The patch titled
kcore: fix vread/vwrite to be aware of holes
has been added to the -mm tree. Its filename is
kcore-fix-vread-vwrite-to-be-aware-of-holes.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 ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: kcore: fix vread/vwrite to be aware of holes
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
vread/vwrite access vmalloc area without checking there is a page or not.
In most case, this works well.
In old ages, the caller of get_vm_ara() is only IOREMAP and there is no
memory hole within vm_struct's [addr...addr + size - PAGE_SIZE] (
-PAGE_SIZE is for a guard page.)
After per-cpu-alloc patch, it uses get_vm_area() for reserve continuous
virtual address but remap _later_. There tend to be a hole in valid
vmalloc area in vm_struct lists. Then, skip the hole (not mapped page) is
necessary. This patch updates vread/vwrite() for avoiding memory hole.
Routines which access vmalloc area without knowing for which addr is used
are
- /proc/kcore
- /dev/kmem
kcore checks IOREMAP, /dev/kmem doesn't. After this patch, IOREMAP is
checked and /dev/kmem will avoid to read/write it. Fixes to /proc/kcore
will be in the next patch in series.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: WANG Cong <xiyou.wangcong@xxxxxxxxx>
Cc: Mike Smith <scgtrp@xxxxxxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmalloc.c | 182 ++++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 159 insertions(+), 23 deletions(-)
diff -puN mm/vmalloc.c~kcore-fix-vread-vwrite-to-be-aware-of-holes mm/vmalloc.c
--- a/mm/vmalloc.c~kcore-fix-vread-vwrite-to-be-aware-of-holes
+++ a/mm/vmalloc.c
@@ -25,7 +25,7 @@
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
-
+#include <linux/highmem.h>
#include <asm/atomic.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
@@ -1627,10 +1627,109 @@ void *vmalloc_32_user(unsigned long size
}
EXPORT_SYMBOL(vmalloc_32_user);
+/*
+ * small helper routine , copy contents to buf from addr.
+ * If the page is not present, fill zero.
+ */
+
+static int aligned_vread(char *buf, char *addr, unsigned long count)
+{
+ struct page *p;
+ int copied = 0;
+
+ while (count) {
+ unsigned long offset, length;
+
+ offset = (unsigned long)addr & ~PAGE_MASK;
+ length = PAGE_SIZE - offset;
+ if (length > count)
+ length = count;
+ p = vmalloc_to_page(addr);
+ /*
+ * To do safe access to this _mapped_ area, we need
+ * lock. But adding lock here means that we need to add
+ * overhead of vmalloc()/vfree() calles for this _debug_
+ * interface, rarely used. Instead of that, we'll use
+ * kmap() and get small overhead in this access function.
+ */
+ if (p) {
+ /* we can expect USR1 is not used */
+ void *map = kmap_atomic(p, KM_USER1);
+ memcpy(buf, map + offset, length);
+ kunmap_atomic(map, KM_USER1);
+ } else
+ memset(buf, 0, length);
+
+ addr += length;
+ buf += length;
+ copied += length;
+ count -= length;
+ }
+ return copied;
+}
+
+static int aligned_vwrite(char *buf, char *addr, unsigned long count)
+{
+ struct page *p;
+ int copied = 0;
+
+ while (count) {
+ unsigned long offset, length;
+
+ offset = (unsigned long)addr & ~PAGE_MASK;
+ length = PAGE_SIZE - offset;
+ if (length > count)
+ length = count;
+ p = vmalloc_to_page(addr);
+ /*
+ * To do safe access to this _mapped_ area, we need
+ * lock. But adding lock here means that we need to add
+ * overhead of vmalloc()/vfree() calles for this _debug_
+ * interface, rarely used. Instead of that, we'll use
+ * kmap() and get small overhead in this access function.
+ */
+ if (p) {
+ /* we can expect USR1 is not used */
+ void *map = kmap_atomic(p, KM_USER1);
+ memcpy(map + offset, buf, length);
+ kunmap_atomic(map, KM_USER1);
+ }
+ addr += length;
+ buf += length;
+ copied += length;
+ count -= length;
+ }
+ return copied;
+}
+
+/**
+ * vread() - read vmalloc area in a safe way.
+ * @buf: buffer for reading data
+ * @addr: vm address.
+ * @count: number of bytes to be read.
+ *
+ * Returns # of bytes which addr and buf should be increased.
+ * (same to count).
+ * If [addr...addr+count) doesn't includes any valid area, returns 0.
+ *
+ * This function checks that addr is a valid vmalloc'ed area, and
+ * copy data from that area to a given buffer. If the given memory range of
+ * [addr...addr+count) includes some valid address, data is copied to
+ * proper area of @buf. If there are memory holes, they'll be zero-filled.
+ * IOREMAP area is treated as memory hole and no copy is done.
+ *
+ * Note: In usual ops, vread() is never necessary because the caller should
+ * know vmalloc() area is valid and can use memcpy(). This is for routines
+ * which have to access vmalloc area without any informaion, as /dev/kmem.
+ *
+ * The caller should guarantee KM_USER1 is not used.
+ */
+
long vread(char *buf, char *addr, unsigned long count)
{
struct vm_struct *tmp;
char *vaddr, *buf_start = buf;
+ unsigned long buflen = count;
unsigned long n;
/* Don't allow overflow */
@@ -1638,7 +1737,7 @@ long vread(char *buf, char *addr, unsign
count = -(unsigned long) addr;
read_lock(&vmlist_lock);
- for (tmp = vmlist; tmp; tmp = tmp->next) {
+ for (tmp = vmlist; count && tmp; tmp = tmp->next) {
vaddr = (char *) tmp->addr;
if (addr >= vaddr + tmp->size - PAGE_SIZE)
continue;
@@ -1651,32 +1750,66 @@ long vread(char *buf, char *addr, unsign
count--;
}
n = vaddr + tmp->size - PAGE_SIZE - addr;
- do {
- if (count == 0)
- goto finished;
- *buf = *addr;
- buf++;
- addr++;
- count--;
- } while (--n > 0);
+ if (n > count)
+ n = count;
+ if (!(tmp->flags & VM_IOREMAP))
+ aligned_vread(buf, addr, n);
+ else /* IOREMAP area is treated as memory hole */
+ memset(buf, 0, n);
+ buf += n;
+ addr += n;
+ count -= n;
}
finished:
read_unlock(&vmlist_lock);
- return buf - buf_start;
+
+ if (buf == buf_start)
+ return 0;
+ /* zero-fill memory holes */
+ if (buf != buf_start + buflen)
+ memset(buf, 0, buflen - (buf - buf_start));
+
+ return buflen;
}
+/**
+ * vwrite() - write vmalloc area in a safe way.
+ * @buf: buffer for source data
+ * @addr: vm address.
+ * @count: number of bytes to be read.
+ *
+ * Returns # of bytes which addr and buf should be incresed.
+ * (same to count).
+ * If [addr...addr+count) doesn't includes any valid area, returns 0.
+ *
+ * This function checks that addr is a valid vmalloc'ed area, and
+ * copy data from a buffer to the given addr. If specified range of
+ * [addr...addr+count) includes some valid address, data is copied from
+ * proper area of @buf. If there are memory holes, no copy to hole.
+ * IOREMAP area is treated as memory hole and no copy is done.
+ *
+ * Note: In usual ops, vwrite() is never necessary because the caller
+ * should know vmalloc() area is valid and can use memcpy().
+ * This is for routines which have to access vmalloc area without
+ * any informaion, as /dev/kmem.
+ *
+ * The caller should guarantee KM_USER1 is not used.
+ */
+
long vwrite(char *buf, char *addr, unsigned long count)
{
struct vm_struct *tmp;
- char *vaddr, *buf_start = buf;
- unsigned long n;
+ char *vaddr;
+ unsigned long n, buflen;
+ int copied = 0;
/* Don't allow overflow */
if ((unsigned long) addr + count < count)
count = -(unsigned long) addr;
+ buflen = count;
read_lock(&vmlist_lock);
- for (tmp = vmlist; tmp; tmp = tmp->next) {
+ for (tmp = vmlist; count && tmp; tmp = tmp->next) {
vaddr = (char *) tmp->addr;
if (addr >= vaddr + tmp->size - PAGE_SIZE)
continue;
@@ -1688,18 +1821,21 @@ long vwrite(char *buf, char *addr, unsig
count--;
}
n = vaddr + tmp->size - PAGE_SIZE - addr;
- do {
- if (count == 0)
- goto finished;
- *addr = *buf;
- buf++;
- addr++;
- count--;
- } while (--n > 0);
+ if (n > count)
+ n = count;
+ if (!(tmp->flags & VM_IOREMAP)) {
+ aligned_vwrite(buf, addr, n);
+ copied++;
+ }
+ buf += n;
+ addr += n;
+ count -= n;
}
finished:
read_unlock(&vmlist_lock);
- return buf - buf_start;
+ if (!copied)
+ return 0;
+ return buflen;
}
/**
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
mm-make-set_mempolicympol_interleav-n_high_memory-aware.patch
mm-make-set_mempolicympol_interleav-n_high_memory-aware-fix.patch
mm-clean-up-page_remove_rmap.patch
vmscan-throttle-direct-reclaim-when-too-many-pages-are-isolated-already.patch
mm-remove-__addsub_zone_page_state.patch
vmscan-dont-attempt-to-reclaim-anon-page-in-lumpy-reclaim-when-no-swap-space-is-avilable.patch
ksm-add-mmu_notifier-set_pte_at_notify.patch
ksm-first-tidy-up-madvise_vma.patch
ksm-define-madv_mergeable-and-madv_unmergeable.patch
ksm-the-mm-interface-to-ksm.patch
ksm-no-debug-in-page_dup_rmap.patch
ksm-identify-pageksm-pages.patch
ksm-kernel-samepage-merging.patch
ksm-prevent-mremap-move-poisoning.patch
ksm-change-copyright-message.patch
ksm-change-ksm-nice-level-to-be-5.patch
mm-introduce-proc-pid-oom_adj_child.patch
vmalloc-unmap-vmalloc-area-after-hiding-it.patch
kcore-fix-vread-vwrite-to-be-aware-of-holes.patch
kcore-proc-kcore-should-use-vread.patch
kcore-fix-proc-kcores-statst_size.patch
cgroups-support-named-cgroups-hierarchies.patch
cgroups-move-the-cgroup-debug-subsys-into-cgroupc-to-access-internal-state.patch
cgroups-add-a-back-pointer-from-struct-cg_cgroup_link-to-struct-cgroup.patch
cgroups-allow-cgroup-hierarchies-to-be-created-with-no-bound-subsystems.patch
memcg-remove-the-overhead-associated-with-the-root-cgroup.patch
memcg-remove-the-overhead-associated-with-the-root-cgroup-fix.patch
memcg-remove-the-overhead-associated-with-the-root-cgroup-fix-2.patch
memcg-add-comments-explaining-memory-barriers.patch
memcg-add-comments-explaining-memory-barriers-checkpatch-fixes.patch
memory-controller-soft-limit-documentation-v9.patch
memory-controller-soft-limit-interface-v9.patch
memory-controller-soft-limit-organize-cgroups-v9.patch
memory-controller-soft-limit-organize-cgroups-v9-fix.patch
memory-controller-soft-limit-refactor-reclaim-flags-v9.patch
memory-controller-soft-limit-reclaim-on-contention-v9.patch
memory-controller-soft-limit-reclaim-on-contention-v9-fix.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
