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

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.git.luto@kernel.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/tlbbatch.h

+#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 */

arch/x86/include/asm/tlbflush.h

@@ -329,6 +329,14 @@ static inline void reset_lazy_tlbstate(void)
 	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

arch/x86/mm/tlb.c

@@ -395,6 +395,23 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
+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)
 {

include/linux/mm_types_task.h

@@ -14,6 +14,10 @@
 
 #include <asm/page.h>
 
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+#include <asm/tlbbatch.h>
+#endif
+
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 #define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
 		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
@@ -67,12 +71,15 @@ struct page_frag {
 struct tlbflush_unmap_batch {
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	/*
-	 * 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;
 
 	/*

mm/rmap.c

@@ -579,25 +579,13 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 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(struct mm_struct *mm, bool writable)
 {
 	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;
 
 	/*