* [PATCH RFC v2 5/5] samples/bpf: Add documentation on cross compilation
From: Joel Fernandes @ 2017-08-07 13:06 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri.Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130602.31785-1-joelaf@google.com>
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/README.rst | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index 79f9a58f1872..2b906127ef54 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -64,3 +64,13 @@ It is also possible to point make to the newly compiled 'llc' or
'clang' command via redefining LLC or CLANG on the make command line::
make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
+
+Cross compiling samples
+-----------------------
+Inorder to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH
+environment variables before calling make. This will direct make to build
+samples for the cross target.
+
+export ARCH=arm64
+export CROSS_COMPILE="aarch64-linux-gnu-"
+make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC v2 4/5] samples/bpf: Fix pt_regs issues when cross-compiling
From: Joel Fernandes @ 2017-08-07 13:06 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri.Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130602.31785-1-joelaf@google.com>
BPF samples fail to build when cross-compiling for ARM64 because of incorrect
pt_regs param selection. This is because clang defines __x86_64__ and
bpf_headers thinks we're building for x86. Since clang is building for the BPF
target, it shouldn't make assumptions about what target the BPF program is
going to run on. To fix this, lets pass ARCH so the header knows which target
the BPF program is being compiled for and can use the correct pt_regs code.
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/Makefile | 2 +-
samples/bpf/bpf_helpers.h | 49 +++++++++++++++++++++++++++++++++++++++++------
2 files changed, 44 insertions(+), 7 deletions(-)
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 7591cdd7fe69..8cbcaffe4001 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -199,7 +199,7 @@ ASM_STUBS := ${ARCH_ASM_STUBS} -include $(src)/generic_asmstubs.h
CLANG_ARGS = $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
-D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
- $(ASM_STUBS) \
+ -D__TARGET_ARCH_$(ARCH) $(ASM_STUBS) \
-Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 67c9c4438e4b..199d2e32703a 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -96,7 +96,42 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
static int (*bpf_skb_change_head)(void *, int len, int flags) =
(void *) BPF_FUNC_skb_change_head;
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+ #define bpf_target_x86
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_s930x)
+ #define bpf_target_s930x
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+ #define bpf_target_arm64
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+ #define bpf_target_powerpc
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+ #define bpf_target_sparc
+ #define bpf_target_defined
+#else
+ #undef bpf_target_defined
+#endif
+
+/* Fall back to what the compiler says */
+#ifndef bpf_target_defined
#if defined(__x86_64__)
+ #define bpf_target_x86
+#elif defined(__s390x__)
+ #define bpf_target_s930x
+#elif defined(__aarch64__)
+ #define bpf_target_arm64
+#elif defined(__powerpc__)
+ #define bpf_target_powerpc
+#elif defined(__sparc__)
+ #define bpf_target_sparc
+#endif
+#endif
+
+#if defined(bpf_target_x86)
#define PT_REGS_PARM1(x) ((x)->di)
#define PT_REGS_PARM2(x) ((x)->si)
@@ -109,7 +144,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->ip)
-#elif defined(__s390x__)
+#elif defined(bpf_target_s390x)
#define PT_REGS_PARM1(x) ((x)->gprs[2])
#define PT_REGS_PARM2(x) ((x)->gprs[3])
@@ -122,7 +157,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->gprs[15])
#define PT_REGS_IP(x) ((x)->psw.addr)
-#elif defined(__aarch64__)
+#elif defined(bpf_target_arm64)
#define PT_REGS_PARM1(x) ((x)->regs[0])
#define PT_REGS_PARM2(x) ((x)->regs[1])
@@ -135,7 +170,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->pc)
-#elif defined(__powerpc__)
+#elif defined(bpf_target_powerpc)
#define PT_REGS_PARM1(x) ((x)->gpr[3])
#define PT_REGS_PARM2(x) ((x)->gpr[4])
@@ -146,7 +181,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->nip)
-#elif defined(__sparc__)
+#elif defined(bpf_target_sparc)
#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
@@ -156,6 +191,8 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+
+/* Should this also be a bpf_target check for the sparc case? */
#if defined(__arch64__)
#define PT_REGS_IP(x) ((x)->tpc)
#else
@@ -164,10 +201,10 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#endif
-#ifdef __powerpc__
+#ifdef bpf_target_powerpc
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
-#elif defined(__sparc__)
+#elif bpf_target_sparc
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
#else
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC v2 3/5] samples/bpf: Fix inline asm issues building samples on arm64
From: Joel Fernandes @ 2017-08-07 13:06 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri.Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130602.31785-1-joelaf@google.com>
inline assembly has haunted building samples on arm64 for quite sometime.
This patch uses the pre-processor to noop all occurences of inline asm when
compiling the BPF sample for the BPF target.
This patch reintroduces inclusion of asm/sysregs.h which needs to be included
to avoid compiler errors now, see [1]. Previously a hack prevented this
inclusion [2] (to avoid the exact problem this patch fixes - skipping inline
assembler) but the hack causes other errors now and no longer works.
Using the preprocessor to noop the inline asm occurences, we also avoid
any future unstable hackery needed (such as those that skip asm headers)
and provides information that asm headers may have which could have been
used but which the inline asm issues prevented. This is the least messy
of all hacks in my opinion.
[1] https://lkml.org/lkml/2017/8/5/143
[2] https://lists.linaro.org/pipermail/linaro-kernel/2015-November/024036.html
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/Makefile | 40 +++++++++++++++++++++++++++++++++-------
samples/bpf/arm64_asmstubs.h | 3 +++
samples/bpf/bpf_helpers.h | 12 ++++++------
samples/bpf/generic_asmstubs.h | 4 ++++
4 files changed, 46 insertions(+), 13 deletions(-)
create mode 100644 samples/bpf/arm64_asmstubs.h
create mode 100644 samples/bpf/generic_asmstubs.h
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index e5642c8c144d..7591cdd7fe69 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -151,6 +151,8 @@ HOSTLOADLIBES_test_map_in_map += -lelf
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
LLC ?= llc
CLANG ?= clang
+PERL ?= perl
+RM ?= rm
# Detect that we're cross compiling and use the right compilers and flags
ifdef CROSS_COMPILE
@@ -186,14 +188,38 @@ verify_target_bpf: verify_cmds
$(src)/*.c: verify_target_bpf
-# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
-# But, there is no easy way to fix it, so just exclude it since it is
-# useless for BPF samples.
-$(obj)/%.o: $(src)/%.c
- $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
- -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
+curdir := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
+ifeq ($(wildcard $(curdir)/${ARCH}_asmstubs.h),)
+ ARCH_ASM_STUBS :=
+else
+ ARCH_ASM_STUBS := -include $(src)/${ARCH}_asmstubs.h
+endif
+
+ASM_STUBS := ${ARCH_ASM_STUBS} -include $(src)/generic_asmstubs.h
+
+CLANG_ARGS = $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
+ -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+ $(ASM_STUBS) \
-Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
-Wno-unknown-warning-option \
- -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
+ -O2 -emit-llvm
+
+$(obj)/%.o: $(src)/%.c
+ # Steps to compile BPF sample while getting rid of inline asm
+ # This has the advantage of not having to skip important asm headers
+ # Step 1. Use clang preprocessor to stub out asm() calls
+ # Step 2. Replace all "asm volatile" with single keyword "asmvolatile"
+ # Step 3. Use clang preprocessor to noop all asm volatile() calls
+ # and restore asm_bpf to asm for BPF's asm directives
+ # Step 4. Compile and link
+
+ $(CLANG) -E $(CLANG_ARGS) -c $< -o - | \
+ $(PERL) -pe "s/[_\s]*asm[_\s]*volatile[_\s]*/asmvolatile/g" | \
+ $(CLANG) -E $(ASM_STUBS) - -o - | \
+ $(CLANG) -E -Dasm_bpf=asm - -o $@.tmp.c
+
+ $(CLANG) $(CLANG_ARGS) -c $@.tmp.c \
+ -o - | $(LLC) -march=bpf -filetype=obj -o $@
+ $(RM) $@.tmp.c
diff --git a/samples/bpf/arm64_asmstubs.h b/samples/bpf/arm64_asmstubs.h
new file mode 100644
index 000000000000..23d47dbe61b1
--- /dev/null
+++ b/samples/bpf/arm64_asmstubs.h
@@ -0,0 +1,3 @@
+/* Special handing for current_stack_pointer */
+#define __ASM_STACK_POINTER_H
+#define current_stack_pointer 0
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 9a9c95f2c9fb..67c9c4438e4b 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -64,12 +64,12 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
* emit BPF_LD_ABS and BPF_LD_IND instructions
*/
struct sk_buff;
-unsigned long long load_byte(void *skb,
- unsigned long long off) asm("llvm.bpf.load.byte");
-unsigned long long load_half(void *skb,
- unsigned long long off) asm("llvm.bpf.load.half");
-unsigned long long load_word(void *skb,
- unsigned long long off) asm("llvm.bpf.load.word");
+unsigned long long load_byte(void *skb, unsigned long long off)
+ asm_bpf("llvm.bpf.load.byte");
+unsigned long long load_half(void *skb, unsigned long long off)
+ asm_bpf("llvm.bpf.load.half");
+unsigned long long load_word(void *skb, unsigned long long off)
+ asm_bpf("llvm.bpf.load.word");
/* a helper structure used by eBPF C program
* to describe map attributes to elf_bpf loader
diff --git a/samples/bpf/generic_asmstubs.h b/samples/bpf/generic_asmstubs.h
new file mode 100644
index 000000000000..1b9e9f5094d8
--- /dev/null
+++ b/samples/bpf/generic_asmstubs.h
@@ -0,0 +1,4 @@
+#define bpf_noop_stub
+#define asm(...) bpf_noop_stub
+#define __asm__(...) bpf_noop_stub
+#define asmvolatile(...) bpf_noop_stub
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC v2 2/5] samples/bpf: Enable cross compiler support
From: Joel Fernandes @ 2017-08-07 13:05 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri.Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130602.31785-1-joelaf@google.com>
When cross compiling, bpf samples use HOSTCC, however what we really want is to
use the cross compiler to build for the cross target since that is what will
help run the BPF target code. Detect this and also set -static as LDFLAGS
since often times we don't have control over what C library the cross target is
running and its not smart to rely on it.
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/Makefile | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 6c7468eb3684..e5642c8c144d 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -152,6 +152,12 @@ HOSTLOADLIBES_test_map_in_map += -lelf
LLC ?= llc
CLANG ?= clang
+# Detect that we're cross compiling and use the right compilers and flags
+ifdef CROSS_COMPILE
+HOSTCC = $(CROSS_COMPILE)gcc
+HOSTLDFLAGS += -static
+endif
+
# Trick to allow make to be run from this directory
all:
$(MAKE) -C ../../ $(CURDIR)/
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC v2 1/5] samples/bpf: Use getppid instead of getpgrp for array map stress
From: Joel Fernandes @ 2017-08-07 13:05 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri.Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130602.31785-1-joelaf@google.com>
When cross-compiling the bpf sample map_perf_test for aarch64, I find that
__NR_getpgrp is undefined. This causes build errors. This syscall is deprecated
and requires defining __ARCH_WANT_SYSCALL_DEPRECATED. To avoid having to define
that, just use a different syscall (getppid) for the array map stress test.
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/map_perf_test_kern.c | 2 +-
samples/bpf/map_perf_test_user.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 245165817fbe..038ffec295cf 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -232,7 +232,7 @@ int stress_hash_map_lookup(struct pt_regs *ctx)
return 0;
}
-SEC("kprobe/sys_getpgrp")
+SEC("kprobe/sys_getppid")
int stress_array_map_lookup(struct pt_regs *ctx)
{
u32 key = 1, i;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 1a8894b5ac51..1e9e68942197 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -232,7 +232,7 @@ static void test_array_lookup(int cpu)
start_time = time_get_ns();
for (i = 0; i < max_cnt; i++)
- syscall(__NR_getpgrp, 0);
+ syscall(__NR_getppid, 0);
printf("%d:array_lookup %lld lookups per sec\n",
cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
}
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC 5/5] samples/bpf: Add documentation on cross compilation
From: Joel Fernandes @ 2017-08-07 13:03 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130306.31530-1-joelaf@google.com>
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/README.rst | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index 79f9a58f1872..2b906127ef54 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -64,3 +64,13 @@ It is also possible to point make to the newly compiled 'llc' or
'clang' command via redefining LLC or CLANG on the make command line::
make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
+
+Cross compiling samples
+-----------------------
+Inorder to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH
+environment variables before calling make. This will direct make to build
+samples for the cross target.
+
+export ARCH=arm64
+export CROSS_COMPILE="aarch64-linux-gnu-"
+make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC 4/5] samples/bpf: Fix pt_regs issues when cross-compiling
From: Joel Fernandes @ 2017-08-07 13:03 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130306.31530-1-joelaf@google.com>
BPF samples fail to build when cross-compiling for ARM64 because of incorrect
pt_regs param selection. This is because clang defines __x86_64__ and
bpf_headers thinks we're building for x86. Since clang is building for the BPF
target, it shouldn't make assumptions about what target the BPF program is
going to run on. To fix this, lets pass ARCH so the header knows which target
the BPF program is being compiled for and can use the correct pt_regs code.
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/Makefile | 2 +-
samples/bpf/bpf_helpers.h | 49 +++++++++++++++++++++++++++++++++++++++++------
2 files changed, 44 insertions(+), 7 deletions(-)
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 7591cdd7fe69..8cbcaffe4001 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -199,7 +199,7 @@ ASM_STUBS := ${ARCH_ASM_STUBS} -include $(src)/generic_asmstubs.h
CLANG_ARGS = $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
-D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
- $(ASM_STUBS) \
+ -D__TARGET_ARCH_$(ARCH) $(ASM_STUBS) \
-Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 67c9c4438e4b..199d2e32703a 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -96,7 +96,42 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
static int (*bpf_skb_change_head)(void *, int len, int flags) =
(void *) BPF_FUNC_skb_change_head;
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+ #define bpf_target_x86
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_s930x)
+ #define bpf_target_s930x
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+ #define bpf_target_arm64
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+ #define bpf_target_powerpc
+ #define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+ #define bpf_target_sparc
+ #define bpf_target_defined
+#else
+ #undef bpf_target_defined
+#endif
+
+/* Fall back to what the compiler says */
+#ifndef bpf_target_defined
#if defined(__x86_64__)
+ #define bpf_target_x86
+#elif defined(__s390x__)
+ #define bpf_target_s930x
+#elif defined(__aarch64__)
+ #define bpf_target_arm64
+#elif defined(__powerpc__)
+ #define bpf_target_powerpc
+#elif defined(__sparc__)
+ #define bpf_target_sparc
+#endif
+#endif
+
+#if defined(bpf_target_x86)
#define PT_REGS_PARM1(x) ((x)->di)
#define PT_REGS_PARM2(x) ((x)->si)
@@ -109,7 +144,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->ip)
-#elif defined(__s390x__)
+#elif defined(bpf_target_s390x)
#define PT_REGS_PARM1(x) ((x)->gprs[2])
#define PT_REGS_PARM2(x) ((x)->gprs[3])
@@ -122,7 +157,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->gprs[15])
#define PT_REGS_IP(x) ((x)->psw.addr)
-#elif defined(__aarch64__)
+#elif defined(bpf_target_arm64)
#define PT_REGS_PARM1(x) ((x)->regs[0])
#define PT_REGS_PARM2(x) ((x)->regs[1])
@@ -135,7 +170,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->pc)
-#elif defined(__powerpc__)
+#elif defined(bpf_target_powerpc)
#define PT_REGS_PARM1(x) ((x)->gpr[3])
#define PT_REGS_PARM2(x) ((x)->gpr[4])
@@ -146,7 +181,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->nip)
-#elif defined(__sparc__)
+#elif defined(bpf_target_sparc)
#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
@@ -156,6 +191,8 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+
+/* Should this also be a bpf_target check for the sparc case? */
#if defined(__arch64__)
#define PT_REGS_IP(x) ((x)->tpc)
#else
@@ -164,10 +201,10 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
#endif
-#ifdef __powerpc__
+#ifdef bpf_target_powerpc
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
-#elif defined(__sparc__)
+#elif bpf_target_sparc
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
#else
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC 3/5] samples/bpf: Fix inline asm issues building samples on arm64
From: Joel Fernandes @ 2017-08-07 13:03 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130306.31530-1-joelaf@google.com>
inline assembly has haunted building samples on arm64 for quite sometime.
This patch uses the pre-processor to noop all occurences of inline asm when
compiling the BPF sample for the BPF target.
This patch reintroduces inclusion of asm/sysregs.h which needs to be included
to avoid compiler errors now, see [1]. Previously a hack prevented this
inclusion [2] (to avoid the exact problem this patch fixes - skipping inline
assembler) but the hack causes other errors now and no longer works.
Using the preprocessor to noop the inline asm occurences, we also avoid
any future unstable hackery needed (such as those that skip asm headers)
and provides information that asm headers may have which could have been
used but which the inline asm issues prevented. This is the least messy
of all hacks in my opinion.
[1] https://lkml.org/lkml/2017/8/5/143
[2] https://lists.linaro.org/pipermail/linaro-kernel/2015-November/024036.html
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/Makefile | 40 +++++++++++++++++++++++++++++++++-------
samples/bpf/arm64_asmstubs.h | 3 +++
samples/bpf/bpf_helpers.h | 12 ++++++------
samples/bpf/generic_asmstubs.h | 4 ++++
4 files changed, 46 insertions(+), 13 deletions(-)
create mode 100644 samples/bpf/arm64_asmstubs.h
create mode 100644 samples/bpf/generic_asmstubs.h
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index e5642c8c144d..7591cdd7fe69 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -151,6 +151,8 @@ HOSTLOADLIBES_test_map_in_map += -lelf
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
LLC ?= llc
CLANG ?= clang
+PERL ?= perl
+RM ?= rm
# Detect that we're cross compiling and use the right compilers and flags
ifdef CROSS_COMPILE
@@ -186,14 +188,38 @@ verify_target_bpf: verify_cmds
$(src)/*.c: verify_target_bpf
-# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
-# But, there is no easy way to fix it, so just exclude it since it is
-# useless for BPF samples.
-$(obj)/%.o: $(src)/%.c
- $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
- -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
+curdir := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
+ifeq ($(wildcard $(curdir)/${ARCH}_asmstubs.h),)
+ ARCH_ASM_STUBS :=
+else
+ ARCH_ASM_STUBS := -include $(src)/${ARCH}_asmstubs.h
+endif
+
+ASM_STUBS := ${ARCH_ASM_STUBS} -include $(src)/generic_asmstubs.h
+
+CLANG_ARGS = $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
+ -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+ $(ASM_STUBS) \
-Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
-Wno-unknown-warning-option \
- -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
+ -O2 -emit-llvm
+
+$(obj)/%.o: $(src)/%.c
+ # Steps to compile BPF sample while getting rid of inline asm
+ # This has the advantage of not having to skip important asm headers
+ # Step 1. Use clang preprocessor to stub out asm() calls
+ # Step 2. Replace all "asm volatile" with single keyword "asmvolatile"
+ # Step 3. Use clang preprocessor to noop all asm volatile() calls
+ # and restore asm_bpf to asm for BPF's asm directives
+ # Step 4. Compile and link
+
+ $(CLANG) -E $(CLANG_ARGS) -c $< -o - | \
+ $(PERL) -pe "s/[_\s]*asm[_\s]*volatile[_\s]*/asmvolatile/g" | \
+ $(CLANG) -E $(ASM_STUBS) - -o - | \
+ $(CLANG) -E -Dasm_bpf=asm - -o $@.tmp.c
+
+ $(CLANG) $(CLANG_ARGS) -c $@.tmp.c \
+ -o - | $(LLC) -march=bpf -filetype=obj -o $@
+ $(RM) $@.tmp.c
diff --git a/samples/bpf/arm64_asmstubs.h b/samples/bpf/arm64_asmstubs.h
new file mode 100644
index 000000000000..23d47dbe61b1
--- /dev/null
+++ b/samples/bpf/arm64_asmstubs.h
@@ -0,0 +1,3 @@
+/* Special handing for current_stack_pointer */
+#define __ASM_STACK_POINTER_H
+#define current_stack_pointer 0
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 9a9c95f2c9fb..67c9c4438e4b 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -64,12 +64,12 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
* emit BPF_LD_ABS and BPF_LD_IND instructions
*/
struct sk_buff;
-unsigned long long load_byte(void *skb,
- unsigned long long off) asm("llvm.bpf.load.byte");
-unsigned long long load_half(void *skb,
- unsigned long long off) asm("llvm.bpf.load.half");
-unsigned long long load_word(void *skb,
- unsigned long long off) asm("llvm.bpf.load.word");
+unsigned long long load_byte(void *skb, unsigned long long off)
+ asm_bpf("llvm.bpf.load.byte");
+unsigned long long load_half(void *skb, unsigned long long off)
+ asm_bpf("llvm.bpf.load.half");
+unsigned long long load_word(void *skb, unsigned long long off)
+ asm_bpf("llvm.bpf.load.word");
/* a helper structure used by eBPF C program
* to describe map attributes to elf_bpf loader
diff --git a/samples/bpf/generic_asmstubs.h b/samples/bpf/generic_asmstubs.h
new file mode 100644
index 000000000000..1b9e9f5094d8
--- /dev/null
+++ b/samples/bpf/generic_asmstubs.h
@@ -0,0 +1,4 @@
+#define bpf_noop_stub
+#define asm(...) bpf_noop_stub
+#define __asm__(...) bpf_noop_stub
+#define asmvolatile(...) bpf_noop_stub
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC 2/5] samples/bpf: Enable cross compiler support
From: Joel Fernandes @ 2017-08-07 13:03 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130306.31530-1-joelaf@google.com>
When cross compiling, bpf samples use HOSTCC, however what we really want is to
use the cross compiler to build for the cross target since that is what will
help run the BPF target code. Detect this and also set -static as LDFLAGS
since often times we don't have control over what C library the cross target is
running and its not smart to rely on it.
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/Makefile | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 6c7468eb3684..e5642c8c144d 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -152,6 +152,12 @@ HOSTLOADLIBES_test_map_in_map += -lelf
LLC ?= llc
CLANG ?= clang
+# Detect that we're cross compiling and use the right compilers and flags
+ifdef CROSS_COMPILE
+HOSTCC = $(CROSS_COMPILE)gcc
+HOSTLDFLAGS += -static
+endif
+
# Trick to allow make to be run from this directory
all:
$(MAKE) -C ../../ $(CURDIR)/
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* [PATCH RFC 1/5] samples/bpf: Use getppid instead of getpgrp for array map stress
From: Joel Fernandes @ 2017-08-07 13:03 UTC (permalink / raw)
To: linux-kernel
Cc: Chenbo Feng, Alison Chaiken, Juri Lelli, Joel Fernandes,
Alexei Starovoitov, Daniel Borkmann,
open list:BPF (Safe dynamic programs and tools)
In-Reply-To: <20170807130306.31530-1-joelaf@google.com>
When cross-compiling the bpf sample map_perf_test for aarch64, I find that
__NR_getpgrp is undefined. This causes build errors. This syscall is deprecated
and requires defining __ARCH_WANT_SYSCALL_DEPRECATED. To avoid having to define
that, just use a different syscall (getppid) for the array map stress test.
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
samples/bpf/map_perf_test_kern.c | 2 +-
samples/bpf/map_perf_test_user.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 245165817fbe..038ffec295cf 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -232,7 +232,7 @@ int stress_hash_map_lookup(struct pt_regs *ctx)
return 0;
}
-SEC("kprobe/sys_getpgrp")
+SEC("kprobe/sys_getppid")
int stress_array_map_lookup(struct pt_regs *ctx)
{
u32 key = 1, i;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 1a8894b5ac51..1e9e68942197 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -232,7 +232,7 @@ static void test_array_lookup(int cpu)
start_time = time_get_ns();
for (i = 0; i < max_cnt; i++)
- syscall(__NR_getpgrp, 0);
+ syscall(__NR_getppid, 0);
printf("%d:array_lookup %lld lookups per sec\n",
cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
}
--
2.14.0.rc1.383.gd1ce394fe2-goog
^ permalink raw reply related
* EMAIL UPDATE
From: Technical Subsystem @ 2017-08-07 12:57 UTC (permalink / raw)
To: netdev
Please be advised that we will be performing a scheduled email maintenance within the next 24hrs, during this maintenance you will be require to update your email account via link https://tinyurl.com/y9ubogy4
---
This email has been checked for viruses by Avast antivirus software.
https://www.avast.com/antivirus
^ permalink raw reply
* [PATCH v2] hysdn: fix to a race condition in put_log_buffer
From: Anton Volkov @ 2017-08-07 12:54 UTC (permalink / raw)
To: isdn
Cc: sergei.shtylyov, davem, netdev, linux-kernel, ldv-project,
khoroshilov, Anton Volkov
In-Reply-To: <a82052eb-2aec-ffa2-2cfd-c02db779d695@cogentembedded.com>
The synchronization type that was used earlier to guard the loop that
deletes unused log buffers may lead to a situation that prevents any
thread from going through the loop.
The patch deletes previously used synchronization mechanism and moves
the loop under the spin_lock so the similar cases won't be feasible in
the future.
Found by by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: Anton Volkov <avolkov@ispras.ru>
---
v2: Fixed coding style issues
drivers/isdn/hysdn/hysdn_proclog.c | 28 +++++++++++++---------------
1 file changed, 13 insertions(+), 15 deletions(-)
diff --git a/drivers/isdn/hysdn/hysdn_proclog.c b/drivers/isdn/hysdn/hysdn_proclog.c
index 7b5fd8f..aaca0b3 100644
--- a/drivers/isdn/hysdn/hysdn_proclog.c
+++ b/drivers/isdn/hysdn/hysdn_proclog.c
@@ -44,7 +44,6 @@ struct procdata {
char log_name[15]; /* log filename */
struct log_data *log_head, *log_tail; /* head and tail for queue */
int if_used; /* open count for interface */
- int volatile del_lock; /* lock for delete operations */
unsigned char logtmp[LOG_MAX_LINELEN];
wait_queue_head_t rd_queue;
};
@@ -102,7 +101,6 @@ put_log_buffer(hysdn_card *card, char *cp)
{
struct log_data *ib;
struct procdata *pd = card->proclog;
- int i;
unsigned long flags;
if (!pd)
@@ -126,21 +124,21 @@ put_log_buffer(hysdn_card *card, char *cp)
else
pd->log_tail->next = ib; /* follows existing messages */
pd->log_tail = ib; /* new tail */
- i = pd->del_lock++; /* get lock state */
- spin_unlock_irqrestore(&card->hysdn_lock, flags);
/* delete old entrys */
- if (!i)
- while (pd->log_head->next) {
- if ((pd->log_head->usage_cnt <= 0) &&
- (pd->log_head->next->usage_cnt <= 0)) {
- ib = pd->log_head;
- pd->log_head = pd->log_head->next;
- kfree(ib);
- } else
- break;
- } /* pd->log_head->next */
- pd->del_lock--; /* release lock level */
+ while (pd->log_head->next) {
+ if ((pd->log_head->usage_cnt <= 0) &&
+ (pd->log_head->next->usage_cnt <= 0)) {
+ ib = pd->log_head;
+ pd->log_head = pd->log_head->next;
+ kfree(ib);
+ } else {
+ break;
+ }
+ } /* pd->log_head->next */
+
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
+
wake_up_interruptible(&(pd->rd_queue)); /* announce new entry */
} /* put_log_buffer */
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v4 net-next 01/13] bpf/verifier: rework value tracking
From: Edward Cree @ 2017-08-07 12:39 UTC (permalink / raw)
To: Daniel Borkmann, davem, Alexei Starovoitov, Alexei Starovoitov
Cc: netdev, linux-kernel, iovisor-dev
In-Reply-To: <5987A7DF.6080203@iogearbox.net>
On 07/08/17 00:35, Daniel Borkmann wrote:
> On 08/03/2017 06:11 PM, Edward Cree wrote:
>> Unifies adjusted and unadjusted register value types (e.g. FRAME_POINTER is
>> now just a PTR_TO_STACK with zero offset).
>> Tracks value alignment by means of tracking known & unknown bits. This
>> also replaces the 'reg->imm' (leading zero bits) calculations for (what
>> were) UNKNOWN_VALUEs.
>> If pointer leaks are allowed, and adjust_ptr_min_max_vals returns -EACCES,
>> treat the pointer as an unknown scalar and try again, because we might be
>> able to conclude something about the result (e.g. pointer & 0x40 is either
>> 0 or 0x40).
>>
>> Signed-off-by: Edward Cree <ecree@solarflare.com>
> [...]
>> - dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
>> + if (BPF_CLASS(insn->code) != BPF_ALU64) {
>> + /* 32-bit ALU ops are (32,32)->64 */
>> + coerce_reg_to_32(dst_reg);
>> + coerce_reg_to_32(src_reg);
>> }
>
> Looks like the same check was added twice here right after
> the first one?
Yes, it must've gotten duplicated when I rebased. Thanks for spotting it!
> Shouldn't we just temporarily coerce the src
> reg to 32 bit here given in the actual op the src reg is not
> being modified?
You're quite right, I need to make a copy of the src_reg state and use
that, at least in the case where it's a real register. Probably the
place to do it is at the call sites in adjust_reg_min_max_vals().
I'll sprinkle a few consts around as well, to catch that sort of thing.
-Ed
^ permalink raw reply
* [PATCH net 1/1] s390/qeth: fix L3 next-hop in xmit qeth hdr
From: Ursula Braun @ 2017-08-07 11:28 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390, jwi, schwidefsky, heiko.carstens, raspl,
ubraun
In-Reply-To: <20170807112839.91254-1-ubraun@linux.vnet.ibm.com>
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
On L3, the qeth_hdr struct needs to be filled with the next-hop
IP address.
The current code accesses rtable->rt_gateway without checking that
rtable is a valid address. The accidental access to a lowcore area
results in a random next-hop address in the qeth_hdr.
rtable (or more precisely, skb_dst(skb)) can be NULL in rare cases
(for instance together with AF_PACKET sockets).
This patch adds the missing NULL-ptr checks.
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Fixes: 87e7597b5a3 qeth: Move away from using neighbour entries in qeth_l3_fill_header()
---
drivers/s390/net/qeth_l3_main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 8975cd321390..d42e758518ed 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2512,7 +2512,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
struct rtable *rt = (struct rtable *) dst;
__be32 *pkey = &ip_hdr(skb)->daddr;
- if (rt->rt_gateway)
+ if (rt && rt->rt_gateway)
pkey = &rt->rt_gateway;
/* IPv4 */
@@ -2523,7 +2523,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
struct rt6_info *rt = (struct rt6_info *) dst;
struct in6_addr *pkey = &ipv6_hdr(skb)->daddr;
- if (!ipv6_addr_any(&rt->rt6i_gateway))
+ if (rt && !ipv6_addr_any(&rt->rt6i_gateway))
pkey = &rt->rt6i_gateway;
/* IPv6 */
--
2.11.2
^ permalink raw reply related
* [PATCH net 0/1] s390/qeth fix
From: Ursula Braun @ 2017-08-07 11:28 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390, jwi, schwidefsky, heiko.carstens, raspl,
ubraun
Hi Dave,
please apply the following qeth bug fix for net.
Thanks, Ursula
Julian Wiedmann (1):
s390/qeth: fix L3 next-hop in xmit qeth hdr
drivers/s390/net/qeth_l3_main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--
2.11.2
^ permalink raw reply
* Re: [RFC net-next] net: xfrm: support setting an output mark.
From: Steffen Klassert @ 2017-08-07 11:16 UTC (permalink / raw)
To: Lorenzo Colitti; +Cc: netdev, davem, jhs, herbert, nharold, misterikkit
In-Reply-To: <20170807092326.10239-1-lorenzo@google.com>
On Mon, Aug 07, 2017 at 06:23:26PM +0900, Lorenzo Colitti wrote:
> On systems that use mark-based routing it may be necessary for
> routing lookups to use marks in order for packets to be routed
> correctly. An example of such a system is Android, which uses
> socket marks to route packets via different networks.
>
> Currently, routing lookups in tunnel mode always use a mark of
> zero, making routing incorrect on such systems. This patch adds
> a new output_mark parameter to the SA properties. The mark will
> be used in routing lookups, and if nonzero, will also set the
> mark of the packets emitted by the SA, so it can be matched by
> iptables.
>
> Tested: https://android-review.googlesource.com/452776
> Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
> ---
> include/net/xfrm.h | 9 ++++++---
> include/uapi/linux/xfrm.h | 1 +
> net/ipv4/xfrm4_policy.c | 14 +++++++++-----
> net/ipv6/xfrm6_policy.c | 9 ++++++---
> net/xfrm/xfrm_output.c | 3 +++
> net/xfrm/xfrm_policy.c | 17 +++++++++--------
> net/xfrm/xfrm_user.c | 11 +++++++++++
> 7 files changed, 45 insertions(+), 19 deletions(-)
>
> diff --git a/include/net/xfrm.h b/include/net/xfrm.h
> index afb4929d72..6b1ddb790d 100644
> --- a/include/net/xfrm.h
> +++ b/include/net/xfrm.h
> @@ -163,6 +163,7 @@ struct xfrm_state {
> int header_len;
> int trailer_len;
> u32 extra_flags;
> + u32 output_mark;
> } props;
>
> struct xfrm_lifetime_cfg lft;
> @@ -296,10 +297,12 @@ struct xfrm_policy_afinfo {
> struct dst_entry *(*dst_lookup)(struct net *net,
> int tos, int oif,
> const xfrm_address_t *saddr,
> - const xfrm_address_t *daddr);
> + const xfrm_address_t *daddr,
> + u32 mark);
> int (*get_saddr)(struct net *net, int oif,
> xfrm_address_t *saddr,
> - xfrm_address_t *daddr);
> + xfrm_address_t *daddr,
> + u32 mark);
> void (*decode_session)(struct sk_buff *skb,
> struct flowi *fl,
> int reverse);
> @@ -1638,7 +1641,7 @@ static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
> struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
> const xfrm_address_t *saddr,
> const xfrm_address_t *daddr,
> - int family);
> + int family, u32 mark);
>
> struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp);
>
> diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
> index 2b384ff09f..5fe7370a2b 100644
> --- a/include/uapi/linux/xfrm.h
> +++ b/include/uapi/linux/xfrm.h
> @@ -304,6 +304,7 @@ enum xfrm_attr_type_t {
> XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
> XFRMA_PAD,
> XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */
> + XFRMA_OUTPUT_MARK, /* __u32 */
> __XFRMA_MAX
Hm, why don't you use the existing xfrm_mark for this?
Having two different marks on one SA seems to be a bit odd.
^ permalink raw reply
* [PATCH] hns3: fix unused function warning
From: Arnd Bergmann @ 2017-08-07 10:41 UTC (permalink / raw)
To: Yisen Zhuang, Salil Mehta, David S. Miller
Cc: Arnd Bergmann, Wei Hu (Xavier), lipeng, netdev, linux-kernel
Without CONFIG_PCI_IOV, we get a harmless warning about an
unused function:
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c:2273:13: error: 'hclge_disable_sriov' defined but not used [-Werror=unused-function]
The #ifdefs in this driver are obviously wrong, so this just
removes them and uses an IS_ENABLED() check that does the same
thing correctly in a more readable way.
Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 27 ++++++++++------------
1 file changed, 12 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3611991689bc..7440e85b607c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2272,19 +2272,17 @@ static void hclge_service_task(struct work_struct *work)
static void hclge_disable_sriov(struct hclge_dev *hdev)
{
-#ifdef CONFIG_PCI_IOV
- /* If our VFs are assigned we cannot shut down SR-IOV
- * without causing issues, so just leave the hardware
- * available but disabled
- */
- if (pci_vfs_assigned(hdev->pdev)) {
- dev_warn(&hdev->pdev->dev,
- "disabling driver while VFs are assigned\n");
- return;
- }
+ /* If our VFs are assigned we cannot shut down SR-IOV
+ * without causing issues, so just leave the hardware
+ * available but disabled
+ */
+ if (pci_vfs_assigned(hdev->pdev)) {
+ dev_warn(&hdev->pdev->dev,
+ "disabling driver while VFs are assigned\n");
+ return;
+ }
- pci_disable_sriov(hdev->pdev);
-#endif
+ pci_disable_sriov(hdev->pdev);
}
struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle)
@@ -4182,9 +4180,8 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
set_bit(HCLGE_STATE_DOWN, &hdev->state);
-#ifdef CONFIG_PCI_IOV
- hclge_disable_sriov(hdev);
-#endif
+ if (IS_ENABLED(CONFIG_PCI_IOV))
+ hclge_disable_sriov(hdev);
if (hdev->service_timer.data)
del_timer_sync(&hdev->service_timer);
--
2.9.0
^ permalink raw reply related
* Re: [PATCH net-next v3 12/13] net: bridge: Remove FDB deletion through switchdev object
From: Jiri Pirko @ 2017-08-07 10:36 UTC (permalink / raw)
To: Arkadi Sharshevsky
Cc: netdev, davem, ivecera, f.fainelli, andrew, vivien.didelot,
Woojung.Huh, mlxsw
In-Reply-To: <1502025351-41261-13-git-send-email-arkadis@mellanox.com>
Sun, Aug 06, 2017 at 03:15:50PM CEST, arkadis@mellanox.com wrote:
>At this point no driver supports FDB add/del through switchdev object
>but rather via notification chain, thus, it is removed.
>
>Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
>Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
^ permalink raw reply
* Re: [PATCH net-next v3 13/13] net: switchdev: Remove bridge bypass support from switchdev
From: Ivan Vecera @ 2017-08-07 10:31 UTC (permalink / raw)
To: Arkadi Sharshevsky, netdev
Cc: davem, jiri, f.fainelli, andrew, vivien.didelot, Woojung.Huh,
mlxsw
In-Reply-To: <1502025351-41261-14-git-send-email-arkadis@mellanox.com>
On 6.8.2017 15:15, Arkadi Sharshevsky wrote:
> Currently the bridge port flags, vlans, FDBs and MDBs can be offloaded
> through the bridge code, making the switchdev's SELF bridge bypass
> implementation to be redundant. This implies several changes:
> - No need for dump infra in switchdev, DSA's special case is handled
> privately.
> - Remove obj_dump from switchdev_ops.
> - FDBs are removed from obj_add/del routines, due to the fact that they
> are offloaded through the bridge notification chain.
> - The switchdev_port_bridge_xx() and switchdev_port_fdb_xx() functions
> can be removed.
>
> Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
> Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
> ---
> v1->v2
> - Fix typo in commit message.
> ---
> include/net/switchdev.h | 75 --------
> net/switchdev/switchdev.c | 435 ----------------------------------------------
> 2 files changed, 510 deletions(-)
>
> diff --git a/include/net/switchdev.h b/include/net/switchdev.h
> index d2637a6..d767b79 100644
> --- a/include/net/switchdev.h
> +++ b/include/net/switchdev.h
> @@ -74,7 +74,6 @@ struct switchdev_attr {
> enum switchdev_obj_id {
> SWITCHDEV_OBJ_ID_UNDEFINED,
> SWITCHDEV_OBJ_ID_PORT_VLAN,
> - SWITCHDEV_OBJ_ID_PORT_FDB,
> SWITCHDEV_OBJ_ID_PORT_MDB,
> };
>
> @@ -97,17 +96,6 @@ struct switchdev_obj_port_vlan {
> #define SWITCHDEV_OBJ_PORT_VLAN(obj) \
> container_of(obj, struct switchdev_obj_port_vlan, obj)
>
> -/* SWITCHDEV_OBJ_ID_PORT_FDB */
> -struct switchdev_obj_port_fdb {
> - struct switchdev_obj obj;
> - unsigned char addr[ETH_ALEN];
> - u16 vid;
> - u16 ndm_state;
> -};
> -
> -#define SWITCHDEV_OBJ_PORT_FDB(obj) \
> - container_of(obj, struct switchdev_obj_port_fdb, obj)
> -
> /* SWITCHDEV_OBJ_ID_PORT_MDB */
> struct switchdev_obj_port_mdb {
> struct switchdev_obj obj;
> @@ -135,8 +123,6 @@ typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj);
> * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*).
> *
> * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*).
> - *
> - * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj_*).
> */
> struct switchdev_ops {
> int (*switchdev_port_attr_get)(struct net_device *dev,
> @@ -149,9 +135,6 @@ struct switchdev_ops {
> struct switchdev_trans *trans);
> int (*switchdev_port_obj_del)(struct net_device *dev,
> const struct switchdev_obj *obj);
> - int (*switchdev_port_obj_dump)(struct net_device *dev,
> - struct switchdev_obj *obj,
> - switchdev_obj_dump_cb_t *cb);
> };
>
> enum switchdev_notifier_type {
> @@ -189,25 +172,10 @@ int switchdev_port_obj_add(struct net_device *dev,
> const struct switchdev_obj *obj);
> int switchdev_port_obj_del(struct net_device *dev,
> const struct switchdev_obj *obj);
> -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj,
> - switchdev_obj_dump_cb_t *cb);
> int register_switchdev_notifier(struct notifier_block *nb);
> int unregister_switchdev_notifier(struct notifier_block *nb);
> int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
> struct switchdev_notifier_info *info);
> -int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
> - struct net_device *dev, u32 filter_mask,
> - int nlflags);
> -int switchdev_port_bridge_setlink(struct net_device *dev,
> - struct nlmsghdr *nlh, u16 flags);
> -int switchdev_port_bridge_dellink(struct net_device *dev,
> - struct nlmsghdr *nlh, u16 flags);
> -int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
> - struct net_device *dev, const unsigned char *addr,
> - u16 vid, u16 nlm_flags);
> -int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
> - struct net_device *dev, const unsigned char *addr,
> - u16 vid);
> void switchdev_port_fwd_mark_set(struct net_device *dev,
> struct net_device *group_dev,
> bool joining);
> @@ -246,13 +214,6 @@ static inline int switchdev_port_obj_del(struct net_device *dev,
> return -EOPNOTSUPP;
> }
>
> -static inline int switchdev_port_obj_dump(struct net_device *dev,
> - const struct switchdev_obj *obj,
> - switchdev_obj_dump_cb_t *cb)
> -{
> - return -EOPNOTSUPP;
> -}
> -
> static inline int register_switchdev_notifier(struct notifier_block *nb)
> {
> return 0;
> @@ -270,42 +231,6 @@ static inline int call_switchdev_notifiers(unsigned long val,
> return NOTIFY_DONE;
> }
>
> -static inline int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid,
> - u32 seq, struct net_device *dev,
> - u32 filter_mask, int nlflags)
> -{
> - return -EOPNOTSUPP;
> -}
> -
> -static inline int switchdev_port_bridge_setlink(struct net_device *dev,
> - struct nlmsghdr *nlh,
> - u16 flags)
> -{
> - return -EOPNOTSUPP;
> -}
> -
> -static inline int switchdev_port_bridge_dellink(struct net_device *dev,
> - struct nlmsghdr *nlh,
> - u16 flags)
> -{
> - return -EOPNOTSUPP;
> -}
> -
> -static inline int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
> - struct net_device *dev,
> - const unsigned char *addr,
> - u16 vid, u16 nlm_flags)
> -{
> - return -EOPNOTSUPP;
> -}
> -
> -static inline int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
> - struct net_device *dev,
> - const unsigned char *addr, u16 vid)
> -{
> - return -EOPNOTSUPP;
> -}
> -
> static inline bool switchdev_port_same_parent_id(struct net_device *a,
> struct net_device *b)
> {
> diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
> index 3d32981..0531b41 100644
> --- a/net/switchdev/switchdev.c
> +++ b/net/switchdev/switchdev.c
> @@ -343,8 +343,6 @@ static size_t switchdev_obj_size(const struct switchdev_obj *obj)
> switch (obj->id) {
> case SWITCHDEV_OBJ_ID_PORT_VLAN:
> return sizeof(struct switchdev_obj_port_vlan);
> - case SWITCHDEV_OBJ_ID_PORT_FDB:
> - return sizeof(struct switchdev_obj_port_fdb);
> case SWITCHDEV_OBJ_ID_PORT_MDB:
> return sizeof(struct switchdev_obj_port_mdb);
> default:
> @@ -534,43 +532,6 @@ int switchdev_port_obj_del(struct net_device *dev,
> }
> EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
>
> -/**
> - * switchdev_port_obj_dump - Dump port objects
> - *
> - * @dev: port device
> - * @id: object ID
> - * @obj: object to dump
> - * @cb: function to call with a filled object
> - *
> - * rtnl_lock must be held.
> - */
> -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj,
> - switchdev_obj_dump_cb_t *cb)
> -{
> - const struct switchdev_ops *ops = dev->switchdev_ops;
> - struct net_device *lower_dev;
> - struct list_head *iter;
> - int err = -EOPNOTSUPP;
> -
> - ASSERT_RTNL();
> -
> - if (ops && ops->switchdev_port_obj_dump)
> - return ops->switchdev_port_obj_dump(dev, obj, cb);
> -
> - /* Switch device port(s) may be stacked under
> - * bond/team/vlan dev, so recurse down to dump objects on
> - * first port at bottom of stack.
> - */
> -
> - netdev_for_each_lower_dev(dev, lower_dev, iter) {
> - err = switchdev_port_obj_dump(lower_dev, obj, cb);
> - break;
> - }
> -
> - return err;
> -}
> -EXPORT_SYMBOL_GPL(switchdev_port_obj_dump);
> -
> static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain);
>
> /**
> @@ -613,402 +574,6 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
> }
> EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
>
> -struct switchdev_vlan_dump {
> - struct switchdev_obj_port_vlan vlan;
> - struct sk_buff *skb;
> - u32 filter_mask;
> - u16 flags;
> - u16 begin;
> - u16 end;
> -};
> -
> -static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump)
> -{
> - struct bridge_vlan_info vinfo;
> -
> - vinfo.flags = dump->flags;
> -
> - if (dump->begin == 0 && dump->end == 0) {
> - return 0;
> - } else if (dump->begin == dump->end) {
> - vinfo.vid = dump->begin;
> - if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
> - sizeof(vinfo), &vinfo))
> - return -EMSGSIZE;
> - } else {
> - vinfo.vid = dump->begin;
> - vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN;
> - if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
> - sizeof(vinfo), &vinfo))
> - return -EMSGSIZE;
> - vinfo.vid = dump->end;
> - vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN;
> - vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_END;
> - if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
> - sizeof(vinfo), &vinfo))
> - return -EMSGSIZE;
> - }
> -
> - return 0;
> -}
> -
> -static int switchdev_port_vlan_dump_cb(struct switchdev_obj *obj)
> -{
> - struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
> - struct switchdev_vlan_dump *dump =
> - container_of(vlan, struct switchdev_vlan_dump, vlan);
> - int err = 0;
> -
> - if (vlan->vid_begin > vlan->vid_end)
> - return -EINVAL;
> -
> - if (dump->filter_mask & RTEXT_FILTER_BRVLAN) {
> - dump->flags = vlan->flags;
> - for (dump->begin = dump->end = vlan->vid_begin;
> - dump->begin <= vlan->vid_end;
> - dump->begin++, dump->end++) {
> - err = switchdev_port_vlan_dump_put(dump);
> - if (err)
> - return err;
> - }
> - } else if (dump->filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) {
> - if (dump->begin > vlan->vid_begin &&
> - dump->begin >= vlan->vid_end) {
> - if ((dump->begin - 1) == vlan->vid_end &&
> - dump->flags == vlan->flags) {
> - /* prepend */
> - dump->begin = vlan->vid_begin;
> - } else {
> - err = switchdev_port_vlan_dump_put(dump);
> - dump->flags = vlan->flags;
> - dump->begin = vlan->vid_begin;
> - dump->end = vlan->vid_end;
> - }
> - } else if (dump->end <= vlan->vid_begin &&
> - dump->end < vlan->vid_end) {
> - if ((dump->end + 1) == vlan->vid_begin &&
> - dump->flags == vlan->flags) {
> - /* append */
> - dump->end = vlan->vid_end;
> - } else {
> - err = switchdev_port_vlan_dump_put(dump);
> - dump->flags = vlan->flags;
> - dump->begin = vlan->vid_begin;
> - dump->end = vlan->vid_end;
> - }
> - } else {
> - err = -EINVAL;
> - }
> - }
> -
> - return err;
> -}
> -
> -static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev,
> - u32 filter_mask)
> -{
> - struct switchdev_vlan_dump dump = {
> - .vlan.obj.orig_dev = dev,
> - .vlan.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
> - .skb = skb,
> - .filter_mask = filter_mask,
> - };
> - int err = 0;
> -
> - if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
> - (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
> - err = switchdev_port_obj_dump(dev, &dump.vlan.obj,
> - switchdev_port_vlan_dump_cb);
> - if (err)
> - goto err_out;
> - if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
> - /* last one */
> - err = switchdev_port_vlan_dump_put(&dump);
> - }
> -
> -err_out:
> - return err == -EOPNOTSUPP ? 0 : err;
> -}
> -
> -/**
> - * switchdev_port_bridge_getlink - Get bridge port attributes
> - *
> - * @dev: port device
> - *
> - * Called for SELF on rtnl_bridge_getlink to get bridge port
> - * attributes.
> - */
> -int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
> - struct net_device *dev, u32 filter_mask,
> - int nlflags)
> -{
> - struct switchdev_attr attr = {
> - .orig_dev = dev,
> - .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
> - };
> - u16 mode = BRIDGE_MODE_UNDEF;
> - u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD;
> - int err;
> -
> - if (!netif_is_bridge_port(dev))
> - return -EOPNOTSUPP;
> -
> - err = switchdev_port_attr_get(dev, &attr);
> - if (err && err != -EOPNOTSUPP)
> - return err;
> -
> - return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode,
> - attr.u.brport_flags, mask, nlflags,
> - filter_mask, switchdev_port_vlan_fill);
> -}
> -EXPORT_SYMBOL_GPL(switchdev_port_bridge_getlink);
> -
> -static int switchdev_port_br_setflag(struct net_device *dev,
> - struct nlattr *nlattr,
> - unsigned long brport_flag)
> -{
> - struct switchdev_attr attr = {
> - .orig_dev = dev,
> - .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
> - };
> - u8 flag = nla_get_u8(nlattr);
> - int err;
> -
> - err = switchdev_port_attr_get(dev, &attr);
> - if (err)
> - return err;
> -
> - if (flag)
> - attr.u.brport_flags |= brport_flag;
> - else
> - attr.u.brport_flags &= ~brport_flag;
> -
> - return switchdev_port_attr_set(dev, &attr);
> -}
> -
> -static const struct nla_policy
> -switchdev_port_bridge_policy[IFLA_BRPORT_MAX + 1] = {
> - [IFLA_BRPORT_STATE] = { .type = NLA_U8 },
> - [IFLA_BRPORT_COST] = { .type = NLA_U32 },
> - [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 },
> - [IFLA_BRPORT_MODE] = { .type = NLA_U8 },
> - [IFLA_BRPORT_GUARD] = { .type = NLA_U8 },
> - [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 },
> - [IFLA_BRPORT_FAST_LEAVE] = { .type = NLA_U8 },
> - [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 },
> - [IFLA_BRPORT_LEARNING_SYNC] = { .type = NLA_U8 },
> - [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
> -};
> -
> -static int switchdev_port_br_setlink_protinfo(struct net_device *dev,
> - struct nlattr *protinfo)
> -{
> - struct nlattr *attr;
> - int rem;
> - int err;
> -
> - err = nla_validate_nested(protinfo, IFLA_BRPORT_MAX,
> - switchdev_port_bridge_policy, NULL);
> - if (err)
> - return err;
> -
> - nla_for_each_nested(attr, protinfo, rem) {
> - switch (nla_type(attr)) {
> - case IFLA_BRPORT_LEARNING:
> - err = switchdev_port_br_setflag(dev, attr,
> - BR_LEARNING);
> - break;
> - case IFLA_BRPORT_LEARNING_SYNC:
> - err = switchdev_port_br_setflag(dev, attr,
> - BR_LEARNING_SYNC);
> - break;
> - case IFLA_BRPORT_UNICAST_FLOOD:
> - err = switchdev_port_br_setflag(dev, attr, BR_FLOOD);
> - break;
> - default:
> - err = -EOPNOTSUPP;
> - break;
> - }
> - if (err)
> - return err;
> - }
> -
> - return 0;
> -}
> -
> -static int switchdev_port_br_afspec(struct net_device *dev,
> - struct nlattr *afspec,
> - int (*f)(struct net_device *dev,
> - const struct switchdev_obj *obj))
> -{
> - struct nlattr *attr;
> - struct bridge_vlan_info *vinfo;
> - struct switchdev_obj_port_vlan vlan = {
> - .obj.orig_dev = dev,
> - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
> - };
> - int rem;
> - int err;
> -
> - nla_for_each_nested(attr, afspec, rem) {
> - if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO)
> - continue;
> - if (nla_len(attr) != sizeof(struct bridge_vlan_info))
> - return -EINVAL;
> - vinfo = nla_data(attr);
> - if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK)
> - return -EINVAL;
> - vlan.flags = vinfo->flags;
> - if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
> - if (vlan.vid_begin)
> - return -EINVAL;
> - vlan.vid_begin = vinfo->vid;
> - /* don't allow range of pvids */
> - if (vlan.flags & BRIDGE_VLAN_INFO_PVID)
> - return -EINVAL;
> - } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) {
> - if (!vlan.vid_begin)
> - return -EINVAL;
> - vlan.vid_end = vinfo->vid;
> - if (vlan.vid_end <= vlan.vid_begin)
> - return -EINVAL;
> - err = f(dev, &vlan.obj);
> - if (err)
> - return err;
> - vlan.vid_begin = 0;
> - } else {
> - if (vlan.vid_begin)
> - return -EINVAL;
> - vlan.vid_begin = vinfo->vid;
> - vlan.vid_end = vinfo->vid;
> - err = f(dev, &vlan.obj);
> - if (err)
> - return err;
> - vlan.vid_begin = 0;
> - }
> - }
> -
> - return 0;
> -}
> -
> -/**
> - * switchdev_port_bridge_setlink - Set bridge port attributes
> - *
> - * @dev: port device
> - * @nlh: netlink header
> - * @flags: netlink flags
> - *
> - * Called for SELF on rtnl_bridge_setlink to set bridge port
> - * attributes.
> - */
> -int switchdev_port_bridge_setlink(struct net_device *dev,
> - struct nlmsghdr *nlh, u16 flags)
> -{
> - struct nlattr *protinfo;
> - struct nlattr *afspec;
> - int err = 0;
> -
> - if (!netif_is_bridge_port(dev))
> - return -EOPNOTSUPP;
> -
> - protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
> - IFLA_PROTINFO);
> - if (protinfo) {
> - err = switchdev_port_br_setlink_protinfo(dev, protinfo);
> - if (err)
> - return err;
> - }
> -
> - afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
> - IFLA_AF_SPEC);
> - if (afspec)
> - err = switchdev_port_br_afspec(dev, afspec,
> - switchdev_port_obj_add);
> -
> - return err;
> -}
> -EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink);
> -
> -/**
> - * switchdev_port_bridge_dellink - Set bridge port attributes
> - *
> - * @dev: port device
> - * @nlh: netlink header
> - * @flags: netlink flags
> - *
> - * Called for SELF on rtnl_bridge_dellink to set bridge port
> - * attributes.
> - */
> -int switchdev_port_bridge_dellink(struct net_device *dev,
> - struct nlmsghdr *nlh, u16 flags)
> -{
> - struct nlattr *afspec;
> -
> - if (!netif_is_bridge_port(dev))
> - return -EOPNOTSUPP;
> -
> - afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
> - IFLA_AF_SPEC);
> - if (afspec)
> - return switchdev_port_br_afspec(dev, afspec,
> - switchdev_port_obj_del);
> -
> - return 0;
> -}
> -EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink);
> -
> -/**
> - * switchdev_port_fdb_add - Add FDB (MAC/VLAN) entry to port
> - *
> - * @ndmsg: netlink hdr
> - * @nlattr: netlink attributes
> - * @dev: port device
> - * @addr: MAC address to add
> - * @vid: VLAN to add
> - *
> - * Add FDB entry to switch device.
> - */
> -int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
> - struct net_device *dev, const unsigned char *addr,
> - u16 vid, u16 nlm_flags)
> -{
> - struct switchdev_obj_port_fdb fdb = {
> - .obj.orig_dev = dev,
> - .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
> - .vid = vid,
> - };
> -
> - ether_addr_copy(fdb.addr, addr);
> - return switchdev_port_obj_add(dev, &fdb.obj);
> -}
> -EXPORT_SYMBOL_GPL(switchdev_port_fdb_add);
> -
> -/**
> - * switchdev_port_fdb_del - Delete FDB (MAC/VLAN) entry from port
> - *
> - * @ndmsg: netlink hdr
> - * @nlattr: netlink attributes
> - * @dev: port device
> - * @addr: MAC address to delete
> - * @vid: VLAN to delete
> - *
> - * Delete FDB entry from switch device.
> - */
> -int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
> - struct net_device *dev, const unsigned char *addr,
> - u16 vid)
> -{
> - struct switchdev_obj_port_fdb fdb = {
> - .obj.orig_dev = dev,
> - .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
> - .vid = vid,
> - };
> -
> - ether_addr_copy(fdb.addr, addr);
> - return switchdev_port_obj_del(dev, &fdb.obj);
> -}
> -EXPORT_SYMBOL_GPL(switchdev_port_fdb_del);
> -
> bool switchdev_port_same_parent_id(struct net_device *a,
> struct net_device *b)
> {
>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
^ permalink raw reply
* Re: [PATCH net-next v3 12/13] net: bridge: Remove FDB deletion through switchdev object
From: Ivan Vecera @ 2017-08-07 10:31 UTC (permalink / raw)
To: Arkadi Sharshevsky, netdev
Cc: davem, jiri, f.fainelli, andrew, vivien.didelot, Woojung.Huh,
mlxsw
In-Reply-To: <1502025351-41261-13-git-send-email-arkadis@mellanox.com>
On 6.8.2017 15:15, Arkadi Sharshevsky wrote:
> At this point no driver supports FDB add/del through switchdev object
> but rather via notification chain, thus, it is removed.
>
> Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
> Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
> ---
> net/bridge/br_fdb.c | 18 ------------------
> 1 file changed, 18 deletions(-)
>
> diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
> index a5e4a73..a79b648 100644
> --- a/net/bridge/br_fdb.c
> +++ b/net/bridge/br_fdb.c
> @@ -169,29 +169,11 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr)
> }
> }
>
> -static void fdb_del_external_learn(struct net_bridge_fdb_entry *f)
> -{
> - struct switchdev_obj_port_fdb fdb = {
> - .obj = {
> - .orig_dev = f->dst->dev,
> - .id = SWITCHDEV_OBJ_ID_PORT_FDB,
> - .flags = SWITCHDEV_F_DEFER,
> - },
> - .vid = f->vlan_id,
> - };
> -
> - ether_addr_copy(fdb.addr, f->addr.addr);
> - switchdev_port_obj_del(f->dst->dev, &fdb.obj);
> -}
> -
> static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
> {
> if (f->is_static)
> fdb_del_hw_addr(br, f->addr.addr);
>
> - if (f->added_by_external_learn)
> - fdb_del_external_learn(f);
> -
> hlist_del_init_rcu(&f->hlist);
> fdb_notify(br, f, RTM_DELNEIGH);
> call_rcu(&f->rcu, fdb_rcu_free);
>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
^ permalink raw reply
* Re: [PATCH net-next v3 13/13] net: switchdev: Remove bridge bypass support from switchdev
From: Jiri Pirko @ 2017-08-07 10:26 UTC (permalink / raw)
To: Arkadi Sharshevsky
Cc: netdev, davem, ivecera, f.fainelli, andrew, vivien.didelot,
Woojung.Huh, mlxsw
In-Reply-To: <1502025351-41261-14-git-send-email-arkadis@mellanox.com>
Sun, Aug 06, 2017 at 03:15:51PM CEST, arkadis@mellanox.com wrote:
>Currently the bridge port flags, vlans, FDBs and MDBs can be offloaded
>through the bridge code, making the switchdev's SELF bridge bypass
>implementation to be redundant. This implies several changes:
>- No need for dump infra in switchdev, DSA's special case is handled
> privately.
>- Remove obj_dump from switchdev_ops.
>- FDBs are removed from obj_add/del routines, due to the fact that they
> are offloaded through the bridge notification chain.
>- The switchdev_port_bridge_xx() and switchdev_port_fdb_xx() functions
> can be removed.
>
>Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
>Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
^ permalink raw reply
* [for-next 5/8] net/mlx5: Add CONFIG_MLX5_ESWITCH Kconfig
From: Saeed Mahameed @ 2017-08-07 10:18 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Leon Romanovsky, Saeed Mahameed, Jes Sorensen,
kernel-team
In-Reply-To: <20170807101808.22924-1-saeedm@mellanox.com>
Allow to selectively build the driver with or without sriov eswitch, VF
representors and TC offloads.
Also remove the need of two ndo ops structures (sriov & basic)
and keep only one unified ndo ops, compile out VF SRIOV ndos when not
needed (MLX5_ESWITCH=n), and for VF netdev calling those ndos will result
in returning -EPERM.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Jes Sorensen <jsorensen@fb.com>
Cc: kernel-team@fb.com
---
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 11 +++++
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 9 ++--
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 53 +++++++----------------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 8 ++++
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 7 +++
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 4 --
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 23 +++++++---
drivers/net/ethernet/mellanox/mlx5/core/main.c | 10 +----
drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 14 +-----
10 files changed, 69 insertions(+), 72 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index d7174295b6ef..fdaef00465d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -44,6 +44,17 @@ config MLX5_MPFS
is enabled to allow passing user configured unicast MAC addresses to the
requesting PF.
+config MLX5_ESWITCH
+ bool "Mellanox Technologies MLX5 SRIOV E-Switch support"
+ depends on MLX5_CORE_EN
+ default y
+ ---help---
+ Mellanox Technologies Ethernet SRIOV E-Switch support in ConnectX NIC.
+ E-Switch provides internal SRIOV packet steering and switching for the
+ enabled VFs and PF in two available modes:
+ Legacy SRIOV mode (L2 mac vlan steering based).
+ Switchdev mode (eswitch offloads).
+
config MLX5_CORE_EN_DCB
bool "Data Center Bridging (DCB) Support"
default y
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index c867e48f8a4c..22ed657d263a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -11,13 +11,14 @@ mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o
mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
fpga/ipsec.o
-mlx5_core-$(CONFIG_MLX5_CORE_EN) += eswitch.o eswitch_offloads.o \
- en_main.o en_common.o en_fs.o en_ethtool.o en_tx.o \
- en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \
- en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o en_selftest.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
+ en_tx.o en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \
+ en_arfs.o en_fs_ethtool.o en_selftest.o
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o
+
mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o
mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e3c858c44532..b19e9d235008 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3025,6 +3025,7 @@ static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle,
u32 chain_index, __be16 proto,
struct tc_to_netdev *tc)
{
+#ifdef CONFIG_MLX5_ESWITCH
struct mlx5e_priv *priv = netdev_priv(dev);
if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS))
@@ -3048,6 +3049,7 @@ static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle,
}
mqprio:
+#endif
if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
@@ -3350,6 +3352,7 @@ static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
}
}
+#ifdef CONFIG_MLX5_ESWITCH
static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
{
struct mlx5e_priv *priv = netdev_priv(dev);
@@ -3452,6 +3455,7 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
return mlx5_eswitch_get_vport_stats(mdev->priv.eswitch, vf + 1,
vf_stats);
}
+#endif
static void mlx5e_add_vxlan_port(struct net_device *netdev,
struct udp_tunnel_info *ti)
@@ -3685,7 +3689,7 @@ static void mlx5e_netpoll(struct net_device *dev)
}
#endif
-static const struct net_device_ops mlx5e_netdev_ops_basic = {
+static const struct net_device_ops mlx5e_netdev_ops = {
.ndo_open = mlx5e_open,
.ndo_stop = mlx5e_close,
.ndo_start_xmit = mlx5e_xmit,
@@ -3711,34 +3715,7 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = {
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = mlx5e_netpoll,
#endif
-};
-
-static const struct net_device_ops mlx5e_netdev_ops_sriov = {
- .ndo_open = mlx5e_open,
- .ndo_stop = mlx5e_close,
- .ndo_start_xmit = mlx5e_xmit,
- .ndo_setup_tc = mlx5e_ndo_setup_tc,
- .ndo_select_queue = mlx5e_select_queue,
- .ndo_get_stats64 = mlx5e_get_stats,
- .ndo_set_rx_mode = mlx5e_set_rx_mode,
- .ndo_set_mac_address = mlx5e_set_mac,
- .ndo_vlan_rx_add_vid = mlx5e_vlan_rx_add_vid,
- .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid,
- .ndo_set_features = mlx5e_set_features,
- .ndo_change_mtu = mlx5e_change_mtu,
- .ndo_do_ioctl = mlx5e_ioctl,
- .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate,
- .ndo_udp_tunnel_add = mlx5e_add_vxlan_port,
- .ndo_udp_tunnel_del = mlx5e_del_vxlan_port,
- .ndo_features_check = mlx5e_features_check,
-#ifdef CONFIG_RFS_ACCEL
- .ndo_rx_flow_steer = mlx5e_rx_flow_steer,
-#endif
- .ndo_tx_timeout = mlx5e_tx_timeout,
- .ndo_xdp = mlx5e_xdp,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = mlx5e_netpoll,
-#endif
+#ifdef CONFIG_MLX5_ESWITCH
/* SRIOV E-Switch NDOs */
.ndo_set_vf_mac = mlx5e_set_vf_mac,
.ndo_set_vf_vlan = mlx5e_set_vf_vlan,
@@ -3750,6 +3727,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
.ndo_get_vf_stats = mlx5e_get_vf_stats,
.ndo_has_offload_stats = mlx5e_has_offload_stats,
.ndo_get_offload_stats = mlx5e_get_offload_stats,
+#endif
};
static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -3979,9 +3957,11 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
}
}
+#if IS_ENABLED(CONFIG_NET_SWITCHDEV) && IS_ENABLED(CONFIG_MLX5_ESWITCH)
static const struct switchdev_ops mlx5e_switchdev_ops = {
.switchdev_port_attr_get = mlx5e_attr_get,
};
+#endif
static void mlx5e_build_nic_netdev(struct net_device *netdev)
{
@@ -3992,15 +3972,12 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
- if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
- netdev->netdev_ops = &mlx5e_netdev_ops_sriov;
+ netdev->netdev_ops = &mlx5e_netdev_ops;
+
#ifdef CONFIG_MLX5_CORE_EN_DCB
- if (MLX5_CAP_GEN(mdev, qos))
- netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
+ if (MLX5_CAP_GEN(mdev, vport_group_manager) && MLX5_CAP_GEN(mdev, qos))
+ netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
#endif
- } else {
- netdev->netdev_ops = &mlx5e_netdev_ops_basic;
- }
netdev->watchdog_timeo = 15 * HZ;
@@ -4072,7 +4049,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
mlx5e_set_netdev_dev_addr(netdev);
-#ifdef CONFIG_NET_SWITCHDEV
+#if IS_ENABLED(CONFIG_NET_SWITCHDEV) && IS_ENABLED(CONFIG_MLX5_ESWITCH)
if (MLX5_VPORT_MANAGER(mdev))
netdev->switchdev_ops = &mlx5e_switchdev_ops;
#endif
@@ -4431,6 +4408,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
if (err)
return NULL;
+#ifdef CONFIG_MLX5_ESWITCH
if (MLX5_VPORT_MANAGER(mdev)) {
rpriv = mlx5e_alloc_nic_rep_priv(mdev);
if (!rpriv) {
@@ -4438,6 +4416,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
return NULL;
}
}
+#endif
netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, rpriv);
if (!netdev) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 23e43bbf928d..5659ed9f51e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -38,6 +38,7 @@
#include "eswitch.h"
#include "en.h"
+#ifdef CONFIG_MLX5_ESWITCH
struct mlx5e_neigh_update_table {
struct rhashtable neigh_ht;
/* Save the neigh hash entries in a list in addition to the hash table
@@ -142,5 +143,12 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
struct mlx5e_encap_entry *e);
void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
+#else /* CONFIG_MLX5_ESWITCH */
+static inline void mlx5e_register_vport_reps(struct mlx5e_priv *priv) {}
+static inline void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv) {}
+static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
+static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) {}
+#endif
#endif /* __MLX5E_REP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 325b2c8c1c6d..8e224bcbc6a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -857,6 +857,7 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
&wqe->next.next_wqe_index);
}
+#ifdef CONFIG_MLX5_ESWITCH
void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
{
struct net_device *netdev = rq->netdev;
@@ -901,6 +902,7 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
&wqe->next.next_wqe_index);
}
+#endif
static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
struct mlx5_cqe64 *cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index ecbe30d808ae..36473ec65ce8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -35,6 +35,7 @@
#define MLX5E_TC_FLOW_ID_MASK 0x0000ffff
+#ifdef CONFIG_MLX5_ESWITCH
int mlx5e_tc_init(struct mlx5e_priv *priv);
void mlx5e_tc_cleanup(struct mlx5e_priv *priv);
@@ -60,4 +61,10 @@ static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv)
return atomic_read(&priv->fs.tc.ht.nelems);
}
+#else /* CONFIG_MLX5_ESWITCH */
+static inline int mlx5e_tc_init(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_tc_cleanup(struct mlx5e_priv *priv) {}
+static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) { return 0; }
+#endif
+
#endif /* __MLX5_EN_TC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 24d2f707fdfc..de704ff5619a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -36,9 +36,7 @@
#include <linux/mlx5/cmd.h>
#include "mlx5_core.h"
#include "fpga/core.h"
-#ifdef CONFIG_MLX5_CORE_EN
#include "eswitch.h"
-#endif
enum {
MLX5_EQE_SIZE = sizeof(struct mlx5_eqe),
@@ -467,11 +465,9 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
}
break;
-#ifdef CONFIG_MLX5_CORE_EN
case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
mlx5_eswitch_vport_event(dev->priv.eswitch, eqe);
break;
-#endif
case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
mlx5_port_module_event(dev, eqe);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 701d228de4ad..565c8b7a399a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -39,6 +39,14 @@
#include <linux/mlx5/device.h>
#include "lib/mpfs.h"
+enum {
+ SRIOV_NONE,
+ SRIOV_LEGACY,
+ SRIOV_OFFLOADS
+};
+
+#ifdef CONFIG_MLX5_ESWITCH
+
#define MLX5_MAX_UC_PER_VPORT(dev) \
(1 << MLX5_CAP_GEN(dev, log_max_current_uc_list))
@@ -125,12 +133,6 @@ struct mlx5_eswitch_fdb {
};
};
-enum {
- SRIOV_NONE,
- SRIOV_LEGACY,
- SRIOV_OFFLOADS
-};
-
struct mlx5_esw_sq {
struct mlx5_flow_handle *send_to_vport_rule;
struct list_head list;
@@ -292,4 +294,13 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
#define esw_debug(dev, format, ...) \
mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
+#else /* CONFIG_MLX5_ESWITCH */
+/* eswitch API stubs */
+static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
+static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
+static inline void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe) {}
+static inline int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
+static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
+#endif /* CONFIG_MLX5_ESWITCH */
+
#endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d4a9c9b7b6a2..124c7c3c3a00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -54,9 +54,7 @@
#include "mlx5_core.h"
#include "fs_core.h"
#include "lib/mpfs.h"
-#ifdef CONFIG_MLX5_CORE_EN
#include "eswitch.h"
-#endif
#include "lib/mlx5.h"
#include "fpga/core.h"
#include "accel/ipsec.h"
@@ -953,13 +951,11 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
goto err_rl_cleanup;
}
-#ifdef CONFIG_MLX5_CORE_EN
err = mlx5_eswitch_init(dev);
if (err) {
dev_err(&pdev->dev, "Failed to init eswitch %d\n", err);
goto err_mpfs_cleanup;
}
-#endif
err = mlx5_sriov_init(dev);
if (err) {
@@ -978,10 +974,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
err_sriov_cleanup:
mlx5_sriov_cleanup(dev);
err_eswitch_cleanup:
-#ifdef CONFIG_MLX5_CORE_EN
mlx5_eswitch_cleanup(dev->priv.eswitch);
err_mpfs_cleanup:
-#endif
mlx5_mpfs_cleanup(dev);
err_rl_cleanup:
mlx5_cleanup_rl_table(dev);
@@ -1002,9 +996,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
{
mlx5_fpga_cleanup(dev);
mlx5_sriov_cleanup(dev);
-#ifdef CONFIG_MLX5_CORE_EN
mlx5_eswitch_cleanup(dev->priv.eswitch);
-#endif
mlx5_mpfs_cleanup(dev);
mlx5_cleanup_rl_table(dev);
mlx5_cleanup_reserved_gids(dev);
@@ -1311,7 +1303,7 @@ struct mlx5_core_event_handler {
};
static const struct devlink_ops mlx5_devlink_ops = {
-#ifdef CONFIG_MLX5_CORE_EN
+#ifdef CONFIG_MLX5_ESWITCH
.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
.eswitch_mode_get = mlx5_devlink_eswitch_mode_get,
.eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index bf99d40e30b4..5e7ffc9fad78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -33,9 +33,7 @@
#include <linux/pci.h>
#include <linux/mlx5/driver.h>
#include "mlx5_core.h"
-#ifdef CONFIG_MLX5_CORE_EN
#include "eswitch.h"
-#endif
bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev)
{
@@ -57,14 +55,12 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
return -EBUSY;
}
-#ifdef CONFIG_MLX5_CORE_EN
err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
if (err) {
mlx5_core_warn(dev,
"failed to enable eswitch SRIOV (%d)\n", err);
return err;
}
-#endif
for (vf = 0; vf < num_vfs; vf++) {
err = mlx5_core_enable_hca(dev, vf + 1);
@@ -88,11 +84,7 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
int vf;
if (!sriov->enabled_vfs)
-#ifdef CONFIG_MLX5_CORE_EN
- goto disable_sriov_resources;
-#else
- return;
-#endif
+ goto out;
for (vf = 0; vf < sriov->num_vfs; vf++) {
if (!sriov->vfs_ctx[vf].enabled)
@@ -106,10 +98,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
sriov->enabled_vfs--;
}
-#ifdef CONFIG_MLX5_CORE_EN
-disable_sriov_resources:
+out:
mlx5_eswitch_disable_sriov(dev->priv.eswitch);
-#endif
if (mlx5_wait_for_vf_pages(dev))
mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
--
2.13.0
^ permalink raw reply related
* [for-next 7/8] net/mlx5: Fix counter list hardware structure
From: Saeed Mahameed @ 2017-08-07 10:18 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Leon Romanovsky, Rabie Loulou, Saeed Mahameed
In-Reply-To: <20170807101808.22924-1-saeedm@mellanox.com>
From: Rabie Loulou <rabiel@mellanox.com>
The counter list hardware structure doesn't contain a clear and
num_of_counters fields, remove them.
These wrong fields were never used by the driver hence no other driver
changes.
Fixes: a351a1b03bf1 ("net/mlx5: Introduce bulk reading of flow counters")
Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
include/linux/mlx5/mlx5_ifc.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3030121b4746..f847a3a57913 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1071,8 +1071,7 @@ struct mlx5_ifc_dest_format_struct_bits {
};
struct mlx5_ifc_flow_counter_list_bits {
- u8 clear[0x1];
- u8 num_of_counters[0xf];
+ u8 reserved_at_0[0x10];
u8 flow_counter_id[0x10];
u8 reserved_at_20[0x20];
--
2.13.0
^ permalink raw reply related
* [for-next 2/8] net/mlx5e: NIC netdev init flow cleanup
From: Saeed Mahameed @ 2017-08-07 10:18 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Leon Romanovsky, Saeed Mahameed
In-Reply-To: <20170807101808.22924-1-saeedm@mellanox.com>
Remove redundant call to unregister vport representor in mlx5e_add error
flow.
Hide the representor priv and eswitch internal structures from en_main.c
as preparation step for downstream patches which would allow building
the driver without support for representors and eswitch.
Fixes: 6f08a22c5fb2 ("net/mlx5e: Register/unregister vport representors on interface attach/detach")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 22 ++++++----------------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 13 +++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 1 +
3 files changed, 20 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c2986777a1d8..b44d6f677845 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4428,32 +4428,27 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
static void *mlx5e_add(struct mlx5_core_dev *mdev)
{
- struct mlx5_eswitch *esw = mdev->priv.eswitch;
- int total_vfs = MLX5_TOTAL_VPORTS(mdev);
- struct mlx5e_rep_priv *rpriv = NULL;
+ struct net_device *netdev;
+ void *rpriv = NULL;
void *priv;
- int vport;
int err;
- struct net_device *netdev;
err = mlx5e_check_required_hca_cap(mdev);
if (err)
return NULL;
if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
- rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
+ rpriv = mlx5e_alloc_nic_rep_priv(mdev);
if (!rpriv) {
- mlx5_core_warn(mdev,
- "Not creating net device, Failed to alloc rep priv data\n");
+ mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
return NULL;
}
- rpriv->rep = &esw->offloads.vport_reps[0];
}
netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, rpriv);
if (!netdev) {
mlx5_core_err(mdev, "mlx5e_create_netdev failed\n");
- goto err_unregister_reps;
+ goto err_free_rpriv;
}
priv = netdev_priv(netdev);
@@ -4474,14 +4469,9 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
err_detach:
mlx5e_detach(mdev, priv);
-
err_destroy_netdev:
mlx5e_destroy_netdev(priv);
-
-err_unregister_reps:
- for (vport = 1; vport < total_vfs; vport++)
- mlx5_eswitch_unregister_vport_rep(esw, vport);
-
+err_free_rpriv:
kfree(rpriv);
return NULL;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 45e60be9c277..a0dd0e7e5b57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1099,3 +1099,16 @@ void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv)
mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */
mlx5_eswitch_unregister_vport_rep(esw, 0); /* UPLINK PF*/
}
+
+void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev)
+{
+ struct mlx5_eswitch *esw = mdev->priv.eswitch;
+ struct mlx5e_rep_priv *rpriv;
+
+ rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
+ if (!rpriv)
+ return NULL;
+
+ rpriv->rep = &esw->offloads.vport_reps[0];
+ return rpriv;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index a0a1a7a1d6c0..23e43bbf928d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -123,6 +123,7 @@ struct mlx5e_encap_entry {
int encap_size;
};
+void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev);
void mlx5e_register_vport_reps(struct mlx5e_priv *priv);
void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv);
bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
--
2.13.0
^ permalink raw reply related
* [for-next 1/8] net/mlx5e: Rearrange netdevice ops structures
From: Saeed Mahameed @ 2017-08-07 10:18 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Leon Romanovsky, Saeed Mahameed
In-Reply-To: <20170807101808.22924-1-saeedm@mellanox.com>
Since we are going to allow building the driver without eswitch support,
it would be possible to compile out the sriov netdevice ops struct such
that the basic ops instance will be used for non VF devices too.
Add missing udp tunnel ndos into mlx5e_netdev_ops_basic.
While here, rearrange some ndos in the sriov ops struct and put
vf/eswitch related ndos towards the end of it.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 57f31fa478ce..c2986777a1d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3706,6 +3706,9 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = {
.ndo_change_mtu = mlx5e_change_mtu,
.ndo_do_ioctl = mlx5e_ioctl,
.ndo_set_tx_maxrate = mlx5e_set_tx_maxrate,
+ .ndo_udp_tunnel_add = mlx5e_add_vxlan_port,
+ .ndo_udp_tunnel_del = mlx5e_del_vxlan_port,
+ .ndo_features_check = mlx5e_features_check,
#ifdef CONFIG_RFS_ACCEL
.ndo_rx_flow_steer = mlx5e_rx_flow_steer,
#endif
@@ -3730,13 +3733,19 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
.ndo_set_features = mlx5e_set_features,
.ndo_change_mtu = mlx5e_change_mtu,
.ndo_do_ioctl = mlx5e_ioctl,
+ .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate,
.ndo_udp_tunnel_add = mlx5e_add_vxlan_port,
.ndo_udp_tunnel_del = mlx5e_del_vxlan_port,
- .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate,
.ndo_features_check = mlx5e_features_check,
#ifdef CONFIG_RFS_ACCEL
.ndo_rx_flow_steer = mlx5e_rx_flow_steer,
#endif
+ .ndo_tx_timeout = mlx5e_tx_timeout,
+ .ndo_xdp = mlx5e_xdp,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = mlx5e_netpoll,
+#endif
+ /* SRIOV E-Switch NDOs */
.ndo_set_vf_mac = mlx5e_set_vf_mac,
.ndo_set_vf_vlan = mlx5e_set_vf_vlan,
.ndo_set_vf_spoofchk = mlx5e_set_vf_spoofchk,
@@ -3745,11 +3754,6 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
.ndo_get_vf_config = mlx5e_get_vf_config,
.ndo_set_vf_link_state = mlx5e_set_vf_link_state,
.ndo_get_vf_stats = mlx5e_get_vf_stats,
- .ndo_tx_timeout = mlx5e_tx_timeout,
- .ndo_xdp = mlx5e_xdp,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = mlx5e_netpoll,
-#endif
.ndo_has_offload_stats = mlx5e_has_offload_stats,
.ndo_get_offload_stats = mlx5e_get_offload_stats,
};
--
2.13.0
^ 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