summaryrefslogtreecommitdiff
path: root/arch/x86/mm/tlb.c
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2025-05-16 15:43:04 +0200
committerDave Hansen <dave.hansen@linux.intel.com>2025-10-13 13:55:53 -0700
commit83b0177a6c4889b3a6e865da5e21b2c9d97d0551 (patch)
treebf37d926cd4947bacd56f5be2ecaf29f7389cfc7 /arch/x86/mm/tlb.c
parentf25785f9b088ed65089dd0d0034da52858417839 (diff)
x86/mm: Fix SMP ordering in switch_mm_irqs_off()
Stephen noted that it is possible to not have an smp_mb() between the loaded_mm store and the tlb_gen load in switch_mm(), meaning the ordering against flush_tlb_mm_range() goes out the window, and it becomes possible for switch_mm() to not observe a recent tlb_gen update and fail to flush the TLBs. [ dhansen: merge conflict fixed by Ingo ] Fixes: 209954cbc7d0 ("x86/mm/tlb: Update mm_cpumask lazily") Reported-by: Stephen Dolan <sdolan@janestreet.com> Closes: https://lore.kernel.org/all/CAHDw0oGd0B4=uuv8NGqbUQ_ZVmSheU2bN70e4QhFXWvuAZdt2w@mail.gmail.com/ Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Diffstat (limited to 'arch/x86/mm/tlb.c')
-rw-r--r--arch/x86/mm/tlb.c24
1 files changed, 22 insertions, 2 deletions
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 39f80111e6f1..5d221709353e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -911,11 +911,31 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
* CR3 and cpu_tlbstate.loaded_mm are not all in sync.
*/
this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
- barrier();
- /* Start receiving IPIs and then read tlb_gen (and LAM below) */
+ /*
+ * Make sure this CPU is set in mm_cpumask() such that we'll
+ * receive invalidation IPIs.
+ *
+ * Rely on the smp_mb() implied by cpumask_set_cpu()'s atomic
+ * operation, or explicitly provide one. Such that:
+ *
+ * switch_mm_irqs_off() flush_tlb_mm_range()
+ * smp_store_release(loaded_mm, SWITCHING); atomic64_inc_return(tlb_gen)
+ * smp_mb(); // here // smp_mb() implied
+ * atomic64_read(tlb_gen); this_cpu_read(loaded_mm);
+ *
+ * we properly order against flush_tlb_mm_range(), where the
+ * loaded_mm load can happen in mative_flush_tlb_multi() ->
+ * should_flush_tlb().
+ *
+ * This way switch_mm() must see the new tlb_gen or
+ * flush_tlb_mm_range() must see the new loaded_mm, or both.
+ */
if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
cpumask_set_cpu(cpu, mm_cpumask(next));
+ else
+ smp_mb();
+
next_tlb_gen = atomic64_read(&next->context.tlb_gen);
ns = choose_new_asid(next, next_tlb_gen);