mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH] dma-buf: Restore the scatterlist entry count before freeing
@ 2026-10-13 11:46 Leon Romanovsky
  0 siblings, 0 replies; only message in thread
From: Leon Romanovsky @ 2026-10-13 11:46 UTC (permalink / raw)
  To: Sumit Semwal, Christian König, Kevin Tian, Leon Romanovsky,
	Jason Gunthorpe, Nicolin Chen, Ankit Agrawal
  Cc: Alex Williamson, linux-media, dri-devel, linaro-mm-sig, linux-kernel

From: Leon Romanovsky <leonro@nvidia.com>

dma_buf_phys_vec_to_sgt() clears orig_nents to mark the returned table
as DMA-only. Since sg_free_table() uses orig_nents to walk and free the
scatterlist, dma_buf_free_sgt() leaks the allocation on every successful
map/unmap cycle.

Restore orig_nents from nents before freeing the table. The helper
allocates the DMA list directly, so nents retains the allocation count,
including for chained scatterlists.


The reported kmemleak output was:

KMEMLEAK LEAK: 2 driver-related leak(s)
KMEMLEAK LEAK: unreferenced object 0xff11000125ceff00 (size 32):
KMEMLEAK LEAK:   comm dtr, pid 4432, jiffies 4295031027
KMEMLEAK LEAK:   hex dump (first 32 bytes):
KMEMLEAK LEAK:     02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
KMEMLEAK LEAK:     00 00 01 00 28 38 00 00 00 10 00 00 00 00 00 00  ....(8..........
KMEMLEAK LEAK:   backtrace (crc 4e8077f2):
KMEMLEAK LEAK:     __kmalloc_noprof+0x451/0x8b0
KMEMLEAK LEAK:     __sg_alloc_table+0x2a0/0x4d0
KMEMLEAK LEAK:     sg_alloc_table+0x24/0x170
KMEMLEAK LEAK:     dma_buf_phys_vec_to_sgt+0x84f/0xed0
KMEMLEAK LEAK:     0xffffffffa1ad21a8
KMEMLEAK LEAK:     dma_buf_map_attachment+0x138/0x690
KMEMLEAK LEAK:     ib_umem_dmabuf_map_pages+0x249/0xc90 [ib_core]
KMEMLEAK LEAK:     0xffffffffa138f8d2
KMEMLEAK LEAK:     0xffffffffa1396abe
KMEMLEAK LEAK:     0xffffffffa1331a5f
KMEMLEAK LEAK:     0xffffffffa13320dd
KMEMLEAK LEAK:     0xffffffffa1ad696d
KMEMLEAK LEAK:     0xffffffffa1acecc7
KMEMLEAK LEAK:     0xffffffffa1acfd17
KMEMLEAK LEAK:     __x64_sys_ioctl+0x72c/0x11f0
KMEMLEAK LEAK:     do_syscall_64+0xa1/0x4f0
KMEMLEAK LEAK: unreferenced object 0xff1100016dbf3a80 (size 32):
KMEMLEAK LEAK:   comm dtr, pid 4432, jiffies 4295034705
KMEMLEAK LEAK:   hex dump (first 32 bytes):
KMEMLEAK LEAK:     02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
KMEMLEAK LEAK:     00 20 10 00 28 38 00 00 00 10 00 00 00 00 00 00  . ..(8..........

Fixes: 3aa31a8bb11e ("dma-buf: provide phys_vec to scatter-gather mapping routine")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/dma-buf/dma-buf-mapping.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/dma-buf/dma-buf-mapping.c b/drivers/dma-buf/dma-buf-mapping.c
index 833be519e1e6..cbdf99cb0e05 100644
--- a/drivers/dma-buf/dma-buf-mapping.c
+++ b/drivers/dma-buf/dma-buf-mapping.c
@@ -251,6 +251,8 @@ void dma_buf_free_sgt(struct dma_buf_attachment *attach, struct sg_table *sgt,
 				       sg_dma_len(sgl), dir, DMA_ATTR_MMIO);
 	}
 
+	/* Restore the allocation count cleared for the DMA-only table. */
+	sgt->orig_nents = sgt->nents;
 	sg_free_table(sgt);
 	kfree(dma->state);
 	kfree(dma);

---
base-commit: 39d3758108bb0ef9da484062d65288bbe9cada0e
change-id: 20261013-dma-buf-fixes-99dd3fd00f48

Best regards,
--  
Leon Romanovsky <leonro@nvidia.com>


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2026-10-13 11:46 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-10-13 11:46 [PATCH] dma-buf: Restore the scatterlist entry count before freeing Leon Romanovsky

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®