mm/mprotect: use mmu_gather

Patch series "mm/mprotect: avoid unnecessary TLB flushes", v6.

This patchset is intended to remove unnecessary TLB flushes during
mprotect() syscalls.  Once this patch-set make it through, similar and
further optimizations for MADV_COLD and userfaultfd would be possible.

Basically, there are 3 optimizations in this patch-set:

1. Use TLB batching infrastructure to batch flushes across VMAs and do
   better/fewer flushes.  This would also be handy for later userfaultfd
   enhancements.

2. Avoid unnecessary TLB flushes.  This optimization is the one that
   provides most of the performance benefits.  Unlike previous versions,
   we now only avoid flushes that would not result in spurious
   page-faults.

3. Avoiding TLB flushes on change_huge_pmd() that are only needed to
   prevent the A/D bits from changing.

Andrew asked for some benchmark numbers.  I do not have an easy
determinate macrobenchmark in which it is easy to show benefit.  I
therefore ran a microbenchmark: a loop that does the following on
anonymous memory, just as a sanity check to see that time is saved by
avoiding TLB flushes.  The loop goes:

	mprotect(p, PAGE_SIZE, PROT_READ)
	mprotect(p, PAGE_SIZE, PROT_READ|PROT_WRITE)
	*p = 0; // make the page writable

The test was run in KVM guest with 1 or 2 threads (the second thread was
busy-looping).  I measured the time (cycles) of each operation:

		1 thread		2 threads
		mmots	+patch		mmots	+patch
PROT_READ	3494	2725 (-22%)	8630	7788 (-10%)
PROT_READ|WRITE	3952	2724 (-31%)	9075	2865 (-68%)

[ mmots = v5.17-rc6-mmots-2022-03-06-20-38 ]

The exact numbers are really meaningless, but the benefit is clear.  There
are 2 interesting results though.  

(1) PROT_READ is cheaper, while one can expect it not to be affected. 
This is presumably due to TLB miss that is saved

(2) Without memory access (*p = 0), the speedup of the patch is even
greater.  In that scenario mprotect(PROT_READ) also avoids the TLB flush. 
As a result both operations on the patched kernel take roughly ~1500
cycles (with either 1 or 2 threads), whereas on mmotm their cost is as
high as presented in the table.


This patch (of 3):

change_pXX_range() currently does not use mmu_gather, but instead
implements its own deferred TLB flushes scheme.  This both complicates the
code, as developers need to be aware of different invalidation schemes,
and prevents opportunities to avoid TLB flushes or perform them in finer
granularity.

The use of mmu_gather for modified PTEs has benefits in various scenarios
even if pages are not released.  For instance, if only a single page needs
to be flushed out of a range of many pages, only that page would be
flushed.  If a THP page is flushed, on x86 a single TLB invlpg instruction
can be used instead of 512 instructions (or a full TLB flush, which would
Linux would actually use by default).  mprotect() over multiple VMAs
requires a single flush.

Use mmu_gather in change_pXX_range().  As the pages are not released, only
record the flushed range using tlb_flush_pXX_range().

Handle THP similarly and get rid of flush_cache_range() which becomes
redundant since tlb_start_vma() calls it when needed.

Link: https://lkml.kernel.org/r/20220401180821.1986781-1-namit@vmware.com
Link: https://lkml.kernel.org/r/20220401180821.1986781-2-namit@vmware.com
Signed-off-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

7 files changed, 82 insertions, 51 deletions

diff --git a/fs/exec.c b/fs/exec.c
index e3e55d5e0be1..14b4b3755580 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -758,6 +758,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	unsigned long stack_size;
 	unsigned long stack_expand;
 	unsigned long rlim_stack;
+	struct mmu_gather tlb;
 
 #ifdef CONFIG_STACK_GROWSUP
 	/* Limit stack size */
@@ -812,8 +813,11 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	vm_flags |= mm->def_flags;
 	vm_flags |= VM_STACK_INCOMPLETE_SETUP;
 
-	ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end,
+	tlb_gather_mmu(&tlb, mm);
+	ret = mprotect_fixup(&tlb, vma, &prev, vma->vm_start, vma->vm_end,
 			vm_flags);
+	tlb_finish_mmu(&tlb);
+
 	if (ret)
 		goto out_unlock;
 	BUG_ON(prev != vma);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 2999190adc22..9a26bd10e083 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -36,8 +36,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud,
 		 unsigned long addr);
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		   unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd);
-int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
-		    pgprot_t newprot, unsigned long cp_flags);
+int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
+		    unsigned long cp_flags);
 vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
 				   pgprot_t pgprot, bool write);
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5dc5005ccc9b..d63ba0e0e068 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1967,10 +1967,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
-extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+extern unsigned long change_protection(struct mmu_gather *tlb,
+			      struct vm_area_struct *vma, unsigned long start,
 			      unsigned long end, pgprot_t newprot,
 			      unsigned long cp_flags);
-extern int mprotect_fixup(struct vm_area_struct *vma,
+extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86eae6834db7..8db17c042aed 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1709,8 +1709,9 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
  *      or if prot_numa but THP migration is not supported
  *  - HPAGE_PMD_NR if protections changed and TLB flush necessary
  */
-int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, pgprot_t newprot, unsigned long cp_flags)
+int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
+		    unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
@@ -1721,6 +1722,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
+
 	if (prot_numa && !thp_migration_supported())
 		return 1;
 
@@ -1819,6 +1822,9 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	}
 	ret = HPAGE_PMD_NR;
 	set_pmd_at(mm, addr, pmd, entry);
+
+	tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
+
 	BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
 unlock:
 	spin_unlock(ptl);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0288ffaea064..3934476fb708 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -104,6 +104,7 @@
 #include <linux/swapops.h>
 
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 #include <linux/uaccess.h>
 
 #include "internal.h"
@@ -630,12 +631,18 @@ unlock:
 unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long addr, unsigned long end)
 {
+	struct mmu_gather tlb;
 	int nr_updated;
 
-	nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA);
+	tlb_gather_mmu(&tlb, vma->vm_mm);
+
+	nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE,
+				       MM_CP_PROT_NUMA);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 
+	tlb_finish_mmu(&tlb);
+
 	return nr_updated;
 }
 #else
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 56060acdabd3..420be0201118 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -33,12 +33,13 @@
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 
 #include "internal.h"
 
-static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		unsigned long cp_flags)
+static unsigned long change_pte_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
@@ -49,6 +50,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
+	tlb_change_page_size(tlb, PAGE_SIZE);
+
 	/*
 	 * Can be called with only the mmap_lock for reading by
 	 * prot_numa so we must check the pmd isn't constantly
@@ -149,6 +152,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				ptent = pte_mkwrite(ptent);
 			}
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
+			tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
@@ -234,9 +238,9 @@ static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
 	return 0;
 }
 
-static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
-		pud_t *pud, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_pmd_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pud_t *pud, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -276,8 +280,12 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			if (next - addr != HPAGE_PMD_SIZE) {
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
 			} else {
-				int nr_ptes = change_huge_pmd(vma, pmd, addr,
-							      newprot, cp_flags);
+				/*
+				 * change_huge_pmd() does not defer TLB flushes,
+				 * so no need to propagate the tlb argument.
+				 */
+				int nr_ptes = change_huge_pmd(tlb, vma, pmd,
+						addr, newprot, cp_flags);
 
 				if (nr_ptes) {
 					if (nr_ptes == HPAGE_PMD_NR) {
@@ -291,8 +299,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			}
 			/* fall through, the trans huge pmd just split */
 		}
-		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-					      cp_flags);
+		this_pages = change_pte_range(tlb, vma, pmd, addr, next,
+					      newprot, cp_flags);
 		pages += this_pages;
 next:
 		cond_resched();
@@ -306,9 +314,9 @@ next:
 	return pages;
 }
 
-static inline unsigned long change_pud_range(struct vm_area_struct *vma,
-		p4d_t *p4d, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_pud_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -319,16 +327,16 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		pages += change_pmd_range(vma, pud, addr, next, newprot,
+		pages += change_pmd_range(tlb, vma, pud, addr, next, newprot,
 					  cp_flags);
 	} while (pud++, addr = next, addr != end);
 
 	return pages;
 }
 
-static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
-		pgd_t *pgd, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_p4d_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	p4d_t *p4d;
 	unsigned long next;
@@ -339,44 +347,40 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 		next = p4d_addr_end(addr, end);
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
-		pages += change_pud_range(vma, p4d, addr, next, newprot,
+		pages += change_pud_range(tlb, vma, p4d, addr, next, newprot,
 					  cp_flags);
 	} while (p4d++, addr = next, addr != end);
 
 	return pages;
 }
 
-static unsigned long change_protection_range(struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		unsigned long cp_flags)
+static unsigned long change_protection_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long start = addr;
 	unsigned long pages = 0;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
-	flush_cache_range(vma, addr, end);
-	inc_tlb_flush_pending(mm);
+	tlb_start_vma(tlb, vma);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		pages += change_p4d_range(vma, pgd, addr, next, newprot,
+		pages += change_p4d_range(tlb, vma, pgd, addr, next, newprot,
 					  cp_flags);
 	} while (pgd++, addr = next, addr != end);
 
-	/* Only flush the TLB if we actually modified any entries: */
-	if (pages)
-		flush_tlb_range(vma, start, end);
-	dec_tlb_flush_pending(mm);
+	tlb_end_vma(tlb, vma);
 
 	return pages;
 }
 
-unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+unsigned long change_protection(struct mmu_gather *tlb,
+		       struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
 		       unsigned long cp_flags)
 {
@@ -387,7 +391,7 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
-		pages = change_protection_range(vma, start, end, newprot,
+		pages = change_protection_range(tlb, vma, start, end, newprot,
 						cp_flags);
 
 	return pages;
@@ -421,8 +425,9 @@ static const struct mm_walk_ops prot_none_walk_ops = {
 };
 
 int
-mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
-	unsigned long start, unsigned long end, unsigned long newflags)
+mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma,
+	       struct vm_area_struct **pprev, unsigned long start,
+	       unsigned long end, unsigned long newflags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long oldflags = vma->vm_flags;
@@ -509,7 +514,7 @@ success:
 	dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
 	vma_set_page_prot(vma);
 
-	change_protection(vma, start, end, vma->vm_page_prot,
+	change_protection(tlb, vma, start, end, vma->vm_page_prot,
 			  dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
 
 	/*
@@ -543,6 +548,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
+	struct mmu_gather tlb;
 
 	start = untagged_addr(start);
 
@@ -602,6 +608,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	else
 		prev = vma->vm_prev;
 
+	tlb_gather_mmu(&tlb, current->mm);
 	for (nstart = start ; ; ) {
 		unsigned long mask_off_old_flags;
 		unsigned long newflags;
@@ -628,18 +635,18 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
 			error = -EACCES;
-			goto out;
+			break;
 		}
 
 		/* Allow architectures to sanity-check the new flags */
 		if (!arch_validate_flags(newflags)) {
 			error = -EINVAL;
-			goto out;
+			break;
 		}
 
 		error = security_file_mprotect(vma, reqprot, prot);
 		if (error)
-			goto out;
+			break;
 
 		tmp = vma->vm_end;
 		if (tmp > end)
@@ -648,27 +655,28 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		if (vma->vm_ops && vma->vm_ops->mprotect) {
 			error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
 			if (error)
-				goto out;
+				break;
 		}
 
-		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
+		error = mprotect_fixup(&tlb, vma, &prev, nstart, tmp, newflags);
 		if (error)
-			goto out;
+			break;
 
 		nstart = tmp;
 
 		if (nstart < prev->vm_end)
 			nstart = prev->vm_end;
 		if (nstart >= end)
-			goto out;
+			break;
 
 		vma = prev->vm_next;
 		if (!vma || vma->vm_start != nstart) {
 			error = -ENOMEM;
-			goto out;
+			break;
 		}
 		prot = reqprot;
 	}
+	tlb_finish_mmu(&tlb);
 out:
 	mmap_write_unlock(current->mm);
 	return error;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index dae25d985d15..9cdaed939203 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -16,6 +16,7 @@
 #include <linux/hugetlb.h>
 #include <linux/shmem_fs.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 #include "internal.h"
 
 static __always_inline
@@ -687,6 +688,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 			atomic_t *mmap_changing)
 {
 	struct vm_area_struct *dst_vma;
+	struct mmu_gather tlb;
 	pgprot_t newprot;
 	int err;
 
@@ -728,8 +730,10 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 	else
 		newprot = vm_get_page_prot(dst_vma->vm_flags);
 
-	change_protection(dst_vma, start, start + len, newprot,
+	tlb_gather_mmu(&tlb, dst_mm);
+	change_protection(&tlb, dst_vma, start, start + len, newprot,
 			  enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE);
+	tlb_finish_mmu(&tlb);
 
 	err = 0;
 out_unlock: