Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add the ability to use unaligned chunks in the AF_XDP umem. By
   relaxing where the chunks can be placed, it allows to use an
   arbitrary buffer size and place whenever there is a free
   address in the umem. Helps more seamless DPDK AF_XDP driver
   integration. Support for i40e, ixgbe and mlx5e, from Kevin and
   Maxim.

2) Addition of a wakeup flag for AF_XDP tx and fill rings so the
   application can wake up the kernel for rx/tx processing which
   avoids busy-spinning of the latter, useful when app and driver
   is located on the same core. Support for i40e, ixgbe and mlx5e,
   from Magnus and Maxim.

3) bpftool fixes for printf()-like functions so compiler can actually
   enforce checks, bpftool build system improvements for custom output
   directories, and addition of 'bpftool map freeze' command, from Quentin.

4) Support attaching/detaching XDP programs from 'bpftool net' command,
   from Daniel.

5) Automatic xskmap cleanup when AF_XDP socket is released, and several
   barrier/{read,write}_once fixes in AF_XDP code, from Björn.

6) Relicense of bpf_helpers.h/bpf_endian.h for future libbpf
   inclusion as well as libbpf versioning improvements, from Andrii.

7) Several new BPF kselftests for verifier precision tracking, from Alexei.

8) Several BPF kselftest fixes wrt endianess to run on s390x, from Ilya.

9) And more BPF kselftest improvements all over the place, from Stanislav.

10) Add simple BPF map op cache for nfp driver to batch dumps, from Jakub.

11) AF_XDP socket umem mapping improvements for 32bit archs, from Ivan.

12) Add BPF-to-BPF call and BTF line info support for s390x JIT, from Yauheni.

13) Small optimization in arm64 JIT to spare 1 insns for BPF_MOD, from Jerin.

14) Fix an error check in bpf_tcp_gen_syncookie() helper, from Petar.

15) Various minor fixes and cleanups, from Nathan, Masahiro, Masanari,
    Peter, Wei, Yue.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller
2019-09-06 16:49:17 +02:00
124 changed files with 3492 additions and 701 deletions

View File

@@ -1,9 +1,10 @@
# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
# Most of this file is copied from tools/lib/traceevent/Makefile
BPF_VERSION = 0
BPF_PATCHLEVEL = 0
BPF_EXTRAVERSION = 4
LIBBPF_VERSION := $(shell \
grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \
sort -rV | head -n1 | cut -d'_' -f2)
LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
MAKEFLAGS += --no-print-directory
@@ -79,15 +80,9 @@ export prefix libdir src obj
libdir_SQ = $(subst ','\'',$(libdir))
libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
VERSION = $(BPF_VERSION)
PATCHLEVEL = $(BPF_PATCHLEVEL)
EXTRAVERSION = $(BPF_EXTRAVERSION)
OBJ = $@
N =
LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION)
LIB_FILE = libbpf.a libbpf.so*
PC_FILE = libbpf.pc
@@ -113,6 +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 =
@@ -138,7 +134,9 @@ LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE))
GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \
sort -u | wc -l)
VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
@@ -178,10 +176,10 @@ $(BPF_IN): force elfdep bpfdep
$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
-Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
@ln -sf $(@F) $(OUTPUT)libbpf.so
@ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
@ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
$(OUTPUT)libbpf.a: $(BPF_IN)
$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
@@ -205,6 +203,7 @@ check_abi: $(OUTPUT)libbpf.so
"Please make sure all LIBBPF_API symbols are" \
"versioned in $(VERSION_SCRIPT)." >&2; \
readelf -s --wide $(OUTPUT)libbpf-in.o | \
cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \
sort -u > $(OUTPUT)libbpf_global_syms.tmp; \
readelf -s --wide $(OUTPUT)libbpf.so | \
@@ -257,7 +256,8 @@ config-clean:
clean:
$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
*.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd *.pc LIBBPF-CFLAGS
*.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
*.pc LIBBPF-CFLAGS
$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf

View File

@@ -568,7 +568,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
return ret;
}
int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
{
union bpf_attr attr;
int err;
@@ -576,26 +576,26 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
memset(&attr, 0, sizeof(attr));
attr.start_id = start_id;
err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr));
err = sys_bpf(cmd, &attr, sizeof(attr));
if (!err)
*next_id = attr.next_id;
return err;
}
int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
{
return bpf_obj_get_next_id(start_id, next_id, BPF_PROG_GET_NEXT_ID);
}
int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
{
union bpf_attr attr;
int err;
return bpf_obj_get_next_id(start_id, next_id, BPF_MAP_GET_NEXT_ID);
}
memset(&attr, 0, sizeof(attr));
attr.start_id = start_id;
err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr));
if (!err)
*next_id = attr.next_id;
return err;
int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id)
{
return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID);
}
int bpf_prog_get_fd_by_id(__u32 id)

View File

@@ -156,6 +156,7 @@ LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
__u32 *retval, __u32 *duration);
LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);

View File

@@ -183,4 +183,10 @@ LIBBPF_0.0.4 {
perf_buffer__new;
perf_buffer__new_raw;
perf_buffer__poll;
xsk_umem__create;
} LIBBPF_0.0.3;
LIBBPF_0.0.5 {
global:
bpf_btf_get_next_id;
} LIBBPF_0.0.4;

View File

@@ -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;
@@ -116,6 +99,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
cfg->comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
cfg->flags = XSK_UMEM__DEFAULT_FLAGS;
return;
}
@@ -123,6 +107,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
cfg->comp_size = usr_cfg->comp_size;
cfg->frame_size = usr_cfg->frame_size;
cfg->frame_headroom = usr_cfg->frame_headroom;
cfg->flags = usr_cfg->flags;
}
static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
@@ -149,9 +134,10 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
return 0;
}
int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
struct xsk_ring_prod *fill, struct xsk_ring_cons *comp,
const struct xsk_umem_config *usr_config)
int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
__u64 size, struct xsk_ring_prod *fill,
struct xsk_ring_cons *comp,
const struct xsk_umem_config *usr_config)
{
struct xdp_mmap_offsets off;
struct xdp_umem_reg mr;
@@ -182,6 +168,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
mr.len = size;
mr.chunk_size = umem->config.frame_size;
mr.headroom = umem->config.frame_headroom;
mr.flags = umem->config.flags;
err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr));
if (err) {
@@ -210,10 +197,9 @@ 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;
@@ -224,13 +210,13 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
fill->size = umem->config.fill_size;
fill->producer = map + off.fr.producer;
fill->consumer = map + off.fr.consumer;
fill->flags = map + off.fr.flags;
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;
@@ -241,6 +227,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
comp->size = umem->config.comp_size;
comp->producer = map + off.cr.producer;
comp->consumer = map + off.cr.consumer;
comp->flags = map + off.cr.flags;
comp->ring = map + off.cr.desc;
*umem_ptr = umem;
@@ -255,6 +242,29 @@ out_umem_alloc:
return err;
}
struct xsk_umem_config_v1 {
__u32 fill_size;
__u32 comp_size;
__u32 frame_size;
__u32 frame_headroom;
};
int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
__u64 size, struct xsk_ring_prod *fill,
struct xsk_ring_cons *comp,
const struct xsk_umem_config *usr_config)
{
struct xsk_umem_config config;
memcpy(&config, usr_config, sizeof(struct xsk_umem_config_v1));
config.flags = 0;
return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp,
&config);
}
asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2");
asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4");
static int xsk_load_xdp_prog(struct xsk_socket *xsk)
{
static const int log_buf_size = 16 * 1024;
@@ -550,11 +560,10 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
}
if (rx) {
rx_map = xsk_mmap(NULL, off.rx.desc +
xsk->config.rx_size * sizeof(struct xdp_desc),
PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_POPULATE,
xsk->fd, XDP_PGOFF_RX_RING);
rx_map = mmap(NULL, off.rx.desc +
xsk->config.rx_size * sizeof(struct xdp_desc),
PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
xsk->fd, XDP_PGOFF_RX_RING);
if (rx_map == MAP_FAILED) {
err = -errno;
goto out_socket;
@@ -564,16 +573,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
rx->size = xsk->config.rx_size;
rx->producer = rx_map + off.rx.producer;
rx->consumer = rx_map + off.rx.consumer;
rx->flags = rx_map + off.rx.flags;
rx->ring = rx_map + off.rx.desc;
}
xsk->rx = rx;
if (tx) {
tx_map = xsk_mmap(NULL, off.tx.desc +
xsk->config.tx_size * sizeof(struct xdp_desc),
PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_POPULATE,
xsk->fd, XDP_PGOFF_TX_RING);
tx_map = mmap(NULL, off.tx.desc +
xsk->config.tx_size * sizeof(struct xdp_desc),
PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
xsk->fd, XDP_PGOFF_TX_RING);
if (tx_map == MAP_FAILED) {
err = -errno;
goto out_mmap_rx;
@@ -583,6 +592,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
tx->size = xsk->config.tx_size;
tx->producer = tx_map + off.tx.producer;
tx->consumer = tx_map + off.tx.consumer;
tx->flags = tx_map + off.tx.flags;
tx->ring = tx_map + off.tx.desc;
tx->cached_cons = xsk->config.tx_size;
}

View File

@@ -32,6 +32,7 @@ struct name { \
__u32 *producer; \
__u32 *consumer; \
void *ring; \
__u32 *flags; \
}
DEFINE_XSK_RING(xsk_ring_prod);
@@ -76,6 +77,11 @@ xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx)
return &descs[idx & rx->mask];
}
static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r)
{
return *r->flags & XDP_RING_NEED_WAKEUP;
}
static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
{
__u32 free_entries = r->cached_cons - r->cached_prod;
@@ -162,6 +168,21 @@ static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
return &((char *)umem_area)[addr];
}
static inline __u64 xsk_umem__extract_addr(__u64 addr)
{
return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
}
static inline __u64 xsk_umem__extract_offset(__u64 addr)
{
return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
}
static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr)
{
return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr);
}
LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem);
LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
@@ -170,12 +191,14 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */
#define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0
#define XSK_UMEM__DEFAULT_FLAGS 0
struct xsk_umem_config {
__u32 fill_size;
__u32 comp_size;
__u32 frame_size;
__u32 frame_headroom;
__u32 flags;
};
/* Flags for the libbpf_flags field. */
@@ -195,6 +218,16 @@ LIBBPF_API int xsk_umem__create(struct xsk_umem **umem,
struct xsk_ring_prod *fill,
struct xsk_ring_cons *comp,
const struct xsk_umem_config *config);
LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
void *umem_area, __u64 size,
struct xsk_ring_prod *fill,
struct xsk_ring_cons *comp,
const struct xsk_umem_config *config);
LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
void *umem_area, __u64 size,
struct xsk_ring_prod *fill,
struct xsk_ring_cons *comp,
const struct xsk_umem_config *config);
LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk,
const char *ifname, __u32 queue_id,
struct xsk_umem *umem,