[PATCH 3.10 153/180] x86/mm: Improve switch_mm() barrier comments

From: Willy Tarreau
Date: Sun Aug 21 2016 - 11:43:26 EST


From: Andy Lutomirski <luto@xxxxxxxxxx>

commit 4eaffdd5a5fe6ff9f95e1ab4de1ac904d5e0fa8b upstream.

My previous comments were still a bit confusing and there was a
typo. Fix it up.

Reported-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Fixes: 71b3c126e611 ("x86/mm: Add barriers and document switch_mm()-vs-flush synchronization")
Link: http://lkml.kernel.org/r/0a0b43cdcdd241c5faaaecfbcc91a155ddedc9a1.1452631609.git.luto@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
---
arch/x86/include/asm/mmu_context.h | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index c0d2f6b..29a3d1b 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -58,14 +58,16 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
* be sent, and CPU 0's TLB will contain a stale entry.)
*
* The bad outcome can occur if either CPU's load is
- * reordered before that CPU's store, so both CPUs much
+ * reordered before that CPU's store, so both CPUs must
* execute full barriers to prevent this from happening.
*
* Thus, switch_mm needs a full barrier between the
* store to mm_cpumask and any operation that could load
- * from next->pgd. This barrier synchronizes with
- * remote TLB flushers. Fortunately, load_cr3 is
- * serializing and thus acts as a full barrier.
+ * from next->pgd. TLB fills are special and can happen
+ * due to instruction fetches or for no reason at all,
+ * and neither LOCK nor MFENCE orders them.
+ * Fortunately, load_cr3() is serializing and gives the
+ * ordering guarantee we need.
*
*/
load_cr3(next->pgd);
@@ -96,9 +98,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
* tlb flush IPI delivery. We must reload CR3
* to make sure to use no freed page tables.
*
- * As above, this is a barrier that forces
- * TLB repopulation to be ordered after the
- * store to mm_cpumask.
+ * As above, load_cr3() is serializing and orders TLB
+ * fills with respect to the mm_cpumask write.
*/
load_cr3(next->pgd);
load_LDT_nolock(&next->context);
--
2.8.0.rc2.1.gbe9624a