From: Christoph Hellwig <hch@lst.de>
To: Keith Busch <kbusch@kernel.org>, Sagi Grimberg <sagi@grimberg.me>
Cc: linux-nvme@lists.infradead.org
Subject: [PATCH 1/2] nvme-pci: fix freeing of the HMB descriptor table
Date: Fri, 1 Nov 2024 05:40:04 +0100 [thread overview]
Message-ID: <20241101044016.405265-2-hch@lst.de> (raw)
In-Reply-To: <20241101044016.405265-1-hch@lst.de>
The HMB descriptor table is sized to the maximum number of descriptors
that could be used for a given device, but __nvme_alloc_host_mem could
break out of the loop earlier on memory allocation failure and end up
using less descriptors than planned for, which leads to an incorrect
size passed to dma_free_coherent.
In practice this was not showing up because the number of descriptors
tends to be low and the dma coherent allocator always allocates and
frees at least a page.
Fixes: 87ad72a59a38 ("nvme-pci: implement host memory buffer support")
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/pci.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4b9fda0b1d9a..34daf6d8db07 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -153,6 +153,7 @@ struct nvme_dev {
/* host memory buffer support: */
u64 host_mem_size;
u32 nr_host_mem_descs;
+ u32 host_mem_descs_size;
dma_addr_t host_mem_descs_dma;
struct nvme_host_mem_buf_desc *host_mem_descs;
void **host_mem_desc_bufs;
@@ -1966,10 +1967,10 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
kfree(dev->host_mem_desc_bufs);
dev->host_mem_desc_bufs = NULL;
- dma_free_coherent(dev->dev,
- dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
+ dma_free_coherent(dev->dev, dev->host_mem_descs_size,
dev->host_mem_descs, dev->host_mem_descs_dma);
dev->host_mem_descs = NULL;
+ dev->host_mem_descs_size = 0;
dev->nr_host_mem_descs = 0;
}
@@ -1977,7 +1978,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
u32 chunk_size)
{
struct nvme_host_mem_buf_desc *descs;
- u32 max_entries, len;
+ u32 max_entries, len, descs_size;
dma_addr_t descs_dma;
int i = 0;
void **bufs;
@@ -1990,8 +1991,9 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
max_entries = dev->ctrl.hmmaxd;
- descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs),
- &descs_dma, GFP_KERNEL);
+ descs_size = max_entries * sizeof(*descs);
+ descs = dma_alloc_coherent(dev->dev, descs_size, &descs_dma,
+ GFP_KERNEL);
if (!descs)
goto out;
@@ -2020,6 +2022,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
dev->host_mem_size = size;
dev->host_mem_descs = descs;
dev->host_mem_descs_dma = descs_dma;
+ dev->host_mem_descs_size = descs_size;
dev->host_mem_desc_bufs = bufs;
return 0;
@@ -2034,8 +2037,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
kfree(bufs);
out_free_descs:
- dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs,
- descs_dma);
+ dma_free_coherent(dev->dev, descs_size, descs, descs_dma);
out:
dev->host_mem_descs = NULL;
return -ENOMEM;
--
2.45.2
next prev parent reply other threads:[~2024-11-01 4:40 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-01 4:40 create single-segment HMBs when using IOMMU Christoph Hellwig
2024-11-01 4:40 ` Christoph Hellwig [this message]
2024-11-01 4:40 ` [PATCH 2/2] nvme-pci: use dma_alloc_noncontigous if possible Christoph Hellwig
2024-12-02 19:05 ` Leon Romanovsky
2024-12-02 19:15 ` Keith Busch
2024-12-02 19:20 ` Leon Romanovsky
2024-12-03 0:33 ` Christoph Hellwig
2024-11-05 15:59 ` create single-segment HMBs when using IOMMU Keith Busch
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241101044016.405265-2-hch@lst.de \
--to=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=sagi@grimberg.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox