[PATCH net-next v3 0/3] Fix late DMA unmap crash for page pool

[PATCH net-next v3 0/3] Fix late DMA unmap crash for page pool

[Toke Høiland-Jørgensen]

This series fixes the late dma_unmap crash for page pool first reported
by Yonglong Liu in [0]. It is an alternative approach to the one
submitted by Yunsheng Lin, most recently in [1]. The first two commits
are small refactors of the page pool code, in preparation of the main
change in patch 3. See the commit message of patch 3 for the details.

-Toke

[0] https://lore.kernel.org/lkml/8067f204-1380-4d37-8ffd-007fc6f26738@kernel.org/T/
[1] https://lore.kernel.org/r/20250307092356.638242-1-linyunsheng@huawei.com

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
Changes in v3:
- Use a full-width bool for pp->dma_sync instead of a full unsigned
  long (in patch 2), and leave pp->dma_sync_cpu alone.

- Link to v2: https://lore.kernel.org/r/20250325-page-pool-track-dma-v2-0-113ebc1946f3@redhat.com

Changes in v2:
- Always leave two bits at the top of pp_magic as zero, instead of one

- Add an rcu_read_lock() around __page_pool_dma_sync_for_device()

- Add a comment in poison.h with a reference to the bitmask definition

- Add a longer description of the logic of the bitmask definitions to
  the comment in types.h, and a summary of the security implications of
  using the pp_magic field to the commit message of patch 3

- Collect Mina's Reviewed-by and Yonglong's Tested-by tags

- Link to v1: https://lore.kernel.org/r/20250314-page-pool-track-dma-v1-0-c212e57a74c2@redhat.com

---
Toke Høiland-Jørgensen (3):
      page_pool: Move pp_magic check into helper functions
      page_pool: Turn dma_sync into a full-width bool field
      page_pool: Track DMA-mapped pages and unmap them when destroying the pool

 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c |  4 +-
 include/linux/poison.h                           |  4 ++
 include/net/page_pool/types.h                    | 65 ++++++++++++++++++-
 mm/page_alloc.c                                  |  9 +--
 net/core/netmem_priv.h                           | 33 +++++++++-
 net/core/page_pool.c                             | 81 ++++++++++++++++++++----
 net/core/skbuff.c                                | 16 +----
 net/core/xdp.c                                   |  4 +-
 8 files changed, 176 insertions(+), 40 deletions(-)
---
base-commit: 45e36a8e3c17c4d50ecbc863893f253fb46ac070
change-id: 20250310-page-pool-track-dma-0332343a460e

[PATCH net-next v3 1/3] page_pool: Move pp_magic check into helper functions

[Toke Høiland-Jørgensen]

Since we are about to stash some more information into the pp_magic
field, let's move the magic signature checks into a pair of helper
functions so it can be changed in one place.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Tested-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c |  4 ++--
 include/net/page_pool/types.h                    | 18 ++++++++++++++++++
 mm/page_alloc.c                                  |  9 +++------
 net/core/netmem_priv.h                           |  5 +++++
 net/core/skbuff.c                                | 16 ++--------------
 net/core/xdp.c                                   |  4 ++--
 6 files changed, 32 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 6f3094a479e1ec61854bb48a6a0c812167487173..70c6f0b2abb921778c98fbd428594ebd7986a302 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -706,8 +706,8 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 				page = xdpi.page.page;
 
-				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-				 * as we know this is a page_pool page.
+				/* No need to check page_pool_page_is_pp() as we
+				 * know this is a page_pool page.
 				 */
 				page_pool_recycle_direct(page->pp, page);
 			} while (++n < num);
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 36eb57d73abc6cfc601e700ca08be20fb8281055..df0d3c1608929605224feb26173135ff37951ef8 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -54,6 +54,14 @@ struct pp_alloc_cache {
 	netmem_ref cache[PP_ALLOC_CACHE_SIZE];
 };
 
+/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
+ * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
+ * the head page of compound page and bit 1 for pfmemalloc page.
+ * page_is_pfmemalloc() is checked in __page_pool_put_page() to avoid recycling
+ * the pfmemalloc page.
+ */
+#define PP_MAGIC_MASK ~0x3UL
+
 /**
  * struct page_pool_params - page pool parameters
  * @fast:	params accessed frequently on hotpath
@@ -264,6 +272,11 @@ void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
 			   const struct xdp_mem_info *mem);
 void page_pool_put_netmem_bulk(netmem_ref *data, u32 count);
+
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
 #else
 static inline void page_pool_destroy(struct page_pool *pool)
 {
@@ -278,6 +291,11 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
 static inline void page_pool_put_netmem_bulk(netmem_ref *data, u32 count)
 {
 }
+
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return false;
+}
 #endif
 
 void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 542d25f77be80304b731411ffd29b276ee13be0c..3535ee76afe946cbb042ecbce603bdbedc9233b9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -55,6 +55,7 @@
 #include <linux/delayacct.h>
 #include <linux/cacheinfo.h>
 #include <linux/pgalloc_tag.h>
+#include <net/page_pool/types.h>
 #include <asm/div64.h>
 #include "internal.h"
 #include "shuffle.h"
@@ -872,9 +873,7 @@ static inline bool page_expected_state(struct page *page,
 #ifdef CONFIG_MEMCG
 			page->memcg_data |
 #endif
-#ifdef CONFIG_PAGE_POOL
-			((page->pp_magic & ~0x3UL) == PP_SIGNATURE) |
-#endif
+			page_pool_page_is_pp(page) |
 			(page->flags & check_flags)))
 		return false;
 
@@ -901,10 +900,8 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
 	if (unlikely(page->memcg_data))
 		bad_reason = "page still charged to cgroup";
 #endif
-#ifdef CONFIG_PAGE_POOL
-	if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE))
+	if (unlikely(page_pool_page_is_pp(page)))
 		bad_reason = "page_pool leak";
-#endif
 	return bad_reason;
 }
 
diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
index 7eadb8393e002fd1cc2cef8a313d2ea7df76f301..f33162fd281c23e109273ba09950c5d0a2829bc9 100644
--- a/net/core/netmem_priv.h
+++ b/net/core/netmem_priv.h
@@ -18,6 +18,11 @@ static inline void netmem_clear_pp_magic(netmem_ref netmem)
 	__netmem_clear_lsb(netmem)->pp_magic = 0;
 }
 
+static inline bool netmem_is_pp(netmem_ref netmem)
+{
+	return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
+
 static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)
 {
 	__netmem_clear_lsb(netmem)->pp = pool;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ab8acb737b93299f503e5c298b87e18edd59d555..a64d777488e403d5fdef83ae42ae9e4924c1a0dc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -893,11 +893,6 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
-static bool is_pp_netmem(netmem_ref netmem)
-{
-	return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE;
-}
-
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
 		    unsigned int headroom)
 {
@@ -995,14 +990,7 @@ bool napi_pp_put_page(netmem_ref netmem)
 {
 	netmem = netmem_compound_head(netmem);
 
-	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
-	 * in order to preserve any existing bits, such as bit 0 for the
-	 * head page of compound page and bit 1 for pfmemalloc page, so
-	 * mask those bits for freeing side when doing below checking,
-	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
-	 * to avoid recycling the pfmemalloc page.
-	 */
-	if (unlikely(!is_pp_netmem(netmem)))
+	if (unlikely(!netmem_is_pp(netmem)))
 		return false;
 
 	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
@@ -1042,7 +1030,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
 
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		head_netmem = netmem_compound_head(shinfo->frags[i].netmem);
-		if (likely(is_pp_netmem(head_netmem)))
+		if (likely(netmem_is_pp(head_netmem)))
 			page_pool_ref_netmem(head_netmem);
 		else
 			page_ref_inc(netmem_to_page(head_netmem));
diff --git a/net/core/xdp.c b/net/core/xdp.c
index f86eedad586a77eb63a96a85aa6d068d3e94f077..0ba73943c6eed873b3d1c681b3b9a802b590f2d9 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -437,8 +437,8 @@ void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type,
 		netmem = netmem_compound_head(netmem);
 		if (napi_direct && xdp_return_frame_no_direct())
 			napi_direct = false;
-		/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-		 * as mem->type knows this a page_pool page
+		/* No need to check netmem_is_pp() as mem->type knows this a
+		 * page_pool page
 		 */
 		page_pool_put_full_netmem(netmem_get_pp(netmem), netmem,
 					  napi_direct);

-- 
2.48.1

[PATCH net-next v3 2/3] page_pool: Turn dma_sync into a full-width bool field

[Toke Høiland-Jørgensen]

Change the single-bit boolean for dma_sync into a full-width bool, so we
can read it as volatile with READ_ONCE(). A subsequent patch will add
writing with WRITE_ONCE() on teardown.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Tested-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 include/net/page_pool/types.h | 6 +++---
 net/core/page_pool.c          | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index df0d3c1608929605224feb26173135ff37951ef8..d6c93150384fbc4579bb0d0afb357ebb26c564a3 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -173,10 +173,10 @@ struct page_pool {
 	int cpuid;
 	u32 pages_state_hold_cnt;
 
-	bool has_init_callback:1;	/* slow::init_callback is set */
+	bool dma_sync;				/* Perform DMA sync for device */
+	bool dma_sync_for_cpu:1;		/* Perform DMA sync for cpu */
 	bool dma_map:1;			/* Perform DMA mapping */
-	bool dma_sync:1;		/* Perform DMA sync for device */
-	bool dma_sync_for_cpu:1;	/* Perform DMA sync for cpu */
+	bool has_init_callback:1;	/* slow::init_callback is set */
 #ifdef CONFIG_PAGE_POOL_STATS
 	bool system:1;			/* This is a global percpu pool */
 #endif
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index acef1fcd8ddcfd1853a6f2055c1f1820ab248e8d..fb32768a97765aacc7f1103bfee38000c988b0de 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -466,7 +466,7 @@ page_pool_dma_sync_for_device(const struct page_pool *pool,
 			      netmem_ref netmem,
 			      u32 dma_sync_size)
 {
-	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
+	if (READ_ONCE(pool->dma_sync) && dma_dev_need_sync(pool->p.dev))
 		__page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
 }
 

-- 
2.48.1

[PATCH net-next v3 3/3] page_pool: Track DMA-mapped pages and unmap them when destroying the pool

[Toke Høiland-Jørgensen]

When enabling DMA mapping in page_pool, pages are kept DMA mapped until
they are released from the pool, to avoid the overhead of re-mapping the
pages every time they are used. This causes resource leaks and/or
crashes when there are pages still outstanding while the device is torn
down, because page_pool will attempt an unmap through a non-existent DMA
device on the subsequent page return.

To fix this, implement a simple tracking of outstanding DMA-mapped pages
in page pool using an xarray. This was first suggested by Mina[0], and
turns out to be fairly straight forward: We simply store pointers to
pages directly in the xarray with xa_alloc() when they are first DMA
mapped, and remove them from the array on unmap. Then, when a page pool
is torn down, it can simply walk the xarray and unmap all pages still
present there before returning, which also allows us to get rid of the
get/put_device() calls in page_pool. Using xa_cmpxchg(), no additional
synchronisation is needed, as a page will only ever be unmapped once.

To avoid having to walk the entire xarray on unmap to find the page
reference, we stash the ID assigned by xa_alloc() into the page
structure itself, using the upper bits of the pp_magic field. This
requires a couple of defines to avoid conflicting with the
POINTER_POISON_DELTA define, but this is all evaluated at compile-time,
so does not affect run-time performance. The bitmap calculations in this
patch gives the following number of bits for different architectures:

- 23 bits on 32-bit architectures
- 21 bits on PPC64 (because of the definition of ILLEGAL_POINTER_VALUE)
- 32 bits on other 64-bit architectures

Stashing a value into the unused bits of pp_magic does have the effect
that it can make the value stored there lie outside the unmappable
range (as governed by the mmap_min_addr sysctl), for architectures that
don't define ILLEGAL_POINTER_VALUE. This means that if one of the
pointers that is aliased to the pp_magic field (such as page->lru.next)
is dereferenced while the page is owned by page_pool, that could lead to
a dereference into userspace, which is a security concern. The risk of
this is mitigated by the fact that (a) we always clear pp_magic before
releasing a page from page_pool, and (b) this would need a
use-after-free bug for struct page, which can have many other risks
since page->lru.next is used as a generic list pointer in multiple
places in the kernel. As such, with this patch we take the position that
this risk is negligible in practice. For more discussion, see[1].

Since all the tracking added in this patch is performed on DMA
map/unmap, no additional code is needed in the fast path, meaning the
performance overhead of this tracking is negligible there. A
micro-benchmark shows that the total overhead of the tracking itself is
about 400 ns (39 cycles(tsc) 395.218 ns; sum for both map and unmap[2]).
Since this cost is only paid on DMA map and unmap, it seems like an
acceptable cost to fix the late unmap issue. Further optimisation can
narrow the cases where this cost is paid (for instance by eliding the
tracking when DMA map/unmap is a no-op).

The extra memory needed to track the pages is neatly encapsulated inside
xarray, which uses the 'struct xa_node' structure to track items. This
structure is 576 bytes long, with slots for 64 items, meaning that a
full node occurs only 9 bytes of overhead per slot it tracks (in
practice, it probably won't be this efficient, but in any case it should
be an acceptable overhead).

[0] https://lore.kernel.org/all/CAHS8izPg7B5DwKfSuzz-iOop_YRbk3Sd6Y4rX7KBG9DcVJcyWg@mail.gmail.com/
[1] https://lore.kernel.org/r/20250320023202.GA25514@openwall.com
[2] https://lore.kernel.org/r/ae07144c-9295-4c9d-a400-153bb689fe9e@huawei.com

Reported-by: Yonglong Liu <liuyonglong@huawei.com>
Closes: https://lore.kernel.org/r/8743264a-9700-4227-a556-5f931c720211@huawei.com
Fixes: ff7d6b27f894 ("page_pool: refurbish version of page_pool code")
Suggested-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Jesper Dangaard Brouer <hawk@kernel.org>
Tested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Tested-by: Qiuling Ren <qren@redhat.com>
Tested-by: Yuying Ma <yuma@redhat.com>
Tested-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 include/linux/poison.h        |  4 +++
 include/net/page_pool/types.h | 49 +++++++++++++++++++++++---
 net/core/netmem_priv.h        | 28 ++++++++++++++-
 net/core/page_pool.c          | 81 ++++++++++++++++++++++++++++++++++++-------
 4 files changed, 145 insertions(+), 17 deletions(-)

diff --git a/include/linux/poison.h b/include/linux/poison.h
index 331a9a996fa8746626afa63ea462b85ca3e5938b..5351efd710d5e21cc341f7bb533b1aeea4a0808a 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -70,6 +70,10 @@
 #define KEY_DESTROY		0xbd
 
 /********** net/core/page_pool.c **********/
+/*
+ * page_pool uses additional free bits within this value to store data, see the
+ * definition of PP_DMA_INDEX_MASK in include/net/page_pool/types.h
+ */
 #define PP_SIGNATURE		(0x40 + POISON_POINTER_DELTA)
 
 /********** net/core/skbuff.c **********/
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index d6c93150384fbc4579bb0d0afb357ebb26c564a3..cdc06fb67642c104b071998920bd88125fbefd43 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -6,6 +6,7 @@
 #include <linux/dma-direction.h>
 #include <linux/ptr_ring.h>
 #include <linux/types.h>
+#include <linux/xarray.h>
 #include <net/netmem.h>
 
 #define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
@@ -54,13 +55,51 @@ struct pp_alloc_cache {
 	netmem_ref cache[PP_ALLOC_CACHE_SIZE];
 };
 
+/*
+ * DMA mapping IDs
+ *
+ * When DMA-mapping a page, we allocate an ID (from an xarray) and stash this in
+ * the upper bits of page->pp_magic. We always want to be able to unambiguously
+ * identify page pool pages (using page_pool_page_is_pp()). Non-PP pages can
+ * have arbitrary kernel pointers stored in the same field as pp_magic (since it
+ * overlaps with page->lru.next), so we must ensure that we cannot mistake a
+ * valid kernel pointer with any of the values we write into this field.
+ *
+ * On architectures that set POISON_POINTER_DELTA, this is already ensured,
+ * since this value becomes part of PP_SIGNATURE; meaning we can just use the
+ * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the
+ * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is
+ * 0, we make sure that we leave the two topmost bits empty, as that guarantees
+ * we won't mistake a valid kernel pointer for a value we set, regardless of the
+ * VMSPLIT setting.
+ *
+ * Altogether, this means that the number of bits available is constrained by
+ * the size of an unsigned long (at the upper end, subtracting two bits per the
+ * above), and the definition of PP_SIGNATURE (with or without
+ * POISON_POINTER_DELTA).
+ */
+#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA))
+#if POISON_POINTER_DELTA > 0
+/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA
+ * index to not overlap with that if set
+ */
+#define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT)
+#else
+/* Always leave out the topmost two; see above. */
+#define PP_DMA_INDEX_BITS MIN(32, BITS_PER_LONG - PP_DMA_INDEX_SHIFT - 2)
+#endif
+
+#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
+				  PP_DMA_INDEX_SHIFT)
+#define PP_DMA_INDEX_LIMIT XA_LIMIT(1, BIT(PP_DMA_INDEX_BITS) - 1)
+
 /* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
  * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
- * the head page of compound page and bit 1 for pfmemalloc page.
- * page_is_pfmemalloc() is checked in __page_pool_put_page() to avoid recycling
- * the pfmemalloc page.
+ * the head page of compound page and bit 1 for pfmemalloc page, as well as the
+ * bits used for the DMA index. page_is_pfmemalloc() is checked in
+ * __page_pool_put_page() to avoid recycling the pfmemalloc page.
  */
-#define PP_MAGIC_MASK ~0x3UL
+#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
 
 /**
  * struct page_pool_params - page pool parameters
@@ -229,6 +268,8 @@ struct page_pool {
 	void *mp_priv;
 	const struct memory_provider_ops *mp_ops;
 
+	struct xarray dma_mapped;
+
 #ifdef CONFIG_PAGE_POOL_STATS
 	/* recycle stats are per-cpu to avoid locking */
 	struct page_pool_recycle_stats __percpu *recycle_stats;
diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
index f33162fd281c23e109273ba09950c5d0a2829bc9..cd95394399b40c3604934ba7898eeeeacb8aee99 100644
--- a/net/core/netmem_priv.h
+++ b/net/core/netmem_priv.h
@@ -5,7 +5,7 @@
 
 static inline unsigned long netmem_get_pp_magic(netmem_ref netmem)
 {
-	return __netmem_clear_lsb(netmem)->pp_magic;
+	return __netmem_clear_lsb(netmem)->pp_magic & ~PP_DMA_INDEX_MASK;
 }
 
 static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
@@ -15,6 +15,8 @@ static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
 
 static inline void netmem_clear_pp_magic(netmem_ref netmem)
 {
+	WARN_ON_ONCE(__netmem_clear_lsb(netmem)->pp_magic & PP_DMA_INDEX_MASK);
+
 	__netmem_clear_lsb(netmem)->pp_magic = 0;
 }
 
@@ -33,4 +35,28 @@ static inline void netmem_set_dma_addr(netmem_ref netmem,
 {
 	__netmem_clear_lsb(netmem)->dma_addr = dma_addr;
 }
+
+static inline unsigned long netmem_get_dma_index(netmem_ref netmem)
+{
+	unsigned long magic;
+
+	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
+		return 0;
+
+	magic = __netmem_clear_lsb(netmem)->pp_magic;
+
+	return (magic & PP_DMA_INDEX_MASK) >> PP_DMA_INDEX_SHIFT;
+}
+
+static inline void netmem_set_dma_index(netmem_ref netmem,
+					unsigned long id)
+{
+	unsigned long magic;
+
+	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
+		return;
+
+	magic = netmem_get_pp_magic(netmem) | (id << PP_DMA_INDEX_SHIFT);
+	__netmem_clear_lsb(netmem)->pp_magic = magic;
+}
 #endif
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index fb32768a97765aacc7f1103bfee38000c988b0de..5eb132f7f2193bda76121cc10a24dac4993b2c21 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -226,6 +226,8 @@ static int page_pool_init(struct page_pool *pool,
 			return -EINVAL;
 
 		pool->dma_map = true;
+
+		xa_init_flags(&pool->dma_mapped, XA_FLAGS_ALLOC1);
 	}
 
 	if (pool->slow.flags & PP_FLAG_DMA_SYNC_DEV) {
@@ -275,9 +277,6 @@ static int page_pool_init(struct page_pool *pool,
 	/* Driver calling page_pool_create() also call page_pool_destroy() */
 	refcount_set(&pool->user_cnt, 1);
 
-	if (pool->dma_map)
-		get_device(pool->p.dev);
-
 	if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) {
 		/* We rely on rtnl_lock()ing to make sure netdev_rx_queue
 		 * configuration doesn't change while we're initializing
@@ -325,7 +324,7 @@ static void page_pool_uninit(struct page_pool *pool)
 	ptr_ring_cleanup(&pool->ring, NULL);
 
 	if (pool->dma_map)
-		put_device(pool->p.dev);
+		xa_destroy(&pool->dma_mapped);
 
 #ifdef CONFIG_PAGE_POOL_STATS
 	if (!pool->system)
@@ -466,13 +465,20 @@ page_pool_dma_sync_for_device(const struct page_pool *pool,
 			      netmem_ref netmem,
 			      u32 dma_sync_size)
 {
-	if (READ_ONCE(pool->dma_sync) && dma_dev_need_sync(pool->p.dev))
-		__page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
+	if (dma_dev_need_sync(pool->p.dev)) {
+		rcu_read_lock();
+		if (READ_ONCE(pool->dma_sync))
+			__page_pool_dma_sync_for_device(pool, netmem,
+							dma_sync_size);
+		rcu_read_unlock();
+	}
 }
 
-static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
+static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem, gfp_t gfp)
 {
 	dma_addr_t dma;
+	int err;
+	u32 id;
 
 	/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
 	 * since dma_addr_t can be either 32 or 64 bits and does not always fit
@@ -486,15 +492,28 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
 	if (dma_mapping_error(pool->p.dev, dma))
 		return false;
 
-	if (page_pool_set_dma_addr_netmem(netmem, dma))
+	if (in_softirq())
+		err = xa_alloc(&pool->dma_mapped, &id, netmem_to_page(netmem),
+			       PP_DMA_INDEX_LIMIT, gfp);
+	else
+		err = xa_alloc_bh(&pool->dma_mapped, &id, netmem_to_page(netmem),
+				  PP_DMA_INDEX_LIMIT, gfp);
+	if (err) {
+		WARN_ONCE(1, "couldn't track DMA mapping, please report to netdev@");
 		goto unmap_failed;
+	}
 
+	if (page_pool_set_dma_addr_netmem(netmem, dma)) {
+		WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
+		goto unmap_failed;
+	}
+
+	netmem_set_dma_index(netmem, id);
 	page_pool_dma_sync_for_device(pool, netmem, pool->p.max_len);
 
 	return true;
 
 unmap_failed:
-	WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
 	dma_unmap_page_attrs(pool->p.dev, dma,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
@@ -511,7 +530,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 	if (unlikely(!page))
 		return NULL;
 
-	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page)))) {
+	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page), gfp))) {
 		put_page(page);
 		return NULL;
 	}
@@ -557,7 +576,7 @@ static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool,
 	 */
 	for (i = 0; i < nr_pages; i++) {
 		netmem = pool->alloc.cache[i];
-		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem))) {
+		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem, gfp))) {
 			put_page(netmem_to_page(netmem));
 			continue;
 		}
@@ -659,6 +678,8 @@ void page_pool_clear_pp_info(netmem_ref netmem)
 static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 							 netmem_ref netmem)
 {
+	struct page *old, *page = netmem_to_page(netmem);
+	unsigned long id;
 	dma_addr_t dma;
 
 	if (!pool->dma_map)
@@ -667,6 +688,17 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 		 */
 		return;
 
+	id = netmem_get_dma_index(netmem);
+	if (!id)
+		return;
+
+	if (in_softirq())
+		old = xa_cmpxchg(&pool->dma_mapped, id, page, NULL, 0);
+	else
+		old = xa_cmpxchg_bh(&pool->dma_mapped, id, page, NULL, 0);
+	if (old != page)
+		return;
+
 	dma = page_pool_get_dma_addr_netmem(netmem);
 
 	/* When page is unmapped, it cannot be returned to our pool */
@@ -674,6 +706,7 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	page_pool_set_dma_addr_netmem(netmem, 0);
+	netmem_set_dma_index(netmem, 0);
 }
 
 /* Disconnects a page (from a page_pool).  API users can have a need
@@ -1083,8 +1116,32 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool)
 
 static void page_pool_scrub(struct page_pool *pool)
 {
+	unsigned long id;
+	void *ptr;
+
 	page_pool_empty_alloc_cache_once(pool);
-	pool->destroy_cnt++;
+	if (!pool->destroy_cnt++ && pool->dma_map) {
+		if (pool->dma_sync) {
+			/* paired with READ_ONCE in
+			 * page_pool_dma_sync_for_device() and
+			 * __page_pool_dma_sync_for_cpu()
+			 */
+			WRITE_ONCE(pool->dma_sync, false);
+
+			/* Make sure all concurrent returns that may see the old
+			 * value of dma_sync (and thus perform a sync) have
+			 * finished before doing the unmapping below. Skip the
+			 * wait if the device doesn't actually need syncing, or
+			 * if there are no outstanding mapped pages.
+			 */
+			if (dma_dev_need_sync(pool->p.dev) &&
+			    !xa_empty(&pool->dma_mapped))
+				synchronize_net();
+		}
+
+		xa_for_each(&pool->dma_mapped, id, ptr)
+			__page_pool_release_page_dma(pool, page_to_netmem(ptr));
+	}
 
 	/* No more consumers should exist, but producers could still
 	 * be in-flight.

-- 
2.48.1

Re: [PATCH net-next v3 0/3] Fix late DMA unmap crash for page pool

[Jakub Kicinski]

On Wed, 26 Mar 2025 09:18:37 +0100 Toke Høiland-Jørgensen wrote:
> This series fixes the late dma_unmap crash for page pool first reported
> by Yonglong Liu in [0]. It is an alternative approach to the one
> submitted by Yunsheng Lin, most recently in [1]. The first two commits
> are small refactors of the page pool code, in preparation of the main
> change in patch 3. See the commit message of patch 3 for the details.

Doesn't apply, FWIW, maybe rebase/repost after Linus pull net-next, 
in case something conflicts on the MM side
-- 
pw-bot: cr

Re: [PATCH net-next v3 0/3] Fix late DMA unmap crash for page pool

[Toke Høiland-Jørgensen]

Jakub Kicinski <kuba@kernel.org> writes:

> On Wed, 26 Mar 2025 09:18:37 +0100 Toke Høiland-Jørgensen wrote:
>> This series fixes the late dma_unmap crash for page pool first reported
>> by Yonglong Liu in [0]. It is an alternative approach to the one
>> submitted by Yunsheng Lin, most recently in [1]. The first two commits
>> are small refactors of the page pool code, in preparation of the main
>> change in patch 3. See the commit message of patch 3 for the details.
>
> Doesn't apply, FWIW,

Ugh, sorry about that; rebased yesterday before reposting, but forgot to
do so this morning :/

> maybe rebase/repost after Linus pull net-next, in case something
> conflicts on the MM side

As in, you want to wait until after the merge window? Sure, can do.

-Toke

Re: [PATCH net-next v3 1/3] page_pool: Move pp_magic check into helper functions

[Jesper Dangaard Brouer]

On 26/03/2025 09.18, Toke Høiland-Jørgensen wrote:
> Since we are about to stash some more information into the pp_magic
> field, let's move the magic signature checks into a pair of helper
> functions so it can be changed in one place.
> 
> Reviewed-by: Mina Almasry<almasrymina@google.com>
> Tested-by: Yonglong Liu<liuyonglong@huawei.com>
> Signed-off-by: Toke Høiland-Jørgensen<toke@redhat.com>
> ---
>   drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c |  4 ++--
>   include/net/page_pool/types.h                    | 18 ++++++++++++++++++
>   mm/page_alloc.c                                  |  9 +++------
>   net/core/netmem_priv.h                           |  5 +++++
>   net/core/skbuff.c                                | 16 ++--------------
>   net/core/xdp.c                                   |  4 ++--
>   6 files changed, 32 insertions(+), 24 deletions(-)

LGTM

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>

Re: [PATCH net-next v3 2/3] page_pool: Turn dma_sync into a full-width bool field

[Jesper Dangaard Brouer]

On 26/03/2025 09.18, Toke Høiland-Jørgensen wrote:
> Change the single-bit boolean for dma_sync into a full-width bool, so we
> can read it as volatile with READ_ONCE(). A subsequent patch will add
> writing with WRITE_ONCE() on teardown.
> 
> Reviewed-by: Mina Almasry<almasrymina@google.com>
> Tested-by: Yonglong Liu<liuyonglong@huawei.com>
> Signed-off-by: Toke Høiland-Jørgensen<toke@redhat.com>
> ---
>   include/net/page_pool/types.h | 6 +++---
>   net/core/page_pool.c          | 2 +-
>   2 files changed, 4 insertions(+), 4 deletions(-)

LGTM

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>

Re: [PATCH net-next v3 0/3] Fix late DMA unmap crash for page pool

[Jakub Kicinski]

On Wed, 26 Mar 2025 13:20:37 +0100 Toke Høiland-Jørgensen wrote:
> > maybe rebase/repost after Linus pull net-next, in case something
> > conflicts on the MM side  
> 
> As in, you want to wait until after the merge window? Sure, can do.

I think we can try in this merge window, just after our first big PR
which will hopefully come out today.

Re: [PATCH net-next v3 1/3] page_pool: Move pp_magic check into helper functions

[Ilias Apalodimas]

Thanks Toke,

On Wed, 26 Mar 2025 at 10:19, Toke Høiland-Jørgensen <toke@redhat.com> wrote:
>
> Since we are about to stash some more information into the pp_magic
> field, let's move the magic signature checks into a pair of helper
> functions so it can be changed in one place.
>
> Reviewed-by: Mina Almasry <almasrymina@google.com>
> Tested-by: Yonglong Liu <liuyonglong@huawei.com>
> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>

> ---
>  drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c |  4 ++--
>  include/net/page_pool/types.h                    | 18 ++++++++++++++++++
>  mm/page_alloc.c                                  |  9 +++------
>  net/core/netmem_priv.h                           |  5 +++++
>  net/core/skbuff.c                                | 16 ++--------------
>  net/core/xdp.c                                   |  4 ++--
>  6 files changed, 32 insertions(+), 24 deletions(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
> index 6f3094a479e1ec61854bb48a6a0c812167487173..70c6f0b2abb921778c98fbd428594ebd7986a302 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
> @@ -706,8 +706,8 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
>                                 xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
>                                 page = xdpi.page.page;
>
> -                               /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
> -                                * as we know this is a page_pool page.
> +                               /* No need to check page_pool_page_is_pp() as we
> +                                * know this is a page_pool page.
>                                  */
>                                 page_pool_recycle_direct(page->pp, page);
>                         } while (++n < num);
> diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
> index 36eb57d73abc6cfc601e700ca08be20fb8281055..df0d3c1608929605224feb26173135ff37951ef8 100644
> --- a/include/net/page_pool/types.h
> +++ b/include/net/page_pool/types.h
> @@ -54,6 +54,14 @@ struct pp_alloc_cache {
>         netmem_ref cache[PP_ALLOC_CACHE_SIZE];
>  };
>
> +/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
> + * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
> + * the head page of compound page and bit 1 for pfmemalloc page.
> + * page_is_pfmemalloc() is checked in __page_pool_put_page() to avoid recycling
> + * the pfmemalloc page.
> + */
> +#define PP_MAGIC_MASK ~0x3UL
> +
>  /**
>   * struct page_pool_params - page pool parameters
>   * @fast:      params accessed frequently on hotpath
> @@ -264,6 +272,11 @@ void page_pool_destroy(struct page_pool *pool);
>  void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
>                            const struct xdp_mem_info *mem);
>  void page_pool_put_netmem_bulk(netmem_ref *data, u32 count);
> +
> +static inline bool page_pool_page_is_pp(struct page *page)
> +{
> +       return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
> +}
>  #else
>  static inline void page_pool_destroy(struct page_pool *pool)
>  {
> @@ -278,6 +291,11 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
>  static inline void page_pool_put_netmem_bulk(netmem_ref *data, u32 count)
>  {
>  }
> +
> +static inline bool page_pool_page_is_pp(struct page *page)
> +{
> +       return false;
> +}
>  #endif
>
>  void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 542d25f77be80304b731411ffd29b276ee13be0c..3535ee76afe946cbb042ecbce603bdbedc9233b9 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -55,6 +55,7 @@
>  #include <linux/delayacct.h>
>  #include <linux/cacheinfo.h>
>  #include <linux/pgalloc_tag.h>
> +#include <net/page_pool/types.h>
>  #include <asm/div64.h>
>  #include "internal.h"
>  #include "shuffle.h"
> @@ -872,9 +873,7 @@ static inline bool page_expected_state(struct page *page,
>  #ifdef CONFIG_MEMCG
>                         page->memcg_data |
>  #endif
> -#ifdef CONFIG_PAGE_POOL
> -                       ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) |
> -#endif
> +                       page_pool_page_is_pp(page) |
>                         (page->flags & check_flags)))
>                 return false;
>
> @@ -901,10 +900,8 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
>         if (unlikely(page->memcg_data))
>                 bad_reason = "page still charged to cgroup";
>  #endif
> -#ifdef CONFIG_PAGE_POOL
> -       if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE))
> +       if (unlikely(page_pool_page_is_pp(page)))
>                 bad_reason = "page_pool leak";
> -#endif
>         return bad_reason;
>  }
>
> diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
> index 7eadb8393e002fd1cc2cef8a313d2ea7df76f301..f33162fd281c23e109273ba09950c5d0a2829bc9 100644
> --- a/net/core/netmem_priv.h
> +++ b/net/core/netmem_priv.h
> @@ -18,6 +18,11 @@ static inline void netmem_clear_pp_magic(netmem_ref netmem)
>         __netmem_clear_lsb(netmem)->pp_magic = 0;
>  }
>
> +static inline bool netmem_is_pp(netmem_ref netmem)
> +{
> +       return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE;
> +}
> +
>  static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)
>  {
>         __netmem_clear_lsb(netmem)->pp = pool;
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index ab8acb737b93299f503e5c298b87e18edd59d555..a64d777488e403d5fdef83ae42ae9e4924c1a0dc 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -893,11 +893,6 @@ static void skb_clone_fraglist(struct sk_buff *skb)
>                 skb_get(list);
>  }
>
> -static bool is_pp_netmem(netmem_ref netmem)
> -{
> -       return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE;
> -}
> -
>  int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
>                     unsigned int headroom)
>  {
> @@ -995,14 +990,7 @@ bool napi_pp_put_page(netmem_ref netmem)
>  {
>         netmem = netmem_compound_head(netmem);
>
> -       /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
> -        * in order to preserve any existing bits, such as bit 0 for the
> -        * head page of compound page and bit 1 for pfmemalloc page, so
> -        * mask those bits for freeing side when doing below checking,
> -        * and page_is_pfmemalloc() is checked in __page_pool_put_page()
> -        * to avoid recycling the pfmemalloc page.
> -        */
> -       if (unlikely(!is_pp_netmem(netmem)))
> +       if (unlikely(!netmem_is_pp(netmem)))
>                 return false;
>
>         page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
> @@ -1042,7 +1030,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
>
>         for (i = 0; i < shinfo->nr_frags; i++) {
>                 head_netmem = netmem_compound_head(shinfo->frags[i].netmem);
> -               if (likely(is_pp_netmem(head_netmem)))
> +               if (likely(netmem_is_pp(head_netmem)))
>                         page_pool_ref_netmem(head_netmem);
>                 else
>                         page_ref_inc(netmem_to_page(head_netmem));
> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index f86eedad586a77eb63a96a85aa6d068d3e94f077..0ba73943c6eed873b3d1c681b3b9a802b590f2d9 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -437,8 +437,8 @@ void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type,
>                 netmem = netmem_compound_head(netmem);
>                 if (napi_direct && xdp_return_frame_no_direct())
>                         napi_direct = false;
> -               /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
> -                * as mem->type knows this a page_pool page
> +               /* No need to check netmem_is_pp() as mem->type knows this a
> +                * page_pool page
>                  */
>                 page_pool_put_full_netmem(netmem_get_pp(netmem), netmem,
>                                           napi_direct);
>
> --
> 2.48.1
>

Re: [PATCH net-next v3 2/3] page_pool: Turn dma_sync into a full-width bool field

[Alexander Lobakin]

From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Wed, 26 Mar 2025 09:18:39 +0100

> Change the single-bit boolean for dma_sync into a full-width bool, so we
> can read it as volatile with READ_ONCE(). A subsequent patch will add
> writing with WRITE_ONCE() on teardown.

Don't we have something like READ_ONCE(), but for one bit? Like
atomic-load-blah?

> 
> Reviewed-by: Mina Almasry <almasrymina@google.com>
> Tested-by: Yonglong Liu <liuyonglong@huawei.com>
> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
> ---
>  include/net/page_pool/types.h | 6 +++---
>  net/core/page_pool.c          | 2 +-
>  2 files changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
> index df0d3c1608929605224feb26173135ff37951ef8..d6c93150384fbc4579bb0d0afb357ebb26c564a3 100644
> --- a/include/net/page_pool/types.h
> +++ b/include/net/page_pool/types.h
> @@ -173,10 +173,10 @@ struct page_pool {
>  	int cpuid;
>  	u32 pages_state_hold_cnt;
>  
> -	bool has_init_callback:1;	/* slow::init_callback is set */
> +	bool dma_sync;				/* Perform DMA sync for device */
> +	bool dma_sync_for_cpu:1;		/* Perform DMA sync for cpu */
>  	bool dma_map:1;			/* Perform DMA mapping */
> -	bool dma_sync:1;		/* Perform DMA sync for device */
> -	bool dma_sync_for_cpu:1;	/* Perform DMA sync for cpu */
> +	bool has_init_callback:1;	/* slow::init_callback is set */
>  #ifdef CONFIG_PAGE_POOL_STATS
>  	bool system:1;			/* This is a global percpu pool */
>  #endif
> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> index acef1fcd8ddcfd1853a6f2055c1f1820ab248e8d..fb32768a97765aacc7f1103bfee38000c988b0de 100644
> --- a/net/core/page_pool.c
> +++ b/net/core/page_pool.c
> @@ -466,7 +466,7 @@ page_pool_dma_sync_for_device(const struct page_pool *pool,
>  			      netmem_ref netmem,
>  			      u32 dma_sync_size)
>  {
> -	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
> +	if (READ_ONCE(pool->dma_sync) && dma_dev_need_sync(pool->p.dev))
>  		__page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
>  }

Thanks,
Olek

Re: [PATCH net-next v3 0/3] Fix late DMA unmap crash for page pool

[Toke Høiland-Jørgensen]

Jakub Kicinski <kuba@kernel.org> writes:

> On Wed, 26 Mar 2025 13:20:37 +0100 Toke Høiland-Jørgensen wrote:
>> > maybe rebase/repost after Linus pull net-next, in case something
>> > conflicts on the MM side  
>> 
>> As in, you want to wait until after the merge window? Sure, can do.
>
> I think we can try in this merge window, just after our first big PR
> which will hopefully come out today.

Alright, cool. That seems to have been merged this morning, so I'll
rebase and send a v4.

-Toke