From fa7aae8a4257e6be7051420dac1f150c1eef721b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 6 Oct 2015 18:46:22 +0100 Subject: arm64: proc: de-scope TLBI operation during cold boot When cold-booting a CPU, we must invalidate any junk entries from the local TLB prior to enabling the MMU. This doesn't require broadcasting within the inner-shareable domain, so de-scope the operation to apply only to the local CPU. Acked-by: Catalin Marinas Reviewed-by: Catalin Marinas Tested-by: Mark Rutland Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/mm/proc.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index e4ee7bd8830a..bbde13d77da5 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -146,8 +146,8 @@ ENDPROC(cpu_do_switch_mm) * value of the SCTLR_EL1 register. */ ENTRY(__cpu_setup) - tlbi vmalle1is // invalidate I + D TLBs - dsb ish + tlbi vmalle1 // Invalidate local TLB + dsb nsh mov x0, #3 << 20 msr cpacr_el1, x0 // Enable FP/ASIMD -- cgit v1.2.3 From 8e63d38876691756f9bc6930850f1fb77809be1b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 6 Oct 2015 18:46:23 +0100 Subject: arm64: flush: use local TLB and I-cache invalidation There are a number of places where a single CPU is running with a private page-table and we need to perform maintenance on the TLB and I-cache in order to ensure correctness, but do not require the operation to be broadcast to other CPUs. This patch adds local variants of tlb_flush_all and __flush_icache_all to support these use-cases and updates the callers respectively. __local_flush_icache_all also implies an isb, since it is intended to be used synchronously. Reviewed-by: Catalin Marinas Acked-by: David Daney Acked-by: Ard Biesheuvel Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cacheflush.h | 7 +++++++ arch/arm64/include/asm/tlbflush.h | 8 ++++++++ arch/arm64/kernel/efi.c | 4 ++-- arch/arm64/kernel/smp.c | 2 +- arch/arm64/kernel/suspend.c | 2 +- arch/arm64/mm/context.c | 4 ++-- arch/arm64/mm/mmu.c | 2 +- 7 files changed, 22 insertions(+), 7 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index c75b8d027eb1..54efedaf331f 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -115,6 +115,13 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); +static inline void __local_flush_icache_all(void) +{ + asm("ic iallu"); + dsb(nsh); + isb(); +} + static inline void __flush_icache_all(void) { asm("ic ialluis"); diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 7bd2da021658..96f944e75dc4 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -63,6 +63,14 @@ * only require the D-TLB to be invalidated. * - kaddr - Kernel virtual memory address */ +static inline void local_flush_tlb_all(void) +{ + dsb(nshst); + asm("tlbi vmalle1"); + dsb(nsh); + isb(); +} + static inline void flush_tlb_all(void) { dsb(ishst); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 13671a9cf016..4d12926ea40d 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -344,9 +344,9 @@ static void efi_set_pgd(struct mm_struct *mm) else cpu_switch_mm(mm->pgd, mm); - flush_tlb_all(); + local_flush_tlb_all(); if (icache_is_aivivt()) - __flush_icache_all(); + __local_flush_icache_all(); } void efi_virtmap_load(void) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index dbdaacddd9a5..fdd4d4dbd64f 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -152,7 +152,7 @@ asmlinkage void secondary_start_kernel(void) * point to zero page to avoid speculatively fetching new entries. */ cpu_set_reserved_ttbr0(); - flush_tlb_all(); + local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); preempt_disable(); diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 8297d502217e..3c5e4e6dcf68 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -90,7 +90,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) else cpu_switch_mm(mm->pgd, mm); - flush_tlb_all(); + local_flush_tlb_all(); /* * Restore per-cpu offset before any kernel diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index d70ff14dbdbd..48b53fb381af 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -48,9 +48,9 @@ static void flush_context(void) { /* set the reserved TTBR0 before flushing the TLB */ cpu_set_reserved_ttbr0(); - flush_tlb_all(); + local_flush_tlb_all(); if (icache_is_aivivt()) - __flush_icache_all(); + __local_flush_icache_all(); } static void set_mm_context(struct mm_struct *mm, unsigned int asid) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9211b8527f25..71a310478c9e 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -456,7 +456,7 @@ void __init paging_init(void) * point to zero page to avoid speculatively fetching new entries. */ cpu_set_reserved_ttbr0(); - flush_tlb_all(); + local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); } -- cgit v1.2.3 From 5aec715d7d3122f77cabaa7578d9d25a0c1ed20e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 6 Oct 2015 18:46:24 +0100 Subject: arm64: mm: rewrite ASID allocator and MM context-switching code Our current switch_mm implementation suffers from a number of problems: (1) The ASID allocator relies on IPIs to synchronise the CPUs on a rollover event (2) Because of (1), we cannot allocate ASIDs with interrupts disabled and therefore make use of a TIF_SWITCH_MM flag to postpone the actual switch to finish_arch_post_lock_switch (3) We run context switch with a reserved (invalid) TTBR0 value, even though the ASID and pgd are updated atomically (4) We take a global spinlock (cpu_asid_lock) during context-switch (5) We use h/w broadcast TLB operations when they are not required (e.g. in flush_context) This patch addresses these problems by rewriting the ASID algorithm to match the bitmap-based arch/arm/ implementation more closely. This in turn allows us to remove much of the complications surrounding switch_mm, including the ugly thread flag. Reviewed-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/mmu.h | 15 +-- arch/arm64/include/asm/mmu_context.h | 76 ++--------- arch/arm64/include/asm/thread_info.h | 1 - arch/arm64/kernel/asm-offsets.c | 2 +- arch/arm64/kernel/efi.c | 1 - arch/arm64/mm/context.c | 238 +++++++++++++++++++++-------------- arch/arm64/mm/proc.S | 2 +- 7 files changed, 166 insertions(+), 169 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 030208767185..990124a67eeb 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -17,15 +17,16 @@ #define __ASM_MMU_H typedef struct { - unsigned int id; - raw_spinlock_t id_lock; - void *vdso; + atomic64_t id; + void *vdso; } mm_context_t; -#define INIT_MM_CONTEXT(name) \ - .context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock), - -#define ASID(mm) ((mm)->context.id & 0xffff) +/* + * This macro is only used by the TLBI code, which cannot race with an + * ASID change and therefore doesn't need to reload the counter using + * atomic64_read. + */ +#define ASID(mm) ((mm)->context.id.counter & 0xffff) extern void paging_init(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 549b89554ce8..f4c74a951b6c 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -28,13 +28,6 @@ #include #include -#define MAX_ASID_BITS 16 - -extern unsigned int cpu_last_asid; - -void __init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void __new_context(struct mm_struct *mm); - #ifdef CONFIG_PID_IN_CONTEXTIDR static inline void contextidr_thread_switch(struct task_struct *next) { @@ -96,66 +89,19 @@ static inline void cpu_set_default_tcr_t0sz(void) : "r"(TCR_T0SZ(VA_BITS)), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH)); } -static inline void switch_new_context(struct mm_struct *mm) -{ - unsigned long flags; - - __new_context(mm); - - local_irq_save(flags); - cpu_switch_mm(mm->pgd, mm); - local_irq_restore(flags); -} - -static inline void check_and_switch_context(struct mm_struct *mm, - struct task_struct *tsk) -{ - /* - * Required during context switch to avoid speculative page table - * walking with the wrong TTBR. - */ - cpu_set_reserved_ttbr0(); - - if (!((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) - /* - * The ASID is from the current generation, just switch to the - * new pgd. This condition is only true for calls from - * context_switch() and interrupts are already disabled. - */ - cpu_switch_mm(mm->pgd, mm); - else if (irqs_disabled()) - /* - * Defer the new ASID allocation until after the context - * switch critical region since __new_context() cannot be - * called with interrupts disabled. - */ - set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM); - else - /* - * That is a direct call to switch_mm() or activate_mm() with - * interrupts enabled and a new context. - */ - switch_new_context(mm); -} - -#define init_new_context(tsk,mm) (__init_new_context(tsk,mm),0) +/* + * It would be nice to return ASIDs back to the allocator, but unfortunately + * that introduces a race with a generation rollover where we could erroneously + * free an ASID allocated in a future generation. We could workaround this by + * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap), + * but we'd then need to make sure that we didn't dirty any TLBs afterwards. + * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you + * take CPU migration into account. + */ #define destroy_context(mm) do { } while(0) +void check_and_switch_context(struct mm_struct *mm, unsigned int cpu); -#define finish_arch_post_lock_switch \ - finish_arch_post_lock_switch -static inline void finish_arch_post_lock_switch(void) -{ - if (test_and_clear_thread_flag(TIF_SWITCH_MM)) { - struct mm_struct *mm = current->mm; - unsigned long flags; - - __new_context(mm); - - local_irq_save(flags); - cpu_switch_mm(mm->pgd, mm); - local_irq_restore(flags); - } -} +#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) /* * This is called when "tsk" is about to enter lazy TLB mode. diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index dcd06d18a42a..555c6dec5ef2 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -111,7 +111,6 @@ static inline struct thread_info *current_thread_info(void) #define TIF_RESTORE_SIGMASK 20 #define TIF_SINGLESTEP 21 #define TIF_32BIT 22 /* 32bit process */ -#define TIF_SWITCH_MM 23 /* deferred switch_mm */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 8d89cf8dae55..25de8b244961 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -60,7 +60,7 @@ int main(void) DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); - DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id)); + DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); BLANK(); DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm)); DEFINE(VMA_VM_FLAGS, offsetof(struct vm_area_struct, vm_flags)); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 4d12926ea40d..a48d1f477b2e 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -48,7 +48,6 @@ static struct mm_struct efi_mm = { .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem), .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), - INIT_MM_CONTEXT(efi_mm) }; static int uefi_debug __initdata; diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 48b53fb381af..e902229b1a3d 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -17,135 +17,187 @@ * along with this program. If not, see . */ -#include +#include #include +#include #include -#include -#include +#include #include #include -#include -#define asid_bits(reg) \ - (((read_cpuid(ID_AA64MMFR0_EL1) & 0xf0) >> 2) + 8) +static u32 asid_bits; +static DEFINE_RAW_SPINLOCK(cpu_asid_lock); -#define ASID_FIRST_VERSION (1 << MAX_ASID_BITS) +static atomic64_t asid_generation; +static unsigned long *asid_map; -static DEFINE_RAW_SPINLOCK(cpu_asid_lock); -unsigned int cpu_last_asid = ASID_FIRST_VERSION; +static DEFINE_PER_CPU(atomic64_t, active_asids); +static DEFINE_PER_CPU(u64, reserved_asids); +static cpumask_t tlb_flush_pending; -/* - * We fork()ed a process, and we need a new context for the child to run in. - */ -void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) +#define ASID_MASK (~GENMASK(asid_bits - 1, 0)) +#define ASID_FIRST_VERSION (1UL << asid_bits) +#define NUM_USER_ASIDS ASID_FIRST_VERSION + +static void flush_context(unsigned int cpu) { - mm->context.id = 0; - raw_spin_lock_init(&mm->context.id_lock); + int i; + u64 asid; + + /* Update the list of reserved ASIDs and the ASID bitmap. */ + bitmap_clear(asid_map, 0, NUM_USER_ASIDS); + + /* + * Ensure the generation bump is observed before we xchg the + * active_asids. + */ + smp_wmb(); + + for_each_possible_cpu(i) { + asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0); + /* + * If this CPU has already been through a + * rollover, but hasn't run another task in + * the meantime, we must preserve its reserved + * ASID, as this is the only trace we have of + * the process it is still running. + */ + if (asid == 0) + asid = per_cpu(reserved_asids, i); + __set_bit(asid & ~ASID_MASK, asid_map); + per_cpu(reserved_asids, i) = asid; + } + + /* Queue a TLB invalidate and flush the I-cache if necessary. */ + cpumask_setall(&tlb_flush_pending); + + if (icache_is_aivivt()) + __flush_icache_all(); } -static void flush_context(void) +static int is_reserved_asid(u64 asid) { - /* set the reserved TTBR0 before flushing the TLB */ - cpu_set_reserved_ttbr0(); - local_flush_tlb_all(); - if (icache_is_aivivt()) - __local_flush_icache_all(); + int cpu; + for_each_possible_cpu(cpu) + if (per_cpu(reserved_asids, cpu) == asid) + return 1; + return 0; } -static void set_mm_context(struct mm_struct *mm, unsigned int asid) +static u64 new_context(struct mm_struct *mm, unsigned int cpu) { - unsigned long flags; + static u32 cur_idx = 1; + u64 asid = atomic64_read(&mm->context.id); + u64 generation = atomic64_read(&asid_generation); - /* - * Locking needed for multi-threaded applications where the same - * mm->context.id could be set from different CPUs during the - * broadcast. This function is also called via IPI so the - * mm->context.id_lock has to be IRQ-safe. - */ - raw_spin_lock_irqsave(&mm->context.id_lock, flags); - if (likely((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) { + if (asid != 0) { /* - * Old version of ASID found. Set the new one and reset - * mm_cpumask(mm). + * If our current ASID was active during a rollover, we + * can continue to use it and this was just a false alarm. */ - mm->context.id = asid; - cpumask_clear(mm_cpumask(mm)); + if (is_reserved_asid(asid)) + return generation | (asid & ~ASID_MASK); + + /* + * We had a valid ASID in a previous life, so try to re-use + * it if possible. + */ + asid &= ~ASID_MASK; + if (!__test_and_set_bit(asid, asid_map)) + goto bump_gen; } - raw_spin_unlock_irqrestore(&mm->context.id_lock, flags); /* - * Set the mm_cpumask(mm) bit for the current CPU. + * Allocate a free ASID. If we can't find one, take a note of the + * currently active ASIDs and mark the TLBs as requiring flushes. + * We always count from ASID #1, as we use ASID #0 when setting a + * reserved TTBR0 for the init_mm. */ - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx); + if (asid != NUM_USER_ASIDS) + goto set_asid; + + /* We're out of ASIDs, so increment the global generation count */ + generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION, + &asid_generation); + flush_context(cpu); + + /* We have at least 1 ASID per CPU, so this will always succeed */ + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); + +set_asid: + __set_bit(asid, asid_map); + cur_idx = asid; + +bump_gen: + asid |= generation; + cpumask_clear(mm_cpumask(mm)); + return asid; } -/* - * Reset the ASID on the current CPU. This function call is broadcast from the - * CPU handling the ASID rollover and holding cpu_asid_lock. - */ -static void reset_context(void *info) +void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) { - unsigned int asid; - unsigned int cpu = smp_processor_id(); - struct mm_struct *mm = current->active_mm; + unsigned long flags; + u64 asid; + + asid = atomic64_read(&mm->context.id); /* - * current->active_mm could be init_mm for the idle thread immediately - * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to - * the reserved value, so no need to reset any context. + * The memory ordering here is subtle. We rely on the control + * dependency between the generation read and the update of + * active_asids to ensure that we are synchronised with a + * parallel rollover (i.e. this pairs with the smp_wmb() in + * flush_context). */ - if (mm == &init_mm) - return; + if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits) + && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid)) + goto switch_mm_fastpath; + + raw_spin_lock_irqsave(&cpu_asid_lock, flags); + /* Check that our ASID belongs to the current generation. */ + asid = atomic64_read(&mm->context.id); + if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) { + asid = new_context(mm, cpu); + atomic64_set(&mm->context.id, asid); + } - smp_rmb(); - asid = cpu_last_asid + cpu; + if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) + local_flush_tlb_all(); - flush_context(); - set_mm_context(mm, asid); + atomic64_set(&per_cpu(active_asids, cpu), asid); + cpumask_set_cpu(cpu, mm_cpumask(mm)); + raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); - /* set the new ASID */ +switch_mm_fastpath: cpu_switch_mm(mm->pgd, mm); } -void __new_context(struct mm_struct *mm) +static int asids_init(void) { - unsigned int asid; - unsigned int bits = asid_bits(); - - raw_spin_lock(&cpu_asid_lock); - /* - * Check the ASID again, in case the change was broadcast from another - * CPU before we acquired the lock. - */ - if (!unlikely((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) { - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - raw_spin_unlock(&cpu_asid_lock); - return; - } - /* - * At this point, it is guaranteed that the current mm (with an old - * ASID) isn't active on any other CPU since the ASIDs are changed - * simultaneously via IPI. - */ - asid = ++cpu_last_asid; - - /* - * If we've used up all our ASIDs, we need to start a new version and - * flush the TLB. - */ - if (unlikely((asid & ((1 << bits) - 1)) == 0)) { - /* increment the ASID version */ - cpu_last_asid += (1 << MAX_ASID_BITS) - (1 << bits); - if (cpu_last_asid == 0) - cpu_last_asid = ASID_FIRST_VERSION; - asid = cpu_last_asid + smp_processor_id(); - flush_context(); - smp_wmb(); - smp_call_function(reset_context, NULL, 1); - cpu_last_asid += NR_CPUS - 1; + int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1), 4); + + switch (fld) { + default: + pr_warn("Unknown ASID size (%d); assuming 8-bit\n", fld); + /* Fallthrough */ + case 0: + asid_bits = 8; + break; + case 2: + asid_bits = 16; } - set_mm_context(mm, asid); - raw_spin_unlock(&cpu_asid_lock); + /* If we end up with more CPUs than ASIDs, expect things to crash */ + WARN_ON(NUM_USER_ASIDS < num_possible_cpus()); + atomic64_set(&asid_generation, ASID_FIRST_VERSION); + asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map), + GFP_KERNEL); + if (!asid_map) + panic("Failed to allocate bitmap for %lu ASIDs\n", + NUM_USER_ASIDS); + + pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS); + return 0; } +early_initcall(asids_init); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index bbde13d77da5..91cb2eaac256 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -130,7 +130,7 @@ ENDPROC(cpu_do_resume) * - pgd_phys - physical address of new TTB */ ENTRY(cpu_do_switch_mm) - mmid w1, x1 // get mm->context.id + mmid x1, x1 // get mm->context.id bfi x0, x1, #48, #16 // set the ASID msr ttbr0_el1, x0 // set TTBR0 isb -- cgit v1.2.3 From c2775b2ee5caca19f661ee2ab5af92462596db71 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 6 Oct 2015 18:46:27 +0100 Subject: arm64: switch_mm: simplify mm and CPU checks switch_mm performs some checks to try and avoid entering the ASID allocator: (1) If we're switching to the init_mm (no user mappings), then simply set a reserved TTBR0 value with no page table (the zero page) (2) If prev == next *and* the mm_cpumask indicates that we've run on this CPU before, then we can skip the allocator. However, there is plenty of redundancy here. With the new ASID allocator, if prev == next, then we know that our ASID is valid and do not need to worry about re-allocation. Consequently, we can drop the mm_cpumask check in (2) and move the prev == next check before the init_mm check, since if prev == next == init_mm then there's nothing to do. Reviewed-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/mmu_context.h | 6 ++++-- arch/arm64/mm/context.c | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index f4c74a951b6c..c0e87898ba96 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -129,6 +129,9 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, { unsigned int cpu = smp_processor_id(); + if (prev == next) + return; + /* * init_mm.pgd does not contain any user mappings and it is always * active for kernel addresses in TTBR1. Just set the reserved TTBR0. @@ -138,8 +141,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, return; } - if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) - check_and_switch_context(next, tsk); + check_and_switch_context(next, cpu); } #define deactivate_mm(tsk,mm) do { } while (0) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index e902229b1a3d..4b9ec4484e3f 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -166,10 +166,10 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) local_flush_tlb_all(); atomic64_set(&per_cpu(active_asids, cpu), asid); - cpumask_set_cpu(cpu, mm_cpumask(mm)); raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); switch_mm_fastpath: + cpumask_set_cpu(cpu, mm_cpumask(mm)); cpu_switch_mm(mm->pgd, mm); } -- cgit v1.2.3 From 38d96287504a2478eb538bfecfa1fddd743bb6b2 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 6 Oct 2015 18:46:28 +0100 Subject: arm64: mm: kill mm_cpumask usage mm_cpumask isn't actually used for anything on arm64, so remove all the code trying to keep it up-to-date. Reviewed-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/smp.c | 7 ------- arch/arm64/mm/context.c | 2 -- 2 files changed, 9 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index fdd4d4dbd64f..03b0aa28ea61 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -142,7 +142,6 @@ asmlinkage void secondary_start_kernel(void) */ atomic_inc(&mm->mm_count); current->active_mm = mm; - cpumask_set_cpu(cpu, mm_cpumask(mm)); set_my_cpu_offset(per_cpu_offset(smp_processor_id())); printk("CPU%u: Booted secondary processor\n", cpu); @@ -233,12 +232,6 @@ int __cpu_disable(void) * OK - migrate IRQs away from this CPU */ migrate_irqs(); - - /* - * Remove this CPU from the vm mask set of all processes. - */ - clear_tasks_mm_cpumask(cpu); - return 0; } diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 4b9ec4484e3f..f636a2639f03 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -132,7 +132,6 @@ set_asid: bump_gen: asid |= generation; - cpumask_clear(mm_cpumask(mm)); return asid; } @@ -169,7 +168,6 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); switch_mm_fastpath: - cpumask_set_cpu(cpu, mm_cpumask(mm)); cpu_switch_mm(mm->pgd, mm); } -- cgit v1.2.3 From 202e41a1c257eb56a05b5ff5bfde06f7ae98e6eb Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Wed, 7 Oct 2015 12:00:23 -0500 Subject: arm64: Make the kernel page dump utility aware of the CONT bit The kernel page dump utility needs to be aware of the CONT bit before it will break up pages ranges for display. Signed-off-by: Jeremy Linton Signed-off-by: Catalin Marinas --- arch/arm64/mm/dump.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index f3d6221cd5bd..5a22a119a74c 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -67,6 +67,12 @@ static struct addr_marker address_markers[] = { { -1, NULL }, }; +/* + * The page dumper groups page table entries of the same type into a single + * description. It uses pg_state to track the range information while + * iterating over the pte entries. When the continuity is broken it then + * dumps out a description of the range. + */ struct pg_state { struct seq_file *seq; const struct addr_marker *marker; @@ -113,6 +119,16 @@ static const struct prot_bits pte_bits[] = { .val = PTE_NG, .set = "NG", .clear = " ", + }, { + .mask = PTE_CONT, + .val = PTE_CONT, + .set = "CON", + .clear = " ", + }, { + .mask = PTE_TABLE_BIT, + .val = PTE_TABLE_BIT, + .set = " ", + .clear = "BLK", }, { .mask = PTE_UXN, .val = PTE_UXN, @@ -198,7 +214,7 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, unsigned long delta; if (st->current_prot) { - seq_printf(st->seq, "0x%16lx-0x%16lx ", + seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr); delta = (addr - st->start_address) >> 10; -- cgit v1.2.3 From 348a65cdcbbf243073ee39d1f7d4413081ad7eab Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Wed, 7 Oct 2015 12:00:25 -0500 Subject: arm64: Mark kernel page ranges contiguous With 64k pages, the next larger segment size is 512M. The linux kernel also uses different protection flags to cover its code and data. Because of this requirement, the vast majority of the kernel code and data structures end up being mapped with 64k pages instead of the larger pages common with a 4k page kernel. Recent ARM processors support a contiguous bit in the page tables which allows the a TLB to cover a range larger than a single PTE if that range is mapped into physically contiguous ram. So, for the kernel its a good idea to set this flag. Some basic micro benchmarks show it can significantly reduce the number of L1 dTLB refills. Add boot option to enable/disable CONT marking, as well as fix a bug found by Steve Capper. Signed-off-by: Jeremy Linton [catalin.marinas@arm.com: remove CONFIG_ARM64_CONT_PTE altogether] Signed-off-by: Catalin Marinas --- arch/arm64/mm/mmu.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 61 insertions(+), 8 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 71a310478c9e..eed6d52f5e54 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -80,19 +80,55 @@ static void split_pmd(pmd_t *pmd, pte_t *pte) do { /* * Need to have the least restrictive permissions available - * permissions will be fixed up later + * permissions will be fixed up later. Default the new page + * range as contiguous ptes. */ - set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); + set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT)); pfn++; } while (pte++, i++, i < PTRS_PER_PTE); } +/* + * Given a PTE with the CONT bit set, determine where the CONT range + * starts, and clear the entire range of PTE CONT bits. + */ +static void clear_cont_pte_range(pte_t *pte, unsigned long addr) +{ + int i; + + pte -= CONT_RANGE_OFFSET(addr); + for (i = 0; i < CONT_PTES; i++) { + set_pte(pte, pte_mknoncont(*pte)); + pte++; + } + flush_tlb_all(); +} + +/* + * Given a range of PTEs set the pfn and provided page protection flags + */ +static void __populate_init_pte(pte_t *pte, unsigned long addr, + unsigned long end, phys_addr_t phys, + pgprot_t prot) +{ + unsigned long pfn = __phys_to_pfn(phys); + + do { + /* clear all the bits except the pfn, then apply the prot */ + set_pte(pte, pfn_pte(pfn, prot)); + pte++; + pfn++; + addr += PAGE_SIZE; + } while (addr != end); +} + static void alloc_init_pte(pmd_t *pmd, unsigned long addr, - unsigned long end, unsigned long pfn, + unsigned long end, phys_addr_t phys, pgprot_t prot, void *(*alloc)(unsigned long size)) { pte_t *pte; + unsigned long next; if (pmd_none(*pmd) || pmd_sect(*pmd)) { pte = alloc(PTRS_PER_PTE * sizeof(pte_t)); @@ -105,9 +141,27 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr, pte = pte_offset_kernel(pmd, addr); do { - set_pte(pte, pfn_pte(pfn, prot)); - pfn++; - } while (pte++, addr += PAGE_SIZE, addr != end); + next = min(end, (addr + CONT_SIZE) & CONT_MASK); + if (((addr | next | phys) & ~CONT_MASK) == 0) { + /* a block of CONT_PTES */ + __populate_init_pte(pte, addr, next, phys, + prot | __pgprot(PTE_CONT)); + } else { + /* + * If the range being split is already inside of a + * contiguous range but this PTE isn't going to be + * contiguous, then we want to unmark the adjacent + * ranges, then update the portion of the range we + * are interrested in. + */ + clear_cont_pte_range(pte, addr); + __populate_init_pte(pte, addr, next, phys, prot); + } + + pte += (next - addr) >> PAGE_SHIFT; + phys += next - addr; + addr = next; + } while (addr != end); } void split_pud(pud_t *old_pud, pmd_t *pmd) @@ -168,8 +222,7 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, } } } else { - alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), - prot, alloc); + alloc_init_pte(pmd, addr, next, phys, prot, alloc); } phys += next - addr; } while (pmd++, addr = next, addr != end); -- cgit v1.2.3 From 207918461eb0aca720fddec5da79bc71c133b9f1 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 8 Oct 2015 20:02:03 +0100 Subject: arm64: use ENDPIPROC() to annotate position independent assembler routines For more control over which functions are called with the MMU off or with the UEFI 1:1 mapping active, annotate some assembler routines as position independent. This is done by introducing ENDPIPROC(), which replaces the ENDPROC() declaration of those routines. Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/assembler.h | 11 +++++++++++ arch/arm64/lib/memchr.S | 2 +- arch/arm64/lib/memcmp.S | 2 +- arch/arm64/lib/memcpy.S | 2 +- arch/arm64/lib/memmove.S | 2 +- arch/arm64/lib/memset.S | 2 +- arch/arm64/lib/strcmp.S | 2 +- arch/arm64/lib/strlen.S | 2 +- arch/arm64/lib/strncmp.S | 2 +- arch/arm64/mm/cache.S | 10 +++++----- 10 files changed, 24 insertions(+), 13 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index b51f2cc22ca9..12eff928ef8b 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -193,4 +193,15 @@ lr .req x30 // link register str \src, [\tmp, :lo12:\sym] .endm +/* + * Annotate a function as position independent, i.e., safe to be called before + * the kernel virtual mapping is activated. + */ +#define ENDPIPROC(x) \ + .globl __pi_##x; \ + .type __pi_##x, %function; \ + .set __pi_##x, x; \ + .size __pi_##x, . - x; \ + ENDPROC(x) + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S index 8636b7549163..4444c1d25f4b 100644 --- a/arch/arm64/lib/memchr.S +++ b/arch/arm64/lib/memchr.S @@ -41,4 +41,4 @@ ENTRY(memchr) ret 2: mov x0, #0 ret -ENDPROC(memchr) +ENDPIPROC(memchr) diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S index 6ea0776ba6de..ffbdec00327d 100644 --- a/arch/arm64/lib/memcmp.S +++ b/arch/arm64/lib/memcmp.S @@ -255,4 +255,4 @@ CPU_LE( rev data2, data2 ) .Lret0: mov result, #0 ret -ENDPROC(memcmp) +ENDPIPROC(memcmp) diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S index 173a1aace9bb..36a6a62cf263 100644 --- a/arch/arm64/lib/memcpy.S +++ b/arch/arm64/lib/memcpy.S @@ -71,4 +71,4 @@ ENTRY(memcpy) #include "copy_template.S" ret -ENDPROC(memcpy) +ENDPIPROC(memcpy) diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S index 57b19ea2dad4..68e2f2035e23 100644 --- a/arch/arm64/lib/memmove.S +++ b/arch/arm64/lib/memmove.S @@ -194,4 +194,4 @@ ENTRY(memmove) tst count, #0x3f b.ne .Ltail63 ret -ENDPROC(memmove) +ENDPIPROC(memmove) diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S index 7c72dfd36b63..29f405f08792 100644 --- a/arch/arm64/lib/memset.S +++ b/arch/arm64/lib/memset.S @@ -213,4 +213,4 @@ ENTRY(memset) ands count, count, zva_bits_x b.ne .Ltail_maybe_long ret -ENDPROC(memset) +ENDPIPROC(memset) diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S index 42f828b06c59..471fe61760ef 100644 --- a/arch/arm64/lib/strcmp.S +++ b/arch/arm64/lib/strcmp.S @@ -231,4 +231,4 @@ CPU_BE( orr syndrome, diff, has_nul ) lsr data1, data1, #56 sub result, data1, data2, lsr #56 ret -ENDPROC(strcmp) +ENDPIPROC(strcmp) diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S index 987b68b9ce44..55ccc8e24c08 100644 --- a/arch/arm64/lib/strlen.S +++ b/arch/arm64/lib/strlen.S @@ -123,4 +123,4 @@ CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ csinv data1, data1, xzr, le csel data2, data2, data2a, le b .Lrealigned -ENDPROC(strlen) +ENDPIPROC(strlen) diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S index 0224cf5a5533..e267044761c6 100644 --- a/arch/arm64/lib/strncmp.S +++ b/arch/arm64/lib/strncmp.S @@ -307,4 +307,4 @@ CPU_BE( orr syndrome, diff, has_nul ) .Lret0: mov result, #0 ret -ENDPROC(strncmp) +ENDPIPROC(strncmp) diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index eb48d5df4a0f..cfa44a6adc0a 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -98,7 +98,7 @@ ENTRY(__flush_dcache_area) b.lo 1b dsb sy ret -ENDPROC(__flush_dcache_area) +ENDPIPROC(__flush_dcache_area) /* * __inval_cache_range(start, end) @@ -131,7 +131,7 @@ __dma_inv_range: b.lo 2b dsb sy ret -ENDPROC(__inval_cache_range) +ENDPIPROC(__inval_cache_range) ENDPROC(__dma_inv_range) /* @@ -171,7 +171,7 @@ ENTRY(__dma_flush_range) b.lo 1b dsb sy ret -ENDPROC(__dma_flush_range) +ENDPIPROC(__dma_flush_range) /* * __dma_map_area(start, size, dir) @@ -184,7 +184,7 @@ ENTRY(__dma_map_area) cmp w2, #DMA_FROM_DEVICE b.eq __dma_inv_range b __dma_clean_range -ENDPROC(__dma_map_area) +ENDPIPROC(__dma_map_area) /* * __dma_unmap_area(start, size, dir) @@ -197,4 +197,4 @@ ENTRY(__dma_unmap_area) cmp w2, #DMA_TO_DEVICE b.ne __dma_inv_range ret -ENDPROC(__dma_unmap_area) +ENDPIPROC(__dma_unmap_area) -- cgit v1.2.3 From fd2203dd3556f6553231fa026060793e67a25ce6 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Mon, 12 Oct 2015 18:52:57 +0300 Subject: arm64: move PGD_SIZE definition to pgalloc.h This will be used by KASAN latter. Signed-off-by: Andrey Ryabinin Acked-by: Catalin Marinas Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgalloc.h | 1 + arch/arm64/mm/pgd.c | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 76420568d66a..c15053902942 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -27,6 +27,7 @@ #define check_pgt_cache() do { } while (0) #define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 71ca104f97bd..cb3ba1b812e7 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -28,8 +28,6 @@ #include "mm.h" -#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) - static struct kmem_cache *pgd_cache; pgd_t *pgd_alloc(struct mm_struct *mm) -- cgit v1.2.3 From 39d114ddc68223022c12ae3a1573912bc4b585e5 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Mon, 12 Oct 2015 18:52:58 +0300 Subject: arm64: add KASAN support This patch adds arch specific code for kernel address sanitizer (see Documentation/kasan.txt). 1/8 of kernel addresses reserved for shadow memory. There was no big enough hole for this, so virtual addresses for shadow were stolen from vmalloc area. At early boot stage the whole shadow region populated with just one physical page (kasan_zero_page). Later, this page reused as readonly zero shadow for some memory that KASan currently don't track (vmalloc). After mapping the physical memory, pages for shadow memory are allocated and mapped. Functions like memset/memmove/memcpy do a lot of memory accesses. If bad pointer passed to one of these function it is important to catch this. Compiler's instrumentation cannot do this since these functions are written in assembly. KASan replaces memory functions with manually instrumented variants. Original functions declared as weak symbols so strong definitions in mm/kasan/kasan.c could replace them. Original functions have aliases with '__' prefix in name, so we could call non-instrumented variant if needed. Some files built without kasan instrumentation (e.g. mm/slub.c). Original mem* function replaced (via #define) with prefixed variants to disable memory access checks for such files. Signed-off-by: Andrey Ryabinin Tested-by: Linus Walleij Reviewed-by: Catalin Marinas Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 1 + arch/arm64/Makefile | 7 ++ arch/arm64/include/asm/kasan.h | 36 +++++++++ arch/arm64/include/asm/pgtable.h | 7 ++ arch/arm64/include/asm/string.h | 16 ++++ arch/arm64/kernel/Makefile | 2 + arch/arm64/kernel/arm64ksyms.c | 3 + arch/arm64/kernel/head.S | 3 + arch/arm64/kernel/image.h | 6 ++ arch/arm64/kernel/module.c | 16 +++- arch/arm64/kernel/setup.c | 4 + arch/arm64/lib/memcpy.S | 3 + arch/arm64/lib/memmove.S | 7 +- arch/arm64/lib/memset.S | 3 + arch/arm64/mm/Makefile | 3 + arch/arm64/mm/kasan_init.c | 165 +++++++++++++++++++++++++++++++++++++++ drivers/firmware/efi/Makefile | 8 ++ scripts/Makefile.kasan | 4 +- 18 files changed, 288 insertions(+), 6 deletions(-) create mode 100644 arch/arm64/include/asm/kasan.h create mode 100644 arch/arm64/mm/kasan_init.c (limited to 'arch/arm64/mm') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1b35bdbd5d74..2782c1189208 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -48,6 +48,7 @@ config ARM64 select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_BITREVERSE select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index f9914d7c1bb0..f41c6761ec36 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -55,6 +55,13 @@ else TEXT_OFFSET := 0x00080000 endif +# KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - 3)) - (1 << 61) +# in 32-bit arithmetic +KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \ + (0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 32))) \ + + (1 << ($(CONFIG_ARM64_VA_BITS) - 32 - 3)) \ + - (1 << (64 - 32 - 3)) )) ) + export TEXT_OFFSET GZFLAGS core-y += arch/arm64/kernel/ arch/arm64/mm/ diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h new file mode 100644 index 000000000000..71dfe14acdca --- /dev/null +++ b/arch/arm64/include/asm/kasan.h @@ -0,0 +1,36 @@ +#ifndef __ASM_KASAN_H +#define __ASM_KASAN_H + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_KASAN + +#include + +/* + * KASAN_SHADOW_START: beginning of the kernel virtual addresses. + * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/8 of kernel virtual addresses. + */ +#define KASAN_SHADOW_START (VA_START) +#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1UL << (VA_BITS - 3))) + +/* + * This value is used to map an address to the corresponding shadow + * address by the following formula: + * shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET; + * + * (1 << 61) shadow addresses - [KASAN_SHADOW_OFFSET,KASAN_SHADOW_END] + * cover all 64-bits of virtual addresses. So KASAN_SHADOW_OFFSET + * should satisfy the following equation: + * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - (1ULL << 61) + */ +#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << (64 - 3))) + +void kasan_init(void); + +#else +static inline void kasan_init(void) { } +#endif + +#endif +#endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 3f481ef42c07..e3b515fbf0c2 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -41,7 +41,14 @@ * fixed mappings and modules */ #define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) + +#ifndef CONFIG_KASAN #define VMALLOC_START (VA_START) +#else +#include +#define VMALLOC_START (KASAN_SHADOW_END + SZ_64K) +#endif + #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) #define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index 64d2d4884a9d..2eb714c4639f 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -36,17 +36,33 @@ extern __kernel_size_t strnlen(const char *, __kernel_size_t); #define __HAVE_ARCH_MEMCPY extern void *memcpy(void *, const void *, __kernel_size_t); +extern void *__memcpy(void *, const void *, __kernel_size_t); #define __HAVE_ARCH_MEMMOVE extern void *memmove(void *, const void *, __kernel_size_t); +extern void *__memmove(void *, const void *, __kernel_size_t); #define __HAVE_ARCH_MEMCHR extern void *memchr(const void *, int, __kernel_size_t); #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, __kernel_size_t); +extern void *__memset(void *, int, __kernel_size_t); #define __HAVE_ARCH_MEMCMP extern int memcmp(const void *, const void *, size_t); + +#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) + +/* + * For files that are not instrumented (e.g. mm/slub.c) we + * should use not instrumented version of mem* functions. + */ + +#define memcpy(dst, src, len) __memcpy(dst, src, len) +#define memmove(dst, src, len) __memmove(dst, src, len) +#define memset(s, c, n) __memset(s, c, n) +#endif + #endif diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 7b17f6245f1e..1b6bda2ff102 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -7,6 +7,8 @@ AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) CFLAGS_armv8_deprecated.o := -I$(src) +KASAN_SANITIZE_efi-stub.o := n + CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_insn.o = -pg CFLAGS_REMOVE_return_address.o = -pg diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index a85843ddbde8..3b6d8cc9dfe0 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -51,6 +51,9 @@ EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(__memset); +EXPORT_SYMBOL(__memcpy); +EXPORT_SYMBOL(__memmove); EXPORT_SYMBOL(memchr); EXPORT_SYMBOL(memcmp); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 28a81e948df9..2a8c1d5b3fae 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -444,6 +444,9 @@ __mmap_switched: str_l x21, __fdt_pointer, x5 // Save FDT pointer str_l x24, memstart_addr, x6 // Save PHYS_OFFSET mov x29, #0 +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif b start_kernel ENDPROC(__mmap_switched) diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index e083af0dd546..6eb8fee93321 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -80,6 +80,12 @@ __efistub_strcmp = __pi_strcmp; __efistub_strncmp = __pi_strncmp; __efistub___flush_dcache_area = __pi___flush_dcache_area; +#ifdef CONFIG_KASAN +__efistub___memcpy = __pi_memcpy; +__efistub___memmove = __pi_memmove; +__efistub___memset = __pi_memset; +#endif + __efistub__text = _text; __efistub__end = _end; __efistub__edata = _edata; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 876eb8df50bf..f4bc779e62e8 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -34,9 +35,18 @@ void *module_alloc(unsigned long size) { - return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, 0, - NUMA_NO_NODE, __builtin_return_address(0)); + void *p; + + p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, 0, + NUMA_NO_NODE, __builtin_return_address(0)); + + if (p && (kasan_module_alloc(p, size) < 0)) { + vfree(p); + return NULL; + } + + return p; } enum aarch64_reloc_op { diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 6bab21f84a9f..79df79a2ea61 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include #include @@ -434,6 +435,9 @@ void __init setup_arch(char **cmdline_p) paging_init(); relocate_initrd(); + + kasan_init(); + request_standard_resources(); early_ioremap_reset(); diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S index 36a6a62cf263..67613937711f 100644 --- a/arch/arm64/lib/memcpy.S +++ b/arch/arm64/lib/memcpy.S @@ -68,7 +68,10 @@ stp \ptr, \regB, [\regC], \val .endm + .weak memcpy +ENTRY(__memcpy) ENTRY(memcpy) #include "copy_template.S" ret ENDPIPROC(memcpy) +ENDPROC(__memcpy) diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S index 68e2f2035e23..a5a4459013b1 100644 --- a/arch/arm64/lib/memmove.S +++ b/arch/arm64/lib/memmove.S @@ -57,12 +57,14 @@ C_h .req x12 D_l .req x13 D_h .req x14 + .weak memmove +ENTRY(__memmove) ENTRY(memmove) cmp dstin, src - b.lo memcpy + b.lo __memcpy add tmp1, src, count cmp dstin, tmp1 - b.hs memcpy /* No overlap. */ + b.hs __memcpy /* No overlap. */ add dst, dstin, count add src, src, count @@ -195,3 +197,4 @@ ENTRY(memmove) b.ne .Ltail63 ret ENDPIPROC(memmove) +ENDPROC(__memmove) diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S index 29f405f08792..f2670a9f218c 100644 --- a/arch/arm64/lib/memset.S +++ b/arch/arm64/lib/memset.S @@ -54,6 +54,8 @@ dst .req x8 tmp3w .req w9 tmp3 .req x9 + .weak memset +ENTRY(__memset) ENTRY(memset) mov dst, dstin /* Preserve return value. */ and A_lw, val, #255 @@ -214,3 +216,4 @@ ENTRY(memset) b.ne .Ltail_maybe_long ret ENDPIPROC(memset) +ENDPROC(__memset) diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 773d37a14039..57f57fde5722 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -4,3 +4,6 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ context.o proc.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_ARM64_PTDUMP) += dump.o + +obj-$(CONFIG_KASAN) += kasan_init.o +KASAN_SANITIZE_kasan_init.o := n diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c new file mode 100644 index 000000000000..b6a92f5dd568 --- /dev/null +++ b/arch/arm64/mm/kasan_init.c @@ -0,0 +1,165 @@ +/* + * This file contains kasan initialization code for ARM64. + * + * Copyright (c) 2015 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#define pr_fmt(fmt) "kasan: " fmt +#include +#include +#include +#include + +#include +#include +#include +#include + +static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); + +static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr, + unsigned long end) +{ + pte_t *pte; + unsigned long next; + + if (pmd_none(*pmd)) + pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); + + pte = pte_offset_kernel(pmd, addr); + do { + next = addr + PAGE_SIZE; + set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page), + PAGE_KERNEL)); + } while (pte++, addr = next, addr != end && pte_none(*pte)); +} + +static void __init kasan_early_pmd_populate(pud_t *pud, + unsigned long addr, + unsigned long end) +{ + pmd_t *pmd; + unsigned long next; + + if (pud_none(*pud)) + pud_populate(&init_mm, pud, kasan_zero_pmd); + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + kasan_early_pte_populate(pmd, addr, next); + } while (pmd++, addr = next, addr != end && pmd_none(*pmd)); +} + +static void __init kasan_early_pud_populate(pgd_t *pgd, + unsigned long addr, + unsigned long end) +{ + pud_t *pud; + unsigned long next; + + if (pgd_none(*pgd)) + pgd_populate(&init_mm, pgd, kasan_zero_pud); + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + kasan_early_pmd_populate(pud, addr, next); + } while (pud++, addr = next, addr != end && pud_none(*pud)); +} + +static void __init kasan_map_early_shadow(void) +{ + unsigned long addr = KASAN_SHADOW_START; + unsigned long end = KASAN_SHADOW_END; + unsigned long next; + pgd_t *pgd; + + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + kasan_early_pud_populate(pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +void __init kasan_early_init(void) +{ + BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << 61)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); + kasan_map_early_shadow(); +} + +static void __init clear_pgds(unsigned long start, + unsigned long end) +{ + /* + * Remove references to kasan page tables from + * swapper_pg_dir. pgd_clear() can't be used + * here because it's nop on 2,3-level pagetable setups + */ + for (; start < end; start += PGDIR_SIZE) + set_pgd(pgd_offset_k(start), __pgd(0)); +} + +static void __init cpu_set_ttbr1(unsigned long ttbr1) +{ + asm( + " msr ttbr1_el1, %0\n" + " isb" + : + : "r" (ttbr1)); +} + +void __init kasan_init(void) +{ + struct memblock_region *reg; + + /* + * We are going to perform proper setup of shadow memory. + * At first we should unmap early shadow (clear_pgds() call bellow). + * However, instrumented code couldn't execute without shadow memory. + * tmp_pg_dir used to keep early shadow mapped until full shadow + * setup will be finished. + */ + memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); + cpu_set_ttbr1(__pa(tmp_pg_dir)); + flush_tlb_all(); + + clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + + kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, + kasan_mem_to_shadow((void *)MODULES_VADDR)); + + for_each_memblock(memory, reg) { + void *start = (void *)__phys_to_virt(reg->base); + void *end = (void *)__phys_to_virt(reg->base + reg->size); + + if (start >= end) + break; + + /* + * end + 1 here is intentional. We check several shadow bytes in + * advance to slightly speed up fastpath. In some rare cases + * we could cross boundary of mapped shadow, so we just map + * some more here. + */ + vmemmap_populate((unsigned long)kasan_mem_to_shadow(start), + (unsigned long)kasan_mem_to_shadow(end) + 1, + pfn_to_nid(virt_to_pfn(start))); + } + + memset(kasan_zero_page, 0, PAGE_SIZE); + cpu_set_ttbr1(__pa(swapper_pg_dir)); + flush_tlb_all(); + + /* At this point kasan is fully initialized. Enable error messages */ + init_task.kasan_depth = 0; + pr_info("KernelAddressSanitizer initialized\n"); +} diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index 6fd3da938717..413fcf2970c0 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -1,6 +1,14 @@ # # Makefile for linux kernel # + +# +# ARM64 maps efi runtime services in userspace addresses +# which don't have KASAN shadow. So dereference of these addresses +# in efi_call_virt() will cause crash if this code instrumented. +# +KASAN_SANITIZE_runtime-wrappers.o := n + obj-$(CONFIG_EFI) += efi.o vars.o reboot.o obj-$(CONFIG_EFI_VARS) += efivars.o obj-$(CONFIG_EFI_ESRT) += esrt.o diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 3f874d24234f..37323b0df374 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -5,10 +5,12 @@ else call_threshold := 0 endif +KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET) + CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address CFLAGS_KASAN := $(call cc-option, -fsanitize=kernel-address \ - -fasan-shadow-offset=$(CONFIG_KASAN_SHADOW_OFFSET) \ + -fasan-shadow-offset=$(KASAN_SHADOW_OFFSET) \ --param asan-stack=1 --param asan-globals=1 \ --param asan-instrumentation-with-call-threshold=$(call_threshold)) -- cgit v1.2.3 From ee7f881b59de4e0e0be250fd0c5d4ade3e30ec34 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 12 Oct 2015 18:52:59 +0300 Subject: ARM64: kasan: print memory assignment This prints out the virtual memory assigned to KASan in the boot crawl along with other memory assignments, if and only if KASan is activated. Example dmesg from the Juno Development board: Memory: 1691156K/2080768K available (5465K kernel code, 444K rwdata, 2160K rodata, 340K init, 217K bss, 373228K reserved, 16384K cma-reserved) Virtual kernel memory layout: kasan : 0xffffff8000000000 - 0xffffff9000000000 ( 64 GB) vmalloc : 0xffffff9000000000 - 0xffffffbdbfff0000 ( 182 GB) vmemmap : 0xffffffbdc0000000 - 0xffffffbfc0000000 ( 8 GB maximum) 0xffffffbdc2000000 - 0xffffffbdc3fc0000 ( 31 MB actual) fixed : 0xffffffbffabfd000 - 0xffffffbffac00000 ( 12 KB) PCI I/O : 0xffffffbffae00000 - 0xffffffbffbe00000 ( 16 MB) modules : 0xffffffbffc000000 - 0xffffffc000000000 ( 64 MB) memory : 0xffffffc000000000 - 0xffffffc07f000000 ( 2032 MB) .init : 0xffffffc0007f5000 - 0xffffffc00084a000 ( 340 KB) .text : 0xffffffc000080000 - 0xffffffc0007f45b4 ( 7634 KB) .data : 0xffffffc000850000 - 0xffffffc0008bf200 ( 445 KB) Signed-off-by: Linus Walleij Signed-off-by: Andrey Ryabinin Acked-by: Catalin Marinas Signed-off-by: Catalin Marinas --- arch/arm64/mm/init.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index f5c0680d17d9..7a1f9a05dc82 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -298,6 +298,9 @@ void __init mem_init(void) #define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K) pr_notice("Virtual kernel memory layout:\n" +#ifdef CONFIG_KASAN + " kasan : 0x%16lx - 0x%16lx (%6ld GB)\n" +#endif " vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n" #ifdef CONFIG_SPARSEMEM_VMEMMAP " vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n" @@ -310,6 +313,9 @@ void __init mem_init(void) " .init : 0x%p" " - 0x%p" " (%6ld KB)\n" " .text : 0x%p" " - 0x%p" " (%6ld KB)\n" " .data : 0x%p" " - 0x%p" " (%6ld KB)\n", +#ifdef CONFIG_KASAN + MLG(KASAN_SHADOW_START, KASAN_SHADOW_END), +#endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP MLG((unsigned long)vmemmap, -- cgit v1.2.3 From 83040123fde42ec532d3b632efb5f7f84024e61d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 13 Oct 2015 14:01:06 +0100 Subject: arm64: kasan: fix issues reported by sparse Sparse reports some new issues introduced by the kasan patches: arch/arm64/mm/kasan_init.c:91:13: warning: no previous prototype for 'kasan_early_init' [-Wmissing-prototypes] void __init kasan_early_init(void) ^ arch/arm64/mm/kasan_init.c:91:13: warning: symbol 'kasan_early_init' was not declared. Should it be static? [sparse] This patch resolves the problem by adding a prototype for kasan_early_init and marking the function as asmlinkage, since it's only called from head.S. Signed-off-by: Will Deacon Acked-by: Andrey Ryabinin Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/kasan.h | 2 ++ arch/arm64/mm/kasan_init.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index 71dfe14acdca..2774fa384c47 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -5,6 +5,7 @@ #ifdef CONFIG_KASAN +#include #include /* @@ -27,6 +28,7 @@ #define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << (64 - 3))) void kasan_init(void); +asmlinkage void kasan_early_init(void); #else static inline void kasan_init(void) { } diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index b6a92f5dd568..cf038c7d9fa9 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -88,7 +88,7 @@ static void __init kasan_map_early_shadow(void) } while (pgd++, addr = next, addr != end); } -void __init kasan_early_init(void) +asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << 61)); BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); -- cgit v1.2.3 From b433dce056d3814dc4b33e5a8a533d6401ffcfb0 Mon Sep 17 00:00:00 2001 From: "Suzuki K. Poulose" Date: Mon, 19 Oct 2015 14:19:28 +0100 Subject: arm64: Handle section maps for swapper/idmap We use section maps with 4K page size to create the swapper/idmaps. So far we have used !64K or 4K checks to handle the case where we use the section maps. This patch adds a new symbol, ARM64_SWAPPER_USES_SECTION_MAPS, to handle cases where we use section maps, instead of using the page size symbols. Cc: Will Deacon Signed-off-by: Suzuki K. Poulose Reviewed-by: Ard Biesheuvel Acked-by: Mark Rutland Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/kernel-pgtable.h | 37 ++++++++++++----- arch/arm64/mm/mmu.c | 74 +++++++++++++++------------------ 2 files changed, 59 insertions(+), 52 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 3c92fa7bad2b..4e08faabd9e4 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -19,6 +19,19 @@ #ifndef __ASM_KERNEL_PGTABLE_H #define __ASM_KERNEL_PGTABLE_H + +/* + * The linear mapping and the start of memory are both 2M aligned (per + * the arm64 booting.txt requirements). Hence we can use section mapping + * with 4K (section size = 2M) but not with 16K (section size = 32M) or + * 64K (section size = 512M). + */ +#ifdef CONFIG_ARM64_4K_PAGES +#define ARM64_SWAPPER_USES_SECTION_MAPS 1 +#else +#define ARM64_SWAPPER_USES_SECTION_MAPS 0 +#endif + /* * The idmap and swapper page tables need some space reserved in the kernel * image. Both require pgd, pud (4 levels only) and pmd tables to (section) @@ -28,26 +41,28 @@ * could be increased on the fly if system RAM is out of reach for the default * VA range, so 3 pages are reserved in all cases. */ -#ifdef CONFIG_ARM64_64K_PAGES -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) -#else +#if ARM64_SWAPPER_USES_SECTION_MAPS #define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1) +#else +#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) #endif #define SWAPPER_DIR_SIZE (SWAPPER_PGTABLE_LEVELS * PAGE_SIZE) #define IDMAP_DIR_SIZE (3 * PAGE_SIZE) /* Initial memory map size */ -#ifdef CONFIG_ARM64_64K_PAGES -#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT -#define SWAPPER_BLOCK_SIZE PAGE_SIZE -#define SWAPPER_TABLE_SHIFT PMD_SHIFT -#else +#if ARM64_SWAPPER_USES_SECTION_MAPS #define SWAPPER_BLOCK_SHIFT SECTION_SHIFT #define SWAPPER_BLOCK_SIZE SECTION_SIZE #define SWAPPER_TABLE_SHIFT PUD_SHIFT +#else +#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT +#define SWAPPER_BLOCK_SIZE PAGE_SIZE +#define SWAPPER_TABLE_SHIFT PMD_SHIFT #endif +/* The size of the initial kernel direct mapping */ +#define SWAPPER_INIT_MAP_SIZE (_AC(1, UL) << SWAPPER_TABLE_SHIFT) /* * Initial memory map attributes. @@ -55,10 +70,10 @@ #define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#ifdef CONFIG_ARM64_64K_PAGES -#define SWAPPER_MM_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS) -#else +#if ARM64_SWAPPER_USES_SECTION_MAPS #define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS) +#else +#define SWAPPER_MM_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS) #endif diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index eed6d52f5e54..c2fa6b56613c 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -32,6 +32,7 @@ #include #include +#include #include #include #include @@ -406,14 +407,11 @@ static void __init map_mem(void) * memory addressable from the initial direct kernel mapping. * * The initial direct kernel mapping, located at swapper_pg_dir, gives - * us PUD_SIZE (4K pages) or PMD_SIZE (64K pages) memory starting from - * PHYS_OFFSET (which must be aligned to 2MB as per - * Documentation/arm64/booting.txt). + * us PUD_SIZE (with SECTION maps) or PMD_SIZE (without SECTION maps, + * memory starting from PHYS_OFFSET (which must be aligned to 2MB as + * per Documentation/arm64/booting.txt). */ - if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) - limit = PHYS_OFFSET + PMD_SIZE; - else - limit = PHYS_OFFSET + PUD_SIZE; + limit = PHYS_OFFSET + SWAPPER_INIT_MAP_SIZE; memblock_set_current_limit(limit); /* map all the memory banks */ @@ -424,21 +422,24 @@ static void __init map_mem(void) if (start >= end) break; -#ifndef CONFIG_ARM64_64K_PAGES - /* - * For the first memory bank align the start address and - * current memblock limit to prevent create_mapping() from - * allocating pte page tables from unmapped memory. - * When 64K pages are enabled, the pte page table for the - * first PGDIR_SIZE is already present in swapper_pg_dir. - */ - if (start < limit) - start = ALIGN(start, PMD_SIZE); - if (end < limit) { - limit = end & PMD_MASK; - memblock_set_current_limit(limit); + if (ARM64_SWAPPER_USES_SECTION_MAPS) { + /* + * For the first memory bank align the start address and + * current memblock limit to prevent create_mapping() from + * allocating pte page tables from unmapped memory. With + * the section maps, if the first block doesn't end on section + * size boundary, create_mapping() will try to allocate a pte + * page, which may be returned from an unmapped area. + * When section maps are not used, the pte page table for the + * current limit is already present in swapper_pg_dir. + */ + if (start < limit) + start = ALIGN(start, SECTION_SIZE); + if (end < limit) { + limit = end & SECTION_MASK; + memblock_set_current_limit(limit); + } } -#endif __map_memblock(start, end); } @@ -551,12 +552,12 @@ int kern_addr_valid(unsigned long addr) return pfn_valid(pte_pfn(*pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP -#ifdef CONFIG_ARM64_64K_PAGES +#if !ARM64_SWAPPER_USES_SECTION_MAPS int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { return vmemmap_populate_basepages(start, end, node); } -#else /* !CONFIG_ARM64_64K_PAGES */ +#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { unsigned long addr = start; @@ -691,7 +692,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); pgprot_t prot = PAGE_KERNEL | PTE_RDONLY; - int granularity, size, offset; + int size, offset; void *dt_virt; /* @@ -717,24 +718,15 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) */ BUILD_BUG_ON(dt_virt_base % SZ_2M); - if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) { - BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PMD_SHIFT != - __fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT); - - granularity = PAGE_SIZE; - } else { - BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PUD_SHIFT != - __fix_to_virt(FIX_BTMAP_BEGIN) >> PUD_SHIFT); - - granularity = PMD_SIZE; - } + BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> SWAPPER_TABLE_SHIFT != + __fix_to_virt(FIX_BTMAP_BEGIN) >> SWAPPER_TABLE_SHIFT); - offset = dt_phys % granularity; + offset = dt_phys % SWAPPER_BLOCK_SIZE; dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ - create_mapping(round_down(dt_phys, granularity), dt_virt_base, - granularity, prot); + create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, + SWAPPER_BLOCK_SIZE, prot); if (fdt_check_header(dt_virt) != 0) return NULL; @@ -743,9 +735,9 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) if (size > MAX_FDT_SIZE) return NULL; - if (offset + size > granularity) - create_mapping(round_down(dt_phys, granularity), dt_virt_base, - round_up(offset + size, granularity), prot); + if (offset + size > SWAPPER_BLOCK_SIZE) + create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, + round_up(offset + size, SWAPPER_BLOCK_SIZE), prot); memblock_reserve(dt_phys, size); -- cgit v1.2.3 From 44eaacf1b8999b15cec89bd9d9cd989da4798d53 Mon Sep 17 00:00:00 2001 From: "Suzuki K. Poulose" Date: Mon, 19 Oct 2015 14:19:37 +0100 Subject: arm64: Add 16K page size support This patch turns on the 16K page support in the kernel. We support 48bit VA (4 level page tables) and 47bit VA (3 level page tables). With 16K we can map 128 entries using contiguous bit hint at level 3 to map 2M using single TLB entry. TODO: 16K supports 32 contiguous entries at level 2 to get us 1G(which is not yet supported by the infrastructure). That should be a separate patch altogether. Cc: Will Deacon Cc: Jeremy Linton Cc: Marc Zyngier Cc: Christoffer Dall Cc: Steve Capper Signed-off-by: Suzuki K. Poulose Reviewed-by: Ard Biesheuvel Tested-by: Ard Biesheuvel Acked-by: Mark Rutland Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 42 +++++++++++++++++++++++++++++++----- arch/arm64/include/asm/page.h | 3 +++ arch/arm64/include/asm/sysreg.h | 3 +++ arch/arm64/include/asm/thread_info.h | 2 ++ arch/arm64/kvm/Kconfig | 3 +++ arch/arm64/mm/proc.S | 4 +++- 6 files changed, 51 insertions(+), 6 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 13b51a0c4e7f..854166422c42 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -173,7 +173,8 @@ config PGTABLE_LEVELS default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42 default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48 default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39 - default 4 if ARM64_4K_PAGES && ARM64_VA_BITS_48 + default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47 + default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48 source "init/Kconfig" @@ -363,6 +364,13 @@ config ARM64_4K_PAGES help This feature enables 4KB pages support. +config ARM64_16K_PAGES + bool "16KB" + help + The system will use 16KB pages support. AArch32 emulation + requires applications compiled with 16K (or a multiple of 16K) + aligned segments. + config ARM64_64K_PAGES bool "64KB" help @@ -376,6 +384,7 @@ endchoice choice prompt "Virtual address space size" default ARM64_VA_BITS_39 if ARM64_4K_PAGES + default ARM64_VA_BITS_47 if ARM64_16K_PAGES default ARM64_VA_BITS_42 if ARM64_64K_PAGES help Allows choosing one of multiple possible virtual address @@ -390,6 +399,10 @@ config ARM64_VA_BITS_42 bool "42-bit" depends on ARM64_64K_PAGES +config ARM64_VA_BITS_47 + bool "47-bit" + depends on ARM64_16K_PAGES + config ARM64_VA_BITS_48 bool "48-bit" @@ -399,6 +412,7 @@ config ARM64_VA_BITS int default 39 if ARM64_VA_BITS_39 default 42 if ARM64_VA_BITS_42 + default 47 if ARM64_VA_BITS_47 default 48 if ARM64_VA_BITS_48 config CPU_BIG_ENDIAN @@ -466,7 +480,7 @@ config ARCH_WANT_GENERAL_HUGETLB def_bool y config ARCH_WANT_HUGE_PMD_SHARE - def_bool y if ARM64_4K_PAGES + def_bool y if ARM64_4K_PAGES || ARM64_16K_PAGES config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y @@ -503,7 +517,25 @@ config XEN config FORCE_MAX_ZONEORDER int default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE) + default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE) default "11" + help + The kernel memory allocator divides physically contiguous memory + blocks into "zones", where each zone is a power of two number of + pages. This option selects the largest power of two that the kernel + keeps in the memory allocator. If you need to allocate very large + blocks of physically contiguous memory, then you may need to + increase this value. + + This config option is actually maximum order plus one. For example, + a value of 11 means that the largest free memory block is 2^10 pages. + + We make sure that we can allocate upto a HugePage size for each configuration. + Hence we have : + MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2 + + However for 4K, we choose a higher default value, 11 as opposed to 10, giving us + 4M allocations matching the default size used by generic code. menuconfig ARMV8_DEPRECATED bool "Emulate deprecated/obsolete ARMv8 instructions" @@ -689,9 +721,9 @@ config COMPAT the user helper functions, VFP support and the ptrace interface are handled appropriately by the kernel. - If you also enabled CONFIG_ARM64_64K_PAGES, please be aware that you - will only be able to execute AArch32 binaries that were compiled with - 64k aligned segments. + If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware + that you will only be able to execute AArch32 binaries that were compiled + with page size aligned segments. If you want to execute 32-bit userspace applications, say Y. diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index da3235494ffd..9b2f5a9d019d 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -24,6 +24,9 @@ #ifdef CONFIG_ARM64_64K_PAGES #define PAGE_SHIFT 16 #define CONT_SHIFT 5 +#elif defined(CONFIG_ARM64_16K_PAGES) +#define PAGE_SHIFT 14 +#define CONT_SHIFT 7 #else #define PAGE_SHIFT 12 #define CONT_SHIFT 4 diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index d59cb231a673..4b57e1080538 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -59,6 +59,9 @@ #if defined(CONFIG_ARM64_4K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT #define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN4_SUPPORTED +#elif defined(CONFIG_ARM64_16K_PAGES) +#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT +#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN16_SUPPORTED #elif defined(CONFIG_ARM64_64K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT #define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN64_SUPPORTED diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 5eac6a2300af..90c7ff233735 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -25,6 +25,8 @@ #ifdef CONFIG_ARM64_4K_PAGES #define THREAD_SIZE_ORDER 2 +#elif defined(CONFIG_ARM64_16K_PAGES) +#define THREAD_SIZE_ORDER 0 #endif #define THREAD_SIZE 16384 diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 5c7e920e4861..6a7d5cd772e6 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -19,6 +19,7 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" depends on OF + depends on !ARM64_16K_PAGES select MMU_NOTIFIER select PREEMPT_NOTIFIERS select ANON_INODES @@ -33,6 +34,8 @@ config KVM select HAVE_KVM_IRQFD ---help--- Support hosting virtualized guest machines. + We don't support KVM with 16K page tables yet, due to the multiple + levels of fake page tables. If unsure, say N. diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 91cb2eaac256..3a4b8b19978b 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -30,7 +30,9 @@ #ifdef CONFIG_ARM64_64K_PAGES #define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K -#else +#elif defined(CONFIG_ARM64_16K_PAGES) +#define TCR_TG_FLAGS TCR_TG0_16K | TCR_TG1_16K +#else /* CONFIG_ARM64_4K_PAGES */ #define TCR_TG_FLAGS TCR_TG0_4K | TCR_TG1_4K #endif -- cgit v1.2.3 From dbb4e152b8da1f977d9d8cd7e494ab4ee3622f72 Mon Sep 17 00:00:00 2001 From: "Suzuki K. Poulose" Date: Mon, 19 Oct 2015 14:24:50 +0100 Subject: arm64: Delay cpu feature capability checks At the moment we run through the arm64_features capability list for each CPU and set the capability if one of the CPU supports it. This could be problematic in a heterogeneous system with differing capabilities. Delay the CPU feature checks until all the enabled CPUs are up(i.e, smp_cpus_done(), so that we can make better decisions based on the overall system capability. Once we decide and advertise the capabilities the alternatives can be applied. From this state, we cannot roll back a feature to disabled based on the values from a new hotplugged CPU, due to the runtime patching and other reasons. So, for all new CPUs, we need to make sure that they have the established system capabilities. Failing which, we bring the CPU down, preventing it from turning online. Once the capabilities are decided, any new CPU booting up goes through verification to ensure that it has all the enabled capabilities and also invokes the respective enable() method on the CPU. The CPU errata checks are not delayed and is still executed per-CPU to detect the respective capabilities. If we ever come across a non-errata capability that needs to be checked on each-CPU, we could introduce them via a new capability table(or introduce a flag), which can be processed per CPU. The next patch will make the feature checks use the system wide safe value of a feature register. NOTE: The enable() methods associated with the capability is scheduled on all the CPUs (which is the only use case at the moment). If we need a different type of 'enable()' which only needs to be run once on any CPU, we should be able to handle that when needed. Signed-off-by: Suzuki K. Poulose Tested-by: Dave Martin [catalin.marinas@arm.com: static variable and coding style fixes] Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpufeature.h | 11 ++++- arch/arm64/include/asm/processor.h | 2 +- arch/arm64/kernel/cpufeature.c | 97 +++++++++++++++++++++++++++++++++++-- arch/arm64/kernel/cpuinfo.c | 1 - arch/arm64/kernel/smp.c | 7 +++ arch/arm64/mm/fault.c | 2 +- 6 files changed, 111 insertions(+), 9 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 12d883a067c4..1603ae84ea45 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -70,7 +70,7 @@ struct arm64_cpu_capabilities { const char *desc; u16 capability; bool (*matches)(const struct arm64_cpu_capabilities *); - void (*enable)(void); + void (*enable)(void *); /* Called on all active CPUs */ union { struct { /* To be used for erratum handling only */ u32 midr_model; @@ -140,7 +140,14 @@ void __init setup_cpu_features(void); void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, const char *info); void check_local_cpu_errata(void); -void check_local_cpu_features(void); + +#ifdef CONFIG_HOTPLUG_CPU +void verify_local_cpu_capabilities(void); +#else +static inline void verify_local_cpu_capabilities(void) +{ +} +#endif u64 read_system_reg(u32 id); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 98f32355dc97..4acb7ca94fcd 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -186,6 +186,6 @@ static inline void spin_lock_prefetch(const void *x) #endif -void cpu_enable_pan(void); +void cpu_enable_pan(void *__unused); #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 78c4cb7af20e..e002cadf84bf 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -645,19 +646,101 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, } /* - * Run through the enabled capabilities and enable() it on the CPUs + * Run through the enabled capabilities and enable() it on all active + * CPUs */ void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) { int i; + for (i = 0; caps[i].desc; i++) + if (caps[i].enable && cpus_have_cap(caps[i].capability)) + on_each_cpu(caps[i].enable, NULL, true); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Flag to indicate if we have computed the system wide + * capabilities based on the boot time active CPUs. This + * will be used to determine if a new booting CPU should + * go through the verification process to make sure that it + * supports the system capabilities, without using a hotplug + * notifier. + */ +static bool sys_caps_initialised; + +static inline void set_sys_caps_initialised(void) +{ + sys_caps_initialised = true; +} + +/* + * Park the CPU which doesn't have the capability as advertised + * by the system. + */ +static void fail_incapable_cpu(char *cap_type, + const struct arm64_cpu_capabilities *cap) +{ + int cpu = smp_processor_id(); + + pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc); + /* Mark this CPU absent */ + set_cpu_present(cpu, 0); + + /* Check if we can park ourselves */ + if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) + cpu_ops[cpu]->cpu_die(cpu); + asm( + "1: wfe\n" + " wfi\n" + " b 1b"); +} + +/* + * Run through the enabled system capabilities and enable() it on this CPU. + * The capabilities were decided based on the available CPUs at the boot time. + * Any new CPU should match the system wide status of the capability. If the + * new CPU doesn't have a capability which the system now has enabled, we + * cannot do anything to fix it up and could cause unexpected failures. So + * we park the CPU. + */ +void verify_local_cpu_capabilities(void) +{ + int i; + const struct arm64_cpu_capabilities *caps; + + /* + * If we haven't computed the system capabilities, there is nothing + * to verify. + */ + if (!sys_caps_initialised) + return; + + caps = arm64_features; for (i = 0; caps[i].desc; i++) { - if (cpus_have_cap(caps[i].capability) && caps[i].enable) - caps[i].enable(); + if (!cpus_have_cap(caps[i].capability)) + continue; + /* + * If the new CPU misses an advertised feature, we cannot proceed + * further, park the cpu. + */ + if (!caps[i].matches(&caps[i])) + fail_incapable_cpu("arm64_features", &caps[i]); + if (caps[i].enable) + caps[i].enable(NULL); } } -void check_local_cpu_features(void) +#else /* !CONFIG_HOTPLUG_CPU */ + +static inline void set_sys_caps_initialised(void) +{ +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +static void setup_feature_capabilities(void) { update_cpu_capabilities(arm64_features, "detected feature:"); enable_cpu_capabilities(arm64_features); @@ -670,6 +753,12 @@ void __init setup_cpu_features(void) u32 cwg; int cls; + /* Set the CPU feature capabilies */ + setup_feature_capabilities(); + + /* Advertise that we have computed the system capabilities */ + set_sys_caps_initialised(); + /* * Check for sane CTR_EL0.CWG value. */ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index f25869ea2646..789fbea92b79 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -229,7 +229,6 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) cpuinfo_detect_icache_policy(info); check_local_cpu_errata(); - check_local_cpu_features(); } void cpuinfo_store_cpu(void) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d1d00499f0cf..2bbdc0e4fd14 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -156,6 +156,13 @@ asmlinkage void secondary_start_kernel(void) preempt_disable(); trace_hardirqs_off(); + /* + * If the system has established the capabilities, make sure + * this CPU ticks all of those. If it doesn't, the CPU will + * fail to come online. + */ + verify_local_cpu_capabilities(); + if (cpu_ops[cpu]->cpu_postboot) cpu_ops[cpu]->cpu_postboot(); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index aba9ead1384c..066d5aea16c6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -555,7 +555,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, } #ifdef CONFIG_ARM64_PAN -void cpu_enable_pan(void) +void cpu_enable_pan(void *__unused) { config_sctlr_el1(SCTLR_EL1_SPAN, 0); } -- cgit v1.2.3 From f23bef34d34b6325916daddc4cfdeee53d5139e6 Mon Sep 17 00:00:00 2001 From: Alexander Kuleshov Date: Mon, 26 Oct 2015 17:26:57 +0600 Subject: arm64/mm: use PAGE_ALIGNED instead of IS_ALIGNED The already provides the PAGE_ALIGNED macro. Let's use this macro instead of IS_ALIGNED and passing PAGE_SIZE directly. Signed-off-by: Alexander Kuleshov Acked-by: Laura Abbott Signed-off-by: Catalin Marinas --- arch/arm64/mm/pageattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index e47ed1c5dce1..3571c7309c5e 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -45,7 +45,7 @@ static int change_memory_common(unsigned long addr, int numpages, int ret; struct page_change_data data; - if (!IS_ALIGNED(addr, PAGE_SIZE)) { + if (!PAGE_ALIGNED(addr)) { start &= PAGE_MASK; end = start + size; WARN_ON_ONCE(1); -- cgit v1.2.3 From 86a5906e4d1df1ec160fa9e18b6f2277a5216c60 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 27 Oct 2015 17:40:26 +0000 Subject: arm64: Fix build with CONFIG_ZONE_DMA=n Trying to build with CONFIG_ZONE_DMA=n leaves visible references to the now-undefined ZONE_DMA, resulting in a syntax error. Hide the references behind an #ifdef instead of using IS_ENABLED. Signed-off-by: Robin Murphy Signed-off-by: Catalin Marinas --- arch/arm64/mm/init.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 7a1f9a05dc82..17bf39ac83ba 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -86,10 +86,10 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) memset(zone_size, 0, sizeof(zone_size)); /* 4GB maximum for 32-bit only capable devices */ - if (IS_ENABLED(CONFIG_ZONE_DMA)) { - max_dma = PFN_DOWN(arm64_dma_phys_limit); - zone_size[ZONE_DMA] = max_dma - min; - } +#ifdef CONFIG_ZONE_DMA + max_dma = PFN_DOWN(arm64_dma_phys_limit); + zone_size[ZONE_DMA] = max_dma - min; +#endif zone_size[ZONE_NORMAL] = max - max_dma; memcpy(zhole_size, zone_size, sizeof(zhole_size)); @@ -101,11 +101,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (start >= max) continue; - if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) { +#ifdef CONFIG_ZONE_DMA + if (start < max_dma) { unsigned long dma_end = min(end, max_dma); zhole_size[ZONE_DMA] -= dma_end - start; } - +#endif if (end > max_dma) { unsigned long normal_end = min(end, max); unsigned long normal_start = max(start, max_dma); -- cgit v1.2.3