diff options
Diffstat (limited to 'arch/x86/mm/tlb.c')
-rw-r--r-- | arch/x86/mm/tlb.c | 137 |
1 files changed, 126 insertions, 11 deletions
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 3118392cdf75..8dcc0607f805 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -6,13 +6,14 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> -#include <linux/debugfs.h> /* * TLB flushing, formerly SMP-only @@ -28,6 +29,38 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ +/* + * We get here when we do something requiring a TLB invalidation + * but could not go invalidate all of the contexts. We do the + * necessary invalidation by clearing out the 'ctx_id' which + * forces a TLB flush when the context is loaded. + */ +void clear_asid_other(void) +{ + u16 asid; + + /* + * This is only expected to be set if we have disabled + * kernel _PAGE_GLOBAL pages. + */ + if (!static_cpu_has(X86_FEATURE_PTI)) { + WARN_ON_ONCE(1); + return; + } + + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { + /* Do not need to flush the current asid */ + if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid)) + continue; + /* + * Make sure the next time we go to switch to + * this asid, we do a flush: + */ + this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0); + } + this_cpu_write(cpu_tlbstate.invalidate_other, false); +} + atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); @@ -42,6 +75,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, return; } + if (this_cpu_read(cpu_tlbstate.invalidate_other)) + clear_asid_other(); + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) != next->context.ctx_id) @@ -65,6 +101,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, *need_flush = true; } +static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush) +{ + unsigned long new_mm_cr3; + + if (need_flush) { + invalidate_user_asid(new_asid); + new_mm_cr3 = build_cr3(pgdir, new_asid); + } else { + new_mm_cr3 = build_cr3_noflush(pgdir, new_asid); + } + + /* + * Caution: many callers of this function expect + * that load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask writes. + */ + write_cr3(new_mm_cr3); +} + void leave_mm(int cpu) { struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); @@ -97,6 +152,34 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } +static void sync_current_stack_to_mm(struct mm_struct *mm) +{ + unsigned long sp = current_stack_pointer; + pgd_t *pgd = pgd_offset(mm, sp); + + if (CONFIG_PGTABLE_LEVELS > 4) { + if (unlikely(pgd_none(*pgd))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + + set_pgd(pgd, *pgd_ref); + } + } else { + /* + * "pgd" is faked. The top level entries are "p4d"s, so sync + * the p4d. This compiles to approximately the same code as + * the 5-level case. + */ + p4d_t *p4d = p4d_offset(pgd, sp); + + if (unlikely(p4d_none(*p4d))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + p4d_t *p4d_ref = p4d_offset(pgd_ref, sp); + + set_p4d(p4d, *p4d_ref); + } + } +} + void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -128,7 +211,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) { + if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) { /* * If we were to BUG here, we'd be very likely to kill * the system so hard that we don't see the call trace. @@ -146,6 +229,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, #endif this_cpu_write(cpu_tlbstate.is_lazy, false); + /* + * The membarrier system call requires a full memory barrier and + * core serialization before returning to user-space, after + * storing to rq->curr. Writing to CR3 provides that full + * memory barrier and core serializing instruction. + */ if (real_prev == next) { VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); @@ -165,6 +254,27 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } else { u16 new_asid; bool need_flush; + u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); + + /* + * Avoid user/user BTB poisoning by flushing the branch + * predictor when switching between processes. This stops + * one process from doing Spectre-v2 attacks on another. + * + * As an optimization, flush indirect branches only when + * switching into processes that disable dumping. This + * protects high value processes like gpg, without having + * too high performance overhead. IBPB is *expensive*! + * + * This will not flush branches when switching into kernel + * threads. It will also not flush if we switch to idle + * thread and back to the same process. It will flush if we + * switch to a different non-dumpable process. + */ + if (tsk && tsk->mm && + tsk->mm->context.ctx_id != last_ctx_id && + get_dumpable(tsk->mm) != SUID_DUMP_USER) + indirect_branch_prediction_barrier(); if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* @@ -172,11 +282,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer); - pgd_t *pgd = next->pgd + index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[index]); + sync_current_stack_to_mm(next); } /* Stop remote flushes for the previous mm */ @@ -195,7 +301,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - write_cr3(build_cr3(next, new_asid)); + load_new_mm_cr3(next->pgd, new_asid, true); /* * NB: This gets called via leave_mm() in the idle path @@ -208,12 +314,20 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ - write_cr3(build_cr3_noflush(next, new_asid)); + load_new_mm_cr3(next->pgd, new_asid, false); /* See above wrt _rcuidle. */ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); } @@ -288,9 +402,10 @@ void initialize_tlbstate_and_flush(void) !(cr4_read_shadow() & X86_CR4_PCIDE)); /* Force ASID 0 and force a TLB flush. */ - write_cr3(build_cr3(mm, 0)); + write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ + this_cpu_write(cpu_tlbstate.last_ctx_id, mm->context.ctx_id); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); @@ -551,7 +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_single(addr); + __flush_tlb_one(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) |