diff mbox series

[net-next,v13,11/13] net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags

Message ID 20240625024721.2140656-12-almasrymina@google.com (mailing list archive)
State Superseded
Headers show
Series Device Memory TCP | expand

Commit Message

Mina Almasry June 25, 2024, 2:47 a.m. UTC
Add an interface for the user to notify the kernel that it is done
reading the devmem dmabuf frags returned as cmsg. The kernel will
drop the reference on the frags to make them available for reuse.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>

---

v10:
- Fix leak of tokens (Nikolay).

v7:
- Updated SO_DEVMEM_* uapi to use the next available entry (Arnd).

v6:
- Squash in locking optimizations from edumazet@google.com. With his
  changes we lock the xarray once per sock_devmem_dontneed operation
  rather than once per frag.

Changes in v1:
- devmemtoken -> dmabuf_token (David).
- Use napi_pp_put_page() for refcounting (Yunsheng).
- Fix build error with missing socket options on other asms.

---
 arch/alpha/include/uapi/asm/socket.h  |  1 +
 arch/mips/include/uapi/asm/socket.h   |  1 +
 arch/parisc/include/uapi/asm/socket.h |  1 +
 arch/sparc/include/uapi/asm/socket.h  |  1 +
 include/uapi/asm-generic/socket.h     |  1 +
 include/uapi/linux/uio.h              |  4 ++
 net/core/sock.c                       | 61 +++++++++++++++++++++++++++
 7 files changed, 70 insertions(+)

Comments

Pavel Begunkov June 26, 2024, 1:47 p.m. UTC | #1
On 6/25/24 03:47, Mina Almasry wrote:
> Add an interface for the user to notify the kernel that it is done
> reading the devmem dmabuf frags returned as cmsg. The kernel will
> drop the reference on the frags to make them available for reuse.

The sock_devmem_dontneed loop is a bit crude, but that can
be handled by follow up patches.

Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>

> diff --git a/net/core/sock.c b/net/core/sock.c
> index 9abc4fe259535..040c66ac26244 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
...
>   
> +#ifdef CONFIG_PAGE_POOL
> +static noinline_for_stack int
> +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
> +{
> +	unsigned int num_tokens, i, j, k, netmem_num = 0;
> +	struct dmabuf_token *tokens;
> +	netmem_ref netmems[16];
> +	int ret = 0;
> +
> +	if (sk->sk_type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP)
> +		return -EBADF;
> +
> +	if (optlen % sizeof(struct dmabuf_token) ||
> +	    optlen > sizeof(*tokens) * 128)
> +		return -EINVAL;
> +
> +	tokens = kvmalloc_array(128, sizeof(*tokens), GFP_KERNEL);
> +	if (!tokens)
> +		return -ENOMEM;
> +
> +	num_tokens = optlen / sizeof(struct dmabuf_token);
> +	if (copy_from_sockptr(tokens, optval, optlen)) {
> +		kvfree(tokens);
> +		return -EFAULT;
> +	}
> +
> +	xa_lock_bh(&sk->sk_user_frags);
> +	for (i = 0; i < num_tokens; i++) {
> +		for (j = 0; j < tokens[i].token_count; j++) {
> +			netmem_ref netmem = (__force netmem_ref)__xa_erase(
> +				&sk->sk_user_frags, tokens[i].token_start + j);
> +
> +			if (netmem &&
> +			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
> +				netmems[netmem_num++] = netmem;
> +				if (netmem_num == ARRAY_SIZE(netmems)) {
> +					xa_unlock_bh(&sk->sk_user_frags);
> +					for (k = 0; k < netmem_num; k++)
> +						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
> +					netmem_num = 0;
> +					xa_lock_bh(&sk->sk_user_frags);
> +				}
> +				ret++;
> +			}
> +		}
> +	}
> +
> +	xa_unlock_bh(&sk->sk_user_frags);
> +	for (k = 0; k < netmem_num; k++)
> +		WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
> +
> +	kvfree(tokens);
> +	return ret;
> +}
> +#endif
diff mbox series

Patch

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index ef4656a41058a..251b73c5481ea 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -144,6 +144,7 @@ 
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 414807d55e33f..8ab7582291abf 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -155,6 +155,7 @@ 
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 2b817efd45444..38fc0b188e084 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -136,6 +136,7 @@ 
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 00248fc689773..57084ed2f3c4e 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -137,6 +137,7 @@ 
 #define SCM_DEVMEM_LINEAR        SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF         0x0058
 #define SCM_DEVMEM_DMABUF        SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED       0x0059
 
 #if !defined(__KERNEL__)
 
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 25a2f5255f523..1acb77780f103 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -135,6 +135,7 @@ 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_DONTNEED	97
 #define SO_DEVMEM_LINEAR	98
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	99
diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
index 3a22ddae376a2..d17f8fcd93ec9 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -33,6 +33,10 @@  struct dmabuf_cmsg {
 				 */
 };
 
+struct dmabuf_token {
+	__u32 token_start;
+	__u32 token_count;
+};
 /*
  *	UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
diff --git a/net/core/sock.c b/net/core/sock.c
index 9abc4fe259535..040c66ac26244 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -124,6 +124,7 @@ 
 #include <linux/netdevice.h>
 #include <net/protocol.h>
 #include <linux/skbuff.h>
+#include <linux/skbuff_ref.h>
 #include <net/net_namespace.h>
 #include <net/request_sock.h>
 #include <net/sock.h>
@@ -1049,6 +1050,62 @@  static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+#ifdef CONFIG_PAGE_POOL
+static noinline_for_stack int
+sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
+{
+	unsigned int num_tokens, i, j, k, netmem_num = 0;
+	struct dmabuf_token *tokens;
+	netmem_ref netmems[16];
+	int ret = 0;
+
+	if (sk->sk_type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP)
+		return -EBADF;
+
+	if (optlen % sizeof(struct dmabuf_token) ||
+	    optlen > sizeof(*tokens) * 128)
+		return -EINVAL;
+
+	tokens = kvmalloc_array(128, sizeof(*tokens), GFP_KERNEL);
+	if (!tokens)
+		return -ENOMEM;
+
+	num_tokens = optlen / sizeof(struct dmabuf_token);
+	if (copy_from_sockptr(tokens, optval, optlen)) {
+		kvfree(tokens);
+		return -EFAULT;
+	}
+
+	xa_lock_bh(&sk->sk_user_frags);
+	for (i = 0; i < num_tokens; i++) {
+		for (j = 0; j < tokens[i].token_count; j++) {
+			netmem_ref netmem = (__force netmem_ref)__xa_erase(
+				&sk->sk_user_frags, tokens[i].token_start + j);
+
+			if (netmem &&
+			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
+				netmems[netmem_num++] = netmem;
+				if (netmem_num == ARRAY_SIZE(netmems)) {
+					xa_unlock_bh(&sk->sk_user_frags);
+					for (k = 0; k < netmem_num; k++)
+						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+					netmem_num = 0;
+					xa_lock_bh(&sk->sk_user_frags);
+				}
+				ret++;
+			}
+		}
+	}
+
+	xa_unlock_bh(&sk->sk_user_frags);
+	for (k = 0; k < netmem_num; k++)
+		WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+
+	kvfree(tokens);
+	return ret;
+}
+#endif
+
 void sockopt_lock_sock(struct sock *sk)
 {
 	/* When current->bpf_ctx is set, the setsockopt is called from
@@ -1211,6 +1268,10 @@  int sk_setsockopt(struct sock *sk, int level, int optname,
 			ret = -EOPNOTSUPP;
 		return ret;
 		}
+#ifdef CONFIG_PAGE_POOL
+	case SO_DEVMEM_DONTNEED:
+		return sock_devmem_dontneed(sk, optval, optlen);
+#endif
 	}
 
 	sockopt_lock_sock(sk);