cond_ibpb() has the necessary bits required to track the previous mm in switch_mm_irqs_off(). This can be reused for other use cases like L1D flushing on context switch.
[ tglx: Moved comment, added a separate define for state (re)initialization ] Suggested-by: Thomas Gleixner <t...@linutronix.de> Signed-off-by: Balbir Singh <sbl...@amazon.com> Signed-off-by: Thomas Gleixner <t...@linutronix.de> Link: https://lkml.kernel.org/r/20200510014803.12190-4-sbl...@amazon.com Link: https://lore.kernel.org/r/20200729001103.6450-3-sbl...@amazon.com --- arch/x86/include/asm/tlbflush.h | 2 +- arch/x86/mm/tlb.c | 53 ++++++++++++++++++--------------- 2 files changed, 30 insertions(+), 25 deletions(-) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 8c87a2e0b660..a927d40664df 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -83,7 +83,7 @@ struct tlb_state { /* Last user mm for optimizing IBPB */ union { struct mm_struct *last_user_mm; - unsigned long last_user_mm_ibpb; + unsigned long last_user_mm_spec; }; u16 loaded_mm_asid; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 569ac1d57f55..7320348b5a61 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -42,10 +42,14 @@ */ /* - * Use bit 0 to mangle the TIF_SPEC_IB state into the mm pointer which is - * stored in cpu_tlb_state.last_user_mm_ibpb. + * Bits to mangle the TIF_SPEC_IB state into the mm pointer which is + * stored in cpu_tlb_state.last_user_mm_spec. */ #define LAST_USER_MM_IBPB 0x1UL +#define LAST_USER_MM_SPEC_MASK (LAST_USER_MM_IBPB) + +/* Bits to set when tlbstate and flush is (re)initialized */ +#define LAST_USER_MM_INIT LAST_USER_MM_IBPB /* * The x86 feature is called PCID (Process Context IDentifier). It is similar @@ -316,20 +320,29 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } -static inline unsigned long mm_mangle_tif_spec_ib(struct task_struct *next) +static inline unsigned long mm_mangle_tif_spec_bits(struct task_struct *next) { unsigned long next_tif = task_thread_info(next)->flags; - unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB; + unsigned long spec_bits = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_SPEC_MASK; - return (unsigned long)next->mm | ibpb; + return (unsigned long)next->mm | spec_bits; } -static void cond_ibpb(struct task_struct *next) +static void cond_mitigation(struct task_struct *next) { + unsigned long prev_mm, next_mm; + if (!next || !next->mm) return; + next_mm = mm_mangle_tif_spec_bits(next); + prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec); + /* + * 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. + * * Both, the conditional and the always IBPB mode use the mm * pointer to avoid the IBPB when switching between tasks of the * same process. Using the mm pointer instead of mm->context.ctx_id @@ -339,8 +352,6 @@ static void cond_ibpb(struct task_struct *next) * exposed data is not really interesting. */ if (static_branch_likely(&switch_mm_cond_ibpb)) { - unsigned long prev_mm, next_mm; - /* * This is a bit more complex than the always mode because * it has to handle two cases: @@ -370,20 +381,14 @@ static void cond_ibpb(struct task_struct *next) * Optimize this with reasonably small overhead for the * above cases. Mangle the TIF_SPEC_IB bit into the mm * pointer of the incoming task which is stored in - * cpu_tlbstate.last_user_mm_ibpb for comparison. - */ - next_mm = mm_mangle_tif_spec_ib(next); - prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_ibpb); - - /* + * cpu_tlbstate.last_user_mm_spec for comparison. + * * Issue IBPB only if the mm's are different and one or * both have the IBPB bit set. */ if (next_mm != prev_mm && (next_mm | prev_mm) & LAST_USER_MM_IBPB) indirect_branch_prediction_barrier(); - - this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, next_mm); } if (static_branch_unlikely(&switch_mm_always_ibpb)) { @@ -392,11 +397,12 @@ static void cond_ibpb(struct task_struct *next) * different context than the user space task which ran * last on this CPU. */ - if (this_cpu_read(cpu_tlbstate.last_user_mm) != next->mm) { + if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != + (unsigned long)next->mm) indirect_branch_prediction_barrier(); - this_cpu_write(cpu_tlbstate.last_user_mm, next->mm); - } } + + this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm); } #ifdef CONFIG_PERF_EVENTS @@ -524,11 +530,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, need_flush = true; } else { /* - * 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. + * Apply process to process speculation vulnerability + * mitigations if applicable. */ - cond_ibpb(tsk); + cond_mitigation(tsk); /* * Stop remote flushes for the previous mm. @@ -636,7 +641,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ - this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, LAST_USER_MM_IBPB); + this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT); 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); -- 2.17.1
