| Message ID | 20240513211755.2751955-3-zijianzhang@bytedance.com (mailing list archive) |
|---|---|
| State | Deferred |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | net: A lightweight zero-copy notification | expand |
Hi, kernel test robot noticed the following build warnings: [auto build test WARNING on net-next/main] url: https://github.com/intel-lab-lkp/linux/commits/zijianzhang-bytedance-com/selftests-fix-OOM-problem-in-msg_zerocopy-selftest/20240514-051839 base: net-next/main patch link: https://lore.kernel.org/r/20240513211755.2751955-3-zijianzhang%40bytedance.com patch subject: [PATCH net-next v4 2/3] sock: add MSG_ZEROCOPY notification mechanism based on msg_control config: openrisc-defconfig (https://download.01.org/0day-ci/archive/20240514/202405141135.xZDS5YLg-lkp@intel.com/config) compiler: or1k-linux-gcc (GCC) 13.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240514/202405141135.xZDS5YLg-lkp@intel.com/reproduce) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp@intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202405141135.xZDS5YLg-lkp@intel.com/ All warnings (new ones prefixed by >>): net/core/sock.c: In function '__sock_cmsg_send': >> net/core/sock.c:2850:39: warning: unused variable 'tmp' [-Wunused-variable] 2850 | struct sk_buff *skb, *tmp; | ^~~ vim +/tmp +2850 net/core/sock.c 2807 2808 int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, 2809 struct sockcm_cookie *sockc) 2810 { 2811 u32 tsflags; 2812 2813 switch (cmsg->cmsg_type) { 2814 case SO_MARK: 2815 if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && 2816 !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) 2817 return -EPERM; 2818 if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) 2819 return -EINVAL; 2820 sockc->mark = *(u32 *)CMSG_DATA(cmsg); 2821 break; 2822 case SO_TIMESTAMPING_OLD: 2823 case SO_TIMESTAMPING_NEW: 2824 if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) 2825 return -EINVAL; 2826 2827 tsflags = *(u32 *)CMSG_DATA(cmsg); 2828 if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) 2829 return -EINVAL; 2830 2831 sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; 2832 sockc->tsflags |= tsflags; 2833 break; 2834 case SCM_TXTIME: 2835 if (!sock_flag(sk, SOCK_TXTIME)) 2836 return -EINVAL; 2837 if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64))) 2838 return -EINVAL; 2839 sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg)); 2840 break; 2841 /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ 2842 case SCM_RIGHTS: 2843 case SCM_CREDENTIALS: 2844 break; 2845 case SCM_ZC_NOTIFICATION: { 2846 struct zc_info_elem zc_info_kern[SOCK_ZC_INFO_MAX]; 2847 int cmsg_data_len, zc_info_elem_num; 2848 struct sk_buff_head *q, local_q; 2849 struct sock_exterr_skb *serr; > 2850 struct sk_buff *skb, *tmp; 2851 void __user *usr_addr; 2852 unsigned long flags; 2853 int ret, i = 0; 2854 2855 if (!sock_flag(sk, SOCK_ZEROCOPY) || sk->sk_family == PF_RDS) 2856 return -EINVAL; 2857 2858 cmsg_data_len = cmsg->cmsg_len - sizeof(struct cmsghdr); 2859 if (cmsg_data_len % sizeof(struct zc_info_elem)) 2860 return -EINVAL; 2861 2862 zc_info_elem_num = cmsg_data_len / sizeof(struct zc_info_elem); 2863 if (!zc_info_elem_num || zc_info_elem_num > SOCK_ZC_INFO_MAX) 2864 return -EINVAL; 2865 2866 if (in_compat_syscall()) 2867 usr_addr = compat_ptr(*(compat_uptr_t *)CMSG_DATA(cmsg)); 2868 else 2869 usr_addr = (void __user *)*(void **)CMSG_DATA(cmsg); 2870 if (!access_ok(usr_addr, cmsg_data_len)) 2871 return -EFAULT; 2872 2873 q = &sk->sk_error_queue; 2874 skb_queue_head_init(&local_q); 2875 spin_lock_irqsave(&q->lock, flags); 2876 skb = skb_peek(q); 2877 while (skb && i < zc_info_elem_num) { 2878 struct sk_buff *skb_next = skb_peek_next(skb, q); 2879 2880 serr = SKB_EXT_ERR(skb); 2881 if (serr->ee.ee_errno == 0 && 2882 serr->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY) { 2883 zc_info_kern[i].hi = serr->ee.ee_data; 2884 zc_info_kern[i].lo = serr->ee.ee_info; 2885 zc_info_kern[i].zerocopy = !(serr->ee.ee_code 2886 & SO_EE_CODE_ZEROCOPY_COPIED); 2887 __skb_unlink(skb, q); 2888 __skb_queue_tail(&local_q, skb); 2889 i++; 2890 } 2891 skb = skb_next; 2892 } 2893 spin_unlock_irqrestore(&q->lock, flags); 2894 2895 ret = copy_to_user(usr_addr, 2896 zc_info_kern, 2897 i * sizeof(struct zc_info_elem)); 2898 2899 if (unlikely(ret)) { 2900 spin_lock_irqsave(&q->lock, flags); 2901 skb_queue_splice_init(&local_q, q); 2902 spin_unlock_irqrestore(&q->lock, flags); 2903 return -EFAULT; 2904 } 2905 2906 while ((skb = __skb_dequeue(&local_q))) 2907 consume_skb(skb); 2908 break; 2909 } 2910 default: 2911 return -EINVAL; 2912 } 2913 return 0; 2914 } 2915 EXPORT_SYMBOL(__sock_cmsg_send); 2916
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/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..16911bca45f3 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 64 + +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 8d6e638b5426..eafa98c70d9a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2842,6 +2842,71 @@ 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[SOCK_ZC_INFO_MAX]; + int cmsg_data_len, zc_info_elem_num; + struct sk_buff_head *q, local_q; + struct sock_exterr_skb *serr; + struct sk_buff *skb, *tmp; + void __user *usr_addr; + unsigned long flags; + int ret, 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; + + if (in_compat_syscall()) + usr_addr = compat_ptr(*(compat_uptr_t *)CMSG_DATA(cmsg)); + else + usr_addr = (void __user *)*(void **)CMSG_DATA(cmsg); + if (!access_ok(usr_addr, cmsg_data_len)) + return -EFAULT; + + q = &sk->sk_error_queue; + skb_queue_head_init(&local_q); + 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); + __skb_queue_tail(&local_q, skb); + i++; + } + skb = skb_next; + } + spin_unlock_irqrestore(&q->lock, flags); + + ret = copy_to_user(usr_addr, + zc_info_kern, + i * sizeof(struct zc_info_elem)); + + if (unlikely(ret)) { + spin_lock_irqsave(&q->lock, flags); + skb_queue_splice_init(&local_q, q); + spin_unlock_irqrestore(&q->lock, flags); + return -EFAULT; + } + + while ((skb = __skb_dequeue(&local_q))) + consume_skb(skb); + break; + } default: return -EINVAL; }