Netdev List
 help / color / mirror / Atom feed
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
To: netdev@vger.kernel.org, Jakub Kicinski <kuba@kernel.org>
Cc: Tony Nguyen <anthony.l.nguyen@intel.com>,
	Aleksandr Loktionov <aleksandr.loktionov@intel.com>,
	Michal Schmidt <mschmidt@redhat.com>,
	intel-wired-lan@lists.osuosl.org, edumazet@google.com,
	horms@kernel.org, pabeni@redhat.com, davem@davemloft.net,
	Przemek Kitszel <przemyslaw.kitszel@intel.com>
Subject: [PATCH net v3 4/5] ice: rebuild ring stats arrays instead of reallocating them in place
Date: Fri, 11 Sep 2026 13:26:19 +0200	[thread overview]
Message-ID: <20260911113848.44086-5-przemyslaw.kitszel@intel.com> (raw)
In-Reply-To: <20260911113848.44086-1-przemyslaw.kitszel@intel.com>

ice_vsi_realloc_stat_arrays() resized the ring stats arrays in place
with krealloc_array(), sizing them from vsi->req_txq/req_rxq. That is
not what ice_vsi_set_num_qs() computes later in ice_vsi_cfg_def(), so
after a rebuild the arrays could end up shorter than vsi->alloc_txq /
vsi->alloc_rxq, and ice_vsi_alloc_ring_stats() then walked past their
end. Requesting fewer queues than the PF pool can hand out was enough
to trigger it.

Replace it with ice_vsi_resize_stat_arrays(), which allocates a fresh
struct ice_vsi_stats instead, sized with ice_vsi_get_num_qs() and the
queues ice_vsi_decfg() is about to return to the PF pool, which is
exactly what ice_vsi_set_num_qs() will compute once they are back
there. Copy the surviving entry pointers over and install the new
structure, all before ice_vsi_decfg() runs. The entries that did not
fit are freed together with the old container, via
__ice_vsi_free_stats() with @free_entries set to false.

Doing the allocation up front also means the failure path is a plain
unlock and return, with the VSI still fully configured, rather than a
half-torn-down VSI to unwind.

While at it, skip the stats handling for ICE_VSI_CHNL, which has no
entry in pf->vsi_stats[] to begin with.

Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
---
this is an actual fix/improvement, that removes some of the tech debt,
but there is no Fixes tag, as this was not directly caused by an user
observable bug, rather as a pre-work / ai-review resolution for the next
commit
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 118 +++++++++++++----------
 1 file changed, 69 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 998b9eb6e9fe..0cd54af40c37 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2953,6 +2953,51 @@ ice_vsi_rebuild_get_coalesce(struct ice_vsi *vsi,
 	return vsi->num_q_vectors;
 }
 
+static void ice_vsi_free_unused_stat_arrays(struct ice_vsi_stats *vsi_stat,
+					    struct ice_vsi_stats *new_vsi_stat)
+{
+	int new_txq = new_vsi_stat->tx_ring_stats_len;
+	int new_rxq = new_vsi_stat->rx_ring_stats_len;
+	int prev_txq = vsi_stat->tx_ring_stats_len;
+	int prev_rxq = vsi_stat->rx_ring_stats_len;
+
+	for (int i = new_txq; i < prev_txq; i++) {
+		if (vsi_stat->tx_ring_stats[i]) {
+			kfree_rcu(vsi_stat->tx_ring_stats[i], rcu);
+			WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL);
+		}
+	}
+	for (int i = new_rxq; i < prev_rxq; i++) {
+		if (vsi_stat->rx_ring_stats[i]) {
+			kfree_rcu(vsi_stat->rx_ring_stats[i], rcu);
+			WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL);
+		}
+	}
+}
+
+static void ice_vsi_set_stat_arrays(struct ice_vsi *vsi,
+				    struct ice_vsi_stats *new_vsi_stat)
+{
+	u16 new_txq, new_rxq, prev_txq, prev_rxq;
+	struct ice_vsi_stats *vsi_stat;
+	struct ice_pf *pf = vsi->back;
+
+	new_txq = new_vsi_stat->tx_ring_stats_len;
+	new_rxq = new_vsi_stat->rx_ring_stats_len;
+	vsi_stat = pf->vsi_stats[vsi->idx];
+	pf->vsi_stats[vsi->idx] = new_vsi_stat;
+	if (!vsi_stat)
+		return; /* don't copy if there is no source */
+
+	prev_txq = vsi_stat->tx_ring_stats_len;
+	prev_rxq = vsi_stat->rx_ring_stats_len;
+
+	memcpy(new_vsi_stat->tx_ring_stats, vsi_stat->tx_ring_stats,
+	       sizeof(*vsi_stat->tx_ring_stats) * min(prev_txq, new_txq));
+	memcpy(new_vsi_stat->rx_ring_stats, vsi_stat->rx_ring_stats,
+	       sizeof(*vsi_stat->rx_ring_stats) * min(prev_rxq, new_rxq));
+}
+
 /**
  * ice_vsi_rebuild_set_coalesce - set coalesce from earlier saved arrays
  * @vsi: VSI connected with q_vectors
@@ -3039,63 +3084,38 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi,
 }
 
 /**
- * ice_vsi_realloc_stat_arrays - Frees unused stat structures or alloc new ones
- * @vsi: VSI pointer
+ * ice_vsi_resize_stat_arrays - resize ring stats arrays for new queue count
+ * @vsi: VSI to swap the ring stats arrays of
+ *
+ * Call while @vsi still owns its queues and before ice_vsi_decfg() returns them
+ * to the PF pool, so that the new size is what ice_vsi_set_num_qs() will compute
+ * afterwards. Surviving entries are carried over, the rest is freed.
+ *
+ * Returns 0 on success and negative value on failure
  */
-static int
-ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi)
+static int ice_vsi_resize_stat_arrays(struct ice_vsi *vsi)
 {
-	u16 req_txq = vsi->req_txq ? vsi->req_txq : vsi->alloc_txq;
-	u16 req_rxq = vsi->req_rxq ? vsi->req_rxq : vsi->alloc_rxq;
-	struct ice_ring_stats **tx_ring_stats;
-	struct ice_ring_stats **rx_ring_stats;
-	struct ice_vsi_stats *vsi_stat;
+	struct ice_vsi_alloc_queues_params qs;
+	struct ice_vsi_stats *old_stat;
+	struct ice_vsi_stats *new_stat;
 	struct ice_pf *pf = vsi->back;
-	u16 prev_txq = vsi->alloc_txq;
-	u16 prev_rxq = vsi->alloc_rxq;
-	int i;
 
-	vsi_stat = pf->vsi_stats[vsi->idx];
+	if (vsi->type == ICE_VSI_CHNL)
+		return 0;
 
-	if (req_txq < prev_txq) {
-		for (i = req_txq; i < prev_txq; i++) {
-			if (vsi_stat->tx_ring_stats[i]) {
-				kfree_rcu(vsi_stat->tx_ring_stats[i], rcu);
-				WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL);
-			}
-		}
-	}
+	qs = ice_vsi_get_num_qs(vsi, vsi->alloc_txq + vsi->num_xdp_txq,
+				vsi->alloc_rxq);
 
-	tx_ring_stats = vsi_stat->tx_ring_stats;
-	vsi_stat->tx_ring_stats =
-		krealloc_array(vsi_stat->tx_ring_stats, req_txq,
-			       sizeof(*vsi_stat->tx_ring_stats),
-			       GFP_KERNEL | __GFP_ZERO);
-	if (!vsi_stat->tx_ring_stats) {
-		vsi_stat->tx_ring_stats = tx_ring_stats;
+	new_stat = ice_vsi_new_stat_arrays(qs.alloc_txq, qs.alloc_rxq);
+	if (!new_stat)
 		return -ENOMEM;
-	}
-	vsi_stat->tx_ring_stats_len = req_txq;
 
-	if (req_rxq < prev_rxq) {
-		for (i = req_rxq; i < prev_rxq; i++) {
-			if (vsi_stat->rx_ring_stats[i]) {
-				kfree_rcu(vsi_stat->rx_ring_stats[i], rcu);
-				WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL);
-			}
-		}
-	}
-
-	rx_ring_stats = vsi_stat->rx_ring_stats;
-	vsi_stat->rx_ring_stats =
-		krealloc_array(vsi_stat->rx_ring_stats, req_rxq,
-			       sizeof(*vsi_stat->rx_ring_stats),
-			       GFP_KERNEL | __GFP_ZERO);
-	if (!vsi_stat->rx_ring_stats) {
-		vsi_stat->rx_ring_stats = rx_ring_stats;
-		return -ENOMEM;
+	old_stat = pf->vsi_stats[vsi->idx];
+	ice_vsi_set_stat_arrays(vsi, new_stat);
+	if (old_stat) {
+		ice_vsi_free_unused_stat_arrays(old_stat, new_stat);
+		__ice_vsi_free_stats(old_stat, false);
 	}
-	vsi_stat->rx_ring_stats_len = req_rxq;
 
 	return 0;
 }
@@ -3127,7 +3147,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 
 	mutex_lock(&vsi->xdp_state_lock);
 
-	ret = ice_vsi_realloc_stat_arrays(vsi);
+	ret = ice_vsi_resize_stat_arrays(vsi);
 	if (ret)
 		goto unlock;
 
-- 
2.51.1


  parent reply	other threads:[~2026-09-11 11:39 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-11 11:26 [PATCH net v3 0/5] ice: fix stats array overflow via proper realloc Przemek Kitszel
2026-09-11 11:26 ` [PATCH net v3 1/5] ice: extract __ice_vsi_free_stats() Przemek Kitszel
2026-09-11 11:26 ` [PATCH net v3 2/5] ice: extract ice_vsi_new_stat_arrays() Przemek Kitszel
2026-09-11 11:26 ` [PATCH net v3 3/5] ice: extract ice_vsi_get_num_qs() Przemek Kitszel
2026-09-11 11:26 ` Przemek Kitszel [this message]
2026-09-11 11:26 ` [PATCH net v3 5/5] ice: fix stats array overflow when VF requests more queues Przemek Kitszel
2026-09-11 16:52 ` [PATCH net v3 0/5] ice: fix stats array overflow via proper realloc Jakub Kicinski
2026-09-11 16:56   ` Jakub Kicinski

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260911113848.44086-5-przemyslaw.kitszel@intel.com \
    --to=przemyslaw.kitszel@intel.com \
    --cc=aleksandr.loktionov@intel.com \
    --cc=anthony.l.nguyen@intel.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=horms@kernel.org \
    --cc=intel-wired-lan@lists.osuosl.org \
    --cc=kuba@kernel.org \
    --cc=mschmidt@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox