| Message ID | 20240626193403.3854451-4-zijianzhang@bytedance.com (mailing list archive) |
|---|---|
| State | Superseded |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | net: A lightweight zero-copy notification | expand |
zijianzhang@ wrote: > From: Zijian Zhang <zijianzhang@bytedance.com> > > The MSG_ZEROCOPY flag enables copy avoidance for socket send calls. > However, zerocopy is not a free lunch. Apart from the management of user > pages, the combination of poll + recvmsg to receive notifications incurs > unignorable overhead in the applications. The overhead of such sometimes > might be more than the CPU savings from zerocopy. We try to solve this > problem with a new notification mechanism based on msgcontrol. > > This new mechanism aims to reduce the overhead associated with receiving > notifications by embedding them directly into user arguments passed with > each sendmsg control message. By doing so, we can significantly reduce > the complexity and overhead for managing notifications. In an ideal > pattern, the user will keep calling sendmsg with SCM_ZC_NOTIFICATION > msg_control, and the notification will be delivered as soon as possible. > > Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com> > Signed-off-by: Xiaochun Lu <xiaochun.lu@bytedance.com> > --- > arch/alpha/include/uapi/asm/socket.h | 2 ++ > arch/mips/include/uapi/asm/socket.h | 2 ++ > arch/parisc/include/uapi/asm/socket.h | 2 ++ > arch/sparc/include/uapi/asm/socket.h | 2 ++ > include/linux/socket.h | 2 +- > include/uapi/asm-generic/socket.h | 2 ++ > include/uapi/linux/socket.h | 10 +++++++ > net/core/sock.c | 42 +++++++++++++++++++++++++++ > 8 files changed, 63 insertions(+), 1 deletion(-) > > diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h > index e94f621903fe..7761a4e0ea2c 100644 > --- a/arch/alpha/include/uapi/asm/socket.h > +++ b/arch/alpha/include/uapi/asm/socket.h > @@ -140,6 +140,8 @@ > #define SO_PASSPIDFD 76 > #define SO_PEERPIDFD 77 > > +#define SCM_ZC_NOTIFICATION 78 > + > #if !defined(__KERNEL__) > > #if __BITS_PER_LONG == 64 > diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h > index 60ebaed28a4c..89edc51380f0 100644 > --- a/arch/mips/include/uapi/asm/socket.h > +++ b/arch/mips/include/uapi/asm/socket.h > @@ -151,6 +151,8 @@ > #define SO_PASSPIDFD 76 > #define SO_PEERPIDFD 77 > > +#define SCM_ZC_NOTIFICATION 78 > + > #if !defined(__KERNEL__) > > #if __BITS_PER_LONG == 64 > diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h > index be264c2b1a11..2911b43e6a9d 100644 > --- a/arch/parisc/include/uapi/asm/socket.h > +++ b/arch/parisc/include/uapi/asm/socket.h > @@ -132,6 +132,8 @@ > #define SO_PASSPIDFD 0x404A > #define SO_PEERPIDFD 0x404B > > +#define SCM_ZC_NOTIFICATION 0x404C > + > #if !defined(__KERNEL__) > > #if __BITS_PER_LONG == 64 > diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h > index 682da3714686..dc045e87cc8e 100644 > --- a/arch/sparc/include/uapi/asm/socket.h > +++ b/arch/sparc/include/uapi/asm/socket.h > @@ -133,6 +133,8 @@ > #define SO_PASSPIDFD 0x0055 > #define SO_PEERPIDFD 0x0056 > > +#define SCM_ZC_NOTIFICATION 0x0057 > + > #if !defined(__KERNEL__) > > > diff --git a/include/linux/socket.h b/include/linux/socket.h > index 35adc30c9db6..f2f013166525 100644 > --- a/include/linux/socket.h > +++ b/include/linux/socket.h > @@ -170,7 +170,7 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr > > static inline bool cmsg_copy_to_user(struct cmsghdr *__cmsg) > { > - return 0; > + return __cmsg->cmsg_type == SCM_ZC_NOTIFICATION; > } > > static inline size_t msg_data_left(struct msghdr *msg) > diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h > index 8ce8a39a1e5f..7474c8a244bc 100644 > --- a/include/uapi/asm-generic/socket.h > +++ b/include/uapi/asm-generic/socket.h > @@ -135,6 +135,8 @@ > #define SO_PASSPIDFD 76 > #define SO_PEERPIDFD 77 > > +#define SCM_ZC_NOTIFICATION 78 > + > #if !defined(__KERNEL__) > > #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) > diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h > index d3fcd3b5ec53..26bee6291c6c 100644 > --- a/include/uapi/linux/socket.h > +++ b/include/uapi/linux/socket.h > @@ -2,6 +2,8 @@ > #ifndef _UAPI_LINUX_SOCKET_H > #define _UAPI_LINUX_SOCKET_H > > +#include <linux/types.h> > + > /* > * Desired design of maximum size and alignment (see RFC2553) > */ > @@ -35,4 +37,12 @@ struct __kernel_sockaddr_storage { > #define SOCK_TXREHASH_DISABLED 0 > #define SOCK_TXREHASH_ENABLED 1 > > +#define SOCK_ZC_INFO_MAX 16 > + > +struct zc_info_elem { > + __u32 lo; > + __u32 hi; > + __u8 zerocopy; > +}; > + > #endif /* _UAPI_LINUX_SOCKET_H */ > diff --git a/net/core/sock.c b/net/core/sock.c > index 4a766a91ff5c..1b2ce72e1338 100644 > --- a/net/core/sock.c > +++ b/net/core/sock.c > @@ -2863,6 +2863,48 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, > case SCM_RIGHTS: > case SCM_CREDENTIALS: > break; > + case SCM_ZC_NOTIFICATION: { > + struct zc_info_elem *zc_info_kern = CMSG_DATA(cmsg); > + int cmsg_data_len, zc_info_elem_num; > + struct sock_exterr_skb *serr; > + struct sk_buff_head *q; > + unsigned long flags; > + struct sk_buff *skb; > + int i = 0; > + > + if (!sock_flag(sk, SOCK_ZEROCOPY) || sk->sk_family == PF_RDS) > + return -EINVAL; > + > + cmsg_data_len = cmsg->cmsg_len - sizeof(struct cmsghdr); > + if (cmsg_data_len % sizeof(struct zc_info_elem)) > + return -EINVAL; > + > + zc_info_elem_num = cmsg_data_len / sizeof(struct zc_info_elem); > + if (!zc_info_elem_num || zc_info_elem_num > SOCK_ZC_INFO_MAX) > + return -EINVAL; > + > + q = &sk->sk_error_queue; > + spin_lock_irqsave(&q->lock, flags); > + skb = skb_peek(q); > + while (skb && i < zc_info_elem_num) { > + struct sk_buff *skb_next = skb_peek_next(skb, q); > + > + serr = SKB_EXT_ERR(skb); > + if (serr->ee.ee_errno == 0 && > + serr->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY) { > + zc_info_kern[i].hi = serr->ee.ee_data; > + zc_info_kern[i].lo = serr->ee.ee_info; > + zc_info_kern[i].zerocopy = !(serr->ee.ee_code > + & SO_EE_CODE_ZEROCOPY_COPIED); > + __skb_unlink(skb, q); > + consume_skb(skb); > + } > + skb = skb_next; > + i++; > + } How will userspace know the number of entries written? Since the cmsg_len is not updated, is the expectation that the CMSG_DATA is zero initialized by the user and the list will be zero-element terminated? > + spin_unlock_irqrestore(&q->lock, flags); > + break; > + } > default: > return -EINVAL; > } > -- > 2.20.1 >
On 6/30/24 7:44 AM, Willem de Bruijn wrote: > zijianzhang@ wrote: >> From: Zijian Zhang <zijianzhang@bytedance.com> >> >> The MSG_ZEROCOPY flag enables copy avoidance for socket send calls. >> However, zerocopy is not a free lunch. Apart from the management of user >> pages, the combination of poll + recvmsg to receive notifications incurs >> unignorable overhead in the applications. The overhead of such sometimes >> might be more than the CPU savings from zerocopy. We try to solve this >> problem with a new notification mechanism based on msgcontrol. >> >> This new mechanism aims to reduce the overhead associated with receiving >> notifications by embedding them directly into user arguments passed with >> each sendmsg control message. By doing so, we can significantly reduce >> the complexity and overhead for managing notifications. In an ideal >> pattern, the user will keep calling sendmsg with SCM_ZC_NOTIFICATION >> msg_control, and the notification will be delivered as soon as possible. >> >> Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com> >> Signed-off-by: Xiaochun Lu <xiaochun.lu@bytedance.com> >> --- >> arch/alpha/include/uapi/asm/socket.h | 2 ++ >> arch/mips/include/uapi/asm/socket.h | 2 ++ >> arch/parisc/include/uapi/asm/socket.h | 2 ++ >> arch/sparc/include/uapi/asm/socket.h | 2 ++ >> include/linux/socket.h | 2 +- >> include/uapi/asm-generic/socket.h | 2 ++ >> include/uapi/linux/socket.h | 10 +++++++ >> net/core/sock.c | 42 +++++++++++++++++++++++++++ >> 8 files changed, 63 insertions(+), 1 deletion(-) >> >> diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h >> index e94f621903fe..7761a4e0ea2c 100644 >> --- a/arch/alpha/include/uapi/asm/socket.h >> +++ b/arch/alpha/include/uapi/asm/socket.h >> @@ -140,6 +140,8 @@ >> #define SO_PASSPIDFD 76 >> #define SO_PEERPIDFD 77 >> >> +#define SCM_ZC_NOTIFICATION 78 >> + >> #if !defined(__KERNEL__) >> >> #if __BITS_PER_LONG == 64 >> diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h >> index 60ebaed28a4c..89edc51380f0 100644 >> --- a/arch/mips/include/uapi/asm/socket.h >> +++ b/arch/mips/include/uapi/asm/socket.h >> @@ -151,6 +151,8 @@ >> #define SO_PASSPIDFD 76 >> #define SO_PEERPIDFD 77 >> >> +#define SCM_ZC_NOTIFICATION 78 >> + >> #if !defined(__KERNEL__) >> >> #if __BITS_PER_LONG == 64 >> diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h >> index be264c2b1a11..2911b43e6a9d 100644 >> --- a/arch/parisc/include/uapi/asm/socket.h >> +++ b/arch/parisc/include/uapi/asm/socket.h >> @@ -132,6 +132,8 @@ >> #define SO_PASSPIDFD 0x404A >> #define SO_PEERPIDFD 0x404B >> >> +#define SCM_ZC_NOTIFICATION 0x404C >> + >> #if !defined(__KERNEL__) >> >> #if __BITS_PER_LONG == 64 >> diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h >> index 682da3714686..dc045e87cc8e 100644 >> --- a/arch/sparc/include/uapi/asm/socket.h >> +++ b/arch/sparc/include/uapi/asm/socket.h >> @@ -133,6 +133,8 @@ >> #define SO_PASSPIDFD 0x0055 >> #define SO_PEERPIDFD 0x0056 >> >> +#define SCM_ZC_NOTIFICATION 0x0057 >> + >> #if !defined(__KERNEL__) >> >> >> diff --git a/include/linux/socket.h b/include/linux/socket.h >> index 35adc30c9db6..f2f013166525 100644 >> --- a/include/linux/socket.h >> +++ b/include/linux/socket.h >> @@ -170,7 +170,7 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr >> >> static inline bool cmsg_copy_to_user(struct cmsghdr *__cmsg) >> { >> - return 0; >> + return __cmsg->cmsg_type == SCM_ZC_NOTIFICATION; >> } >> >> static inline size_t msg_data_left(struct msghdr *msg) >> diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h >> index 8ce8a39a1e5f..7474c8a244bc 100644 >> --- a/include/uapi/asm-generic/socket.h >> +++ b/include/uapi/asm-generic/socket.h >> @@ -135,6 +135,8 @@ >> #define SO_PASSPIDFD 76 >> #define SO_PEERPIDFD 77 >> >> +#define SCM_ZC_NOTIFICATION 78 >> + >> #if !defined(__KERNEL__) >> >> #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) >> diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h >> index d3fcd3b5ec53..26bee6291c6c 100644 >> --- a/include/uapi/linux/socket.h >> +++ b/include/uapi/linux/socket.h >> @@ -2,6 +2,8 @@ >> #ifndef _UAPI_LINUX_SOCKET_H >> #define _UAPI_LINUX_SOCKET_H >> >> +#include <linux/types.h> >> + >> /* >> * Desired design of maximum size and alignment (see RFC2553) >> */ >> @@ -35,4 +37,12 @@ struct __kernel_sockaddr_storage { >> #define SOCK_TXREHASH_DISABLED 0 >> #define SOCK_TXREHASH_ENABLED 1 >> >> +#define SOCK_ZC_INFO_MAX 16 >> + >> +struct zc_info_elem { >> + __u32 lo; >> + __u32 hi; >> + __u8 zerocopy; >> +}; >> + >> #endif /* _UAPI_LINUX_SOCKET_H */ >> diff --git a/net/core/sock.c b/net/core/sock.c >> index 4a766a91ff5c..1b2ce72e1338 100644 >> --- a/net/core/sock.c >> +++ b/net/core/sock.c >> @@ -2863,6 +2863,48 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, >> case SCM_RIGHTS: >> case SCM_CREDENTIALS: >> break; >> + case SCM_ZC_NOTIFICATION: { >> + struct zc_info_elem *zc_info_kern = CMSG_DATA(cmsg); >> + int cmsg_data_len, zc_info_elem_num; >> + struct sock_exterr_skb *serr; >> + struct sk_buff_head *q; >> + unsigned long flags; >> + struct sk_buff *skb; >> + int i = 0; >> + >> + if (!sock_flag(sk, SOCK_ZEROCOPY) || sk->sk_family == PF_RDS) >> + return -EINVAL; >> + >> + cmsg_data_len = cmsg->cmsg_len - sizeof(struct cmsghdr); >> + if (cmsg_data_len % sizeof(struct zc_info_elem)) >> + return -EINVAL; >> + >> + zc_info_elem_num = cmsg_data_len / sizeof(struct zc_info_elem); >> + if (!zc_info_elem_num || zc_info_elem_num > SOCK_ZC_INFO_MAX) >> + return -EINVAL; >> + >> + q = &sk->sk_error_queue; >> + spin_lock_irqsave(&q->lock, flags); >> + skb = skb_peek(q); >> + while (skb && i < zc_info_elem_num) { >> + struct sk_buff *skb_next = skb_peek_next(skb, q); >> + >> + serr = SKB_EXT_ERR(skb); >> + if (serr->ee.ee_errno == 0 && >> + serr->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY) { >> + zc_info_kern[i].hi = serr->ee.ee_data; >> + zc_info_kern[i].lo = serr->ee.ee_info; >> + zc_info_kern[i].zerocopy = !(serr->ee.ee_code >> + & SO_EE_CODE_ZEROCOPY_COPIED); >> + __skb_unlink(skb, q); >> + consume_skb(skb); >> + } >> + skb = skb_next; >> + i++; >> + } > > How will userspace know the number of entries written? Since the > cmsg_len is not updated, is the expectation that the CMSG_DATA is zero > initialized by the user and the list will be zero-element terminated? > Since zero-element is a valid value(the first sendmsg with non-zerocopy) in our case, zero-element terminated might not be feasible. In current selftest, the user initializes zerocopy field to a invalid value, and upon returning iterate the array until the invalid value. It is very dependent to the user, I think it's not good enough. I agree that updating cmsg_len is better. >> + spin_unlock_irqrestore(&q->lock, flags); >> + break; >> + } >> default: >> return -EINVAL; >> } >> -- >> 2.20.1 >> > >
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e94f621903fe..7761a4e0ea2c 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -140,6 +140,8 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SCM_ZC_NOTIFICATION 78 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 60ebaed28a4c..89edc51380f0 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -151,6 +151,8 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SCM_ZC_NOTIFICATION 78 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index be264c2b1a11..2911b43e6a9d 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -132,6 +132,8 @@ #define SO_PASSPIDFD 0x404A #define SO_PEERPIDFD 0x404B +#define SCM_ZC_NOTIFICATION 0x404C + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 682da3714686..dc045e87cc8e 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -133,6 +133,8 @@ #define SO_PASSPIDFD 0x0055 #define SO_PEERPIDFD 0x0056 +#define SCM_ZC_NOTIFICATION 0x0057 + #if !defined(__KERNEL__) diff --git a/include/linux/socket.h b/include/linux/socket.h index 35adc30c9db6..f2f013166525 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -170,7 +170,7 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr static inline bool cmsg_copy_to_user(struct cmsghdr *__cmsg) { - return 0; + return __cmsg->cmsg_type == SCM_ZC_NOTIFICATION; } static inline size_t msg_data_left(struct msghdr *msg) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..7474c8a244bc 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,8 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SCM_ZC_NOTIFICATION 78 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index d3fcd3b5ec53..26bee6291c6c 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_SOCKET_H #define _UAPI_LINUX_SOCKET_H +#include <linux/types.h> + /* * Desired design of maximum size and alignment (see RFC2553) */ @@ -35,4 +37,12 @@ struct __kernel_sockaddr_storage { #define SOCK_TXREHASH_DISABLED 0 #define SOCK_TXREHASH_ENABLED 1 +#define SOCK_ZC_INFO_MAX 16 + +struct zc_info_elem { + __u32 lo; + __u32 hi; + __u8 zerocopy; +}; + #endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/net/core/sock.c b/net/core/sock.c index 4a766a91ff5c..1b2ce72e1338 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2863,6 +2863,48 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, case SCM_RIGHTS: case SCM_CREDENTIALS: break; + case SCM_ZC_NOTIFICATION: { + struct zc_info_elem *zc_info_kern = CMSG_DATA(cmsg); + int cmsg_data_len, zc_info_elem_num; + struct sock_exterr_skb *serr; + struct sk_buff_head *q; + unsigned long flags; + struct sk_buff *skb; + int i = 0; + + if (!sock_flag(sk, SOCK_ZEROCOPY) || sk->sk_family == PF_RDS) + return -EINVAL; + + cmsg_data_len = cmsg->cmsg_len - sizeof(struct cmsghdr); + if (cmsg_data_len % sizeof(struct zc_info_elem)) + return -EINVAL; + + zc_info_elem_num = cmsg_data_len / sizeof(struct zc_info_elem); + if (!zc_info_elem_num || zc_info_elem_num > SOCK_ZC_INFO_MAX) + return -EINVAL; + + q = &sk->sk_error_queue; + spin_lock_irqsave(&q->lock, flags); + skb = skb_peek(q); + while (skb && i < zc_info_elem_num) { + struct sk_buff *skb_next = skb_peek_next(skb, q); + + serr = SKB_EXT_ERR(skb); + if (serr->ee.ee_errno == 0 && + serr->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY) { + zc_info_kern[i].hi = serr->ee.ee_data; + zc_info_kern[i].lo = serr->ee.ee_info; + zc_info_kern[i].zerocopy = !(serr->ee.ee_code + & SO_EE_CODE_ZEROCOPY_COPIED); + __skb_unlink(skb, q); + consume_skb(skb); + } + skb = skb_next; + i++; + } + spin_unlock_irqrestore(&q->lock, flags); + break; + } default: return -EINVAL; }