diff mbox series

[net-next,V2,2/6] net/mlx5: hw counters: Use kvmalloc for bulk query buffer

Message ID 20241001103709.58127-3-tariqt@nvidia.com (mailing list archive)
State Accepted
Commit 10cd92df833c3f6c35dc5e923651146d41332538
Delegated to: Netdev Maintainers
Headers show
Series net/mlx5: hw counters refactor | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 9 this patch: 9
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 1 maintainers not CCed: linux-rdma@vger.kernel.org
netdev/build_clang success Errors and warnings before: 9 this patch: 9
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn fail Errors and warnings before: 12 this patch: 12
netdev/checkpatch warning WARNING: line length of 87 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Tariq Toukan Oct. 1, 2024, 10:37 a.m. UTC 
From: Cosmin Ratiu <cratiu@nvidia.com>

The bulk query buffer starts out small (see [1]) and as soon as the
number of counters goes past the initial threshold grows to max
size (32K entries, 512KB) with a retry scheme.

This commit switches to using kvmalloc for the buffer, which has a near
zero likelihood of failing, and thus the explicit retry scheme becomes
superfluous and is taken out. On the low chance the allocation fails, it
will still be retried every sampling_interval, when the wq task runs.

[1] commit b247f32aecad ("net/mlx5: Dynamically resize flow counters
query buffer")

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/fs_counters.c | 59 +++++++------------
 1 file changed, 22 insertions(+), 37 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 7d6174d0f260..9892895da9ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -38,7 +38,6 @@ 
 #include "fs_cmd.h"
 
 #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000)
-#define MLX5_FC_BULK_QUERY_ALLOC_PERIOD msecs_to_jiffies(180 * 1000)
 /* Max number of counters to query in bulk read is 32K */
 #define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
 #define MLX5_INIT_COUNTERS_BULK 8
@@ -263,39 +262,28 @@  static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter)
 		mlx5_fc_free(dev, counter);
 }
 
-static void mlx5_fc_stats_bulk_query_size_increase(struct mlx5_core_dev *dev)
+static void mlx5_fc_stats_bulk_query_buf_realloc(struct mlx5_core_dev *dev,
+						 int bulk_query_len)
 {
 	struct mlx5_fc_stats *fc_stats = dev->priv.fc_stats;
-	int max_bulk_len = get_max_bulk_query_len(dev);
-	unsigned long now = jiffies;
 	u32 *bulk_query_out_tmp;
-	int max_out_len;
-
-	if (fc_stats->bulk_query_alloc_failed &&
-	    time_before(now, fc_stats->next_bulk_query_alloc))
-		return;
+	int out_len;
 
-	max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len);
-	bulk_query_out_tmp = kzalloc(max_out_len, GFP_KERNEL);
+	out_len = mlx5_cmd_fc_get_bulk_query_out_len(bulk_query_len);
+	bulk_query_out_tmp = kvzalloc(out_len, GFP_KERNEL);
 	if (!bulk_query_out_tmp) {
 		mlx5_core_warn_once(dev,
-				    "Can't increase flow counters bulk query buffer size, insufficient memory, bulk_size(%d)\n",
-				    max_bulk_len);
-		fc_stats->bulk_query_alloc_failed = true;
-		fc_stats->next_bulk_query_alloc =
-			now + MLX5_FC_BULK_QUERY_ALLOC_PERIOD;
+				    "Can't increase flow counters bulk query buffer size, alloc failed, bulk_query_len(%d)\n",
+				    bulk_query_len);
 		return;
 	}
 
-	kfree(fc_stats->bulk_query_out);
+	kvfree(fc_stats->bulk_query_out);
 	fc_stats->bulk_query_out = bulk_query_out_tmp;
-	fc_stats->bulk_query_len = max_bulk_len;
-	if (fc_stats->bulk_query_alloc_failed) {
-		mlx5_core_info(dev,
-			       "Flow counters bulk query buffer size increased, bulk_size(%d)\n",
-			       max_bulk_len);
-		fc_stats->bulk_query_alloc_failed = false;
-	}
+	fc_stats->bulk_query_len = bulk_query_len;
+	mlx5_core_info(dev,
+		       "Flow counters bulk query buffer size increased, bulk_query_len(%d)\n",
+		       bulk_query_len);
 }
 
 static void mlx5_fc_stats_work(struct work_struct *work)
@@ -327,13 +315,14 @@  static void mlx5_fc_stats_work(struct work_struct *work)
 		fc_stats->num_counters--;
 	}
 
-	if (fc_stats->bulk_query_len < get_max_bulk_query_len(dev) &&
-	    fc_stats->num_counters > get_init_bulk_query_len(dev))
-		mlx5_fc_stats_bulk_query_size_increase(dev);
-
 	if (time_before(now, fc_stats->next_query) ||
 	    list_empty(&fc_stats->counters))
 		return;
+
+	if (fc_stats->bulk_query_len < get_max_bulk_query_len(dev) &&
+	    fc_stats->num_counters > get_init_bulk_query_len(dev))
+		mlx5_fc_stats_bulk_query_buf_realloc(dev, get_max_bulk_query_len(dev));
+
 	last = list_last_entry(&fc_stats->counters, struct mlx5_fc, list);
 
 	counter = list_first_entry(&fc_stats->counters, struct mlx5_fc,
@@ -453,12 +442,11 @@  EXPORT_SYMBOL(mlx5_fc_destroy);
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fc_stats *fc_stats;
-	int init_bulk_len;
-	int init_out_len;
 
 	fc_stats = kzalloc(sizeof(*fc_stats), GFP_KERNEL);
 	if (!fc_stats)
 		return -ENOMEM;
+	dev->priv.fc_stats = fc_stats;
 
 	spin_lock_init(&fc_stats->counters_idr_lock);
 	idr_init(&fc_stats->counters_idr);
@@ -466,12 +454,10 @@  int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
 	init_llist_head(&fc_stats->addlist);
 	init_llist_head(&fc_stats->dellist);
 
-	init_bulk_len = get_init_bulk_query_len(dev);
-	init_out_len = mlx5_cmd_fc_get_bulk_query_out_len(init_bulk_len);
-	fc_stats->bulk_query_out = kzalloc(init_out_len, GFP_KERNEL);
+	/* Allocate initial (small) bulk query buffer. */
+	mlx5_fc_stats_bulk_query_buf_realloc(dev, get_init_bulk_query_len(dev));
 	if (!fc_stats->bulk_query_out)
 		goto err_bulk;
-	fc_stats->bulk_query_len = init_bulk_len;
 
 	fc_stats->wq = create_singlethread_workqueue("mlx5_fc");
 	if (!fc_stats->wq)
@@ -481,12 +467,11 @@  int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
 	INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work);
 
 	mlx5_fc_pool_init(&fc_stats->fc_pool, dev);
-	dev->priv.fc_stats = fc_stats;
 
 	return 0;
 
 err_wq_create:
-	kfree(fc_stats->bulk_query_out);
+	kvfree(fc_stats->bulk_query_out);
 err_bulk:
 	kfree(fc_stats);
 	return -ENOMEM;
@@ -512,7 +497,7 @@  void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
 
 	mlx5_fc_pool_cleanup(&fc_stats->fc_pool);
 	idr_destroy(&fc_stats->counters_idr);
-	kfree(fc_stats->bulk_query_out);
+	kvfree(fc_stats->bulk_query_out);
 	kfree(fc_stats);
 }