* [PATCH 06/61] 9p: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Eric Van Hensbergen, Latchesar Ionkov, Dominique Martinet,
Christian Schoenebeck
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: Eric Van Hensbergen <ericvh@kernel.org>
To: Latchesar Ionkov <lucho@ionkov.net>
To: Dominique Martinet <asmadeus@codewreck.org>
To: Christian Schoenebeck <linux_oss@crudebyte.com>
Cc: v9fs@lists.linux.dev
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/9p/fid.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/9p/fid.h b/fs/9p/fid.h
index 0d6138bee2a3d1ab565ab2d210c0a3f3bf97e4e3..3bb7ef4380e972a2d9ab67eb4aab6cc5bfe2eea7 100644
--- a/fs/9p/fid.h
+++ b/fs/9p/fid.h
@@ -27,7 +27,7 @@ static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
struct p9_fid *fid, *nfid;
fid = v9fs_fid_lookup(dentry);
- if (!fid || IS_ERR(fid))
+ if (IS_ERR_OR_NULL(fid))
return fid;
nfid = clone_fid(fid);
--
2.43.0
^ permalink raw reply related
* [PATCH 18/61] sound: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Sylwester Nawrocki, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Max Filippov
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: Sylwester Nawrocki <s.nawrocki@samsung.com>
To: Liam Girdwood <lgirdwood@gmail.com>
To: Mark Brown <broonie@kernel.org>
To: Jaroslav Kysela <perex@perex.cz>
To: Takashi Iwai <tiwai@suse.com>
To: Max Filippov <jcmvbkbc@gmail.com>
Cc: linux-sound@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
sound/soc/samsung/i2s.c | 4 ++--
sound/soc/xtensa/xtfpga-i2s.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index e9964f0e010aee549cced75d8fe2023e8271d443..6e86f3a0a52dd3f8fc728d634594eb81f9945c57 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -559,7 +559,7 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai, int clk_id, unsigned int rfs,
clk_id = 1;
if (!any_active(i2s)) {
- if (priv->op_clk && !IS_ERR(priv->op_clk)) {
+ if (!IS_ERR_OR_NULL(priv->op_clk)) {
if ((clk_id && !(mod & rsrc_mask)) ||
(!clk_id && (mod & rsrc_mask))) {
clk_disable_unprepare(priv->op_clk);
@@ -812,7 +812,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
i2s->frmclk = params_rate(params);
rclksrc = priv->clk_table[CLK_I2S_RCLK_SRC];
- if (rclksrc && !IS_ERR(rclksrc))
+ if (!IS_ERR_OR_NULL(rclksrc))
priv->rclk_srcrate = clk_get_rate(rclksrc);
return 0;
diff --git a/sound/soc/xtensa/xtfpga-i2s.c b/sound/soc/xtensa/xtfpga-i2s.c
index 678ded059b959d475b6be3766867c8a78bdd4e54..698905257b690457a5d3d315e77d99d487d91f77 100644
--- a/sound/soc/xtensa/xtfpga-i2s.c
+++ b/sound/soc/xtensa/xtfpga-i2s.c
@@ -609,7 +609,7 @@ static void xtfpga_i2s_remove(struct platform_device *pdev)
{
struct xtfpga_i2s *i2s = dev_get_drvdata(&pdev->dev);
- if (i2s->regmap && !IS_ERR(i2s->regmap)) {
+ if (!IS_ERR_OR_NULL(i2s->regmap)) {
regmap_write(i2s->regmap, XTFPGA_I2S_CONFIG, 0);
regmap_write(i2s->regmap, XTFPGA_I2S_INT_MASK, 0);
regmap_write(i2s->regmap, XTFPGA_I2S_INT_STATUS,
--
2.43.0
^ permalink raw reply related
* [PATCH 09/61] ntfs3: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Konstantin Komarov
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Cc: ntfs3@lists.linux.dev
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/ntfs3/fsntfs.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 0df2aa81d8845f21bfb571c408bd65b9e1fb8128..3ced4f95c2e95bac1fe5b334f976b8c8a15cf19d 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -237,7 +237,7 @@ int ntfs_extend_init(struct ntfs_sb_info *sbi)
/* Try to find $ObjId */
inode2 = dir_search_u(inode, &NAME_OBJID, NULL);
- if (inode2 && !IS_ERR(inode2)) {
+ if (!IS_ERR_OR_NULL(inode2)) {
if (is_bad_inode(inode2)) {
iput(inode2);
} else {
@@ -248,21 +248,21 @@ int ntfs_extend_init(struct ntfs_sb_info *sbi)
/* Try to find $Quota */
inode2 = dir_search_u(inode, &NAME_QUOTA, NULL);
- if (inode2 && !IS_ERR(inode2)) {
+ if (!IS_ERR_OR_NULL(inode2)) {
sbi->quota_no = inode2->i_ino;
iput(inode2);
}
/* Try to find $Reparse */
inode2 = dir_search_u(inode, &NAME_REPARSE, NULL);
- if (inode2 && !IS_ERR(inode2)) {
+ if (!IS_ERR_OR_NULL(inode2)) {
sbi->reparse.ni = ntfs_i(inode2);
sbi->reparse_no = inode2->i_ino;
}
/* Try to find $UsnJrnl */
inode2 = dir_search_u(inode, &NAME_USNJRNL, NULL);
- if (inode2 && !IS_ERR(inode2)) {
+ if (!IS_ERR_OR_NULL(inode2)) {
sbi->usn_jrnl_no = inode2->i_ino;
iput(inode2);
}
--
2.43.0
^ permalink raw reply related
* [PATCH 04/61] ext4: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Theodore Ts'o, Andreas Dilger
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: "Theodore Ts'o" <tytso@mit.edu>
To: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: linux-ext4@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/ext4/fast_commit.c | 2 +-
fs/ext4/mballoc.c | 2 +-
fs/ext4/namei.c | 2 +-
fs/ext4/symlink.c | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f575751f1cae430eead31afa4f7d03ade1099d4a..bc69ac1195acb823465e735572b8a21255d485f5 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -320,7 +320,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
if (ext4_fc_disabled(sb))
return;
- if (handle && !IS_ERR(handle))
+ if (!IS_ERR_OR_NULL(handle))
tid = handle->h_transaction->t_tid;
else {
read_lock(&sbi->s_journal->j_state_lock);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 20e9fdaf4301b61c9d54401ed95067db6b6b8173..d7f004817c1ff758e4e25f84b2c27238b7420f84 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2870,7 +2870,7 @@ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group,
EXT4_MB_GRP_NEED_INIT(grp) &&
ext4_free_group_clusters(sb, gdp) > 0 ) {
bh = ext4_read_block_bitmap_nowait(sb, group, true);
- if (bh && !IS_ERR(bh)) {
+ if (!IS_ERR_OR_NULL(bh)) {
if (!buffer_uptodate(bh) && cnt)
(*cnt)++;
brelse(bh);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index c4b5e252af0efbfcbaf83688a32d445327a74a02..4fdfc81f79028a588b3c1f912bff5e8a52cd9f13 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -723,7 +723,7 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
struct stats stats;
printk("%s%3u:%03u hash %8x/%8x ",levels?"":" ", i, block, hash, range);
bh = ext4_bread(NULL,dir, block, 0);
- if (!bh || IS_ERR(bh))
+ if (IS_ERR_OR_NULL(bh))
continue;
stats = levels?
dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1):
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 645240cc0229fe4a2eda4499ae4a834fe3bd3a66..b612262719ede35d2612c5834d2bef7f18215516 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -92,7 +92,7 @@ static const char *ext4_get_link(struct dentry *dentry, struct inode *inode,
if (!dentry) {
bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT);
- if (IS_ERR(bh) || !bh)
+ if (IS_ERR_OR_NULL(bh))
return ERR_PTR(-ECHILD);
if (!ext4_buffer_uptodate(bh)) {
brelse(bh);
--
2.43.0
^ permalink raw reply related
* [PATCH 10/61] gfs2: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Andreas Gruenbacher
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: Andreas Gruenbacher <agruenba@redhat.com>
Cc: gfs2@lists.linux.dev
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/gfs2/glock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 2acbabccc8adf957e02845041193502a96370a6d..8ed6b4535a728e217e5cec7b64488583b5737c58 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -2013,7 +2013,7 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
do {
rhashtable_walk_start(&iter);
- while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl)) {
+ while (!IS_ERR_OR_NULL((gl = rhashtable_walk_next(&iter)))) {
if (glock_sbd(gl) == sdp)
examiner(gl);
}
--
2.43.0
^ permalink raw reply related
* [PATCH 07/61] erofs: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu, Sandeep Dhavale, Hongbo Li,
Chunhai Guo
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: Gao Xiang <xiang@kernel.org>
To: Chao Yu <chao@kernel.org>
To: Yue Hu <zbestahu@gmail.com>
To: Jeffle Xu <jefflexu@linux.alibaba.com>
To: Sandeep Dhavale <dhavale@google.com>
To: Hongbo Li <lihongbo22@huawei.com>
To: Chunhai Guo <guochunhai@vivo.com>
Cc: linux-erofs@lists.ozlabs.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/erofs/zdata.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 3977e42b9516861bf3d59c072b6b8aaa6898dd8a..88c293ab2b1ef7962c6f5c0aa82639859e41b8e2 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1227,7 +1227,7 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_backend *be, bool *overlapped)
struct page *page = bvec->page;
/* compressed data ought to be valid when decompressing */
- if (IS_ERR(page) || !page) {
+ if (IS_ERR_OR_NULL(page)) {
bvec->page = NULL; /* clear the failure reason */
err = page ? PTR_ERR(page) : -EIO;
continue;
--
2.43.0
^ permalink raw reply related
* [PATCH 01/61] Coccinelle: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Julia Lawall, Nicolas Palix
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Find and convert uses of IS_ERR() plus NULL check to IS_ERR_OR_NULL().
There are several cases where `!ptr && WARN_ON[_ONCE](IS_ERR(ptr))` is
used:
- arch/x86/kernel/callthunks.c:215 WARN_ON_ONCE
- drivers/clk/clk.c:4561 WARN_ON_ONCE
- drivers/interconnect/core.c:793 WARN_ON
- drivers/reset/core.c:718 WARN_ON
The change is not 100% semantical equivalent as the warning will now
also happen when the pointer is NULL.
To: Julia Lawall <Julia.Lawall@inria.fr>
To: Nicolas Palix <nicolas.palix@imag.fr>
Cc: cocci@inria.fr
Cc: linux-kernel@vger.kernel.org
---
drivers/clocksource/mips-gic-timer.c:283 looks suspicious: ret != clk,
but Daniel Lezcano verified it as cottect.
There are some cases where the checks are part of a larger expression:
- mm/kmemleak.c:1095
- mm/kmemleak.c:1155
- mm/kmemleak.c:1173
- mm/kmemleak.c:1290
- mm/kmemleak.c:1328
- mm/kmemleak.c:1241
- mm/kmemleak.c:1310
- mm/kmemleak.c:1258
- net/netlink/af_netlink.c:2670
Thanks to Julia Lawall for the help to also handle them.
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
scripts/coccinelle/api/is_err_or_null.cocci | 125 ++++++++++++++++++++++++++++
1 file changed, 125 insertions(+)
diff --git a/scripts/coccinelle/api/is_err_or_null.cocci b/scripts/coccinelle/api/is_err_or_null.cocci
new file mode 100644
index 0000000000000000000000000000000000000000..7a430eadccd9f9f28b1711d67dd87a817a45bd52
--- /dev/null
+++ b/scripts/coccinelle/api/is_err_or_null.cocci
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-only
+///
+/// Use IF_ERR_OR_NULL() instead of IS_ERR() plus a check for (not) NULL
+///
+// Copyright: (C) 2026 Philipp Hahn, FRITZ! Technology GmbH.
+// Confidence: High
+// Options: --no-includes --include-headers
+// Keywords: IS_ERR, IS_ERR_OR_NULL
+
+virtual patch
+virtual report
+virtual org
+
+@p1 depends on patch@
+expression E;
+@@
+(
+- E != NULL && !IS_ERR(E)
++ !IS_ERR_OR_NULL(E)
+|
+- E == NULL || IS_ERR(E)
++ IS_ERR_OR_NULL(E)
+|
+- !IS_ERR(E) && E != NULL
++ !IS_ERR_OR_NULL(E)
+|
+- IS_ERR(E) || E == NULL
++ IS_ERR_OR_NULL(E)
+)
+
+@p2 depends on patch@
+expression E;
+@@
+(
+- E == NULL || WARN_ON(IS_ERR(E))
++ WARN_ON(IS_ERR_OR_NULL(E))
+|
+- E == NULL || WARN_ON_ONCE(IS_ERR(E))
++ WARN_ON_ONCE(IS_ERR_OR_NULL(E))
+)
+
+@p3 depends on patch@
+expression E,e1;
+@@
+(
+- e1 && E != NULL && !IS_ERR(E)
++ e1 && !IS_ERR_OR_NULL(E)
+|
+- e1 || E == NULL || IS_ERR(E)
++ e1 || IS_ERR_OR_NULL(E)
+|
+- e1 && !IS_ERR(E) && E != NULL
++ e1 && !IS_ERR_OR_NULL(E)
+|
+- e1 || IS_ERR(E) || E == NULL
++ e1 || IS_ERR_OR_NULL(E)
+)
+
+@r1 depends on report || org@
+expression E;
+position p;
+@@
+(
+ E != NULL && ... && !IS_ERR@p(E)
+|
+ E == NULL || ... || IS_ERR@p(E)
+|
+ !IS_ERR@p(E) && ... && E != NULL
+|
+ IS_ERR@p(E) || ... || E == NULL
+)
+
+@script:python depends on report@
+p << r1.p;
+@@
+coccilib.report.print_report(p[0], "opportunity for IS_ERR_OR_NULL()")
+
+@script:python depends on org@
+p << r1.p;
+@@
+coccilib.org.print_todo(p[0], "opportunity for IS_ERR_OR_NULL()")
+
+@p4 depends on patch@
+identifier I;
+expression E;
+@@
+(
+- (I = E) != NULL && !IS_ERR(I)
++ !IS_ERR_OR_NULL((I = E))
+|
+- (I = E) == NULL || IS_ERR(I)
++ IS_ERR_OR_NULL((I = E))
+)
+
+@r2 depends on report || org@
+identifier I;
+expression E;
+position p;
+@@
+(
+* (I = E) != NULL && ... && !IS_ERR@p(I)
+|
+* (I = E) == NULL || ... || IS_ERR@p(I)
+)
+
+@script:python depends on report@
+p << r2.p;
+@@
+coccilib.report.print_report(p[0], "opportunity for IS_ERR_OR_NULL()")
+
+@script:python depends on org@
+p << r2.p;
+@@
+coccilib.org.print_todo(p[0], "opportunity for IS_ERR_OR_NULL()")
+
+@p5 depends on patch disable unlikely @
+expression E;
+@@
+-\( likely \| unlikely \)(
+(
+ IS_ERR_OR_NULL(E)
+|
+ !IS_ERR_OR_NULL(E)
+)
+-)
--
2.43.0
^ permalink raw reply related
* [PATCH 02/61] btrfs: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Chris Mason, David Sterba
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
IS_ERR_OR_NULL() already uses likely(!ptr) internally. checkpatch does
not like nesting it:
> WARNING: nested (un)?likely() calls, IS_ERR_OR_NULL already uses
> unlikely() internally
Remove the explicit use of likely().
Change generated with coccinelle.
To: Chris Mason <clm@fb.com>
To: David Sterba <dsterba@suse.com>
Cc: linux-btrfs@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/btrfs/inode.c | 2 +-
fs/btrfs/transaction.c | 2 +-
fs/btrfs/tree-log.c | 2 +-
fs/btrfs/uuid-tree.c | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a11fcc9e9f502c559148cf33679014fb83b0d3b0..7c26a0bf56bf7309e2ce8256854d760b2d64b16a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4683,7 +4683,7 @@ static noinline int may_destroy_subvol(struct btrfs_root *root)
dir_id = btrfs_super_root_dir(fs_info->super_copy);
di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path,
dir_id, &name, 0);
- if (di && !IS_ERR(di)) {
+ if (!IS_ERR_OR_NULL(di)) {
btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
if (key.objectid == btrfs_root_id(root)) {
ret = -EPERM;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7ef8c9b7dfc17a5133b6d2dc134e288975ed98d1..40b83037725033d3178dc3fc2c1e347ad2c597f7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1737,7 +1737,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
dir_item = btrfs_lookup_dir_item(NULL, parent_root, path,
btrfs_ino(parent_inode),
&fname.disk_name, 0);
- if (unlikely(dir_item != NULL && !IS_ERR(dir_item))) {
+ if (!IS_ERR_OR_NULL(dir_item)) {
pending->error = -EEXIST;
goto dir_item_existed;
} else if (IS_ERR(dir_item)) {
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 780a06d592409b05fb42dc8079b019d23fe0cdfa..2e07ae393cf9d16f562047dd4cbfd7b4b9f2952e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5750,7 +5750,7 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb,
name_str.len = this_name_len;
di = btrfs_lookup_dir_item(NULL, inode->root, search_path,
parent, &name_str, 0);
- if (di && !IS_ERR(di)) {
+ if (!IS_ERR_OR_NULL(di)) {
struct btrfs_key di_key;
btrfs_dir_item_key_to_cpu(search_path->nodes[0],
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index f24c14b9bb2fd7420b06263a5a0c4b889a859bc6..c497b287f3418933e532903b326b969416ae22cb 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -478,7 +478,7 @@ int btrfs_uuid_scan_kthread(void *data)
out:
btrfs_free_path(path);
- if (trans && !IS_ERR(trans))
+ if (!IS_ERR_OR_NULL(trans))
btrfs_end_transaction(trans);
if (ret)
btrfs_warn(fs_info, "btrfs_uuid_scan_kthread failed %d", ret);
--
2.43.0
^ permalink raw reply related
* [PATCH 13/61] squashfs: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Phillip Lougher
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: Phillip Lougher <phillip@squashfs.org.uk>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/squashfs/cache.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 67abd4dff222235e75d8c2b10d5e9b811d6e38d8..8888cc02966e2e33210c872c733205d4c581ecc9 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -198,7 +198,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache)
{
int i, j;
- if (IS_ERR(cache) || cache == NULL)
+ if (IS_ERR_OR_NULL(cache))
return;
for (i = 0; i < cache->entries; i++) {
--
2.43.0
^ permalink raw reply related
* [PATCH 03/61] ceph: Prefer IS_ERR_OR_NULL over manual NULL check
From: Philipp Hahn @ 2026-03-10 11:48 UTC (permalink / raw)
To: amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel, dri-devel,
gfs2, intel-gfx, intel-wired-lan, iommu, kvm, linux-arm-kernel,
linux-block, linux-bluetooth, linux-btrfs, linux-cifs, linux-clk,
linux-erofs, linux-ext4, linux-fsdevel, linux-gpio, linux-hyperv,
linux-input, linux-kernel, linux-leds, linux-media, linux-mips,
linux-mm, linux-modules, linux-mtd, linux-nfs, linux-omap,
linux-phy, linux-pm, linux-rockchip, linux-s390, linux-scsi,
linux-sctp, linux-security-module, linux-sh, linux-sound,
linux-stm32, linux-trace-kernel, linux-usb, linux-wireless,
netdev, ntfs3, samba-technical, sched-ext, target-devel,
tipc-discussion, v9fs, Philipp Hahn
Cc: Ilya Dryomov, Alex Markuze, Viacheslav Dubeyko
In-Reply-To: <20260310-b4-is_err_or_null-v1-0-bd63b656022d@avm.de>
Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
check.
Change generated with coccinelle.
To: Ilya Dryomov <idryomov@gmail.com>
To: Alex Markuze <amarkuze@redhat.com>
To: Viacheslav Dubeyko <slava@dubeyko.com>
Cc: ceph-devel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
---
fs/ceph/dir.c | 2 +-
fs/ceph/snap.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 86d7aa594ea99335af3e91a95c0a418fdc1b8a8a..934250748ae4fd4c148fd27bdf91175047c2877d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -889,7 +889,7 @@ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
{
struct dentry *result = ceph_lookup(dir, dentry, 0);
- if (result && !IS_ERR(result)) {
+ if (!IS_ERR_OR_NULL(result)) {
/*
* We created the item, then did a lookup, and found
* it was already linked to another inode we already
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 52b4c2684f922bfed39550311e793bfe3622cd26..528ad581be160713f91416115659e2dc6f259576 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -902,7 +902,7 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
bad:
err = -EIO;
fail:
- if (realm && !IS_ERR(realm))
+ if (!IS_ERR_OR_NULL(realm))
ceph_put_snap_realm(mdsc, realm);
if (first_realm)
ceph_put_snap_realm(mdsc, first_realm);
--
2.43.0
^ permalink raw reply related
* Re: [PATCH] Drivers: hv: vmbus: Fix potential NULL pointer dereference in vmbus_acpi_add()
From: Naman Jain @ 2026-03-10 11:18 UTC (permalink / raw)
To: Ваторопин Андрей,
K. Y. Srinivasan
Cc: Haiyang Zhang, Wei Liu, Dexuan Cui, Long Li, Saurabh Sengar,
Michael Kelley, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, lvc-project@linuxtesting.org,
stable@vger.kernel.org
In-Reply-To: <20260310084140.473079-1-a.vatoropin@crpt.ru>
On 3/10/2026 2:12 PM, Ваторопин Андрей wrote:
> From: Andrey Vatoropin <a.vatoropin@crpt.ru>
>
> The current driver supports detection via both the ACPI interface and the
> Device Tree interface (OF).
>
> In the function vmbus_platform_driver_probe() upon driver detection via OF,
> the branch vmbus_device_add() should be executed.
>
> However, the variable "acpi_disabled" is a global variable that, in general
> equals 0 when CONFIG_ACPI is enabled. Therefore, it may enter another
> branch with vmbus_acpi_add().
>
> Therefore, in the function vmbus_acpi_add(), when the device is not ACPI,
> the ACPI_COMPANION macro may return a NULL value, and this pointer is then
> dereferenced.
>
> Add a NULL pointer check for the "device" pointer before dereferencing it.
>
> Found by Linux Verification Center (linuxtesting.org) with SVACE.
>
> Fixes: f83705a51275 ("Driver: VMBus: Add Devicetree support")
> Cc: stable@vger.kernel.org
> Signed-off-by: Andrey Vatoropin <a.vatoropin@crpt.ru>
> ---
> drivers/hv/vmbus_drv.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index bc4fc1951ae1..c9ee3375b524 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -2571,6 +2571,9 @@ static int vmbus_acpi_add(struct platform_device *pdev)
> struct acpi_device *ancestor;
> struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
>
> + if (!device)
> + return -ENODEV;
> +
> vmbus_root_device = &device->dev;
>
> /*
I understand the case we are trying to make here, but I tried
reproducing this at my end, where we are probing VMBus using Devicetree,
and CONFIG_ACPI is enabled and there is no "acpi=off" in kernel cmdline.
But still, when the control reaches this particular function -
vmbus_platform_driver_probe(), acpi_disabled still shows up as 1 for me.
Can you please share your configuration how you are able to reproduce
this issue.
Secondly, let's say this case happens, then while our fix prevents null
pointer crash from happening, it does not fix the problem completely in
the sense - vmbus_device_add() should still have been called in this
scenario IMO. Please see if there is any way to do that, or comment, if
you feel this issue won't be there.
Regards,
Naman
^ permalink raw reply
* [PATCH] Drivers: hv: vmbus: Fix potential NULL pointer dereference in vmbus_acpi_add()
From: Ваторопин Андрей @ 2026-03-10 8:42 UTC (permalink / raw)
To: K. Y. Srinivasan
Cc: Ваторопин Андрей,
Haiyang Zhang, Wei Liu, Dexuan Cui, Long Li, Saurabh Sengar,
Michael Kelley, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, lvc-project@linuxtesting.org,
stable@vger.kernel.org
From: Andrey Vatoropin <a.vatoropin@crpt.ru>
The current driver supports detection via both the ACPI interface and the
Device Tree interface (OF).
In the function vmbus_platform_driver_probe() upon driver detection via OF,
the branch vmbus_device_add() should be executed.
However, the variable "acpi_disabled" is a global variable that, in general
equals 0 when CONFIG_ACPI is enabled. Therefore, it may enter another
branch with vmbus_acpi_add().
Therefore, in the function vmbus_acpi_add(), when the device is not ACPI,
the ACPI_COMPANION macro may return a NULL value, and this pointer is then
dereferenced.
Add a NULL pointer check for the "device" pointer before dereferencing it.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: f83705a51275 ("Driver: VMBus: Add Devicetree support")
Cc: stable@vger.kernel.org
Signed-off-by: Andrey Vatoropin <a.vatoropin@crpt.ru>
---
drivers/hv/vmbus_drv.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index bc4fc1951ae1..c9ee3375b524 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2571,6 +2571,9 @@ static int vmbus_acpi_add(struct platform_device *pdev)
struct acpi_device *ancestor;
struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
+ if (!device)
+ return -ENODEV;
+
vmbus_root_device = &device->dev;
/*
--
2.43.0
^ permalink raw reply related
* [PATCH net-next,V4, 3/3] net: mana: Add ethtool counters for RX CQEs in coalesced type
From: Haiyang Zhang @ 2026-03-09 21:20 UTC (permalink / raw)
To: linux-hyperv, netdev, K. Y. Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Konstantin Taranov, Simon Horman,
Erni Sri Satya Vennela, Dipayaan Roy, Shradha Gupta,
Shiraz Saleem, Kees Cook, Subbaraya Sundeep, Aditya Garg,
Breno Leitao, linux-kernel, linux-rdma
Cc: paulros
In-Reply-To: <20260309212106.764156-1-haiyangz@linux.microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
For RX CQEs with type CQE_RX_COALESCED_4, to measure the coalescing
efficiency, add counters to count how many contains 2, 3, 4 packets
respectively.
Also, add a counter for the error case of first packet with length == 0.
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 21 ++++++++++++++++++-
.../ethernet/microsoft/mana/mana_ethtool.c | 15 +++++++++++--
include/net/mana/mana.h | 9 +++++---
3 files changed, 39 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index fa30046dcd3d..85f7a56d0d90 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2148,11 +2148,23 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
old_buf = NULL;
pktlen = oob->ppi[i].pkt_len;
if (pktlen == 0) {
- if (i == 0)
+ /* Collect coalesced CQE count based on packets processed.
+ * Coalesced CQEs have at least 2 packets, so index is i - 2.
+ */
+ if (i > 1) {
+ u64_stats_update_begin(&rxq->stats.syncp);
+ rxq->stats.coalesced_cqe[i - 2]++;
+ u64_stats_update_end(&rxq->stats.syncp);
+ } else if (i == 0) {
+ /* Error case stat */
+ u64_stats_update_begin(&rxq->stats.syncp);
+ rxq->stats.pkt_len0_err++;
+ u64_stats_update_end(&rxq->stats.syncp);
netdev_err_once(
ndev,
"RX pkt len=0, rq=%u, cq=%u, rxobj=0x%llx\n",
rxq->gdma_id, cq->gdma_id, rxq->rxobj);
+ }
break;
}
@@ -2175,6 +2187,13 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
if (!coalesced)
break;
}
+
+ /* Coalesced CQE with all 4 packets */
+ if (coalesced && i == MANA_RXCOMP_OOB_NUM_PPI) {
+ u64_stats_update_begin(&rxq->stats.syncp);
+ rxq->stats.coalesced_cqe[MANA_RXCOMP_OOB_NUM_PPI - 2]++;
+ u64_stats_update_end(&rxq->stats.syncp);
+ }
}
static void mana_poll_rx_cq(struct mana_cq *cq)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 4b234b16e57a..6a4b42fe0944 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -149,7 +149,7 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
{
struct mana_port_context *apc = netdev_priv(ndev);
unsigned int num_queues = apc->num_queues;
- int i;
+ int i, j;
if (stringset != ETH_SS_STATS)
return;
@@ -168,6 +168,9 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
ethtool_sprintf(&data, "rx_%d_xdp_drop", i);
ethtool_sprintf(&data, "rx_%d_xdp_tx", i);
ethtool_sprintf(&data, "rx_%d_xdp_redirect", i);
+ ethtool_sprintf(&data, "rx_%d_pkt_len0_err", i);
+ for (j = 0; j < MANA_RXCOMP_OOB_NUM_PPI - 1; j++)
+ ethtool_sprintf(&data, "rx_%d_coalesced_cqe_%d", i, j + 2);
}
for (i = 0; i < num_queues; i++) {
@@ -201,6 +204,8 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
u64 xdp_xmit;
u64 xdp_drop;
u64 xdp_tx;
+ u64 pkt_len0_err;
+ u64 coalesced_cqe[MANA_RXCOMP_OOB_NUM_PPI - 1];
u64 tso_packets;
u64 tso_bytes;
u64 tso_inner_packets;
@@ -209,7 +214,7 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
u64 short_pkt_fmt;
u64 csum_partial;
u64 mana_map_err;
- int q, i = 0;
+ int q, i = 0, j;
if (!apc->port_is_up)
return;
@@ -239,6 +244,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
xdp_drop = rx_stats->xdp_drop;
xdp_tx = rx_stats->xdp_tx;
xdp_redirect = rx_stats->xdp_redirect;
+ pkt_len0_err = rx_stats->pkt_len0_err;
+ for (j = 0; j < MANA_RXCOMP_OOB_NUM_PPI - 1; j++)
+ coalesced_cqe[j] = rx_stats->coalesced_cqe[j];
} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
data[i++] = packets;
@@ -246,6 +254,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
data[i++] = xdp_drop;
data[i++] = xdp_tx;
data[i++] = xdp_redirect;
+ data[i++] = pkt_len0_err;
+ for (j = 0; j < MANA_RXCOMP_OOB_NUM_PPI - 1; j++)
+ data[i++] = coalesced_cqe[j];
}
for (q = 0; q < num_queues; q++) {
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index a7f89e7ddc56..3336688fed5e 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -61,8 +61,11 @@ enum TRI_STATE {
#define MAX_PORTS_IN_MANA_DEV 256
+/* Maximum number of packets per coalesced CQE */
+#define MANA_RXCOMP_OOB_NUM_PPI 4
+
/* Update this count whenever the respective structures are changed */
-#define MANA_STATS_RX_COUNT 5
+#define MANA_STATS_RX_COUNT (6 + MANA_RXCOMP_OOB_NUM_PPI - 1)
#define MANA_STATS_TX_COUNT 11
#define MANA_RX_FRAG_ALIGNMENT 64
@@ -73,6 +76,8 @@ struct mana_stats_rx {
u64 xdp_drop;
u64 xdp_tx;
u64 xdp_redirect;
+ u64 pkt_len0_err;
+ u64 coalesced_cqe[MANA_RXCOMP_OOB_NUM_PPI - 1];
struct u64_stats_sync syncp;
};
@@ -227,8 +232,6 @@ struct mana_rxcomp_perpkt_info {
u32 pkt_hash;
}; /* HW DATA */
-#define MANA_RXCOMP_OOB_NUM_PPI 4
-
/* Receive completion OOB */
struct mana_rxcomp_oob {
struct mana_cqe_header cqe_hdr;
--
2.34.1
^ permalink raw reply related
* [PATCH net-next,V4, 2/3] net: mana: Add support for RX CQE Coalescing
From: Haiyang Zhang @ 2026-03-09 21:20 UTC (permalink / raw)
To: linux-hyperv, netdev, K. Y. Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Konstantin Taranov, Simon Horman,
Erni Sri Satya Vennela, Shradha Gupta, Dipayaan Roy,
Shiraz Saleem, Kees Cook, Subbaraya Sundeep, Breno Leitao,
Aditya Garg, linux-kernel, linux-rdma
Cc: paulros
In-Reply-To: <20260309212106.764156-1-haiyangz@linux.microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
Our NIC can have up to 4 RX packets on 1 CQE. To support this feature,
check and process the type CQE_RX_COALESCED_4. The default setting is
disabled, to avoid possible regression on latency.
And, add ethtool handler to switch this feature. To turn it on, run:
ethtool -C <nic> rx-cqe-frames 4
To turn it off:
ethtool -C <nic> rx-cqe-frames 1
The rx-cqe-nsec is the time out value in nanoseconds after the first
packet arrival in a coalesced CQE to be sent. It's read-only for this
NIC.
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
v4:
Fixed the old_buf issue found by AI.
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 74 ++++++++++++-------
.../ethernet/microsoft/mana/mana_ethtool.c | 60 ++++++++++++++-
include/net/mana/mana.h | 8 +-
3 files changed, 113 insertions(+), 29 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ea71de39f996..fa30046dcd3d 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1365,6 +1365,7 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
sizeof(resp));
req->hdr.req.msg_version = GDMA_MESSAGE_V2;
+ req->hdr.resp.msg_version = GDMA_MESSAGE_V2;
req->vport = apc->port_handle;
req->num_indir_entries = apc->indir_table_sz;
@@ -1376,7 +1377,9 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
req->update_hashkey = update_key;
req->update_indir_tab = update_tab;
req->default_rxobj = apc->default_rxobj;
- req->cqe_coalescing_enable = 0;
+
+ if (rx != TRI_STATE_FALSE)
+ req->cqe_coalescing_enable = apc->cqe_coalescing_enable;
if (update_key)
memcpy(&req->hashkey, apc->hashkey, MANA_HASH_KEY_SIZE);
@@ -1405,8 +1408,13 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
netdev_err(ndev, "vPort RX configuration failed: 0x%x\n",
resp.hdr.status);
err = -EPROTO;
+ goto out;
}
+ if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V2)
+ apc->cqe_coalescing_timeout_ns =
+ resp.cqe_coalescing_timeout_ns;
+
netdev_info(ndev, "Configured steering vPort %llu entries %u\n",
apc->port_handle, apc->indir_table_sz);
out:
@@ -1915,11 +1923,12 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va,
}
static void mana_rx_skb(void *buf_va, bool from_pool,
- struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq)
+ struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq,
+ int i)
{
struct mana_stats_rx *rx_stats = &rxq->stats;
struct net_device *ndev = rxq->ndev;
- uint pkt_len = cqe->ppi[0].pkt_len;
+ uint pkt_len = cqe->ppi[i].pkt_len;
u16 rxq_idx = rxq->rxq_idx;
struct napi_struct *napi;
struct xdp_buff xdp = {};
@@ -1963,7 +1972,7 @@ static void mana_rx_skb(void *buf_va, bool from_pool,
}
if (cqe->rx_hashtype != 0 && (ndev->features & NETIF_F_RXHASH)) {
- hash_value = cqe->ppi[0].pkt_hash;
+ hash_value = cqe->ppi[i].pkt_hash;
if (cqe->rx_hashtype & MANA_HASH_L4)
skb_set_hash(skb, hash_value, PKT_HASH_TYPE_L4);
@@ -2098,9 +2107,11 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
struct mana_recv_buf_oob *rxbuf_oob;
struct mana_port_context *apc;
struct device *dev = gc->dev;
+ bool coalesced = false;
void *old_buf = NULL;
u32 curr, pktlen;
bool old_fp;
+ int i;
apc = netdev_priv(ndev);
@@ -2112,13 +2123,16 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
++ndev->stats.rx_dropped;
rxbuf_oob = &rxq->rx_oobs[rxq->buf_index];
netdev_warn_once(ndev, "Dropped a truncated packet\n");
- goto drop;
- case CQE_RX_COALESCED_4:
- netdev_err(ndev, "RX coalescing is unsupported\n");
- apc->eth_stats.rx_coalesced_err++;
+ mana_move_wq_tail(rxq->gdma_rq,
+ rxbuf_oob->wqe_inf.wqe_size_in_bu);
+ mana_post_pkt_rxq(rxq);
return;
+ case CQE_RX_COALESCED_4:
+ coalesced = true;
+ break;
+
case CQE_RX_OBJECT_FENCE:
complete(&rxq->fence_event);
return;
@@ -2130,30 +2144,37 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
return;
}
- pktlen = oob->ppi[0].pkt_len;
+ for (i = 0; i < MANA_RXCOMP_OOB_NUM_PPI; i++) {
+ old_buf = NULL;
+ pktlen = oob->ppi[i].pkt_len;
+ if (pktlen == 0) {
+ if (i == 0)
+ netdev_err_once(
+ ndev,
+ "RX pkt len=0, rq=%u, cq=%u, rxobj=0x%llx\n",
+ rxq->gdma_id, cq->gdma_id, rxq->rxobj);
+ break;
+ }
- if (pktlen == 0) {
- /* data packets should never have packetlength of zero */
- netdev_err(ndev, "RX pkt len=0, rq=%u, cq=%u, rxobj=0x%llx\n",
- rxq->gdma_id, cq->gdma_id, rxq->rxobj);
- return;
- }
+ curr = rxq->buf_index;
+ rxbuf_oob = &rxq->rx_oobs[curr];
+ WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
- curr = rxq->buf_index;
- rxbuf_oob = &rxq->rx_oobs[curr];
- WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
+ mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
- mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
+ /* Unsuccessful refill will have old_buf == NULL.
+ * In this case, mana_rx_skb() will drop the packet.
+ */
+ mana_rx_skb(old_buf, old_fp, oob, rxq, i);
- /* Unsuccessful refill will have old_buf == NULL.
- * In this case, mana_rx_skb() will drop the packet.
- */
- mana_rx_skb(old_buf, old_fp, oob, rxq);
+ mana_move_wq_tail(rxq->gdma_rq,
+ rxbuf_oob->wqe_inf.wqe_size_in_bu);
-drop:
- mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu);
+ mana_post_pkt_rxq(rxq);
- mana_post_pkt_rxq(rxq);
+ if (!coalesced)
+ break;
+ }
}
static void mana_poll_rx_cq(struct mana_cq *cq)
@@ -3332,6 +3353,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
apc->port_handle = INVALID_MANA_HANDLE;
apc->pf_filter_handle = INVALID_MANA_HANDLE;
apc->port_idx = port_idx;
+ apc->cqe_coalescing_enable = 0;
mutex_init(&apc->vport_mutex);
apc->vport_use_count = 0;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index f2d220b371b5..4b234b16e57a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -20,8 +20,6 @@ static const struct mana_stats_desc mana_eth_stats[] = {
tx_cqe_unknown_type)},
{"tx_linear_pkt_cnt", offsetof(struct mana_ethtool_stats,
tx_linear_pkt_cnt)},
- {"rx_coalesced_err", offsetof(struct mana_ethtool_stats,
- rx_coalesced_err)},
{"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
rx_cqe_unknown_type)},
};
@@ -390,6 +388,61 @@ static void mana_get_channels(struct net_device *ndev,
channel->combined_count = apc->num_queues;
}
+#define MANA_RX_CQE_NSEC_DEF 2048
+static int mana_get_coalesce(struct net_device *ndev,
+ struct ethtool_coalesce *ec,
+ struct kernel_ethtool_coalesce *kernel_coal,
+ struct netlink_ext_ack *extack)
+{
+ struct mana_port_context *apc = netdev_priv(ndev);
+
+ kernel_coal->rx_cqe_frames =
+ apc->cqe_coalescing_enable ? MANA_RXCOMP_OOB_NUM_PPI : 1;
+
+ kernel_coal->rx_cqe_nsecs = apc->cqe_coalescing_timeout_ns;
+
+ /* Return the default timeout value for old FW not providing
+ * this value.
+ */
+ if (apc->port_is_up && apc->cqe_coalescing_enable &&
+ !kernel_coal->rx_cqe_nsecs)
+ kernel_coal->rx_cqe_nsecs = MANA_RX_CQE_NSEC_DEF;
+
+ return 0;
+}
+
+static int mana_set_coalesce(struct net_device *ndev,
+ struct ethtool_coalesce *ec,
+ struct kernel_ethtool_coalesce *kernel_coal,
+ struct netlink_ext_ack *extack)
+{
+ struct mana_port_context *apc = netdev_priv(ndev);
+ u8 saved_cqe_coalescing_enable;
+ int err;
+
+ if (kernel_coal->rx_cqe_frames != 1 &&
+ kernel_coal->rx_cqe_frames != MANA_RXCOMP_OOB_NUM_PPI) {
+ NL_SET_ERR_MSG_FMT(extack,
+ "rx-frames must be 1 or %u, got %u",
+ MANA_RXCOMP_OOB_NUM_PPI,
+ kernel_coal->rx_cqe_frames);
+ return -EINVAL;
+ }
+
+ saved_cqe_coalescing_enable = apc->cqe_coalescing_enable;
+ apc->cqe_coalescing_enable =
+ kernel_coal->rx_cqe_frames == MANA_RXCOMP_OOB_NUM_PPI;
+
+ if (!apc->port_is_up)
+ return 0;
+
+ err = mana_config_rss(apc, TRI_STATE_TRUE, false, false);
+ if (err)
+ apc->cqe_coalescing_enable = saved_cqe_coalescing_enable;
+
+ return err;
+}
+
static int mana_set_channels(struct net_device *ndev,
struct ethtool_channels *channels)
{
@@ -510,6 +563,7 @@ static int mana_get_link_ksettings(struct net_device *ndev,
}
const struct ethtool_ops mana_ethtool_ops = {
+ .supported_coalesce_params = ETHTOOL_COALESCE_RX_CQE_FRAMES,
.get_ethtool_stats = mana_get_ethtool_stats,
.get_sset_count = mana_get_sset_count,
.get_strings = mana_get_strings,
@@ -520,6 +574,8 @@ const struct ethtool_ops mana_ethtool_ops = {
.set_rxfh = mana_set_rxfh,
.get_channels = mana_get_channels,
.set_channels = mana_set_channels,
+ .get_coalesce = mana_get_coalesce,
+ .set_coalesce = mana_set_coalesce,
.get_ringparam = mana_get_ringparam,
.set_ringparam = mana_set_ringparam,
.get_link_ksettings = mana_get_link_ksettings,
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index a078af283bdd..a7f89e7ddc56 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -378,7 +378,6 @@ struct mana_ethtool_stats {
u64 tx_cqe_err;
u64 tx_cqe_unknown_type;
u64 tx_linear_pkt_cnt;
- u64 rx_coalesced_err;
u64 rx_cqe_unknown_type;
};
@@ -557,6 +556,9 @@ struct mana_port_context {
bool port_is_up;
bool port_st_save; /* Saved port state */
+ u8 cqe_coalescing_enable;
+ u32 cqe_coalescing_timeout_ns;
+
struct mana_ethtool_stats eth_stats;
struct mana_ethtool_phy_stats phy_stats;
@@ -902,6 +904,10 @@ struct mana_cfg_rx_steer_req_v2 {
struct mana_cfg_rx_steer_resp {
struct gdma_resp_hdr hdr;
+
+ /* V2 */
+ u32 cqe_coalescing_timeout_ns;
+ u32 reserved1;
}; /* HW DATA */
/* Register HW vPort */
--
2.34.1
^ permalink raw reply related
* [PATCH net-next,V4, 1/3] net: ethtool: add ethtool COALESCE_RX_CQE_FRAMES/NSECS
From: Haiyang Zhang @ 2026-03-09 21:20 UTC (permalink / raw)
To: linux-hyperv, netdev, Andrew Lunn, Jakub Kicinski, Donald Hunter,
David S. Miller, Eric Dumazet, Paolo Abeni, Simon Horman,
Jonathan Corbet, Shuah Khan, Kory Maincent (Dent Project),
Gal Pressman, Oleksij Rempel, Vadim Fedorenko, linux-kernel,
linux-doc
Cc: haiyangz, paulros
In-Reply-To: <20260309212106.764156-1-haiyangz@linux.microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
Add two parameters for drivers supporting Rx CQE Coalescing.
ETHTOOL_A_COALESCE_RX_CQE_FRAMES:
Maximum number of frames that can be coalesced into a CQE.
ETHTOOL_A_COALESCE_RX_CQE_NSECS:
Time out value in nanoseconds after the first packet arrival in a
coalesced CQE to be sent.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
Documentation/netlink/specs/ethtool.yaml | 8 ++++++++
Documentation/networking/ethtool-netlink.rst | 10 ++++++++++
include/linux/ethtool.h | 6 +++++-
include/uapi/linux/ethtool_netlink_generated.h | 2 ++
net/ethtool/coalesce.c | 14 +++++++++++++-
5 files changed, 38 insertions(+), 2 deletions(-)
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 4707063af3b4..d254e26c014c 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -861,6 +861,12 @@ attribute-sets:
name: tx-profile
type: nest
nested-attributes: profile
+ -
+ name: rx-cqe-frames
+ type: u32
+ -
+ name: rx-cqe-nsecs
+ type: u32
-
name: pause-stat
@@ -2257,6 +2263,8 @@ operations:
- tx-aggr-time-usecs
- rx-profile
- tx-profile
+ - rx-cqe-frames
+ - rx-cqe-nsecs
dump: *coalesce-get-op
-
name: coalesce-set
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 32179168eb73..a9fbb16891fa 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1076,6 +1076,8 @@ Kernel response contents:
``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx
``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx
``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx
+ ``ETHTOOL_A_COALESCE_RX_CQE_FRAMES`` u32 max packets, Rx CQE
+ ``ETHTOOL_A_COALESCE_RX_CQE_NSECS`` u32 delay (ns), Rx CQE
=========================================== ====== =======================
Attributes are only included in reply if their value is not zero or the
@@ -1109,6 +1111,12 @@ well with frequent small-sized URBs transmissions.
to DIM parameters, see `Generic Network Dynamic Interrupt Moderation (Net DIM)
<https://www.kernel.org/doc/Documentation/networking/net_dim.rst>`_.
+Rx CQE coalescing allows multiple received packets to be coalesced into a single
+Completion Queue Entry (CQE). ``ETHTOOL_A_COALESCE_RX_CQE_FRAMES`` describes the
+maximum number of frames that can be coalesced into a CQE.
+``ETHTOOL_A_COALESCE_RX_CQE_NSECS`` describes max time in nanoseconds after the
+first packet arrival in a coalesced CQE to be sent.
+
COALESCE_SET
============
@@ -1147,6 +1155,8 @@ Request contents:
``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx
``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx
``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx
+ ``ETHTOOL_A_COALESCE_RX_CQE_FRAMES`` u32 max packets, Rx CQE
+ ``ETHTOOL_A_COALESCE_RX_CQE_NSECS`` u32 delay (ns), Rx CQE
=========================================== ====== =======================
Request is rejected if it attributes declared as unsupported by driver (i.e.
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 83c375840835..656d465bcd06 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -332,6 +332,8 @@ struct kernel_ethtool_coalesce {
u32 tx_aggr_max_bytes;
u32 tx_aggr_max_frames;
u32 tx_aggr_time_usecs;
+ u32 rx_cqe_frames;
+ u32 rx_cqe_nsecs;
};
/**
@@ -380,7 +382,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
#define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26)
#define ETHTOOL_COALESCE_RX_PROFILE BIT(27)
#define ETHTOOL_COALESCE_TX_PROFILE BIT(28)
-#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0)
+#define ETHTOOL_COALESCE_RX_CQE_FRAMES BIT(29)
+#define ETHTOOL_COALESCE_RX_CQE_NSECS BIT(30)
+#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(30, 0)
#define ETHTOOL_COALESCE_USECS \
(ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS)
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index 114b83017297..8134baf7860f 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -371,6 +371,8 @@ enum {
ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS,
ETHTOOL_A_COALESCE_RX_PROFILE,
ETHTOOL_A_COALESCE_TX_PROFILE,
+ ETHTOOL_A_COALESCE_RX_CQE_FRAMES,
+ ETHTOOL_A_COALESCE_RX_CQE_NSECS,
__ETHTOOL_A_COALESCE_CNT,
ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1)
diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c
index 3e18ca1ccc5e..349bb02c517a 100644
--- a/net/ethtool/coalesce.c
+++ b/net/ethtool/coalesce.c
@@ -118,6 +118,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base,
nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */
nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */
nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */
+ nla_total_size(sizeof(u32)) + /* _RX_CQE_FRAMES */
+ nla_total_size(sizeof(u32)) + /* _RX_CQE_NSECS */
total_modersz * 2; /* _{R,T}X_PROFILE */
}
@@ -269,7 +271,11 @@ static int coalesce_fill_reply(struct sk_buff *skb,
coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES,
kcoal->tx_aggr_max_frames, supported) ||
coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS,
- kcoal->tx_aggr_time_usecs, supported))
+ kcoal->tx_aggr_time_usecs, supported) ||
+ coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_CQE_FRAMES,
+ kcoal->rx_cqe_frames, supported) ||
+ coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_CQE_NSECS,
+ kcoal->rx_cqe_nsecs, supported))
return -EMSGSIZE;
if (!req_base->dev || !req_base->dev->irq_moder)
@@ -338,6 +344,8 @@ const struct nla_policy ethnl_coalesce_set_policy[] = {
[ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 },
[ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 },
[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 },
+ [ETHTOOL_A_COALESCE_RX_CQE_FRAMES] = { .type = NLA_U32 },
+ [ETHTOOL_A_COALESCE_RX_CQE_NSECS] = { .type = NLA_U32 },
[ETHTOOL_A_COALESCE_RX_PROFILE] =
NLA_POLICY_NESTED(coalesce_profile_policy),
[ETHTOOL_A_COALESCE_TX_PROFILE] =
@@ -570,6 +578,10 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info,
tb[ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES], &mod);
ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs,
tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod);
+ ethnl_update_u32(&kernel_coalesce.rx_cqe_frames,
+ tb[ETHTOOL_A_COALESCE_RX_CQE_FRAMES], &mod);
+ ethnl_update_u32(&kernel_coalesce.rx_cqe_nsecs,
+ tb[ETHTOOL_A_COALESCE_RX_CQE_NSECS], &mod);
if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) {
ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile,
--
2.34.1
^ permalink raw reply related
* [PATCH net-next,V4, 0/3] add ethtool COALESCE_RX_CQE_FRAMES/NSECS and use it in MANA driver
From: Haiyang Zhang @ 2026-03-09 21:20 UTC (permalink / raw)
To: linux-hyperv, netdev; +Cc: haiyangz, paulros
From: Haiyang Zhang <haiyangz@microsoft.com>
Add two parameters for drivers supporting Rx CQE Coalescing.
ETHTOOL_A_COALESCE_RX_CQE_FRAMES:
Maximum number of frames that can be coalesced into a CQE.
ETHTOOL_A_COALESCE_RX_CQE_NSECS:
Time out value in nanoseconds after the first packet arrival in a
coalesced CQE to be sent.
Also implement in MANA driver with the new parameter and
counters.
Haiyang Zhang (3):
net: ethtool: add ethtool COALESCE_RX_CQE_FRAMES/NSECS
net: mana: Add support for RX CQE Coalescing
net: mana: Add ethtool counters for RX CQEs in coalesced type
Documentation/netlink/specs/ethtool.yaml | 8 ++
Documentation/networking/ethtool-netlink.rst | 10 ++
drivers/net/ethernet/microsoft/mana/mana_en.c | 93 +++++++++++++------
.../ethernet/microsoft/mana/mana_ethtool.c | 75 ++++++++++++++-
include/linux/ethtool.h | 6 +-
include/net/mana/mana.h | 17 +++-
.../uapi/linux/ethtool_netlink_generated.h | 2 +
net/ethtool/coalesce.c | 14 ++-
8 files changed, 189 insertions(+), 36 deletions(-)
--
2.34.1
^ permalink raw reply
* [PATCH net] net: mana: Fix use-after-free in mana_hwc_destroy_channel() by re-ordering teardown
From: Dipayaan Roy @ 2026-03-09 18:21 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, leon, longli, kotaranov, horms, shradhagupta,
ssengar, ernis, shirazsaleem, linux-hyperv, netdev, linux-kernel,
linux-rdma, dipayanroy
A potential race condition exists in mana_hwc_destroy_channel() where
hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and
Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt
handler to dereference freed memory, leading to a use-after-free or
NULL pointer dereference in mana_hwc_handle_resp().
mana_smc_teardown_hwc() signals the hardware to stop but does not
synchronize against IRQ handlers already executing on other CPUs. The
IRQ synchronization only happens in mana_hwc_destroy_cq() via
mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs
after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler()
can dereference freed caller_ctx (and rxq->msg_buf) in
mana_hwc_handle_resp().
Fix this by reordering teardown to reverse-of-creation order: destroy
the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This
ensures all in-flight interrupt handlers complete before the memory they
access is freed.
Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)")
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
---
drivers/net/ethernet/microsoft/mana/hw_channel.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 91975bdb5686..dbbde0fa57e7 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -814,9 +814,6 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
gc->max_num_cqs = 0;
}
- kfree(hwc->caller_ctx);
- hwc->caller_ctx = NULL;
-
if (hwc->txq)
mana_hwc_destroy_wq(hwc, hwc->txq);
@@ -826,6 +823,9 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
if (hwc->cq)
mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc->cq);
+ kfree(hwc->caller_ctx);
+ hwc->caller_ctx = NULL;
+
mana_gd_free_res_map(&hwc->inflight_msg_res);
hwc->num_inflight_msg = 0;
--
2.43.0
^ permalink raw reply related
* Re: [PATCH v8 09/10] x86/hyperv/vtl: Mark the wakeup mailbox page as private
From: Wei Liu @ 2026-03-09 17:57 UTC (permalink / raw)
To: Ricardo Neri
Cc: x86, Krzysztof Kozlowski, Conor Dooley, Rob Herring,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Michael Kelley, Rafael J. Wysocki, Saurabh Sengar, Chris Oo,
Kirill A. Shutemov, linux-hyperv, devicetree, linux-acpi,
linux-kernel, Ricardo Neri, Yunhong Jiang
In-Reply-To: <20260107-rneri-wakeup-mailbox-v8-9-2f5b6785f2f5@linux.intel.com>
Dexuan, are you happy with the patch? You can also delegate to Saurabh
if you think it's more appropriate. Thanks!
On Wed, Jan 07, 2026 at 01:44:45PM -0800, Ricardo Neri wrote:
> From: Yunhong Jiang <yunhong.jiang@linux.intel.com>
>
> The current code maps MMIO devices as shared (decrypted) by default in a
> confidential computing VM.
>
> In a TDX environment, secondary CPUs are booted using the Multiprocessor
> Wakeup Structure defined in the ACPI specification. The virtual firmware
> and the operating system function in the guest context, without
> intervention from the VMM. Map the physical memory of the mailbox as
> private. Use the is_private_mmio() callback.
>
> Signed-off-by: Yunhong Jiang <yunhong.jiang@linux.intel.com>
> Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> ---
> Changes in v8:
> - Included linux/acpi.h to add missing definitions that caused build
> breaks (kernel test robot)
>
> Changes in v7:
> - Dropped check for !CONFIG_X86_MAILBOX_WAKEUP. The symbol is no longer
> valid and now we have a stub for !CONFIG_ACPI.
> - Dropped Reviewed-by tags from Dexuan and Michael as this patch
> changed.
>
> Changes in v6:
> - Fixed a compile error with !CONFIG_X86_MAILBOX_WAKEUP.
> - Added Reviewed-by tag from Dexuan. Thanks!
>
> Changes in v5:
> - None
>
> Changes in v4:
> - Updated to use the renamed function acpi_get_mp_wakeup_mailbox_paddr().
> - Added Reviewed-by tag from Michael. Thanks!
>
> Changes in v3:
> - Use the new helper function get_mp_wakeup_mailbox_paddr().
> - Edited the commit message for clarity.
>
> Changes in v2:
> - Added the helper function within_page() to improve readability
> - Override the is_private_mmio() callback when detecting a TDX
> environment. The address of the mailbox is checked in
> hv_is_private_mmio_tdx().
> ---
> arch/x86/hyperv/hv_vtl.c | 17 +++++++++++++++++
> 1 file changed, 17 insertions(+)
>
> diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
> index 752101544663..2af825f7a447 100644
> --- a/arch/x86/hyperv/hv_vtl.c
> +++ b/arch/x86/hyperv/hv_vtl.c
> @@ -6,6 +6,9 @@
> * Saurabh Sengar <ssengar@microsoft.com>
> */
>
> +#include <linux/acpi.h>
> +
> +#include <asm/acpi.h>
> #include <asm/apic.h>
> #include <asm/boot.h>
> #include <asm/desc.h>
> @@ -59,6 +62,18 @@ static void __noreturn hv_vtl_restart(char __maybe_unused *cmd)
> hv_vtl_emergency_restart();
> }
>
> +static inline bool within_page(u64 addr, u64 start)
> +{
> + return addr >= start && addr < (start + PAGE_SIZE);
> +}
> +
> +static bool hv_vtl_is_private_mmio_tdx(u64 addr)
> +{
> + u64 mb_addr = acpi_get_mp_wakeup_mailbox_paddr();
> +
> + return mb_addr && within_page(addr, mb_addr);
> +}
> +
> void __init hv_vtl_init_platform(void)
> {
> /*
> @@ -71,6 +86,8 @@ void __init hv_vtl_init_platform(void)
> /* There is no paravisor present if we are here. */
> if (hv_isolation_type_tdx()) {
> x86_init.resources.realmode_limit = SZ_4G;
> + x86_platform.hyper.is_private_mmio = hv_vtl_is_private_mmio_tdx;
> +
> } else {
> x86_platform.realmode_reserve = x86_init_noop;
> x86_platform.realmode_init = x86_init_noop;
>
> --
> 2.43.0
>
^ permalink raw reply
* [PATCH net-next v2] net: mana: Expose hardware diagnostic info via debugfs
From: Erni Sri Satya Vennela @ 2026-03-09 14:38 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, longli, andrew+netdev, davem,
edumazet, kuba, pabeni, kotaranov, horms, shradhagupta,
dipayanroy, yury.norov, kees, ernis, shirazsaleem, linux-hyperv,
netdev, linux-kernel, linux-rdma
Add debugfs entries to expose hardware configuration and diagnostic
information that aids in debugging driver initialization and runtime
operations without adding noise to dmesg.
Device-level entries (under /sys/kernel/debug/mana/<slot>/):
- num_msix_usable, max_num_queues: Max resources from hardware
- gdma_protocol_ver, pf_cap_flags1: VF version negotiation results
- num_vports, bm_hostmode: Device configuration
Per-vPort entries (under /sys/kernel/debug/mana/<slot>/vportN/):
- port_handle: Hardware vPort handle
- max_sq, max_rq: Max queues from vPort config
- indir_table_sz: Indirection table size
- steer_rx, steer_rss, steer_update_tab, steer_cqe_coalescing:
Last applied steering configuration parameters
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
---
Changes in v2:
* Add debugfs_remove_recursice for gc>mana_pci_debugfs in
mana_gd_suspend to handle multiple duplicates creation in
mana_gd_setup and mana_gd_resume path.
* Move debugfs creation for num_vports and bm_hostmode out of
if(!resuming) condition since we have to create it again even for
resume.
* Recreate mana_pci_debugfs in mana_gd_resume.
---
.../net/ethernet/microsoft/mana/gdma_main.c | 21 +++++++++++++
drivers/net/ethernet/microsoft/mana/mana_en.c | 31 +++++++++++++++++++
include/net/mana/gdma.h | 1 +
include/net/mana/mana.h | 8 +++++
4 files changed, 61 insertions(+)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index aef8612b73cb..43fb366dc183 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -152,6 +152,11 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
if (gc->max_num_queues > gc->num_msix_usable - 1)
gc->max_num_queues = gc->num_msix_usable - 1;
+ debugfs_create_u32("num_msix_usable", 0400, gc->mana_pci_debugfs,
+ &gc->num_msix_usable);
+ debugfs_create_u32("max_num_queues", 0400, gc->mana_pci_debugfs,
+ &gc->max_num_queues);
+
return 0;
}
@@ -1222,6 +1227,13 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
return err ? err : -EPROTO;
}
gc->pf_cap_flags1 = resp.pf_cap_flags1;
+ gc->gdma_protocol_ver = resp.gdma_protocol_ver;
+
+ debugfs_create_x64("gdma_protocol_ver", 0400, gc->mana_pci_debugfs,
+ &gc->gdma_protocol_ver);
+ debugfs_create_x64("pf_cap_flags1", 0400, gc->mana_pci_debugfs,
+ &gc->pf_cap_flags1);
+
if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) {
err = mana_gd_query_hwc_timeout(pdev, &hwc->hwc_timeout);
if (err) {
@@ -2128,6 +2140,9 @@ int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
mana_gd_cleanup(pdev);
+ debugfs_remove_recursive(gc->mana_pci_debugfs);
+ gc->mana_pci_debugfs = NULL;
+
return 0;
}
@@ -2140,6 +2155,12 @@ int mana_gd_resume(struct pci_dev *pdev)
struct gdma_context *gc = pci_get_drvdata(pdev);
int err;
+ if (gc->is_pf)
+ gc->mana_pci_debugfs = debugfs_create_dir("0", mana_debugfs_root);
+ else
+ gc->mana_pci_debugfs = debugfs_create_dir(pci_slot_name(pdev->slot),
+ mana_debugfs_root);
+
err = mana_gd_setup(pdev);
if (err)
return err;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ea71de39f996..1117ae16b065 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1263,6 +1263,9 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index,
apc->port_handle = resp.vport;
ether_addr_copy(apc->mac_addr, resp.mac_addr);
+ apc->vport_max_sq = *max_sq;
+ apc->vport_max_rq = *max_rq;
+
return 0;
}
@@ -1409,6 +1412,11 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
netdev_info(ndev, "Configured steering vPort %llu entries %u\n",
apc->port_handle, apc->indir_table_sz);
+
+ apc->steer_rx = rx;
+ apc->steer_rss = apc->rss_state;
+ apc->steer_update_tab = update_tab;
+ apc->steer_cqe_coalescing = req->cqe_coalescing_enable;
out:
kfree(req);
return err;
@@ -3110,6 +3118,24 @@ static int mana_init_port(struct net_device *ndev)
eth_hw_addr_set(ndev, apc->mac_addr);
sprintf(vport, "vport%d", port_idx);
apc->mana_port_debugfs = debugfs_create_dir(vport, gc->mana_pci_debugfs);
+
+ debugfs_create_u64("port_handle", 0400, apc->mana_port_debugfs,
+ &apc->port_handle);
+ debugfs_create_u32("max_sq", 0400, apc->mana_port_debugfs,
+ &apc->vport_max_sq);
+ debugfs_create_u32("max_rq", 0400, apc->mana_port_debugfs,
+ &apc->vport_max_rq);
+ debugfs_create_u32("indir_table_sz", 0400, apc->mana_port_debugfs,
+ &apc->indir_table_sz);
+ debugfs_create_u32("steer_rx", 0400, apc->mana_port_debugfs,
+ &apc->steer_rx);
+ debugfs_create_u32("steer_rss", 0400, apc->mana_port_debugfs,
+ &apc->steer_rss);
+ debugfs_create_u32("steer_update_tab", 0400, apc->mana_port_debugfs,
+ &apc->steer_update_tab);
+ debugfs_create_u32("steer_cqe_coalescing", 0400, apc->mana_port_debugfs,
+ &apc->steer_cqe_coalescing);
+
return 0;
reset_apc:
@@ -3598,6 +3624,11 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
ac->bm_hostmode = bm_hostmode;
+ debugfs_create_u16("num_vports", 0400, gc->mana_pci_debugfs,
+ &ac->num_ports);
+ debugfs_create_u8("bm_hostmode", 0400, gc->mana_pci_debugfs,
+ &ac->bm_hostmode);
+
if (!resuming) {
ac->num_ports = num_ports;
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index ec17004b10c0..917945f0e3dc 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -440,6 +440,7 @@ struct gdma_context {
struct gdma_dev mana_ib;
u64 pf_cap_flags1;
+ u64 gdma_protocol_ver;
struct workqueue_struct *service_wq;
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index a078af283bdd..83f6de67c0cc 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -563,6 +563,14 @@ struct mana_port_context {
/* Debugfs */
struct dentry *mana_port_debugfs;
+
+ /* Cached vport/steering config for debugfs */
+ u32 vport_max_sq;
+ u32 vport_max_rq;
+ u32 steer_rx;
+ u32 steer_rss;
+ u32 steer_update_tab;
+ u32 steer_cqe_coalescing;
};
netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev);
--
2.34.1
^ permalink raw reply related
* Re: [net-next] net: mana: Expose hardware diagnostic info via debugfs
From: Erni Sri Satya Vennela @ 2026-03-09 11:49 UTC (permalink / raw)
To: Jakub Kicinski
Cc: pabeni, linux-kernel, yury.norov, kys, decui, kees, longli,
dipayanroy, davem, netdev, linux-rdma, kotaranov, andrew+netdev,
linux-hyperv, edumazet, haiyangz, ssengar, shradhagupta, horms,
shirazsaleem, wei.liu
In-Reply-To: <20260307032228.1379456-1-kuba@kernel.org>
On Fri, Mar 06, 2026 at 07:22:28PM -0800, Jakub Kicinski wrote:
> This is an AI-generated review of your patch. The human sending this
> email has considered the AI review valid, or at least plausible.
>
> For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
> ---
> net: mana: Expose hardware diagnostic info via debugfs
>
> This commit adds debugfs entries to expose hardware configuration and
> diagnostic information for the MANA driver. It creates device-level and
> port-level debugfs entries to aid in debugging initialization and runtime
> operations.
> Do these debugfs entries get recreated on every suspend/resume cycle?
No. Thankyou for pointing out Jakub.
I'll make this change in next version.
>
> Both mana_gd_query_max_resources() and mana_gd_verify_vf_version() are
> called from mana_gd_setup() during device initialization. On suspend,
> mana_gd_suspend() calls mana_gd_cleanup() which doesn't remove these
> debugfs entries. When mana_gd_resume() calls mana_gd_setup() again, it
> attempts to create the same debugfs entries a second time.
>
> This means debugfs_start_creating() in fs/debugfs/inode.c will print an
> error for each duplicate file:
>
> "'num_msix_usable' already exists in 'mana/<slot>/'"
> "'max_num_queues' already exists in 'mana/<slot>/'"
> "'gdma_protocol_ver' already exists in 'mana/<slot>/'"
> "'pf_cap_flags1' already exists in 'mana/<slot>/'"
>
> This produces 4 error messages in dmesg on every suspend/resume cycle,
> contradicting the commit message's goal of operating "without adding
> noise to dmesg."
>
> Should these device-level entries be removed during suspend (in
> mana_gd_cleanup or mana_gd_suspend), or should their creation be moved
> to mana_gd_probe where they're only created once?
Right. I will remove the entries during suspend and re-create them in
resume.
>
> [ ... ]
> --
> pw-bot: cr
^ permalink raw reply
* RE: [PATCH net-next,V3, 2/3] net: mana: Add support for RX CQE Coalescing
From: Haiyang Zhang @ 2026-03-08 16:30 UTC (permalink / raw)
To: Haiyang Zhang, linux-hyperv@vger.kernel.org,
netdev@vger.kernel.org, KY Srinivasan, Wei Liu, Dexuan Cui,
Long Li, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Konstantin Taranov, Simon Horman,
Erni Sri Satya Vennela, Shradha Gupta, Dipayaan Roy,
Shiraz Saleem, Kees Cook, Subbaraya Sundeep, Breno Leitao,
Aditya Garg, linux-kernel@vger.kernel.org,
linux-rdma@vger.kernel.org
Cc: Paul Rosswurm
In-Reply-To: <20260306231936.549499-3-haiyangz@linux.microsoft.com>
> -----Original Message-----
> From: Haiyang Zhang <haiyangz@linux.microsoft.com>
> Sent: Friday, March 6, 2026 6:19 PM
> To: linux-hyperv@vger.kernel.org; netdev@vger.kernel.org; KY Srinivasan
> <kys@microsoft.com>; Haiyang Zhang <haiyangz@microsoft.com>; Wei Liu
> <wei.liu@kernel.org>; Dexuan Cui <DECUI@microsoft.com>; Long Li
> <longli@microsoft.com>; Andrew Lunn <andrew+netdev@lunn.ch>; David S.
> Miller <davem@davemloft.net>; Eric Dumazet <edumazet@google.com>; Jakub
> Kicinski <kuba@kernel.org>; Paolo Abeni <pabeni@redhat.com>; Konstantin
> Taranov <kotaranov@microsoft.com>; Simon Horman <horms@kernel.org>; Erni
> Sri Satya Vennela <ernis@linux.microsoft.com>; Shradha Gupta
> <shradhagupta@linux.microsoft.com>; Dipayaan Roy
> <dipayanroy@linux.microsoft.com>; Shiraz Saleem
> <shirazsaleem@microsoft.com>; Kees Cook <kees@kernel.org>; Subbaraya
> Sundeep <sbhatta@marvell.com>; Breno Leitao <leitao@debian.org>; Aditya
> Garg <gargaditya@linux.microsoft.com>; linux-kernel@vger.kernel.org;
> linux-rdma@vger.kernel.org
> Cc: Paul Rosswurm <paulros@microsoft.com>
> Subject: [PATCH net-next,V3, 2/3] net: mana: Add support for RX CQE
> Coalescing
>
> From: Haiyang Zhang <haiyangz@microsoft.com>
> @@ -2112,13 +2122,16 @@ static void mana_process_rx_cqe(struct mana_rxq
> *rxq, struct mana_cq *cq,
> ++ndev->stats.rx_dropped;
> rxbuf_oob = &rxq->rx_oobs[rxq->buf_index];
> netdev_warn_once(ndev, "Dropped a truncated packet\n");
> - goto drop;
>
> - case CQE_RX_COALESCED_4:
> - netdev_err(ndev, "RX coalescing is unsupported\n");
> - apc->eth_stats.rx_coalesced_err++;
> + mana_move_wq_tail(rxq->gdma_rq,
> + rxbuf_oob->wqe_inf.wqe_size_in_bu);
> + mana_post_pkt_rxq(rxq);
> return;
>
> + case CQE_RX_COALESCED_4:
> + coalesced = true;
> + break;
> +
> case CQE_RX_OBJECT_FENCE:
> complete(&rxq->fence_event);
> return;
> @@ -2130,30 +2143,36 @@ static void mana_process_rx_cqe(struct mana_rxq
> *rxq, struct mana_cq *cq,
> return;
> }
>
> - pktlen = oob->ppi[0].pkt_len;
> + for (i = 0; i < MANA_RXCOMP_OOB_NUM_PPI; i++) {
> + pktlen = oob->ppi[i].pkt_len;
> + if (pktlen == 0) {
> + if (i == 0)
> + netdev_err_once(
> + ndev,
> + "RX pkt len=0, rq=%u, cq=%u,
> rxobj=0x%llx\n",
> + rxq->gdma_id, cq->gdma_id, rxq->rxobj);
> + break;
> + }
>
> - if (pktlen == 0) {
> - /* data packets should never have packetlength of zero */
> - netdev_err(ndev, "RX pkt len=0, rq=%u, cq=%u, rxobj=0x%llx\n",
> - rxq->gdma_id, cq->gdma_id, rxq->rxobj);
> - return;
> - }
> + curr = rxq->buf_index;
> + rxbuf_oob = &rxq->rx_oobs[curr];
> + WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
>
> - curr = rxq->buf_index;
> - rxbuf_oob = &rxq->rx_oobs[curr];
> - WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
> + mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
>
> - mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
> + /* Unsuccessful refill will have old_buf == NULL.
> + * In this case, mana_rx_skb() will drop the packet.
> + */
> + mana_rx_skb(old_buf, old_fp, oob, rxq, i);
>
> - /* Unsuccessful refill will have old_buf == NULL.
> - * In this case, mana_rx_skb() will drop the packet.
> - */
> - mana_rx_skb(old_buf, old_fp, oob, rxq);
> + mana_move_wq_tail(rxq->gdma_rq,
> + rxbuf_oob->wqe_inf.wqe_size_in_bu);
I will fix this pointed out by AI review:
> The comment says "Unsuccessful refill will have old_buf == NULL" but this is
> only true for the first iteration.
> Should old_buf be set to NULL at the top of the loop, before calling
> mana_refill_rx_oob()?
^ permalink raw reply
* Re: [PATCH rdma-next 0/8] RDMA/mana_ib: Handle service reset for RDMA resources
From: Leon Romanovsky @ 2026-03-07 17:38 UTC (permalink / raw)
To: Long Li
Cc: Konstantin Taranov, Jakub Kicinski, David S . Miller, Paolo Abeni,
Eric Dumazet, Andrew Lunn, Jason Gunthorpe, Haiyang Zhang,
K . Y . Srinivasan, Wei Liu, Dexuan Cui, Simon Horman, netdev,
linux-rdma, linux-hyperv, linux-kernel
In-Reply-To: <20260307014723.556523-1-longli@microsoft.com>
On Fri, Mar 06, 2026 at 05:47:14PM -0800, Long Li wrote:
> When the MANA hardware undergoes a service reset, the ETH auxiliary device
> (mana.eth) used by DPDK persists across the reset cycle — it is not removed
> and re-added like RC/UD/GSI QPs. This means userspace RDMA consumers such
> as DPDK have no way of knowing that firmware handles for their PD, CQ, WQ,
> QP and MR resources have become stale.
NAK to any of this.
In case of hardware reset, mana_ib AUX device needs to be destroyed and
recreated later.
The same is applicable for mana.eth as well.
Thanks
^ permalink raw reply
* Re: [net-next] net: mana: Expose hardware diagnostic info via debugfs
From: Jakub Kicinski @ 2026-03-07 3:22 UTC (permalink / raw)
To: ernis
Cc: Jakub Kicinski, pabeni, linux-kernel, yury.norov, kys, decui,
kees, longli, dipayanroy, davem, netdev, linux-rdma, kotaranov,
andrew+netdev, linux-hyperv, edumazet, haiyangz, ssengar,
shradhagupta, horms, shirazsaleem, wei.liu
In-Reply-To: <20260305205252.470089-1-ernis@linux.microsoft.com>
This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
---
net: mana: Expose hardware diagnostic info via debugfs
This commit adds debugfs entries to expose hardware configuration and
diagnostic information for the MANA driver. It creates device-level and
port-level debugfs entries to aid in debugging initialization and runtime
operations.
> diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> index aef8612b73cb..fb513d7802cb 100644
> --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> @@ -152,6 +152,11 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
> if (gc->max_num_queues > gc->num_msix_usable - 1)
> gc->max_num_queues = gc->num_msix_usable - 1;
>
> + debugfs_create_u32("num_msix_usable", 0400, gc->mana_pci_debugfs,
> + &gc->num_msix_usable);
> + debugfs_create_u32("max_num_queues", 0400, gc->mana_pci_debugfs,
> + &gc->max_num_queues);
> +
> return 0;
> }
>
> @@ -1222,6 +1227,13 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
> return err ? err : -EPROTO;
> }
> gc->pf_cap_flags1 = resp.pf_cap_flags1;
> + gc->gdma_protocol_ver = resp.gdma_protocol_ver;
> +
> + debugfs_create_x64("gdma_protocol_ver", 0400, gc->mana_pci_debugfs,
> + &gc->gdma_protocol_ver);
> + debugfs_create_x64("pf_cap_flags1", 0400, gc->mana_pci_debugfs,
> + &gc->pf_cap_flags1);
> +
Do these debugfs entries get recreated on every suspend/resume cycle?
Both mana_gd_query_max_resources() and mana_gd_verify_vf_version() are
called from mana_gd_setup() during device initialization. On suspend,
mana_gd_suspend() calls mana_gd_cleanup() which doesn't remove these
debugfs entries. When mana_gd_resume() calls mana_gd_setup() again, it
attempts to create the same debugfs entries a second time.
This means debugfs_start_creating() in fs/debugfs/inode.c will print an
error for each duplicate file:
"'num_msix_usable' already exists in 'mana/<slot>/'"
"'max_num_queues' already exists in 'mana/<slot>/'"
"'gdma_protocol_ver' already exists in 'mana/<slot>/'"
"'pf_cap_flags1' already exists in 'mana/<slot>/'"
This produces 4 error messages in dmesg on every suspend/resume cycle,
contradicting the commit message's goal of operating "without adding
noise to dmesg."
Should these device-level entries be removed during suspend (in
mana_gd_cleanup or mana_gd_suspend), or should their creation be moved
to mana_gd_probe where they're only created once?
[ ... ]
--
pw-bot: cr
^ permalink raw reply
* [PATCH rdma-next 8/8] RDMA/mana_ib: Skip firmware commands for invalidated handles
From: Long Li @ 2026-03-07 1:47 UTC (permalink / raw)
To: Long Li, Konstantin Taranov, Jakub Kicinski, David S . Miller,
Paolo Abeni, Eric Dumazet, Andrew Lunn, Jason Gunthorpe,
Leon Romanovsky, Haiyang Zhang, K . Y . Srinivasan, Wei Liu,
Dexuan Cui
Cc: Simon Horman, netdev, linux-rdma, linux-hyperv, linux-kernel
In-Reply-To: <20260307014723.556523-1-longli@microsoft.com>
After a service reset, firmware handles for PD, CQ, WQ, QP, and MR
are set to INVALID_MANA_HANDLE by the reset notification path.
Check for INVALID_MANA_HANDLE in each destroy callback before issuing
firmware destroy commands. When a handle is invalid, skip the firmware
call and proceed directly to kernel resource cleanup (umem, queues,
memory). This avoids sending stale handles to firmware after reset.
Affected callbacks:
- mana_ib_dealloc_pd: skip mana_ib_gd_destroy_pd
- mana_ib_destroy_cq: skip mana_ib_gd_destroy_cq and queue destroy
- mana_ib_destroy_wq: skip mana_ib_destroy_queue
- mana_ib_destroy_qp_rss: skip mana_destroy_wq_obj per WQ
- mana_ib_destroy_qp_raw: skip mana_destroy_wq_obj
- mana_ib_dereg_mr: skip mana_ib_gd_destroy_mr
Signed-off-by: Long Li <longli@microsoft.com>
---
drivers/infiniband/hw/mana/cq.c | 10 ++++++----
drivers/infiniband/hw/mana/main.c | 12 +++++++++---
drivers/infiniband/hw/mana/mr.c | 8 +++++---
drivers/infiniband/hw/mana/qp.c | 9 ++++++---
4 files changed, 26 insertions(+), 13 deletions(-)
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index b054684b8de7..315301bccb97 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -143,10 +143,12 @@ int mana_ib_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
mana_ib_remove_cq_cb(mdev, cq);
- /* Ignore return code as there is not much we can do about it.
- * The error message is printed inside.
- */
- mana_ib_gd_destroy_cq(mdev, cq);
+ if (cq->cq_handle != INVALID_MANA_HANDLE) {
+ /* Ignore return code as there is not much we can do about it.
+ * The error message is printed inside.
+ */
+ mana_ib_gd_destroy_cq(mdev, cq);
+ }
mana_ib_destroy_queue(mdev, &cq->queue);
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 61ce30aa9cb2..d60205184dba 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -147,6 +147,9 @@ int mana_ib_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
mutex_unlock(&mana_ucontext->lock);
}
+ if (pd->pd_handle == INVALID_MANA_HANDLE)
+ return 0;
+
mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_PD, sizeof(req),
sizeof(resp));
@@ -280,9 +283,12 @@ void mana_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
list_del_init(&mana_ucontext->dev_list);
mutex_unlock(&mdev->ucontext_lock);
- ret = mana_gd_destroy_doorbell_page(gc, mana_ucontext->doorbell);
- if (ret)
- ibdev_dbg(ibdev, "Failed to destroy doorbell page %d\n", ret);
+ if (mana_ucontext->doorbell != INVALID_DOORBELL) {
+ ret = mana_gd_destroy_doorbell_page(gc, mana_ucontext->doorbell);
+ if (ret)
+ ibdev_dbg(ibdev, "Failed to destroy doorbell page %d\n",
+ ret);
+ }
}
int mana_ib_create_kernel_queue(struct mana_ib_dev *mdev, u32 size, enum gdma_queue_type type,
diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c
index 7189ccd41576..75bc2a9c366a 100644
--- a/drivers/infiniband/hw/mana/mr.c
+++ b/drivers/infiniband/hw/mana/mr.c
@@ -336,9 +336,11 @@ int mana_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
mutex_unlock(&mana_ucontext->lock);
}
- err = mana_ib_gd_destroy_mr(dev, mr->mr_handle);
- if (err)
- return err;
+ if (mr->mr_handle != INVALID_MANA_HANDLE) {
+ err = mana_ib_gd_destroy_mr(dev, mr->mr_handle);
+ if (err)
+ return err;
+ }
if (mr->umem)
ib_umem_release(mr->umem);
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index d590aca9b93a..76d59addb645 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -846,9 +846,11 @@ static int mana_ib_destroy_qp_rss(struct mana_ib_qp *qp,
for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
ibwq = ind_tbl->ind_tbl[i];
wq = container_of(ibwq, struct mana_ib_wq, ibwq);
- ibdev_dbg(&mdev->ib_dev, "destroying wq->rx_object %llu\n",
+ ibdev_dbg(&mdev->ib_dev,
+ "destroying wq->rx_object %llu\n",
wq->rx_object);
- mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object);
+ if (wq->rx_object != INVALID_MANA_HANDLE)
+ mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object);
}
return 0;
@@ -867,7 +869,8 @@ static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata *udata)
mpc = netdev_priv(ndev);
pd = container_of(ibpd, struct mana_ib_pd, ibpd);
- mana_destroy_wq_obj(mpc, GDMA_SQ, qp->qp_handle);
+ if (qp->qp_handle != INVALID_MANA_HANDLE)
+ mana_destroy_wq_obj(mpc, GDMA_SQ, qp->qp_handle);
mana_ib_destroy_queue(mdev, &qp->raw_sq);
--
2.43.0
^ permalink raw reply related
* [PATCH rdma-next 7/8] RDMA/mana_ib: Notify service reset events to RDMA devices
From: Long Li @ 2026-03-07 1:47 UTC (permalink / raw)
To: Long Li, Konstantin Taranov, Jakub Kicinski, David S . Miller,
Paolo Abeni, Eric Dumazet, Andrew Lunn, Jason Gunthorpe,
Leon Romanovsky, Haiyang Zhang, K . Y . Srinivasan, Wei Liu,
Dexuan Cui
Cc: Simon Horman, netdev, linux-rdma, linux-hyperv, linux-kernel
In-Reply-To: <20260307014723.556523-1-longli@microsoft.com>
Register reset_notify and resume_notify callbacks so the RDMA driver
is informed when the MANA service undergoes a reset cycle.
On reset notification:
- Acquire reset_rwsem write lock to serialize with resource creation
- Walk every tracked ucontext and invalidate firmware handles for
all PD, CQ, WQ, QP, and MR resources (set to INVALID_MANA_HANDLE)
- Dispatch IB_EVENT_PORT_ERR to each affected ucontext so userspace
(e.g. DPDK) learns about the reset
On resume notification:
- Release reset_rwsem write lock, unblocking new resource creation
Resource creation paths (alloc_pd, create_cq, create_wq, create_qp for
RAW_PACKET, reg_user_mr) acquire reset_rwsem read lock to ensure handles
are not invalidated while being set up.
Signed-off-by: Long Li <longli@microsoft.com>
---
drivers/infiniband/hw/mana/cq.c | 15 ++-
drivers/infiniband/hw/mana/device.c | 103 ++++++++++++++++++
drivers/infiniband/hw/mana/main.c | 9 ++
drivers/infiniband/hw/mana/mana_ib.h | 2 +
drivers/infiniband/hw/mana/mr.c | 4 +
drivers/infiniband/hw/mana/qp.c | 5 +
drivers/infiniband/hw/mana/wq.c | 4 +
drivers/net/ethernet/microsoft/mana/mana_en.c | 14 ++-
include/net/mana/gdma.h | 6 +
9 files changed, 155 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index 89cf60987ff5..b054684b8de7 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -41,13 +41,17 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
return -EINVAL;
}
+ }
+
+ down_read(&mdev->reset_rwsem);
+ if (udata) {
cq->cqe = attr->cqe;
err = mana_ib_create_queue(mdev, ucmd.buf_addr, cq->cqe * COMP_ENTRY_SIZE,
&cq->queue);
if (err) {
ibdev_dbg(ibdev, "Failed to create queue for create cq, %d\n", err);
- return err;
+ goto err_unlock;
}
mana_ucontext = rdma_udata_to_drv_context(udata, struct mana_ib_ucontext,
@@ -56,14 +60,15 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
} else {
if (attr->cqe > U32_MAX / COMP_ENTRY_SIZE / 2 + 1) {
ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
- return -EINVAL;
+ err = -EINVAL;
+ goto err_unlock;
}
buf_size = MANA_PAGE_ALIGN(roundup_pow_of_two(attr->cqe * COMP_ENTRY_SIZE));
cq->cqe = buf_size / COMP_ENTRY_SIZE;
err = mana_ib_create_kernel_queue(mdev, buf_size, GDMA_CQ, &cq->queue);
if (err) {
ibdev_dbg(ibdev, "Failed to create kernel queue for create cq, %d\n", err);
- return err;
+ goto err_unlock;
}
doorbell = mdev->gdma_dev->doorbell;
}
@@ -105,6 +110,7 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
mutex_unlock(&mana_ucontext->lock);
}
+ up_read(&mdev->reset_rwsem);
return 0;
err_remove_cq_cb:
@@ -113,7 +119,8 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
mana_ib_gd_destroy_cq(mdev, cq);
err_destroy_queue:
mana_ib_destroy_queue(mdev, &cq->queue);
-
+err_unlock:
+ up_read(&mdev->reset_rwsem);
return err;
}
diff --git a/drivers/infiniband/hw/mana/device.c b/drivers/infiniband/hw/mana/device.c
index 149e8d4d5b8e..081be31563ca 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -103,6 +103,7 @@ static int mana_ib_netdev_event(struct notifier_block *this,
netdev_put(ndev, &dev->dev_tracker);
return NOTIFY_OK;
+
default:
return NOTIFY_DONE;
}
@@ -110,6 +111,93 @@ static int mana_ib_netdev_event(struct notifier_block *this,
return NOTIFY_DONE;
}
+/*
+ * Reset cleanup: invalidate firmware handles for all tracked user objects.
+ *
+ * Called during service reset BEFORE dispatching IB_EVENT_PORT_ERR to
+ * user-mode.
+ *
+ * Only invalidates FW handles — does NOT free kernel resources (umem, queues)
+ * or remove objects from lists. The IB core's destroy callbacks handle full
+ * resource teardown when user-space closes the uverbs FD or ib_unregister_device
+ * is called. The destroy callbacks skip FW commands when the handle is already
+ * INVALID_MANA_HANDLE.
+ *
+ * For CQs, also removes the CQ callback to prevent stale completions.
+ */
+static void mana_ib_reset_notify(void *ctx)
+{
+ struct mana_ib_dev *mdev = ctx;
+ struct mana_ib_ucontext *uctx;
+ struct mana_ib_qp *qp;
+ struct mana_ib_wq *wq;
+ struct mana_ib_cq *cq;
+ struct mana_ib_mr *mr;
+ struct mana_ib_pd *pd;
+ struct ib_event ibev;
+ int i;
+
+ down_write(&mdev->reset_rwsem);
+
+ ibdev_dbg(&mdev->ib_dev, "reset cleanup starting\n");
+
+ mutex_lock(&mdev->ucontext_lock);
+ list_for_each_entry(uctx, &mdev->ucontext_list, dev_list) {
+ mutex_lock(&uctx->lock);
+
+ list_for_each_entry(qp, &uctx->qp_list, ucontext_list)
+ qp->qp_handle = INVALID_MANA_HANDLE;
+
+ list_for_each_entry(wq, &uctx->wq_list, ucontext_list)
+ wq->rx_object = INVALID_MANA_HANDLE;
+
+ list_for_each_entry(cq, &uctx->cq_list, ucontext_list) {
+ mana_ib_remove_cq_cb(mdev, cq);
+ cq->cq_handle = INVALID_MANA_HANDLE;
+ }
+
+ list_for_each_entry(mr, &uctx->mr_list, ucontext_list)
+ mr->mr_handle = INVALID_MANA_HANDLE;
+
+ list_for_each_entry(pd, &uctx->pd_list, ucontext_list)
+ pd->pd_handle = INVALID_MANA_HANDLE;
+
+ uctx->doorbell = INVALID_DOORBELL;
+
+ mutex_unlock(&uctx->lock);
+ }
+ mutex_unlock(&mdev->ucontext_lock);
+
+ up_write(&mdev->reset_rwsem);
+
+ /* Revoke user doorbell mappings so userspace cannot ring
+ * stale doorbells after firmware handles are invalidated.
+ */
+ rdma_user_mmap_disassociate(&mdev->ib_dev);
+
+ /* Notify userspace (e.g. DPDK) that the port is down */
+ for (i = 0; i < mdev->ib_dev.phys_port_cnt; i++) {
+ ibev.device = &mdev->ib_dev;
+ ibev.element.port_num = i + 1;
+ ibev.event = IB_EVENT_PORT_ERR;
+ ib_dispatch_event(&ibev);
+ }
+}
+
+static void mana_ib_resume_notify(void *ctx)
+{
+ struct mana_ib_dev *dev = ctx;
+ struct ib_event ibev;
+ int i;
+
+ for (i = 0; i < dev->ib_dev.phys_port_cnt; i++) {
+ ibev.device = &dev->ib_dev;
+ ibev.element.port_num = i + 1;
+ ibev.event = IB_EVENT_PORT_ACTIVE;
+ ib_dispatch_event(&ibev);
+ }
+}
+
static int mana_ib_probe(struct auxiliary_device *adev,
const struct auxiliary_device_id *id)
{
@@ -134,6 +222,7 @@ static int mana_ib_probe(struct auxiliary_device *adev,
xa_init_flags(&dev->qp_table_wq, XA_FLAGS_LOCK_IRQ);
mutex_init(&dev->ucontext_lock);
INIT_LIST_HEAD(&dev->ucontext_list);
+ init_rwsem(&dev->reset_rwsem);
if (mana_ib_is_rnic(dev)) {
dev->ib_dev.phys_port_cnt = 1;
@@ -216,6 +305,15 @@ static int mana_ib_probe(struct auxiliary_device *adev,
dev_set_drvdata(&adev->dev, dev);
+ /* ETH device persists across reset — use callback for cleanup.
+ * RNIC device is removed/re-added, so its cleanup happens in remove.
+ */
+ if (!mana_ib_is_rnic(dev)) {
+ mdev->reset_notify = mana_ib_reset_notify;
+ mdev->resume_notify = mana_ib_resume_notify;
+ mdev->reset_notify_ctx = dev;
+ }
+
return 0;
deallocate_pool:
@@ -242,6 +340,11 @@ static void mana_ib_remove(struct auxiliary_device *adev)
if (mana_ib_is_rnic(dev))
mana_drain_gsi_sqs(dev);
+ if (!mana_ib_is_rnic(dev)) {
+ dev->gdma_dev->reset_notify = NULL;
+ dev->gdma_dev->resume_notify = NULL;
+ dev->gdma_dev->reset_notify_ctx = NULL;
+ }
ib_unregister_device(&dev->ib_dev);
dma_pool_destroy(dev->av_pool);
if (mana_ib_is_rnic(dev)) {
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index f739e6da5435..61ce30aa9cb2 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -81,6 +81,8 @@ int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
gc = mdev_to_gc(dev);
+ down_read(&dev->reset_rwsem);
+
mana_gd_init_req_hdr(&req.hdr, GDMA_CREATE_PD, sizeof(req),
sizeof(resp));
@@ -98,6 +100,7 @@ int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
if (!err)
err = -EPROTO;
+ up_read(&dev->reset_rwsem);
return err;
}
@@ -118,6 +121,7 @@ int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
mutex_unlock(&mana_ucontext->lock);
}
+ up_read(&dev->reset_rwsem);
return 0;
}
@@ -230,10 +234,13 @@ int mana_ib_alloc_ucontext(struct ib_ucontext *ibcontext,
mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
gc = mdev_to_gc(mdev);
+ down_read(&mdev->reset_rwsem);
+
/* Allocate a doorbell page index */
ret = mana_gd_allocate_doorbell_page(gc, &doorbell_page);
if (ret) {
ibdev_dbg(ibdev, "Failed to allocate doorbell page %d\n", ret);
+ up_read(&mdev->reset_rwsem);
return ret;
}
@@ -252,6 +259,8 @@ int mana_ib_alloc_ucontext(struct ib_ucontext *ibcontext,
list_add_tail(&ucontext->dev_list, &mdev->ucontext_list);
mutex_unlock(&mdev->ucontext_lock);
+ up_read(&mdev->reset_rwsem);
+
return 0;
}
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index ce5c6c030fb2..29201cf3274c 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -86,6 +86,8 @@ struct mana_ib_dev {
/* Protects ucontext_list */
struct mutex ucontext_lock;
struct list_head ucontext_list;
+ /* Serializes resource create callbacks vs reset cleanup */
+ struct rw_semaphore reset_rwsem;
};
struct mana_ib_wq {
diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c
index 559bb4f7c31d..7189ccd41576 100644
--- a/drivers/infiniband/hw/mana/mr.c
+++ b/drivers/infiniband/hw/mana/mr.c
@@ -141,6 +141,8 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length,
if (!mr)
return ERR_PTR(-ENOMEM);
+ down_read(&dev->reset_rwsem);
+
mr->umem = ib_umem_get(ibdev, start, length, access_flags);
if (IS_ERR(mr->umem)) {
err = PTR_ERR(mr->umem);
@@ -195,6 +197,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length,
mutex_unlock(&mana_ucontext->lock);
}
+ up_read(&dev->reset_rwsem);
return &mr->ibmr;
err_dma_region:
@@ -204,6 +207,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length,
ib_umem_release(mr->umem);
err_free:
+ up_read(&dev->reset_rwsem);
kfree(mr);
return ERR_PTR(err);
}
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index 315bc54d8ae6..d590aca9b93a 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -701,12 +701,16 @@ int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
struct ib_udata *udata)
{
struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+ struct mana_ib_dev *mdev =
+ container_of(ibqp->device, struct mana_ib_dev, ib_dev);
int err;
INIT_LIST_HEAD(&qp->ucontext_list);
switch (attr->qp_type) {
case IB_QPT_RAW_PACKET:
+ down_read(&mdev->reset_rwsem);
+
/* When rwq_ind_tbl is used, it's for creating WQs for RSS */
if (attr->rwq_ind_tbl)
err = mana_ib_create_qp_rss(ibqp, ibqp->pd, attr,
@@ -724,6 +728,7 @@ int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
mutex_unlock(&mana_ucontext->lock);
}
+ up_read(&mdev->reset_rwsem);
return err;
case IB_QPT_RC:
return mana_ib_create_rc_qp(ibqp, ibqp->pd, attr, udata);
diff --git a/drivers/infiniband/hw/mana/wq.c b/drivers/infiniband/hw/mana/wq.c
index 1af9869933aa..67b757cf30f9 100644
--- a/drivers/infiniband/hw/mana/wq.c
+++ b/drivers/infiniband/hw/mana/wq.c
@@ -31,6 +31,8 @@ struct ib_wq *mana_ib_create_wq(struct ib_pd *pd,
ibdev_dbg(&mdev->ib_dev, "ucmd wq_buf_addr 0x%llx\n", ucmd.wq_buf_addr);
+ down_read(&mdev->reset_rwsem);
+
err = mana_ib_create_queue(mdev, ucmd.wq_buf_addr, ucmd.wq_buf_size, &wq->queue);
if (err) {
ibdev_dbg(&mdev->ib_dev,
@@ -52,9 +54,11 @@ struct ib_wq *mana_ib_create_wq(struct ib_pd *pd,
mutex_unlock(&mana_ucontext->lock);
}
+ up_read(&mdev->reset_rwsem);
return &wq->ibwq;
err_free_wq:
+ up_read(&mdev->reset_rwsem);
kfree(wq);
return ERR_PTR(err);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ea71de39f996..3493b36426f7 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -3659,15 +3659,19 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
}
}
- err = add_adev(gd, "eth");
+ if (!resuming)
+ err = add_adev(gd, "eth");
INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler);
schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD);
-
out:
if (err) {
mana_remove(gd, false);
} else {
+ /* Notify IB layer that ports are back up after reset */
+ if (resuming && gd->resume_notify)
+ gd->resume_notify(gd->reset_notify_ctx);
+
dev_dbg(dev, "gd=%p, id=%u, num_ports=%d, type=%u, instance=%u\n",
gd, gd->dev_id.as_uint32, ac->num_ports,
gd->dev_id.type, gd->dev_id.instance);
@@ -3691,9 +3695,13 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
cancel_delayed_work_sync(&ac->gf_stats_work);
/* adev currently doesn't support suspending, always remove it */
- if (gd->adev)
+ if (gd->adev && !suspending)
remove_adev(gd);
+ /* Notify IB layer before tearing down net devices during reset */
+ if (suspending && gd->reset_notify)
+ gd->reset_notify(gd->reset_notify_ctx);
+
for (i = 0; i < ac->num_ports; i++) {
ndev = ac->ports[i];
if (!ndev) {
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index ec17004b10c0..9187c5b4d0d1 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -249,6 +249,12 @@ struct gdma_dev {
struct auxiliary_device *adev;
bool is_suspended;
bool rdma_teardown;
+
+ /* Called by mana_remove() during reset to notify IB layer */
+ void (*reset_notify)(void *ctx);
+ /* Called by mana_probe() during resume to notify IB layer */
+ void (*resume_notify)(void *ctx);
+ void *reset_notify_ctx;
};
/* MANA_PAGE_SIZE is the DMA unit */
--
2.43.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox