diff mbox series

[bpf-next,1/3] skmsg: Calculate the data length in ingress_msg

Message ID 1699962120-3390-2-git-send-email-yangpc@wangsu.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series skmsg: Add the data length in skmsg to SIOCINQ ioctl and rx_queue | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR fail PR summary
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
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: 1175 this patch: 1175
netdev/cc_maintainers warning 1 maintainers not CCed: pabeni@redhat.com
netdev/build_clang success Errors and warnings before: 1162 this patch: 1162
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: 1202 this patch: 1202
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 68 lines checked
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
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 Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-3 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-5 fail Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 fail 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-9 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-16 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 fail Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-19 fail 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-20 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-21 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-22 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-llvm-16 / build / build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-26 fail Logs for x86_64-llvm-16 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-27 fail Logs for x86_64-llvm-16 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-16 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-llvm-16 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-16 / veristat
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-11 fail Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 fail 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-10 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc

Commit Message

Pengcheng Yang Nov. 14, 2023, 11:41 a.m. UTC 
Currently we cannot get the data length in ingress_msg,
we introduce sk_msg_queue_len() to do this.

Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
---
 include/linux/skmsg.h | 24 ++++++++++++++++++++++--
 net/core/skmsg.c      |  4 ++++
 2 files changed, 26 insertions(+), 2 deletions(-)

Comments

Eric Dumazet Nov. 14, 2023, 1:15 p.m. UTC | #1 
On Tue, Nov 14, 2023 at 12:42 PM Pengcheng Yang <yangpc@wangsu.com> wrote:
>
> Currently we cannot get the data length in ingress_msg,
> we introduce sk_msg_queue_len() to do this.
>
> Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
> ---
>  include/linux/skmsg.h | 24 ++++++++++++++++++++++--
>  net/core/skmsg.c      |  4 ++++
>  2 files changed, 26 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
> index c1637515a8a4..3023a573859d 100644
> --- a/include/linux/skmsg.h
> +++ b/include/linux/skmsg.h
> @@ -82,6 +82,7 @@ struct sk_psock {
>         u32                             apply_bytes;
>         u32                             cork_bytes;
>         u32                             eval;
> +       u32                             msg_len;
>         bool                            redir_ingress; /* undefined if sk_redir is null */
>         struct sk_msg                   *cork;
>         struct sk_psock_progs           progs;
> @@ -131,6 +132,11 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
>                    int len, int flags);
>  bool sk_msg_is_readable(struct sock *sk);
>
> +static inline void sk_msg_queue_consumed(struct sk_psock *psock, u32 len)
> +{
> +       psock->msg_len -= len;
> +}
> +
>  static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
>  {
>         WARN_ON(i == msg->sg.end && bytes);
> @@ -311,9 +317,10 @@ static inline void sk_psock_queue_msg(struct sk_psock *psock,
>                                       struct sk_msg *msg)
>  {
>         spin_lock_bh(&psock->ingress_lock);
> -       if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
> +       if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
>                 list_add_tail(&msg->list, &psock->ingress_msg);
> -       else {
> +               psock->msg_len += msg->sg.size;
> +       } else {
>                 sk_msg_free(psock->sk, msg);
>                 kfree(msg);
>         }
> @@ -368,6 +375,19 @@ static inline void kfree_sk_msg(struct sk_msg *msg)
>         kfree(msg);
>  }
>
> +static inline u32 sk_msg_queue_len(struct sock *sk)

const struct sock *sk;

> +{
> +       struct sk_psock *psock;
> +       u32 len = 0;
> +
> +       rcu_read_lock();
> +       psock = sk_psock(sk);
> +       if (psock)
> +               len = psock->msg_len;

This is racy against writers.

You must use READ_ONCE() here, and WRITE_ONCE() on write sides.

> +       rcu_read_unlock();
> +       return len;
> +}
> +
>  static inline void sk_psock_report_error(struct sk_psock *psock, int err)
>  {
>         struct sock *sk = psock->sk;
> diff --git a/net/core/skmsg.c b/net/core/skmsg.c
> index 6c31eefbd777..b3de17e99b67 100644
> --- a/net/core/skmsg.c
> +++ b/net/core/skmsg.c
> @@ -481,6 +481,8 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
>                 msg_rx = sk_psock_peek_msg(psock);
>         }
>  out:
> +       if (likely(!peek) && copied > 0)
> +               sk_msg_queue_consumed(psock, copied);
>         return copied;
>  }
>  EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
> @@ -771,9 +773,11 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
>
>         list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) {
>                 list_del(&msg->list);
> +               sk_msg_queue_consumed(psock, msg->sg.size);
>                 sk_msg_free(psock->sk, msg);
>                 kfree(msg);
>         }
> +       WARN_ON_ONCE(psock->msg_len != 0);
>  }
>
>  static void __sk_psock_zap_ingress(struct sk_psock *psock)
> --
> 2.38.1
>
diff mbox series

Patch

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c1637515a8a4..3023a573859d 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -82,6 +82,7 @@  struct sk_psock {
 	u32				apply_bytes;
 	u32				cork_bytes;
 	u32				eval;
+	u32				msg_len;
 	bool				redir_ingress; /* undefined if sk_redir is null */
 	struct sk_msg			*cork;
 	struct sk_psock_progs		progs;
@@ -131,6 +132,11 @@  int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		   int len, int flags);
 bool sk_msg_is_readable(struct sock *sk);
 
+static inline void sk_msg_queue_consumed(struct sk_psock *psock, u32 len)
+{
+	psock->msg_len -= len;
+}
+
 static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
 {
 	WARN_ON(i == msg->sg.end && bytes);
@@ -311,9 +317,10 @@  static inline void sk_psock_queue_msg(struct sk_psock *psock,
 				      struct sk_msg *msg)
 {
 	spin_lock_bh(&psock->ingress_lock);
-	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
 		list_add_tail(&msg->list, &psock->ingress_msg);
-	else {
+		psock->msg_len += msg->sg.size;
+	} else {
 		sk_msg_free(psock->sk, msg);
 		kfree(msg);
 	}
@@ -368,6 +375,19 @@  static inline void kfree_sk_msg(struct sk_msg *msg)
 	kfree(msg);
 }
 
+static inline u32 sk_msg_queue_len(struct sock *sk)
+{
+	struct sk_psock *psock;
+	u32 len = 0;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (psock)
+		len = psock->msg_len;
+	rcu_read_unlock();
+	return len;
+}
+
 static inline void sk_psock_report_error(struct sk_psock *psock, int err)
 {
 	struct sock *sk = psock->sk;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6c31eefbd777..b3de17e99b67 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -481,6 +481,8 @@  int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		msg_rx = sk_psock_peek_msg(psock);
 	}
 out:
+	if (likely(!peek) && copied > 0)
+		sk_msg_queue_consumed(psock, copied);
 	return copied;
 }
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
@@ -771,9 +773,11 @@  static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
 
 	list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) {
 		list_del(&msg->list);
+		sk_msg_queue_consumed(psock, msg->sg.size);
 		sk_msg_free(psock->sk, msg);
 		kfree(msg);
 	}
+	WARN_ON_ONCE(psock->msg_len != 0);
 }
 
 static void __sk_psock_zap_ingress(struct sk_psock *psock)