Merge branch 'akpm' (patches from Andrew)

Merge patch-bomb from Andrew Morton:

 - a few misc things

 - Andy's "ambient capabilities"

 - fs/nofity updates

 - the ocfs2 queue

 - kernel/watchdog.c updates and feature work.

 - some of MM.  Includes Andrea's userfaultfd feature.

[ Hadn't noticed that userfaultfd was 'default y' when applying the
  patches, so that got fixed in this merge instead.  We do _not_ mark
  new features that nobody uses yet 'default y'   - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  mm/hugetlb.c: make vma_has_reserves() return bool
  mm/madvise.c: make madvise_behaviour_valid() return bool
  mm/memory.c: make tlb_next_batch() return bool
  mm/dmapool.c: change is_page_busy() return from int to bool
  mm: remove struct node_active_region
  mremap: simplify the "overlap" check in mremap_to()
  mremap: don't do uneccesary checks if new_len == old_len
  mremap: don't do mm_populate(new_addr) on failure
  mm: move ->mremap() from file_operations to vm_operations_struct
  mremap: don't leak new_vma if f_op->mremap() fails
  mm/hugetlb.c: make vma_shareable() return bool
  mm: make GUP handle pfn mapping unless FOLL_GET is requested
  mm: fix status code which move_pages() returns for zero page
  mm: memcontrol: bring back the VM_BUG_ON() in mem_cgroup_swapout()
  genalloc: add support of multiple gen_pools per device
  genalloc: add name arg to gen_pool_get() and devm_gen_pool_create()
  mm/memblock: WARN_ON when nid differs from overlap region
  Documentation/features/vm: add feature description and arch support status for batched TLB flush after unmap
  mm: defer flush of writable TLB entries
  mm: send one IPI per CPU to TLB flush all entries after unmapping pages
  ...

1 files changed, 117 insertions, 1 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index 171b68768df1..0db38e7d0a72 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -62,6 +62,8 @@
 
 #include <asm/tlbflush.h>
 
+#include <trace/events/tlb.h>
+
 #include "internal.h"
 
 static struct kmem_cache *anon_vma_cachep;
@@ -583,6 +585,107 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 	return address;
 }
 
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+static void percpu_flush_tlb_batch_pages(void *data)
+{
+	/*
+	 * All TLB entries are flushed on the assumption that it is
+	 * cheaper to flush all TLBs and let them be refilled than
+	 * flushing individual PFNs. Note that we do not track mm's
+	 * to flush as that might simply be multiple full TLB flushes
+	 * for no gain.
+	 */
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	flush_tlb_local();
+}
+
+/*
+ * Flush TLB entries for recently unmapped pages from remote CPUs. It is
+ * important if a PTE was dirty when it was unmapped that it's flushed
+ * before any IO is initiated on the page to prevent lost writes. Similarly,
+ * it must be flushed before freeing to prevent data leakage.
+ */
+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();
+
+	trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL);
+
+	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask))
+		percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask);
+
+	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) {
+		smp_call_function_many(&tlb_ubc->cpumask,
+			percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true);
+	}
+	cpumask_clear(&tlb_ubc->cpumask);
+	tlb_ubc->flush_required = false;
+	tlb_ubc->writable = false;
+	put_cpu();
+}
+
+/* Flush iff there are potentially writable TLB entries that can race with IO */
+void try_to_unmap_flush_dirty(void)
+{
+	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+
+	if (tlb_ubc->writable)
+		try_to_unmap_flush();
+}
+
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
+		struct page *page, bool writable)
+{
+	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+
+	cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm));
+	tlb_ubc->flush_required = true;
+
+	/*
+	 * If the PTE was dirty then it's best to assume it's writable. The
+	 * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
+	 * before the page is queued for IO.
+	 */
+	if (writable)
+		tlb_ubc->writable = true;
+}
+
+/*
+ * Returns true if the TLB flush should be deferred to the end of a batch of
+ * unmap operations to reduce IPIs.
+ */
+static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
+{
+	bool should_defer = false;
+
+	if (!(flags & TTU_BATCH_FLUSH))
+		return false;
+
+	/* If remote CPUs need to be flushed then defer batch the flush */
+	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
+		should_defer = true;
+	put_cpu();
+
+	return should_defer;
+}
+#else
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
+		struct page *page, bool writable)
+{
+}
+
+static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
+{
+	return false;
+}
+#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
+
 /*
  * At what user virtual address is page expected in vma?
  * Caller should check the page is actually part of the vma.
@@ -1220,7 +1323,20 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 
 	/* Nuke the page table entry. */
 	flush_cache_page(vma, address, page_to_pfn(page));
-	pteval = ptep_clear_flush(vma, address, pte);
+	if (should_defer_flush(mm, flags)) {
+		/*
+		 * We clear the PTE but do not flush so potentially a remote
+		 * CPU could still be writing to the page. If the entry was
+		 * previously clean then the architecture must guarantee that
+		 * a clear->dirty transition on a cached TLB entry is written
+		 * through and traps if the PTE is unmapped.
+		 */
+		pteval = ptep_get_and_clear(mm, address, pte);
+
+		set_tlb_ubc_flush_pending(mm, page, pte_dirty(pteval));
+	} else {
+		pteval = ptep_clear_flush(vma, address, pte);
+	}
 
 	/* Move the dirty bit to the physical page now the pte is gone. */
 	if (pte_dirty(pteval))