* [PATCH bpf-next v2 5/8] bpf, arm64: save 4 bytes of unneeded stack space
From: Daniel Borkmann @ 2018-05-14 21:22 UTC (permalink / raw)
To: alexei.starovoitov; +Cc: netdev, Daniel Borkmann
In-Reply-To: <20180514212234.2661-1-daniel@iogearbox.net>
Follow-up to 816d9ef32a8b ("bpf, arm64: remove ld_abs/ld_ind") in
that the extra 4 byte JIT scratchpad is not needed anymore since it
was in ld_abs/ld_ind as stack buffer for bpf_load_pointer().
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
arch/arm64/net/bpf_jit_comp.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 0b40c8f..85113ca 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -21,7 +21,6 @@
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/printk.h>
-#include <linux/skbuff.h>
#include <linux/slab.h>
#include <asm/byteorder.h>
@@ -188,7 +187,7 @@ static int build_prologue(struct jit_ctx *ctx)
* | ... | BPF prog stack
* | |
* +-----+ <= (BPF_FP - prog->aux->stack_depth)
- * |RSVD | JIT scratchpad
+ * |RSVD | padding
* current A64_SP => +-----+ <= (BPF_FP - ctx->stack_size)
* | |
* | ... | Function call stack
@@ -220,9 +219,7 @@ static int build_prologue(struct jit_ctx *ctx)
return -1;
}
- /* 4 byte extra for skb_copy_bits buffer */
- ctx->stack_size = prog->aux->stack_depth + 4;
- ctx->stack_size = STACK_ALIGN(ctx->stack_size);
+ ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);
/* Set up function call stack */
emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next v2 7/8] bpf, arm64: save 4 bytes in prologue when ebpf insns came from cbpf
From: Daniel Borkmann @ 2018-05-14 21:22 UTC (permalink / raw)
To: alexei.starovoitov; +Cc: netdev, Daniel Borkmann
In-Reply-To: <20180514212234.2661-1-daniel@iogearbox.net>
We can trivially save 4 bytes in prologue for cBPF since tail calls
can never be used from there. The register push/pop is pairwise,
here, x25 (fp) and x26 (tcc), so no point in changing that, only
reset to zero is not needed.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
arch/arm64/net/bpf_jit_comp.c | 23 +++++++++++++----------
1 file changed, 13 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index c8a2620..a6fdaea 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -185,7 +185,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
/* Tail call offset to jump into */
#define PROLOGUE_OFFSET 7
-static int build_prologue(struct jit_ctx *ctx)
+static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
{
const struct bpf_prog *prog = ctx->prog;
const u8 r6 = bpf2a64[BPF_REG_6];
@@ -232,14 +232,16 @@ static int build_prologue(struct jit_ctx *ctx)
/* Set up BPF prog stack base register */
emit(A64_MOV(1, fp, A64_SP), ctx);
- /* Initialize tail_call_cnt */
- emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+ if (!ebpf_from_cbpf) {
+ /* Initialize tail_call_cnt */
+ emit(A64_MOVZ(1, tcc, 0, 0), ctx);
- cur_offset = ctx->idx - idx0;
- if (cur_offset != PROLOGUE_OFFSET) {
- pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
- cur_offset, PROLOGUE_OFFSET);
- return -1;
+ cur_offset = ctx->idx - idx0;
+ if (cur_offset != PROLOGUE_OFFSET) {
+ pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+ cur_offset, PROLOGUE_OFFSET);
+ return -1;
+ }
}
ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);
@@ -806,6 +808,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
struct bpf_prog *tmp, *orig_prog = prog;
struct bpf_binary_header *header;
struct arm64_jit_data *jit_data;
+ bool was_classic = bpf_prog_was_classic(prog);
bool tmp_blinded = false;
bool extra_pass = false;
struct jit_ctx ctx;
@@ -860,7 +863,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
goto out_off;
}
- if (build_prologue(&ctx)) {
+ if (build_prologue(&ctx, was_classic)) {
prog = orig_prog;
goto out_off;
}
@@ -883,7 +886,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
skip_init_ctx:
ctx.idx = 0;
- build_prologue(&ctx);
+ build_prologue(&ctx, was_classic);
if (build_body(&ctx)) {
bpf_jit_binary_free(header);
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next v2 6/8] bpf, arm64: optimize 32/64 immediate emission
From: Daniel Borkmann @ 2018-05-14 21:22 UTC (permalink / raw)
To: alexei.starovoitov; +Cc: netdev, Daniel Borkmann
In-Reply-To: <20180514212234.2661-1-daniel@iogearbox.net>
Improve the JIT to emit 64 and 32 bit immediates, the current
algorithm is not optimal and we often emit more instructions
than actually needed. arm64 has movz, movn, movk variants but
for the current 64 bit immediates we only use movz with a
series of movk when needed.
For example loading ffffffffffffabab emits the following 4
instructions in the JIT today:
* movz: abab, shift: 0, result: 000000000000abab
* movk: ffff, shift: 16, result: 00000000ffffabab
* movk: ffff, shift: 32, result: 0000ffffffffabab
* movk: ffff, shift: 48, result: ffffffffffffabab
Whereas after the patch the same load only needs a single
instruction:
* movn: 5454, shift: 0, result: ffffffffffffabab
Another example where two extra instructions can be saved:
* movz: abab, shift: 0, result: 000000000000abab
* movk: 1f2f, shift: 16, result: 000000001f2fabab
* movk: ffff, shift: 32, result: 0000ffff1f2fabab
* movk: ffff, shift: 48, result: ffffffff1f2fabab
After the patch:
* movn: e0d0, shift: 16, result: ffffffff1f2fffff
* movk: abab, shift: 0, result: ffffffff1f2fabab
Another example with movz, before:
* movz: 0000, shift: 0, result: 0000000000000000
* movk: fea0, shift: 32, result: 0000fea000000000
After:
* movz: fea0, shift: 32, result: 0000fea000000000
Moreover, reuse emit_a64_mov_i() for 32 bit immediates that
are loaded via emit_a64_mov_i64() which is a similar optimization
as done in 6fe8b9c1f41d ("bpf, x64: save several bytes by using
mov over movabsq when possible"). On arm64, the latter allows to
use a single instruction with movn due to zero extension where
otherwise two would be needed. And last but not least add a
missing optimization in emit_a64_mov_i() where movn is used but
the subsequent movk not needed. With some of the Cilium programs
in use, this shrinks the needed instructions by about three
percent. Tested on Cavium ThunderX CN8890.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
arch/arm64/net/bpf_jit_comp.c | 85 +++++++++++++++++++++++++++----------------
1 file changed, 54 insertions(+), 31 deletions(-)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 85113ca..c8a2620 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -79,23 +79,66 @@ static inline void emit(const u32 insn, struct jit_ctx *ctx)
ctx->idx++;
}
+static inline void emit_a64_mov_i(const int is64, const int reg,
+ const s32 val, struct jit_ctx *ctx)
+{
+ u16 hi = val >> 16;
+ u16 lo = val & 0xffff;
+
+ if (hi & 0x8000) {
+ if (hi == 0xffff) {
+ emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
+ } else {
+ emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
+ if (lo != 0xffff)
+ emit(A64_MOVK(is64, reg, lo, 0), ctx);
+ }
+ } else {
+ emit(A64_MOVZ(is64, reg, lo, 0), ctx);
+ if (hi)
+ emit(A64_MOVK(is64, reg, hi, 16), ctx);
+ }
+}
+
+static int i64_i16_blocks(const u64 val, bool inverse)
+{
+ return (((val >> 0) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+ (((val >> 16) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+ (((val >> 32) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+ (((val >> 48) & 0xffff) != (inverse ? 0xffff : 0x0000));
+}
+
static inline void emit_a64_mov_i64(const int reg, const u64 val,
struct jit_ctx *ctx)
{
- u64 tmp = val;
- int shift = 0;
-
- emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
- tmp >>= 16;
- shift += 16;
- while (tmp) {
- if (tmp & 0xffff)
- emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
- tmp >>= 16;
- shift += 16;
+ u64 nrm_tmp = val, rev_tmp = ~val;
+ bool inverse;
+ int shift;
+
+ if (!(nrm_tmp >> 32))
+ return emit_a64_mov_i(0, reg, (u32)val, ctx);
+
+ inverse = i64_i16_blocks(nrm_tmp, true) < i64_i16_blocks(nrm_tmp, false);
+ shift = max(round_down((inverse ? (fls64(rev_tmp) - 1) :
+ (fls64(nrm_tmp) - 1)), 16), 0);
+ if (inverse)
+ emit(A64_MOVN(1, reg, (rev_tmp >> shift) & 0xffff, shift), ctx);
+ else
+ emit(A64_MOVZ(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
+ shift -= 16;
+ while (shift >= 0) {
+ if (((nrm_tmp >> shift) & 0xffff) != (inverse ? 0xffff : 0x0000))
+ emit(A64_MOVK(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
+ shift -= 16;
}
}
+/*
+ * This is an unoptimized 64 immediate emission used for BPF to BPF call
+ * addresses. It will always do a full 64 bit decomposition as otherwise
+ * more complexity in the last extra pass is required since we previously
+ * reserved 4 instructions for the address.
+ */
static inline void emit_addr_mov_i64(const int reg, const u64 val,
struct jit_ctx *ctx)
{
@@ -110,26 +153,6 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
}
}
-static inline void emit_a64_mov_i(const int is64, const int reg,
- const s32 val, struct jit_ctx *ctx)
-{
- u16 hi = val >> 16;
- u16 lo = val & 0xffff;
-
- if (hi & 0x8000) {
- if (hi == 0xffff) {
- emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
- } else {
- emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
- emit(A64_MOVK(is64, reg, lo, 0), ctx);
- }
- } else {
- emit(A64_MOVZ(is64, reg, lo, 0), ctx);
- if (hi)
- emit(A64_MOVK(is64, reg, hi, 16), ctx);
- }
-}
-
static inline int bpf2a64_offset(int bpf_to, int bpf_from,
const struct jit_ctx *ctx)
{
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next v2 8/8] bpf: add ld64 imm test cases
From: Daniel Borkmann @ 2018-05-14 21:22 UTC (permalink / raw)
To: alexei.starovoitov; +Cc: netdev, Daniel Borkmann
In-Reply-To: <20180514212234.2661-1-daniel@iogearbox.net>
Add test cases where we combine semi-random imm values, mainly for testing
JITs when they have different encoding options for 64 bit immediates in
order to reduce resulting image size.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
tools/testing/selftests/bpf/bpf_rand.h | 80 +++++++++++++++++++++++++++++
tools/testing/selftests/bpf/test_verifier.c | 62 ++++++++++++++++++++++
2 files changed, 142 insertions(+)
create mode 100644 tools/testing/selftests/bpf/bpf_rand.h
diff --git a/tools/testing/selftests/bpf/bpf_rand.h b/tools/testing/selftests/bpf/bpf_rand.h
new file mode 100644
index 0000000..59bf3e1
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_rand.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_RAND__
+#define __BPF_RAND__
+
+#include <stdint.h>
+#include <stdlib.h>
+#include <time.h>
+
+static inline uint64_t bpf_rand_mask(uint64_t mask)
+{
+ return (((uint64_t)(uint32_t)rand()) |
+ ((uint64_t)(uint32_t)rand() << 32)) & mask;
+}
+
+#define bpf_rand_ux(x, m) \
+static inline uint64_t bpf_rand_u##x(int shift) \
+{ \
+ return bpf_rand_mask((m)) << shift; \
+}
+
+bpf_rand_ux( 8, 0xffULL)
+bpf_rand_ux(16, 0xffffULL)
+bpf_rand_ux(24, 0xffffffULL)
+bpf_rand_ux(32, 0xffffffffULL)
+bpf_rand_ux(40, 0xffffffffffULL)
+bpf_rand_ux(48, 0xffffffffffffULL)
+bpf_rand_ux(56, 0xffffffffffffffULL)
+bpf_rand_ux(64, 0xffffffffffffffffULL)
+
+static inline void bpf_semi_rand_init(void)
+{
+ srand(time(NULL));
+}
+
+static inline uint64_t bpf_semi_rand_get(void)
+{
+ switch (rand() % 39) {
+ case 0: return 0x000000ff00000000ULL | bpf_rand_u8(0);
+ case 1: return 0xffffffff00000000ULL | bpf_rand_u16(0);
+ case 2: return 0x00000000ffff0000ULL | bpf_rand_u16(0);
+ case 3: return 0x8000000000000000ULL | bpf_rand_u32(0);
+ case 4: return 0x00000000f0000000ULL | bpf_rand_u32(0);
+ case 5: return 0x0000000100000000ULL | bpf_rand_u24(0);
+ case 6: return 0x800ff00000000000ULL | bpf_rand_u32(0);
+ case 7: return 0x7fffffff00000000ULL | bpf_rand_u32(0);
+ case 8: return 0xffffffffffffff00ULL ^ bpf_rand_u32(24);
+ case 9: return 0xffffffffffffff00ULL | bpf_rand_u8(0);
+ case 10: return 0x0000000010000000ULL | bpf_rand_u32(0);
+ case 11: return 0xf000000000000000ULL | bpf_rand_u8(0);
+ case 12: return 0x0000f00000000000ULL | bpf_rand_u8(8);
+ case 13: return 0x000000000f000000ULL | bpf_rand_u8(16);
+ case 14: return 0x0000000000000f00ULL | bpf_rand_u8(32);
+ case 15: return 0x00fff00000000f00ULL | bpf_rand_u8(48);
+ case 16: return 0x00007fffffffffffULL ^ bpf_rand_u32(1);
+ case 17: return 0xffff800000000000ULL | bpf_rand_u8(4);
+ case 18: return 0xffff800000000000ULL | bpf_rand_u8(20);
+ case 19: return (0xffffffc000000000ULL + 0x80000ULL) | bpf_rand_u32(0);
+ case 20: return (0xffffffc000000000ULL - 0x04000000ULL) | bpf_rand_u32(0);
+ case 21: return 0x0000000000000000ULL | bpf_rand_u8(55) | bpf_rand_u32(20);
+ case 22: return 0xffffffffffffffffULL ^ bpf_rand_u8(3) ^ bpf_rand_u32(40);
+ case 23: return 0x0000000000000000ULL | bpf_rand_u8(bpf_rand_u8(0) % 64);
+ case 24: return 0x0000000000000000ULL | bpf_rand_u16(bpf_rand_u8(0) % 64);
+ case 25: return 0xffffffffffffffffULL ^ bpf_rand_u8(bpf_rand_u8(0) % 64);
+ case 26: return 0xffffffffffffffffULL ^ bpf_rand_u40(bpf_rand_u8(0) % 64);
+ case 27: return 0x0000800000000000ULL;
+ case 28: return 0x8000000000000000ULL;
+ case 29: return 0x0000000000000000ULL;
+ case 30: return 0xffffffffffffffffULL;
+ case 31: return bpf_rand_u16(bpf_rand_u8(0) % 64);
+ case 32: return bpf_rand_u24(bpf_rand_u8(0) % 64);
+ case 33: return bpf_rand_u32(bpf_rand_u8(0) % 64);
+ case 34: return bpf_rand_u40(bpf_rand_u8(0) % 64);
+ case 35: return bpf_rand_u48(bpf_rand_u8(0) % 64);
+ case 36: return bpf_rand_u56(bpf_rand_u8(0) % 64);
+ case 37: return bpf_rand_u64(bpf_rand_u8(0) % 64);
+ default: return bpf_rand_u64(0);
+ }
+}
+
+#endif /* __BPF_RAND__ */
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 275b457..a877af0 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -41,6 +41,7 @@
# endif
#endif
#include "bpf_rlimit.h"
+#include "bpf_rand.h"
#include "../../../include/linux/filter.h"
#ifndef ARRAY_SIZE
@@ -152,6 +153,30 @@ static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
insn[i] = BPF_EXIT_INSN();
}
+static void bpf_fill_rand_ld_dw(struct bpf_test *self)
+{
+ struct bpf_insn *insn = self->insns;
+ uint64_t res = 0;
+ int i = 0;
+
+ insn[i++] = BPF_MOV32_IMM(BPF_REG_0, 0);
+ while (i < self->retval) {
+ uint64_t val = bpf_semi_rand_get();
+ struct bpf_insn tmp[2] = { BPF_LD_IMM64(BPF_REG_1, val) };
+
+ res ^= val;
+ insn[i++] = tmp[0];
+ insn[i++] = tmp[1];
+ insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
+ }
+ insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0);
+ insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32);
+ insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
+ insn[i] = BPF_EXIT_INSN();
+ res ^= (res >> 32);
+ self->retval = (uint32_t)res;
+}
+
static struct bpf_test tests[] = {
{
"add+sub+mul",
@@ -11974,6 +11999,42 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
.retval = 10,
},
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 1",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 4090,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 2",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 2047,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 3",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 511,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 4",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 5,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
@@ -12346,5 +12407,6 @@ int main(int argc, char **argv)
return EXIT_FAILURE;
}
+ bpf_semi_rand_init();
return do_test(unpriv, from, to);
}
--
2.9.5
^ permalink raw reply related
* Re: [PATCH ghak81 RFC V2 3/5] audit: use inline function to get audit context
From: Paul Moore @ 2018-05-14 21:44 UTC (permalink / raw)
To: Richard Guy Briggs
Cc: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list, Eric Paris, Steve Grubb, Ingo Molnar, David Howells
In-Reply-To: <baa29a694e352bd4fe8acd0f46f7baca1ad2c147.1526173613.git.rgb@redhat.com>
On Sat, May 12, 2018 at 9:58 PM, Richard Guy Briggs <rgb@redhat.com> wrote:
> Recognizing that the audit context is an internal audit value, use an
> access function to retrieve the audit context pointer for the task
> rather than reaching directly into the task struct to get it.
>
> Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
> ---
> include/linux/audit.h | 14 ++++++--
> include/net/xfrm.h | 2 +-
> kernel/audit.c | 6 ++--
> kernel/audit_watch.c | 2 +-
> kernel/auditsc.c | 64 +++++++++++++++++-------------------
> net/bridge/netfilter/ebtables.c | 2 +-
> net/core/dev.c | 2 +-
> net/netfilter/x_tables.c | 2 +-
> net/netlabel/netlabel_user.c | 2 +-
> security/integrity/ima/ima_api.c | 2 +-
> security/integrity/integrity_audit.c | 2 +-
> security/lsm_audit.c | 2 +-
> security/selinux/hooks.c | 4 +--
> security/selinux/selinuxfs.c | 6 ++--
> security/selinux/ss/services.c | 12 +++----
> 15 files changed, 64 insertions(+), 60 deletions(-)
Merged, but there was some fuzz due to the missing 1/5 patch and a
handfull of checkpatch.pl fixes. Please take a look at the commit in
the audit/next branch and if anything looks awry please send a patch
to fix it.
--
paul moore
www.paul-moore.com
^ permalink raw reply
* Re: [PATCH net-next v3 0/7] Microsemi Ocelot Ethernet switch support
From: James Hogan @ 2018-05-14 21:47 UTC (permalink / raw)
To: Andrew Lunn
Cc: Alexandre Belloni, David S . Miller, Allan Nielsen,
razvan.stefanescu, po.liu, Thomas Petazzoni, Florian Fainelli,
netdev, linux-kernel, linux-mips
In-Reply-To: <20180514205844.GG1057@lunn.ch>
[-- Attachment #1: Type: text/plain, Size: 460 bytes --]
On Mon, May 14, 2018 at 10:58:44PM +0200, Andrew Lunn wrote:
> Hi Alexandre
> >
> > The ocelot dts changes are here for reference and should probably go
> > through the MIPS tree once the bindings are accepted.
>
> For your next version, you probably want to drop those patches, so
> that David can apply the network patches to net-next.
Since it sounds like the net patches are ready now, I'll apply the MIPS
DTS ones for 4.18.
Thanks
James
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply
* Re: [PATCH ghak81 RFC V2 4/5] audit: use inline function to set audit context
From: Paul Moore @ 2018-05-14 21:51 UTC (permalink / raw)
To: Richard Guy Briggs
Cc: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list, Eric Paris, Steve Grubb, Ingo Molnar, David Howells
In-Reply-To: <567735cef55507a38120e30bea178980bb146313.1526173613.git.rgb@redhat.com>
On Sat, May 12, 2018 at 9:58 PM, Richard Guy Briggs <rgb@redhat.com> wrote:
> Recognizing that the audit context is an internal audit value, use an
> access function to set the audit context pointer for the task
> rather than reaching directly into the task struct to set it.
>
> Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
> ---
> include/linux/audit.h | 6 ++++++
> kernel/auditsc.c | 7 +++----
> kernel/fork.c | 2 +-
> 3 files changed, 10 insertions(+), 5 deletions(-)
Merged with some minor fuzz.
--
paul moore
www.paul-moore.com
^ permalink raw reply
* Re: [PATCH ghak81 RFC V2 5/5] audit: collect audit task parameters
From: Paul Moore @ 2018-05-14 21:54 UTC (permalink / raw)
To: Richard Guy Briggs
Cc: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list, Eric Paris, Steve Grubb, Ingo Molnar, David Howells
In-Reply-To: <90031e185e85e5e327aaafb40882d2e3e52ea4c8.1526173613.git.rgb@redhat.com>
On Sat, May 12, 2018 at 9:58 PM, Richard Guy Briggs <rgb@redhat.com> wrote:
> The audit-related parameters in struct task_struct should ideally be
> collected together and accessed through a standard audit API.
>
> Collect the existing loginuid, sessionid and audit_context together in a
> new struct audit_task_info called "audit" in struct task_struct.
>
> See: https://github.com/linux-audit/audit-kernel/issues/81
>
> Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
> ---
> MAINTAINERS | 2 +-
> include/linux/audit.h | 10 +++++-----
> include/linux/audit_task.h | 31 +++++++++++++++++++++++++++++++
> include/linux/sched.h | 6 ++----
> init/init_task.c | 7 +++++--
> kernel/auditsc.c | 6 +++---
> 6 files changed, 47 insertions(+), 15 deletions(-)
> create mode 100644 include/linux/audit_task.h
I'm not going to merge this right now; there is still the question of
static vs dynamic (as mentioned in 0/5) and with the main motivation
being the audit container ID work, I think it would be good to wait
for the next round of those patches before committing to something.
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 0a1410d..8c7992d 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -2510,7 +2510,7 @@ L: linux-audit@redhat.com (moderated for non-subscribers)
> W: https://github.com/linux-audit
> T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git
> S: Supported
> -F: include/linux/audit.h
> +F: include/linux/audit*.h
> F: include/uapi/linux/audit.h
> F: kernel/audit*
>
> diff --git a/include/linux/audit.h b/include/linux/audit.h
> index f7973e4..6d599b6 100644
> --- a/include/linux/audit.h
> +++ b/include/linux/audit.h
> @@ -237,11 +237,11 @@ extern void __audit_inode_child(struct inode *parent,
>
> static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx)
> {
> - task->audit_context = ctx;
> + task->audit.ctx = ctx;
> }
> static inline struct audit_context *audit_context(void)
> {
> - return current->audit_context;
> + return current->audit.ctx;
> }
> static inline bool audit_dummy_context(void)
> {
> @@ -250,7 +250,7 @@ static inline bool audit_dummy_context(void)
> }
> static inline void audit_free(struct task_struct *task)
> {
> - if (unlikely(task->audit_context))
> + if (unlikely(task->audit.ctx))
> __audit_free(task);
> }
> static inline void audit_syscall_entry(int major, unsigned long a0,
> @@ -330,12 +330,12 @@ extern int auditsc_get_stamp(struct audit_context *ctx,
>
> static inline kuid_t audit_get_loginuid(struct task_struct *tsk)
> {
> - return tsk->loginuid;
> + return tsk->audit.loginuid;
> }
>
> static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
> {
> - return tsk->sessionid;
> + return tsk->audit.sessionid;
> }
>
> extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
> diff --git a/include/linux/audit_task.h b/include/linux/audit_task.h
> new file mode 100644
> index 0000000..d4b3a20
> --- /dev/null
> +++ b/include/linux/audit_task.h
> @@ -0,0 +1,31 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/* audit_task.h -- definition of audit_task_info structure
> + *
> + * Copyright 2018 Red Hat Inc., Raleigh, North Carolina.
> + * All Rights Reserved.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * Written by Richard Guy Briggs <rgb@redhat.com>
> + *
> + */
> +
> +#ifndef _LINUX_AUDIT_TASK_H_
> +#define _LINUX_AUDIT_TASK_H_
> +
> +struct audit_context;
> +struct audit_task_info {
> + kuid_t loginuid;
> + unsigned int sessionid;
> + struct audit_context *ctx;
> +};
> +
> +#endif
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index b3d697f..b58eca0 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -27,9 +27,9 @@
> #include <linux/signal_types.h>
> #include <linux/mm_types_task.h>
> #include <linux/task_io_accounting.h>
> +#include <linux/audit_task.h>
>
> /* task_struct member predeclarations (sorted alphabetically): */
> -struct audit_context;
> struct backing_dev_info;
> struct bio_list;
> struct blk_plug;
> @@ -832,10 +832,8 @@ struct task_struct {
>
> struct callback_head *task_works;
>
> - struct audit_context *audit_context;
> #ifdef CONFIG_AUDITSYSCALL
> - kuid_t loginuid;
> - unsigned int sessionid;
> + struct audit_task_info audit;
> #endif
> struct seccomp seccomp;
>
> diff --git a/init/init_task.c b/init/init_task.c
> index 74f60ba..d33260d 100644
> --- a/init/init_task.c
> +++ b/init/init_task.c
> @@ -119,8 +119,11 @@ struct task_struct init_task
> .thread_group = LIST_HEAD_INIT(init_task.thread_group),
> .thread_node = LIST_HEAD_INIT(init_signals.thread_head),
> #ifdef CONFIG_AUDITSYSCALL
> - .loginuid = INVALID_UID,
> - .sessionid = AUDIT_SID_UNSET,
> + .audit = {
> + .loginuid = INVALID_UID,
> + .sessionid = AUDIT_SID_UNSET,
> + .ctx = NULL,
> + },
> #endif
> #ifdef CONFIG_PERF_EVENTS
> .perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
> diff --git a/kernel/auditsc.c b/kernel/auditsc.c
> index d441d68..4c1fd18 100644
> --- a/kernel/auditsc.c
> +++ b/kernel/auditsc.c
> @@ -836,7 +836,7 @@ static inline struct audit_context *audit_take_context(struct task_struct *tsk,
> int return_valid,
> long return_code)
> {
> - struct audit_context *context = tsk->audit_context;
> + struct audit_context *context = tsk->audit.ctx;
>
> if (!context)
> return NULL;
> @@ -2066,8 +2066,8 @@ int audit_set_loginuid(kuid_t loginuid)
> sessionid = (unsigned int)atomic_inc_return(&session_id);
> }
>
> - task->sessionid = sessionid;
> - task->loginuid = loginuid;
> + task->audit.sessionid = sessionid;
> + task->audit.loginuid = loginuid;
> out:
> audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
> return rc;
> --
> 1.8.3.1
>
--
paul moore
www.paul-moore.com
^ permalink raw reply
* Re: linux-next: manual merge of the bpf-next tree with the bpf tree
From: Stephen Rothwell @ 2018-05-14 21:57 UTC (permalink / raw)
To: Jakub Kicinski, Alexei Starovoitov
Cc: Daniel Borkmann, Networking, Linux-Next Mailing List,
Linux Kernel Mailing List
In-Reply-To: <20180514134140.0c468174@cakuba>
[-- Attachment #1: Type: text/plain, Size: 958 bytes --]
Hi Jakub,
On Mon, 14 May 2018 13:41:40 -0700 Jakub Kicinski <jakub.kicinski@netronome.com> wrote:
>
> On Mon, 14 May 2018 11:57:00 +1000, Stephen Rothwell wrote:
> > diff --cc tools/lib/bpf/libbpf.c
> > index 8da4eeb101a6,df54c4c9e48a..000000000000
> > --- a/tools/lib/bpf/libbpf.c
> > +++ b/tools/lib/bpf/libbpf.c
> > @@@ -2163,9 -2193,12 +2193,12 @@@ int bpf_prog_load_xattr(const struct bp
> >
> > if (!attr)
> > return -EINVAL;
> > + if (!attr->file)
> > + return -EINVAL;
> >
> > - obj = bpf_object__open(attr->file);
> > + obj = __bpf_object__open(attr->file, NULL, 0,
> > + bpf_prog_type__needs_kver(attr->prog_type));
> > - if (IS_ERR(obj))
> > + if (IS_ERR_OR_NULL(obj))
> > return -ENOENT;
>
> This is okay, thanks. The OR_NULL is unnecessary just using the
> bpf-next code is a better merge IMO.
Thanks, I have updated my merge resolution from today.
--
Cheers,
Stephen Rothwell
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: [PATCH v1 iproute2-next 2/3] rdma: print driver resource attributes
From: Steve Wise @ 2018-05-14 22:04 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: dsahern, leon, stephen, netdev, linux-rdma
In-Reply-To: <20180514204125.GM21531@ziepe.ca>
On 5/14/2018 3:41 PM, Jason Gunthorpe wrote:
> On Mon, May 07, 2018 at 08:53:16AM -0700, Steve Wise wrote:
>> This enhancement allows printing rdma device-specific state, if provided
>> by the kernel. This is done in a generic manner, so rdma tool doesn't
>> need to know about the details of every type of rdma device.
>>
>> Driver attributes for a rdma resource are in the form of <key,
>> [print_type], value> tuples, where the key is a string and the value can
>> be any supported driver attribute. The print_type attribute, if present,
>> provides a print format to use vs the standard print format for the type.
>> For example, the default print type for a PROVIDER_S32 value is "%d ",
>> but "0x%x " if the print_type of PRINT_TYPE_HEX is included inthe tuple.
>>
>> Driver resources are only printed when the -dd flag is present.
>> If -p is present, then the output is formatted to not exceed 80 columns,
>> otherwise it is printed as a single row to be grep/awk friendly.
>>
>> Example output:
>>
>> # rdma resource show qp lqpn 1028 -dd -p
>> link cxgb4_0/- lqpn 1028 rqpn 0 type RC state RTS rq-psn 0 sq-psn 0 path-mig-state MIGRATED pid 0 comm [nvme_rdma]
>> sqid 1028 flushed 0 memsize 123968 cidx 85 pidx 85 wq_pidx 106 flush_cidx 85 in_use 0
>> size 386 flags 0x0 rqid 1029 memsize 16768 cidx 43 pidx 41 wq_pidx 171 msn 44 rqt_hwaddr 0x2a8a5d00
>> rqt_size 256 in_use 128 size 130 idx 43 wr_id 0xffff881057c03408 idx 40 wr_id 0xffff881057c033f0
> Hey some of these look like kernel pointers.. That is a no-no.. What
> is up there?
Nothing is defined as a kernel pointer. But wr_id is often a pointer to
the kernel rdma application's context...
> The wr_id often contains a pointer, right? So we cannot just pass it
> to user space..
Hmm. It is useful for debugging kernel rdma applications. Perhaps
these attrs can be only be sent up by the kernel if the capabilities
allow. But previous review comments of the kernel series, which is now
merged, forced me to remove passing the capabilities information to the
driver resource fill functions.
So what's the right way to do this?
Steve.
^ permalink raw reply
* maximal supported bit rate in traffic control
From: Eitan Raviv @ 2018-05-14 22:15 UTC (permalink / raw)
To: netdev
Hi,
In RHEVM we use traffic control to enable users to shape their QoS on
the networks they use.
IIUC from the traffic control man page, the maximal bit rate currently
supported (RHEL 7.4) is 2^32 - 1 bytes per sec, which translates to 32
Gibit\s if I have done my maths correctly.
Does anyone know whether there are any plans to support larger bit
rate values upstream or downstream soon or at all?
Thanks a lot
erav
oVirt\RHEVM networking
^ permalink raw reply
* [pull request][net-next 00/16] Mellanox, mlx5e updates 2018-05-14
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
Hi Dave,
The following series contains misc updates for mlx5e netdevice driver.
For more information please see tag log below.
Please pull and let me know if there's any problem.
Thanks,
Saeed.
---
The following changes since commit 7cfac881660ac7b7229950e0a942201be63c15d1:
cxgb4: do not fail vf instatiation in slave mode (2018-05-14 16:42:09 -0400)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux.git tags/mlx5e-updates-2018-05-14
for you to fetch changes up to 0e5c04f6b52b248cfdb7e791fd5702f12270df7b:
net/mlx5e: Remove MLX5E_TEST_BIT macro (2018-05-14 15:10:21 -0700)
----------------------------------------------------------------
mlx5e-updates-2018-05-14
Misc update for mlx5e netdevice driver
>From Gal Pressman:
- Remove MLX5E_TEST_BIT macros and use test_bit instead
- Use __set_bit when possible
>From Eran Ben Elisha:
- Improve debug print on initial RX posting timeout
>From Or Gerlitz:
- Support offloaded TC flows with no matches on headers
- mlx5e TC cleanups
Trivial cleanups From Roi, Tariq and Saeed:
- Use bool as return type for mlx5e_xdp_handle
- Use u8 instead of int for LRO number of segments
- Skip redundant checks when providing NUD lastuse feedback
- Remove redundant vport context vlan update
----------------------------------------------------------------
Eran Ben Elisha (1):
net/mlx5e: Report all channels with min RX WQEs timeout
Gal Pressman (3):
net/mlx5e: Use __set_bit for adaptive-moderation bit in RQ state
net/mlx5e: Use test bit in en accel xmit flow
net/mlx5e: Remove MLX5E_TEST_BIT macro
Or Gerlitz (8):
net/mlx5e: Remove double defined DMAC header re-write element
net/mlx5e: Clean static checker complaints on TC offload and VF reps code
net/mlx5e: Avoid redundant zeroing of offloaded TC flow attributes
net/mlx5e: Return success when TC offloaded fdb actions parsed ok
net/mlx5e: Use local actions var while processing offloaded TC flow actions
net/mlx5e: Properly order min inline mode setup while parsing TC matches
net/mlx5e: Get the required HW match level while parsing TC flow matches
net/mlx5e: Support offloaded TC flows with no matches on headers
Roi Dayan (1):
net/mlx5e: Skip redundant checks when providing NUD lastuse feedback
Saeed Mahameed (1):
net/mlx5e: Remove redundant vport context vlan update
Tariq Toukan (2):
net/mlx5e: Use u8 instead of int for LRO number of segments
net/mlx5e: Use bool as return type for mlx5e_xdp_handle
drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 -
.../mellanox/mlx5/core/en_accel/en_accel.h | 4 +-
drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 1 -
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 25 ++-
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 8 +-
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 19 +-
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 224 ++++++++++++---------
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c | 4 +-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 8 +
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 8 +-
11 files changed, 173 insertions(+), 132 deletions(-)
^ permalink raw reply
* [net-next 02/16] net/mlx5e: Skip redundant checks when providing NUD lastuse feedback
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Roi Dayan, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Roi Dayan <roid@mellanox.com>
It's redundant to continue the loop if we found one flow whose lastuse value
being newer than the last one we reported, since this is enough for us to
trigger a NUD update (neigh_event_send()).
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b94276db3ce9..9b0e3ccffa66 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -982,6 +982,8 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
}
}
}
+ if (neigh_used)
+ break;
}
if (neigh_used) {
--
2.17.0
^ permalink raw reply related
* [net-next 01/16] net/mlx5e: Remove redundant vport context vlan update
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
In delete vlan flow an extra call to mlx5e_vport_context_update_vlans
was added by mistake, remove it.
Fixes: 86d722ad2c3b ("net/mlx5: Use flow steering infrastructure for mlx5_en")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Gal Pressman <galp@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index f64dda2bed31..76cc10e44080 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -277,7 +277,6 @@ static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv,
}
break;
case MLX5E_VLAN_RULE_TYPE_MATCH_CTAG_VID:
- mlx5e_vport_context_update_vlans(priv);
if (priv->fs.vlan.active_cvlans_rule[vid]) {
mlx5_del_flow_rules(priv->fs.vlan.active_cvlans_rule[vid]);
priv->fs.vlan.active_cvlans_rule[vid] = NULL;
--
2.17.0
^ permalink raw reply related
* [net-next 03/16] net/mlx5e: Use u8 instead of int for LRO number of segments
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Tariq Toukan, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Range of LRO number of segments fits in u8.
Also, bring initialization and declaration together to
save code.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7bbf0db27a01..e10422b845ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -681,11 +681,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
struct mlx5e_rq *rq,
struct sk_buff *skb)
{
+ u8 lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
struct net_device *netdev = rq->netdev;
- int lro_num_seg;
skb->mac_len = ETH_HLEN;
- lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
if (lro_num_seg > 1) {
mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
--
2.17.0
^ permalink raw reply related
* [net-next 05/16] net/mlx5e: Remove double defined DMAC header re-write element
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
The firmware DMAC_47_16 header re-write token was defined twice,
clean it up.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9b0e3ccffa66..969a1768da71 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1579,7 +1579,6 @@ struct mlx5_fields {
{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, offsetof(struct pedit_headers, field) + (off)}
static struct mlx5_fields fields[] = {
- OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0),
OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0),
OFFLOAD(DMAC_15_0, 2, eth.h_dest[4], 0),
OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0),
--
2.17.0
^ permalink raw reply related
* [net-next 04/16] net/mlx5e: Use bool as return type for mlx5e_xdp_handle
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Tariq Toukan, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Function returns boolean values, use bool instead of int.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e10422b845ca..abc6ca8168d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -807,9 +807,9 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
}
/* returns true if packet was consumed by xdp */
-static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
- struct mlx5e_dma_info *di,
- void *va, u16 *rx_headroom, u32 *len)
+static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
+ struct mlx5e_dma_info *di,
+ void *va, u16 *rx_headroom, u32 *len)
{
struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
struct xdp_buff xdp;
--
2.17.0
^ permalink raw reply related
* [net-next 06/16] net/mlx5e: Clean static checker complaints on TC offload and VF reps code
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Clean warning/check complaints made by checkpatch on en_{tc,rep}.c
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 8 ++++----
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 11 +++++------
2 files changed, 9 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 876c3e4c6193..a689f4c90fe3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -681,8 +681,8 @@ static int mlx5e_rep_open(struct net_device *dev)
goto unlock;
if (!mlx5_modify_vport_admin_state(priv->mdev,
- MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
- rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
+ MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+ rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
netif_carrier_on(dev);
unlock:
@@ -699,8 +699,8 @@ static int mlx5e_rep_close(struct net_device *dev)
mutex_lock(&priv->state_lock);
mlx5_modify_vport_admin_state(priv->mdev,
- MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
- rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+ MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+ rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
ret = mlx5e_close_locked(dev);
mutex_unlock(&priv->state_lock);
return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 969a1768da71..85ad0948951c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -97,7 +97,7 @@ enum {
};
#define MLX5E_TC_TABLE_NUM_GROUPS 4
-#define MLX5E_TC_TABLE_MAX_GROUP_SIZE (1 << 16)
+#define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(16)
struct mlx5e_hairpin {
struct mlx5_hairpin *pair;
@@ -789,7 +789,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
mlx5_del_flow_rules(flow->rule);
mlx5_fc_destroy(priv->mdev, counter);
- if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
+ if (!mlx5e_tc_num_filters(priv) && priv->fs.tc.t) {
mlx5_destroy_flow_table(priv->fs.tc.t);
priv->fs.tc.t = NULL;
}
@@ -1765,12 +1765,12 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv,
err = -EOPNOTSUPP; /* can't be all optimistic */
if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) {
- printk(KERN_WARNING "mlx5: legacy pedit isn't offloaded\n");
+ netdev_warn(priv->netdev, "legacy pedit isn't offloaded\n");
goto out_err;
}
if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) {
- printk(KERN_WARNING "mlx5: pedit cmd %d isn't offloaded\n", cmd);
+ netdev_warn(priv->netdev, "pedit cmd %d isn't offloaded\n", cmd);
goto out_err;
}
@@ -1794,8 +1794,7 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv,
for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
cmd_masks = &masks[cmd];
if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
- printk(KERN_WARNING "mlx5: attempt to offload an unsupported field (cmd %d)\n",
- cmd);
+ netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd);
print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS,
16, 1, cmd_masks, sizeof(zero_masks), true);
err = -EOPNOTSUPP;
--
2.17.0
^ permalink raw reply related
* [net-next 07/16] net/mlx5e: Avoid redundant zeroing of offloaded TC flow attributes
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
This is not needed as the attributes are zeroed out on allocation.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 85ad0948951c..7d88e813bad1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1923,7 +1923,6 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
return -EINVAL;
attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
- attr->action = 0;
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
@@ -2464,7 +2463,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
if (!tcf_exts_has_actions(exts))
return -EINVAL;
- memset(attr, 0, sizeof(*attr));
attr->in_rep = rpriv->rep;
tcf_exts_to_list(exts, &actions);
--
2.17.0
^ permalink raw reply related
* [net-next 09/16] net/mlx5e: Use local actions var while processing offloaded TC flow actions
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Use local actions variable while parsing the actions of offloaded TC flow.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_tc.c | 44 ++++++++++---------
1 file changed, 24 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index c15bd7b6a840..24b6ca205c74 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1917,6 +1917,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
struct mlx5_nic_flow_attr *attr = flow->nic_attr;
const struct tc_action *a;
LIST_HEAD(actions);
+ u32 action = 0;
int err;
if (!tcf_exts_has_actions(exts))
@@ -1927,10 +1928,10 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
if (is_tcf_gact_shot(a)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
+ action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
if (MLX5_CAP_FLOWTABLE(priv->mdev,
flow_table_properties_nic_receive.flow_counter))
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
continue;
}
@@ -1940,13 +1941,13 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
if (err)
return err;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
continue;
}
if (is_tcf_csum(a)) {
- if (csum_offload_supported(priv, attr->action,
+ if (csum_offload_supported(priv, action,
tcf_csum_update_flags(a)))
continue;
@@ -1960,8 +1961,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
same_hw_devs(priv, netdev_priv(peer_dev))) {
parse_attr->mirred_ifindex = peer_dev->ifindex;
flow->flags |= MLX5E_TC_FLOW_HAIRPIN;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
} else {
netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n",
peer_dev->name);
@@ -1980,13 +1981,14 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
}
attr->flow_tag = mark;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
continue;
}
return -EINVAL;
}
+ attr->action = action;
if (!actions_match_supported(priv, exts, parse_attr, flow))
return -EOPNOTSUPP;
@@ -2458,6 +2460,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
const struct tc_action *a;
LIST_HEAD(actions);
bool encap = false;
+ u32 action = 0;
if (!tcf_exts_has_actions(exts))
return -EINVAL;
@@ -2467,8 +2470,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
if (is_tcf_gact_shot(a)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
continue;
}
@@ -2480,12 +2483,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
if (err)
return err;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
continue;
}
if (is_tcf_csum(a)) {
- if (csum_offload_supported(priv, attr->action,
+ if (csum_offload_supported(priv, action,
tcf_csum_update_flags(a)))
continue;
@@ -2500,8 +2503,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
if (switchdev_port_same_parent_id(priv->netdev,
out_dev)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
out_priv = netdev_priv(out_dev);
rpriv = out_priv->ppriv;
attr->out_rep = rpriv->rep;
@@ -2509,9 +2512,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
parse_attr->mirred_ifindex = out_dev->ifindex;
parse_attr->tun_info = *info;
attr->parse_attr = parse_attr;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
/* attr->out_rep is resolved when we handle encap */
} else {
pr_err("devices %s %s not on same switch HW, can't offload forwarding\n",
@@ -2532,9 +2535,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
if (is_tcf_vlan(a)) {
if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+ action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+ action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
attr->vlan_vid = tcf_vlan_push_vid(a);
if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) {
attr->vlan_prio = tcf_vlan_push_prio(a);
@@ -2552,13 +2555,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
}
if (is_tcf_tunnel_release(a)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
+ action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
continue;
}
return -EINVAL;
}
+ attr->action = action;
if (!actions_match_supported(priv, exts, parse_attr, flow))
return -EOPNOTSUPP;
--
2.17.0
^ permalink raw reply related
* [net-next 08/16] net/mlx5e: Return success when TC offloaded fdb actions parsed ok
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Reaching here, means we didn't err anywhere, so lets just
return success.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 7d88e813bad1..c15bd7b6a840 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2458,7 +2458,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
const struct tc_action *a;
LIST_HEAD(actions);
bool encap = false;
- int err = 0;
if (!tcf_exts_has_actions(exts))
return -EINVAL;
@@ -2474,6 +2473,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
}
if (is_tcf_pedit(a)) {
+ int err;
+
err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
parse_attr);
if (err)
@@ -2561,7 +2562,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
if (!actions_match_supported(priv, exts, parse_attr, flow))
return -EOPNOTSUPP;
- return err;
+ return 0;
}
int mlx5e_configure_flower(struct mlx5e_priv *priv,
--
2.17.0
^ permalink raw reply related
* [net-next 10/16] net/mlx5e: Properly order min inline mode setup while parsing TC matches
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Set the initial value to none instead of L2, and set to L2
where the previous initial value was assumed. Make sure to
parse L2 matches before L3 matches and L3 before L4.
This is a pre-step to get the match level for more purposes
other than the validating the needed vs. actual inline level.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_tc.c | 129 +++++++++++-------
1 file changed, 76 insertions(+), 53 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 24b6ca205c74..78f5c47affb4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1201,7 +1201,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
u16 addr_type = 0;
u8 ip_proto = 0;
- *min_inline = MLX5_INLINE_MODE_L2;
+ *min_inline = MLX5_INLINE_MODE_NONE;
if (f->dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
@@ -1251,58 +1251,6 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
inner_headers);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
- struct flow_dissector_key_control *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_CONTROL,
- f->key);
-
- struct flow_dissector_key_control *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_CONTROL,
- f->mask);
- addr_type = key->addr_type;
-
- /* the HW doesn't support frag first/later */
- if (mask->flags & FLOW_DIS_FIRST_FRAG)
- return -EOPNOTSUPP;
-
- if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
- MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
- key->flags & FLOW_DIS_IS_FRAGMENT);
-
- /* the HW doesn't need L3 inline to match on frag=no */
- if (key->flags & FLOW_DIS_IS_FRAGMENT)
- *min_inline = MLX5_INLINE_MODE_IP;
- }
- }
-
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
- struct flow_dissector_key_basic *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->key);
- struct flow_dissector_key_basic *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->mask);
- ip_proto = key->ip_proto;
-
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
- ntohs(mask->n_proto));
- MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
- ntohs(key->n_proto));
-
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
- mask->ip_proto);
- MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
- key->ip_proto);
-
- if (mask->ip_proto)
- *min_inline = MLX5_INLINE_MODE_IP;
- }
-
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct flow_dissector_key_eth_addrs *key =
skb_flow_dissector_target(f->dissector,
@@ -1326,6 +1274,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
smac_47_16),
key->src);
+
+ if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
+ *min_inline = MLX5_INLINE_MODE_L2;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
@@ -1346,9 +1297,79 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority);
+
+ *min_inline = MLX5_INLINE_MODE_L2;
}
}
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->key);
+ struct flow_dissector_key_basic *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->mask);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
+ ntohs(mask->n_proto));
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+ ntohs(key->n_proto));
+
+ if (mask->n_proto)
+ *min_inline = MLX5_INLINE_MODE_L2;
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+ struct flow_dissector_key_control *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_CONTROL,
+ f->key);
+
+ struct flow_dissector_key_control *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_CONTROL,
+ f->mask);
+ addr_type = key->addr_type;
+
+ /* the HW doesn't support frag first/later */
+ if (mask->flags & FLOW_DIS_FIRST_FRAG)
+ return -EOPNOTSUPP;
+
+ if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
+ key->flags & FLOW_DIS_IS_FRAGMENT);
+
+ /* the HW doesn't need L3 inline to match on frag=no */
+ if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
+ *min_inline = MLX5_INLINE_MODE_L2;
+ /* *** L2 attributes parsing up to here *** */
+ else
+ *min_inline = MLX5_INLINE_MODE_IP;
+ }
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->key);
+ struct flow_dissector_key_basic *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->mask);
+ ip_proto = key->ip_proto;
+
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
+ mask->ip_proto);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
+ key->ip_proto);
+
+ if (mask->ip_proto)
+ *min_inline = MLX5_INLINE_MODE_IP;
+ }
+
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
struct flow_dissector_key_ipv4_addrs *key =
skb_flow_dissector_target(f->dissector,
@@ -1433,6 +1454,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
*min_inline = MLX5_INLINE_MODE_IP;
}
+ /* *** L3 attributes parsing up to here *** */
+
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
struct flow_dissector_key_ports *key =
skb_flow_dissector_target(f->dissector,
--
2.17.0
^ permalink raw reply related
* [net-next 11/16] net/mlx5e: Get the required HW match level while parsing TC flow matches
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Introduce levels of matching on headers of offloaded flows
(none, L2, L3, L4) that follow the inline mode levels.
This is pre-step for us to offload flows without any
matches on headers.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_tc.c | 34 +++++++++----------
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 7 ++++
2 files changed, 24 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 78f5c47affb4..e84bcea8b071 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1192,7 +1192,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
static int __parse_cls_flower(struct mlx5e_priv *priv,
struct mlx5_flow_spec *spec,
struct tc_cls_flower_offload *f,
- u8 *min_inline)
+ u8 *match_level)
{
void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
outer_headers);
@@ -1201,7 +1201,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
u16 addr_type = 0;
u8 ip_proto = 0;
- *min_inline = MLX5_INLINE_MODE_NONE;
+ *match_level = MLX5_MATCH_NONE;
if (f->dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
@@ -1276,7 +1276,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
key->src);
if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
- *min_inline = MLX5_INLINE_MODE_L2;
+ *match_level = MLX5_MATCH_L2;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
@@ -1298,7 +1298,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority);
- *min_inline = MLX5_INLINE_MODE_L2;
+ *match_level = MLX5_MATCH_L2;
}
}
@@ -1317,7 +1317,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
ntohs(key->n_proto));
if (mask->n_proto)
- *min_inline = MLX5_INLINE_MODE_L2;
+ *match_level = MLX5_MATCH_L2;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
@@ -1343,10 +1343,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
/* the HW doesn't need L3 inline to match on frag=no */
if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
- *min_inline = MLX5_INLINE_MODE_L2;
+ *match_level = MLX5_INLINE_MODE_L2;
/* *** L2 attributes parsing up to here *** */
else
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_INLINE_MODE_IP;
}
}
@@ -1367,7 +1367,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
key->ip_proto);
if (mask->ip_proto)
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_MATCH_L3;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
@@ -1394,7 +1394,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
&key->dst, sizeof(key->dst));
if (mask->src || mask->dst)
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_MATCH_L3;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
@@ -1423,7 +1423,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY ||
ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY)
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_MATCH_L3;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) {
@@ -1451,7 +1451,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
return -EOPNOTSUPP;
if (mask->tos || mask->ttl)
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_MATCH_L3;
}
/* *** L3 attributes parsing up to here *** */
@@ -1496,7 +1496,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
}
if (mask->src || mask->dst)
- *min_inline = MLX5_INLINE_MODE_TCP_UDP;
+ *match_level = MLX5_MATCH_L4;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) {
@@ -1515,7 +1515,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
ntohs(key->flags));
if (mask->flags)
- *min_inline = MLX5_INLINE_MODE_TCP_UDP;
+ *match_level = MLX5_MATCH_L4;
}
return 0;
@@ -1530,19 +1530,19 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
struct mlx5_eswitch *esw = dev->priv.eswitch;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep;
- u8 min_inline;
+ u8 match_level;
int err;
- err = __parse_cls_flower(priv, spec, f, &min_inline);
+ err = __parse_cls_flower(priv, spec, f, &match_level);
if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
rep = rpriv->rep;
if (rep->vport != FDB_UPLINK_VPORT &&
(esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
- esw->offloads.inline_mode < min_inline)) {
+ esw->offloads.inline_mode < match_level)) {
netdev_warn(priv->netdev,
"Flow is not offloaded due to min inline setting, required %d actual %d\n",
- min_inline, esw->offloads.inline_mode);
+ match_level, esw->offloads.inline_mode);
return -EOPNOTSUPP;
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 4cd773fa55e3..efae77dd1e35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -227,6 +227,13 @@ enum {
SET_VLAN_INSERT = BIT(1)
};
+enum mlx5_flow_match_level {
+ MLX5_MATCH_NONE = MLX5_INLINE_MODE_NONE,
+ MLX5_MATCH_L2 = MLX5_INLINE_MODE_L2,
+ MLX5_MATCH_L3 = MLX5_INLINE_MODE_IP,
+ MLX5_MATCH_L4 = MLX5_INLINE_MODE_TCP_UDP,
+};
+
struct mlx5_esw_flow_attr {
struct mlx5_eswitch_rep *in_rep;
struct mlx5_eswitch_rep *out_rep;
--
2.17.0
^ permalink raw reply related
* [net-next 12/16] net/mlx5e: Support offloaded TC flows with no matches on headers
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
For example:
tc filter add dev ens2f0_0 parent ffff: flower skip_sw action drop
Note that for eswitch flows, we still always match on the source port.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 10 +++++++++-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 1 +
.../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 8 ++++++--
3 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e84bcea8b071..1dc24e3a0841 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -58,6 +58,7 @@ struct mlx5_nic_flow_attr {
u32 flow_tag;
u32 mod_hdr_id;
u32 hairpin_tirn;
+ u8 match_level;
struct mlx5_flow_table *hairpin_ft;
};
@@ -753,7 +754,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
table_created = true;
}
- parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+ if (attr->match_level != MLX5_MATCH_NONE)
+ parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
rule = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec,
&flow_act, dest, dest_ix);
@@ -1547,6 +1550,11 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
}
}
+ if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+ flow->esw_attr->match_level = match_level;
+ else
+ flow->nic_attr->match_level = match_level;
+
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index efae77dd1e35..edf47a4d549e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -245,6 +245,7 @@ struct mlx5_esw_flow_attr {
bool vlan_handled;
u32 encap_id;
u32 mod_hdr_id;
+ u8 match_level;
struct mlx5e_tc_flow_parse_attr *parse_attr;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 35e256eb2f6e..8dd0eca03202 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -91,8 +91,12 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
- MLX5_MATCH_MISC_PARAMETERS;
+ if (attr->match_level == MLX5_MATCH_NONE)
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ else
+ spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
+ MLX5_MATCH_MISC_PARAMETERS;
+
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
--
2.17.0
^ permalink raw reply related
* [net-next 13/16] net/mlx5e: Report all channels with min RX WQEs timeout
From: Saeed Mahameed @ 2018-05-14 22:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Saeed Mahameed
In-Reply-To: <20180514221934.20246-1-saeedm@mellanox.com>
From: Eran Ben Elisha <eranbe@mellanox.com>
Report all channels which got timeout on posting the minimal number of
RX WQEs and not only the first one. Avoid busy wait on every channel,
when one of the RQs check got timeout, poll once for the remaining RQs.
In addition, add channel index to log when failed to get min RX WQEs
This info is needed in order to debug in case of dysfunctional channel.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_main.c | 23 +++++++++----------
1 file changed, 11 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0f2b66b41899..b0d6dde2754f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -747,23 +747,24 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
mlx5_core_destroy_rq(rq->mdev, rq->rqn);
}
-static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq)
+static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
{
- unsigned long exp_time = jiffies + msecs_to_jiffies(20000);
+ unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time);
struct mlx5e_channel *c = rq->channel;
struct mlx5_wq_ll *wq = &rq->wq;
u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq));
- while (time_before(jiffies, exp_time)) {
+ do {
if (wq->cur_sz >= min_wqes)
return 0;
msleep(20);
- }
+ } while (time_before(jiffies, exp_time));
+
+ netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
+ c->ix, rq->rqn, wq->cur_sz, min_wqes);
- netdev_warn(c->netdev, "Failed to get min RX wqes on RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
- rq->rqn, wq->cur_sz, min_wqes);
return -ETIMEDOUT;
}
@@ -2128,13 +2129,11 @@ static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs)
int err = 0;
int i;
- for (i = 0; i < chs->num; i++) {
- err = mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq);
- if (err)
- break;
- }
+ for (i = 0; i < chs->num; i++)
+ err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq,
+ err ? 0 : 20000);
- return err;
+ return err ? -ETIMEDOUT : 0;
}
static void mlx5e_deactivate_channels(struct mlx5e_channels *chs)
--
2.17.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox