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

x86/mm: Refactor flush_tlb_mm_range() to merge local and remote cases

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: x86-mm-refactor-flush_tlb_mm_range-to-merge-local-and-remote-cases.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 454bbad9793f59f5656ce5971ee473a8be736ef5 Mon Sep 17 00:00:00 2001

From: Andy Lutomirski luto@kernel.org Date: Sun, 28 May 2017 10:00:12 -0700 Subject: x86/mm: Refactor flush_tlb_mm_range() to merge local and remote cases

From: Andy Lutomirski luto@kernel.org

commit 454bbad9793f59f5656ce5971ee473a8be736ef5 upstream.

The local flush path is very similar to the remote flush path. Merge them.

This is intended to make no difference to behavior whatsoever. It removes some code and will make future changes to the flushing mechanics simpler.

This patch does remove one small optimization: flush_tlb_mm_range() now has an unconditional smp_mb() instead of using MOV to CR3 or INVLPG as a full barrier when applicable. I think this is okay for a few reasons. First, smp_mb() is quite cheap compared to the cost of a TLB flush. Second, this rearrangement makes a bigger optimization available: with some work on the SMP function call code, we could do the local and remote flushes in parallel. Third, I'm planning a rework of the TLB flush algorithm that will require an atomic operation at the beginning of each flush, and that operation will replace the smp_mb().

Signed-off-by: Andy Lutomirski luto@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Cc: Arjan van de Ven arjan@linux.intel.com 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: Thomas Gleixner tglx@linutronix.de Cc: linux-mm@kvack.org 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/tlbflush.h | 1 arch/x86/mm/tlb.c | 111 +++++++++++++++++----------------------- 2 files changed, 48 insertions(+), 64 deletions(-)

--- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -216,7 +216,6 @@ static inline void __flush_tlb_one(unsig * ..but the i386 has somewhat limited tlb flushing capabilities, * and page-granular flushes are available only on i486 and up. */ - struct flush_tlb_info { struct mm_struct *mm; unsigned long start; --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -216,22 +216,9 @@ void switch_mm_irqs_off(struct mm_struct * write/read ordering problems. */

-/* - * TLB flush funcation: - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ -static void flush_tlb_func(void *info) +static void flush_tlb_func_common(const struct flush_tlb_info *f, + bool local, enum tlb_flush_reason reason) { - const struct flush_tlb_info *f = info; - - inc_irq_stat(irq_tlb_count); - - if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.active_mm)) - return; - - count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { leave_mm(smp_processor_id()); return; @@ -239,7 +226,9 @@ static void flush_tlb_func(void *info)

if (f->end == TLB_FLUSH_ALL) { local_flush_tlb(); - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); + if (local) + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + trace_tlb_flush(reason, TLB_FLUSH_ALL); } else { unsigned long addr; unsigned long nr_pages = @@ -249,10 +238,32 @@ static void flush_tlb_func(void *info) __flush_tlb_single(addr); addr += PAGE_SIZE; } - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); + if (local) + count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); + trace_tlb_flush(reason, nr_pages); } }

+static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason) +{ + const struct flush_tlb_info *f = info; + + flush_tlb_func_common(f, true, reason); +} + +static void flush_tlb_func_remote(void *info) +{ + const struct flush_tlb_info *f = info; + + inc_irq_stat(irq_tlb_count); + + if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.active_mm)) + return; + + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN); +} + void native_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) { @@ -269,11 +280,11 @@ void native_flush_tlb_others(const struc cpu = smp_processor_id(); cpumask = uv_flush_tlb_others(cpumask, info); if (cpumask) - smp_call_function_many(cpumask, flush_tlb_func, + smp_call_function_many(cpumask, flush_tlb_func_remote, (void *)info, 1); return; } - smp_call_function_many(cpumask, flush_tlb_func, + smp_call_function_many(cpumask, flush_tlb_func_remote, (void *)info, 1); }

@@ -315,59 +326,33 @@ static unsigned long tlb_single_page_flu void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { - unsigned long addr; - struct flush_tlb_info info; - /* do a global flush by default */ - unsigned long base_pages_to_flush = TLB_FLUSH_ALL; - - preempt_disable(); - if (current->active_mm != mm) { - /* Synchronize with switch_mm. */ - smp_mb(); + int cpu;

- goto out; - } - - if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { - leave_mm(smp_processor_id()); - - /* Synchronize with switch_mm. */ - smp_mb(); + struct flush_tlb_info info = { + .mm = mm, + };

- goto out; - } + cpu = get_cpu();

- if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) - base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* Synchronize with switch_mm. */ + smp_mb();

- /* - * Both branches below are implicit full barriers (MOV to CR or - * INVLPG) that synchronize with switch_mm. - */ - if (base_pages_to_flush > tlb_single_page_flush_ceiling) { - base_pages_to_flush = TLB_FLUSH_ALL; - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); + /* Should we flush just the requested range? */ + if ((end != TLB_FLUSH_ALL) && + !(vmflag & VM_HUGETLB) && + ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) { + info.start = start; + info.end = end; } else { - /* flush range by one by one 'invlpg' */ - for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); - } - } - trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush); -out: - info.mm = mm; - if (base_pages_to_flush == TLB_FLUSH_ALL) { info.start = 0UL; info.end = TLB_FLUSH_ALL; - } else { - info.start = start; - info.end = end; } - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) + + if (mm == current->active_mm) + flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN); + if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), &info); - preempt_enable(); + put_cpu(); }

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