diff mbox series

[bpf-next,3/9] net: napi: add ability to create CPU-pinned threaded NAPI

Message ID 20240830162508.1009458-4-aleksander.lobakin@intel.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series bpf: cpumap: enable GRO for XDP_PASS frames | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-17 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-18 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
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: 55 this patch: 55
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers success CCed 5 of 5 maintainers
netdev/build_clang success Errors and warnings before: 102 this patch: 102
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 success Errors and warnings before: 4071 this patch: 4071
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 95 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 101 this patch: 101
netdev/source_inline success Was 0 now: 0

Commit Message

Alexander Lobakin Aug. 30, 2024, 4:25 p.m. UTC 
From: Lorenzo Bianconi <lorenzo@kernel.org>

Add netif_napi_add_percpu() to pin NAPI in threaded mode to a particular
CPU. This means, if the NAPI is not threaded, it will be run as usually,
but when switching to threaded mode, it will always be run on the
specified CPU.
It's not meant to be used in drivers, but might be useful when creating
percpu threaded NAPIs, for example, to replace percpu kthreads or
workers where a NAPI context is needed.
The already existing netif_napi_add*() are not anyhow affected.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
 include/linux/netdevice.h | 35 +++++++++++++++++++++++++++++++++--
 net/core/dev.c            | 18 +++++++++++++-----
 2 files changed, 46 insertions(+), 7 deletions(-)

Comments

Daniel Xu Aug. 31, 2024, 12:19 a.m. UTC | #1 
On Fri, Aug 30, 2024, at 9:25 AM, Alexander Lobakin wrote:
> From: Lorenzo Bianconi <lorenzo@kernel.org>
>
> Add netif_napi_add_percpu() to pin NAPI in threaded mode to a particular
> CPU. This means, if the NAPI is not threaded, it will be run as usually,
> but when switching to threaded mode, it will always be run on the
> specified CPU.
> It's not meant to be used in drivers, but might be useful when creating
> percpu threaded NAPIs, for example, to replace percpu kthreads or
> workers where a NAPI context is needed.
> The already existing netif_napi_add*() are not anyhow affected.
>
> Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
> ---
>  include/linux/netdevice.h | 35 +++++++++++++++++++++++++++++++++--
>  net/core/dev.c            | 18 +++++++++++++-----
>  2 files changed, 46 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index ca5f0dda733b..4d6fb0ccdea1 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -377,6 +377,7 @@ struct napi_struct {
>  	struct list_head	dev_list;
>  	struct hlist_node	napi_hash_node;
>  	int			irq;
> +	int			thread_cpuid;
>  };
> 
>  enum {
> @@ -2619,8 +2620,18 @@ static inline void netif_napi_set_irq(struct 
> napi_struct *napi, int irq)
>   */
>  #define NAPI_POLL_WEIGHT 64
> 
> -void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
> -			   int (*poll)(struct napi_struct *, int), int weight);
> +void netif_napi_add_weight_percpu(struct net_device *dev,
> +				  struct napi_struct *napi,
> +				  int (*poll)(struct napi_struct *, int),
> +				  int weight, int thread_cpuid);
> +
> +static inline void netif_napi_add_weight(struct net_device *dev,
> +					 struct napi_struct *napi,
> +					 int (*poll)(struct napi_struct *, int),
> +					 int weight)
> +{
> +	netif_napi_add_weight_percpu(dev, napi, poll, weight, -1);
> +}
> 
>  /**
>   * netif_napi_add() - initialize a NAPI context
> @@ -2665,6 +2676,26 @@ static inline void netif_napi_add_tx(struct 
> net_device *dev,
>  	netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
>  }
> 
> +/**
> + * netif_napi_add_percpu() - initialize a CPU-pinned threaded NAPI 
> context
> + * @dev:  network device
> + * @napi: NAPI context
> + * @poll: polling function
> + * @thread_cpuid: CPU which this NAPI will be pinned to
> + *
> + * Variant of netif_napi_add() which pins the NAPI to the specified 
> CPU. No
> + * changes in the "standard" mode, but in case with the threaded one, 
> this
> + * NAPI will always be run on the passed CPU no matter where scheduled.
> + */
> +static inline void netif_napi_add_percpu(struct net_device *dev,
> +					 struct napi_struct *napi,
> +					 int (*poll)(struct napi_struct *, int),
> +					 int thread_cpuid)
> +{
> +	netif_napi_add_weight_percpu(dev, napi, poll, NAPI_POLL_WEIGHT,
> +				     thread_cpuid);
> +}
> +
>  /**
>   *  __netif_napi_del - remove a NAPI context
>   *  @napi: NAPI context
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 98bb5f890b88..93ca3df8e9dd 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -1428,8 +1428,13 @@ static int napi_kthread_create(struct 
> napi_struct *n)
>  	 * TASK_INTERRUPTIBLE mode to avoid the blocked task
>  	 * warning and work with loadavg.
>  	 */
> -	n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
> -				n->dev->name, n->napi_id);
> +	if (n->thread_cpuid >= 0)
> +		n->thread = kthread_run_on_cpu(napi_threaded_poll, n,
> +					       n->thread_cpuid, "napi/%s-%u",
> +					       n->dev->name);
> +	else
> +		n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
> +					n->dev->name, n->napi_id);
>  	if (IS_ERR(n->thread)) {
>  		err = PTR_ERR(n->thread);
>  		pr_err("kthread_run failed with err %d\n", err);
> @@ -6640,8 +6645,10 @@ void netif_queue_set_napi(struct net_device 
> *dev, unsigned int queue_index,
>  }
>  EXPORT_SYMBOL(netif_queue_set_napi);
> 
> -void netif_napi_add_weight(struct net_device *dev, struct napi_struct 
> *napi,
> -			   int (*poll)(struct napi_struct *, int), int weight)
> +void netif_napi_add_weight_percpu(struct net_device *dev,
> +				  struct napi_struct *napi,
> +				  int (*poll)(struct napi_struct *, int),
> +				  int weight, int thread_cpuid)
>  {
>  	if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
>  		return;
> @@ -6664,6 +6671,7 @@ void netif_napi_add_weight(struct net_device 
> *dev, struct napi_struct *napi,
>  	napi->poll_owner = -1;
>  #endif
>  	napi->list_owner = -1;
> +	napi->thread_cpuid = thread_cpuid;
>  	set_bit(NAPI_STATE_SCHED, &napi->state);
>  	set_bit(NAPI_STATE_NPSVC, &napi->state);
>  	list_add_rcu(&napi->dev_list, &dev->napi_list);
> @@ -6677,7 +6685,7 @@ void netif_napi_add_weight(struct net_device 
> *dev, struct napi_struct *napi,
>  		dev->threaded = false;
>  	netif_napi_set_irq(napi, -1);
>  }
> -EXPORT_SYMBOL(netif_napi_add_weight);
> +EXPORT_SYMBOL(netif_napi_add_weight_percpu);
> 
>  void napi_disable(struct napi_struct *n)
>  {
> -- 
> 2.46.0

Acked-by: Daniel Xu <dxu@dxuuu.xyz>
diff mbox series

Patch

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ca5f0dda733b..4d6fb0ccdea1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -377,6 +377,7 @@  struct napi_struct {
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	int			irq;
+	int			thread_cpuid;
 };
 
 enum {
@@ -2619,8 +2620,18 @@  static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
  */
 #define NAPI_POLL_WEIGHT 64
 
-void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
-			   int (*poll)(struct napi_struct *, int), int weight);
+void netif_napi_add_weight_percpu(struct net_device *dev,
+				  struct napi_struct *napi,
+				  int (*poll)(struct napi_struct *, int),
+				  int weight, int thread_cpuid);
+
+static inline void netif_napi_add_weight(struct net_device *dev,
+					 struct napi_struct *napi,
+					 int (*poll)(struct napi_struct *, int),
+					 int weight)
+{
+	netif_napi_add_weight_percpu(dev, napi, poll, weight, -1);
+}
 
 /**
  * netif_napi_add() - initialize a NAPI context
@@ -2665,6 +2676,26 @@  static inline void netif_napi_add_tx(struct net_device *dev,
 	netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
 }
 
+/**
+ * netif_napi_add_percpu() - initialize a CPU-pinned threaded NAPI context
+ * @dev:  network device
+ * @napi: NAPI context
+ * @poll: polling function
+ * @thread_cpuid: CPU which this NAPI will be pinned to
+ *
+ * Variant of netif_napi_add() which pins the NAPI to the specified CPU. No
+ * changes in the "standard" mode, but in case with the threaded one, this
+ * NAPI will always be run on the passed CPU no matter where scheduled.
+ */
+static inline void netif_napi_add_percpu(struct net_device *dev,
+					 struct napi_struct *napi,
+					 int (*poll)(struct napi_struct *, int),
+					 int thread_cpuid)
+{
+	netif_napi_add_weight_percpu(dev, napi, poll, NAPI_POLL_WEIGHT,
+				     thread_cpuid);
+}
+
 /**
  *  __netif_napi_del - remove a NAPI context
  *  @napi: NAPI context
diff --git a/net/core/dev.c b/net/core/dev.c
index 98bb5f890b88..93ca3df8e9dd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1428,8 +1428,13 @@  static int napi_kthread_create(struct napi_struct *n)
 	 * TASK_INTERRUPTIBLE mode to avoid the blocked task
 	 * warning and work with loadavg.
 	 */
-	n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
-				n->dev->name, n->napi_id);
+	if (n->thread_cpuid >= 0)
+		n->thread = kthread_run_on_cpu(napi_threaded_poll, n,
+					       n->thread_cpuid, "napi/%s-%u",
+					       n->dev->name);
+	else
+		n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
+					n->dev->name, n->napi_id);
 	if (IS_ERR(n->thread)) {
 		err = PTR_ERR(n->thread);
 		pr_err("kthread_run failed with err %d\n", err);
@@ -6640,8 +6645,10 @@  void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 }
 EXPORT_SYMBOL(netif_queue_set_napi);
 
-void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
-			   int (*poll)(struct napi_struct *, int), int weight)
+void netif_napi_add_weight_percpu(struct net_device *dev,
+				  struct napi_struct *napi,
+				  int (*poll)(struct napi_struct *, int),
+				  int weight, int thread_cpuid)
 {
 	if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
 		return;
@@ -6664,6 +6671,7 @@  void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 	napi->poll_owner = -1;
 #endif
 	napi->list_owner = -1;
+	napi->thread_cpuid = thread_cpuid;
 	set_bit(NAPI_STATE_SCHED, &napi->state);
 	set_bit(NAPI_STATE_NPSVC, &napi->state);
 	list_add_rcu(&napi->dev_list, &dev->napi_list);
@@ -6677,7 +6685,7 @@  void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 		dev->threaded = false;
 	netif_napi_set_irq(napi, -1);
 }
-EXPORT_SYMBOL(netif_napi_add_weight);
+EXPORT_SYMBOL(netif_napi_add_weight_percpu);
 
 void napi_disable(struct napi_struct *n)
 {