lkml.org 
[lkml]   [2018]   [Apr]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH net-next 2/2] selftests: net: tcp_mmap must use TCP_ZEROCOPY_RECEIVE
Date
After prior kernel change, mmap() on TCP socket only reserves VMA.

We have to use setsockopt(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 setsockopt(...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 <edumazet@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
---
tools/testing/selftests/net/tcp_mmap.c | 63 +++++++++++++++-----------
1 file changed, 36 insertions(+), 27 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index dea342fe6f4e88b5709d2ac37b2fc9a2a320bf44..5b381cdbdd6319556ba4e3dad530fae8f13f5a9b 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -76,9 +76,10 @@
#include <time.h>
#include <sys/time.h>
#include <netinet/in.h>
-#include <netinet/tcp.h>
#include <arpa/inet.h>
#include <poll.h>
+#include <linux/tcp.h>
+#include <assert.h>

#ifndef MSG_ZEROCOPY
#define MSG_ZEROCOPY 0x4000000
@@ -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 +155,45 @@ 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(&pfd, 1, 10000);
if (zflg) {
- void *naddr;
+ 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 = setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
+ &zc, sizeof(zc));
+ 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) {
+ if (xflg)
+ hash_zone(buffer, lu);
+ total += lu;
+ }
}
continue;
}
-fallback:
sub = 0;
while (sub < chunk_size) {
lu = read(fd, buffer + sub, chunk_size - sub);
@@ -228,6 +234,8 @@ void *child_thread(void *arg)
error:
free(buffer);
close(fd);
+ if (zflg)
+ munmap(addr, chunk_size);
pthread_exit(0);
}

@@ -371,7 +379,8 @@ int main(int argc, char *argv[])
setup_sockaddr(cfg_family, host, &listenaddr);

if (mss &&
- setsockopt(fdlisten, SOL_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
+ setsockopt(fdlisten, IPPROTO_TCP, TCP_MAXSEG,
+ &mss, sizeof(mss)) == -1) {
perror("setsockopt TCP_MAXSEG");
exit(1);
}
@@ -402,7 +411,7 @@ int main(int argc, char *argv[])
setup_sockaddr(cfg_family, host, &addr);

if (mss &&
- setsockopt(fd, SOL_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
+ setsockopt(fd, IPPROTO_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
perror("setsockopt TCP_MAXSEG");
exit(1);
}
--
2.17.0.484.g0c8726318c-goog
\
 
 \ /
  Last update: 2018-04-25 07:28    [W:0.086 / U:0.644 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site