[Devel] [PATCH RHEL7 COMMIT] ms/mm: replace remap_file_pages() syscall with emulation

Kirill Tkhai ktkhai at virtuozzo.com
Mon Oct 3 07:28:27 PDT 2016


The commit is pushed to "branch-rh7-3.10.0-327.36.1.vz7.18.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.36.1.vz7.18.3
------>
commit 11f0d41e66bebde9aa8e07ec998bede873c356e5
Author: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
Date:   Mon Oct 3 14:27:25 2016 +0000

    ms/mm: replace remap_file_pages() syscall with emulation
    
    remap_file_pages(2) was invented to be able efficiently map parts of
    huge file into limited 32-bit virtual address space such as in database
    workloads.
    
    Nonlinear mappings are pain to support and it seems there's no
    legitimate use-cases nowadays since 64-bit systems are widely available.
    
    Let's drop it and get rid of all these special-cased code.
    
    The patch replaces the syscall with emulation which creates new VMA on
    each remap_file_pages(), unless they it can be merged with an adjacent
    one.
    
    I didn't find *any* real code that uses remap_file_pages(2) to test
    emulation impact on.  I've checked Debian code search and source of all
    packages in ALT Linux.  No real users: libc wrappers, mentions in
    strace, gdb, valgrind and this kind of stuff.
    
    There are few basic tests in LTP for the syscall.  They work just fine
    with emulation.
    
    To test performance impact, I've written small test case which
    demonstrate pretty much worst case scenario: map 4G shmfs file, write to
    begin of every page pgoff of the page, remap pages in reverse order,
    read every page.
    
    The test creates 1 million of VMAs if emulation is in use, so I had to
    set vm.max_map_count to 1100000 to avoid -ENOMEM.
    
    Before:		23.3 ( +-  4.31% ) seconds
    After:		43.9 ( +-  0.85% ) seconds
    Slowdown:	1.88x
    
    I believe we can live with that.
    
    Test case:
    
            #define _GNU_SOURCE
            #include <assert.h>
            #include <stdlib.h>
            #include <stdio.h>
            #include <sys/mman.h>
    
            #define MB	(1024UL * 1024)
            #define SIZE	(4096 * MB)
    
            int main(int argc, char **argv)
            {
                    unsigned long *p;
                    long i, pass;
    
                    for (pass = 0; pass < 10; pass++) {
                            p = mmap(NULL, SIZE, PROT_READ|PROT_WRITE,
                                            MAP_SHARED | MAP_ANONYMOUS, -1, 0);
                            if (p == MAP_FAILED) {
                                    perror("mmap");
                                    return -1;
                            }
    
                            for (i = 0; i < SIZE / 4096; i++)
                                    p[i * 4096 / sizeof(*p)] = i;
    
                            for (i = 0; i < SIZE / 4096; i++) {
                                    if (remap_file_pages(p + i * 4096 / sizeof(*p), 4096,
                                                    0, (SIZE - 4096 * (i + 1)) >> 12, 0)) {
                                            perror("remap_file_pages");
                                            return -1;
                                    }
                            }
    
                            for (i = SIZE / 4096 - 1; i >= 0; i--)
                                    assert(p[i * 4096 / sizeof(*p)] == SIZE / 4096 - i - 1);
    
                            munmap(p, SIZE);
                    }
    
                    return 0;
            }
    
    [akpm at linux-foundation.org: fix spello]
    [sasha.levin at oracle.com: initialize populate before usage]
    [sasha.levin at oracle.com: grab file ref to prevent race while mmaping]
    Signed-off-by: "Kirill A. Shutemov" <kirill at shutemov.name>
    Cc: Peter Zijlstra <peterz at infradead.org>
    Cc: Ingo Molnar <mingo at kernel.org>
    Cc: Dave Jones <davej at redhat.com>
    Cc: Linus Torvalds <torvalds at linux-foundation.org>
    Cc: Armin Rigo <arigo at tunes.org>
    Signed-off-by: Sasha Levin <sasha.levin at oracle.com>
    Cc: Hugh Dickins <hughd at google.com>
    Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
    
    https://jira.sw.ru/browse/PSBM-52992
    
    (cherry picked from commit c8d78c1823f46519473949d33f0d1d33fe21ea16)
    Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
    Reviewed-by: Cyrill Gorcunov <gorcunov at openvz.org>
---
 Documentation/vm/remap_file_pages.txt |  27 ++++
 include/linux/fs.h                    |   8 +-
 mm/Makefile                           |   2 +-
 mm/fremap.c                           | 264 ----------------------------------
 mm/mmap.c                             |  69 +++++++++
 mm/nommu.c                            |   8 --
 6 files changed, 103 insertions(+), 275 deletions(-)

diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.txt
new file mode 100644
index 0000000..f609142
--- /dev/null
+++ b/Documentation/vm/remap_file_pages.txt
@@ -0,0 +1,27 @@
+The remap_file_pages() system call is used to create a nonlinear mapping,
+that is, a mapping in which the pages of the file are mapped into a
+nonsequential order in memory. The advantage of using remap_file_pages()
+over using repeated calls to mmap(2) is that the former approach does not
+require the kernel to create additional VMA (Virtual Memory Area) data
+structures.
+
+Supporting of nonlinear mapping requires significant amount of non-trivial
+code in kernel virtual memory subsystem including hot paths. Also to get
+nonlinear mapping work kernel need a way to distinguish normal page table
+entries from entries with file offset (pte_file). Kernel reserves flag in
+PTE for this purpose. PTE flags are scarce resource especially on some CPU
+architectures. It would be nice to free up the flag for other usage.
+
+Fortunately, there are not many users of remap_file_pages() in the wild.
+It's only known that one enterprise RDBMS implementation uses the syscall
+on 32-bit systems to map files bigger than can linearly fit into 32-bit
+virtual address space. This use-case is not critical anymore since 64-bit
+systems are widely available.
+
+The syscall is deprecated and replaced it with an emulation now. The
+emulation creates new VMAs instead of nonlinear mappings. It's going to
+work slower for rare users of remap_file_pages() but ABI is preserved.
+
+One side effect of emulation (apart from performance) is that user can hit
+vm.max_map_count limit more easily due to additional VMAs. See comment for
+DEFAULT_MAX_MAP_COUNT for more details on the limit.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed9519f..683b2b3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2809,9 +2809,13 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
-		unsigned long size, pgoff_t pgoff);
 extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
+static inline int generic_file_remap_pages(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long size, pgoff_t pgoff)
+{
+	BUG();
+	return 0;
+}
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *, loff_t);
diff --git a/mm/Makefile b/mm/Makefile
index 4c3899b..ea2a36e 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -6,7 +6,7 @@ KASAN_SANITIZE_slab_common.o := n
 KASAN_SANITIZE_slub.o := n
 
 mmu-y			:= nommu.o
-mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
+mmu-$(CONFIG_MMU)	:= highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
 			   vmalloc.o pagewalk.o pgtable-generic.o
 
diff --git a/mm/fremap.c b/mm/fremap.c
deleted file mode 100644
index 8a6482b..0000000
--- a/mm/fremap.c
+++ /dev/null
@@ -1,264 +0,0 @@
-/*
- *   linux/mm/fremap.c
- * 
- * Explicit pagetable population and nonlinear (random) mappings support.
- *
- * started by Ingo Molnar, Copyright (C) 2002, 2003
- */
-#include <linux/export.h>
-#include <linux/backing-dev.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/file.h>
-#include <linux/mman.h>
-#include <linux/pagemap.h>
-#include <linux/swapops.h>
-#include <linux/rmap.h>
-#include <linux/syscalls.h>
-#include <linux/mmu_notifier.h>
-#include <linux/module.h>
-
-#include <asm/mmu_context.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-#include <bc/vmpages.h>
-
-#include "internal.h"
-
-static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long addr, pte_t *ptep)
-{
-	pte_t pte = *ptep;
-
-	if (pte_present(pte)) {
-		struct page *page;
-
-		flush_cache_page(vma, addr, pte_pfn(pte));
-		pte = ptep_clear_flush_notify(vma, addr, ptep);
-		page = vm_normal_page(vma, addr, pte);
-		if (page) {
-			if (pte_dirty(pte))
-				set_page_dirty_mm(page, mm);
-			page_remove_rmap(page);
-			page_cache_release(page);
-			update_hiwater_rss(mm);
-			dec_mm_counter(mm, MM_FILEPAGES);
-		}
-	} else {
-		if (!pte_file(pte))
-			free_swap_and_cache(pte_to_swp_entry(pte));
-		pte_clear_not_present_full(mm, addr, ptep, 0);
-	}
-}
-
-/*
- * Install a file pte to a given virtual memory address, release any
- * previously existing mapping.
- */
-static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long pgoff, pgprot_t prot)
-{
-	int err = -ENOMEM;
-	pte_t *pte, ptfile;
-	spinlock_t *ptl;
-
-	pte = get_locked_pte(mm, addr, &ptl);
-	if (!pte)
-		goto out;
-
-	ptfile = pgoff_to_pte(pgoff);
-
-	if (!pte_none(*pte))
-		zap_pte(mm, vma, addr, pte);
-
-	set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile));
-	/*
-	 * We don't need to run update_mmu_cache() here because the "file pte"
-	 * being installed by install_file_pte() is not a real pte - it's a
-	 * non-present entry (like a swap entry), noting what file offset should
-	 * be mapped there when there's a fault (in a non-linear vma where
-	 * that's not obvious).
-	 */
-	pte_unmap_unlock(pte, ptl);
-	err = 0;
-out:
-	return err;
-}
-
-int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
-			     unsigned long size, pgoff_t pgoff)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	int err;
-
-	do {
-		err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
-		if (err)
-			return err;
-
-		size -= PAGE_SIZE;
-		addr += PAGE_SIZE;
-		pgoff++;
-	} while (size);
-
-	return 0;
-}
-EXPORT_SYMBOL(generic_file_remap_pages);
-
-/**
- * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma
- * @start: start of the remapped virtual memory range
- * @size: size of the remapped virtual memory range
- * @prot: new protection bits of the range (see NOTE)
- * @pgoff: to-be-mapped page of the backing store file
- * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
- *
- * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma
- * (shared backing store file).
- *
- * This syscall works purely via pagetables, so it's the most efficient
- * way to map the same (large) file into a given virtual window. Unlike
- * mmap()/mremap() it does not create any new vmas. The new mappings are
- * also safe across swapout.
- *
- * NOTE: the @prot parameter right now is ignored (but must be zero),
- * and the vma's default protection is used. Arbitrary protections
- * might be implemented in the future.
- */
-SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
-		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
-{
-	struct mm_struct *mm = current->mm;
-	struct address_space *mapping;
-	struct vm_area_struct *vma;
-	int err = -EINVAL;
-	int has_write_lock = 0;
-	vm_flags_t vm_flags = 0;
-
-	if (prot)
-		return err;
-	/*
-	 * Sanitize the syscall parameters:
-	 */
-	start = start & PAGE_MASK;
-	size = size & PAGE_MASK;
-
-	/* Does the address range wrap, or is the span zero-sized? */
-	if (start + size <= start)
-		return err;
-
-	/* Does pgoff wrap? */
-	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
-		return err;
-
-	/* Can we represent this offset inside this architecture's pte's? */
-#if PTE_FILE_MAX_BITS < BITS_PER_LONG
-	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
-		return err;
-#endif
-
-	/* We need down_write() to change vma->vm_flags. */
-	down_read(&mm->mmap_sem);
- retry:
-	vma = find_vma(mm, start);
-
-	/*
-	 * Make sure the vma is shared, that it supports prefaulting,
-	 * and that the remapped range is valid and fully within
-	 * the single existing vma.
-	 */
-	if (!vma || !(vma->vm_flags & VM_SHARED))
-		goto out;
-
-	if (!vma->vm_ops || !vma->vm_ops->remap_pages)
-		goto out;
-
-	if (start < vma->vm_start || start + size > vma->vm_end)
-		goto out;
-
-	/* Must set VM_NONLINEAR before any pages are populated. */
-	if (!(vma->vm_flags & VM_NONLINEAR)) {
-		/*
-		 * vm_private_data is used as a swapout cursor
-		 * in a VM_NONLINEAR vma.
-		 */
-		if (vma->vm_private_data)
-			goto out;
-
-		/* Don't need a nonlinear mapping, exit success */
-		if (pgoff == linear_page_index(vma, start)) {
-			err = 0;
-			goto out;
-		}
-
-		if (!has_write_lock) {
-get_write_lock:
-			up_read(&mm->mmap_sem);
-			down_write(&mm->mmap_sem);
-			has_write_lock = 1;
-			goto retry;
-		}
-		mapping = vma->vm_file->f_mapping;
-		/*
-		 * page_mkclean doesn't work on nonlinear vmas, so if
-		 * dirty pages need to be accounted, emulate with linear
-		 * vmas.
-		 */
-		if (mapping_cap_account_dirty(mapping)) {
-			unsigned long addr;
-			struct file *file = get_file(vma->vm_file);
-
-			addr = mmap_region(file, start, size,
-					vma->vm_flags, pgoff);
-			fput(file);
-			if (IS_ERR_VALUE(addr)) {
-				err = addr;
-			} else {
-				BUG_ON(addr != start);
-				err = 0;
-			}
-			goto out;
-		}
-		mutex_lock(&mapping->i_mmap_mutex);
-		flush_dcache_mmap_lock(mapping);
-		vma->vm_flags |= VM_NONLINEAR;
-		vma_interval_tree_remove(vma, &mapping->i_mmap);
-		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
-		flush_dcache_mmap_unlock(mapping);
-		mutex_unlock(&mapping->i_mmap_mutex);
-	}
-
-	if (vma->vm_flags & VM_LOCKED) {
-		/*
-		 * drop PG_Mlocked flag for over-mapped range
-		 */
-		if (!has_write_lock)
-			goto get_write_lock;
-		vm_flags = vma->vm_flags;
-		__munlock_vma_pages_range(vma, start, start + size, 0);
-		vma->vm_flags = vm_flags;
-	}
-
-	mmu_notifier_invalidate_range_start(mm, start, start + size);
-	err = vma->vm_ops->remap_pages(vma, start, size, pgoff);
-	mmu_notifier_invalidate_range_end(mm, start, start + size);
-
-	/*
-	 * We can't clear VM_NONLINEAR because we'd have to do
-	 * it after ->populate completes, and that would prevent
-	 * downgrading the lock.  (Locks can't be upgraded).
-	 */
-
-out:
-	if (vma)
-		vm_flags = vma->vm_flags;
-	if (likely(!has_write_lock))
-		up_read(&mm->mmap_sem);
-	else
-		up_write(&mm->mmap_sem);
-	if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK)))
-		mm_populate(start, size);
-
-	return err;
-}
diff --git a/mm/mmap.c b/mm/mmap.c
index fcd1ea3..eeebddc 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2674,6 +2674,75 @@ SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 	return vm_munmap(addr, len);
 }
 
+
+/*
+ * Emulation of deprecated remap_file_pages() syscall.
+ */
+SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
+{
+
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long populate = 0;
+	unsigned long ret = -EINVAL;
+	struct file *file;
+
+	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
+			"See Documentation/vm/remap_file_pages.txt.\n",
+			current->comm, current->pid);
+
+	if (prot)
+		return ret;
+	start = start & PAGE_MASK;
+	size = size & PAGE_MASK;
+
+	if (start + size <= start)
+		return ret;
+
+	/* Does pgoff wrap? */
+	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
+		return ret;
+
+	down_write(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+
+	if (!vma || !(vma->vm_flags & VM_SHARED))
+		goto out;
+
+	if (start < vma->vm_start || start + size > vma->vm_end)
+		goto out;
+
+	if (pgoff == linear_page_index(vma, start)) {
+		ret = 0;
+		goto out;
+	}
+
+	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
+	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
+	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
+
+	flags &= MAP_NONBLOCK;
+	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
+	if (vma->vm_flags & VM_LOCKED) {
+		flags |= MAP_LOCKED;
+		/* drop PG_Mlocked flag for over-mapped range */
+		munlock_vma_pages_range(vma, start, start + size);
+	}
+
+	file = get_file(vma->vm_file);
+	ret = do_mmap_pgoff(vma->vm_file, start, size,
+			prot, flags, pgoff, &populate);
+	fput(file);
+out:
+	up_write(&mm->mmap_sem);
+	if (populate)
+		mm_populate(ret, populate);
+	if (!IS_ERR_VALUE(ret))
+		ret = 0;
+	return ret;
+}
+
 static inline void verify_mm_writelocked(struct mm_struct *mm)
 {
 #ifdef CONFIG_DEBUG_VM
diff --git a/mm/nommu.c b/mm/nommu.c
index c4dd6b4..e6aca48 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -2020,14 +2020,6 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
-int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
-			     unsigned long size, pgoff_t pgoff)
-{
-	BUG();
-	return 0;
-}
-EXPORT_SYMBOL(generic_file_remap_pages);
-
 static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, int write)
 {


More information about the Devel mailing list