Commit 71dd77fd authored by Ivan Khoronzhuk's avatar Ivan Khoronzhuk Committed by Daniel Borkmann
Browse files

libbpf: use LFS (_FILE_OFFSET_BITS) instead of direct mmap2 syscall 



Drop __NR_mmap2 fork in flavor of LFS, that is _FILE_OFFSET_BITS=64
(glibc & bionic) / LARGEFILE64_SOURCE (for musl) decision. It allows
mmap() to use 64bit offset that is passed to mmap2 syscall. As result
pgoff is not truncated and no need to use direct access to mmap2 for
32 bits systems.

Signed-off-by: default avatarIvan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Acked-by: default avatarYonghong Song <yhs@fb.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
parent 51746f94

tools/lib/bpf/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -108,6 +108,7 @@ override CFLAGS += -Werror -Wall 
override CFLAGS += -fPIC

override CFLAGS += $(INCLUDES)

override CFLAGS += -fvisibility=hidden

override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64



ifeq ($(VERBOSE),1)

  Q =

tools/lib/bpf/xsk.c

+14 −35
Original line number Diff line number Diff line
@@ -74,23 +74,6 @@ struct xsk_nl_info { 
	int fd;

};



/* For 32-bit systems, we need to use mmap2 as the offsets are 64-bit.

 * Unfortunately, it is not part of glibc.

 */

static inline void *xsk_mmap(void *addr, size_t length, int prot, int flags,

			     int fd, __u64 offset)

{

#ifdef __NR_mmap2

	unsigned int page_shift = __builtin_ffs(getpagesize()) - 1;

	long ret = syscall(__NR_mmap2, addr, length, prot, flags, fd,

			   (off_t)(offset >> page_shift));



	return (void *)ret;

#else

	return mmap(addr, length, prot, flags, fd, offset);

#endif

}



int xsk_umem__fd(const struct xsk_umem *umem)

{

	return umem ? umem->fd : -EINVAL;
@@ -210,10 +193,9 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, 
		goto out_socket;

	}



	map = xsk_mmap(NULL, off.fr.desc +

		       umem->config.fill_size * sizeof(__u64),

		       PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,

		       umem->fd, XDP_UMEM_PGOFF_FILL_RING);

	map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64),

		   PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd,

		   XDP_UMEM_PGOFF_FILL_RING);

	if (map == MAP_FAILED) {

		err = -errno;

		goto out_socket;
@@ -228,10 +210,9 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, 
	fill->ring = map + off.fr.desc;

	fill->cached_cons = umem->config.fill_size;



	map = xsk_mmap(NULL,

		       off.cr.desc + umem->config.comp_size * sizeof(__u64),

		       PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,

		       umem->fd, XDP_UMEM_PGOFF_COMPLETION_RING);

	map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64),

		   PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd,

		   XDP_UMEM_PGOFF_COMPLETION_RING);

	if (map == MAP_FAILED) {

		err = -errno;

		goto out_mmap;
@@ -552,10 +533,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, 
	}



	if (rx) {

		rx_map = xsk_mmap(NULL, off.rx.desc +

		rx_map = mmap(NULL, off.rx.desc +

			      xsk->config.rx_size * sizeof(struct xdp_desc),

				  PROT_READ | PROT_WRITE,

				  MAP_SHARED | MAP_POPULATE,

			      PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,

			      xsk->fd, XDP_PGOFF_RX_RING);

		if (rx_map == MAP_FAILED) {

			err = -errno;
@@ -572,10 +552,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, 
	xsk->rx = rx;



	if (tx) {

		tx_map = xsk_mmap(NULL, off.tx.desc +

		tx_map = mmap(NULL, off.tx.desc +

			      xsk->config.tx_size * sizeof(struct xdp_desc),

				  PROT_READ | PROT_WRITE,

				  MAP_SHARED | MAP_POPULATE,

			      PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,

			      xsk->fd, XDP_PGOFF_TX_RING);

		if (tx_map == MAP_FAILED) {

			err = -errno;

CRA Git | Maintained and supported by SUSTech CRA and CCSE