +555,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd) /* Find an entry in the frst-level page table. */ #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -#define pud_offset_phys(dir, addr) (pgd_page_paddr(*(dir)) + pud_index(addr) * sizeof(pud_t)) +#define pud_offset_phys(dir, addr) (pgd_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) #define pud_offset(dir, addr) ((pud_t *)__va(pud_offset_phys((dir), (addr)))) #define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 472ef944e932..902f9edacbea 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -28,7 +28,7 @@ struct stackframe { unsigned long fp; unsigned long pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - unsigned int graph; + int graph; #endif }; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 543e11f0f657..e66b0fca99c2 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -72,15 +72,15 @@ static inline void set_fs(mm_segment_t fs) * This is equivalent to the following test: * (u65)addr + (u65)size <= (u65)current->addr_limit + 1 */ -static inline unsigned long __range_ok(unsigned long addr, unsigned long size) +static inline unsigned long __range_ok(const void __user *addr, unsigned long size) { - unsigned long limit = current_thread_info()->addr_limit; + unsigned long ret, limit = current_thread_info()->addr_limit; __chk_user_ptr(addr); asm volatile( // A + B <= C + 1 for all A,B,C, in four easy steps: // 1: X = A + B; X' = X % 2^64 - " adds %0, %0, %2\n" + " adds %0, %3, %2\n" // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4 " csel %1, xzr, %1, hi\n" // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X' @@ -92,9 +92,9 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size) // testing X' - C == 0, subject to the previous adjustments. " sbcs xzr, %0, %1\n" " cset %0, ls\n" - : "+r" (addr), "+r" (limit) : "Ir" (size) : "cc"); + : "=&r" (ret), "+r" (limit) : "Ir" (size), "0" (addr) : "cc"); - return addr; + return ret; } /* @@ -104,7 +104,7 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size) */ #define untagged_addr(addr) sign_extend64(addr, 55) -#define access_ok(type, addr, size) __range_ok((unsigned long)(addr), size) +#define access_ok(type, addr, size) __range_ok(addr, size) #define user_addr_max get_fs #define _ASM_EXTABLE(from, to) \ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index c33b5e4010ab..68450e954d47 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -370,6 +370,7 @@ static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr) static int swp_handler(struct pt_regs *regs, u32 instr) { u32 destreg, data, type, address = 0; + const void __user *user_ptr; int rn, rt2, res = 0; perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc); @@ -401,7 +402,8 @@ static int swp_handler(struct pt_regs *regs, u32 instr) aarch32_insn_extract_reg_num(instr, A32_RT2_OFFSET), data); /* Check access in reasonable access range for both SWP and SWPB */ - if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) { + user_ptr = (const void __user *)(unsigned long)(address & ~3); + if (!access_ok(VERIFY_WRITE, user_ptr, 4)) { pr_debug("SWP{B} emulation: access to 0x%08x not allowed!\n", address); goto fault; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 07823595b7f0..52f15cd896e1 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -408,6 +408,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + .enable = qcom_enable_link_stack_sanitization, + }, + { + .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + }, + { + .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), .enable = enable_smccc_arch_workaround_1, }, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 29b1f873e337..2985a067fc13 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -199,9 +199,11 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { }; static const struct arm64_ftr_bits ftr_ctr[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1), /* DIC */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1), /* IDC */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0), /* ERG */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ /* * Linux can handle differing I-cache policies. Userspace JITs will diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index f85ac58d08a3..a8bf1c892b90 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -90,7 +90,7 @@ static int __init set_permissions(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { efi_memory_desc_t *md = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); if (md->attribute & EFI_MEMORY_RO) pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f20cf7e99249..1ec5f28c39fc 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -202,10 +202,10 @@ static int create_safe_exec_page(void *src_start, size_t length, gfp_t mask) { int rc = 0; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; unsigned long dst = (unsigned long)allocator(mask); if (!dst) { @@ -216,38 +216,38 @@ static int create_safe_exec_page(void *src_start, size_t length, memcpy((void *)dst, src_start, length); flush_icache_range(dst, dst + length); - pgd = pgd_offset_raw(allocator(mask), dst_addr); - if (pgd_none(*pgd)) { - pud = allocator(mask); - if (!pud) { + pgdp = pgd_offset_raw(allocator(mask), dst_addr); + if (pgd_none(READ_ONCE(*pgdp))) { + pudp = allocator(mask); + if (!pudp) { rc = -ENOMEM; goto out; } - pgd_populate(&init_mm, pgd, pud); + pgd_populate(&init_mm, pgdp, pudp); } - pud = pud_offset(pgd, dst_addr); - if (pud_none(*pud)) { - pmd = allocator(mask); - if (!pmd) { + pudp = pud_offset(pgdp, dst_addr); + if (pud_none(READ_ONCE(*pudp))) { + pmdp = allocator(mask); + if (!pmdp) { rc = -ENOMEM; goto out; } - pud_populate(&init_mm, pud, pmd); + pud_populate(&init_mm, pudp, pmdp); } - pmd = pmd_offset(pud, dst_addr); - if (pmd_none(*pmd)) { - pte = allocator(mask); - if (!pte) { + pmdp = pmd_offset(pudp, dst_addr); + if (pmd_none(READ_ONCE(*pmdp))) { + ptep = allocator(mask); + if (!ptep) { rc = -ENOMEM; goto out; } - pmd_populate_kernel(&init_mm, pmd, pte); + pmd_populate_kernel(&init_mm, pmdp, ptep); } - pte = pte_offset_kernel(pmd, dst_addr); - set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); + ptep = pte_offset_kernel(pmdp, dst_addr); + set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); /* * Load our new page tables. A strict BBM approach requires that we @@ -263,7 +263,7 @@ static int create_safe_exec_page(void *src_start, size_t length, */ cpu_set_reserved_ttbr0(); local_flush_tlb_all(); - write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1); + write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1); isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -320,9 +320,9 @@ int swsusp_arch_suspend(void) return ret; } -static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) +static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) { - pte_t pte = *src_pte; + pte_t pte = READ_ONCE(*src_ptep); if (pte_valid(pte)) { /* @@ -330,7 +330,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) * read only (code, rodata). Clear the RDONLY bit from * the temporary mappings we use during restore. */ - set_pte(dst_pte, pte_mkwrite(pte)); + set_pte(dst_ptep, pte_mkwrite(pte)); } else if (debug_pagealloc_enabled() && !pte_none(pte)) { /* * debug_pagealloc will removed the PTE_VALID bit if @@ -343,112 +343,116 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) */ BUG_ON(!pfn_valid(pte_pfn(pte))); - set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte))); + set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte))); } } -static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start, +static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start, unsigned long end) { - pte_t *src_pte; - pte_t *dst_pte; + pte_t *src_ptep; + pte_t *dst_ptep; unsigned long addr = start; - dst_pte = (pte_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pte) + dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC); + if (!dst_ptep) return -ENOMEM; - pmd_populate_kernel(&init_mm, dst_pmd, dst_pte); - dst_pte = pte_offset_kernel(dst_pmd, start); + pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep); + dst_ptep = pte_offset_kernel(dst_pmdp, start); - src_pte = pte_offset_kernel(src_pmd, start); + src_ptep = pte_offset_kernel(src_pmdp, start); do { - _copy_pte(dst_pte, src_pte, addr); - } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + _copy_pte(dst_ptep, src_ptep, addr); + } while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end); return 0; } -static int copy_pmd(pud_t *dst_pud, pud_t *src_pud, unsigned long start, +static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start, unsigned long end) { - pmd_t *src_pmd; - pmd_t *dst_pmd; + pmd_t *src_pmdp; + pmd_t *dst_pmdp; unsigned long next; unsigned long addr = start; - if (pud_none(*dst_pud)) { - dst_pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pmd) + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pmdp) return -ENOMEM; - pud_populate(&init_mm, dst_pud, dst_pmd); + pud_populate(&init_mm, dst_pudp, dst_pmdp); } - dst_pmd = pmd_offset(dst_pud, start); + dst_pmdp = pmd_offset(dst_pudp, start); - src_pmd = pmd_offset(src_pud, start); + src_pmdp = pmd_offset(src_pudp, start); do { + pmd_t pmd = READ_ONCE(*src_pmdp); + next = pmd_addr_end(addr, end); - if (pmd_none(*src_pmd)) + if (pmd_none(pmd)) continue; - if (pmd_table(*src_pmd)) { - if (copy_pte(dst_pmd, src_pmd, addr, next)) + if (pmd_table(pmd)) { + if (copy_pte(dst_pmdp, src_pmdp, addr, next)) return -ENOMEM; } else { - set_pmd(dst_pmd, - __pmd(pmd_val(*src_pmd) & ~PMD_SECT_RDONLY)); + set_pmd(dst_pmdp, + __pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY)); } - } while (dst_pmd++, src_pmd++, addr = next, addr != end); + } while (dst_pmdp++, src_pmdp++, addr = next, addr != end); return 0; } -static int copy_pud(pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long start, +static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, unsigned long end) { - pud_t *dst_pud; - pud_t *src_pud; + pud_t *dst_pudp; + pud_t *src_pudp; unsigned long next; unsigned long addr = start; - if (pgd_none(*dst_pgd)) { - dst_pud = (pud_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pud) + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pudp) return -ENOMEM; - pgd_populate(&init_mm, dst_pgd, dst_pud); + pgd_populate(&init_mm, dst_pgdp, dst_pudp); } - dst_pud = pud_offset(dst_pgd, start); + dst_pudp = pud_offset(dst_pgdp, start); - src_pud = pud_offset(src_pgd, start); + src_pudp = pud_offset(src_pgdp, start); do { + pud_t pud = READ_ONCE(*src_pudp); + next = pud_addr_end(addr, end); - if (pud_none(*src_pud)) + if (pud_none(pud)) continue; - if (pud_table(*(src_pud))) { - if (copy_pmd(dst_pud, src_pud, addr, next)) + if (pud_table(pud)) { + if (copy_pmd(dst_pudp, src_pudp, addr, next)) return -ENOMEM; } else { - set_pud(dst_pud, - __pud(pud_val(*src_pud) & ~PMD_SECT_RDONLY)); + set_pud(dst_pudp, + __pud(pud_val(pud) & ~PMD_SECT_RDONLY)); } - } while (dst_pud++, src_pud++, addr = next, addr != end); + } while (dst_pudp++, src_pudp++, addr = next, addr != end); return 0; } -static int copy_page_tables(pgd_t *dst_pgd, unsigned long start, +static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, unsigned long end) { unsigned long next; unsigned long addr = start; - pgd_t *src_pgd = pgd_offset_k(start); + pgd_t *src_pgdp = pgd_offset_k(start); - dst_pgd = pgd_offset_raw(dst_pgd, start); + dst_pgdp = pgd_offset_raw(dst_pgdp, start); do { next = pgd_addr_end(addr, end); - if (pgd_none(*src_pgd)) + if (pgd_none(READ_ONCE(*src_pgdp))) continue; - if (copy_pud(dst_pgd, src_pgd, addr, next)) + if (copy_pud(dst_pgdp, src_pgdp, addr, next)) return -ENOMEM; - } while (dst_pgd++, src_pgd++, addr = next, addr != end); + } while (dst_pgdp++, src_pgdp++, addr = next, addr != end); return 0; } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 75b220ba73a3..85a251b6dfa8 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -908,9 +908,9 @@ static void __armv8pmu_probe_pmu(void *info) int pmuver; dfr0 = read_sysreg(id_aa64dfr0_el1); - pmuver = cpuid_feature_extract_signed_field(dfr0, + pmuver = cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_PMUVER_SHIFT); - if (pmuver < 1) + if (pmuver == 0xf || pmuver == 0) return; probe->present = true; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index ad8aeb098b31..c0da6efe5465 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -220,8 +220,15 @@ void __show_regs(struct pt_regs *regs) show_regs_print_info(KERN_DEFAULT); print_pstate(regs); - printk("pc : %pS\n", (void *)regs->pc); - printk("lr : %pS\n", (void *)lr); + + if (!user_mode(regs)) { + printk("pc : %pS\n", (void *)regs->pc); + printk("lr : %pS\n", (void *)lr); + } else { + printk("pc : %016llx\n", regs->pc); + printk("lr : %016llx\n", lr); + } + printk("sp : %016llx\n", sp); i = top_reg; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6618036ae6d4..9ae31f7e2243 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1419,7 +1419,7 @@ static int compat_ptrace_hbp_get(unsigned int note_type, u64 addr = 0; u32 ctrl = 0; - int err, idx = compat_ptrace_hbp_num_to_idx(num);; + int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { err = ptrace_hbp_get_addr(note_type, tsk, idx, &addr); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 76809ccd309c..d5718a060672 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -59,6 +59,11 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { + if (WARN_ON_ONCE(frame->graph == -1)) + return -EINVAL; + if (frame->graph < -1) + frame->graph += FTRACE_NOTRACE_DEPTH; + /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 8b8bbd3eaa52..a382b2a1b84e 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -57,7 +57,7 @@ do_compat_cache_op(unsigned long start, unsigned long end, int flags) if (end < start || flags) return -EINVAL; - if (!access_ok(VERIFY_READ, start, end - start)) + if (!access_ok(VERIFY_READ, (const void __user *)start, end - start)) return -EFAULT; return __do_compat_cache_op(start, end); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index a4391280fba9..f258636273c9 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -52,7 +52,7 @@ unsigned long profile_pc(struct pt_regs *regs) frame.fp = regs->regs[29]; frame.pc = regs->pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = -1; /* no task info */ + frame.graph = current->curr_ret_stack; #endif do { int ret = unwind_frame(NULL, &frame); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index bbb0fde2780e..eb2d15147e8d 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -57,7 +57,7 @@ static const char *handler[]= { "Error" }; -int show_unhandled_signals = 1; +int show_unhandled_signals = 0; static void dump_backtrace_entry(unsigned long where) { @@ -526,14 +526,6 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs) } #endif - if (show_unhandled_signals_ratelimited()) { - pr_info("%s[%d]: syscall %d\n", current->comm, - task_pid_nr(current), regs->syscallno); - dump_instr("", regs); - if (user_mode(regs)) - __show_regs(regs); - } - return sys_ni_syscall(); } diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 116252a8d3a5..870f4b1587f9 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -407,8 +407,10 @@ again: u32 midr = read_cpuid_id(); /* Apply BTAC predictors mitigation to all Falkor chips */ - if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1) + if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) || + ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) { __qcom_hyp_sanitize_btac_predictors(); + } } fp_enabled = __fpsimd_enabled(); diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 7b60d62ac593..65dfc8571bf8 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,48 +286,52 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) { - pte_t *pte = pte_offset_kernel(pmd, 0UL); + pte_t *ptep = pte_offset_kernel(pmdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { addr = start + i * PAGE_SIZE; - note_page(st, addr, 4, pte_val(*pte)); + note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); } } -static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) { - pmd_t *pmd = pmd_offset(pud, 0UL); + pmd_t *pmdp = pmd_offset(pudp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + pmd_t pmd = READ_ONCE(*pmdp); + addr = start + i * PMD_SIZE; - if (pmd_none(*pmd) || pmd_sect(*pmd)) { - note_page(st, addr, 3, pmd_val(*pmd)); + if (pmd_none(pmd) || pmd_sect(pmd)) { + note_page(st, addr, 3, pmd_val(pmd)); } else { - BUG_ON(pmd_bad(*pmd)); - walk_pte(st, pmd, addr); + BUG_ON(pmd_bad(pmd)); + walk_pte(st, pmdp, addr); } } } -static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) { - pud_t *pud = pud_offset(pgd, 0UL); + pud_t *pudp = pud_offset(pgdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + pud_t pud = READ_ONCE(*pudp); + addr = start + i * PUD_SIZE; - if (pud_none(*pud) || pud_sect(*pud)) { - note_page(st, addr, 2, pud_val(*pud)); + if (pud_none(pud) || pud_sect(pud)) { + note_page(st, addr, 2, pud_val(pud)); } else { - BUG_ON(pud_bad(*pud)); - walk_pmd(st, pud, addr); + BUG_ON(pud_bad(pud)); + walk_pmd(st, pudp, addr); } } } @@ -335,17 +339,19 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgd = pgd_offset(mm, 0UL); + pgd_t *pgdp = pgd_offset(mm, 0UL); unsigned i; unsigned long addr; - for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { + for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + pgd_t pgd = READ_ONCE(*pgdp); + addr = start + i * PGDIR_SIZE; - if (pgd_none(*pgd)) { - note_page(st, addr, 1, pgd_val(*pgd)); + if (pgd_none(pgd)) { + note_page(st, addr, 1, pgd_val(pgd)); } else { - BUG_ON(pgd_bad(*pgd)); - walk_pud(st, pgd, addr); + BUG_ON(pgd_bad(pgd)); + walk_pud(st, pgdp, addr); } } } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index f76bb2c3c943..bff11553eb05 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -130,7 +130,8 @@ static void mem_abort_decode(unsigned int esr) void show_pte(unsigned long addr) { struct mm_struct *mm; - pgd_t *pgd; + pgd_t *pgdp; + pgd_t pgd; if (addr < TASK_SIZE) { /* TTBR0 */ @@ -149,33 +150,37 @@ void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n", + pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, VA_BITS, mm->pgd); - pgd = pgd_offset(mm, addr); - pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd)); + pgdp = pgd_offset(mm, addr); + pgd = READ_ONCE(*pgdp); + pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; - if (pgd_none(*pgd) || pgd_bad(*pgd)) + if (pgd_none(pgd) || pgd_bad(pgd)) break; - pud = pud_offset(pgd, addr); - pr_cont(", *pud=%016llx", pud_val(*pud)); - if (pud_none(*pud) || pud_bad(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + pr_cont(", pud=%016llx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud)) break; - pmd = pmd_offset(pud, addr); - pr_cont(", *pmd=%016llx", pmd_val(*pmd)); - if (pmd_none(*pmd) || pmd_bad(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + pr_cont(", pmd=%016llx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd)) break; - pte = pte_offset_map(pmd, addr); - pr_cont(", *pte=%016llx", pte_val(*pte)); - pte_unmap(pte); + ptep = pte_offset_map(pmdp, addr); + pte = READ_ONCE(*ptep); + pr_cont(", pte=%016llx", pte_val(pte)); + pte_unmap(ptep); } while(0); pr_cont("\n"); @@ -196,8 +201,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma, pte_t entry, int dirty) { pteval_t old_pteval, pteval; + pte_t pte = READ_ONCE(*ptep); - if (pte_same(*ptep, entry)) + if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ @@ -210,7 +216,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; - pteval = READ_ONCE(pte_val(*ptep)); + pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 6cb0fa92a651..ecc6818191df 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -54,14 +54,14 @@ static inline pgprot_t pte_pgprot(pte_t pte) static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { - pgd_t *pgd = pgd_offset(mm, addr); - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp = pgd_offset(mm, addr); + pud_t *pudp; + pmd_t *pmdp; *pgsize = PAGE_SIZE; - pud = pud_offset(pgd, addr); - pmd = pmd_offset(pud, addr); - if ((pte_t *)pmd == ptep) { + pudp = pud_offset(pgdp, addr); + pmdp = pmd_offset(pudp, addr); + if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } @@ -181,11 +181,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, clear_flush(mm, addr, ptep, pgsize, ncontig); - for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) { - pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep, - pte_val(pfn_pte(pfn, hugeprot))); + for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); - } } void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, @@ -203,20 +200,20 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz); - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (!pud) + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep = NULL; + + pgdp = pgd_offset(mm, addr); + pudp = pud_alloc(mm, pgdp, addr); + if (!pudp) return NULL; if (sz == PUD_SIZE) { - pte = (pte_t *)pud; + ptep = (pte_t *)pudp; } else if (sz == (PAGE_SIZE * CONT_PTES)) { - pmd_t *pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); /* @@ -226,60 +223,55 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, * will be no pte_unmap() to correspond with this * pte_alloc_map(). */ - pte = pte_alloc_map(mm, pmd, addr); + ptep = pte_alloc_map(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && - pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); + pud_none(READ_ONCE(*pudp))) + ptep = huge_pmd_share(mm, addr, pudp); else - pte = (pte_t *)pmd_alloc(mm, pud, addr); + ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (PMD_SIZE * CONT_PMDS)) { - pmd_t *pmd; - - pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); - return (pte_t *)pmd; + return (pte_t *)pmdp; } - pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr, - sz, pte, pte_val(*pte)); - return pte; + return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; - pgd = pgd_offset(mm, addr); - pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd); - if (!pgd_present(*pgd)) + pgdp = pgd_offset(mm, addr); + if (!pgd_present(READ_ONCE(*pgdp))) return NULL; - pud = pud_offset(pgd, addr); - if (sz != PUD_SIZE && pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ - if (pud_huge(*pud) || !pud_present(*pud)) - return (pte_t *)pud; + if (pud_huge(pud) || !pud_present(pud)) + return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; - pmd = pmd_offset(pud, addr); + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && - pmd_none(*pmd)) + pmd_none(pmd)) return NULL; - if (pmd_huge(*pmd) || !pmd_present(*pmd)) - return (pte_t *)pmd; + if (pmd_huge(pmd) || !pmd_present(pmd)) + return (pte_t *)pmdp; - if (sz == CONT_PTE_SIZE) { - pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK)); - return pte; - } + if (sz == CONT_PTE_SIZE) + return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK)); return NULL; } @@ -367,7 +359,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, size_t pgsize; pte_t pte; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_set_wrprotect(mm, addr, ptep); return; } @@ -391,7 +383,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, size_t pgsize; int ncontig; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_clear_flush(vma, addr, ptep); return; } diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6e02e6fb4c7b..dabfc1ecda3d 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -44,92 +44,92 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) return __pa(p); } -static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node, +static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { - if (pmd_none(*pmd)) { + if (pmd_none(READ_ONCE(*pmdp))) { phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte) : kasan_alloc_zeroed_page(node); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); } - return early ? pte_offset_kimg(pmd, addr) - : pte_offset_kernel(pmd, addr); + return early ? pte_offset_kimg(pmdp, addr) + : pte_offset_kernel(pmdp, addr); } -static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node, +static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { - if (pud_none(*pud)) { + if (pud_none(READ_ONCE(*pudp))) { phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd) : kasan_alloc_zeroed_page(node); - __pud_populate(pud, pmd_phys, PMD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE); } - return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr); + return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr); } -static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node, +static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) { - if (pgd_none(*pgd)) { + if (pgd_none(READ_ONCE(*pgdp))) { phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud) : kasan_alloc_zeroed_page(node); - __pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE); } - return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr); + return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr); } -static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr, +static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pte_t *pte = kasan_pte_offset(pmd, addr, node, early); + pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early); do { phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page) : kasan_alloc_zeroed_page(node); next = addr + PAGE_SIZE; - set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); - } while (pte++, addr = next, addr != end && pte_none(*pte)); + set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); + } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep))); } -static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr, +static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early); + pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early); do { next = pmd_addr_end(addr, end); - kasan_pte_populate(pmd, addr, next, node, early); - } while (pmd++, addr = next, addr != end && pmd_none(*pmd)); + kasan_pte_populate(pmdp, addr, next, node, early); + } while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp))); } -static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pud_t *pud = kasan_pud_offset(pgd, addr, node, early); + pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early); do { next = pud_addr_end(addr, end); - kasan_pmd_populate(pud, addr, next, node, early); - } while (pud++, addr = next, addr != end && pud_none(*pud)); + kasan_pmd_populate(pudp, addr, next, node, early); + } while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pgd_t *pgd; + pgd_t *pgdp; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - kasan_pud_populate(pgd, addr, next, node, early); - } while (pgd++, addr = next, addr != end); + kasan_pud_populate(pgdp, addr, next, node, early); + } while (pgdp++, addr = next, addr != end); } /* The early shadow maps everything to a single page of zeroes */ @@ -155,14 +155,14 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, */ void __init kasan_copy_shadow(pgd_t *pgdir) { - pgd_t *pgd, *pgd_new, *pgd_end; + pgd_t *pgdp, *pgdp_new, *pgdp_end; - pgd = pgd_offset_k(KASAN_SHADOW_START); - pgd_end = pgd_offset_k(KASAN_SHADOW_END); - pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); + pgdp = pgd_offset_k(KASAN_SHADOW_START); + pgdp_end = pgd_offset_k(KASAN_SHADOW_END); + pgdp_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); do { - set_pgd(pgd_new, *pgd); - } while (pgd++, pgd_new++, pgd != pgd_end); + set_pgd(pgdp_new, READ_ONCE(*pgdp)); + } while (pgdp++, pgdp_new++, pgdp != pgdp_end); } static void __init clear_pgds(unsigned long start, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 4694cda823c9..84a019f55022 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -125,45 +125,48 @@ static bool pgattr_change_is_safe(u64 old, u64 new) return ((old ^ new) & ~mask) == 0; } -static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, +static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot) { - pte_t *pte; + pte_t *ptep; - pte = pte_set_fixmap_offset(pmd, addr); + ptep = pte_set_fixmap_offset(pmdp, addr); do { - pte_t old_pte = *pte; + pte_t old_pte = READ_ONCE(*ptep); - set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot)); + set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot)); /* * After the PTE entry has been populated once, we * only allow updates to the permission attributes. */ - BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte))); + BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), + READ_ONCE(pte_val(*ptep)))); phys += PAGE_SIZE; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (ptep++, addr += PAGE_SIZE, addr != end); pte_clear_fixmap(); } -static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, +static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pmd_t pmd = READ_ONCE(*pmdp); - BUG_ON(pmd_sect(*pmd)); - if (pmd_none(*pmd)) { + BUG_ON(pmd_sect(pmd)); + if (pmd_none(pmd)) { phys_addr_t pte_phys; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); + pmd = READ_ONCE(*pmdp); } - BUG_ON(pmd_bad(*pmd)); + BUG_ON(pmd_bad(pmd)); do { pgprot_t __prot = prot; @@ -175,67 +178,69 @@ static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pte(pmd, addr, next, phys, __prot); + init_pte(pmdp, addr, next, phys, __prot); phys += next - addr; } while (addr = next, addr != end); } -static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end, +static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; - pmd_t *pmd; + pmd_t *pmdp; - pmd = pmd_set_fixmap_offset(pud, addr); + pmdp = pmd_set_fixmap_offset(pudp, addr); do { - pmd_t old_pmd = *pmd; + pmd_t old_pmd = READ_ONCE(*pmdp); next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && (flags & NO_BLOCK_MAPPINGS) == 0) { - pmd_set_huge(pmd, phys, prot); + pmd_set_huge(pmdp, phys, prot); /* * After the PMD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), - pmd_val(*pmd))); + READ_ONCE(pmd_val(*pmdp)))); } else { - alloc_init_cont_pte(pmd, addr, next, phys, prot, + alloc_init_cont_pte(pmdp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pmd_val(old_pmd) != 0 && - pmd_val(old_pmd) != pmd_val(*pmd)); + pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; - } while (pmd++, addr = next, addr != end); + } while (pmdp++, addr = next, addr != end); pmd_clear_fixmap(); } -static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, +static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pud_t pud = READ_ONCE(*pudp); /* * Check for initial section mappings in the pgd/pud. */ - BUG_ON(pud_sect(*pud)); - if (pud_none(*pud)) { + BUG_ON(pud_sect(pud)); + if (pud_none(pud)) { phys_addr_t pmd_phys; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(); - __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE); + pud = READ_ONCE(*pudp); } - BUG_ON(pud_bad(*pud)); + BUG_ON(pud_bad(pud)); do { pgprot_t __prot = prot; @@ -247,7 +252,7 @@ static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags); + init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags); phys += next - addr; } while (addr = next, addr != end); @@ -265,25 +270,27 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, return true; } -static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void), - int flags) +static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(void), + int flags) { - pud_t *pud; unsigned long next; + pud_t *pudp; + pgd_t pgd = READ_ONCE(*pgdp); - if (pgd_none(*pgd)) { + if (pgd_none(pgd)) { phys_addr_t pud_phys; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(); - __pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE); + pgd = READ_ONCE(*pgdp); } - BUG_ON(pgd_bad(*pgd)); + BUG_ON(pgd_bad(pgd)); - pud = pud_set_fixmap_offset(pgd, addr); + pudp = pud_set_fixmap_offset(pgdp, addr); do { - pud_t old_pud = *pud; + pud_t old_pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); @@ -292,23 +299,23 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, */ if (use_1G_block(addr, next, phys) && (flags & NO_BLOCK_MAPPINGS) == 0) { - pud_set_huge(pud, phys, prot); + pud_set_huge(pudp, phys, prot); /* * After the PUD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), - pud_val(*pud))); + READ_ONCE(pud_val(*pudp)))); } else { - alloc_init_cont_pmd(pud, addr, next, phys, prot, + alloc_init_cont_pmd(pudp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pud_val(old_pud) != 0 && - pud_val(old_pud) != pud_val(*pud)); + pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); } phys += next - addr; - } while (pud++, addr = next, addr != end); + } while (pudp++, addr = next, addr != end); pud_clear_fixmap(); } @@ -320,7 +327,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, int flags) { unsigned long addr, length, end, next; - pgd_t *pgd = pgd_offset_raw(pgdir, virt); + pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* * If the virtual and physical address don't have the same offset @@ -336,10 +343,10 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, + alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, flags); phys += next - addr; - } while (pgd++, addr = next, addr != end); + } while (pgdp++, addr = next, addr != end); } static phys_addr_t pgd_pgtable_alloc(void) @@ -401,10 +408,10 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, flush_tlb_kernel_range(virt, virt + size); } -static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, +static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { - __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, + __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, prot, early_pgtable_alloc, flags); } @@ -418,7 +425,7 @@ void __init mark_linear_text_alias_ro(void) PAGE_KERNEL_RO); } -static void __init map_mem(pgd_t *pgd) +static void __init map_mem(pgd_t *pgdp) { phys_addr_t kernel_start = __pa_symbol(_text); phys_addr_t kernel_end = __pa_symbol(__init_begin); @@ -451,7 +458,7 @@ static void __init map_mem(pgd_t *pgd) if (memblock_is_nomap(reg)) continue; - __map_memblock(pgd, start, end, PAGE_KERNEL, flags); + __map_memblock(pgdp, start, end, PAGE_KERNEL, flags); } /* @@ -464,7 +471,7 @@ static void __init map_mem(pgd_t *pgd) * Note that contiguous mappings cannot be remapped in this way, * so we should avoid them here. */ - __map_memblock(pgd, kernel_start, kernel_end, + __map_memblock(pgdp, kernel_start, kernel_end, PAGE_KERNEL, NO_CONT_MAPPINGS); memblock_clear_nomap(kernel_start, kernel_end - kernel_start); @@ -475,7 +482,7 @@ static void __init map_mem(pgd_t *pgd) * through /sys/kernel/kexec_crash_size interface. */ if (crashk_res.end) { - __map_memblock(pgd, crashk_res.start, crashk_res.end + 1, + __map_memblock(pgdp, crashk_res.start, crashk_res.end + 1, PAGE_KERNEL, NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS); memblock_clear_nomap(crashk_res.start, @@ -499,7 +506,7 @@ void mark_rodata_ro(void) debug_checkwx(); } -static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, +static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, pgprot_t prot, struct vm_struct *vma, int flags, unsigned long vm_flags) { @@ -509,7 +516,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); - __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, + __create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot, early_pgtable_alloc, flags); if (!(vm_flags & VM_NO_GUARD)) @@ -562,7 +569,7 @@ core_initcall(map_entry_trampoline); /* * Create fine-grained mappings for the kernel. */ -static void __init map_kernel(pgd_t *pgd) +static void __init map_kernel(pgd_t *pgdp) { static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext, vmlinux_initdata, vmlinux_data; @@ -578,24 +585,24 @@ static void __init map_kernel(pgd_t *pgd) * Only rodata will be remapped with different permissions later on, * all other segments are allowed to use contiguous mappings. */ - map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0, + map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL, + map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL, &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD); - map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot, + map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot, &vmlinux_inittext, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL, + map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL, &vmlinux_initdata, 0, VM_NO_GUARD); - map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); + map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); - if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) { + if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) { /* * The fixmap falls in a separate pgd to the kernel, and doesn't * live in the carveout for the swapper_pg_dir. We can simply * re-use the existing dir for the fixmap. */ - set_pgd(pgd_offset_raw(pgd, FIXADDR_START), - *pgd_offset_k(FIXADDR_START)); + set_pgd(pgd_offset_raw(pgdp, FIXADDR_START), + READ_ONCE(*pgd_offset_k(FIXADDR_START))); } else if (CONFIG_PGTABLE_LEVELS > 3) { /* * The fixmap shares its top level pgd entry with the kernel @@ -604,14 +611,15 @@ static void __init map_kernel(pgd_t *pgd) * entry instead. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START), + pud_populate(&init_mm, + pud_set_fixmap_offset(pgdp, FIXADDR_START), lm_alias(bm_pmd)); pud_clear_fixmap(); } else { BUG(); } - kasan_copy_shadow(pgd); + kasan_copy_shadow(pgdp); } /* @@ -621,10 +629,10 @@ static void __init map_kernel(pgd_t *pgd) void __init paging_init(void) { phys_addr_t pgd_phys = early_pgtable_alloc(); - pgd_t *pgd = pgd_set_fixmap(pgd_phys); + pgd_t *pgdp = pgd_set_fixmap(pgd_phys); - map_kernel(pgd); - map_mem(pgd); + map_kernel(pgdp); + map_mem(pgdp); /* * We want to reuse the original swapper_pg_dir so we don't have to @@ -635,7 +643,7 @@ void __init paging_init(void) * To do this we need to go via a temporary pgd. */ cpu_replace_ttbr1(__va(pgd_phys)); - memcpy(swapper_pg_dir, pgd, PGD_SIZE); + memcpy(swapper_pg_dir, pgdp, PGD_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); pgd_clear_fixmap(); @@ -655,37 +663,40 @@ void __init paging_init(void) */ int kern_addr_valid(unsigned long addr) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; if ((((long)addr) >> VA_BITS) != -1UL) return 0; - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return 0; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return 0; - if (pud_sect(*pud)) - return pfn_valid(pud_pfn(*pud)); + if (pud_sect(pud)) + return pfn_valid(pud_pfn(pud)); - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return 0; - if (pmd_sect(*pmd)) - return pfn_valid(pmd_pfn(*pmd)); + if (pmd_sect(pmd)) + return pfn_valid(pmd_pfn(pmd)); - pte = pte_offset_kernel(pmd, addr); - if (pte_none(*pte)) + ptep = pte_offset_kernel(pmdp, addr); + pte = READ_ONCE(*ptep); + if (pte_none(pte)) return 0; - return pfn_valid(pte_pfn(*pte)); + return pfn_valid(pte_pfn(pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP #if !ARM64_SWAPPER_USES_SECTION_MAPS @@ -700,32 +711,32 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { unsigned long addr = start; unsigned long next; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; do { next = pmd_addr_end(addr, end); - pgd = vmemmap_pgd_populate(addr, node); - if (!pgd) + pgdp = vmemmap_pgd_populate(addr, node); + if (!pgdp) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); - if (!pud) + pudp = vmemmap_pud_populate(pgdp, addr, node); + if (!pudp) return -ENOMEM; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { + pmdp = pmd_offset(pudp, addr); + if (pmd_none(READ_ONCE(*pmdp))) { void *p = NULL; p = vmemmap_alloc_block_buf(PMD_SIZE, node); if (!p) return -ENOMEM; - pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL)); + pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); } else - vmemmap_verify((pte_t *)pmd, node, addr, next); + vmemmap_verify((pte_t *)pmdp, node, addr, next); } while (addr = next, addr != end); return 0; @@ -739,20 +750,22 @@ void vmemmap_free(unsigned long start, unsigned long end, static inline pud_t * fixmap_pud(unsigned long addr) { - pgd_t *pgd = pgd_offset_k(addr); + pgd_t *pgdp = pgd_offset_k(addr); + pgd_t pgd = READ_ONCE(*pgdp); - BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); + BUG_ON(pgd_none(pgd) || pgd_bad(pgd)); - return pud_offset_kimg(pgd, addr); + return pud_offset_kimg(pgdp, addr); } static inline pmd_t * fixmap_pmd(unsigned long addr) { - pud_t *pud = fixmap_pud(addr); + pud_t *pudp = fixmap_pud(addr); + pud_t pud = READ_ONCE(*pudp); - BUG_ON(pud_none(*pud) || pud_bad(*pud)); + BUG_ON(pud_none(pud) || pud_bad(pud)); - return pmd_offset_kimg(pud, addr); + return pmd_offset_kimg(pudp, addr); } static inline pte_t * fixmap_pte(unsigned long addr) @@ -768,30 +781,31 @@ static inline pte_t * fixmap_pte(unsigned long addr) */ void __init early_fixmap_init(void) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp, pgd; + pud_t *pudp; + pmd_t *pmdp; unsigned long addr = FIXADDR_START; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); + pgd = READ_ONCE(*pgdp); if (CONFIG_PGTABLE_LEVELS > 3 && - !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) { + !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud = pud_offset_kimg(pgd, addr); + pudp = pud_offset_kimg(pgdp, addr); } else { - if (pgd_none(*pgd)) - __pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE); - pud = fixmap_pud(addr); + if (pgd_none(pgd)) + __pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE); + pudp = fixmap_pud(addr); } - if (pud_none(*pud)) - __pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); - pmd = fixmap_pmd(addr); - __pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE); + if (pud_none(READ_ONCE(*pudp))) + __pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); + pmdp = fixmap_pmd(addr); + __pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE); /* * The boot-ioremap range spans multiple pmds, for which @@ -800,11 +814,11 @@ void __init early_fixmap_init(void) BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); - if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) - || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { + if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) + || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { WARN_ON(1); - pr_warn("pmd %p != %p, %p\n", - pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), + pr_warn("pmdp %p != %p, %p\n", + pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), fixmap_pmd(fix_to_virt(FIX_BTMAP_END))); pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n", fix_to_virt(FIX_BTMAP_BEGIN)); @@ -824,16 +838,16 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); - pte_t *pte; + pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); - pte = fixmap_pte(addr); + ptep = fixmap_pte(addr); if (pgprot_val(flags)) { - set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); + set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { - pte_clear(&init_mm, addr, pte); + pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } @@ -915,36 +929,46 @@ int __init arch_ioremap_pmd_supported(void) return 1; } -int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) +int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); + + /* ioremap_page_range doesn't honour BBM */ + if (pud_present(READ_ONCE(*pudp))) + return 0; + BUG_ON(phys & ~PUD_MASK); - set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot)); + set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot)); return 1; } -int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) +int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); + + /* ioremap_page_range doesn't honour BBM */ + if (pmd_present(READ_ONCE(*pmdp))) + return 0; + BUG_ON(phys & ~PMD_MASK); - set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot)); + set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot)); return 1; } -int pud_clear_huge(pud_t *pud) +int pud_clear_huge(pud_t *pudp) { - if (!pud_sect(*pud)) + if (!pud_sect(READ_ONCE(*pudp))) return 0; - pud_clear(pud); + pud_clear(pudp); return 1; } -int pmd_clear_huge(pmd_t *pmd) +int pmd_clear_huge(pmd_t *pmdp) { - if (!pmd_sect(*pmd)) + if (!pmd_sect(READ_ONCE(*pmdp))) return 0; - pmd_clear(pmd); + pmd_clear(pmdp); return 1; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index a682a0a2a0fa..a56359373d8b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -29,7 +29,7 @@ static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct page_change_data *cdata = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); pte = clear_pte_bit(pte, cdata->clear_mask); pte = set_pte_bit(pte, cdata->set_mask); @@ -156,30 +156,32 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) */ bool kernel_page_present(struct page *page) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return false; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return false; - if (pud_sect(*pud)) + if (pud_sect(pud)) return true; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return false; - if (pmd_sect(*pmd)) + if (pmd_sect(pmd)) return true; - pte = pte_offset_kernel(pmd, addr); - return pte_valid(*pte); + ptep = pte_offset_kernel(pmdp, addr); + return pte_valid(READ_ONCE(*ptep)); } #endif /* CONFIG_HIBERNATION */ #endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 71baed7e592a..c0af47617299 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -205,7 +205,8 @@ ENDPROC(idmap_cpu_replace_ttbr1) dc cvac, cur_\()\type\()p // Ensure any existing dirty dmb sy // lines are written back before ldr \type, [cur_\()\type\()p] // loading the entry - tbz \type, #0, next_\()\type // Skip invalid entries + tbz \type, #0, skip_\()\type // Skip invalid and + tbnz \type, #11, skip_\()\type // non-global entries .endm .macro __idmap_kpti_put_pgtable_ent_ng, type @@ -265,8 +266,9 @@ ENTRY(idmap_kpti_install_ng_mappings) add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) do_pgd: __idmap_kpti_get_pgtable_ent pgd tbnz pgd, #1, walk_puds - __idmap_kpti_put_pgtable_ent_ng pgd next_pgd: + __idmap_kpti_put_pgtable_ent_ng pgd +skip_pgd: add cur_pgdp, cur_pgdp, #8 cmp cur_pgdp, end_pgdp b.ne do_pgd @@ -294,8 +296,9 @@ walk_puds: add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) do_pud: __idmap_kpti_get_pgtable_ent pud tbnz pud, #1, walk_pmds - __idmap_kpti_put_pgtable_ent_ng pud next_pud: + __idmap_kpti_put_pgtable_ent_ng pud +skip_pud: add cur_pudp, cur_pudp, 8 cmp cur_pudp, end_pudp b.ne do_pud @@ -314,8 +317,9 @@ walk_pmds: add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) do_pmd: __idmap_kpti_get_pgtable_ent pmd tbnz pmd, #1, walk_ptes - __idmap_kpti_put_pgtable_ent_ng pmd next_pmd: + __idmap_kpti_put_pgtable_ent_ng pmd +skip_pmd: add cur_pmdp, cur_pmdp, #8 cmp cur_pmdp, end_pmdp b.ne do_pmd @@ -333,7 +337,7 @@ walk_ptes: add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) do_pte: __idmap_kpti_get_pgtable_ent pte __idmap_kpti_put_pgtable_ent_ng pte -next_pte: +skip_pte: add cur_ptep, cur_ptep, #8 cmp cur_ptep, end_ptep b.ne do_pte diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 1d4f1da7c58f..a93350451e8e 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -250,8 +250,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) off = offsetof(struct bpf_array, map.max_entries); emit_a64_mov_i64(tmp, off, ctx); emit(A64_LDR32(tmp, r2, tmp), ctx); + emit(A64_MOV(0, r3, r3), ctx); emit(A64_CMP(0, r3, tmp), ctx); - emit(A64_B_(A64_COND_GE, jmp_offset), ctx); + emit(A64_B_(A64_COND_CS, jmp_offset), ctx); /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; @@ -259,7 +260,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) */ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); emit(A64_CMP(1, tcc, tmp), ctx); - emit(A64_B_(A64_COND_GT, jmp_offset), ctx); + emit(A64_B_(A64_COND_HI, jmp_offset), ctx); emit(A64_ADD_I(1, tcc, tcc, 1), ctx); /* prog = array->ptrs[index]; diff --git a/arch/cris/include/arch-v10/arch/bug.h b/arch/cris/include/arch-v10/arch/bug.h index 905afeacfedf..06da9d49152a 100644 --- a/arch/cris/include/arch-v10/arch/bug.h +++ b/arch/cris/include/arch-v10/arch/bug.h @@ -44,18 +44,25 @@ struct bug_frame { * not be used like this with newer versions of gcc. */ #define BUG() \ +do { \ __asm__ __volatile__ ("clear.d [" __stringify(BUG_MAGIC) "]\n\t"\ "movu.w " __stringify(__LINE__) ",$r0\n\t"\ "jump 0f\n\t" \ ".section .rodata\n" \ "0:\t.string \"" __FILE__ "\"\n\t" \ - ".previous") + ".previous"); \ + unreachable(); \ +} while (0) #endif #else /* This just causes an oops. */ -#define BUG() (*(int *)0 = 0) +#define BUG() \ +do { \ + barrier_before_unreachable(); \ + __builtin_trap(); \ +} while (0) #endif diff --git a/arch/ia64/include/asm/bug.h b/arch/ia64/include/asm/bug.h index bd3eeb8d1cfa..66b37a532765 100644 --- a/arch/ia64/include/asm/bug.h +++ b/arch/ia64/include/asm/bug.h @@ -4,7 +4,11 @@ #ifdef CONFIG_BUG #define ia64_abort() __builtin_trap() -#define BUG() do { printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); ia64_abort(); } while (0) +#define BUG() do { \ + printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ + ia64_abort(); \ +} while (0) /* should this BUG be made generic? */ #define HAVE_ARCH_BUG diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 0b4c65a1af25..498f3da3f225 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -41,7 +41,6 @@ ifneq ($(CONFIG_IA64_ESI),) obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o -obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o diff --git a/arch/m68k/include/asm/bug.h b/arch/m68k/include/asm/bug.h index b7e2bf1ba4a6..275dca1435bf 100644 --- a/arch/m68k/include/asm/bug.h +++ b/arch/m68k/include/asm/bug.h @@ -8,16 +8,19 @@ #ifndef CONFIG_SUN3 #define BUG() do { \ pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #else #define BUG() do { \ pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ panic("BUG!"); \ } while (0) #endif #else #define BUG() do { \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #endif diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile index 1bd5c4f00d19..c22da16d67b8 100644 --- a/arch/mips/boot/Makefile +++ b/arch/mips/boot/Makefile @@ -126,6 +126,7 @@ $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS quiet_cmd_cpp_its_S = ITS $@ cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \ + -D__ASSEMBLY__ \ -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \ -DVMLINUX_BINARY="\"$(3)\"" \ -DVMLINUX_COMPRESSION="\"$(2)\"" \ diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 946681db8dc3..9a0fa66b81ac 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -86,7 +86,6 @@ struct compat_flock { compat_off_t l_len; s32 l_sysid; compat_pid_t l_pid; - short __unused; s32 pad[4]; }; diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c index 19c88d770054..fcf9af492d60 100644 --- a/arch/mips/kernel/mips-cpc.c +++ b/arch/mips/kernel/mips-cpc.c @@ -10,6 +10,8 @@ #include <linux/errno.h> #include <linux/percpu.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/spinlock.h> #include <asm/mips-cps.h> @@ -22,6 +24,17 @@ static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags); phys_addr_t __weak mips_cpc_default_phys_base(void) { + struct device_node *cpc_node; + struct resource res; + int err; + + cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc"); + if (cpc_node) { + err = of_address_to_resource(cpc_node, 0, &res); + if (!err) + return res.start; + } + return 0; } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 85bc601e9a0d..5f8b0a9e30b3 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -375,6 +375,7 @@ static void __init bootmem_init(void) unsigned long reserved_end; unsigned long mapstart = ~0UL; unsigned long bootmap_size; + phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX; bool bootmap_valid = false; int i; @@ -395,7 +396,8 @@ static void __init bootmem_init(void) max_low_pfn = 0; /* - * Find the highest page frame number we have available. + * Find the highest page frame number we have available + * and the lowest used RAM address */ for (i = 0; i < boot_mem_map.nr_map; i++) { unsigned long start, end; @@ -407,6 +409,8 @@ static void __init bootmem_init(void) end = PFN_DOWN(boot_mem_map.map[i].addr + boot_mem_map.map[i].size); + ramstart = min(ramstart, boot_mem_map.map[i].addr); + #ifndef CONFIG_HIGHMEM /* * Skip highmem here so we get an accurate max_low_pfn if low @@ -436,6 +440,13 @@ static void __init bootmem_init(void) mapstart = max(reserved_end, start); } + /* + * Reserve any memory between the start of RAM and PHYS_OFFSET + */ + if (ramstart > PHYS_OFFSET) + add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET, + BOOT_MEM_RESERVED); + if (min_low_pfn >= max_low_pfn) panic("Incorrect memory mapping !!!"); if (min_low_pfn > ARCH_PFN_OFFSET) { @@ -664,9 +675,6 @@ static int __init early_parse_mem(char *p) add_memory_region(start, size, BOOT_MEM_RAM); - if (start && start > PHYS_OFFSET) - add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET, - BOOT_MEM_RESERVED); return 0; } early_param("mem", early_parse_mem); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 87dcac2447c8..9d41732a9146 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -572,7 +572,7 @@ asmlinkage void __weak plat_wired_tlb_setup(void) */ } -void __init bmips_cpu_setup(void) +void bmips_cpu_setup(void) { void __iomem __maybe_unused *cbr = BMIPS_GET_CBR(); u32 __maybe_unused cfg; diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 30a155c0a6b0..c615abdce119 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -16,6 +16,7 @@ #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 949d691094a4..67c5475311ee 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -63,7 +63,8 @@ static inline int hash__hugepd_ok(hugepd_t hpd) * keeping the prototype consistent across the two formats. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, unsigned long hidx, + int offset) { return (hidx << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX); diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 338b7da468ce..3bcf269f8f55 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -45,7 +45,7 @@ * generic accessors and iterators here */ #define __real_pte __real_pte -static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) { real_pte_t rpte; unsigned long *hidxp; @@ -59,7 +59,7 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) */ smp_rmb(); - hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + hidxp = (unsigned long *)(ptep + offset); rpte.hidx = *hidxp; return rpte; } @@ -86,9 +86,10 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) * expected to modify the PTE bits accordingly and commit the PTE to memory. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, + unsigned long hidx, int offset) { - unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + unsigned long *hidxp = (unsigned long *)(ptep + offset); rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index); *hidxp = rpte.hidx | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index); @@ -140,13 +141,18 @@ static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long a } #define H_PTE_TABLE_SIZE PTE_FRAG_SIZE -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE) #define H_PMD_TABLE_SIZE ((sizeof(pmd_t) << PMD_INDEX_SIZE) + \ (sizeof(unsigned long) << PMD_INDEX_SIZE)) #else #define H_PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) #endif +#ifdef CONFIG_HUGETLB_PAGE +#define H_PUD_TABLE_SIZE ((sizeof(pud_t) << PUD_INDEX_SIZE) + \ + (sizeof(unsigned long) << PUD_INDEX_SIZE)) +#else #define H_PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#endif #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 0920eff731b3..935adcd92a81 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -23,7 +23,8 @@ H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) #define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_PPC_64K_PAGES) +#if (defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)) && \ + defined(CONFIG_PPC_64K_PAGES) /* * only with hash 64k we need to use the second half of pmd page table * to store pointer to deposited pgtable_t @@ -33,6 +34,16 @@ #define H_PMD_CACHE_INDEX H_PMD_INDEX_SIZE #endif /* + * We store the slot details in the second half of page table. + * Increase the pud level table so that hugetlb ptes can be stored + * at pud level. + */ +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE + 1) +#else +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE) +#endif +/* * Define the address range of the kernel non-linear virtual area */ #define H_KERN_VIRT_START ASM_CONST(0xD000000000000000) diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 1fcfa425cefa..4746bc68d446 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -73,10 +73,16 @@ static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { + pgd_t *pgd; + if (radix_enabled()) return radix__pgd_alloc(mm); - return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), - pgtable_gfp_flags(mm, GFP_KERNEL)); + + pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), + pgtable_gfp_flags(mm, GFP_KERNEL)); + memset(pgd, 0, PGD_TABLE_SIZE); + + return pgd; } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -93,13 +99,13 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), + return kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), pgtable_gfp_flags(mm, GFP_KERNEL)); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud); + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) @@ -115,7 +121,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE); + pgtable_free_tlb(tlb, pud, PUD_CACHE_INDEX); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 51017726d495..a6b9f1d74600 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -232,11 +232,13 @@ extern unsigned long __pmd_index_size; extern unsigned long __pud_index_size; extern unsigned long __pgd_index_size; extern unsigned long __pmd_cache_index; +extern unsigned long __pud_cache_index; #define PTE_INDEX_SIZE __pte_index_size #define PMD_INDEX_SIZE __pmd_index_size #define PUD_INDEX_SIZE __pud_index_size #define PGD_INDEX_SIZE __pgd_index_size #define PMD_CACHE_INDEX __pmd_cache_index +#define PUD_CACHE_INDEX __pud_cache_index /* * Because of use of pte fragments and THP, size of page table * are not always derived out of index size above. @@ -348,7 +350,7 @@ extern unsigned long pci_io_base; */ #ifndef __real_pte -#define __real_pte(e,p) ((real_pte_t){(e)}) +#define __real_pte(e, p, o) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) #define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 176dfb73d42c..471b2274fbeb 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -645,7 +645,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXC_HV, SOFTEN_TEST_HV, bitmask) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec, bitmask);\ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 511acfd7ab0d..535add3f7791 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -52,7 +52,7 @@ #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) #define FW_FEATURE_DRMEM_V2 ASM_CONST(0x0000000400000000) -#define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000400000000) +#define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000800000000) #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 88e5e8f17e98..855e17d158b1 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -30,6 +30,16 @@ #define PACA_IRQ_PMI 0x40 /* + * Some soft-masked interrupts must be hard masked until they are replayed + * (e.g., because the soft-masked handler does not clear the exception). + */ +#ifdef CONFIG_PPC_BOOK3S +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_PMI) +#else +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE) +#endif + +/* * flags for paca->irq_soft_mask */ #define IRQS_ENABLED 0 @@ -244,7 +254,7 @@ static inline bool lazy_irq_pending(void) static inline void may_hard_irq_enable(void) { get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; - if (!(get_paca()->irq_happened & PACA_IRQ_EE)) + if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) __hard_irq_enable(); } diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 9dcbfa6bbb91..d8b1e8e7e035 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -140,6 +140,12 @@ static inline bool kdump_in_progress(void) return false; } +static inline void crash_ipi_callback(struct pt_regs *regs) { } + +static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) +{ +} + #endif /* CONFIG_KEXEC_CORE */ #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 504a3c36ce5c..03bbd1149530 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -24,6 +24,7 @@ extern int icache_44x_need_flush; #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index abddf5830ad5..5c5f75d005ad 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -27,6 +27,7 @@ #else #define PMD_CACHE_INDEX PMD_INDEX_SIZE #endif +#define PUD_CACHE_INDEX PUD_INDEX_SIZE /* * Define the address range of the kernel non-linear virtual area diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 88187c285c70..9f421641a35c 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,6 +44,11 @@ extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); extern int numa_update_cpu_topology(bool cpus_locked); +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) +{ + numa_cpu_lookup_table[cpu] = node; +} + static inline int early_cpu_to_node(int cpu) { int nid; @@ -76,12 +81,16 @@ static inline int numa_update_cpu_topology(bool cpus_locked) { return 0; } + +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} + #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int start_topology_update(void); extern int stop_topology_update(void); extern int prrn_is_enabled(void); +extern int find_and_online_cpu_nid(int cpu); #else static inline int start_topology_update(void) { @@ -95,6 +104,10 @@ static inline int prrn_is_enabled(void) { return 0; } +static inline int find_and_online_cpu_nid(int cpu) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index beea2182d754..0c0b66fc5bfb 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -384,7 +384,8 @@ static void *eeh_report_resume(void *data, void *userdata) eeh_pcid_put(dev); pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); #ifdef CONFIG_PCI_IOV - eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); + if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev)) + eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); #endif return NULL; } diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index ee832d344a5a..9b6e653e501a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -943,6 +943,8 @@ kernel_dbg_exc: /* * An interrupt came in while soft-disabled; We mark paca->irq_happened * accordingly and if the interrupt is level sensitive, we hard disable + * hard disable (full_mask) corresponds to PACA_IRQ_MUST_HARD_MASK, so + * keep these in synch. */ .macro masked_interrupt_book3e paca_irq full_mask diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 243d072a225a..3ac87e53b3da 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1426,7 +1426,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) * triggered and won't automatically refire. * - If it was a HMI we return immediately since we handled it in realmode * and it won't refire. - * - else we hard disable and return. + * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return. * This is called with r10 containing the value to OR to the paca field. */ #define MASKED_INTERRUPT(_H) \ @@ -1441,8 +1441,8 @@ masked_##_H##interrupt: \ ori r10,r10,0xffff; \ mtspr SPRN_DEC,r10; \ b MASKED_DEC_HANDLER_LABEL; \ -1: andi. r10,r10,(PACA_IRQ_DBELL|PACA_IRQ_HMI); \ - bne 2f; \ +1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK; \ + beq 2f; \ mfspr r10,SPRN_##_H##SRR1; \ xori r10,r10,MSR_EE; /* clear MSR_EE */ \ mtspr SPRN_##_H##SRR1,r10; \ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index adf044daafd7..d22c41c26bb3 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -874,7 +874,7 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .mmu = 0, .hash_ext = 0, .radix_ext = 0, - .byte22 = OV5_FEAT(OV5_DRC_INFO), + .byte22 = 0, }, /* option vector 6: IBM PAPR hints */ diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5a8bfee6e187..04d0bbd7a1dd 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -788,7 +788,8 @@ static int register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_create_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_create_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ @@ -873,7 +874,8 @@ static int unregister_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_remove_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_remove_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index f0f5cd4d2fe7..f9818d7d3381 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -188,7 +188,7 @@ static int xive_provision_queue(struct kvm_vcpu *vcpu, u8 prio) if (!qpage) { pr_err("Failed to allocate queue %d for VCPU %d\n", prio, xc->server_num); - return -ENOMEM;; + return -ENOMEM; } memset(qpage, 0, 1 << xive->q_order); diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 1604110c4238..3f1803672c9b 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -98,7 +98,7 @@ static void init_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell, dr_cell->base_addr = cpu_to_be64(lmb->base_addr); dr_cell->drc_index = cpu_to_be32(lmb->drc_index); dr_cell->aa_index = cpu_to_be32(lmb->aa_index); - dr_cell->flags = cpu_to_be32(lmb->flags); + dr_cell->flags = cpu_to_be32(drmem_lmb_flags(lmb)); } static int drmem_update_dt_v2(struct device_node *memory, @@ -121,7 +121,7 @@ static int drmem_update_dt_v2(struct device_node *memory, } if (prev_lmb->aa_index != lmb->aa_index || - prev_lmb->flags != lmb->flags) + drmem_lmb_flags(prev_lmb) != drmem_lmb_flags(lmb)) lmb_sets++; prev_lmb = lmb; @@ -150,7 +150,7 @@ static int drmem_update_dt_v2(struct device_node *memory, } if (prev_lmb->aa_index != lmb->aa_index || - prev_lmb->flags != lmb->flags) { + drmem_lmb_flags(prev_lmb) != drmem_lmb_flags(lmb)) { /* end of one set, start of another */ dr_cell->seq_lmbs = cpu_to_be32(seq_lmbs); dr_cell++; @@ -216,6 +216,8 @@ static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm, u32 i, n_lmbs; n_lmbs = of_read_number(prop++, 1); + if (n_lmbs == 0) + return; for (i = 0; i < n_lmbs; i++) { read_drconf_v1_cell(&lmb, &prop); @@ -245,6 +247,8 @@ static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, u32 i, j, lmb_sets; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; for (i = 0; i < lmb_sets; i++) { read_drconf_v2_cell(&dr_cell, &prop); @@ -354,6 +358,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) struct drmem_lmb *lmb; drmem_info->n_lmbs = of_read_number(prop++, 1); + if (drmem_info->n_lmbs == 0) + return; drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb), GFP_KERNEL); @@ -373,6 +379,8 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) int lmb_index; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; /* first pass, calculate the number of LMBs */ p = prop; diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c index 5a69b51d08a3..d573d7d07f25 100644 --- a/arch/powerpc/mm/hash64_4k.c +++ b/arch/powerpc/mm/hash64_4k.c @@ -55,7 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, * need to add in 0x1 if it's a read-only user page */ rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -117,7 +117,7 @@ repeat: return -1; } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 2253bbc6a599..e601d95c3b20 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -86,7 +86,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, subpg_index = (ea & (PAGE_SIZE - 1)) >> shift; vpn = hpt_vpn(ea, vsid, ssize); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); /* *None of the sub 4k page is hashed */ @@ -214,7 +214,7 @@ repeat: return -1; } - new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot); + new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE); new_pte |= H_PAGE_HASHPTE; *ptep = __pte(new_pte & ~H_PAGE_BUSY); @@ -262,7 +262,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -327,7 +327,7 @@ repeat: } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 7d07c7e17db6..cf290d415dcd 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1008,6 +1008,7 @@ void __init hash__early_init_mmu(void) __pmd_index_size = H_PMD_INDEX_SIZE; __pud_index_size = H_PUD_INDEX_SIZE; __pgd_index_size = H_PGD_INDEX_SIZE; + __pud_cache_index = H_PUD_CACHE_INDEX; __pmd_cache_index = H_PMD_CACHE_INDEX; __pte_table_size = H_PTE_TABLE_SIZE; __pmd_table_size = H_PMD_TABLE_SIZE; diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index 12511f5a015f..b320f5097a06 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -27,7 +27,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, unsigned long vpn; unsigned long old_pte, new_pte; unsigned long rflags, pa, sz; - long slot; + long slot, offset; BUG_ON(shift != mmu_psize_defs[mmu_psize].shift); @@ -63,7 +63,11 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + if (unlikely(mmu_psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; + rpte = __real_pte(__pte(old_pte), ptep, offset); sz = ((1UL) << shift); if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -104,7 +108,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, return -1; } - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, offset); } /* diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index eb8c6c8c4851..2b656e67f2ea 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -100,6 +100,6 @@ void pgtable_cache_init(void) * same size as either the pgd or pmd index except with THP enabled * on book3s 64 */ - if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE)) - pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor); + if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX)) + pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 314d19ab9385..edd8d0bc9364 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -143,11 +143,6 @@ static void reset_numa_cpu_lookup_table(void) numa_cpu_lookup_table[cpu] = -1; } -static void update_numa_cpu_lookup_table(unsigned int cpu, int node) -{ - numa_cpu_lookup_table[cpu] = node; -} - static void map_cpu_to_node(int cpu, int node) { update_numa_cpu_lookup_table(cpu, node); diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 573a9a2ee455..2e10a964e290 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -17,9 +17,11 @@ #include <linux/of_fdt.h> #include <linux/mm.h> #include <linux/string_helpers.h> +#include <linux/stop_machine.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> +#include <asm/mmu_context.h> #include <asm/dma.h> #include <asm/machdep.h> #include <asm/mmu.h> @@ -333,6 +335,22 @@ static void __init radix_init_pgtable(void) "r" (TLBIEL_INVAL_SET_LPID), "r" (0)); asm volatile("eieio; tlbsync; ptesync" : : : "memory"); trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1); + + /* + * The init_mm context is given the first available (non-zero) PID, + * which is the "guard PID" and contains no page table. PIDR should + * never be set to zero because that duplicates the kernel address + * space at the 0x0... offset (quadrant 0)! + * + * An arbitrary PID that may later be allocated by the PID allocator + * for userspace processes must not be used either, because that + * would cause stale user mappings for that PID on CPUs outside of + * the TLB invalidation scheme (because it won't be in mm_cpumask). + * + * So permanently carve out one PID for the purpose of a guard PID. + */ + init_mm.context.id = mmu_base_pid; + mmu_base_pid++; } static void __init radix_init_partition_table(void) @@ -535,6 +553,7 @@ void __init radix__early_init_mmu(void) __pmd_index_size = RADIX_PMD_INDEX_SIZE; __pud_index_size = RADIX_PUD_INDEX_SIZE; __pgd_index_size = RADIX_PGD_INDEX_SIZE; + __pud_cache_index = RADIX_PUD_INDEX_SIZE; __pmd_cache_index = RADIX_PMD_INDEX_SIZE; __pte_table_size = RADIX_PTE_TABLE_SIZE; __pmd_table_size = RADIX_PMD_TABLE_SIZE; @@ -579,7 +598,8 @@ void __init radix__early_init_mmu(void) radix_init_iamr(); radix_init_pgtable(); - + /* Switch to the guard PID before turning on MMU */ + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } @@ -604,6 +624,7 @@ void radix__early_init_mmu_secondary(void) } radix_init_iamr(); + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } @@ -666,6 +687,30 @@ static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) pud_clear(pud); } +struct change_mapping_params { + pte_t *pte; + unsigned long start; + unsigned long end; + unsigned long aligned_start; + unsigned long aligned_end; +}; + +static int stop_machine_change_mapping(void *data) +{ + struct change_mapping_params *params = + (struct change_mapping_params *)data; + + if (!data) + return -1; + + spin_unlock(&init_mm.page_table_lock); + pte_clear(&init_mm, params->aligned_start, params->pte); + create_physical_mapping(params->aligned_start, params->start); + create_physical_mapping(params->end, params->aligned_end); + spin_lock(&init_mm.page_table_lock); + return 0; +} + static void remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end) { @@ -694,6 +739,52 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, } } +/* + * clear the pte and potentially split the mapping helper + */ +static void split_kernel_mapping(unsigned long addr, unsigned long end, + unsigned long size, pte_t *pte) +{ + unsigned long mask = ~(size - 1); + unsigned long aligned_start = addr & mask; + unsigned long aligned_end = addr + size; + struct change_mapping_params params; + bool split_region = false; + + if ((end - addr) < size) { + /* + * We're going to clear the PTE, but not flushed + * the mapping, time to remap and flush. The + * effects if visible outside the processor or + * if we are running in code close to the + * mapping we cleared, we are in trouble. + */ + if (overlaps_kernel_text(aligned_start, addr) || + overlaps_kernel_text(end, aligned_end)) { + /* + * Hack, just return, don't pte_clear + */ + WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel " + "text, not splitting\n", addr, end); + return; + } + split_region = true; + } + + if (split_region) { + params.pte = pte; + params.start = addr; + params.end = end; + params.aligned_start = addr & ~(size - 1); + params.aligned_end = min_t(unsigned long, aligned_end, + (unsigned long)__va(memblock_end_of_DRAM())); + stop_machine(stop_machine_change_mapping, ¶ms, NULL); + return; + } + + pte_clear(&init_mm, addr, pte); +} + static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end) { @@ -709,13 +800,7 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_huge(*pmd)) { - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pmd); + split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd); continue; } @@ -740,13 +825,7 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, continue; if (pud_huge(*pud)) { - if (!IS_ALIGNED(addr, PUD_SIZE) || - !IS_ALIGNED(next, PUD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pud); + split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud); continue; } @@ -772,13 +851,7 @@ static void remove_pagetable(unsigned long start, unsigned long end) continue; if (pgd_huge(*pgd)) { - if (!IS_ALIGNED(addr, PGDIR_SIZE) || - !IS_ALIGNED(next, PGDIR_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pgd); + split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd); continue; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index c9a623c2d8a2..28c980eb4422 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -82,6 +82,8 @@ unsigned long __pgd_index_size; EXPORT_SYMBOL(__pgd_index_size); unsigned long __pmd_cache_index; EXPORT_SYMBOL(__pmd_cache_index); +unsigned long __pud_cache_index; +EXPORT_SYMBOL(__pud_cache_index); unsigned long __pte_table_size; EXPORT_SYMBOL(__pte_table_size); unsigned long __pmd_table_size; @@ -471,6 +473,8 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, if (old & PATB_HR) { asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : : "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1); } else { asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 881ebd53ffc2..9b23f12e863c 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -51,7 +51,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, unsigned int psize; int ssize; real_pte_t rpte; - int i; + int i, offset; i = batch->index; @@ -67,6 +67,10 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, psize = get_slice_psize(mm, addr); /* Mask the address for the correct page size */ addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1); + if (unlikely(psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; #else BUG(); psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */ @@ -78,6 +82,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, * support 64k pages, this might be different from the * hardware page size encoded in the slice table. */ addr &= PAGE_MASK; + offset = PTRS_PER_PTE; } @@ -91,7 +96,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, } WARN_ON(vsid == 0); vpn = hpt_vpn(addr, vsid, ssize); - rpte = __real_pte(__pte(pte), ptep); + rpte = __real_pte(__pte(pte), ptep, offset); /* * Check if we have an active batch on this CPU. If not, just diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 872d1f6dd11e..a9636d8cba15 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -327,6 +327,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); break; + case BPF_LDX | BPF_W | BPF_ABS: /* A = *((u32 *)(seccomp_data + K)); */ + PPC_LWZ_OFFS(r_A, r_skb, K); + break; case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */ PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len)); break; diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index dd4c9b8b8a81..f6f55ab4980e 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -199,9 +199,11 @@ static void disable_nest_pmu_counters(void) const struct cpumask *l_cpumask; get_online_cpus(); - for_each_online_node(nid) { + for_each_node_with_cpus(nid) { l_cpumask = cpumask_of_node(nid); - cpu = cpumask_first(l_cpumask); + cpu = cpumask_first_and(l_cpumask, cpu_online_mask); + if (cpu >= nr_cpu_ids) + continue; opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(cpu)); } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 496e47696ed0..a6c92c78c9b2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1854,7 +1854,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) s64 rc; if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) - return -ENODEV;; + return -ENODEV; pe = &phb->ioda.pe_array[pdn->pe_number]; if (pe->tce_bypass_enabled) { diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 4fb21e17504a..092715b9674b 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -80,6 +80,10 @@ static void pnv_setup_rfi_flush(void) if (np && of_property_read_bool(np, "disabled")) enable--; + np = of_get_child_by_name(fw_features, "speculation-policy-favor-security"); + if (np && of_property_read_bool(np, "disabled")) + enable = 0; + of_node_put(np); of_node_put(fw_features); } diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index 2b3eb01ab110..b7c53a51c31b 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -1063,16 +1063,16 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop, rc = PTR_ERR(txwin->paste_kaddr); goto free_window; } + } else { + /* + * A user mapping must ensure that context switch issues + * CP_ABORT for this thread. + */ + rc = set_thread_uses_vas(); + if (rc) + goto free_window; } - /* - * Now that we have a send window, ensure context switch issues - * CP_ABORT for this thread. - */ - rc = -EINVAL; - if (set_thread_uses_vas() < 0) - goto free_window; - set_vinst_win(vinst, txwin); return txwin; diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index dceb51454d8d..652d3e96b812 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -36,6 +36,7 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/plpar_wrappers.h> +#include <asm/topology.h> #include "pseries.h" #include "offline_states.h" @@ -331,6 +332,7 @@ static void pseries_remove_processor(struct device_node *np) BUG_ON(cpu_online(cpu)); set_cpu_present(cpu, false); set_hard_smp_processor_id(cpu, -1); + update_numa_cpu_lookup_table(cpu, -1); break; } if (cpu >= nr_cpu_ids) @@ -340,8 +342,6 @@ static void pseries_remove_processor(struct device_node *np) cpu_maps_update_done(); } -extern int find_and_online_cpu_nid(int cpu); - static int dlpar_online_cpu(struct device_node *dn) { int rc = 0; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 81d8614e7379..5e1ef9150182 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -49,6 +49,28 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id); /* + * Enable the hotplug interrupt late because processing them may touch other + * devices or systems (e.g. hugepages) that have not been initialized at the + * subsys stage. + */ +int __init init_ras_hotplug_IRQ(void) +{ + struct device_node *np; + + /* Hotplug Events */ + np = of_find_node_by_path("/event-sources/hot-plug-events"); + if (np != NULL) { + if (dlpar_workqueue_init() == 0) + request_event_sources_irqs(np, ras_hotplug_interrupt, + "RAS_HOTPLUG"); + of_node_put(np); + } + + return 0; +} +machine_late_initcall(pseries, init_ras_hotplug_IRQ); + +/* * Initialize handlers for the set of interrupts caused by hardware errors * and power system events. */ @@ -66,15 +88,6 @@ static int __init init_ras_IRQ(void) of_node_put(np); } - /* Hotplug Events */ - np = of_find_node_by_path("/event-sources/hot-plug-events"); - if (np != NULL) { - if (dlpar_workqueue_init() == 0) - request_event_sources_irqs(np, ras_hotplug_interrupt, - "RAS_HOTPLUG"); - of_node_put(np); - } - /* EPOW Events */ np = of_find_node_by_path("/event-sources/epow-events"); if (np != NULL) { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 372d7ada1a0c..1a527625acf7 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -482,7 +482,8 @@ static void pseries_setup_rfi_flush(void) if (types == L1D_FLUSH_NONE) types = L1D_FLUSH_FALLBACK; - if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) + if ((!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) || + (!(result.behaviour & H_CPU_BEHAV_FAVOUR_SECURITY))) enable = false; } else { /* Default to fallback if case hcall is not available */ diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index d9c4c9366049..091f1d0d0af1 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -356,7 +356,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size); if (rc) { - pr_err("Error %lld getting queue info prio %d\n", rc, prio); + pr_err("Error %lld getting queue info CPU %d prio %d\n", rc, + target, prio); rc = -EIO; goto fail; } @@ -370,7 +371,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, /* Configure and enable the queue in HW */ rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order); if (rc) { - pr_err("Error %lld setting queue for prio %d\n", rc, prio); + pr_err("Error %lld setting queue for CPU %d prio %d\n", rc, + target, prio); rc = -EIO; } else { q->qpage = qpage; @@ -389,8 +391,8 @@ static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc, if (IS_ERR(qpage)) return PTR_ERR(qpage); - return xive_spapr_configure_queue(cpu, q, prio, qpage, - xive_queue_shift); + return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu), + q, prio, qpage, xive_queue_shift); } static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, @@ -399,10 +401,12 @@ static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, struct xive_q *q = &xc->queue[prio]; unsigned int alloc_order; long rc; + int hw_cpu = get_hard_smp_processor_id(cpu); - rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0); + rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0); if (rc) - pr_err("Error %ld setting queue for prio %d\n", rc, prio); + pr_err("Error %ld setting queue for CPU %d prio %d\n", rc, + hw_cpu, prio); alloc_order = xive_alloc_order(xive_queue_shift); free_pages((unsigned long)q->qpage, alloc_order); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b6722c246d9c..04807c7f64cc 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -8,7 +8,6 @@ config RISCV select OF select OF_EARLY_FLATTREE select OF_IRQ - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_WANT_FRAME_POINTERS select CLONE_BACKWARDS select COMMON_CLK @@ -20,7 +19,6 @@ config RISCV select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A - select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_API_DEBUG @@ -34,7 +32,6 @@ config RISCV select HAVE_ARCH_TRACEHOOK select MODULES_USE_ELF_RELA if MODULES select THREAD_INFO_IN_TASK - select RISCV_IRQ_INTC select RISCV_TIMER config MMU diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 87fc045be51f..56fa592cfa34 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -172,6 +172,9 @@ ENTRY(handle_exception) move a1, sp /* pt_regs */ tail do_IRQ 1: + /* Exceptions run with interrupts enabled */ + csrs sstatus, SR_SIE + /* Handle syscalls */ li t0, EXC_SYSCALL beq s4, t0, handle_syscall @@ -198,8 +201,6 @@ handle_syscall: */ addi s2, s2, 0x4 REG_S s2, PT_SEPC(sp) - /* System calls run with interrupts enabled */ - csrs sstatus, SR_SIE /* Trace syscalls, but only if requested by the user. */ REG_L t0, TASK_TI_FLAGS(tp) andi t0, t0, _TIF_SYSCALL_TRACE diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 226eeb190f90..6e07ed37bbff 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -64,7 +64,7 @@ ENTRY(_start) /* Start the kernel */ mv a0, s0 mv a1, s1 - call sbi_save + call parse_dtb tail start_kernel relocate: diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 09f7064e898c..c11f40c1b2a8 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -144,7 +144,7 @@ asmlinkage void __init setup_vm(void) #endif } -void __init sbi_save(unsigned int hartid, void *dtb) +void __init parse_dtb(unsigned int hartid, void *dtb) { early_init_dt_scan(__va(dtb)); } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6bf594ace663..8767e45f1b2b 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -430,6 +430,8 @@ config SPARC_LEON depends on SPARC32 select USB_EHCI_BIG_ENDIAN_MMIO select USB_EHCI_BIG_ENDIAN_DESC + select USB_UHCI_BIG_ENDIAN_MMIO + select USB_UHCI_BIG_ENDIAN_DESC ---help--- If you say Y here if you are running on a SPARC-LEON processor. The LEON processor is a synthesizable VHDL model of the diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h index 6f17528356b2..ea53e418f6c0 100644 --- a/arch/sparc/include/asm/bug.h +++ b/arch/sparc/include/asm/bug.h @@ -9,10 +9,14 @@ void do_BUG(const char *file, int line); #define BUG() do { \ do_BUG(__FILE__, __LINE__); \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #else -#define BUG() __builtin_trap() +#define BUG() do { \ + barrier_before_unreachable(); \ + __builtin_trap(); \ +} while (0) #endif #define HAVE_ARCH_BUG diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index aff152c87cf4..5a82bac5e0bc 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,6 +1,7 @@ boot/compressed/vmlinux tools/test_get_len tools/insn_sanity +tools/insn_decoder_test purgatory/kexec-purgatory.c purgatory/purgatory.ro diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1c4f7b6a94f4..552b3d0eae36 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -423,12 +423,6 @@ config X86_MPPARSE For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -config X86_BIGSMP - bool "Support for big SMP systems with more than 8 CPUs" - depends on X86_32 && SMP - ---help--- - This option is needed for the systems that have more than 8 CPUs - config GOLDFISH def_bool y depends on X86_GOLDFISH @@ -460,6 +454,12 @@ config INTEL_RDT Say N if unsure. if X86_32 +config X86_BIGSMP + bool "Support for big SMP systems with more than 8 CPUs" + depends on SMP + ---help--- + This option is needed for the systems that have more than 8 CPUs + config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" default y @@ -949,25 +949,66 @@ config MAXSMP Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. +# +# The maximum number of CPUs supported: +# +# The main config value is NR_CPUS, which defaults to NR_CPUS_DEFAULT, +# and which can be configured interactively in the +# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range. +# +# The ranges are different on 32-bit and 64-bit kernels, depending on +# hardware capabilities and scalability features of the kernel. +# +# ( If MAXSMP is enabled we just use the highest possible value and disable +# interactive configuration. ) +# + +config NR_CPUS_RANGE_BEGIN + int + default NR_CPUS_RANGE_END if MAXSMP + default 1 if !SMP + default 2 + +config NR_CPUS_RANGE_END + int + depends on X86_32 + default 64 if SMP && X86_BIGSMP + default 8 if SMP && !X86_BIGSMP + default 1 if !SMP + +config NR_CPUS_RANGE_END + int + depends on X86_64 + default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK) + default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK) + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_32 + default 32 if X86_BIGSMP + default 8 if SMP + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_64 + default 8192 if MAXSMP + default 64 if SMP + default 1 if !SMP + config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP - range 2 8 if SMP && X86_32 && !X86_BIGSMP - range 2 64 if SMP && X86_32 && X86_BIGSMP - range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64 - range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64 - default "1" if !SMP - default "8192" if MAXSMP - default "32" if SMP && X86_BIGSMP - default "8" if SMP && X86_32 - default "64" if SMP + range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END + default NR_CPUS_DEFAULT ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum supported value is 8192, otherwise the maximum value is 512. The minimum value which makes sense is 2. - This is purely to save memory - each supported CPU adds - approximately eight kilobytes to the kernel image. + This is purely to save memory: each supported CPU adds about 8KB + to the kernel image. config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" @@ -1363,7 +1404,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486 + depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 select X86_PAE ---help--- Select this if you have a 32-bit processor and more than 4 diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 65a9a4716e34..8b8d2297d486 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -374,7 +374,7 @@ config X86_TSC config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM + depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 # this should be set for all -march=.. options where the compiler # generates cmov. @@ -385,7 +385,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && X86_P6_NOP + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 353e20c3f114..886a9115af62 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -439,7 +439,7 @@ setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) struct efi_uga_draw_protocol *uga = NULL, *first_uga; efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; unsigned long nr_ugas; - u32 *handles = (u32 *)uga_handle;; + u32 *handles = (u32 *)uga_handle; efi_status_t status = EFI_INVALID_PARAMETER; int i; @@ -484,7 +484,7 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) struct efi_uga_draw_protocol *uga = NULL, *first_uga; efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; unsigned long nr_ugas; - u64 *handles = (u64 *)uga_handle;; + u64 *handles = (u64 *)uga_handle; efi_status_t status = EFI_INVALID_PARAMETER; int i; diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3f48f695d5e6..dce7092ab24a 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,80 +97,69 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 - .macro ALLOC_PT_GPREGS_ON_STACK - addq $-(15*8), %rsp - .endm +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax + /* + * Push registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq \rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq \rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + xorq %r8, %r8 /* nospec r8 */ + pushq %r9 /* pt_regs->r9 */ + xorq %r9, %r9 /* nospec r9 */ + pushq %r10 /* pt_regs->r10 */ + xorq %r10, %r10 /* nospec r10 */ + pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11*/ + pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ + pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ + pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12*/ + pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13*/ + pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14*/ + pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15*/ + UNWIND_HINT_REGS +.endm - .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 - .if \r11 - movq %r11, 6*8+\offset(%rsp) - .endif - .if \r8910 - movq %r10, 7*8+\offset(%rsp) - movq %r9, 8*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - .endif - .if \rax - movq %rax, 10*8+\offset(%rsp) - .endif - .if \rcx - movq %rcx, 11*8+\offset(%rsp) - .endif - movq %rdx, 12*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) - movq %rdi, 14*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - .macro SAVE_C_REGS offset=0 - SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0 - SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_R891011 - SAVE_C_REGS_HELPER 0, 1, 1, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RCX_R891011 - SAVE_C_REGS_HELPER 0, 1, 0, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11 - SAVE_C_REGS_HELPER 0, 0, 0, 1, 0 - .endm - - .macro SAVE_EXTRA_REGS offset=0 - movq %r15, 0*8+\offset(%rsp) - movq %r14, 1*8+\offset(%rsp) - movq %r13, 2*8+\offset(%rsp) - movq %r12, 3*8+\offset(%rsp) - movq %rbp, 4*8+\offset(%rsp) - movq %rbx, 5*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset - .endm - - .macro POP_EXTRA_REGS +.macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .endm - - .macro POP_C_REGS + .if \skip_r11rcx + popq %rsi + .else popq %r11 + .endif popq %r10 popq %r9 popq %r8 popq %rax + .if \skip_r11rcx + popq %rsi + .else popq %rcx + .endif popq %rdx popq %rsi + .if \pop_rdi popq %rdi - .endm - - .macro icebp - .byte 0xf1 - .endm + .endif +.endm /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The @@ -178,7 +167,7 @@ For 32-bit we have the following conventions - kernel is built with * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b18acdff9c3f..c9e55b89f03a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -213,7 +213,7 @@ ENTRY(entry_SYSCALL_64) swapgs /* - * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it + * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it * is not required to switch CR3. */ movq %rsp, PER_CPU_VAR(rsp_scratch) @@ -227,22 +227,8 @@ ENTRY(entry_SYSCALL_64) pushq %rcx /* pt_regs->ip */ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + + PUSH_AND_CLEAR_REGS rax=$-ENOSYS TRACE_IRQS_OFF @@ -326,15 +312,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY - POP_EXTRA_REGS - popq %rsi /* skip r11 */ - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rsi /* skip rcx */ - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 skip_r11rcx=1 /* * Now all regs are restored except RSP and RDI. @@ -564,9 +542,7 @@ END(irq_entries_start) call switch_to_thread_stack 1: - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -627,15 +603,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - POP_EXTRA_REGS - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 /* * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. @@ -693,8 +661,7 @@ GLOBAL(restore_regs_and_return_to_kernel) ud2 1: #endif - POP_EXTRA_REGS - POP_C_REGS + POP_REGS addq $8, %rsp /* skip regs->orig_ax */ /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -913,7 +880,9 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - ALLOC_PT_GPREGS_ON_STACK + /* Save all registers in pt_regs */ + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ @@ -1126,9 +1095,7 @@ ENTRY(xen_failsafe_callback) addq $0x30, %rsp UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) @@ -1168,16 +1135,13 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1216,21 +1180,18 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit) /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_REGS offset=8 cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - ENCODE_FRAME_POINTER 8 - xorl %ebx, %ebx testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1411,22 +1372,7 @@ ENTRY(nmi) pushq 1*8(%rdx) /* pt_regs->rip */ UNWIND_HINT_IRET_REGS pushq $-1 /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq (%rdx) /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER /* @@ -1636,7 +1582,8 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - ALLOC_PT_GPREGS_ON_STACK + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit @@ -1660,8 +1607,7 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - POP_EXTRA_REGS - POP_C_REGS + POP_REGS /* * Skip orig_ax and the "outermost" frame to point RSP at the "iret" diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 98d5358e4041..fd65e016e413 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,15 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ cld /* @@ -214,15 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -338,15 +358,25 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15 */ cld /* diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 731153a4681e..56457cb73448 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3559,7 +3559,7 @@ static int intel_snb_pebs_broken(int cpu) break; case INTEL_FAM6_SANDYBRIDGE_X: - switch (cpu_data(cpu).x86_mask) { + switch (cpu_data(cpu).x86_stepping) { case 6: rev = 0x618; break; case 7: rev = 0x70c; break; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index ae64d0b69729..cf372b90557e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1186,7 +1186,7 @@ void __init intel_pmu_lbr_init_atom(void) * on PMU interrupt */ if (boot_cpu_data.x86_model == 28 - && boot_cpu_data.x86_mask < 10) { + && boot_cpu_data.x86_stepping < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c index a5604c352930..408879b0c0d4 100644 --- a/arch/x86/events/intel/p6.c +++ b/arch/x86/events/intel/p6.c @@ -234,7 +234,7 @@ static __initconst const struct x86_pmu p6_pmu = { static __init void p6_pmu_rdpmc_quirk(void) { - if (boot_cpu_data.x86_mask < 9) { + if (boot_cpu_data.x86_stepping < 9) { /* * PPro erratum 26; fixed in stepping 9 and above. */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 44f5d79d5105..11881726ed37 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -94,7 +94,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) if (boot_cpu_data.x86 == 0x0F && boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86_model <= 0x05 && - boot_cpu_data.x86_mask < 0x0A) + boot_cpu_data.x86_stepping < 0x0A) return 1; else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E)) return 1; diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 30d406146016..e1259f043ae9 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, asm ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) - :"r"(size),"r" (index) + :"g"(size),"r" (index) :"cc"); return mask; } diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 34d99af43994..6804d6642767 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -5,23 +5,20 @@ #include <linux/stringify.h> /* - * Since some emulators terminate on UD2, we cannot use it for WARN. - * Since various instruction decoders disagree on the length of UD1, - * we cannot use it either. So use UD0 for WARN. + * Despite that some emulators terminate on UD2, we use it for WARN(). * - * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas - * our kernel decoder thinks it takes a ModRM byte, which seems consistent - * with various things like the Intel SDM instruction encoding rules) + * Since various instruction decoders/specs disagree on the encoding of + * UD0/UD1. */ -#define ASM_UD0 ".byte 0x0f, 0xff" +#define ASM_UD0 ".byte 0x0f, 0xff" /* + ModRM (for Intel) */ #define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */ #define ASM_UD2 ".byte 0x0f, 0x0b" #define INSN_UD0 0xff0f #define INSN_UD2 0x0b0f -#define LEN_UD0 2 +#define LEN_UD2 2 #ifdef CONFIG_GENERIC_BUG @@ -77,7 +74,11 @@ do { \ unreachable(); \ } while (0) -#define __WARN_FLAGS(flags) _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)) +#define __WARN_FLAGS(flags) \ +do { \ + _BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \ + annotate_reachable(); \ +} while (0) #include <asm-generic/bug.h> diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 70eddb3922ff..736771c9822e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -148,45 +148,46 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline __pure bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" - "2:\n" - ".skip -(((5f-4f) - (2b-1b)) > 0) * " - "((5f-4f) - (2b-1b)),0x90\n" - "3:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 4f - .\n" /* repl offset */ - " .word %P1\n" /* always replace */ - " .byte 3b - 1b\n" /* src len */ - " .byte 5f - 4f\n" /* repl len */ - " .byte 3b - 2b\n" /* pad len */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "4: jmp %l[t_no]\n" - "5:\n" - ".previous\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 0\n" /* no replacement */ - " .word %P0\n" /* feature bit */ - " .byte 3b - 1b\n" /* src len */ - " .byte 0\n" /* repl len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .altinstr_aux,\"ax\"\n" - "6:\n" - " testb %[bitnum],%[cap_byte]\n" - " jnz %l[t_yes]\n" - " jmp %l[t_no]\n" - ".previous\n" - : : "i" (bit), "i" (X86_FEATURE_ALWAYS), - [bitnum] "i" (1 << (bit & 7)), - [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) - : : t_yes, t_no); - t_yes: - return true; - t_no: - return false; + asm_volatile_goto("1: jmp 6f\n" + "2:\n" + ".skip -(((5f-4f) - (2b-1b)) > 0) * " + "((5f-4f) - (2b-1b)),0x90\n" + "3:\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 4f - .\n" /* repl offset */ + " .word %P[always]\n" /* always replace */ + " .byte 3b - 1b\n" /* src len */ + " .byte 5f - 4f\n" /* repl len */ + " .byte 3b - 2b\n" /* pad len */ + ".previous\n" + ".section .altinstr_replacement,\"ax\"\n" + "4: jmp %l[t_no]\n" + "5:\n" + ".previous\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 0\n" /* no replacement */ + " .word %P[feature]\n" /* feature bit */ + " .byte 3b - 1b\n" /* src len */ + " .byte 0\n" /* repl len */ + " .byte 0\n" /* pad len */ + ".previous\n" + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" + : : [feature] "i" (bit), + [always] "i" (X86_FEATURE_ALWAYS), + [bitnum] "i" (1 << (bit & 7)), + [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + : : t_yes, t_no); +t_yes: + return true; +t_no: + return false; } #define static_cpu_has(bit) \ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4d57894635f2..81a1be326571 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -6,6 +6,7 @@ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> +#include <asm/msr-index.h> #ifdef __ASSEMBLY__ @@ -164,11 +165,53 @@ static inline void vmexit_fill_RSB(void) static inline void indirect_branch_prediction_barrier(void) { - alternative_input("", - "call __ibp_barrier", - X86_FEATURE_USE_IBPB, - ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory")); + asm volatile(ALTERNATIVE("", + "movl %[msr], %%ecx\n\t" + "movl %[val], %%eax\n\t" + "movl $0, %%edx\n\t" + "wrmsr", + X86_FEATURE_USE_IBPB) + : : [msr] "i" (MSR_IA32_PRED_CMD), + [val] "i" (PRED_CMD_IBPB) + : "eax", "ecx", "edx", "memory"); } #endif /* __ASSEMBLY__ */ + +/* + * Below is used in the eBPF JIT compiler and emits the byte sequence + * for the following assembly: + * + * With retpolines configured: + * + * callq do_rop + * spec_trap: + * pause + * lfence + * jmp spec_trap + * do_rop: + * mov %rax,(%rsp) + * retq + * + * Without retpolines configured: + * + * jmp *%rax + */ +#ifdef CONFIG_RETPOLINE +# define RETPOLINE_RAX_BPF_JIT_SIZE 17 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT1_off32(0xE8, 7); /* callq do_rop */ \ + /* spec_trap: */ \ + EMIT2(0xF3, 0x90); /* pause */ \ + EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ + EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ + /* do_rop: */ \ + EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \ + EMIT1(0xC3); /* retq */ +#else +# define RETPOLINE_RAX_BPF_JIT_SIZE 2 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT2(0xFF, 0xE0); /* jmp *%rax */ +#endif + #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 096378650142..e7f7a4f7375a 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -56,10 +56,6 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); -#ifdef CONFIG_X86_MCE -#define arch_unmap_kpfn arch_unmap_kpfn -#endif - #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 2c0c8c9e9516..6d3b921ae43a 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -297,9 +297,9 @@ static inline void __flush_tlb_global(void) { PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel); } -static inline void __flush_tlb_single(unsigned long addr) +static inline void __flush_tlb_one_user(unsigned long addr) { - PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr); + PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr); } static inline void flush_tlb_others(const struct cpumask *cpumask, diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 6ec54d01972d..f624f1f10316 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -217,7 +217,7 @@ struct pv_mmu_ops { /* TLB operations */ void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_one_user)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, const struct flush_tlb_info *info); diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index d829360e26bd..b838c51d8c78 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -63,7 +63,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define kpte_clear_flush(ptep, vaddr) \ do { \ pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ + __flush_tlb_one_kernel((vaddr)); \ } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 793bae7e7ce3..1bd9ed87606f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -91,7 +91,7 @@ struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; - __u8 x86_mask; + __u8 x86_stepping; #ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; @@ -109,7 +109,7 @@ struct cpuinfo_x86 { char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ - int x86_cache_size; + unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ /* Cache QoS architectural values: */ int x86_cache_max_rmid; /* max index */ @@ -977,7 +977,4 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); - -void __ibp_barrier(void); - #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 461f53d27708..a4189762b266 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); +void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); void common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 2b8f18ca5874..84137c22fdfa 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -140,7 +140,7 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #else #define __flush_tlb() __native_flush_tlb() #define __flush_tlb_global() __native_flush_tlb_global() -#define __flush_tlb_single(addr) __native_flush_tlb_single(addr) +#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif static inline bool tlb_defer_switch_to_init_mm(void) @@ -400,7 +400,7 @@ static inline void __native_flush_tlb_global(void) /* * flush one page in the user mapping */ -static inline void __native_flush_tlb_single(unsigned long addr) +static inline void __native_flush_tlb_one_user(unsigned long addr) { u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); @@ -437,18 +437,31 @@ static inline void __flush_tlb_all(void) /* * flush one page in the kernel mapping */ -static inline void __flush_tlb_one(unsigned long addr) +static inline void __flush_tlb_one_kernel(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); + + /* + * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its + * paravirt equivalent. Even with PCID, this is sufficient: we only + * use PCID if we also use global PTEs for the kernel mapping, and + * INVLPG flushes global translations across all address spaces. + * + * If PTI is on, then the kernel is mapped with non-global PTEs, and + * __flush_tlb_one_user() will flush the given address for the current + * kernel address space and for its usermode counterpart, but it does + * not flush it for other address spaces. + */ + __flush_tlb_one_user(addr); if (!static_cpu_has(X86_FEATURE_PTI)) return; /* - * __flush_tlb_single() will have cleared the TLB entry for this ASID, - * but since kernel space is replicated across all, we must also - * invalidate all others. + * See above. We need to propagate the flush to all other address + * spaces. In principle, we only need to propagate it to kernelmode + * address spaces, but the extra bookkeeping we would need is not + * worth it. */ invalidate_other_asid(); } diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 197c2e6c7376..099414345865 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -241,24 +241,24 @@ #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 struct hv_reenlightenment_control { - u64 vector:8; - u64 reserved1:8; - u64 enabled:1; - u64 reserved2:15; - u64 target_vp:32; + __u64 vector:8; + __u64 reserved1:8; + __u64 enabled:1; + __u64 reserved2:15; + __u64 target_vp:32; }; #define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 #define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 struct hv_tsc_emulation_control { - u64 enabled:1; - u64 reserved:63; + __u64 enabled:1; + __u64 reserved:63; }; struct hv_tsc_emulation_status { - u64 inprogress:1; - u64 reserved:63; + __u64 inprogress:1; + __u64 reserved:63; }; #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 6db28f17ff28..c88e0b127810 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -235,7 +235,7 @@ int amd_cache_northbridges(void) if (boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model >= 0x8 && (boot_cpu_data.x86_model > 0x9 || - boot_cpu_data.x86_mask >= 0x1)) + boot_cpu_data.x86_stepping >= 0x1)) amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; if (boot_cpu_data.x86 == 0x15) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 25ddf02598d2..b203af0855b5 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -546,7 +546,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); static u32 hsx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ case 0x04: return 0x0f; /* EX */ } @@ -556,7 +556,7 @@ static u32 hsx_deadline_rev(void) static u32 bdx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; case 0x03: return 0x0700000e; case 0x04: return 0x0f00000c; @@ -568,7 +568,7 @@ static u32 bdx_deadline_rev(void) static u32 skx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; case 0x04: return 0x02000014; } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3cc471beb50b..bb6f7a2148d7 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -134,21 +134,40 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, { struct apic_chip_data *apicd = apic_chip_data(irqd); struct irq_desc *desc = irq_data_to_desc(irqd); + bool managed = irqd_affinity_is_managed(irqd); lockdep_assert_held(&vector_lock); trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector, apicd->cpu); - /* Setup the vector move, if required */ - if (apicd->vector && cpu_online(apicd->cpu)) { + /* + * If there is no vector associated or if the associated vector is + * the shutdown vector, which is associated to make PCI/MSI + * shutdown mode work, then there is nothing to release. Clear out + * prev_vector for this and the offlined target case. + */ + apicd->prev_vector = 0; + if (!apicd->vector || apicd->vector == MANAGED_IRQ_SHUTDOWN_VECTOR) + goto setnew; + /* + * If the target CPU of the previous vector is online, then mark + * the vector as move in progress and store it for cleanup when the + * first interrupt on the new vector arrives. If the target CPU is + * offline then the regular release mechanism via the cleanup + * vector is not possible and the vector can be immediately freed + * in the underlying matrix allocator. + */ + if (cpu_online(apicd->cpu)) { apicd->move_in_progress = true; apicd->prev_vector = apicd->vector; apicd->prev_cpu = apicd->cpu; } else { - apicd->prev_vector = 0; + irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector, + managed); } +setnew: apicd->vector = newvec; apicd->cpu = newcpu; BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec])); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 46b675aaf20b..f11910b44638 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1176,16 +1176,25 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) uv_gre_table = gre; for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { + unsigned long size = ((unsigned long)(gre->limit - lgre) + << UV_GAM_RANGE_SHFT); + int order = 0; + char suffix[] = " KMGTPE"; + + while (size > 9999 && order < sizeof(suffix)) { + size /= 1024; + order++; + } + if (!index) { pr_info("UV: GAM Range Table...\n"); pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - ((unsigned long)(gre->limit - lgre)) >> - (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ + size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index fa1261eefa16..f91ba53e06c8 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -18,7 +18,7 @@ void foo(void) OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); - OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask); + OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping); OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level); OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability); OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5bddbdcbc4a3..f0e6456ca7d3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -119,7 +119,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if (c->x86_model == 6 && c->x86_mask == 1) { + if (c->x86_model == 6 && c->x86_stepping == 1) { const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); @@ -149,7 +149,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* K6 with old style WHCR */ if (c->x86_model < 8 || - (c->x86_model == 8 && c->x86_mask < 8)) { + (c->x86_model == 8 && c->x86_stepping < 8)) { /* We can only write allocate on the low 508Mb */ if (mbytes > 508) mbytes = 508; @@ -168,7 +168,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if ((c->x86_model == 8 && c->x86_mask > 7) || + if ((c->x86_model == 8 && c->x86_stepping > 7) || c->x86_model == 9 || c->x86_model == 13) { /* The more serious chips .. */ @@ -221,7 +221,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx * As per AMD technical note 27212 0.2 */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", @@ -241,12 +241,12 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * but they are not certified as MP capable. */ /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) + if ((c->x86_model == 6) && ((c->x86_stepping == 0) || + (c->x86_stepping == 1))) return; /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) + if ((c->x86_model == 7) && (c->x86_stepping == 0)) return; /* @@ -256,8 +256,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for * more. */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || + if (((c->x86_model == 6) && (c->x86_stepping >= 2)) || + ((c->x86_model == 7) && (c->x86_stepping >= 1)) || (c->x86_model > 7)) if (cpu_has(c, X86_FEATURE_MP)) return; @@ -628,7 +628,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) /* Set MTRR capability flag if appropriate */ if (c->x86 == 5) if (c->x86_model == 13 || c->x86_model == 9 || - (c->x86_model == 8 && c->x86_mask >= 8)) + (c->x86_model == 8 && c->x86_stepping >= 8)) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) @@ -795,7 +795,7 @@ static void init_amd_zn(struct cpuinfo_x86 *c) * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. */ - if (c->x86_model <= 1 && c->x86_mask <= 1) + if (c->x86_model <= 1 && c->x86_stepping <= 1) set_cpu_cap(c, X86_FEATURE_CPB); } @@ -906,11 +906,11 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { /* Duron Rev A0 */ - if (c->x86_model == 3 && c->x86_mask == 0) + if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; /* Tbird rev A1/A2 */ if (c->x86_model == 4 && - (c->x86_mask == 0 || c->x86_mask == 1)) + (c->x86_stepping == 0 || c->x86_stepping == 1)) size = 256; } return size; @@ -1047,7 +1047,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) } /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_mask; + ms = (cpu->x86_model << 4) | cpu->x86_stepping; while ((range = *erratum++)) if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && (ms >= AMD_MODEL_RANGE_START(range)) && diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 71949bf2de5a..d71c8b54b696 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) return SPECTRE_V2_CMD_NONE; else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_CMD_AUTO; @@ -175,8 +174,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("unknown option (%s). Switching to AUTO select\n", arg); return SPECTRE_V2_CMD_AUTO; } } @@ -185,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -256,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void) goto retpoline_auto; break; } - pr_err("kernel not compiled with retpoline; no mitigation available!"); + pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); return; retpoline_auto: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); goto retpoline_generic; } mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : @@ -281,7 +278,7 @@ retpoline_auto: pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP or KPTI are available, there is a risk of + * If neither SMEP nor PTI are available, there is a risk of * hitting userspace addresses in the RSB after a context switch * from a shallow call stack to a deeper one. To prevent this fill * the entire RSB, even when using IBRS. @@ -295,21 +292,20 @@ retpoline_auto: if ((!boot_cpu_has(X86_FEATURE_PTI) && !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Filling RSB on context switch\n"); + pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); } /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Enabling Indirect Branch Prediction Barrier\n"); + pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } } #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return sprintf(buf, "Not affected\n"); @@ -318,16 +314,14 @@ ssize_t cpu_show_meltdown(struct device *dev, return sprintf(buf, "Vulnerable\n"); } -ssize_t cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } -ssize_t cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); @@ -337,9 +331,3 @@ ssize_t cpu_show_spectre_v2(struct device *dev, spectre_v2_module_string()); } #endif - -void __ibp_barrier(void) -{ - __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); -} -EXPORT_SYMBOL_GPL(__ibp_barrier); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index c578cd29c2d2..e5ec0f11c0de 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -140,7 +140,7 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: - switch (c->x86_mask) { + switch (c->x86_stepping) { default: name = "2"; break; @@ -215,7 +215,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) * - Note, it seems this may only be in engineering samples. */ if ((c->x86 == 6) && (c->x86_model == 9) && - (c->x86_mask == 1) && (size == 65)) + (c->x86_stepping == 1) && (size == 65)) size -= 1; return size; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d63f4b5706e4..824aee0117bb 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -731,7 +731,7 @@ void cpu_detect(struct cpuinfo_x86 *c) cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = x86_family(tfms); c->x86_model = x86_model(tfms); - c->x86_mask = x86_stepping(tfms); + c->x86_stepping = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -1184,9 +1184,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) int i; c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; + c->x86_cache_size = 0; c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; @@ -1378,8 +1378,8 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); - if (c->x86_mask || c->cpuid_level >= 0) - pr_cont(", stepping: 0x%x)\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + pr_cont(", stepping: 0x%x)\n", c->x86_stepping); else pr_cont(")\n"); } diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6b4bb335641f..8949b7ae6d92 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -215,7 +215,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* common case step number/rev -- exceptions handled below */ c->x86_model = (dir1 >> 4) + 1; - c->x86_mask = dir1 & 0xf; + c->x86_stepping = dir1 & 0xf; /* Now cook; the original recipe is by Channing Corn, from Cyrix. * We do the same thing for each generation: we work out diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 319bf989fad1..d19e903214b4 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -116,14 +116,13 @@ struct sku_microcode { u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, @@ -136,8 +135,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, - /* Updated in the 20180108 release; blacklist until we know otherwise */ - { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, /* Observed in the wild */ { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, @@ -149,7 +146,7 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && - c->x86_mask == spectre_bad_microcodes[i].stepping) + c->x86_stepping == spectre_bad_microcodes[i].stepping) return (c->microcode <= spectre_bad_microcodes[i].microcode); } return false; @@ -196,7 +193,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -212,7 +209,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* CPUID workaround for 0F33/0F34 CPU */ if (c->x86 == 0xF && c->x86_model == 0x3 - && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4)) c->x86_phys_bits = 36; /* @@ -310,7 +307,7 @@ int ppro_with_ram_bug(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask < 8) { + boot_cpu_data.x86_stepping < 8) { pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } @@ -327,7 +324,7 @@ static void intel_smp_check(struct cpuinfo_x86 *c) * Mask B, Pentium, but not Pentium MMX */ if (c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_stepping >= 1 && c->x86_stepping <= 4 && c->x86_model <= 3) { /* * Remember we have B step Pentia with bugs @@ -370,7 +367,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until * model 3 mask 3 */ - if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633) + if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633) clear_cpu_cap(c, X86_FEATURE_SEP); /* @@ -388,7 +385,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * P4 Xeon erratum 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ - if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { + if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) { if (msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) { pr_info("CPU: C0 stepping P4 Xeon detected.\n"); @@ -403,7 +400,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Specification Update"). */ if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && - (c->x86_mask < 0x6 || c->x86_mask == 0xb)) + (c->x86_stepping < 0x6 || c->x86_stepping == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -650,7 +647,7 @@ static void init_intel(struct cpuinfo_x86 *c) case 6: if (l2 == 128) p = "Celeron (Mendocino)"; - else if (c->x86_mask == 0 || c->x86_mask == 5) + else if (c->x86_stepping == 0 || c->x86_stepping == 5) p = "Celeron-A"; break; diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 410629f10ad3..589b948e6e01 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -819,7 +819,7 @@ static __init void rdt_quirks(void) cache_alloc_hsw_probe(); break; case INTEL_FAM6_SKYLAKE_X: - if (boot_cpu_data.x86_mask <= 4) + if (boot_cpu_data.x86_stepping <= 4) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); } } diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index bdab7d2f51af..fca759d272a1 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -1804,6 +1804,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, goto out_common_fail; } closid = ret; + ret = 0; rdtgrp->closid = closid; list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index aa0d5df9dc60..e956eb267061 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -115,4 +115,19 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } extern struct mca_config mca_cfg; +#ifndef CONFIG_X86_64 +/* + * On 32-bit systems it would be difficult to safely unmap a poison page + * from the kernel 1:1 map because there are no non-canonical addresses that + * we can use to refer to the address without risking a speculative access. + * However, this isn't much of an issue because: + * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which + * are only mapped into the kernel as needed + * 2) Few people would run a 32-bit kernel on a machine that supports + * recoverable errors because they have too much memory to boot 32-bit. + */ +static inline void mce_unmap_kpfn(unsigned long pfn) {} +#define mce_unmap_kpfn mce_unmap_kpfn +#endif + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index cbb3af721291..3d8c573a9a27 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -105,6 +105,10 @@ static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn); +#endif + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -234,7 +238,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - pr_cont("{%pS}", (void *)m->ip); + pr_cont("{%pS}", (void *)(unsigned long)m->ip); pr_cont("\n"); } @@ -590,7 +594,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; - memory_failure(pfn, 0); + if (!memory_failure(pfn, 0)) + mce_unmap_kpfn(pfn); } return NOTIFY_OK; @@ -1057,12 +1062,13 @@ static int do_memory_failure(struct mce *m) ret = memory_failure(m->addr >> PAGE_SHIFT, flags); if (ret) pr_err("Memory error not recovered"); + else + mce_unmap_kpfn(m->addr >> PAGE_SHIFT); return ret; } -#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) - -void arch_unmap_kpfn(unsigned long pfn) +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn) { unsigned long decoy_addr; @@ -1073,7 +1079,7 @@ void arch_unmap_kpfn(unsigned long pfn) * We would like to just call: * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a - * speculative access to the posion page because we'd have + * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address @@ -1086,7 +1092,6 @@ void arch_unmap_kpfn(unsigned long pfn) if (set_memory_np(decoy_addr, 1)) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); - } #endif diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index f7c55b0e753a..a15db2b4e0d6 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -921,7 +921,7 @@ static bool is_blacklisted(unsigned int cpu) */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && - c->x86_mask == 0x01 && + c->x86_stepping == 0x01 && llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); @@ -944,7 +944,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, return UCODE_NFOUND; sprintf(name, "intel-ucode/%02x-%02x-%02x", - c->x86, c->x86_model, c->x86_mask); + c->x86, c->x86_model, c->x86_stepping); if (request_firmware_direct(&firmware, name, device)) { pr_debug("data file %s load failed\n", name); @@ -982,7 +982,7 @@ static struct microcode_ops microcode_intel_ops = { static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) { - u64 llc_size = c->x86_cache_size * 1024; + u64 llc_size = c->x86_cache_size * 1024ULL; do_div(llc_size, c->x86_max_cores); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fdc55215d44d..e12ee86906c6 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -859,7 +859,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, */ if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask <= 7) { + boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 40d5a8a75212..7468de429087 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -711,8 +711,8 @@ void __init mtrr_bp_init(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 0xF && boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_mask == 0x3 || - boot_cpu_data.x86_mask == 0x4)) + (boot_cpu_data.x86_stepping == 0x3 || + boot_cpu_data.x86_stepping == 0x4)) phys_addr = 36; size_or_mask = SIZE_OR_MASK_BITS(phys_addr); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7ecedafa1c8..2c8522a39ed5 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -72,8 +72,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) c->x86_model, c->x86_model_id[0] ? c->x86_model_id : "unknown"); - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_stepping); else seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) @@ -91,8 +91,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) } /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + if (c->x86_cache_size) + seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size); show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c29020907886..b59e4fb40fd9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -37,7 +37,7 @@ #define X86 new_cpu_data+CPUINFO_x86 #define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor #define X86_MODEL new_cpu_data+CPUINFO_x86_model -#define X86_MASK new_cpu_data+CPUINFO_x86_mask +#define X86_STEPPING new_cpu_data+CPUINFO_x86_stepping #define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math #define X86_CPUID new_cpu_data+CPUINFO_cpuid_level #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability @@ -332,7 +332,7 @@ ENTRY(startup_32_smp) shrb $4,%al movb %al,X86_MODEL andb $0x0f,%cl # mask mask revision - movb %cl,X86_MASK + movb %cl,X86_STEPPING movl %edx,X86_CAPABILITY .Lis486: diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1f790cf9d38f..3b7427aa7d85 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -542,6 +542,7 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: value -= (u64)address; *(u32 *)location = value; break; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index da0c160e5589..f58336af095c 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -191,6 +191,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: if (*(u32 *)loc != 0) goto invalid_relocation; val -= (u64)loc; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 27d0a1712663..f1c5eb99d445 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -410,7 +410,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01; processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping; processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 041096bdef86..99dc79e76bdc 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -200,9 +200,9 @@ static void native_flush_tlb_global(void) __native_flush_tlb_global(); } -static void native_flush_tlb_single(unsigned long addr) +static void native_flush_tlb_one_user(unsigned long addr) { - __native_flush_tlb_single(addr); + __native_flush_tlb_one_user(addr); } struct static_key paravirt_steal_enabled; @@ -401,7 +401,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .flush_tlb_user = native_flush_tlb, .flush_tlb_kernel = native_flush_tlb_global, - .flush_tlb_single = native_flush_tlb_single, + .flush_tlb_one_user = native_flush_tlb_one_user, .flush_tlb_others = native_flush_tlb_others, .pgd_alloc = __paravirt_pgd_alloc, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6f27facbaa9b..ff99e2b6fc54 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void) cpu_set_state_online(me); } -void __init native_smp_cpus_done(unsigned int max_cpus) +void __init calculate_max_logical_packages(void) { int ncpus; - pr_debug("Boot done\n"); /* * Today neither Intel nor AMD support heterogenous systems so * extrapolate the boot cpu's data to all packages. @@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus) ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); pr_info("Max logical packages: %u\n", __max_logical_packages); +} + +void __init native_smp_cpus_done(unsigned int max_cpus) +{ + pr_debug("Boot done\n"); + + calculate_max_logical_packages(); if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); @@ -1430,8 +1436,8 @@ static void remove_siblinginfo(int cpu) cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); - c->phys_proc_id = 0; c->cpu_core_id = 0; + c->booted_cores = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 446c9ef8cfc3..3d9b2308e7fa 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -181,7 +181,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr) break; case BUG_TRAP_TYPE_WARN: - regs->ip += LEN_UD0; + regs->ip += LEN_UD2; return 1; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8eca1d04aeb8..46ff304140c7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5080,7 +5080,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ -static bool +static __always_inline bool slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) @@ -5110,7 +5110,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, return flush; } -static bool +static __always_inline bool slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool lock_flush_tlb) @@ -5121,7 +5121,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5129,7 +5129,7 @@ slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5137,7 +5137,7 @@ slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f427723dc7db..3dec126aa302 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -10136,7 +10136,10 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); } - if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); + else vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_USE_MSR_BITMAPS); } @@ -10224,8 +10227,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, * updated to reflect this when L1 (or its L2s) actually write to * the MSR. */ - bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); - bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); + bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index d6f848d1211d..2dd1fe13a37b 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -18,7 +18,7 @@ unsigned int x86_model(unsigned int sig) { unsigned int fam, model; - fam = x86_family(sig); + fam = x86_family(sig); model = (sig >> 4) & 0xf; diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index 7b881d03d0dd..3cdf06128d13 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -7,6 +7,7 @@ asmlinkage void just_return_func(void); asm( ".type just_return_func, @function\n" + ".globl just_return_func\n" "just_return_func:\n" " ret\n" ".size just_return_func, .-just_return_func\n" diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3186e6836036..9bbc51ae54a6 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -262,7 +262,7 @@ static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) @@ -1199,8 +1199,8 @@ void __init mem_init(void) register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, - PAGE_SIZE, KCORE_OTHER); + if (get_gate_vma(&init_mm)) + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); mem_init_print_info(NULL); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index c45b6ec5357b..e2db83bebc3b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -820,5 +820,5 @@ void __init __early_set_fixmap(enum fixed_addresses idx, set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); else pte_clear(&init_mm, addr, pte); - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 58477ec3d66d..7c8686709636 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -168,7 +168,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->addr); + __flush_tlb_one_kernel(f->addr); return 0; } diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index c3c5274410a9..9bb7f0ab9fe6 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -63,7 +63,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } unsigned long __FIXADDR_TOP = 0xfffff000; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 92cb8a901c36..e055d1a06699 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -498,7 +498,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * flush that changes context.tlb_gen from 2 to 3. If they get * processed on this CPU in reverse order, we'll see * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. - * If we were to use __flush_tlb_single() and set local_tlb_gen to + * If we were to use __flush_tlb_one_user() and set local_tlb_gen to * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * @@ -519,7 +519,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, addr = f->start; while (addr < f->end) { - __flush_tlb_single(addr); + __flush_tlb_one_user(addr); addr += PAGE_SIZE; } if (local) @@ -666,7 +666,7 @@ static void do_kernel_range_flush(void *info) /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4923d92f918d..45e4eb5bcbb2 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -13,6 +13,7 @@ #include <linux/if_vlan.h> #include <asm/cacheflush.h> #include <asm/set_memory.h> +#include <asm/nospec-branch.h> #include <linux/bpf.h> /* @@ -290,7 +291,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT2(0x89, 0xD2); /* mov edx, edx */ EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); -#define OFFSET1 43 /* number of bytes to jump */ +#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -299,7 +300,7 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 32 +#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ @@ -313,7 +314,7 @@ static void emit_bpf_tail_call(u8 **pprog) * goto out; */ EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ -#define OFFSET3 10 +#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JE, OFFSET3); /* je out */ label3 = cnt; @@ -326,7 +327,7 @@ static void emit_bpf_tail_call(u8 **pprog) * rdi == ctx (1st arg) * rax == prog->bpf_func + prologue_size */ - EMIT2(0xFF, 0xE0); /* jmp rax */ + RETPOLINE_RAX_BPF_JIT(); /* out: */ BUILD_BUG_ON(cnt - label1 != OFFSET1); diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 174c59774cc9..a7a7677265b6 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -460,7 +460,7 @@ static int nmi_setup(void) goto fail; for_each_possible_cpu(cpu) { - if (!cpu) + if (!IS_ENABLED(CONFIG_SMP) || !cpu) continue; memcpy(per_cpu(cpu_msrs, cpu).counters, diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index c2e9285d1bf1..db77e087adaf 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, local_flush_tlb(); stat->d_alltlb++; } else { - __flush_tlb_single(msg->address); + __flush_tlb_one_user(msg->address); stat->d_onetlb++; } stat->d_requestee++; diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 5d73c443e778..220e97841e49 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -770,9 +770,12 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, break; case R_X86_64_PC32: + case R_X86_64_PLT32: /* * PC relative relocations don't need to be adjusted unless * referencing a percpu symbol. + * + * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32. */ if (is_percpu_sym(sym, symname)) add_reloc(&relocs32neg, offset); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 3f4fec59af09..d20763472920 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1316,12 +1316,12 @@ static void xen_flush_tlb(void) preempt_enable(); } -static void xen_flush_tlb_single(unsigned long addr) +static void xen_flush_tlb_one_user(unsigned long addr) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_single(addr); + trace_xen_mmu_flush_tlb_one_user(addr); preempt_disable(); @@ -2386,7 +2386,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, + .flush_tlb_one_user = xen_flush_tlb_one_user, .flush_tlb_others = xen_flush_tlb_others, .pgd_alloc = xen_pgd_alloc, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 77c959cf81e7..7a43b2ae19f1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -122,6 +122,8 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); + else + calculate_max_logical_packages(); if (xen_have_vcpu_info_placement) return; diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 623720a11143..732631ce250f 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -16,6 +16,7 @@ */ #include <linux/dma-contiguous.h> +#include <linux/dma-direct.h> #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/mm.h> @@ -123,7 +124,7 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, unsigned long attrs) { unsigned long ret; - unsigned long uncached = 0; + unsigned long uncached; unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page *page = NULL; @@ -144,15 +145,27 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, if (!page) return NULL; - ret = (unsigned long)page_address(page); + *handle = phys_to_dma(dev, page_to_phys(page)); - /* We currently don't support coherent memory outside KSEG */ +#ifdef CONFIG_MMU + if (PageHighMem(page)) { + void *p; + p = dma_common_contiguous_remap(page, size, VM_MAP, + pgprot_noncached(PAGE_KERNEL), + __builtin_return_address(0)); + if (!p) { + if (!dma_release_from_contiguous(dev, page, count)) + __free_pages(page, get_order(size)); + } + return p; + } +#endif + ret = (unsigned long)page_address(page); BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR || ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); uncached = ret + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR; - *handle = virt_to_bus((void *)ret); __invalidate_dcache_range(ret, size); return (void *)uncached; @@ -161,13 +174,20 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, static void xtensa_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { - unsigned long addr = (unsigned long)vaddr + - XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; - struct page *page = virt_to_page(addr); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; - - BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR || - addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); + unsigned long addr = (unsigned long)vaddr; + struct page *page; + + if (addr >= XCHAL_KSEG_BYPASS_VADDR && + addr - XCHAL_KSEG_BYPASS_VADDR < XCHAL_KSEG_SIZE) { + addr += XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; + page = virt_to_page(addr); + } else { +#ifdef CONFIG_MMU + dma_common_free_remap(vaddr, size, VM_MAP); +#endif + page = pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_handle))); + } if (!dma_release_from_contiguous(dev, page, count)) __free_pages(page, get_order(size)); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index d776ec0d7b22..34aead7dcb48 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -79,19 +79,75 @@ void __init zones_init(void) free_area_init_node(0, zones_size, ARCH_PFN_OFFSET, NULL); } +#ifdef CONFIG_HIGHMEM +static void __init free_area_high(unsigned long pfn, unsigned long end) +{ + for (; pfn < end; pfn++) + free_highmem_page(pfn_to_page(pfn)); +} + +static void __init free_highpages(void) +{ + unsigned long max_low = max_low_pfn; + struct memblock_region *mem, *res; + + reset_all_zones_managed_pages(); + /* set highmem page free */ + for_each_memblock(memory, mem) { + unsigned long start = memblock_region_memory_base_pfn(mem); + unsigned long end = memblock_region_memory_end_pfn(mem); + + /* Ignore complete lowmem entries */ + if (end <= max_low) + continue; + + if (memblock_is_nomap(mem)) + continue; + + /* Truncate partial highmem entries */ + if (start < max_low) + start = max_low; + + /* Find and exclude any reserved regions */ + for_each_memblock(reserved, res) { + unsigned long res_start, res_end; + + res_start = memblock_region_reserved_base_pfn(res); + res_end = memblock_region_reserved_end_pfn(res); + + if (res_end < start) + continue; + if (res_start < start) + res_start = start; + if (res_start > end) + res_start = end; + if (res_end > end) + res_end = end; + if (res_start != start) + free_area_high(start, res_start); + start = res_end; + if (start == end) + break; + } + + /* And now free anything which remains */ + if (start < end) + free_area_high(start, end); + } +} +#else +static void __init free_highpages(void) +{ +} +#endif + /* * Initialize memory pages. */ void __init mem_init(void) { -#ifdef CONFIG_HIGHMEM - unsigned long tmp; - - reset_all_zones_managed_pages(); - for (tmp = max_low_pfn; tmp < max_pfn; tmp++) - free_highmem_page(pfn_to_page(tmp)); -#endif + free_highpages(); max_mapnr = max_pfn - ARCH_PFN_OFFSET; high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); |