Handle DMA map/unmap operations up to the addressable limit by comparing
against inclusive end-of-range limits, and changing iteration to
perform relative traversals across range sizes, rather than absolute
traversals across addresses.
vfio_link_dma inserts a zero-sized vfio_dma into the rb-tree, and is
only used for that purpose, so discard the size from consideration for
the insertion point.
Signed-off-by: Alex Mastro <amastro@fb.com>
---
drivers/vfio/vfio_iommu_type1.c | 77 ++++++++++++++++++++++-------------------
1 file changed, 42 insertions(+), 35 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 15aab95d9b8d..567cbab8dfd3 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -166,12 +166,14 @@ static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
{
struct rb_node *node = iommu->dma_list.rb_node;
+ WARN_ON(!size);
+
while (node) {
struct vfio_dma *dma = rb_entry(node, struct vfio_dma, node);
- if (start + size <= dma->iova)
+ if (start + size - 1 < dma->iova)
node = node->rb_left;
- else if (start >= dma->iova + dma->size)
+ else if (start > dma->iova + dma->size - 1)
node = node->rb_right;
else
return dma;
@@ -181,16 +183,19 @@ static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
}
static struct rb_node *vfio_find_dma_first_node(struct vfio_iommu *iommu,
- dma_addr_t start, u64 size)
+ dma_addr_t start,
+ dma_addr_t end)
{
struct rb_node *res = NULL;
struct rb_node *node = iommu->dma_list.rb_node;
struct vfio_dma *dma_res = NULL;
+ WARN_ON(end < start);
+
while (node) {
struct vfio_dma *dma = rb_entry(node, struct vfio_dma, node);
- if (start < dma->iova + dma->size) {
+ if (start <= dma->iova + dma->size - 1) {
res = node;
dma_res = dma;
if (start >= dma->iova)
@@ -200,7 +205,7 @@ static struct rb_node *vfio_find_dma_first_node(struct vfio_iommu *iommu,
node = node->rb_right;
}
}
- if (res && size && dma_res->iova >= start + size)
+ if (res && dma_res->iova > end)
res = NULL;
return res;
}
@@ -210,11 +215,13 @@ static void vfio_link_dma(struct vfio_iommu *iommu, struct vfio_dma *new)
struct rb_node **link = &iommu->dma_list.rb_node, *parent = NULL;
struct vfio_dma *dma;
+ WARN_ON(new->size != 0);
+
while (*link) {
parent = *link;
dma = rb_entry(parent, struct vfio_dma, node);
- if (new->iova + new->size <= dma->iova)
+ if (new->iova <= dma->iova)
link = &(*link)->rb_left;
else
link = &(*link)->rb_right;
@@ -1078,12 +1085,12 @@ static size_t unmap_unpin_slow(struct vfio_domain *domain,
static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
bool do_accounting)
{
- dma_addr_t iova = dma->iova, end = dma->iova + dma->size;
struct vfio_domain *domain, *d;
LIST_HEAD(unmapped_region_list);
struct iommu_iotlb_gather iotlb_gather;
int unmapped_region_cnt = 0;
long unlocked = 0;
+ size_t pos = 0;
if (!dma->size)
return 0;
@@ -1107,13 +1114,14 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
}
iommu_iotlb_gather_init(&iotlb_gather);
- while (iova < end) {
+ while (pos < dma->size) {
size_t unmapped, len;
phys_addr_t phys, next;
+ dma_addr_t iova = dma->iova + pos;
phys = iommu_iova_to_phys(domain->domain, iova);
if (WARN_ON(!phys)) {
- iova += PAGE_SIZE;
+ pos += PAGE_SIZE;
continue;
}
@@ -1122,7 +1130,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
* may require hardware cache flushing, try to find the
* largest contiguous physical memory chunk to unmap.
*/
- for (len = PAGE_SIZE; iova + len < end; len += PAGE_SIZE) {
+ for (len = PAGE_SIZE; pos + len < dma->size; len += PAGE_SIZE) {
next = iommu_iova_to_phys(domain->domain, iova + len);
if (next != phys + len)
break;
@@ -1143,7 +1151,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
break;
}
- iova += unmapped;
+ pos += unmapped;
}
dma->iommu_mapped = false;
@@ -1235,7 +1243,7 @@ static int update_user_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
}
static int vfio_iova_dirty_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
- dma_addr_t iova, size_t size, size_t pgsize)
+ dma_addr_t iova, dma_addr_t iova_end, size_t pgsize)
{
struct vfio_dma *dma;
struct rb_node *n;
@@ -1252,8 +1260,8 @@ static int vfio_iova_dirty_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
if (dma && dma->iova != iova)
return -EINVAL;
- dma = vfio_find_dma(iommu, iova + size - 1, 0);
- if (dma && dma->iova + dma->size != iova + size)
+ dma = vfio_find_dma(iommu, iova_end, 1);
+ if (dma && dma->iova + dma->size - 1 != iova_end)
return -EINVAL;
for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) {
@@ -1262,7 +1270,7 @@ static int vfio_iova_dirty_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
if (dma->iova < iova)
continue;
- if (dma->iova > iova + size - 1)
+ if (dma->iova > iova_end)
break;
ret = update_user_bitmap(bitmap, iommu, dma, iova, pgsize);
@@ -1350,7 +1358,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
if (unmap_all) {
if (iova || size)
goto unlock;
- size = U64_MAX;
+ iova_end = U64_MAX;
} else {
if (!size || size & (pgsize - 1) || size > SIZE_MAX)
goto unlock;
@@ -1405,17 +1413,17 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
if (dma && dma->iova != iova)
goto unlock;
- dma = vfio_find_dma(iommu, iova_end, 0);
- if (dma && dma->iova + dma->size != iova + size)
+ dma = vfio_find_dma(iommu, iova_end, 1);
+ if (dma && dma->iova + dma->size - 1 != iova_end)
goto unlock;
}
ret = 0;
- n = first_n = vfio_find_dma_first_node(iommu, iova, size);
+ n = first_n = vfio_find_dma_first_node(iommu, iova, iova_end);
while (n) {
dma = rb_entry(n, struct vfio_dma, node);
- if (dma->iova >= iova + size)
+ if (dma->iova > iova_end)
break;
if (!iommu->v2 && iova > dma->iova)
@@ -1747,12 +1755,12 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
for (; n; n = rb_next(n)) {
struct vfio_dma *dma;
- dma_addr_t iova;
+ size_t pos = 0;
dma = rb_entry(n, struct vfio_dma, node);
- iova = dma->iova;
- while (iova < dma->iova + dma->size) {
+ while (pos < dma->size) {
+ dma_addr_t iova = dma->iova + pos;
phys_addr_t phys;
size_t size;
@@ -1768,14 +1776,14 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
phys = iommu_iova_to_phys(d->domain, iova);
if (WARN_ON(!phys)) {
- iova += PAGE_SIZE;
+ pos += PAGE_SIZE;
continue;
}
size = PAGE_SIZE;
p = phys + size;
i = iova + size;
- while (i < dma->iova + dma->size &&
+ while (pos + size < dma->size &&
p == iommu_iova_to_phys(d->domain, i)) {
size += PAGE_SIZE;
p += PAGE_SIZE;
@@ -1783,9 +1791,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
}
} else {
unsigned long pfn;
- unsigned long vaddr = dma->vaddr +
- (iova - dma->iova);
- size_t n = dma->iova + dma->size - iova;
+ unsigned long vaddr = dma->vaddr + pos;
+ size_t n = dma->size - pos;
long npage;
npage = vfio_pin_pages_remote(dma, vaddr,
@@ -1816,7 +1823,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
goto unwind;
}
- iova += size;
+ pos += size;
}
}
@@ -1833,29 +1840,29 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
unwind:
for (; n; n = rb_prev(n)) {
struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
- dma_addr_t iova;
+ size_t pos = 0;
if (dma->iommu_mapped) {
iommu_unmap(domain->domain, dma->iova, dma->size);
continue;
}
- iova = dma->iova;
- while (iova < dma->iova + dma->size) {
+ while (pos < dma->size) {
+ dma_addr_t iova = dma->iova + pos;
phys_addr_t phys, p;
size_t size;
dma_addr_t i;
phys = iommu_iova_to_phys(domain->domain, iova);
if (!phys) {
- iova += PAGE_SIZE;
+ pos += PAGE_SIZE;
continue;
}
size = PAGE_SIZE;
p = phys + size;
i = iova + size;
- while (i < dma->iova + dma->size &&
+ while (pos + size < dma->size &&
p == iommu_iova_to_phys(domain->domain, i)) {
size += PAGE_SIZE;
p += PAGE_SIZE;
@@ -2988,7 +2995,7 @@ static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
if (iommu->dirty_page_tracking)
ret = vfio_iova_dirty_bitmap(range.bitmap.data,
iommu, range.iova,
- range.size,
+ range_end,
range.bitmap.pgsize);
else
ret = -EINVAL;
--
2.47.3Hi Alex,
kernel test robot noticed the following build warnings:
[auto build test WARNING on 407aa63018d15c35a34938633868e61174d2ef6e]
url: https://github.com/intel-lab-lkp/linux/commits/Alex-Mastro/vfio-type1-sanitize-for-overflow-using-check_-_overflow/20251010-154148
base: 407aa63018d15c35a34938633868e61174d2ef6e
patch link: https://lore.kernel.org/r/20251010-fix-unmap-v3-3-306c724d6998%40fb.com
patch subject: [PATCH v3 3/3] vfio/type1: handle DMA map/unmap up to the addressable limit
config: i386-buildonly-randconfig-001-20251011 (https://download.01.org/0day-ci/archive/20251011/202510111953.naYvy8XB-lkp@intel.com/config)
compiler: gcc-13 (Debian 13.3.0-16) 13.3.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251011/202510111953.naYvy8XB-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202510111953.naYvy8XB-lkp@intel.com/
All warnings (new ones prefixed by >>):
In file included from include/linux/overflow.h:6,
from include/linux/bits.h:32,
from include/linux/bitops.h:6,
from include/linux/log2.h:12,
from arch/x86/include/asm/div64.h:8,
from include/linux/math.h:6,
from include/linux/math64.h:6,
from include/linux/time.h:6,
from include/linux/compat.h:10,
from drivers/vfio/vfio_iommu_type1.c:24:
drivers/vfio/vfio_iommu_type1.c: In function 'vfio_dma_do_unmap':
>> include/linux/limits.h:25:25: warning: conversion from 'long long unsigned int' to 'dma_addr_t' {aka 'unsigned int'} changes value from '18446744073709551615' to '4294967295' [-Woverflow]
25 | #define U64_MAX ((u64)~0ULL)
| ^
drivers/vfio/vfio_iommu_type1.c:1361:28: note: in expansion of macro 'U64_MAX'
1361 | iova_end = U64_MAX;
| ^~~~~~~
--
In file included from include/linux/overflow.h:6,
from include/linux/bits.h:32,
from include/linux/bitops.h:6,
from include/linux/log2.h:12,
from arch/x86/include/asm/div64.h:8,
from include/linux/math.h:6,
from include/linux/math64.h:6,
from include/linux/time.h:6,
from include/linux/compat.h:10,
from vfio_iommu_type1.c:24:
vfio_iommu_type1.c: In function 'vfio_dma_do_unmap':
>> include/linux/limits.h:25:25: warning: conversion from 'long long unsigned int' to 'dma_addr_t' {aka 'unsigned int'} changes value from '18446744073709551615' to '4294967295' [-Woverflow]
25 | #define U64_MAX ((u64)~0ULL)
| ^
vfio_iommu_type1.c:1361:28: note: in expansion of macro 'U64_MAX'
1361 | iova_end = U64_MAX;
| ^~~~~~~
vim +25 include/linux/limits.h
3c9d017cc283df Andy Shevchenko 2023-08-04 14
54d50897d544c8 Masahiro Yamada 2019-03-07 15 #define U8_MAX ((u8)~0U)
54d50897d544c8 Masahiro Yamada 2019-03-07 16 #define S8_MAX ((s8)(U8_MAX >> 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 17 #define S8_MIN ((s8)(-S8_MAX - 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 18 #define U16_MAX ((u16)~0U)
54d50897d544c8 Masahiro Yamada 2019-03-07 19 #define S16_MAX ((s16)(U16_MAX >> 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 20 #define S16_MIN ((s16)(-S16_MAX - 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 21 #define U32_MAX ((u32)~0U)
3f50f132d8400e John Fastabend 2020-03-30 22 #define U32_MIN ((u32)0)
54d50897d544c8 Masahiro Yamada 2019-03-07 23 #define S32_MAX ((s32)(U32_MAX >> 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 24 #define S32_MIN ((s32)(-S32_MAX - 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 @25 #define U64_MAX ((u64)~0ULL)
54d50897d544c8 Masahiro Yamada 2019-03-07 26 #define S64_MAX ((s64)(U64_MAX >> 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 27 #define S64_MIN ((s64)(-S64_MAX - 1))
54d50897d544c8 Masahiro Yamada 2019-03-07 28
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
© 2016 - 2025 Red Hat, Inc.