linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Nadav Amit <nadav.amit@gmail.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: Nadav Amit <namit@vmware.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andy Lutomirski <luto@kernel.org>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Will Deacon <will@kernel.org>, Yu Zhao <yuzhao@google.com>,
	Nick Piggin <npiggin@gmail.com>,
	x86@kernel.org
Subject: [RFC 08/20] mm: store completed TLB generation
Date: Sat, 30 Jan 2021 16:11:20 -0800	[thread overview]
Message-ID: <20210131001132.3368247-9-namit@vmware.com> (raw)
In-Reply-To: <20210131001132.3368247-1-namit@vmware.com>

From: Nadav Amit <namit@vmware.com>

To detect deferred TLB flushes in fine granularity, we need to keep
track on the completed TLB flush generation for each mm.

Add logic to track for each mm the tlb_gen_completed, which tracks the
completed TLB generation. It is the arch responsibility to call
mark_mm_tlb_gen_done() whenever a TLB flush is completed.

Start the generation numbers from 1 instead of 0. This would allow later
to detect whether flushes of a certain generation were completed.

Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: x86@kernel.org
---
 arch/x86/mm/tlb.c         | 10 ++++++++++
 include/asm-generic/tlb.h | 33 +++++++++++++++++++++++++++++++++
 include/linux/mm_types.h  | 15 ++++++++++++++-
 3 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 7ab21430be41..d17b5575531e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -14,6 +14,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/cache.h>
 #include <asm/apic.h>
+#include <asm/tlb.h>
 
 #include "mm_internal.h"
 
@@ -915,6 +916,9 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), info);
 
+	/* Update the completed generation */
+	mark_mm_tlb_gen_done(mm, new_tlb_gen);
+
 	put_flush_tlb_info();
 	put_cpu();
 }
@@ -1147,6 +1151,12 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 
 	cpumask_clear(&batch->cpumask);
 
+	/*
+	 * We cannot call mark_mm_tlb_gen_done() since we do not know which
+	 * mm's should be flushed. This may lead to some unwarranted TLB
+	 * flushes, but not to correction problems.
+	 */
+
 	put_cpu();
 }
 
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 517c89398c83..427bfcc6cdec 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -513,6 +513,39 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 }
 #endif
 
+#ifdef CONFIG_ARCH_HAS_TLB_GENERATIONS
+
+/*
+ * Helper function to update a generation to have a new value, as long as new
+ * value is greater or equal to gen.
+ */
+static inline void tlb_update_generation(atomic64_t *gen, u64 new_gen)
+{
+	u64 cur_gen = atomic64_read(gen);
+
+	while (cur_gen < new_gen) {
+		u64 old_gen = atomic64_cmpxchg(gen, cur_gen, new_gen);
+
+		/* Check if we succeeded in the cmpxchg */
+		if (likely(cur_gen == old_gen))
+			break;
+
+		cur_gen = old_gen;
+	};
+}
+
+
+static inline void mark_mm_tlb_gen_done(struct mm_struct *mm, u64 gen)
+{
+	/*
+	 * Update the completed generation to the new generation if the new
+	 * generation is greater than the previous one.
+	 */
+	tlb_update_generation(&mm->tlb_gen_completed, gen);
+}
+
+#endif /* CONFIG_ARCH_HAS_TLB_GENERATIONS */
+
 /*
  * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end,
  * and set corresponding cleared_*.
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 2035ac319c2b..8a5eb4bfac59 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -571,6 +571,13 @@ struct mm_struct {
 		 * This is not used on Xen PV.
 		 */
 		atomic64_t tlb_gen;
+
+		/*
+		 * TLB generation which is guarnateed to be flushed, including
+		 * all the PTE changes that were performed before tlb_gen was
+		 * incremented.
+		 */
+		atomic64_t tlb_gen_completed;
 #endif
 	} __randomize_layout;
 
@@ -690,7 +697,13 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
 #ifdef CONFIG_ARCH_HAS_TLB_GENERATIONS
 static inline void init_mm_tlb_gen(struct mm_struct *mm)
 {
-	atomic64_set(&mm->tlb_gen, 0);
+	/*
+	 * Start from generation of 1, so default generation 0 will be
+	 * considered as flushed and would not be regarded as an outstanding
+	 * deferred invalidation.
+	 */
+	atomic64_set(&mm->tlb_gen, 1);
+	atomic64_set(&mm->tlb_gen_completed, 1);
 }
 
 static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
-- 
2.25.1



  parent reply	other threads:[~2021-01-31  0:16 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-31  0:11 [RFC 00/20] TLB batching consolidation and enhancements Nadav Amit
2021-01-31  0:11 ` [RFC 01/20] mm/tlb: fix fullmm semantics Nadav Amit
2021-01-31  1:02   ` Andy Lutomirski
2021-01-31  1:19     ` Nadav Amit
2021-01-31  2:57       ` Andy Lutomirski
2021-02-01  7:30         ` Nadav Amit
2021-02-01 11:36   ` Peter Zijlstra
2021-02-02  9:32     ` Nadav Amit
2021-02-02 11:00       ` Peter Zijlstra
2021-02-02 21:35         ` Nadav Amit
2021-02-03  9:44           ` Will Deacon
2021-02-04  3:20             ` Nadav Amit
2021-01-31  0:11 ` [RFC 02/20] mm/mprotect: use mmu_gather Nadav Amit
2021-01-31  0:11 ` [RFC 03/20] mm/mprotect: do not flush on permission promotion Nadav Amit
2021-01-31  1:07   ` Andy Lutomirski
2021-01-31  1:17     ` Nadav Amit
2021-01-31  2:59       ` Andy Lutomirski
     [not found]     ` <7a6de15a-a570-31f2-14d6-a8010296e694@citrix.com>
2021-02-01  5:58       ` Nadav Amit
2021-02-01 15:38         ` Andrew Cooper
2021-01-31  0:11 ` [RFC 04/20] mm/mapping_dirty_helpers: use mmu_gather Nadav Amit
2021-01-31  0:11 ` [RFC 05/20] mm/tlb: move BATCHED_UNMAP_TLB_FLUSH to tlb.h Nadav Amit
2021-01-31  0:11 ` [RFC 06/20] fs/task_mmu: use mmu_gather interface of clear-soft-dirty Nadav Amit
2021-01-31  0:11 ` [RFC 07/20] mm: move x86 tlb_gen to generic code Nadav Amit
2021-01-31 18:26   ` Andy Lutomirski
2021-01-31  0:11 ` Nadav Amit [this message]
2021-01-31 20:32   ` [RFC 08/20] mm: store completed TLB generation Andy Lutomirski
2021-02-01  7:28     ` Nadav Amit
2021-02-01 16:53       ` Andy Lutomirski
2021-02-01 11:52   ` Peter Zijlstra
2021-01-31  0:11 ` [RFC 09/20] mm: create pte/pmd_tlb_flush_pending() Nadav Amit
2021-01-31  0:11 ` [RFC 10/20] mm: add pte_to_page() Nadav Amit
2021-01-31  0:11 ` [RFC 11/20] mm/tlb: remove arch-specific tlb_start/end_vma() Nadav Amit
2021-02-01 12:09   ` Peter Zijlstra
2021-02-02  6:41     ` Nicholas Piggin
2021-02-02  7:20       ` Nadav Amit
2021-02-02  9:31         ` Peter Zijlstra
2021-02-02  9:54           ` Nadav Amit
2021-02-02 11:04             ` Peter Zijlstra
2021-01-31  0:11 ` [RFC 12/20] mm/tlb: save the VMA that is flushed during tlb_start_vma() Nadav Amit
2021-02-01 12:28   ` Peter Zijlstra
2021-01-31  0:11 ` [RFC 13/20] mm/tlb: introduce tlb_start_ptes() and tlb_end_ptes() Nadav Amit
2021-01-31  9:57   ` Damian Tometzki
2021-01-31 10:07   ` Damian Tometzki
2021-02-01  7:29     ` Nadav Amit
2021-02-01 13:19   ` Peter Zijlstra
2021-02-01 23:00     ` Nadav Amit
2021-01-31  0:11 ` [RFC 14/20] mm: move inc/dec_tlb_flush_pending() to mmu_gather.c Nadav Amit
2021-01-31  0:11 ` [RFC 15/20] mm: detect deferred TLB flushes in vma granularity Nadav Amit
2021-02-01 22:04   ` Nadav Amit
2021-02-02  0:14     ` Andy Lutomirski
2021-02-02 20:51       ` Nadav Amit
2021-02-04  4:35         ` Andy Lutomirski
2021-01-31  0:11 ` [RFC 16/20] mm/tlb: per-page table generation tracking Nadav Amit
2021-01-31  0:11 ` [RFC 17/20] mm/tlb: updated completed deferred TLB flush conditionally Nadav Amit
2021-01-31  0:11 ` [RFC 18/20] mm: make mm_cpumask() volatile Nadav Amit
2021-01-31  0:11 ` [RFC 19/20] lib/cpumask: introduce cpumask_atomic_or() Nadav Amit
2021-01-31  0:11 ` [RFC 20/20] mm/rmap: avoid potential races Nadav Amit
2021-08-23  8:05   ` Huang, Ying
2021-08-23 15:50     ` Nadav Amit
2021-08-24  0:36       ` Huang, Ying
2021-01-31  0:39 ` [RFC 00/20] TLB batching consolidation and enhancements Andy Lutomirski
2021-01-31  1:08   ` Nadav Amit
2021-01-31  3:30 ` Nicholas Piggin
2021-01-31  7:57   ` Nadav Amit
2021-01-31  8:14     ` Nadav Amit
2021-02-01 12:44     ` Peter Zijlstra
2021-02-02  7:14       ` Nicholas Piggin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210131001132.3368247-9-namit@vmware.com \
    --to=nadav.amit@gmail.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=namit@vmware.com \
    --cc=npiggin@gmail.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=yuzhao@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).