Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/intel/iavf/iavf_ethtool.c
  3a0b5a2929fd ("iavf: Introduce new state machines for flow director")
  95260816b489 ("iavf: use iavf_schedule_aq_request() helper")
https://lore.kernel.org/all/84e12519-04dc-bd80-bc34-8cf50d7898ce@intel.com/

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  c13e268c0768 ("bnxt_en: Fix HWTSTAMP_FILTER_ALL packet timestamp logic")
  c2f8063309da ("bnxt_en: Refactor RX VLAN acceleration logic.")
  a7445d69809f ("bnxt_en: Add support for new RX and TPA_START completion types for P7")
  1c7fd6ee2fe4 ("bnxt_en: Rename some macros for the P5 chips")
https://lore.kernel.org/all/20231211110022.27926ad9@canb.auug.org.au/

drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
  bd6781c18cb5 ("bnxt_en: Fix wrong return value check in bnxt_close_nic()")
  84793a499578 ("bnxt_en: Skip nic close/open when configuring tstamp filters")
https://lore.kernel.org/all/20231214113041.3a0c003c@canb.auug.org.au/

drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
  3d7a3f2612d7 ("net/mlx5: Nack sync reset request when HotPlug is enabled")
  cecf44ea1a1f ("net/mlx5: Allow sync reset flow when BF MGT interface device is present")
https://lore.kernel.org/all/20231211110328.76c925af@canb.auug.org.au/

No adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 16 insertions, 6 deletions

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index aa3f6815bb12..ee272c4cefcc 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -366,13 +366,25 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 	if (!masks)
 		goto fail_node_to_cpumask;
 
-	/* Stabilize the cpumasks */
-	cpus_read_lock();
 	build_node_to_cpumask(node_to_cpumask);
 
+	/*
+	 * Make a local cache of 'cpu_present_mask', so the two stages
+	 * spread can observe consistent 'cpu_present_mask' without holding
+	 * cpu hotplug lock, then we can reduce deadlock risk with cpu
+	 * hotplug code.
+	 *
+	 * Here CPU hotplug may happen when reading `cpu_present_mask`, and
+	 * we can live with the case because it only affects that hotplug
+	 * CPU is handled in the 1st or 2nd stage, and either way is correct
+	 * from API user viewpoint since 2-stage spread is sort of
+	 * optimization.
+	 */
+	cpumask_copy(npresmsk, data_race(cpu_present_mask));
+
 	/* grouping present CPUs first */
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
-				  cpu_present_mask, nmsk, masks);
+				  npresmsk, nmsk, masks);
 	if (ret < 0)
 		goto fail_build_affinity;
 	nr_present = ret;
@@ -387,15 +399,13 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 		curgrp = 0;
 	else
 		curgrp = nr_present;
-	cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
+	cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk);
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
 				  npresmsk, nmsk, masks);
 	if (ret >= 0)
 		nr_others = ret;
 
  fail_build_affinity:
-	cpus_read_unlock();
-
 	if (ret >= 0)
 		WARN_ON(nr_present + nr_others < numgrps);