Move some code that will be needed for the lazy -> !lazy state
transition when a lazy TLB CPU has gotten out of date.

No functional changes, since the if (real_prev == next) branch
always returns.

Suggested-by: Andy Lutomirski <[email protected]>
Signed-off-by: Rik van Riel <[email protected]>
Acked-by: Dave Hansen <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
(cherry picked from commit 61d0beb5796ab11f7f3bf38cb2eccc6579aaa70b)
---
 arch/x86/mm/tlb.c | 87 +++++++++++++++++++++++++++++------------------
 1 file changed, 54 insertions(+), 33 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index d19f424073d9..ac05d61cc90e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -158,6 +158,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct 
mm_struct *next,
        u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
        unsigned cpu = smp_processor_id();
        u64 next_tlb_gen;
+       bool need_flush;
+       u16 new_asid;
 
        /*
         * NB: The scheduler will call us with prev == next when switching
@@ -217,8 +219,27 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct 
mm_struct *next,
 
                return;
        } 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)) {
                        /*
@@ -249,44 +270,44 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct 
mm_struct *next,
                /* Let nmi_uaccess_okay() know that we're changing CR3. */
                this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
                barrier();
+       }
 
-               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);
-                       load_new_mm_cr3(next->pgd, new_asid, true);
-
-                       /*
-                        * NB: This gets called via leave_mm() in the idle path
-                        * where RCU functions differently.  Tracing normally
-                        * uses RCU, so we need to use the _rcuidle variant.
-                        *
-                        * (There is no good reason for this.  The idle code 
should
-                        *  be rearranged to call this before rcu_idle_enter().)
-                        */
-                       trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 
TLB_FLUSH_ALL);
-               } else {
-                       /* The new ASID is already up to date. */
-                       load_new_mm_cr3(next->pgd, new_asid, false);
-
-                       /* See above wrt _rcuidle. */
-                       trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
-               }
+       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);
+               load_new_mm_cr3(next->pgd, new_asid, true);
 
                /*
-                * Record last user mm's context id, so we can avoid
-                * flushing branch buffer with IBPB if we switch back
-                * to the same user.
+                * NB: This gets called via leave_mm() in the idle path
+                * where RCU functions differently.  Tracing normally
+                * uses RCU, so we need to use the _rcuidle variant.
+                *
+                * (There is no good reason for this.  The idle code should
+                *  be rearranged to call this before rcu_idle_enter().)
                 */
-               if (next != &init_mm)
-                       this_cpu_write(cpu_tlbstate.last_ctx_id, 
next->context.ctx_id);
-
-               /* Make sure we write CR3 before loaded_mm. */
-               barrier();
+               trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 
TLB_FLUSH_ALL);
+       } else {
+               /* The new ASID is already up to date. */
+               load_new_mm_cr3(next->pgd, new_asid, false);
 
-               this_cpu_write(cpu_tlbstate.loaded_mm, next);
-               this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+               /* 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);
+
+       /* Make sure we write CR3 before loaded_mm. */
+       barrier();
+
+       this_cpu_write(cpu_tlbstate.loaded_mm, next);
+       this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+
        load_mm_cr4(next);
        switch_ldt(real_prev, next);
 }
-- 
2.17.1

Reply via email to