The patch titled
Subject: hugetlbfs: extend hugetlb_vma_lock to private VMAs
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
hugetlbfs-extend-hugetlb_vma_lock-to-private-vmas.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hugetlbfs-extend-hugetlb_vma_lock-to-private-vmas.patch
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Rik van Riel <riel@xxxxxxxxxxx>
Subject: hugetlbfs: extend hugetlb_vma_lock to private VMAs
Date: Sat, 30 Sep 2023 20:55:48 -0400
Patch series "hugetlbfs: close race between MADV_DONTNEED and page fault",
v5.
Malloc libraries, like jemalloc and tcalloc, take decisions on when to
call madvise independently from the code in the main application.
This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.
Usually this is harmless, because we always have some 4kB pages sitting
around to satisfy a page fault. However, with hugetlbfs systems often
allocate only the exact number of huge pages that the application wants.
Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:
CPU 1 CPU 2
MADV_DONTNEED
unmap page
shoot down TLB entry
page fault
fail to allocate a huge page
killed with SIGBUS
free page
Fix that race by extending the hugetlb_vma_lock locking scheme to also
cover private hugetlb mappings (with resv_map), and pulling the locking
from __unmap_hugepage_final_range into helper functions called from
zap_page_range_single. This ensures page faults stay locked out of the
MADV_DONTNEED VMA until the huge pages have actually been freed.
This patch (of 2):
Extend the locking scheme used to protect shared hugetlb mappings from
truncate vs page fault races, in order to protect private hugetlb mappings
(with resv_map) against MADV_DONTNEED.
Add a read-write semaphore to the resv_map data structure, and use that
from the hugetlb_vma_(un)lock_* functions, in preparation for closing the
race between MADV_DONTNEED and page faults.
Link: https://lkml.kernel.org/r/20231001005659.2185316-1-riel@xxxxxxxxxxx
Link: https://lkml.kernel.org/r/20231001005659.2185316-2-riel@xxxxxxxxxxx
Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
Reviewed-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Muchun Song <muchun.song@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 6 +++++
mm/hugetlb.c | 41 ++++++++++++++++++++++++++++++++++----
2 files changed, 43 insertions(+), 4 deletions(-)
--- a/include/linux/hugetlb.h~hugetlbfs-extend-hugetlb_vma_lock-to-private-vmas
+++ a/include/linux/hugetlb.h
@@ -60,6 +60,7 @@ struct resv_map {
long adds_in_progress;
struct list_head region_cache;
long region_cache_count;
+ struct rw_semaphore rw_sema;
#ifdef CONFIG_CGROUP_HUGETLB
/*
* On private mappings, the counter to uncharge reservations is stored
@@ -1233,6 +1234,11 @@ static inline bool __vma_shareable_lock(
return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
}
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+ return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
/*
* Safe version of huge_pte_offset() to check the locks. See comments
* above huge_pte_offset().
--- a/mm/hugetlb.c~hugetlbfs-extend-hugetlb_vma_lock-to-private-vmas
+++ a/mm/hugetlb.c
@@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struc
static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_are
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
down_read(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ down_read(&resv_map->rw_sema);
}
}
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_a
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
up_read(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ up_read(&resv_map->rw_sema);
}
}
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_ar
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
down_write(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ down_write(&resv_map->rw_sema);
}
}
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
up_write(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ up_write(&resv_map->rw_sema);
}
}
int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
{
- struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
- if (!__vma_shareable_lock(vma))
- return 1;
+ if (__vma_shareable_lock(vma)) {
+ struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
- return down_write_trylock(&vma_lock->rw_sema);
+ return down_write_trylock(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ return down_write_trylock(&resv_map->rw_sema);
+ }
+
+ return 1;
}
void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
lockdep_assert_held(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ lockdep_assert_held(&resv_map->rw_sema);
}
}
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_f
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
__hugetlb_vma_unlock_write_put(vma_lock);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ /* no free for anon vmas, but still need to unlock */
+ up_write(&resv_map->rw_sema);
}
}
@@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void)
kref_init(&resv_map->refs);
spin_lock_init(&resv_map->lock);
INIT_LIST_HEAD(&resv_map->regions);
+ init_rwsem(&resv_map->rw_sema);
resv_map->adds_in_progress = 0;
/*
_
Patches currently in -mm which might be from riel@xxxxxxxxxxx are
hugetlbfs-extend-hugetlb_vma_lock-to-private-vmas.patch
hugetlbfs-close-race-between-madv_dontneed-and-page-fault.patch
hugetlbfs-replace-hugetlb_vma_lock-with-invalidate_lock.patch
