[PATCH AUTOSEL 5.2 024/249] selftests/bpf: adjust verifier scale test

[PATCH AUTOSEL 5.2 024/249] selftests/bpf: adjust verifier scale test

[Sasha Levin]

From: Alexei Starovoitov <ast@kernel.org>

[ Upstream commit 7c0c6095d48dcd0e67c917aa73cdbb2715aafc36 ]

Adjust scale tests to check for new jmp sequence limit.

BPF_JGT had to be changed to BPF_JEQ because the verifier was
too smart. It tracked the known safe range of R0 values
and pruned the search earlier before hitting exact 8192 limit.
bpf_semi_rand_get() was too (un)?lucky.

k = 0; was missing in bpf_fill_scale2.
It was testing a bit shorter sequence of jumps than intended.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 31 +++++++++++----------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 288cb740e005..6438d4dc8ae1 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -207,33 +207,35 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	self->retval = (uint32_t)res;
 }
 
-/* test the sequence of 1k jumps */
+#define MAX_JMP_SEQ 8192
+
+/* test the sequence of 8k jumps */
 static void bpf_fill_scale1(struct bpf_test *self)
 {
 	struct bpf_insn *insn = self->fill_insns;
 	int i = 0, k = 0;
 
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
-	/* test to check that the sequence of 1024 jumps is acceptable */
-	while (k++ < 1024) {
+	/* test to check that the long sequence of jumps is acceptable */
+	while (k++ < MAX_JMP_SEQ) {
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 					 BPF_FUNC_get_prandom_u32);
-		insn[i++] = BPF_JMP_IMM(BPF_JGT, BPF_REG_0, bpf_semi_rand_get(), 2);
+		insn[i++] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, bpf_semi_rand_get(), 2);
 		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_10);
 		insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6,
 					-8 * (k % 64 + 1));
 	}
-	/* every jump adds 1024 steps to insn_processed, so to stay exactly
-	 * within 1m limit add MAX_TEST_INSNS - 1025 MOVs and 1 EXIT
+	/* every jump adds 1 step to insn_processed, so to stay exactly
+	 * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT
 	 */
-	while (i < MAX_TEST_INSNS - 1025)
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
 		insn[i++] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 42);
 	insn[i] = BPF_EXIT_INSN();
 	self->prog_len = i + 1;
 	self->retval = 42;
 }
 
-/* test the sequence of 1k jumps in inner most function (function depth 8)*/
+/* test the sequence of 8k jumps in inner most function (function depth 8)*/
 static void bpf_fill_scale2(struct bpf_test *self)
 {
 	struct bpf_insn *insn = self->fill_insns;
@@ -245,19 +247,20 @@ static void bpf_fill_scale2(struct bpf_test *self)
 		insn[i++] = BPF_EXIT_INSN();
 	}
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
-	/* test to check that the sequence of 1024 jumps is acceptable */
-	while (k++ < 1024) {
+	/* test to check that the long sequence of jumps is acceptable */
+	k = 0;
+	while (k++ < MAX_JMP_SEQ) {
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 					 BPF_FUNC_get_prandom_u32);
-		insn[i++] = BPF_JMP_IMM(BPF_JGT, BPF_REG_0, bpf_semi_rand_get(), 2);
+		insn[i++] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, bpf_semi_rand_get(), 2);
 		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_10);
 		insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6,
 					-8 * (k % (64 - 4 * FUNC_NEST) + 1));
 	}
-	/* every jump adds 1024 steps to insn_processed, so to stay exactly
-	 * within 1m limit add MAX_TEST_INSNS - 1025 MOVs and 1 EXIT
+	/* every jump adds 1 step to insn_processed, so to stay exactly
+	 * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT
 	 */
-	while (i < MAX_TEST_INSNS - 1025)
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
 		insn[i++] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 42);
 	insn[i] = BPF_EXIT_INSN();
 	self->prog_len = i + 1;
-- 
2.20.1

[PATCH AUTOSEL 5.2 085/249] selftests/bpf : clean up feature/ when make clean

[Sasha Levin]

From: Hechao Li <hechaol@fb.com>

[ Upstream commit 89cceaa939171fafa153d4bf637b39e396bbd785 ]

An error "implicit declaration of function 'reallocarray'" can be thrown
with the following steps:

$ cd tools/testing/selftests/bpf
$ make clean && make CC=<Path to GCC 4.8.5>
$ make clean && make CC=<Path to GCC 7.x>

The cause is that the feature folder generated by GCC 4.8.5 is not
removed, leaving feature-reallocarray being 1, which causes reallocarray
not defined when re-compliing with GCC 7.x. This diff adds feature
folder to EXTRA_CLEAN to avoid this problem.

v2: Rephrase the commit message.

Signed-off-by: Hechao Li <hechaol@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e36356e2377e..1c9511262947 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -275,4 +275,5 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES)
 		 ) > $(VERIFIER_TESTS_H))
 
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \
-	$(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H)
+	$(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) \
+	feature
-- 
2.20.1

[PATCH AUTOSEL 5.2 095/249] bpf: silence warning messages in core

[Sasha Levin]

From: Valdis Klētnieks <valdis.kletnieks@vt.edu>

[ Upstream commit aee450cbe482a8c2f6fa5b05b178ef8b8ff107ca ]

Compiling kernel/bpf/core.c with W=1 causes a flood of warnings:

kernel/bpf/core.c:1198:65: warning: initialized field overwritten [-Woverride-init]
 1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
      |                                                                 ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
 1087 |  INSN_3(ALU, ADD,  X),   \
      |  ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
 1202 |   BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
      |   ^~~~~~~~~~~~
kernel/bpf/core.c:1198:65: note: (near initialization for 'public_insntable[12]')
 1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
      |                                                                 ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
 1087 |  INSN_3(ALU, ADD,  X),   \
      |  ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
 1202 |   BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
      |   ^~~~~~~~~~~~

98 copies of the above.

The attached patch silences the warnings, because we *know* we're overwriting
the default initializer. That leaves bpf/core.c with only 6 other warnings,
which become more visible in comparison.

Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 4c2fa3ac56f6..29d781061cd5 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
+CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
-- 
2.20.1

[PATCH AUTOSEL 5.2 124/249] bpf: fix callees pruning callers

[Sasha Levin]

From: Alexei Starovoitov <ast@kernel.org>

[ Upstream commit eea1c227b9e9bad295e8ef984004a9acf12bb68c ]

The commit 7640ead93924 partially resolved the issue of callees
incorrectly pruning the callers.
With introduction of bounded loops and jmps_processed heuristic
single verifier state may contain multiple branches and calls.
It's possible that new verifier state (for future pruning) will be
allocated inside callee. Then callee will exit (still within the same
verifier state). It will go back to the caller and there R6-R9 registers
will be read and will trigger mark_reg_read. But the reg->live for all frames
but the top frame is not set to LIVE_NONE. Hence mark_reg_read will fail
to propagate liveness into parent and future walking will incorrectly
conclude that the states are equivalent because LIVE_READ is not set.
In other words the rule for parent/live should be:
whenever register parentage chain is set the reg->live should be set to LIVE_NONE.
is_state_visited logic already follows this rule for spilled registers.

Fixes: 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences")
Fixes: f4d7e40a5b71 ("bpf: introduce function calls (verification)")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/verifier.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a5c369e60343..11528bdaa9dc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6456,17 +6456,18 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	 * the state of the call instruction (with WRITTEN set), and r0 comes
 	 * from callee with its full parentage chain, anyway.
 	 */
-	for (j = 0; j <= cur->curframe; j++)
-		for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++)
-			cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i];
 	/* clear write marks in current state: the writes we did are not writes
 	 * our child did, so they don't screen off its reads from us.
 	 * (There are no read marks in current state, because reads always mark
 	 * their parent and current state never has children yet.  Only
 	 * explored_states can get read marks.)
 	 */
-	for (i = 0; i < BPF_REG_FP; i++)
-		cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE;
+	for (j = 0; j <= cur->curframe; j++) {
+		for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++)
+			cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i];
+		for (i = 0; i < BPF_REG_FP; i++)
+			cur->frame[j]->regs[i].live = REG_LIVE_NONE;
+	}
 
 	/* all stack frames are accessible from callee, clear them all */
 	for (j = 0; j <= cur->curframe; j++) {
-- 
2.20.1

[PATCH AUTOSEL 5.2 175/249] xsk: Properly terminate assignment in xskq_produce_flush_desc

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit f7019b7b0ad14bde732b8953161994edfc384953 ]

Clang warns:

In file included from net/xdp/xsk_queue.c:10:
net/xdp/xsk_queue.h:292:2: warning: expression result unused
[-Wunused-value]
        WRITE_ONCE(q->ring->producer, q->prod_tail);
        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/compiler.h:284:6: note: expanded from macro 'WRITE_ONCE'
        __u.__val;                                      \
        ~~~ ^~~~~
1 warning generated.

The q->prod_tail assignment has a comma at the end, not a semi-colon.
Fix that so clang no longer warns and everything works as expected.

Fixes: c497176cb2e4 ("xsk: add Rx receive functions and poll support")
Link: https://github.com/ClangBuiltLinux/linux/issues/544
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/xdp/xsk_queue.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 88b9ae24658d..cba4a640d5e8 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -288,7 +288,7 @@ static inline void xskq_produce_flush_desc(struct xsk_queue *q)
 	/* Order producer and data */
 	smp_wmb(); /* B, matches C */
 
-	q->prod_tail = q->prod_head,
+	q->prod_tail = q->prod_head;
 	WRITE_ONCE(q->ring->producer, q->prod_tail);
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.2 177/249] bpf: fix BPF_ALU32 | BPF_ARSH on BE arches

[Sasha Levin]

From: Jiong Wang <jiong.wang@netronome.com>

[ Upstream commit 75672dda27bd00109a84cd975c17949ad9c45663 ]

Yauheni reported the following code do not work correctly on BE arches:

       ALU_ARSH_X:
               DST = (u64) (u32) ((*(s32 *) &DST) >> SRC);
               CONT;
       ALU_ARSH_K:
               DST = (u64) (u32) ((*(s32 *) &DST) >> IMM);
               CONT;

and are causing failure of test_verifier test 'arsh32 on imm 2' on BE
arches.

The code is taking address and interpreting memory directly, so is not
endianness neutral. We should instead perform standard C type casting on
the variable. A u64 to s32 conversion will drop the high 32-bit and reserve
the low 32-bit as signed integer, this is all we want.

Fixes: 2dc6b100f928 ("bpf: interpreter support BPF_ALU | BPF_ARSH")
Reported-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 080e2bb644cc..f2148db91439 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1364,10 +1364,10 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 		insn++;
 		CONT;
 	ALU_ARSH_X:
-		DST = (u64) (u32) ((*(s32 *) &DST) >> SRC);
+		DST = (u64) (u32) (((s32) DST) >> SRC);
 		CONT;
 	ALU_ARSH_K:
-		DST = (u64) (u32) ((*(s32 *) &DST) >> IMM);
+		DST = (u64) (u32) (((s32) DST) >> IMM);
 		CONT;
 	ALU64_ARSH_X:
 		(*(s64 *) &DST) >>= SRC;
-- 
2.20.1

[PATCH AUTOSEL 5.2 189/249] net/mlx5e: Attach/detach XDP program safely

[Sasha Levin]

From: Maxim Mikityanskiy <maximmi@mellanox.com>

[ Upstream commit e18953240de8b46360a67090c87ee1ef8160b35d ]

When an XDP program is set, a full reopen of all channels happens in two
cases:

1. When there was no program set, and a new one is being set.

2. When there was a program set, but it's being unset.

The full reopen is necessary, because the channel parameters may change
if XDP is enabled or disabled. However, it's performed in an unsafe way:
if the new channels fail to open, the old ones are already closed, and
the interface goes down. Use the safe way to switch channels instead.
The same way is already used for other configuration changes.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 31 ++++++++++++-------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a8e8350b38aa..8db9fdbc03ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4192,8 +4192,6 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* no need for full reset when exchanging programs */
 	reset = (!priv->channels.params.xdp_prog || !prog);
 
-	if (was_opened && reset)
-		mlx5e_close_locked(netdev);
 	if (was_opened && !reset) {
 		/* num_channels is invariant here, so we can take the
 		 * batched reference right upfront.
@@ -4205,20 +4203,31 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		}
 	}
 
-	/* exchange programs, extra prog reference we got from caller
-	 * as long as we don't fail from this point onwards.
-	 */
-	old_prog = xchg(&priv->channels.params.xdp_prog, prog);
+	if (was_opened && reset) {
+		struct mlx5e_channels new_channels = {};
+
+		new_channels.params = priv->channels.params;
+		new_channels.params.xdp_prog = prog;
+		mlx5e_set_rq_type(priv->mdev, &new_channels.params);
+		old_prog = priv->channels.params.xdp_prog;
+
+		err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+		if (err)
+			goto unlock;
+	} else {
+		/* exchange programs, extra prog reference we got from caller
+		 * as long as we don't fail from this point onwards.
+		 */
+		old_prog = xchg(&priv->channels.params.xdp_prog, prog);
+	}
+
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
-	if (reset) /* change RQ type according to priv->xdp_prog */
+	if (!was_opened && reset) /* change RQ type according to priv->xdp_prog */
 		mlx5e_set_rq_type(priv->mdev, &priv->channels.params);
 
-	if (was_opened && reset)
-		err = mlx5e_open_locked(netdev);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
+	if (!was_opened || reset)
 		goto unlock;
 
 	/* exchanging programs w/o reset, we update ref counts on behalf
-- 
2.20.1

[PATCH AUTOSEL 5.2 207/249] ixgbe: Avoid NULL pointer dereference with VF on non-IPsec hw

[Sasha Levin]

From: Dann Frazier <dann.frazier@canonical.com>

[ Upstream commit 92924064106e410cdc015f1dbfc0499309f9f5b1 ]

An ipsec structure will not be allocated if the hardware does not support
offload. Fixes the following Oops:

[  191.045452] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[  191.054232] Mem abort info:
[  191.057014]   ESR = 0x96000004
[  191.060057]   Exception class = DABT (current EL), IL = 32 bits
[  191.065963]   SET = 0, FnV = 0
[  191.069004]   EA = 0, S1PTW = 0
[  191.072132] Data abort info:
[  191.074999]   ISV = 0, ISS = 0x00000004
[  191.078822]   CM = 0, WnR = 0
[  191.081780] user pgtable: 4k pages, 48-bit VAs, pgdp = 0000000043d9e467
[  191.088382] [0000000000000000] pgd=0000000000000000
[  191.093252] Internal error: Oops: 96000004 [#1] SMP
[  191.098119] Modules linked in: vhost_net vhost tap vfio_pci vfio_virqfd vfio_iommu_type1 vfio xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ipt_REJECT nf_reject_ipv4 xt_tcpudp bridge stp llc ebtable_filter devlink ebtables ip6table_filter ip6_tables iptable_filter bpfilter ipmi_ssif nls_iso8859_1 input_leds joydev ipmi_si hns_roce_hw_v2 ipmi_devintf hns_roce ipmi_msghandler cppc_cpufreq sch_fq_codel ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ip_tables x_tables autofs4 ses enclosure btrfs zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor hid_generic usbhid hid raid6_pq libcrc32c raid1 raid0 multipath linear ixgbevf hibmc_drm ttm
[  191.168607]  drm_kms_helper aes_ce_blk aes_ce_cipher syscopyarea crct10dif_ce sysfillrect ghash_ce qla2xxx sysimgblt sha2_ce sha256_arm64 hisi_sas_v3_hw fb_sys_fops sha1_ce uas nvme_fc mpt3sas ixgbe drm hisi_sas_main nvme_fabrics usb_storage hclge scsi_transport_fc ahci libsas hnae3 raid_class libahci xfrm_algo scsi_transport_sas mdio aes_neon_bs aes_neon_blk crypto_simd cryptd aes_arm64
[  191.202952] CPU: 94 PID: 0 Comm: swapper/94 Not tainted 4.19.0-rc1+ #11
[  191.209553] Hardware name: Huawei D06 /D06, BIOS Hisilicon D06 UEFI RC0 - V1.20.01 04/26/2019
[  191.218064] pstate: 20400089 (nzCv daIf +PAN -UAO)
[  191.222873] pc : ixgbe_ipsec_vf_clear+0x60/0xd0 [ixgbe]
[  191.228093] lr : ixgbe_msg_task+0x2d0/0x1088 [ixgbe]
[  191.233044] sp : ffff000009b3bcd0
[  191.236346] x29: ffff000009b3bcd0 x28: 0000000000000000
[  191.241647] x27: ffff000009628000 x26: 0000000000000000
[  191.246946] x25: ffff803f652d7600 x24: 0000000000000004
[  191.252246] x23: ffff803f6a718900 x22: 0000000000000000
[  191.257546] x21: 0000000000000000 x20: 0000000000000000
[  191.262845] x19: 0000000000000000 x18: 0000000000000000
[  191.268144] x17: 0000000000000000 x16: 0000000000000000
[  191.273443] x15: 0000000000000000 x14: 0000000100000026
[  191.278742] x13: 0000000100000025 x12: ffff8a5f7fbe0df0
[  191.284042] x11: 000000010000000b x10: 0000000000000040
[  191.289341] x9 : 0000000000001100 x8 : ffff803f6a824fd8
[  191.294640] x7 : ffff803f6a825098 x6 : 0000000000000001
[  191.299939] x5 : ffff000000f0ffc0 x4 : 0000000000000000
[  191.305238] x3 : ffff000028c00000 x2 : ffff803f652d7600
[  191.310538] x1 : 0000000000000000 x0 : ffff000000f205f0
[  191.315838] Process swapper/94 (pid: 0, stack limit = 0x00000000addfed5a)
[  191.322613] Call trace:
[  191.325055]  ixgbe_ipsec_vf_clear+0x60/0xd0 [ixgbe]
[  191.329927]  ixgbe_msg_task+0x2d0/0x1088 [ixgbe]
[  191.334536]  ixgbe_msix_other+0x274/0x330 [ixgbe]
[  191.339233]  __handle_irq_event_percpu+0x78/0x270
[  191.343924]  handle_irq_event_percpu+0x40/0x98
[  191.348355]  handle_irq_event+0x50/0xa8
[  191.352180]  handle_fasteoi_irq+0xbc/0x148
[  191.356263]  generic_handle_irq+0x34/0x50
[  191.360259]  __handle_domain_irq+0x68/0xc0
[  191.364343]  gic_handle_irq+0x84/0x180
[  191.368079]  el1_irq+0xe8/0x180
[  191.371208]  arch_cpu_idle+0x30/0x1a8
[  191.374860]  do_idle+0x1dc/0x2a0
[  191.378077]  cpu_startup_entry+0x2c/0x30
[  191.381988]  secondary_start_kernel+0x150/0x1e0
[  191.386506] Code: 6b15003f 54000320 f1404a9f 54000060 (79400260)

Fixes: eda0333ac2930 ("ixgbe: add VF IPsec management")
Signed-off-by: Dann Frazier <dann.frazier@canonical.com>
Acked-by: Shannon Nelson <snelson@pensando.io>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index ff85ce5791a3..31629fc7e820 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -842,6 +842,9 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	int i;
 
+	if (!ipsec)
+		return;
+
 	/* search rx sa table */
 	for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_rx_sa; i++) {
 		if (!ipsec->rx_tbl[i].used)
-- 
2.20.1

[PATCH AUTOSEL 5.2 209/249] bpf: fix uapi bpf_prog_info fields alignment

[Sasha Levin]

From: Baruch Siach <baruch@tkos.co.il>

[ Upstream commit 0472301a28f6cf53a6bc5783e48a2d0bbff4682f ]

Merge commit 1c8c5a9d38f60 ("Merge
git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next") undid the
fix from commit 36f9814a494 ("bpf: fix uapi hole for 32 bit compat
applications") by taking the gpl_compatible 1-bit field definition from
commit b85fab0e67b162 ("bpf: Add gpl_compatible flag to struct
bpf_prog_info") as is. That breaks architectures with 16-bit alignment
like m68k. Add 31-bit pad after gpl_compatible to restore alignment of
following fields.

Thanks to Dmitry V. Levin his analysis of this bug history.

Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/uapi/linux/bpf.h       | 1 +
 tools/include/uapi/linux/bpf.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a8b823c30b43..29a5bc3d5c66 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3143,6 +3143,7 @@ struct bpf_prog_info {
 	char name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
 	__u32 gpl_compatible:1;
+	__u32 :31; /* alignment pad */
 	__u64 netns_dev;
 	__u64 netns_ino;
 	__u32 nr_jited_ksyms;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a8b823c30b43..29a5bc3d5c66 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3143,6 +3143,7 @@ struct bpf_prog_info {
 	char name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
 	__u32 gpl_compatible:1;
+	__u32 :31; /* alignment pad */
 	__u64 netns_dev;
 	__u64 netns_ino;
 	__u32 nr_jited_ksyms;
-- 
2.20.1

[PATCH AUTOSEL 5.2 224/249] libbpf: fix GCC8 warning for strncpy

[Sasha Levin]

From: Andrii Nakryiko <andriin@fb.com>

[ Upstream commit cdfc7f888c2a355b01308e97c6df108f1c2b64e8 ]

GCC8 started emitting warning about using strncpy with number of bytes
exactly equal destination size, which is generally unsafe, as can lead
to non-zero terminated string being copied. Use IFNAMSIZ - 1 as number
of bytes to ensure name is always zero-terminated.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/xsk.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 38667b62f1fe..8a7a05bc657d 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -337,7 +337,8 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 
 	channels.cmd = ETHTOOL_GCHANNELS;
 	ifr.ifr_data = (void *)&channels;
-	strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ);
+	strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
+	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
 	err = ioctl(fd, SIOCETHTOOL, &ifr);
 	if (err && errno != EOPNOTSUPP) {
 		ret = -errno;
-- 
2.20.1

[PATCH AUTOSEL 5.2 225/249] bpf, libbpf, smatch: Fix potential NULL pointer dereference

[Sasha Levin]

From: Leo Yan <leo.yan@linaro.org>

[ Upstream commit 33bae185f74d49a0d7b1bfaafb8e959efce0f243 ]

Based on the following report from Smatch, fix the potential NULL
pointer dereference check:

  tools/lib/bpf/libbpf.c:3493
  bpf_prog_load_xattr() warn: variable dereferenced before check 'attr'
  (see line 3483)

  3479 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
  3480                         struct bpf_object **pobj, int *prog_fd)
  3481 {
  3482         struct bpf_object_open_attr open_attr = {
  3483                 .file           = attr->file,
  3484                 .prog_type      = attr->prog_type,
                                         ^^^^^^
  3485         };

At the head of function, it directly access 'attr' without checking
if it's NULL pointer. This patch moves the values assignment after
validating 'attr' and 'attr->file'.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/libbpf.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 151f7ac1882e..3865a5d27251 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3487,10 +3487,7 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			struct bpf_object **pobj, int *prog_fd)
 {
-	struct bpf_object_open_attr open_attr = {
-		.file		= attr->file,
-		.prog_type	= attr->prog_type,
-	};
+	struct bpf_object_open_attr open_attr = {};
 	struct bpf_program *prog, *first_prog = NULL;
 	enum bpf_attach_type expected_attach_type;
 	enum bpf_prog_type prog_type;
@@ -3503,6 +3500,9 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	if (!attr->file)
 		return -EINVAL;
 
+	open_attr.file = attr->file;
+	open_attr.prog_type = attr->prog_type;
+
 	obj = bpf_object__open_xattr(&open_attr);
 	if (IS_ERR_OR_NULL(obj))
 		return -ENOENT;
-- 
2.20.1

[PATCH AUTOSEL 5.2 226/249] selftests: bpf: fix inlines in test_lwt_seg6local

[Sasha Levin]

From: Jiri Benc <jbenc@redhat.com>

[ Upstream commit 11aca65ec4db09527d3e9b6b41a0615b7da4386b ]

Selftests are reporting this failure in test_lwt_seg6local.sh:

+ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2
Error fetching program/map!
Failed to parse eBPF program: Operation not permitted

The problem is __attribute__((always_inline)) alone is not enough to prevent
clang from inserting those functions in .text. In that case, .text is not
marked as relocateable.

See the output of objdump -h test_lwt_seg6local.o:

Idx Name          Size      VMA               LMA               File off  Algn
  0 .text         00003530  0000000000000000  0000000000000000  00000040  2**3
                  CONTENTS, ALLOC, LOAD, READONLY, CODE

This causes the iproute bpf loader to fail in bpf_fetch_prog_sec:
bpf_has_call_data returns true but bpf_fetch_prog_relo fails as there's no
relocateable .text section in the file.

To fix this, convert to 'static __always_inline'.

v2: Use 'static __always_inline' instead of 'static inline
    __attribute__((always_inline))'

Fixes: c99a84eac026 ("selftests/bpf: test for seg6local End.BPF action")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../testing/selftests/bpf/progs/test_lwt_seg6local.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 0575751bc1bc..e2f6ed0a583d 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
@@ -61,7 +61,7 @@ struct sr6_tlv_t {
 	unsigned char value[0];
 } BPF_PACKET_HEADER;
 
-__attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
+static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb)
 {
 	void *cursor, *data_end;
 	struct ip6_srh_t *srh;
@@ -95,7 +95,7 @@ __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
 	return srh;
 }
 
-__attribute__((always_inline))
+static __always_inline
 int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
 		   uint32_t old_pad, uint32_t pad_off)
 {
@@ -125,7 +125,7 @@ int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
 	return 0;
 }
 
-__attribute__((always_inline))
+static __always_inline
 int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
 			  uint32_t *tlv_off, uint32_t *pad_size,
 			  uint32_t *pad_off)
@@ -184,7 +184,7 @@ int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
 	return 0;
 }
 
-__attribute__((always_inline))
+static __always_inline
 int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
 	    struct sr6_tlv_t *itlv, uint8_t tlv_size)
 {
@@ -228,7 +228,7 @@ int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
 	return update_tlv_pad(skb, new_pad, pad_size, pad_off);
 }
 
-__attribute__((always_inline))
+static __always_inline
 int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
 	       uint32_t tlv_off)
 {
@@ -266,7 +266,7 @@ int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
 	return update_tlv_pad(skb, new_pad, pad_size, pad_off);
 }
 
-__attribute__((always_inline))
+static __always_inline
 int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh)
 {
 	int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) +
-- 
2.20.1

Re: [PATCH AUTOSEL 5.2 226/249] selftests: bpf: fix inlines in test_lwt_seg6local

[Jiri Benc]

On Mon, 15 Jul 2019 09:46:31 -0400, Sasha Levin wrote:
> From: Jiri Benc <jbenc@redhat.com>
> 
> [ Upstream commit 11aca65ec4db09527d3e9b6b41a0615b7da4386b ]
> 
> Selftests are reporting this failure in test_lwt_seg6local.sh:

I don't think this is critical in any way and I don't think this is a
stable material. How was this selected?

 Jiri

Re: [PATCH AUTOSEL 5.2 226/249] selftests: bpf: fix inlines in test_lwt_seg6local

[Sasha Levin]

On Wed, Jul 17, 2019 at 11:43:34AM +0200, Jiri Benc wrote:
>On Mon, 15 Jul 2019 09:46:31 -0400, Sasha Levin wrote:
>> From: Jiri Benc <jbenc@redhat.com>
>>
>> [ Upstream commit 11aca65ec4db09527d3e9b6b41a0615b7da4386b ]
>>
>> Selftests are reporting this failure in test_lwt_seg6local.sh:
>
>I don't think this is critical in any way and I don't think this is a
>stable material. How was this selected?

It fixes a bug, right?

--
Thanks,
Sasha

Re: [PATCH AUTOSEL 5.2 226/249] selftests: bpf: fix inlines in test_lwt_seg6local

[Jiri Benc]

On Wed, 17 Jul 2019 19:47:57 -0400, Sasha Levin wrote:
> It fixes a bug, right?

A bug in selftests. And quite likely, it probably happens only with
some compiler versions.

I don't think patches only touching tools/testing/selftests/ qualify
for stable in general. They don't affect the end users.

 Jiri

Re: [PATCH AUTOSEL 5.2 226/249] selftests: bpf: fix inlines in test_lwt_seg6local

[David Miller]

From: Jiri Benc <jbenc@redhat.com>
Date: Thu, 18 Jul 2019 09:36:54 +0200

> On Wed, 17 Jul 2019 19:47:57 -0400, Sasha Levin wrote:
>> It fixes a bug, right?
> 
> A bug in selftests. And quite likely, it probably happens only with
> some compiler versions.
> 
> I don't think patches only touching tools/testing/selftests/ qualify
> for stable in general. They don't affect the end users.

It has a significant impact on automated testing which lots of
individuals and entities perform, therefore I think it very much is
-stable material.

Re: [PATCH AUTOSEL 5.2 226/249] selftests: bpf: fix inlines in test_lwt_seg6local

[Jiri Benc]

On Thu, 18 Jul 2019 11:55:34 -0700 (PDT), David Miller wrote:
> It has a significant impact on automated testing which lots of
> individuals and entities perform, therefore I think it very much is
> -stable material.

Okay.

Thanks,

 Jiri

Re: [PATCH AUTOSEL 5.2 226/249] selftests: bpf: fix inlines in test_lwt_seg6local

[Sasha Levin]

On Thu, Jul 18, 2019 at 09:36:54AM +0200, Jiri Benc wrote:
>On Wed, 17 Jul 2019 19:47:57 -0400, Sasha Levin wrote:
>> It fixes a bug, right?
>
>A bug in selftests. And quite likely, it probably happens only with
>some compiler versions.
>
>I don't think patches only touching tools/testing/selftests/ qualify
>for stable in general. They don't affect the end users.

I'd argue that a bug in your tests is just as (if not even more) worse
than a bug in the code.

--
Thanks,
Sasha

[PATCH AUTOSEL 5.2 231/249] tools: bpftool: Fix json dump crash on powerpc

[Sasha Levin]

From: Jiri Olsa <jolsa@redhat.com>

[ Upstream commit aa52bcbe0e72fac36b1862db08b9c09c4caefae3 ]

Michael reported crash with by bpf program in json mode on powerpc:

  # bpftool prog -p dump jited id 14
  [{
        "name": "0xd00000000a9aa760",
        "insns": [{
                "pc": "0x0",
                "operation": "nop",
                "operands": [null
                ]
            },{
                "pc": "0x4",
                "operation": "nop",
                "operands": [null
                ]
            },{
                "pc": "0x8",
                "operation": "mflr",
  Segmentation fault (core dumped)

The code is assuming char pointers in format, which is not always
true at least for powerpc. Fixing this by dumping the whole string
into buffer based on its format.

Please note that libopcodes code does not check return values from
fprintf callback, but as per Jakub suggestion returning -1 on allocation
failure so we do the best effort to propagate the error.

Fixes: 107f041212c1 ("tools: bpftool: add JSON output for `bpftool prog dump jited *` command")
Reported-by: Michael Petlan <mpetlan@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/bpf/bpftool/jit_disasm.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index 3ef3093560ba..bfed711258ce 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -11,6 +11,8 @@
  * Licensed under the GNU General Public License, version 2.0 (GPLv2)
  */
 
+#define _GNU_SOURCE
+#include <stdio.h>
 #include <stdarg.h>
 #include <stdint.h>
 #include <stdio.h>
@@ -44,11 +46,13 @@ static int fprintf_json(void *out, const char *fmt, ...)
 	char *s;
 
 	va_start(ap, fmt);
+	if (vasprintf(&s, fmt, ap) < 0)
+		return -1;
+	va_end(ap);
+
 	if (!oper_count) {
 		int i;
 
-		s = va_arg(ap, char *);
-
 		/* Strip trailing spaces */
 		i = strlen(s) - 1;
 		while (s[i] == ' ')
@@ -61,11 +65,10 @@ static int fprintf_json(void *out, const char *fmt, ...)
 	} else if (!strcmp(fmt, ",")) {
 		   /* Skip */
 	} else {
-		s = va_arg(ap, char *);
 		jsonw_string(json_wtr, s);
 		oper_count++;
 	}
-	va_end(ap);
+	free(s);
 	return 0;
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.2 248/249] xdp: fix race on generic receive path

[Sasha Levin]

From: Ilya Maximets <i.maximets@samsung.com>

[ Upstream commit bf0bdd1343efbbf65b4d53aef1fce14acbd79d50 ]

Unlike driver mode, generic xdp receive could be triggered
by different threads on different CPU cores at the same time
leading to the fill and rx queue breakage. For example, this
could happen while sending packets from two processes to the
first interface of veth pair while the second part of it is
open with AF_XDP socket.

Need to take a lock for each generic receive to avoid race.

Fixes: c497176cb2e4 ("xsk: add Rx receive functions and poll support")
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Tested-by: William Tu <u9012063@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/xdp_sock.h |  2 ++
 net/xdp/xsk.c          | 31 ++++++++++++++++++++++---------
 2 files changed, 24 insertions(+), 9 deletions(-)

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index d074b6d60f8a..ac3c047d058c 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -67,6 +67,8 @@ struct xdp_sock {
 	 * in the SKB destructor callback.
 	 */
 	spinlock_t tx_completion_lock;
+	/* Protects generic receive. */
+	spinlock_t rx_lock;
 	u64 rx_dropped;
 };
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index a14e8864e4fa..5e0637db92ea 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -123,13 +123,17 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u64 addr;
 	int err;
 
-	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
-		return -EINVAL;
+	spin_lock_bh(&xs->rx_lock);
+
+	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 
 	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
 	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
-		xs->rx_dropped++;
-		return -ENOSPC;
+		err = -ENOSPC;
+		goto out_drop;
 	}
 
 	addr += xs->umem->headroom;
@@ -138,13 +142,21 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	memcpy(buffer, xdp->data_meta, len + metalen);
 	addr += metalen;
 	err = xskq_produce_batch_desc(xs->rx, addr, len);
-	if (!err) {
-		xskq_discard_addr(xs->umem->fq);
-		xsk_flush(xs);
-		return 0;
-	}
+	if (err)
+		goto out_drop;
+
+	xskq_discard_addr(xs->umem->fq);
+	xskq_produce_flush_desc(xs->rx);
 
+	spin_unlock_bh(&xs->rx_lock);
+
+	xs->sk.sk_data_ready(&xs->sk);
+	return 0;
+
+out_drop:
 	xs->rx_dropped++;
+out_unlock:
+	spin_unlock_bh(&xs->rx_lock);
 	return err;
 }
 
@@ -765,6 +777,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	xs = xdp_sk(sk);
 	mutex_init(&xs->mutex);
+	spin_lock_init(&xs->rx_lock);
 	spin_lock_init(&xs->tx_completion_lock);
 
 	mutex_lock(&net->xdp.lock);
-- 
2.20.1