commit 9ddb3c14afba8bc5950ed297f02d4ae05ff35cd1 upstream
32-bit architectures which expect 8-byte alignment for 8-byte integers and
need 64-bit DMA addresses (arm, mips, ppc) had their struct page
inadvertently expanded in 2019. When the dma_addr_t was added, it forced
the alignment of the union to 8 bytes, which inserted a 4 byte gap between
'flags' and the union.
Fix this by storing the dma_addr_t in one or two adjacent unsigned longs.
This restores the alignment to that of an unsigned long. We always
store the low bits in the first word to prevent the PageTail bit from
being inadvertently set on a big endian platform. If that happened,
get_user_pages_fast() racing against a page which was freed and
reallocated to the page_pool could dereference a bogus compound_head(),
which would be hard to trace back to this cause.
Link: https://lkml.kernel.org/r/20210510153211.1504886-1-willy@infradead.org
Fixes: c25fff7171be ("mm: add dma_addr_t to struct page")
Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Acked-by: Ilias Apalodimas <ilias.apalodimas(a)linaro.org>
Acked-by: Jesper Dangaard Brouer <brouer(a)redhat.com>
Acked-by: Vlastimil Babka <vbabka(a)suse.cz>
Tested-by: Matteo Croce <mcroce(a)linux.microsoft.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
---
include/linux/mm_types.h | 4 ++--
include/net/page_pool.h | 12 +++++++++++-
net/core/page_pool.c | 6 +++---
3 files changed, 16 insertions(+), 6 deletions(-)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 270aa8fd2800..2b3b2fc1cb33 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -95,10 +95,10 @@ struct page {
};
struct { /* page_pool used by netstack */
/**
- * @dma_addr: might require a 64-bit value even on
+ * @dma_addr: might require a 64-bit value on
* 32-bit architectures.
*/
- dma_addr_t dma_addr;
+ unsigned long dma_addr[2];
};
struct { /* slab, slob and slub */
union {
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 1121faa99c12..cf086e13bd25 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -185,7 +185,17 @@ static inline void page_pool_release_page(struct page_pool *pool,
static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
{
- return page->dma_addr;
+ dma_addr_t ret = page->dma_addr[0];
+ if (sizeof(dma_addr_t) > sizeof(unsigned long))
+ ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16;
+ return ret;
+}
+
+static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+{
+ page->dma_addr[0] = addr;
+ if (sizeof(dma_addr_t) > sizeof(unsigned long))
+ page->dma_addr[1] = upper_32_bits(addr);
}
static inline bool is_page_pool_compiled_in(void)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index dfc2501c35d9..335f68eaaa05 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -157,7 +157,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
put_page(page);
return NULL;
}
- page->dma_addr = dma;
+ page_pool_set_dma_addr(page, dma);
skip_dma_map:
/* Track how many pages are held 'in-flight' */
@@ -216,12 +216,12 @@ static void __page_pool_clean_page(struct page_pool *pool,
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
goto skip_dma_unmap;
- dma = page->dma_addr;
+ dma = page_pool_get_dma_addr(page);
/* DMA unmap */
dma_unmap_page_attrs(pool->p.dev, dma,
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC);
- page->dma_addr = 0;
+ page_pool_set_dma_addr(page, 0);
skip_dma_unmap:
/* This may be the last page returned, releasing the pool, so
* it is not safe to reference pool afterwards.
--
2.30.2
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From e9f4eee9a0023ba22db9560d4cc6ee63f933dae8 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj(a)kernel.org>
Date: Tue, 11 May 2021 21:38:36 -0400
Subject: [PATCH] blk-iocost: fix weight updates of inner active iocgs
When the weight of an active iocg is updated, weight_updated() is called
which in turn calls __propagate_weights() to update the active and inuse
weights so that the effective hierarchical weights are update accordingly.
The current implementation is incorrect for inner active nodes. For an
active leaf iocg, inuse can be any value between 1 and active and the
difference represents how much the iocg is donating. When weight is updated,
as long as inuse is clamped between 1 and the new weight, we're alright and
this is what __propagate_weights() currently implements.
However, that's not how an active inner node's inuse is set. An inner node's
inuse is solely determined by the ratio between the sums of inuse's and
active's of its children - ie. they're results of propagating the leaves'
active and inuse weights upwards. __propagate_weights() incorrectly applies
the same clamping as for a leaf when an active inner node's weight is
updated. Consider a hierarchy which looks like the following with saturating
workloads in AA and BB.
R
/ \
A B
| |
AA BB
1. For both A and B, active=100, inuse=100, hwa=0.5, hwi=0.5.
2. echo 200 > A/io.weight
3. __propagate_weights() update A's active to 200 and leave inuse at 100 as
it's already between 1 and the new active, making A:active=200,
A:inuse=100. As R's active_sum is updated along with A's active,
A:hwa=2/3, B:hwa=1/3. However, because the inuses didn't change, the
hwi's remain unchanged at 0.5.
4. The weight of A is now twice that of B but AA and BB still have the same
hwi of 0.5 and thus are doing the same amount of IOs.
Fix it by making __propgate_weights() always calculate the inuse of an
active inner iocg based on the ratio of child_inuse_sum to child_active_sum.
Signed-off-by: Tejun Heo <tj(a)kernel.org>
Reported-by: Dan Schatzberg <dschatzberg(a)fb.com>
Fixes: 7caa47151ab2 ("blkcg: implement blk-iocost")
Cc: stable(a)vger.kernel.org # v5.4+
Link: https://lore.kernel.org/r/YJsxnLZV1MnBcqjj@slm.duckdns.org
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index e0c4baa01857..c2d6bc88d3f1 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1069,7 +1069,17 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse,
lockdep_assert_held(&ioc->lock);
- inuse = clamp_t(u32, inuse, 1, active);
+ /*
+ * For an active leaf node, its inuse shouldn't be zero or exceed
+ * @active. An active internal node's inuse is solely determined by the
+ * inuse to active ratio of its children regardless of @inuse.
+ */
+ if (list_empty(&iocg->active_list) && iocg->child_active_sum) {
+ inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum,
+ iocg->child_active_sum);
+ } else {
+ inuse = clamp_t(u32, inuse, 1, active);
+ }
iocg->last_inuse = iocg->inuse;
if (save)
@@ -1086,7 +1096,7 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse,
/* update the level sums */
parent->child_active_sum += (s32)(active - child->active);
parent->child_inuse_sum += (s32)(inuse - child->inuse);
- /* apply the udpates */
+ /* apply the updates */
child->active = active;
child->inuse = inuse;
The patch below does not apply to the 5.12-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 9ddb3c14afba8bc5950ed297f02d4ae05ff35cd1 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy(a)infradead.org>
Date: Fri, 14 May 2021 17:27:24 -0700
Subject: [PATCH] mm: fix struct page layout on 32-bit systems
32-bit architectures which expect 8-byte alignment for 8-byte integers and
need 64-bit DMA addresses (arm, mips, ppc) had their struct page
inadvertently expanded in 2019. When the dma_addr_t was added, it forced
the alignment of the union to 8 bytes, which inserted a 4 byte gap between
'flags' and the union.
Fix this by storing the dma_addr_t in one or two adjacent unsigned longs.
This restores the alignment to that of an unsigned long. We always
store the low bits in the first word to prevent the PageTail bit from
being inadvertently set on a big endian platform. If that happened,
get_user_pages_fast() racing against a page which was freed and
reallocated to the page_pool could dereference a bogus compound_head(),
which would be hard to trace back to this cause.
Link: https://lkml.kernel.org/r/20210510153211.1504886-1-willy@infradead.org
Fixes: c25fff7171be ("mm: add dma_addr_t to struct page")
Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Acked-by: Ilias Apalodimas <ilias.apalodimas(a)linaro.org>
Acked-by: Jesper Dangaard Brouer <brouer(a)redhat.com>
Acked-by: Vlastimil Babka <vbabka(a)suse.cz>
Tested-by: Matteo Croce <mcroce(a)linux.microsoft.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6613b26a8894..5aacc1c10a45 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -97,10 +97,10 @@ struct page {
};
struct { /* page_pool used by netstack */
/**
- * @dma_addr: might require a 64-bit value even on
+ * @dma_addr: might require a 64-bit value on
* 32-bit architectures.
*/
- dma_addr_t dma_addr;
+ unsigned long dma_addr[2];
};
struct { /* slab, slob and slub */
union {
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 6d517a37c18b..b4b6de909c93 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -198,7 +198,17 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
{
- return page->dma_addr;
+ dma_addr_t ret = page->dma_addr[0];
+ if (sizeof(dma_addr_t) > sizeof(unsigned long))
+ ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16;
+ return ret;
+}
+
+static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+{
+ page->dma_addr[0] = addr;
+ if (sizeof(dma_addr_t) > sizeof(unsigned long))
+ page->dma_addr[1] = upper_32_bits(addr);
}
static inline bool is_page_pool_compiled_in(void)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 9ec1aa9640ad..3c4c4c7a0402 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool,
struct page *page,
unsigned int dma_sync_size)
{
+ dma_addr_t dma_addr = page_pool_get_dma_addr(page);
+
dma_sync_size = min(dma_sync_size, pool->p.max_len);
- dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+ dma_sync_single_range_for_device(pool->p.dev, dma_addr,
pool->p.offset, dma_sync_size,
pool->p.dma_dir);
}
@@ -195,7 +197,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
if (dma_mapping_error(pool->p.dev, dma))
return false;
- page->dma_addr = dma;
+ page_pool_set_dma_addr(page, dma);
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
@@ -331,13 +333,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
*/
goto skip_dma_unmap;
- dma = page->dma_addr;
+ dma = page_pool_get_dma_addr(page);
- /* When page is unmapped, it cannot be returned our pool */
+ /* When page is unmapped, it cannot be returned to our pool */
dma_unmap_page_attrs(pool->p.dev, dma,
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC);
- page->dma_addr = 0;
+ page_pool_set_dma_addr(page, 0);
skip_dma_unmap:
/* This may be the last page returned, releasing the pool, so
* it is not safe to reference pool afterwards.
The patch below does not apply to the 5.11-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 9ddb3c14afba8bc5950ed297f02d4ae05ff35cd1 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy(a)infradead.org>
Date: Fri, 14 May 2021 17:27:24 -0700
Subject: [PATCH] mm: fix struct page layout on 32-bit systems
32-bit architectures which expect 8-byte alignment for 8-byte integers and
need 64-bit DMA addresses (arm, mips, ppc) had their struct page
inadvertently expanded in 2019. When the dma_addr_t was added, it forced
the alignment of the union to 8 bytes, which inserted a 4 byte gap between
'flags' and the union.
Fix this by storing the dma_addr_t in one or two adjacent unsigned longs.
This restores the alignment to that of an unsigned long. We always
store the low bits in the first word to prevent the PageTail bit from
being inadvertently set on a big endian platform. If that happened,
get_user_pages_fast() racing against a page which was freed and
reallocated to the page_pool could dereference a bogus compound_head(),
which would be hard to trace back to this cause.
Link: https://lkml.kernel.org/r/20210510153211.1504886-1-willy@infradead.org
Fixes: c25fff7171be ("mm: add dma_addr_t to struct page")
Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Acked-by: Ilias Apalodimas <ilias.apalodimas(a)linaro.org>
Acked-by: Jesper Dangaard Brouer <brouer(a)redhat.com>
Acked-by: Vlastimil Babka <vbabka(a)suse.cz>
Tested-by: Matteo Croce <mcroce(a)linux.microsoft.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6613b26a8894..5aacc1c10a45 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -97,10 +97,10 @@ struct page {
};
struct { /* page_pool used by netstack */
/**
- * @dma_addr: might require a 64-bit value even on
+ * @dma_addr: might require a 64-bit value on
* 32-bit architectures.
*/
- dma_addr_t dma_addr;
+ unsigned long dma_addr[2];
};
struct { /* slab, slob and slub */
union {
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 6d517a37c18b..b4b6de909c93 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -198,7 +198,17 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
{
- return page->dma_addr;
+ dma_addr_t ret = page->dma_addr[0];
+ if (sizeof(dma_addr_t) > sizeof(unsigned long))
+ ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16;
+ return ret;
+}
+
+static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+{
+ page->dma_addr[0] = addr;
+ if (sizeof(dma_addr_t) > sizeof(unsigned long))
+ page->dma_addr[1] = upper_32_bits(addr);
}
static inline bool is_page_pool_compiled_in(void)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 9ec1aa9640ad..3c4c4c7a0402 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool,
struct page *page,
unsigned int dma_sync_size)
{
+ dma_addr_t dma_addr = page_pool_get_dma_addr(page);
+
dma_sync_size = min(dma_sync_size, pool->p.max_len);
- dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+ dma_sync_single_range_for_device(pool->p.dev, dma_addr,
pool->p.offset, dma_sync_size,
pool->p.dma_dir);
}
@@ -195,7 +197,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
if (dma_mapping_error(pool->p.dev, dma))
return false;
- page->dma_addr = dma;
+ page_pool_set_dma_addr(page, dma);
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
@@ -331,13 +333,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
*/
goto skip_dma_unmap;
- dma = page->dma_addr;
+ dma = page_pool_get_dma_addr(page);
- /* When page is unmapped, it cannot be returned our pool */
+ /* When page is unmapped, it cannot be returned to our pool */
dma_unmap_page_attrs(pool->p.dev, dma,
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC);
- page->dma_addr = 0;
+ page_pool_set_dma_addr(page, 0);
skip_dma_unmap:
/* This may be the last page returned, releasing the pool, so
* it is not safe to reference pool afterwards.