aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--MAINTAINERS1
-rw-r--r--arch/x86/net/bpf_jit_comp32.c284
-rw-r--r--include/net/xdp_sock.h5
-rw-r--r--include/uapi/linux/bpf.h1
-rw-r--r--kernel/bpf/btf.c12
-rw-r--r--kernel/bpf/core.c4
-rw-r--r--net/core/filter.c2
-rw-r--r--net/xdp/xdp_umem.c21
-rw-r--r--net/xdp/xdp_umem.h1
-rw-r--r--net/xdp/xsk.c87
-rw-r--r--net/xdp/xsk_queue.h2
-rw-r--r--samples/bpf/xdp_redirect_user.c2
-rw-r--r--tools/bpf/bpftool/cgroup.c6
-rw-r--r--tools/include/uapi/linux/bpf.h1
-rw-r--r--tools/testing/selftests/bpf/progs/test_lwt_seg6local.c12
-rw-r--r--tools/testing/selftests/bpf/verifier/basic_instr.c85
16 files changed, 230 insertions, 296 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 3c4d72755127..54691cc484da 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17274,6 +17274,7 @@ N: xdp
XDP SOCKETS (AF_XDP)
M: Björn Töpel <bjorn.topel@intel.com>
M: Magnus Karlsson <magnus.karlsson@intel.com>
+R: Jonathan Lemon <jonathan.lemon@gmail.com>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
S: Maintained
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index b29e82f190c7..1d12d2174085 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -724,9 +724,6 @@ static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
{
u8 *prog = *pprog;
int cnt = 0;
- static int jmp_label1 = -1;
- static int jmp_label2 = -1;
- static int jmp_label3 = -1;
u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
@@ -745,79 +742,23 @@ static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
/* mov ecx,src_lo */
EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
- /* cmp ecx,32 */
- EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
- /* Jumps when >= 32 */
- if (is_imm8(jmp_label(jmp_label1, 2)))
- EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
- else
- EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
- /* < 32 */
- /* shl dreg_hi,cl */
- EMIT2(0xD3, add_1reg(0xE0, dreg_hi));
- /* mov ebx,dreg_lo */
- EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+ /* shld dreg_hi,dreg_lo,cl */
+ EMIT3(0x0F, 0xA5, add_2reg(0xC0, dreg_hi, dreg_lo));
/* shl dreg_lo,cl */
EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
- /* IA32_ECX = -IA32_ECX + 32 */
- /* neg ecx */
- EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
- /* add ecx,32 */
- EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+ /* if ecx >= 32, mov dreg_lo into dreg_hi and clear dreg_lo */
- /* shr ebx,cl */
- EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
- /* or dreg_hi,ebx */
- EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
-
- /* goto out; */
- if (is_imm8(jmp_label(jmp_label3, 2)))
- EMIT2(0xEB, jmp_label(jmp_label3, 2));
- else
- EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
- /* >= 32 */
- if (jmp_label1 == -1)
- jmp_label1 = cnt;
-
- /* cmp ecx,64 */
- EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
- /* Jumps when >= 64 */
- if (is_imm8(jmp_label(jmp_label2, 2)))
- EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
- else
- EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+ /* cmp ecx,32 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+ /* skip the next two instructions (4 bytes) when < 32 */
+ EMIT2(IA32_JB, 4);
- /* >= 32 && < 64 */
- /* sub ecx,32 */
- EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
- /* shl dreg_lo,cl */
- EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
/* mov dreg_hi,dreg_lo */
EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
-
/* xor dreg_lo,dreg_lo */
EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
- /* goto out; */
- if (is_imm8(jmp_label(jmp_label3, 2)))
- EMIT2(0xEB, jmp_label(jmp_label3, 2));
- else
- EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
- /* >= 64 */
- if (jmp_label2 == -1)
- jmp_label2 = cnt;
- /* xor dreg_lo,dreg_lo */
- EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
- /* xor dreg_hi,dreg_hi */
- EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
-
- if (jmp_label3 == -1)
- jmp_label3 = cnt;
-
if (dstk) {
/* mov dword ptr [ebp+off],dreg_lo */
EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -836,9 +777,6 @@ static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
{
u8 *prog = *pprog;
int cnt = 0;
- static int jmp_label1 = -1;
- static int jmp_label2 = -1;
- static int jmp_label3 = -1;
u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
@@ -857,79 +795,23 @@ static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
/* mov ecx,src_lo */
EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
- /* cmp ecx,32 */
- EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
- /* Jumps when >= 32 */
- if (is_imm8(jmp_label(jmp_label1, 2)))
- EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
- else
- EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
- /* < 32 */
- /* lshr dreg_lo,cl */
- EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
- /* mov ebx,dreg_hi */
- EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
- /* ashr dreg_hi,cl */
+ /* shrd dreg_lo,dreg_hi,cl */
+ EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi));
+ /* sar dreg_hi,cl */
EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
- /* IA32_ECX = -IA32_ECX + 32 */
- /* neg ecx */
- EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
- /* add ecx,32 */
- EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
- /* shl ebx,cl */
- EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
- /* or dreg_lo,ebx */
- EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+ /* if ecx >= 32, mov dreg_hi to dreg_lo and set/clear dreg_hi depending on sign */
- /* goto out; */
- if (is_imm8(jmp_label(jmp_label3, 2)))
- EMIT2(0xEB, jmp_label(jmp_label3, 2));
- else
- EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
- /* >= 32 */
- if (jmp_label1 == -1)
- jmp_label1 = cnt;
-
- /* cmp ecx,64 */
- EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
- /* Jumps when >= 64 */
- if (is_imm8(jmp_label(jmp_label2, 2)))
- EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
- else
- EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+ /* cmp ecx,32 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+ /* skip the next two instructions (5 bytes) when < 32 */
+ EMIT2(IA32_JB, 5);
- /* >= 32 && < 64 */
- /* sub ecx,32 */
- EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
- /* ashr dreg_hi,cl */
- EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
/* mov dreg_lo,dreg_hi */
EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
-
- /* ashr dreg_hi,imm8 */
+ /* sar dreg_hi,31 */
EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
- /* goto out; */
- if (is_imm8(jmp_label(jmp_label3, 2)))
- EMIT2(0xEB, jmp_label(jmp_label3, 2));
- else
- EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
- /* >= 64 */
- if (jmp_label2 == -1)
- jmp_label2 = cnt;
- /* ashr dreg_hi,imm8 */
- EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
- /* mov dreg_lo,dreg_hi */
- EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
-
- if (jmp_label3 == -1)
- jmp_label3 = cnt;
-
if (dstk) {
/* mov dword ptr [ebp+off],dreg_lo */
EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -948,9 +830,6 @@ static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
{
u8 *prog = *pprog;
int cnt = 0;
- static int jmp_label1 = -1;
- static int jmp_label2 = -1;
- static int jmp_label3 = -1;
u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
@@ -969,77 +848,23 @@ static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
/* mov ecx,src_lo */
EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
- /* cmp ecx,32 */
- EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
- /* Jumps when >= 32 */
- if (is_imm8(jmp_label(jmp_label1, 2)))
- EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
- else
- EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
- /* < 32 */
- /* lshr dreg_lo,cl */
- EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
- /* mov ebx,dreg_hi */
- EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ /* shrd dreg_lo,dreg_hi,cl */
+ EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi));
/* shr dreg_hi,cl */
EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
- /* IA32_ECX = -IA32_ECX + 32 */
- /* neg ecx */
- EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
- /* add ecx,32 */
- EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
- /* shl ebx,cl */
- EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
- /* or dreg_lo,ebx */
- EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
-
- /* goto out; */
- if (is_imm8(jmp_label(jmp_label3, 2)))
- EMIT2(0xEB, jmp_label(jmp_label3, 2));
- else
- EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+ /* if ecx >= 32, mov dreg_hi to dreg_lo and clear dreg_hi */
- /* >= 32 */
- if (jmp_label1 == -1)
- jmp_label1 = cnt;
- /* cmp ecx,64 */
- EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
- /* Jumps when >= 64 */
- if (is_imm8(jmp_label(jmp_label2, 2)))
- EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
- else
- EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+ /* cmp ecx,32 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+ /* skip the next two instructions (4 bytes) when < 32 */
+ EMIT2(IA32_JB, 4);
- /* >= 32 && < 64 */
- /* sub ecx,32 */
- EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
- /* shr dreg_hi,cl */
- EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
/* mov dreg_lo,dreg_hi */
EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
/* xor dreg_hi,dreg_hi */
EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
- /* goto out; */
- if (is_imm8(jmp_label(jmp_label3, 2)))
- EMIT2(0xEB, jmp_label(jmp_label3, 2));
- else
- EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
- /* >= 64 */
- if (jmp_label2 == -1)
- jmp_label2 = cnt;
- /* xor dreg_lo,dreg_lo */
- EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
- /* xor dreg_hi,dreg_hi */
- EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
-
- if (jmp_label3 == -1)
- jmp_label3 = cnt;
-
if (dstk) {
/* mov dword ptr [ebp+off],dreg_lo */
EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -1069,27 +894,10 @@ static inline void emit_ia32_lsh_i64(const u8 dst[], const u32 val,
}
/* Do LSH operation */
if (val < 32) {
- /* shl dreg_hi,imm8 */
- EMIT3(0xC1, add_1reg(0xE0, dreg_hi), val);
- /* mov ebx,dreg_lo */
- EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+ /* shld dreg_hi,dreg_lo,imm8 */
+ EMIT4(0x0F, 0xA4, add_2reg(0xC0, dreg_hi, dreg_lo), val);
/* shl dreg_lo,imm8 */
EMIT3(0xC1, add_1reg(0xE0, dreg_lo), val);
-
- /* IA32_ECX = 32 - val */
- /* mov ecx,val */
- EMIT2(0xB1, val);
- /* movzx ecx,ecx */
- EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
- /* neg ecx */
- EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
- /* add ecx,32 */
- EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
- /* shr ebx,cl */
- EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
- /* or dreg_hi,ebx */
- EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
} else if (val >= 32 && val < 64) {
u32 value = val - 32;
@@ -1135,27 +943,10 @@ static inline void emit_ia32_rsh_i64(const u8 dst[], const u32 val,
/* Do RSH operation */
if (val < 32) {
- /* shr dreg_lo,imm8 */
- EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
- /* mov ebx,dreg_hi */
- EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ /* shrd dreg_lo,dreg_hi,imm8 */
+ EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val);
/* shr dreg_hi,imm8 */
EMIT3(0xC1, add_1reg(0xE8, dreg_hi), val);
-
- /* IA32_ECX = 32 - val */
- /* mov ecx,val */
- EMIT2(0xB1, val);
- /* movzx ecx,ecx */
- EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
- /* neg ecx */
- EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
- /* add ecx,32 */
- EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
- /* shl ebx,cl */
- EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
- /* or dreg_lo,ebx */
- EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
} else if (val >= 32 && val < 64) {
u32 value = val - 32;
@@ -1200,27 +991,10 @@ static inline void emit_ia32_arsh_i64(const u8 dst[], const u32 val,
}
/* Do RSH operation */
if (val < 32) {
- /* shr dreg_lo,imm8 */
- EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
- /* mov ebx,dreg_hi */
- EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ /* shrd dreg_lo,dreg_hi,imm8 */
+ EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val);
/* ashr dreg_hi,imm8 */
EMIT3(0xC1, add_1reg(0xF8, dreg_hi), val);
-
- /* IA32_ECX = 32 - val */
- /* mov ecx,val */
- EMIT2(0xB1, val);
- /* movzx ecx,ecx */
- EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
- /* neg ecx */
- EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
- /* add ecx,32 */
- EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
- /* shl ebx,cl */
- EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
- /* or dreg_lo,ebx */
- EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
} else if (val >= 32 && val < 64) {
u32 value = val - 32;
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index d074b6d60f8a..7da155164947 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -61,6 +61,11 @@ struct xdp_sock {
struct xsk_queue *tx ____cacheline_aligned_in_smp;
struct list_head list;
bool zc;
+ enum {
+ XSK_READY = 0,
+ XSK_BOUND,
+ XSK_UNBOUND,
+ } state;
/* Protects multiple processes in the control path */
struct mutex mutex;
/* Mutual exclusion of NAPI TX thread and sendmsg error paths
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a8b823c30b43..29a5bc3d5c66 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3143,6 +3143,7 @@ struct bpf_prog_info {
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
__u32 gpl_compatible:1;
+ __u32 :31; /* alignment pad */
__u64 netns_dev;
__u64 netns_ino;
__u32 nr_jited_ksyms;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index cad09858a5f2..546ebee39e2a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1928,8 +1928,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
/* Check array->index_type */
index_type_id = array->index_type;
index_type = btf_type_by_id(btf, index_type_id);
- if (btf_type_is_resolve_source_only(index_type) ||
- btf_type_nosize_or_null(index_type)) {
+ if (btf_type_nosize_or_null(index_type) ||
+ btf_type_is_resolve_source_only(index_type)) {
btf_verifier_log_type(env, v->t, "Invalid index");
return -EINVAL;
}
@@ -1948,8 +1948,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
/* Check array->type */
elem_type_id = array->type;
elem_type = btf_type_by_id(btf, elem_type_id);
- if (btf_type_is_resolve_source_only(elem_type) ||
- btf_type_nosize_or_null(elem_type)) {
+ if (btf_type_nosize_or_null(elem_type) ||
+ btf_type_is_resolve_source_only(elem_type)) {
btf_verifier_log_type(env, v->t,
"Invalid elem");
return -EINVAL;
@@ -2170,8 +2170,8 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
const struct btf_type *member_type = btf_type_by_id(env->btf,
member_type_id);
- if (btf_type_is_resolve_source_only(member_type) ||
- btf_type_nosize_or_null(member_type)) {
+ if (btf_type_nosize_or_null(member_type) ||
+ btf_type_is_resolve_source_only(member_type)) {
btf_verifier_log_member(env, v->t, member,
"Invalid member");
return -EINVAL;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 080e2bb644cc..f2148db91439 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1364,10 +1364,10 @@ select_insn:
insn++;
CONT;
ALU_ARSH_X:
- DST = (u64) (u32) ((*(s32 *) &DST) >> SRC);
+ DST = (u64) (u32) (((s32) DST) >> SRC);
CONT;
ALU_ARSH_K:
- DST = (u64) (u32) ((*(s32 *) &DST) >> IMM);
+ DST = (u64) (u32) (((s32) DST) >> IMM);
CONT;
ALU64_ARSH_X:
(*(s64 *) &DST) >>= SRC;
diff --git a/net/core/filter.c b/net/core/filter.c
index f615e42cf4ef..3fdf1b21be36 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4737,7 +4737,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
return -ENODEV;
idev = __in6_dev_get_safely(dev);
- if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
+ if (unlikely(!idev || !idev->cnf.forwarding))
return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 9c6de4f114f8..20c91f02d3d8 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -105,6 +105,9 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
umem->dev = dev;
umem->queue_id = queue_id;
+
+ dev_hold(dev);
+
if (force_copy)
/* For copy-mode, we are done. */
goto out_rtnl_unlock;
@@ -124,7 +127,6 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
goto err_unreg_umem;
rtnl_unlock();
- dev_hold(dev);
umem->zc = true;
return 0;
@@ -138,11 +140,13 @@ out_rtnl_unlock:
return err;
}
-static void xdp_umem_clear_dev(struct xdp_umem *umem)
+void xdp_umem_clear_dev(struct xdp_umem *umem)
{
struct netdev_bpf bpf;
int err;
+ ASSERT_RTNL();
+
if (!umem->dev)
return;
@@ -151,22 +155,17 @@ static void xdp_umem_clear_dev(struct xdp_umem *umem)
bpf.xsk.umem = NULL;
bpf.xsk.queue_id = umem->queue_id;
- rtnl_lock();
err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
- rtnl_unlock();
if (err)
WARN(1, "failed to disable umem!\n");
}
- rtnl_lock();
xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
- rtnl_unlock();
- if (umem->zc) {
- dev_put(umem->dev);
- umem->zc = false;
- }
+ dev_put(umem->dev);
+ umem->dev = NULL;
+ umem->zc = false;
}
static void xdp_umem_unpin_pages(struct xdp_umem *umem)
@@ -194,7 +193,9 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
static void xdp_umem_release(struct xdp_umem *umem)
{
+ rtnl_lock();
xdp_umem_clear_dev(umem);
+ rtnl_unlock();
ida_simple_remove(&umem_ida, umem->id);
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index 27603227601b..a63a9fb251f5 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -10,6 +10,7 @@
int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
u16 queue_id, u16 flags);
+void xdp_umem_clear_dev(struct xdp_umem *umem);
bool xdp_umem_validate_queues(struct xdp_umem *umem);
void xdp_get_umem(struct xdp_umem *umem);
void xdp_put_umem(struct xdp_umem *umem);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index a14e8864e4fa..f53a6ef7c155 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -335,6 +335,22 @@ static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
return 0;
}
+static void xsk_unbind_dev(struct xdp_sock *xs)
+{
+ struct net_device *dev = xs->dev;
+
+ if (!dev || xs->state != XSK_BOUND)
+ return;
+
+ xs->state = XSK_UNBOUND;
+
+ /* Wait for driver to stop using the xdp socket. */
+ xdp_del_sk_umem(xs->umem, xs);
+ xs->dev = NULL;
+ synchronize_net();
+ dev_put(dev);
+}
+
static int xsk_release(struct socket *sock)
{
struct sock *sk = sock->sk;
@@ -354,15 +370,7 @@ static int xsk_release(struct socket *sock)
sock_prot_inuse_add(net, sk->sk_prot, -1);
local_bh_enable();
- if (xs->dev) {
- struct net_device *dev = xs->dev;
-
- /* Wait for driver to stop using the xdp socket. */
- xdp_del_sk_umem(xs->umem, xs);
- xs->dev = NULL;
- synchronize_net();
- dev_put(dev);
- }
+ xsk_unbind_dev(xs);
xskq_destroy(xs->rx);
xskq_destroy(xs->tx);
@@ -412,7 +420,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
return -EINVAL;
mutex_lock(&xs->mutex);
- if (xs->dev) {
+ if (xs->state != XSK_READY) {
err = -EBUSY;
goto out_release;
}
@@ -492,6 +500,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
out_unlock:
if (err)
dev_put(dev);
+ else
+ xs->state = XSK_BOUND;
out_release:
mutex_unlock(&xs->mutex);
return err;
@@ -520,6 +530,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
mutex_lock(&xs->mutex);
+ if (xs->state != XSK_READY) {
+ mutex_unlock(&xs->mutex);
+ return -EBUSY;
+ }
q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx;
err = xsk_init_queue(entries, q, false);
mutex_unlock(&xs->mutex);
@@ -534,7 +548,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
mutex_lock(&xs->mutex);
- if (xs->umem) {
+ if (xs->state != XSK_READY || xs->umem) {
mutex_unlock(&xs->mutex);
return -EBUSY;
}
@@ -561,6 +575,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
mutex_lock(&xs->mutex);
+ if (xs->state != XSK_READY) {
+ mutex_unlock(&xs->mutex);
+ return -EBUSY;
+ }
if (!xs->umem) {
mutex_unlock(&xs->mutex);
return -EINVAL;
@@ -662,6 +680,9 @@ static int xsk_mmap(struct file *file, struct socket *sock,
unsigned long pfn;
struct page *qpg;
+ if (xs->state != XSK_READY)
+ return -EBUSY;
+
if (offset == XDP_PGOFF_RX_RING) {
q = READ_ONCE(xs->rx);
} else if (offset == XDP_PGOFF_TX_RING) {
@@ -693,6 +714,38 @@ static int xsk_mmap(struct file *file, struct socket *sock,
size, vma->vm_page_prot);
}
+static int xsk_notifier(struct notifier_block *this,
+ unsigned long msg, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct net *net = dev_net(dev);
+ struct sock *sk;
+
+ switch (msg) {
+ case NETDEV_UNREGISTER:
+ mutex_lock(&net->xdp.lock);
+ sk_for_each(sk, &net->xdp.list) {
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ mutex_lock(&xs->mutex);
+ if (xs->dev == dev) {
+ sk->sk_err = ENETDOWN;
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_error_report(sk);
+
+ xsk_unbind_dev(xs);
+
+ /* Clear device references in umem. */
+ xdp_umem_clear_dev(xs->umem);
+ }
+ mutex_unlock(&xs->mutex);
+ }
+ mutex_unlock(&net->xdp.lock);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
static struct proto xsk_proto = {
.name = "XDP",
.owner = THIS_MODULE,
@@ -764,6 +817,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
sock_set_flag(sk, SOCK_RCU_FREE);
xs = xdp_sk(sk);
+ xs->state = XSK_READY;
mutex_init(&xs->mutex);
spin_lock_init(&xs->tx_completion_lock);
@@ -784,6 +838,10 @@ static const struct net_proto_family xsk_family_ops = {
.owner = THIS_MODULE,
};
+static struct notifier_block xsk_netdev_notifier = {
+ .notifier_call = xsk_notifier,
+};
+
static int __net_init xsk_net_init(struct net *net)
{
mutex_init(&net->xdp.lock);
@@ -816,8 +874,15 @@ static int __init xsk_init(void)
err = register_pernet_subsys(&xsk_net_ops);
if (err)
goto out_sk;
+
+ err = register_netdevice_notifier(&xsk_netdev_notifier);
+ if (err)
+ goto out_pernet;
+
return 0;
+out_pernet:
+ unregister_pernet_subsys(&xsk_net_ops);
out_sk:
sock_unregister(PF_XDP);
out_proto:
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 88b9ae24658d..cba4a640d5e8 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -288,7 +288,7 @@ static inline void xskq_produce_flush_desc(struct xsk_queue *q)
/* Order producer and data */
smp_wmb(); /* B, matches C */
- q->prod_tail = q->prod_head,
+ q->prod_tail = q->prod_head;
WRITE_ONCE(q->ring->producer, q->prod_tail);
}
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 09747bee6668..003c0c6e38c5 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/samples/bpf/xdp_redirect_user.c
@@ -189,7 +189,7 @@ int main(int argc, char **argv)
}
memset(&info, 0, sizeof(info));
- ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len);
if (ret) {
printf("can't get prog info - %s\n", strerror(errno));
return ret;
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 73ec8ea33fb4..a13fb7265d1a 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -168,7 +168,7 @@ static int do_show(int argc, char **argv)
cgroup_fd = open(argv[0], O_RDONLY);
if (cgroup_fd < 0) {
- p_err("can't open cgroup %s", argv[1]);
+ p_err("can't open cgroup %s", argv[0]);
goto exit;
}
@@ -356,7 +356,7 @@ static int do_attach(int argc, char **argv)
cgroup_fd = open(argv[0], O_RDONLY);
if (cgroup_fd < 0) {
- p_err("can't open cgroup %s", argv[1]);
+ p_err("can't open cgroup %s", argv[0]);
goto exit;
}
@@ -414,7 +414,7 @@ static int do_detach(int argc, char **argv)
cgroup_fd = open(argv[0], O_RDONLY);
if (cgroup_fd < 0) {
- p_err("can't open cgroup %s", argv[1]);
+ p_err("can't open cgroup %s", argv[0]);
goto exit;
}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a8b823c30b43..29a5bc3d5c66 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3143,6 +3143,7 @@ struct bpf_prog_info {
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
__u32 gpl_compatible:1;
+ __u32 :31; /* alignment pad */
__u64 netns_dev;
__u64 netns_ino;
__u32 nr_jited_ksyms;
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 0575751bc1bc..e2f6ed0a583d 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
@@ -61,7 +61,7 @@ struct sr6_tlv_t {
unsigned char value[0];
} BPF_PACKET_HEADER;
-__attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
+static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb)
{
void *cursor, *data_end;
struct ip6_srh_t *srh;
@@ -95,7 +95,7 @@ __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
return srh;
}
-__attribute__((always_inline))
+static __always_inline
int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
uint32_t old_pad, uint32_t pad_off)
{
@@ -125,7 +125,7 @@ int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
return 0;
}
-__attribute__((always_inline))
+static __always_inline
int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
uint32_t *tlv_off, uint32_t *pad_size,
uint32_t *pad_off)
@@ -184,7 +184,7 @@ int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
return 0;
}
-__attribute__((always_inline))
+static __always_inline
int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
struct sr6_tlv_t *itlv, uint8_t tlv_size)
{
@@ -228,7 +228,7 @@ int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
return update_tlv_pad(skb, new_pad, pad_size, pad_off);
}
-__attribute__((always_inline))
+static __always_inline
int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
uint32_t tlv_off)
{
@@ -266,7 +266,7 @@ int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
return update_tlv_pad(skb, new_pad, pad_size, pad_off);
}
-__attribute__((always_inline))
+static __always_inline
int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh)
{
int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) +
diff --git a/tools/testing/selftests/bpf/verifier/basic_instr.c b/tools/testing/selftests/bpf/verifier/basic_instr.c
index ed91a7b9a456..071dbc889e8c 100644
--- a/tools/testing/selftests/bpf/verifier/basic_instr.c
+++ b/tools/testing/selftests/bpf/verifier/basic_instr.c
@@ -91,6 +91,91 @@
.result = ACCEPT,
},
{
+ "lsh64 by 0 imm",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 1),
+ BPF_LD_IMM64(BPF_REG_1, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 1, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "rsh64 by 0 imm",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 1),
+ BPF_LD_IMM64(BPF_REG_1, 0x100000000LL),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 0),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "arsh64 by 0 imm",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 1),
+ BPF_LD_IMM64(BPF_REG_1, 0x100000000LL),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 0),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "lsh64 by 0 reg",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 1),
+ BPF_LD_IMM64(BPF_REG_1, 1),
+ BPF_LD_IMM64(BPF_REG_2, 0),
+ BPF_ALU64_REG(BPF_LSH, BPF_REG_1, BPF_REG_2),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 1, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "rsh64 by 0 reg",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 1),
+ BPF_LD_IMM64(BPF_REG_1, 0x100000000LL),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_1),
+ BPF_LD_IMM64(BPF_REG_3, 0),
+ BPF_ALU64_REG(BPF_RSH, BPF_REG_1, BPF_REG_3),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "arsh64 by 0 reg",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 1),
+ BPF_LD_IMM64(BPF_REG_1, 0x100000000LL),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_1),
+ BPF_LD_IMM64(BPF_REG_3, 0),
+ BPF_ALU64_REG(BPF_ARSH, BPF_REG_1, BPF_REG_3),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
"invalid 64-bit BPF_END",
.insns = {
BPF_MOV32_IMM(BPF_REG_0, 0),
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.