This is a note to let you know that I've just added the patch titled

mm, x86/mm: Make the batched unmap TLB flush API more generic

to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git%3Ba=su...

The filename of the patch is: mm-x86-mm-make-the-batched-unmap-tlb-flush-api-more-generic.patch and it can be found in the queue-4.9 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let stable@vger.kernel.org know about it.

From e73ad5ff2f76da25390e9607cb549691639330c3 Mon Sep 17 00:00:00 2001

From: Andy Lutomirski luto@kernel.org Date: Mon, 22 May 2017 15:30:03 -0700 Subject: mm, x86/mm: Make the batched unmap TLB flush API more generic

From: Andy Lutomirski luto@kernel.org

commit e73ad5ff2f76da25390e9607cb549691639330c3 upstream.

try_to_unmap_flush() used to open-code a rather x86-centric flush sequence: local_flush_tlb() + flush_tlb_others(). Rearrange the code so that the arch (only x86 for now) provides arch_tlbbatch_add_mm() and arch_tlbbatch_flush() and the core code calls those functions instead.

I'll want this for x86 because, to enable address space ids, I can't support the flush_tlb_others() mode used by exising try_to_unmap_flush() implementation with good performance. I can support the new API fairly easily, though.

I imagine that other architectures may be in a similar position. Architectures with strong remote flush primitives (arm64?) may have even worse performance problems with flush_tlb_others() the way that try_to_unmap_flush() uses it.

Signed-off-by: Andy Lutomirski luto@kernel.org Acked-by: Kees Cook keescook@chromium.org Cc: Andrew Morton akpm@linux-foundation.org Cc: Borislav Petkov bpetkov@suse.de Cc: Dave Hansen dave.hansen@intel.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Mel Gorman mgorman@suse.de Cc: Michal Hocko mhocko@suse.com Cc: Nadav Amit nadav.amit@gmail.com Cc: Nadav Amit namit@vmware.com Cc: Peter Zijlstra peterz@infradead.org Cc: Rik van Riel riel@redhat.com Cc: Sasha Levin sasha.levin@oracle.com Cc: Thomas Gleixner tglx@linutronix.de Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/19f25a8581f9fb77876b7ff3b001f89835e34ea3.1495492063... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Eduardo Valentin eduval@amazon.com Signed-off-by: Eduardo Valentin edubezval@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/tlbbatch.h | 16 ++++++++++++++++ arch/x86/include/asm/tlbflush.h | 8 ++++++++ arch/x86/mm/tlb.c | 17 +++++++++++++++++ include/linux/sched.h | 15 +++++++++++---- mm/rmap.c | 16 ++-------------- 5 files changed, 54 insertions(+), 18 deletions(-) create mode 100644 arch/x86/include/asm/tlbbatch.h

--- /dev/null +++ b/arch/x86/include/asm/tlbbatch.h @@ -0,0 +1,16 @@ +#ifndef _ARCH_X86_TLBBATCH_H +#define _ARCH_X86_TLBBATCH_H + +#include <linux/cpumask.h> + +#ifdef CONFIG_SMP +struct arch_tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed.. + */ + struct cpumask cpumask; +}; +#endif + +#endif /* _ARCH_X86_TLBBATCH_H */ --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -327,6 +327,14 @@ static inline void reset_lazy_tlbstate(v this_cpu_write(cpu_tlbstate.active_mm, &init_mm); }

+static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm) +{ + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); +} + +extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); + #endif /* SMP */

#ifndef CONFIG_PARAVIRT --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -410,6 +410,23 @@ void flush_tlb_kernel_range(unsigned lon } }

+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, &batch->cpumask)) { + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); + } + + if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&batch->cpumask, NULL, 0, TLB_FLUSH_ALL); + cpumask_clear(&batch->cpumask); + + put_cpu(); +} + static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1463,15 +1463,22 @@ enum perf_event_task_context { perf_nr_task_contexts, };

+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +#include <asm/tlbbatch.h> +#endif + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { /* - * Each bit set is a CPU that potentially has a TLB entry for one of - * the PFNs being flushed. See set_tlb_ubc_flush_pending(). + * The arch code makes the following promise: generic code can modify a + * PTE, then call arch_tlbbatch_add_mm() (which internally provides all + * needed barriers), then call arch_tlbbatch_flush(), and the entries + * will be flushed on all CPUs by the time that arch_tlbbatch_flush() + * returns. */ - struct cpumask cpumask; + struct arch_tlbflush_unmap_batch arch;

- /* True if any bit in cpumask is set */ + /* True if a flush is needed. */ bool flush_required;

/* --- a/mm/rmap.c +++ b/mm/rmap.c @@ -578,25 +578,13 @@ void page_unlock_anon_vma_read(struct an void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; - int cpu;

if (!tlb_ubc->flush_required) return;

- cpu = get_cpu(); - - if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); - trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); - } - - if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) - flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL); - cpumask_clear(&tlb_ubc->cpumask); + arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; - put_cpu(); }

/* Flush iff there are potentially writable TLB entries that can race with IO */ @@ -613,7 +601,7 @@ static void set_tlb_ubc_flush_pending(st { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;

- cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm)); + arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true;

/*

Patches currently in stable-queue which might be from luto@kernel.org are

queue-4.9/x86-mm-refactor-flush_tlb_mm_range-to-merge-local-and-remote-cases.patch queue-4.9/x86-mm-pass-flush_tlb_info-to-flush_tlb_others-etc.patch queue-4.9/x86-mm-rework-lazy-tlb-to-track-the-actual-loaded-mm.patch queue-4.9/x86-mm-kvm-teach-kvm-s-vmx-code-that-cr3-isn-t-a-constant.patch queue-4.9/x86-mm-use-new-merged-flush-logic-in-arch_tlbbatch_flush.patch queue-4.9/x86-kvm-vmx-simplify-segment_base.patch queue-4.9/x86-entry-unwind-create-stack-frames-for-saved-interrupt-registers.patch queue-4.9/x86-mm-reduce-indentation-in-flush_tlb_func.patch queue-4.9/x86-mm-remove-the-up-asm-tlbflush.h-code-always-use-the-formerly-smp-code.patch queue-4.9/x86-mm-reimplement-flush_tlb_page-using-flush_tlb_mm_range.patch queue-4.9/mm-x86-mm-make-the-batched-unmap-tlb-flush-api-more-generic.patch queue-4.9/x86-kvm-vmx-defer-tr-reload-after-vm-exit.patch queue-4.9/x86-mm-change-the-leave_mm-condition-for-local-tlb-flushes.patch queue-4.9/x86-mm-be-more-consistent-wrt-page_shift-vs-page_size-in-tlb-flush-code.patch