diff mbox series

[RFC,net-next,v6,13/15] net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags

Message ID 20240305020153.2787423-14-almasrymina@google.com
State New
Headers show
Series Device Memory TCP | expand

Commit Message

Mina Almasry March 5, 2024, 2:01 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>

---

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(+)
diff mbox series

Patch

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 1a9439f1c02e..43c98719120a 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -140,6 +140,7 @@ 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_DONTNEED	78
 #define SO_DEVMEM_LINEAR	79
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	80
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index a940747504a0..9a71ee8f36db 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -151,6 +151,7 @@ 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_DONTNEED	78
 #define SO_DEVMEM_LINEAR	79
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	80
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 1d399f104f08..1e77efcc6d63 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -132,6 +132,7 @@ 
 #define SO_PASSPIDFD		0x404A
 #define SO_PEERPIDFD		0x404B
 
+#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/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index a5961ecff31d..ecfc8bfa9fe0 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -133,6 +133,7 @@ 
 #define SO_PASSPIDFD             0x0055
 #define SO_PEERPIDFD             0x0056
 
+#define SO_DEVMEM_DONTNEED       0x0057
 #define SO_DEVMEM_LINEAR         0x0058
 #define SCM_DEVMEM_LINEAR        SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF         0x0059
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 25a2f5255f52..1acb77780f10 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 ad92e37699da..65f33178a601 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -30,6 +30,10 @@  struct dmabuf_cmsg {
 	__u32  dmabuf_id;	/* dmabuf id this frag belongs to. */
 };
 
+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 df2ac54a8f74..dc15d676f46f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1049,6 +1049,63 @@  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;
+
+	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))
+		return -EFAULT;
+
+	ret = 0;
+
+	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],
+									       false));
+					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], false));
+
+	kvfree(tokens);
+	return ret;
+}
+#endif
+
 void sockopt_lock_sock(struct sock *sk)
 {
 	/* When current->bpf_ctx is set, the setsockopt is called from
@@ -1200,6 +1257,10 @@  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);