[PATCH] powerpc/64s: Fix mm_cpumask memory ordering comment

[PATCH] powerpc/64s: Fix mm_cpumask memory ordering comment

[Nicholas Piggin]

The memory ordering comment no longer applies, because mm_ctx_id is
no longer used anywhere. At best always been difficult to follow.

It's better to consider the load on which the slbmte depends on, which
the MMU depends on before it can start loading TLBs, rather than a
store which may or may not have a subsequent dependency chain to the
slbmte.

So update the comment and we use the load of the mm's user context ID.
This is much more analogous the radix ordering too, which is good.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/mm/mmu_context.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index 18f20da0d348..a857af401738 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -43,24 +43,26 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 
 		/*
 		 * This full barrier orders the store to the cpumask above vs
-		 * a subsequent operation which allows this CPU to begin loading
-		 * translations for next.
+		 * a subsequent load which allows this CPU/MMU to begin loading
+		 * translations for 'next' from page table PTEs into the TLB.
 		 *
-		 * When using the radix MMU that operation is the load of the
+		 * When using the radix MMU, that operation is the load of the
 		 * MMU context id, which is then moved to SPRN_PID.
 		 *
 		 * For the hash MMU it is either the first load from slb_cache
-		 * in switch_slb(), and/or the store of paca->mm_ctx_id in
-		 * copy_mm_to_paca().
+		 * in switch_slb() to preload the SLBs, or the load of
+		 * get_user_context which loads the context for the VSID hash
+		 * to insert a new SLB, in the SLB fault handler.
 		 *
 		 * On the other side, the barrier is in mm/tlb-radix.c for
-		 * radix which orders earlier stores to clear the PTEs vs
-		 * the load of mm_cpumask. And pte_xchg which does the same
-		 * thing for hash.
+		 * radix which orders earlier stores to clear the PTEs before
+		 * the load of mm_cpumask to check which CPU TLBs should be
+		 * flushed. For hash, pte_xchg to clear the PTE includes the
+		 * barrier.
 		 *
-		 * This full barrier is needed by membarrier when switching
-		 * between processes after store to rq->curr, before user-space
-		 * memory accesses.
+		 * This full barrier is also needed by membarrier when
+		 * switching between processes after store to rq->curr, before
+		 * user-space memory accesses.
 		 */
 		smp_mb();
 
-- 
2.23.0

Re: [PATCH] powerpc/64s: Fix mm_cpumask memory ordering comment

[Michael Ellerman]

On Thu, 22 Apr 2021 01:17:32 +1000, Nicholas Piggin wrote:
> The memory ordering comment no longer applies, because mm_ctx_id is
> no longer used anywhere. At best always been difficult to follow.
> 
> It's better to consider the load on which the slbmte depends on, which
> the MMU depends on before it can start loading TLBs, rather than a
> store which may or may not have a subsequent dependency chain to the
> slbmte.
> 
> [...]

Applied to powerpc/next.

[1/1] powerpc/64s: Fix mm_cpumask memory ordering comment
      https://git.kernel.org/powerpc/c/0f197ddce403af33aa7f15af55644549778a9988

cheers