tmakin/tegra-linux-noble
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

vfio/mlx5: Align the page tracking max message size with the device capability

Browse Source 
BugLink: https://bugs.launchpad.net/bugs/2102118

[ Upstream commit 9c7c5430bca36e9636eabbba0b3b53251479c7ab ]

Align the page tracking maximum message size with the device's
capability instead of relying on PAGE_SIZE.

This adjustment resolves a mismatch on systems where PAGE_SIZE is 64K,
but the firmware only supports a maximum message size of 4K.

Now that we rely on the device's capability for max_message_size, we
must account for potential future increases in its value.

Key considerations include:
- Supporting message sizes that exceed a single system page (e.g., an 8K
  message on a 4K system).
- Ensuring the RQ size is adjusted to accommodate at least 4
  WQEs/messages, in line with the device specification.

The above has been addressed as part of the patch.

Fixes: 79c3cf2799 ("vfio/mlx5: Init QP based resources for dirty tracking")
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Tested-by: Yingshun Cui <yicui@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241205122654.235619-1-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Koichiro Den <koichiro.den@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
This commit is contained in:
Yishai Hadas
2025-03-12 22:51:00 +09:00
committed by Stefan Bader
parent 0f4121fb07
commit 034c660f96
1 changed files with 35 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
drivers/vfio/pci/mlx5/cmd.c
+35 -12
View File
@@ -1417,7 +1417,8 @@ int mlx5vf_start_page_tracker(struct vfio_device *vdev,
struct mlx5_vhca_qp *host_qp;
struct mlx5_vhca_qp *fw_qp;
struct mlx5_core_dev *mdev;
u32 max_msg_size = PAGE_SIZE;
u32 log_max_msg_size;
u32 max_msg_size;
u64 rq_size = SZ_2M;
u32 max_recv_wr;
int err;
@@ -1434,6 +1435,12 @@ int mlx5vf_start_page_tracker(struct vfio_device *vdev,
}
mdev = mvdev->mdev;
log_max_msg_size = MLX5_CAP_ADV_VIRTUALIZATION(mdev, pg_track_log_max_msg_size);
max_msg_size = (1ULL << log_max_msg_size);
/* The RQ must hold at least 4 WQEs/messages for successful QP creation */
if (rq_size < 4 * max_msg_size)
rq_size = 4 * max_msg_size;
memset(tracker, 0, sizeof(*tracker));
tracker->uar = mlx5_get_uars_page(mdev);
if (IS_ERR(tracker->uar)) {
@@ -1523,25 +1530,41 @@ set_report_output(u32 size, int index, struct mlx5_vhca_qp *qp,
{
u32 entry_size = MLX5_ST_SZ_BYTES(page_track_report_entry);
u32 nent = size / entry_size;
u32 nent_in_page;
u32 nent_to_set;
struct page *page;
u32 page_offset;
u32 page_index;
u32 buf_offset;
void *kaddr;
u64 addr;
u64 *buf;
int i;
if (WARN_ON(index >= qp->recv_buf.npages ||
buf_offset = index * qp->max_msg_size;
if (WARN_ON(buf_offset + size >= qp->recv_buf.npages * PAGE_SIZE ||
(nent > qp->max_msg_size / entry_size)))
return;
page = qp->recv_buf.page_list[index];
buf = kmap_local_page(page);
for (i = 0; i < nent; i++) {
addr = MLX5_GET(page_track_report_entry, buf + i,
dirty_address_low);
addr |= (u64)MLX5_GET(page_track_report_entry, buf + i,
dirty_address_high) << 32;
iova_bitmap_set(dirty, addr, qp->tracked_page_size);
}
kunmap_local(buf);
do {
page_index = buf_offset / PAGE_SIZE;
page_offset = buf_offset % PAGE_SIZE;
nent_in_page = (PAGE_SIZE - page_offset) / entry_size;
page = qp->recv_buf.page_list[page_index];
kaddr = kmap_local_page(page);
buf = kaddr + page_offset;
nent_to_set = min(nent, nent_in_page);
for (i = 0; i < nent_to_set; i++) {
addr = MLX5_GET(page_track_report_entry, buf + i,
dirty_address_low);
addr |= (u64)MLX5_GET(page_track_report_entry, buf + i,
dirty_address_high) << 32;
iova_bitmap_set(dirty, addr, qp->tracked_page_size);
}
kunmap_local(kaddr);
buf_offset += (nent_to_set * entry_size);
nent -= nent_to_set;
} while (nent);
}
static void