The patch titled
Subject: mm: introduce mm_populate() for populating new vmas
has been added to the -mm tree. Its filename is
mm-introduce-mm_populate-for-populating-new-vmas.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Michel Lespinasse <walken@xxxxxxxxxx>
Subject: mm: introduce mm_populate() for populating new vmas
When creating new mappings using the MAP_POPULATE / MAP_LOCKED flags
(or with MCL_FUTURE in effect), we want to populate the pages within the
newly created vmas. This may take a while as we may have to read pages
from disk, so ideally we want to do this outside of the write-locked
mmap_sem region.
This change introduces mm_populate(), which is used to defer populating
such mappings until after the mmap_sem write lock has been released.
This is implemented as a generalization of the former do_mlock_pages(),
which accomplished the same task but was using during mlock() / mlockall().
Signed-off-by: Michel Lespinasse <walken@xxxxxxxxxx>
Reported-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
Tested-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Greg Ungerer <gregungerer@xxxxxxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/aio.c | 6 +++++-
include/linux/mm.h | 18 +++++++++++++++---
ipc/shm.c | 12 +++++++-----
mm/mlock.c | 17 +++++++++++------
mm/mmap.c | 20 +++++++++++++++-----
mm/nommu.c | 5 ++++-
mm/util.c | 6 +++++-
7 files changed, 62 insertions(+), 22 deletions(-)
diff -puN fs/aio.c~mm-introduce-mm_populate-for-populating-new-vmas fs/aio.c
--- a/fs/aio.c~mm-introduce-mm_populate-for-populating-new-vmas
+++ a/fs/aio.c
@@ -103,6 +103,7 @@ static int aio_setup_ring(struct kioctx
unsigned nr_events = ctx->max_reqs;
unsigned long size;
int nr_pages;
+ bool populate;
/* Compensate for the ring buffer's head/tail overlap entry */
nr_events += 2; /* 1 is required, 2 for good luck */
@@ -129,7 +130,8 @@ static int aio_setup_ring(struct kioctx
down_write(&ctx->mm->mmap_sem);
info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size,
PROT_READ|PROT_WRITE,
- MAP_ANONYMOUS|MAP_PRIVATE, 0);
+ MAP_ANONYMOUS|MAP_PRIVATE, 0,
+ &populate);
if (IS_ERR((void *)info->mmap_base)) {
up_write(&ctx->mm->mmap_sem);
info->mmap_size = 0;
@@ -147,6 +149,8 @@ static int aio_setup_ring(struct kioctx
aio_free_ring(ctx);
return -EAGAIN;
}
+ if (populate)
+ mm_populate(info->mmap_base, info->mmap_size);
ctx->user_id = info->mmap_base;
diff -puN include/linux/mm.h~mm-introduce-mm_populate-for-populating-new-vmas include/linux/mm.h
--- a/include/linux/mm.h~mm-introduce-mm_populate-for-populating-new-vmas
+++ a/include/linux/mm.h
@@ -1476,11 +1476,23 @@ extern unsigned long get_unmapped_area(s
extern unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, unsigned long flags,
vm_flags_t vm_flags, unsigned long pgoff);
-extern unsigned long do_mmap_pgoff(struct file *, unsigned long,
- unsigned long, unsigned long,
- unsigned long, unsigned long);
+extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long prot, unsigned long flags,
+ unsigned long pgoff, bool *populate);
extern int do_munmap(struct mm_struct *, unsigned long, size_t);
+#ifdef CONFIG_MMU
+extern int __mm_populate(unsigned long addr, unsigned long len,
+ int ignore_errors);
+static inline void mm_populate(unsigned long addr, unsigned long len)
+{
+ /* Ignore errors */
+ (void) __mm_populate(addr, len, 1);
+}
+#else
+static inline void mm_populate(unsigned long addr, unsigned long len) {}
+#endif
+
/* These take the mm semaphore themselves */
extern unsigned long vm_brk(unsigned long, unsigned long);
extern int vm_munmap(unsigned long, size_t);
diff -puN ipc/shm.c~mm-introduce-mm_populate-for-populating-new-vmas ipc/shm.c
--- a/ipc/shm.c~mm-introduce-mm_populate-for-populating-new-vmas
+++ a/ipc/shm.c
@@ -967,11 +967,11 @@ long do_shmat(int shmid, char __user *sh
unsigned long flags;
unsigned long prot;
int acc_mode;
- unsigned long user_addr;
struct ipc_namespace *ns;
struct shm_file_data *sfd;
struct path path;
fmode_t f_mode;
+ bool populate = false;
err = -EINVAL;
if (shmid < 0)
@@ -1070,13 +1070,15 @@ long do_shmat(int shmid, char __user *sh
goto invalid;
}
- user_addr = do_mmap_pgoff(file, addr, size, prot, flags, 0);
- *raddr = user_addr;
+ addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
+ *raddr = addr;
err = 0;
- if (IS_ERR_VALUE(user_addr))
- err = (long)user_addr;
+ if (IS_ERR_VALUE(addr))
+ err = (long)addr;
invalid:
up_write(¤t->mm->mmap_sem);
+ if (populate)
+ mm_populate(addr, size);
out_fput:
fput(file);
diff -puN mm/mlock.c~mm-introduce-mm_populate-for-populating-new-vmas mm/mlock.c
--- a/mm/mlock.c~mm-introduce-mm_populate-for-populating-new-vmas
+++ a/mm/mlock.c
@@ -416,7 +416,14 @@ static int do_mlock(unsigned long start,
return error;
}
-static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors)
+/*
+ * __mm_populate - populate and/or mlock pages within a range of address space.
+ *
+ * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
+ * flags. VMAs must be already marked with the desired vm_flags, and
+ * mmap_sem must not be held.
+ */
+int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
{
struct mm_struct *mm = current->mm;
unsigned long end, nstart, nend;
@@ -498,7 +505,7 @@ SYSCALL_DEFINE2(mlock, unsigned long, st
error = do_mlock(start, len, 1);
up_write(¤t->mm->mmap_sem);
if (!error)
- error = do_mlock_pages(start, len, 0);
+ error = __mm_populate(start, len, 0);
return error;
}
@@ -565,10 +572,8 @@ SYSCALL_DEFINE1(mlockall, int, flags)
capable(CAP_IPC_LOCK))
ret = do_mlockall(flags);
up_write(¤t->mm->mmap_sem);
- if (!ret && (flags & MCL_CURRENT)) {
- /* Ignore errors */
- do_mlock_pages(0, TASK_SIZE, 1);
- }
+ if (!ret && (flags & MCL_CURRENT))
+ mm_populate(0, TASK_SIZE);
out:
return ret;
}
diff -puN mm/mmap.c~mm-introduce-mm_populate-for-populating-new-vmas mm/mmap.c
--- a/mm/mmap.c~mm-introduce-mm_populate-for-populating-new-vmas
+++ a/mm/mmap.c
@@ -1153,12 +1153,15 @@ static inline unsigned long round_hint_t
unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
- unsigned long flags, unsigned long pgoff)
+ unsigned long flags, unsigned long pgoff,
+ bool *populate)
{
struct mm_struct * mm = current->mm;
struct inode *inode;
vm_flags_t vm_flags;
+ *populate = false;
+
/*
* Does the application expect PROT_READ to imply PROT_EXEC?
*
@@ -1279,7 +1282,12 @@ unsigned long do_mmap_pgoff(struct file
}
}
- return mmap_region(file, addr, len, flags, vm_flags, pgoff);
+ addr = mmap_region(file, addr, len, flags, vm_flags, pgoff);
+ if (!IS_ERR_VALUE(addr) &&
+ ((vm_flags & VM_LOCKED) ||
+ (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
+ *populate = true;
+ return addr;
}
SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
@@ -1530,10 +1538,12 @@ out:
vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
- if (!mlock_vma_pages_range(vma, addr, addr + len))
+ if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||
+ vma == get_gate_vma(current->mm)))
mm->locked_vm += (len >> PAGE_SHIFT);
- } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
- make_pages_present(addr, addr + len);
+ else
+ vma->vm_flags &= ~VM_LOCKED;
+ }
if (file)
uprobe_mmap(vma);
diff -puN mm/nommu.c~mm-introduce-mm_populate-for-populating-new-vmas mm/nommu.c
--- a/mm/nommu.c~mm-introduce-mm_populate-for-populating-new-vmas
+++ a/mm/nommu.c
@@ -1249,7 +1249,8 @@ unsigned long do_mmap_pgoff(struct file
unsigned long len,
unsigned long prot,
unsigned long flags,
- unsigned long pgoff)
+ unsigned long pgoff,
+ bool *populate)
{
struct vm_area_struct *vma;
struct vm_region *region;
@@ -1259,6 +1260,8 @@ unsigned long do_mmap_pgoff(struct file
kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
+ *populate = false;
+
/* decide whether we should attempt the mapping, and if so what sort of
* mapping */
ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
diff -puN mm/util.c~mm-introduce-mm_populate-for-populating-new-vmas mm/util.c
--- a/mm/util.c~mm-introduce-mm_populate-for-populating-new-vmas
+++ a/mm/util.c
@@ -355,12 +355,16 @@ unsigned long vm_mmap_pgoff(struct file
{
unsigned long ret;
struct mm_struct *mm = current->mm;
+ bool populate;
ret = security_mmap_file(file, prot, flag);
if (!ret) {
down_write(&mm->mmap_sem);
- ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff);
+ ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
+ &populate);
up_write(&mm->mmap_sem);
+ if (!IS_ERR_VALUE(ret) && populate)
+ mm_populate(ret, len);
}
return ret;
}
_
Patches currently in -mm which might be from walken@xxxxxxxxxx are
linux-next.patch
mm-make-mlockall-preserve-flags-other-than-vm_locked-in-def_flags.patch
mm-remap_file_pages-fixes.patch
mm-introduce-mm_populate-for-populating-new-vmas.patch
mm-use-mm_populate-for-blocking-remap_file_pages.patch
mm-use-mm_populate-when-adjusting-brk-with-mcl_future-in-effect.patch
mm-use-mm_populate-for-mremap-of-vm_locked-vmas.patch
mm-remove-flags-argument-to-mmap_region.patch
mm-remove-flags-argument-to-mmap_region-fix.patch
mm-directly-use-__mlock_vma_pages_range-in-find_extend_vma.patch
mm-introduce-vm_populate-flag-to-better-deal-with-racy-userspace-programs.patch
mm-make-do_mmap_pgoff-return-populate-as-a-size-in-bytes-not-as-a-bool.patch
mtd-mtd_nandecctest-use-prandom_bytes-instead-of-get_random_bytes.patch
mtd-mtd_oobtest-convert-to-use-prandom-library.patch
mtd-mtd_pagetest-convert-to-use-prandom-library.patch
mtd-mtd_speedtest-use-prandom_bytes.patch
mtd-mtd_subpagetest-convert-to-use-prandom-library.patch
mtd-mtd_stresstest-use-prandom_bytes.patch
mutex-subsystem-synchro-test-module.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
