On Thu, Apr 26, 2018 at 10:50 AM, Eric Dumazet wrote:
> After prior kernel change, mmap() on TCP socket only reserves VMA.
>
> We have to use getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...)
> to perform the transfert of pages from skbs in TCP receive queue into such
> VMA.
>
> struct tcp_zerocopy_receive {
> __u64 address; /* in: address of mapping */
> __u32 length; /* in/out: number of bytes to map/mapped */
> __u32 recv_skip_hint; /* out: amount of bytes to skip */
> };
>
> After a successful getsockopt(...TCP_ZEROCOPY_RECEIVE...), @length contains
> number of bytes that were mapped, and @recv_skip_hint contains number of bytes
> that should be read using conventional read()/recv()/recvmsg() system calls,
> to skip a sequence of bytes that can not be mapped, because not properly page
> aligned.
>
> Signed-off-by: Eric Dumazet
> Cc: Andy Lutomirski
> Cc: Soheil Hassas Yeganeh
Acked-by: Soheil Hassas Yeganeh
Thank you, again!
> ---
> tools/testing/selftests/net/tcp_mmap.c | 64 +++---
> 1 file changed, 37 insertions(+), 27 deletions(-)
>
> diff --git a/tools/testing/selftests/net/tcp_mmap.c
> b/tools/testing/selftests/net/tcp_mmap.c
> index
> dea342fe6f4e88b5709d2ac37b2fc9a2a320bf44..77f762780199ff1f69f9f6b3f18e72deddb69f5e
> 100644
> --- a/tools/testing/selftests/net/tcp_mmap.c
> +++ b/tools/testing/selftests/net/tcp_mmap.c
> @@ -76,9 +76,10 @@
> #include
> #include
> #include
> -#include
> #include
> #include
> +#include
> +#include
>
> #ifndef MSG_ZEROCOPY
> #define MSG_ZEROCOPY0x400
> @@ -134,11 +135,12 @@ void hash_zone(void *zone, unsigned int length)
> void *child_thread(void *arg)
> {
> unsigned long total_mmap = 0, total = 0;
> + struct tcp_zerocopy_receive zc;
> unsigned long delta_usec;
> int flags = MAP_SHARED;
> struct timeval t0, t1;
> char *buffer = NULL;
> - void *oaddr = NULL;
> + void *addr = NULL;
> double throughput;
> struct rusage ru;
> int lu, fd;
> @@ -153,41 +155,46 @@ void *child_thread(void *arg)
> perror("malloc");
> goto error;
> }
> + if (zflg) {
> + addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0);
> + if (addr == (void *)-1)
> + zflg = 0;
> + }
> while (1) {
> struct pollfd pfd = { .fd = fd, .events = POLLIN, };
> int sub;
>
> poll(, 1, 1);
> if (zflg) {
> - void *naddr;
> + socklen_t zc_len = sizeof(zc);
> + int res;
>
> - naddr = mmap(oaddr, chunk_size, PROT_READ, flags, fd,
> 0);
> - if (naddr == (void *)-1) {
> - if (errno == EAGAIN) {
> - /* That is if SO_RCVLOWAT is buggy */
> - usleep(1000);
> - continue;
> - }
> - if (errno == EINVAL) {
> - flags = MAP_SHARED;
> - oaddr = NULL;
> - goto fallback;
> - }
> - if (errno != EIO)
> - perror("mmap()");
> + zc.address = (__u64)addr;
> + zc.length = chunk_size;
> + zc.recv_skip_hint = 0;
> + res = getsockopt(fd, IPPROTO_TCP,
> TCP_ZEROCOPY_RECEIVE,
> +, _len);
> + if (res == -1)
> break;
> +
> + if (zc.length) {
> + assert(zc.length <= chunk_size);
> + total_mmap += zc.length;
> + if (xflg)
> + hash_zone(addr, zc.length);
> + total += zc.length;
> }
> - total_mmap += chunk_size;
> - if (xflg)
> - hash_zone(naddr, chunk_size);
> - total += chunk_size;
> - if (!keepflag) {
> - flags |= MAP_FIXED;
> - oaddr = naddr;
> + if (zc.recv_skip_hint) {
> + assert(zc.recv_skip_hint <= chunk_size);
> + lu = read(fd, buffer, zc.recv_skip_hint);
> + if (lu > 0) {
> +