Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit d86564a2 authored by Peter Zijlstra's avatar Peter Zijlstra Committed by Linus Torvalds
Browse files

mm/tlb, x86/mm: Support invalidating TLB caches for RCU_TABLE_FREE 



Jann reported that x86 was missing required TLB invalidates when he
hit the !*batch slow path in tlb_remove_table().

This is indeed the case; RCU_TABLE_FREE does not provide TLB (cache)
invalidates, the PowerPC-hash where this code originated and the
Sparc-hash where this was subsequently used did not need that. ARM
which later used this put an explicit TLB invalidate in their
__p*_free_tlb() functions, and PowerPC-radix followed that example.

But when we hooked up x86 we failed to consider this. Fix this by
(optionally) hooking tlb_remove_table() into the TLB invalidate code.

NOTE: s390 was also needing something like this and might now
      be able to use the generic code again.

[ Modified to be on top of Nick's cleanups, which simplified this patch
  now that tlb_flush_mmu_tlbonly() really only flushes the TLB - Linus ]

Fixes: 9e52fc2b ("x86/mm: Enable RCU based page table freeing (CONFIG_HAVE_RCU_TABLE_FREE=y)")
Reported-by: default avatarJann Horn <jannh@google.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: default avatarRik van Riel <riel@surriel.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: stable@kernel.org
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent a6f57208

arch/Kconfig

+3 −0
Original line number Original line Diff line number Diff line
@@ -362,6 +362,9 @@ config HAVE_ARCH_JUMP_LABEL 
config HAVE_RCU_TABLE_FREE

config HAVE_RCU_TABLE_FREE

	bool

	bool





config HAVE_RCU_TABLE_INVALIDATE

	bool



config ARCH_HAVE_NMI_SAFE_CMPXCHG

config ARCH_HAVE_NMI_SAFE_CMPXCHG

	bool

	bool

arch/x86/Kconfig

+1 −0
Original line number Original line Diff line number Diff line
@@ -181,6 +181,7 @@ config X86 
	select HAVE_PERF_REGS

	select HAVE_PERF_REGS

	select HAVE_PERF_USER_STACK_DUMP

	select HAVE_PERF_USER_STACK_DUMP

	select HAVE_RCU_TABLE_FREE

	select HAVE_RCU_TABLE_FREE

	select HAVE_RCU_TABLE_INVALIDATE	if HAVE_RCU_TABLE_FREE

	select HAVE_REGS_AND_STACK_ACCESS_API

	select HAVE_REGS_AND_STACK_ACCESS_API

	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION

	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION

	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR

	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR

mm/memory.c

+18 −0
Original line number Original line Diff line number Diff line
@@ -330,6 +330,21 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ 
 * See the comment near struct mmu_table_batch.

 * See the comment near struct mmu_table_batch.

 */

 */





/*

 * If we want tlb_remove_table() to imply TLB invalidates.

 */

static inline void tlb_table_invalidate(struct mmu_gather *tlb)

{

#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE

	/*

	 * Invalidate page-table caches used by hardware walkers. Then we still

	 * need to RCU-sched wait while freeing the pages because software

	 * walkers can still be in-flight.

	 */

	tlb_flush_mmu_tlbonly(tlb);

#endif

}



static void tlb_remove_table_smp_sync(void *arg)

static void tlb_remove_table_smp_sync(void *arg)

{

{

	/* Simply deliver the interrupt */

	/* Simply deliver the interrupt */
@@ -366,6 +381,7 @@ void tlb_table_flush(struct mmu_gather *tlb) 
	struct mmu_table_batch **batch = &tlb->batch;

	struct mmu_table_batch **batch = &tlb->batch;





	if (*batch) {

	if (*batch) {

		tlb_table_invalidate(tlb);

		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);

		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);

		*batch = NULL;

		*batch = NULL;

	}

	}
@@ -378,11 +394,13 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) 
	if (*batch == NULL) {

	if (*batch == NULL) {

		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);

		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);

		if (*batch == NULL) {

		if (*batch == NULL) {

			tlb_table_invalidate(tlb);

			tlb_remove_table_one(table);

			tlb_remove_table_one(table);

			return;

			return;

		}

		}

		(*batch)->nr = 0;

		(*batch)->nr = 0;

	}

	}



	(*batch)->tables[(*batch)->nr++] = table;

	(*batch)->tables[(*batch)->nr++] = table;

	if ((*batch)->nr == MAX_TABLE_BATCH)

	if ((*batch)->nr == MAX_TABLE_BATCH)

		tlb_table_flush(tlb);

		tlb_table_flush(tlb);