diff --git a/Documentation/bpf/bpf_design_QA.rst b/Documentation/bpf/bpf_design_QA.rst
index 38372a956d65..eb19c945f4d5 100644
--- a/Documentation/bpf/bpf_design_QA.rst
+++ b/Documentation/bpf/bpf_design_QA.rst
@@ -140,11 +140,6 @@ A: Because if we picked one-to-one relationship to x64 it would have made
it more complicated to support on arm64 and other archs. Also it
needs div-by-zero runtime check.
-Q: Why there is no BPF_SDIV for signed divide operation?
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-A: Because it would be rarely used. llvm errors in such case and
-prints a suggestion to use unsigned divide instead.
-
Q: Why BPF has implicit prologue and epilogue?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
A: Because architectures like sparc have register windows and in general
diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 751e657973f0..655494ac7af6 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -154,24 +154,27 @@ otherwise identical operations.
The 'code' field encodes the operation as below, where 'src' and 'dst' refer
to the values of the source and destination registers, respectively.
-======== ===== ==========================================================
-code value description
-======== ===== ==========================================================
-BPF_ADD 0x00 dst += src
-BPF_SUB 0x10 dst -= src
-BPF_MUL 0x20 dst \*= src
-BPF_DIV 0x30 dst = (src != 0) ? (dst / src) : 0
-BPF_OR 0x40 dst \|= src
-BPF_AND 0x50 dst &= src
-BPF_LSH 0x60 dst <<= (src & mask)
-BPF_RSH 0x70 dst >>= (src & mask)
-BPF_NEG 0x80 dst = -src
-BPF_MOD 0x90 dst = (src != 0) ? (dst % src) : dst
-BPF_XOR 0xa0 dst ^= src
-BPF_MOV 0xb0 dst = src
-BPF_ARSH 0xc0 sign extending dst >>= (src & mask)
-BPF_END 0xd0 byte swap operations (see `Byte swap instructions`_ below)
-======== ===== ==========================================================
+========= ===== ======= ==========================================================
+code value offset description
+========= ===== ======= ==========================================================
+BPF_ADD 0x00 0 dst += src
+BPF_SUB 0x10 0 dst -= src
+BPF_MUL 0x20 0 dst \*= src
+BPF_DIV 0x30 0 dst = (src != 0) ? (dst / src) : 0
+BPF_SDIV 0x30 1 dst = (src != 0) ? (dst s/ src) : 0
+BPF_OR 0x40 0 dst \|= src
+BPF_AND 0x50 0 dst &= src
+BPF_LSH 0x60 0 dst <<= (src & mask)
+BPF_RSH 0x70 0 dst >>= (src & mask)
+BPF_NEG 0x80 0 dst = -dst
+BPF_MOD 0x90 0 dst = (src != 0) ? (dst % src) : dst
+BPF_SMOD 0x90 1 dst = (src != 0) ? (dst s% src) : dst
+BPF_XOR 0xa0 0 dst ^= src
+BPF_MOV 0xb0 0 dst = src
+BPF_MOVSX 0xb0 8/16/32 dst = (s8,s16,s32)src
+BPF_ARSH 0xc0 0 sign extending dst >>= (src & mask)
+BPF_END 0xd0 0 byte swap operations (see `Byte swap instructions`_ below)
+========= ===== ======= ==========================================================
Underflow and overflow are allowed during arithmetic operations, meaning
the 64-bit or 32-bit value will wrap. If eBPF program execution would
@@ -198,33 +201,51 @@ where '(u32)' indicates that the upper 32 bits are zeroed.
dst = dst ^ imm32
-Also note that the division and modulo operations are unsigned. Thus, for
-``BPF_ALU``, 'imm' is first interpreted as an unsigned 32-bit value, whereas
-for ``BPF_ALU64``, 'imm' is first sign extended to 64 bits and the result
-interpreted as an unsigned 64-bit value. There are no instructions for
-signed division or modulo.
+Note that most instructions have instruction offset of 0. Only three instructions
+(``BPF_SDIV``, ``BPF_SMOD``, ``BPF_MOVSX``) have a non-zero offset.
+
+The devision and modulo operations support both unsigned and signed flavors.
+
+For unsigned operations (``BPF_DIV`` and ``BPF_MOD``), for ``BPF_ALU``,
+'imm' is interpreted as a 32-bit unsigned value. For ``BPF_ALU64``,
+'imm' is first sign extended from 32 to 64 bits, and then interpreted as
+a 64-bit unsigned value.
+
+For signed operations (``BPF_SDIV`` and ``BPF_SMOD``), for ``BPF_ALU``,
+'imm' is interpreted as a 32-bit signed value. For ``BPF_ALU64``, 'imm'
+is first sign extended from 32 to 64 bits, and then interpreted as a
+64-bit signed value.
+
+The ``BPF_MOVSX`` instruction does a move operation with sign extension.
+``BPF_ALU | BPF_MOVSX`` sign extends 8-bit and 16-bit operands into 32
+bit operands, and zeroes the remaining upper 32 bits.
+``BPF_ALU64 | BPF_MOVSX`` sign extends 8-bit, 16-bit, and 32-bit
+operands into 64 bit operands.
Shift operations use a mask of 0x3F (63) for 64-bit operations and 0x1F (31)
for 32-bit operations.
Byte swap instructions
-~~~~~~~~~~~~~~~~~~~~~~
+----------------------
-The byte swap instructions use an instruction class of ``BPF_ALU`` and a 4-bit
-'code' field of ``BPF_END``.
+The byte swap instructions use instruction classes of ``BPF_ALU`` and ``BPF_ALU64``
+and a 4-bit 'code' field of ``BPF_END``.
The byte swap instructions operate on the destination register
only and do not use a separate source register or immediate value.
-The 1-bit source operand field in the opcode is used to select what byte
-order the operation convert from or to:
+For ``BPF_ALU``, the 1-bit source operand field in the opcode is used to
+select what byte order the operation converts from or to. For
+``BPF_ALU64``, the 1-bit source operand field in the opcode is reserved
+and must be set to 0.
-========= ===== =================================================
-source value description
-========= ===== =================================================
-BPF_TO_LE 0x00 convert between host byte order and little endian
-BPF_TO_BE 0x08 convert between host byte order and big endian
-========= ===== =================================================
+========= ========= ===== =================================================
+class source value description
+========= ========= ===== =================================================
+BPF_ALU BPF_TO_LE 0x00 convert between host byte order and little endian
+BPF_ALU BPF_TO_BE 0x08 convert between host byte order and big endian
+BPF_ALU64 Reserved 0x00 do byte swap unconditionally
+========= ========= ===== =================================================
The 'imm' field encodes the width of the swap operations. The following widths
are supported: 16, 32 and 64.
@@ -239,6 +260,12 @@ Examples:
dst = htobe64(dst)
+``BPF_ALU64 | BPF_TO_LE | BPF_END`` with imm = 16/32/64 means::
+
+ dst = bswap16 dst
+ dst = bswap32 dst
+ dst = bswap64 dst
+
Jump instructions
-----------------
@@ -249,7 +276,8 @@ The 'code' field encodes the operation as below:
======== ===== === =========================================== =========================================
code value src description notes
======== ===== === =========================================== =========================================
-BPF_JA 0x0 0x0 PC += offset BPF_JMP only
+BPF_JA 0x0 0x0 PC += offset BPF_JMP class
+BPF_JA 0x0 0x0 PC += imm BPF_JMP32 class
BPF_JEQ 0x1 any PC += offset if dst == src
BPF_JGT 0x2 any PC += offset if dst > src unsigned
BPF_JGE 0x3 any PC += offset if dst >= src unsigned
@@ -278,6 +306,19 @@ Example:
where 's>=' indicates a signed '>=' comparison.
+``BPF_JA | BPF_K | BPF_JMP32`` (0x06) means::
+
+ gotol +imm
+
+where 'imm' means the branch offset comes from insn 'imm' field.
+
+Note that there are two flavors of ``BPF_JA`` instructions. The
+``BPF_JMP`` class permits a 16-bit jump offset specified by the 'offset'
+field, whereas the ``BPF_JMP32`` class permits a 32-bit jump offset
+specified by the 'imm' field. A > 16-bit conditional jump may be
+converted to a < 16-bit conditional jump plus a 32-bit unconditional
+jump.
+
Helper functions
~~~~~~~~~~~~~~~~
@@ -320,6 +361,7 @@ The mode modifier is one of:
BPF_ABS 0x20 legacy BPF packet access (absolute) `Legacy BPF Packet access instructions`_
BPF_IND 0x40 legacy BPF packet access (indirect) `Legacy BPF Packet access instructions`_
BPF_MEM 0x60 regular load and store operations `Regular load and store operations`_
+ BPF_MEMSX 0x80 sign-extension load operations `Sign-extension load operations`_
BPF_ATOMIC 0xc0 atomic operations `Atomic operations`_
============= ===== ==================================== =============
@@ -350,9 +392,23 @@ instructions that transfer data between a register and memory.
``BPF_MEM | <size> | BPF_LDX`` means::
- dst = *(size *) (src + offset)
+ dst = *(unsigned size *) (src + offset)
-Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW``.
+Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW`` and
+'unsigned size' is one of u8, u16, u32 or u64.
+
+Sign-extension load operations
+------------------------------
+
+The ``BPF_MEMSX`` mode modifier is used to encode sign-extension load
+instructions that transfer data between a register and memory.
+
+``BPF_MEMSX | <size> | BPF_LDX`` means::
+
+ dst = *(signed size *) (src + offset)
+
+Where size is one of: ``BPF_B``, ``BPF_H`` or ``BPF_W``, and
+'signed size' is one of s8, s16 or s32.
Atomic operations
-----------------
diff --git a/MAINTAINERS b/MAINTAINERS
index 3f32da783b31..5e2bb1059ab6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3704,7 +3704,7 @@ M: Daniel Borkmann <daniel@iogearbox.net>
M: Andrii Nakryiko <andrii@kernel.org>
R: Martin KaFai Lau <martin.lau@linux.dev>
R: Song Liu <song@kernel.org>
-R: Yonghong Song <yhs@fb.com>
+R: Yonghong Song <yonghong.song@linux.dev>
R: John Fastabend <john.fastabend@gmail.com>
R: KP Singh <kpsingh@kernel.org>
R: Stanislav Fomichev <sdf@google.com>
@@ -3743,7 +3743,7 @@ F: tools/lib/bpf/
F: tools/testing/selftests/bpf/
BPF [ITERATOR]
-M: Yonghong Song <yhs@fb.com>
+M: Yonghong Song <yonghong.song@linux.dev>
L: bpf@vger.kernel.org
S: Maintained
F: kernel/bpf/*iter.c
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index c648864c8cd1..0ca4f5c0097c 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -13,6 +13,8 @@
#include <asm/patch.h>
#include "bpf_jit.h"
+#define RV_FENTRY_NINSNS 2
+
#define RV_REG_TCC RV_REG_A6
#define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */
@@ -241,7 +243,7 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
if (!is_tail_call)
emit_mv(RV_REG_A0, RV_REG_A5, ctx);
emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA,
- is_tail_call ? 20 : 0, /* skip reserved nops and TCC init */
+ is_tail_call ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */
ctx);
}
@@ -618,32 +620,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
return 0;
}
-static int gen_call_or_nops(void *target, void *ip, u32 *insns)
-{
- s64 rvoff;
- int i, ret;
- struct rv_jit_context ctx;
-
- ctx.ninsns = 0;
- ctx.insns = (u16 *)insns;
-
- if (!target) {
- for (i = 0; i < 4; i++)
- emit(rv_nop(), &ctx);
- return 0;
- }
-
- rvoff = (s64)(target - (ip + 4));
- emit(rv_sd(RV_REG_SP, -8, RV_REG_RA), &ctx);
- ret = emit_jump_and_link(RV_REG_RA, rvoff, false, &ctx);
- if (ret)
- return ret;
- emit(rv_ld(RV_REG_RA, -8, RV_REG_SP), &ctx);
-
- return 0;
-}
-
-static int gen_jump_or_nops(void *target, void *ip, u32 *insns)
+static int gen_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call)
{
s64 rvoff;
struct rv_jit_context ctx;
@@ -658,38 +635,35 @@ static int gen_jump_or_nops(void *target, void *ip, u32 *insns)
}
rvoff = (s64)(target - ip);
- return emit_jump_and_link(RV_REG_ZERO, rvoff, false, &ctx);
+ return emit_jump_and_link(is_call ? RV_REG_T0 : RV_REG_ZERO, rvoff, false, &ctx);
}
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
void *old_addr, void *new_addr)
{
- u32 old_insns[4], new_insns[4];
+ u32 old_insns[RV_FENTRY_NINSNS], new_insns[RV_FENTRY_NINSNS];
bool is_call = poke_type == BPF_MOD_CALL;
- int (*gen_insns)(void *target, void *ip, u32 *insns);
- int ninsns = is_call ? 4 : 2;
int ret;
- if (!is_bpf_text_address((unsigned long)ip))
+ if (!is_kernel_text((unsigned long)ip) &&
+ !is_bpf_text_address((unsigned long)ip))
return -ENOTSUPP;
- gen_insns = is_call ? gen_call_or_nops : gen_jump_or_nops;
-
- ret = gen_insns(old_addr, ip, old_insns);
+ ret = gen_jump_or_nops(old_addr, ip, old_insns, is_call);
if (ret)
return ret;
- if (memcmp(ip, old_insns, ninsns * 4))
+ if (memcmp(ip, old_insns, RV_FENTRY_NINSNS * 4))
return -EFAULT;
- ret = gen_insns(new_addr, ip, new_insns);
+ ret = gen_jump_or_nops(new_addr, ip, new_insns, is_call);
if (ret)
return ret;
cpus_read_lock();
mutex_lock(&text_mutex);
- if (memcmp(ip, new_insns, ninsns * 4))
- ret = patch_text(ip, new_insns, ninsns);
+ if (memcmp(ip, new_insns, RV_FENTRY_NINSNS * 4))
+ ret = patch_text(ip, new_insns, RV_FENTRY_NINSNS);
mutex_unlock(&text_mutex);
cpus_read_unlock();
@@ -787,8 +761,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
int i, ret, offset;
int *branches_off = NULL;
int stack_size = 0, nregs = m->nr_args;
- int retaddr_off, fp_off, retval_off, args_off;
- int nregs_off, ip_off, run_ctx_off, sreg_off;
+ int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off;
struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
@@ -796,13 +769,27 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
bool save_ret;
u32 insn;
- /* Generated trampoline stack layout:
+ /* Two types of generated trampoline stack layout:
*
- * FP - 8 [ RA of parent func ] return address of parent
+ * 1. trampoline called from function entry
+ * --------------------------------------
+ * FP + 8 [ RA to parent func ] return address to parent
* function
- * FP - retaddr_off [ RA of traced func ] return address of traced
+ * FP + 0 [ FP of parent func ] frame pointer of parent
* function
- * FP - fp_off [ FP of parent func ]
+ * FP - 8 [ T0 to traced func ] return address of traced
+ * function
+ * FP - 16 [ FP of traced func ] frame pointer of traced
+ * function
+ * --------------------------------------
+ *
+ * 2. trampoline called directly
+ * --------------------------------------
+ * FP - 8 [ RA to caller func ] return address to caller
+ * function
+ * FP - 16 [ FP of caller func ] frame pointer of caller
+ * function
+ * --------------------------------------
*
* FP - retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or
* BPF_TRAMP_F_RET_FENTRY_RET
@@ -833,14 +820,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
if (nregs > 8)
return -ENOTSUPP;
- /* room for parent function return address */
- stack_size += 8;
-
- stack_size += 8;
- retaddr_off = stack_size;
-
- stack_size += 8;
- fp_off = stack_size;
+ /* room of trampoline frame to store return address and frame pointer */
+ stack_size += 16;
save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
if (save_ret) {
@@ -867,12 +848,29 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
stack_size = round_up(stack_size, 16);
- emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx);
+ if (func_addr) {
+ /* For the trampoline called from function entry,
+ * the frame of traced function and the frame of
+ * trampoline need to be considered.
+ */
+ emit_addi(RV_REG_SP, RV_REG_SP, -16, ctx);
+ emit_sd(RV_REG_SP, 8, RV_REG_RA, ctx);
+ emit_sd(RV_REG_SP, 0, RV_REG_FP, ctx);
+ emit_addi(RV_REG_FP, RV_REG_SP, 16, ctx);
- emit_sd(RV_REG_SP, stack_size - retaddr_off, RV_REG_RA, ctx);
- emit_sd(RV_REG_SP, stack_size - fp_off, RV_REG_FP, ctx);
-
- emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx);
+ emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx);
+ emit_sd(RV_REG_SP, stack_size - 8, RV_REG_T0, ctx);
+ emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx);
+ emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx);
+ } else {
+ /* For the trampoline called directly, just handle
+ * the frame of trampoline.
+ */
+ emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx);
+ emit_sd(RV_REG_SP, stack_size - 8, RV_REG_RA, ctx);
+ emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx);
+ emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx);
+ }
/* callee saved register S1 to pass start time */
emit_sd(RV_REG_FP, -sreg_off, RV_REG_S1, ctx);
@@ -890,7 +888,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
/* skip to actual body of traced function */
if (flags & BPF_TRAMP_F_SKIP_FRAME)
- orig_call += 16;
+ orig_call += RV_FENTRY_NINSNS * 4;
if (flags & BPF_TRAMP_F_CALL_ORIG) {
emit_imm(RV_REG_A0, (const s64)im, ctx);
@@ -967,17 +965,30 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx);
- if (flags & BPF_TRAMP_F_SKIP_FRAME)
- /* return address of parent function */
+ if (func_addr) {
+ /* trampoline called from function entry */
+ emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx);
+ emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);
+ emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx);
+
+ emit_ld(RV_REG_RA, 8, RV_REG_SP, ctx);
+ emit_ld(RV_REG_FP, 0, RV_REG_SP, ctx);
+ emit_addi(RV_REG_SP, RV_REG_SP, 16, ctx);
+
+ if (flags & BPF_TRAMP_F_SKIP_FRAME)
+ /* return to parent function */
+ emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx);
+ else
+ /* return to traced function */
+ emit_jalr(RV_REG_ZERO, RV_REG_T0, 0, ctx);
+ } else {
+ /* trampoline called directly */
emit_ld(RV_REG_RA, stack_size - 8, RV_REG_SP, ctx);
- else
- /* return address of traced function */
- emit_ld(RV_REG_RA, stack_size - retaddr_off, RV_REG_SP, ctx);
+ emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);
+ emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx);
- emit_ld(RV_REG_FP, stack_size - fp_off, RV_REG_SP, ctx);
- emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx);
-
- emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx);
+ emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx);
+ }
ret = ctx->ninsns;
out:
@@ -1691,8 +1702,8 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx)
store_offset = stack_adjust - 8;
- /* reserve 4 nop insns */
- for (i = 0; i < 4; i++)
+ /* nops reserved for auipc+jalr pair */
+ for (i = 0; i < RV_FENTRY_NINSNS; i++)
emit(rv_nop(), ctx);
/* First instruction is always setting the tail-call-counter
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 83c4b45dc65f..a5930042139d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -701,6 +701,38 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
*pprog = prog;
}
+static void emit_movsx_reg(u8 **pprog, int num_bits, bool is64, u32 dst_reg,
+ u32 src_reg)
+{
+ u8 *prog = *pprog;
+
+ if (is64) {
+ /* movs[b,w,l]q dst, src */
+ if (num_bits == 8)
+ EMIT4(add_2mod(0x48, src_reg, dst_reg), 0x0f, 0xbe,
+ add_2reg(0xC0, src_reg, dst_reg));
+ else if (num_bits == 16)
+ EMIT4(add_2mod(0x48, src_reg, dst_reg), 0x0f, 0xbf,
+ add_2reg(0xC0, src_reg, dst_reg));
+ else if (num_bits == 32)
+ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x63,
+ add_2reg(0xC0, src_reg, dst_reg));
+ } else {
+ /* movs[b,w]l dst, src */
+ if (num_bits == 8) {
+ EMIT4(add_2mod(0x40, src_reg, dst_reg), 0x0f, 0xbe,
+ add_2reg(0xC0, src_reg, dst_reg));
+ } else if (num_bits == 16) {
+ if (is_ereg(dst_reg) || is_ereg(src_reg))
+ EMIT1(add_2mod(0x40, src_reg, dst_reg));
+ EMIT3(add_2mod(0x0f, src_reg, dst_reg), 0xbf,
+ add_2reg(0xC0, src_reg, dst_reg));
+ }
+ }
+
+ *pprog = prog;
+}
+
/* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */
static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off)
{
@@ -779,6 +811,29 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
*pprog = prog;
}
+/* LDSX: dst_reg = *(s8*)(src_reg + off) */
+static void emit_ldsx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+ u8 *prog = *pprog;
+
+ switch (size) {
+ case BPF_B:
+ /* Emit 'movsx rax, byte ptr [rax + off]' */
+ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBE);
+ break;
+ case BPF_H:
+ /* Emit 'movsx rax, word ptr [rax + off]' */
+ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBF);
+ break;
+ case BPF_W:
+ /* Emit 'movsx rax, dword ptr [rax+0x14]' */
+ EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x63);
+ break;
+ }
+ emit_insn_suffix(&prog, src_reg, dst_reg, off);
+ *pprog = prog;
+}
+
/* STX: *(u8*)(dst_reg + off) = src_reg */
static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
{
@@ -1028,9 +1083,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
case BPF_ALU64 | BPF_MOV | BPF_X:
case BPF_ALU | BPF_MOV | BPF_X:
- emit_mov_reg(&prog,
- BPF_CLASS(insn->code) == BPF_ALU64,
- dst_reg, src_reg);
+ if (insn->off == 0)
+ emit_mov_reg(&prog,
+ BPF_CLASS(insn->code) == BPF_ALU64,
+ dst_reg, src_reg);
+ else
+ emit_movsx_reg(&prog, insn->off,
+ BPF_CLASS(insn->code) == BPF_ALU64,
+ dst_reg, src_reg);
break;
/* neg dst */
@@ -1134,15 +1194,26 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
/* mov rax, dst_reg */
emit_mov_reg(&prog, is64, BPF_REG_0, dst_reg);
- /*
- * xor edx, edx
- * equivalent to 'xor rdx, rdx', but one byte less
- */
- EMIT2(0x31, 0xd2);
+ if (insn->off == 0) {
+ /*
+ * xor edx, edx
+ * equivalent to 'xor rdx, rdx', but one byte less
+ */
+ EMIT2(0x31, 0xd2);
- /* div src_reg */
- maybe_emit_1mod(&prog, src_reg, is64);
- EMIT2(0xF7, add_1reg(0xF0, src_reg));
+ /* div src_reg */
+ maybe_emit_1mod(&prog, src_reg, is64);
+ EMIT2(0xF7, add_1reg(0xF0, src_reg));
+ } else {
+ if (BPF_CLASS(insn->code) == BPF_ALU)
+ EMIT1(0x99); /* cdq */
+ else
+ EMIT2(0x48, 0x99); /* cqo */
+
+ /* idiv src_reg */
+ maybe_emit_1mod(&prog, src_reg, is64);
+ EMIT2(0xF7, add_1reg(0xF8, src_reg));
+ }
if (BPF_OP(insn->code) == BPF_MOD &&
dst_reg != BPF_REG_3)
@@ -1262,6 +1333,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
break;
case BPF_ALU | BPF_END | BPF_FROM_BE:
+ case BPF_ALU64 | BPF_END | BPF_FROM_LE:
switch (imm32) {
case 16:
/* Emit 'ror %ax, 8' to swap lower 2 bytes */
@@ -1370,9 +1442,17 @@ st: if (is_imm8(insn->off))
case BPF_LDX | BPF_PROBE_MEM | BPF_W:
case BPF_LDX | BPF_MEM | BPF_DW:
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+ /* LDXS: dst_reg = *(s8*)(src_reg + off) */
+ case BPF_LDX | BPF_MEMSX | BPF_B:
+ case BPF_LDX | BPF_MEMSX | BPF_H:
+ case BPF_LDX | BPF_MEMSX | BPF_W:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
insn_off = insn->off;
- if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+ if (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX) {
/* Conservatively check that src_reg + insn->off is a kernel address:
* src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE
* src_reg is used as scratch for src_reg += insn->off and restored
@@ -1415,8 +1495,13 @@ st: if (is_imm8(insn->off))
start_of_ldx = prog;
end_of_jmp[-1] = start_of_ldx - end_of_jmp;
}
- emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off);
- if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+ if (BPF_MODE(insn->code) == BPF_PROBE_MEMSX ||
+ BPF_MODE(insn->code) == BPF_MEMSX)
+ emit_ldsx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off);
+ else
+ emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off);
+ if (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX) {
struct exception_table_entry *ex;
u8 *_insn = image + proglen + (start_of_ldx - temp);
s64 delta;
@@ -1730,16 +1815,24 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */
break;
case BPF_JMP | BPF_JA:
- if (insn->off == -1)
- /* -1 jmp instructions will always jump
- * backwards two bytes. Explicitly handling
- * this case avoids wasting too many passes
- * when there are long sequences of replaced
- * dead code.
- */
- jmp_offset = -2;
- else
- jmp_offset = addrs[i + insn->off] - addrs[i];
+ case BPF_JMP32 | BPF_JA:
+ if (BPF_CLASS(insn->code) == BPF_JMP) {
+ if (insn->off == -1)
+ /* -1 jmp instructions will always jump
+ * backwards two bytes. Explicitly handling
+ * this case avoids wasting too many passes
+ * when there are long sequences of replaced
+ * dead code.
+ */
+ jmp_offset = -2;
+ else
+ jmp_offset = addrs[i + insn->off] - addrs[i];
+ } else {
+ if (insn->imm == -1)
+ jmp_offset = -2;
+ else
+ jmp_offset = addrs[i + insn->imm] - addrs[i];
+ }
if (!jmp_offset) {
/*
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f04d4f28eb1a..c9b6440fbc0e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -90,6 +90,7 @@
#include <net/tls.h>
#endif
#include <net/ip6_route.h>
+#include <net/xdp.h>
#include "bonding_priv.h"
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 248b715b4d68..33c923e1261a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -14,6 +14,7 @@
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <net/xdp.h>
#include <uapi/linux/bpf.h>
#include "ena_com.h"
diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h
index 11b29f56aaf9..6e14c918e3fb 100644
--- a/drivers/net/ethernet/engleder/tsnep.h
+++ b/drivers/net/ethernet/engleder/tsnep.h
@@ -14,6 +14,7 @@
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
#include <linux/miscdevice.h>
+#include <net/xdp.h>
#define TSNEP "tsnep"
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index d56d7a13262e..bfb6c96c3b2f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -12,6 +12,7 @@
#include <linux/fsl/mc.h>
#include <linux/net_tstamp.h>
#include <net/devlink.h>
+#include <net/xdp.h>
#include <soc/fsl/dpaa2-io.h>
#include <soc/fsl/dpaa2-fd.h>
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 8577cf7699a0..7439739cd81a 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -11,6 +11,7 @@
#include <linux/if_vlan.h>
#include <linux/phylink.h>
#include <linux/dim.h>
+#include <net/xdp.h>
#include "enetc_hw.h"
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 110f2e9f3e3f..5ca9906d7c6a 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -22,6 +22,7 @@
#include <linux/timecounter.h>
#include <dt-bindings/firmware/imx/rsrc.h>
#include <linux/firmware/imx/sci.h>
+#include <net/xdp.h>
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
index 53b7e95213a8..5eec552a1f24 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
+++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
@@ -5,6 +5,7 @@
#include <linux/netdevice.h>
#include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
/* Tx descriptor size */
#define FUNETH_SQE_SIZE 64U
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 4b425bf71ede..a31256f70348 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -11,6 +11,7 @@
#include <linux/netdevice.h>
#include <linux/pci.h>
#include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
#include "gve_desc.h"
#include "gve_desc_dqo.h"
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 9db384f66a8e..4bffc3cb502f 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -15,6 +15,7 @@
#include <linux/net_tstamp.h>
#include <linux/bitfield.h>
#include <linux/hrtimer.h>
+#include <net/xdp.h>
#include "igc_hw.h"
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index b538d496e8d7..aebc9154693a 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -14,6 +14,7 @@
#include <net/pkt_cls.h>
#include <net/pkt_sched.h>
#include <net/switchdev.h>
+#include <net/xdp.h>
#include <vcap_api.h>
#include <vcap_api_client.h>
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ac2acc9aca9d..21665f114fe9 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -11,6 +11,7 @@
#include <net/checksum.h>
#include <net/ip6_checksum.h>
+#include <net/xdp.h>
#include <net/mana/mana.h>
#include <net/mana/mana_auxiliary.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 4ce5eaaae513..a6d034968654 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -22,6 +22,7 @@
#include <linux/net_tstamp.h>
#include <linux/reset.h>
#include <net/page_pool.h>
+#include <net/xdp.h>
#include <uapi/linux/bpf.h>
struct stmmac_resources {
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 34230145ca0b..0e27c433098d 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -6,6 +6,7 @@
#ifndef DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
#define DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
+#include <net/xdp.h>
#include <uapi/linux/bpf.h>
#include "davinci_cpdma.h"
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index c9dd69dbe1b8..810977952f95 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -16,6 +16,7 @@
#include <linux/hyperv.h>
#include <linux/rndis.h>
#include <linux/jhash.h>
+#include <net/xdp.h>
/* RSS related */
#define OID_GEN_RECEIVE_SCALE_CAPABILITIES 0x00010203 /* query only */
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 5b0f2abf454d..5c01cc7b9949 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -22,6 +22,7 @@
#include <net/net_namespace.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
+#include <net/xdp.h>
#include <linux/virtio_net.h>
#include <linux/skb_array.h>
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c615bbf24c0d..9999f81b78d1 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -22,6 +22,7 @@
#include <net/route.h>
#include <net/xdp.h>
#include <net/net_failover.h>
+#include <net/netdev_rx_queue.h>
static int napi_weight = NAPI_POLL_WEIGHT;
module_param(napi_weight, int, 0444);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ceaa8c23287f..abe75063630b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2661,6 +2661,18 @@ static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
}
#endif /* CONFIG_BPF_SYSCALL */
+static __always_inline int
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
+{
+ int ret = -EFAULT;
+
+ if (IS_ENABLED(CONFIG_BPF_EVENTS))
+ ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+ return ret;
+}
+
void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
struct btf_mod_pair *used_btfs, u32 len);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f69114083ec7..2d6fe30bad5f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -69,6 +69,9 @@ struct ctl_table_header;
/* unused opcode to mark special load instruction. Same as BPF_ABS */
#define BPF_PROBE_MEM 0x20
+/* unused opcode to mark special ldsx instruction. Same as BPF_IND */
+#define BPF_PROBE_MEMSX 0x40
+
/* unused opcode to mark call to interpreter with arguments */
#define BPF_CALL_ARGS 0xe0
@@ -90,22 +93,28 @@ struct ctl_table_header;
/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
-#define BPF_ALU64_REG(OP, DST, SRC) \
+#define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \
((struct bpf_insn) { \
.code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \
.dst_reg = DST, \
.src_reg = SRC, \
- .off = 0, \
+ .off = OFF, \
.imm = 0 })
-#define BPF_ALU32_REG(OP, DST, SRC) \
+#define BPF_ALU64_REG(OP, DST, SRC) \
+ BPF_ALU64_REG_OFF(OP, DST, SRC, 0)
+
+#define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \
((struct bpf_insn) { \
.code = BPF_ALU | BPF_OP(OP) | BPF_X, \
.dst_reg = DST, \
.src_reg = SRC, \
- .off = 0, \
+ .off = OFF, \
.imm = 0 })
+#define BPF_ALU32_REG(OP, DST, SRC) \
+ BPF_ALU32_REG_OFF(OP, DST, SRC, 0)
+
/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
#define BPF_ALU64_IMM(OP, DST, IMM) \
@@ -765,23 +774,6 @@ DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key);
u32 xdp_master_redirect(struct xdp_buff *xdp);
-static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
- struct xdp_buff *xdp)
-{
- /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus
- * under local_bh_disable(), which provides the needed RCU protection
- * for accessing map entries.
- */
- u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
-
- if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) {
- if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev))
- act = xdp_master_redirect(xdp);
- }
-
- return act;
-}
-
void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog);
static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4176a738177b..0896aaa91dd7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -40,7 +40,6 @@
#include <net/dcbnl.h>
#endif
#include <net/netprio_cgroup.h>
-#include <net/xdp.h>
#include <linux/netdev_features.h>
#include <linux/neighbour.h>
@@ -77,8 +76,12 @@ struct udp_tunnel_nic_info;
struct udp_tunnel_nic;
struct bpf_prog;
struct xdp_buff;
+struct xdp_frame;
+struct xdp_metadata_ops;
struct xdp_md;
+typedef u32 xdp_features_t;
+
void synchronize_net(void);
void netdev_set_default_ethtool_ops(struct net_device *dev,
const struct ethtool_ops *ops);
@@ -783,32 +786,6 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
#endif
#endif /* CONFIG_RPS */
-/* This structure contains an instance of an RX queue. */
-struct netdev_rx_queue {
- struct xdp_rxq_info xdp_rxq;
-#ifdef CONFIG_RPS
- struct rps_map __rcu *rps_map;
- struct rps_dev_flow_table __rcu *rps_flow_table;
-#endif
- struct kobject kobj;
- struct net_device *dev;
- netdevice_tracker dev_tracker;
-
-#ifdef CONFIG_XDP_SOCKETS
- struct xsk_buff_pool *pool;
-#endif
-} ____cacheline_aligned_in_smp;
-
-/*
- * RX queue sysfs structures and functions.
- */
-struct rx_queue_attribute {
- struct attribute attr;
- ssize_t (*show)(struct netdev_rx_queue *queue, char *buf);
- ssize_t (*store)(struct netdev_rx_queue *queue,
- const char *buf, size_t len);
-};
-
/* XPS map type and offset of the xps map within net_device->xps_maps[]. */
enum xps_map_type {
XPS_CPUS = 0,
@@ -1670,12 +1647,6 @@ struct net_device_ops {
struct netlink_ext_ack *extack);
};
-struct xdp_metadata_ops {
- int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
- int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
- enum xdp_rss_hash_type *rss_type);
-};
-
/**
* enum netdev_priv_flags - &struct net_device priv_flags
*
@@ -3851,24 +3822,6 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev,
int netif_set_real_num_queues(struct net_device *dev,
unsigned int txq, unsigned int rxq);
-static inline struct netdev_rx_queue *
-__netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
-{
- return dev->_rx + rxq;
-}
-
-#ifdef CONFIG_SYSFS
-static inline unsigned int get_netdev_rx_queue_index(
- struct netdev_rx_queue *queue)
-{
- struct net_device *dev = queue->dev;
- int index = queue - dev->_rx;
-
- BUG_ON(index >= dev->num_rx_queues);
- return index;
-}
-#endif
-
int netif_get_num_default_rss_queues(void);
void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason);
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index d4fed4c508ca..d68644b7c299 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -11,6 +11,7 @@
#include <linux/wait.h>
#include <linux/list.h>
#include <linux/static_key.h>
+#include <linux/module.h>
#include <linux/netfilter_defs.h>
#include <linux/netdevice.h>
#include <linux/sockptr.h>
@@ -481,6 +482,15 @@ struct nfnl_ct_hook {
};
extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook;
+struct nf_defrag_hook {
+ struct module *owner;
+ int (*enable)(struct net *net);
+ void (*disable)(struct net *net);
+};
+
+extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook;
+extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook;
+
/*
* nf_skb_duplicated - TEE target has sent a packet
*
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index f90f0021f5f2..4dabeb6c76d3 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -16,6 +16,7 @@
#include <linux/sched/clock.h>
#include <linux/sched/signal.h>
#include <net/ip.h>
+#include <net/xdp.h>
/* 0 - Reserved to indicate value not set
* 1..NR_CPUS - Reserved for sender_cpu
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 56f1286583d3..284b5ce7205d 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -48,6 +48,22 @@ struct sock *__inet6_lookup_established(struct net *net,
const u16 hnum, const int dif,
const int sdif);
+typedef u32 (inet6_ehashfn_t)(const struct net *net,
+ const struct in6_addr *laddr, const u16 lport,
+ const struct in6_addr *faddr, const __be16 fport);
+
+inet6_ehashfn_t inet6_ehashfn;
+
+INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
+
+struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr,
+ __be16 sport,
+ const struct in6_addr *daddr,
+ unsigned short hnum,
+ inet6_ehashfn_t *ehashfn);
+
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
@@ -57,6 +73,15 @@ struct sock *inet6_lookup_listener(struct net *net,
const unsigned short hnum,
const int dif, const int sdif);
+struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+ int protocol,
+ struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr,
+ const __be16 sport,
+ const struct in6_addr *daddr,
+ const u16 hnum, const int dif,
+ inet6_ehashfn_t *ehashfn);
+
static inline struct sock *__inet6_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
@@ -78,6 +103,46 @@ static inline struct sock *__inet6_lookup(struct net *net,
daddr, hnum, dif, sdif);
}
+static inline
+struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr, const __be16 sport,
+ const struct in6_addr *daddr, const __be16 dport,
+ bool *refcounted, inet6_ehashfn_t *ehashfn)
+{
+ struct sock *sk, *reuse_sk;
+ bool prefetched;
+
+ sk = skb_steal_sock(skb, refcounted, &prefetched);
+ if (!sk)
+ return NULL;
+
+ if (!prefetched)
+ return sk;
+
+ if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_state != TCP_LISTEN)
+ return sk;
+ } else if (sk->sk_protocol == IPPROTO_UDP) {
+ if (sk->sk_state != TCP_CLOSE)
+ return sk;
+ } else {
+ return sk;
+ }
+
+ reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, ntohs(dport),
+ ehashfn);
+ if (!reuse_sk)
+ return sk;
+
+ /* We've chosen a new reuseport sock which is never refcounted. This
+ * implies that sk also isn't refcounted.
+ */
+ WARN_ON_ONCE(*refcounted);
+
+ return reuse_sk;
+}
+
static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
const __be16 sport,
@@ -85,14 +150,20 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
int iif, int sdif,
bool *refcounted)
{
- struct sock *sk = skb_steal_sock(skb, refcounted);
+ struct net *net = dev_net(skb_dst(skb)->dev);
+ const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct sock *sk;
+ sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport,
+ refcounted, inet6_ehashfn);
+ if (IS_ERR(sk))
+ return NULL;
if (sk)
return sk;
- return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
- doff, &ipv6_hdr(skb)->saddr, sport,
- &ipv6_hdr(skb)->daddr, ntohs(dport),
+ return __inet6_lookup(net, hashinfo, skb,
+ doff, &ip6h->saddr, sport,
+ &ip6h->daddr, ntohs(dport),
iif, sdif, refcounted);
}
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 99bd823e97f6..1177effabed3 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,6 +379,27 @@ struct sock *__inet_lookup_established(struct net *net,
const __be32 daddr, const u16 hnum,
const int dif, const int sdif);
+typedef u32 (inet_ehashfn_t)(const struct net *net,
+ const __be32 laddr, const __u16 lport,
+ const __be32 faddr, const __be16 fport);
+
+inet_ehashfn_t inet_ehashfn;
+
+INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn);
+
+struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned short hnum,
+ inet_ehashfn_t *ehashfn);
+
+struct sock *inet_lookup_run_sk_lookup(struct net *net,
+ int protocol,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, u16 hnum, const int dif,
+ inet_ehashfn_t *ehashfn);
+
static inline struct sock *
inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
@@ -428,6 +449,46 @@ static inline struct sock *inet_lookup(struct net *net,
return sk;
}
+static inline
+struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
+ const __be32 saddr, const __be16 sport,
+ const __be32 daddr, const __be16 dport,
+ bool *refcounted, inet_ehashfn_t *ehashfn)
+{
+ struct sock *sk, *reuse_sk;
+ bool prefetched;
+
+ sk = skb_steal_sock(skb, refcounted, &prefetched);
+ if (!sk)
+ return NULL;
+
+ if (!prefetched)
+ return sk;
+
+ if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_state != TCP_LISTEN)
+ return sk;
+ } else if (sk->sk_protocol == IPPROTO_UDP) {
+ if (sk->sk_state != TCP_CLOSE)
+ return sk;
+ } else {
+ return sk;
+ }
+
+ reuse_sk = inet_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, ntohs(dport),
+ ehashfn);
+ if (!reuse_sk)
+ return sk;
+
+ /* We've chosen a new reuseport sock which is never refcounted. This
+ * implies that sk also isn't refcounted.
+ */
+ WARN_ON_ONCE(*refcounted);
+
+ return reuse_sk;
+}
+
static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb,
int doff,
@@ -436,22 +497,23 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
const int sdif,
bool *refcounted)
{
- struct sock *sk = skb_steal_sock(skb, refcounted);
+ struct net *net = dev_net(skb_dst(skb)->dev);
const struct iphdr *iph = ip_hdr(skb);
+ struct sock *sk;
+ sk = inet_steal_sock(net, skb, doff, iph->saddr, sport, iph->daddr, dport,
+ refcounted, inet_ehashfn);
+ if (IS_ERR(sk))
+ return NULL;
if (sk)
return sk;
- return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
+ return __inet_lookup(net, hashinfo, skb,
doff, iph->saddr, sport,
iph->daddr, dport, inet_iif(skb), sdif,
refcounted);
}
-u32 inet6_ehashfn(const struct net *net,
- const struct in6_addr *laddr, const u16 lport,
- const struct in6_addr *faddr, const __be16 fport);
-
static inline void sk_daddr_set(struct sock *sk, __be32 addr)
{
sk->sk_daddr = addr; /* alias of inet_daddr */
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 024ad8ddb27e..1ccdca03e166 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -4,6 +4,8 @@
#ifndef _MANA_H
#define _MANA_H
+#include <net/xdp.h>
+
#include "gdma.h"
#include "hw_channel.h"
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
new file mode 100644
index 000000000000..cdcafb30d437
--- /dev/null
+++ b/include/net/netdev_rx_queue.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NETDEV_RX_QUEUE_H
+#define _LINUX_NETDEV_RX_QUEUE_H
+
+#include <linux/kobject.h>
+#include <linux/netdevice.h>
+#include <linux/sysfs.h>
+#include <net/xdp.h>
+
+/* This structure contains an instance of an RX queue. */
+struct netdev_rx_queue {
+ struct xdp_rxq_info xdp_rxq;
+#ifdef CONFIG_RPS
+ struct rps_map __rcu *rps_map;
+ struct rps_dev_flow_table __rcu *rps_flow_table;
+#endif
+ struct kobject kobj;
+ struct net_device *dev;
+ netdevice_tracker dev_tracker;
+
+#ifdef CONFIG_XDP_SOCKETS
+ struct xsk_buff_pool *pool;
+#endif
+} ____cacheline_aligned_in_smp;
+
+/*
+ * RX queue sysfs structures and functions.
+ */
+struct rx_queue_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct netdev_rx_queue *queue, char *buf);
+ ssize_t (*store)(struct netdev_rx_queue *queue,
+ const char *buf, size_t len);
+};
+
+static inline struct netdev_rx_queue *
+__netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
+{
+ return dev->_rx + rxq;
+}
+
+#ifdef CONFIG_SYSFS
+static inline unsigned int
+get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
+{
+ struct net_device *dev = queue->dev;
+ int index = queue - dev->_rx;
+
+ BUG_ON(index >= dev->num_rx_queues);
+ return index;
+}
+#endif
+#endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 7ae44bf866af..74cbfb15d289 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2815,20 +2815,23 @@ sk_is_refcounted(struct sock *sk)
* skb_steal_sock - steal a socket from an sk_buff
* @skb: sk_buff to steal the socket from
* @refcounted: is set to true if the socket is reference-counted
+ * @prefetched: is set to true if the socket was assigned from bpf
*/
static inline struct sock *
-skb_steal_sock(struct sk_buff *skb, bool *refcounted)
+skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched)
{
if (skb->sk) {
struct sock *sk = skb->sk;
*refcounted = true;
- if (skb_sk_is_prefetched(skb))
+ *prefetched = skb_sk_is_prefetched(skb);
+ if (*prefetched)
*refcounted = sk_is_refcounted(sk);
skb->destructor = NULL;
skb->sk = NULL;
return sk;
}
+ *prefetched = false;
*refcounted = false;
return NULL;
}
diff --git a/include/net/xdp.h b/include/net/xdp.h
index d1c5381fc95f..de08c8e0d134 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -6,9 +6,10 @@
#ifndef __LINUX_NET_XDP_H__
#define __LINUX_NET_XDP_H__
-#include <linux/skbuff.h> /* skb_shared_info */
-#include <uapi/linux/netdev.h>
#include <linux/bitfield.h>
+#include <linux/filter.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h> /* skb_shared_info */
/**
* DOC: XDP RX-queue information
@@ -45,8 +46,6 @@ enum xdp_mem_type {
MEM_TYPE_MAX,
};
-typedef u32 xdp_features_t;
-
/* XDP flags for ndo_xdp_xmit */
#define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */
#define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH
@@ -443,6 +442,12 @@ enum xdp_rss_hash_type {
XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR,
};
+struct xdp_metadata_ops {
+ int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
+ int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
+ enum xdp_rss_hash_type *rss_type);
+};
+
#ifdef CONFIG_NET
u32 bpf_xdp_metadata_kfunc_id(int id);
bool bpf_dev_bound_kfunc_id(u32 btf_id);
@@ -474,4 +479,20 @@ static inline void xdp_clear_features_flag(struct net_device *dev)
xdp_set_features_flag(dev, 0);
}
+static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
+ struct xdp_buff *xdp)
+{
+ /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus
+ * under local_bh_disable(), which provides the needed RCU protection
+ * for accessing map entries.
+ */
+ u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
+
+ if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) {
+ if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev))
+ act = xdp_master_redirect(xdp);
+ }
+
+ return act;
+}
#endif /* __LINUX_NET_XDP_H__ */
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index c40fc97f9417..9adc2bdf2f94 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -9,6 +9,7 @@
#include <linux/filter.h>
#include <linux/tracepoint.h>
#include <linux/bpf.h>
+#include <net/xdp.h>
#define __XDP_ACT_MAP(FN) \
FN(ABORTED) \
@@ -404,6 +405,23 @@ TRACE_EVENT(mem_return_failed,
)
);
+TRACE_EVENT(bpf_xdp_link_attach_failed,
+
+ TP_PROTO(const char *msg),
+
+ TP_ARGS(msg),
+
+ TP_STRUCT__entry(
+ __string(msg, msg)
+ ),
+
+ TP_fast_assign(
+ __assign_str(msg, msg);
+ ),
+
+ TP_printk("errmsg=%s", __get_str(msg))
+);
+
#endif /* _TRACE_XDP_H */
#include <trace/define_trace.h>
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 739c15906a65..70da85200695 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -19,6 +19,7 @@
/* ld/ldx fields */
#define BPF_DW 0x18 /* double word (64-bit) */
+#define BPF_MEMSX 0x80 /* load with sign extension */
#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */
#define BPF_XADD 0xc0 /* exclusive add - legacy name */
@@ -1187,6 +1188,11 @@ enum bpf_perf_event_type {
*/
#define BPF_F_KPROBE_MULTI_RETURN (1U << 0)
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* the following extensions:
*
@@ -4198,9 +4204,6 @@ union bpf_attr {
* **-EOPNOTSUPP** if the operation is not supported, for example
* a call from outside of TC ingress.
*
- * **-ESOCKTNOSUPPORT** if the socket type is not supported
- * (reuseport).
- *
* long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
* Description
* Helper is overloaded depending on BPF program type. This
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ef9581a580e2..249657c466dd 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -29,6 +29,7 @@
#include <net/netfilter/nf_bpf_link.h>
#include <net/sock.h>
+#include <net/xdp.h>
#include "../tools/lib/bpf/relo_core.h"
/* BTF (BPF Type Format) is the meta data format which describes
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index dc85240a0134..0f8f036d8bd1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -61,6 +61,7 @@
#define AX regs[BPF_REG_AX]
#define ARG1 regs[BPF_REG_ARG1]
#define CTX regs[BPF_REG_CTX]
+#define OFF insn->off
#define IMM insn->imm
struct bpf_mem_alloc bpf_global_ma;
@@ -372,7 +373,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
{
const s32 off_min = S16_MIN, off_max = S16_MAX;
s32 delta = end_new - end_old;
- s32 off = insn->off;
+ s32 off;
+
+ if (insn->code == (BPF_JMP32 | BPF_JA))
+ off = insn->imm;
+ else
+ off = insn->off;
if (curr < pos && curr + off + 1 >= end_old)
off += delta;
@@ -380,8 +386,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
off -= delta;
if (off < off_min || off > off_max)
return -ERANGE;
- if (!probe_pass)
- insn->off = off;
+ if (!probe_pass) {
+ if (insn->code == (BPF_JMP32 | BPF_JA))
+ insn->imm = off;
+ else
+ insn->off = off;
+ }
return 0;
}
@@ -1271,7 +1281,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
case BPF_ALU | BPF_MOD | BPF_K:
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
+ *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
case BPF_ALU64 | BPF_ADD | BPF_K:
@@ -1285,7 +1295,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
case BPF_ALU64 | BPF_MOD | BPF_K:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
+ *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
@@ -1523,6 +1533,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(ALU64, DIV, X), \
INSN_3(ALU64, MOD, X), \
INSN_2(ALU64, NEG), \
+ INSN_3(ALU64, END, TO_LE), \
/* Immediate based. */ \
INSN_3(ALU64, ADD, K), \
INSN_3(ALU64, SUB, K), \
@@ -1591,6 +1602,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(JMP, JSLE, K), \
INSN_3(JMP, JSET, K), \
INSN_2(JMP, JA), \
+ INSN_2(JMP32, JA), \
/* Store instructions. */ \
/* Register based. */ \
INSN_3(STX, MEM, B), \
@@ -1610,6 +1622,9 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(LDX, MEM, H), \
INSN_3(LDX, MEM, W), \
INSN_3(LDX, MEM, DW), \
+ INSN_3(LDX, MEMSX, B), \
+ INSN_3(LDX, MEMSX, H), \
+ INSN_3(LDX, MEMSX, W), \
/* Immediate based. */ \
INSN_3(LD, IMM, DW)
@@ -1635,12 +1650,6 @@ bool bpf_opcode_in_insntable(u8 code)
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
-u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
-{
- memset(dst, 0, size);
- return -EFAULT;
-}
-
/**
* ___bpf_prog_run - run eBPF program on a given context
* @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1666,6 +1675,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
[BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W,
};
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
@@ -1733,13 +1745,36 @@ select_insn:
DST = -DST;
CONT;
ALU_MOV_X:
- DST = (u32) SRC;
+ switch (OFF) {
+ case 0:
+ DST = (u32) SRC;
+ break;
+ case 8:
+ DST = (u32)(s8) SRC;
+ break;
+ case 16:
+ DST = (u32)(s16) SRC;
+ break;
+ }
CONT;
ALU_MOV_K:
DST = (u32) IMM;
CONT;
ALU64_MOV_X:
- DST = SRC;
+ switch (OFF) {
+ case 0:
+ DST = SRC;
+ break;
+ case 8:
+ DST = (s8) SRC;
+ break;
+ case 16:
+ DST = (s16) SRC;
+ break;
+ case 32:
+ DST = (s32) SRC;
+ break;
+ }
CONT;
ALU64_MOV_K:
DST = IMM;
@@ -1761,36 +1796,114 @@ select_insn:
(*(s64 *) &DST) >>= IMM;
CONT;
ALU64_MOD_X:
- div64_u64_rem(DST, SRC, &AX);
- DST = AX;
+ switch (OFF) {
+ case 0:
+ div64_u64_rem(DST, SRC, &AX);
+ DST = AX;
+ break;
+ case 1:
+ AX = div64_s64(DST, SRC);
+ DST = DST - AX * SRC;
+ break;
+ }
CONT;
ALU_MOD_X:
- AX = (u32) DST;
- DST = do_div(AX, (u32) SRC);
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) SRC);
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ AX = do_div(AX, abs((s32)SRC));
+ if ((s32)DST < 0)
+ DST = (u32)-AX;
+ else
+ DST = (u32)AX;
+ break;
+ }
CONT;
ALU64_MOD_K:
- div64_u64_rem(DST, IMM, &AX);
- DST = AX;
+ switch (OFF) {
+ case 0:
+ div64_u64_rem(DST, IMM, &AX);
+ DST = AX;
+ break;
+ case 1:
+ AX = div64_s64(DST, IMM);
+ DST = DST - AX * IMM;
+ break;
+ }
CONT;
ALU_MOD_K:
- AX = (u32) DST;
- DST = do_div(AX, (u32) IMM);
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) IMM);
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ AX = do_div(AX, abs((s32)IMM));
+ if ((s32)DST < 0)
+ DST = (u32)-AX;
+ else
+ DST = (u32)AX;
+ break;
+ }
CONT;
ALU64_DIV_X:
- DST = div64_u64(DST, SRC);
+ switch (OFF) {
+ case 0:
+ DST = div64_u64(DST, SRC);
+ break;
+ case 1:
+ DST = div64_s64(DST, SRC);
+ break;
+ }
CONT;
ALU_DIV_X:
- AX = (u32) DST;
- do_div(AX, (u32) SRC);
- DST = (u32) AX;
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ do_div(AX, (u32) SRC);
+ DST = (u32) AX;
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ do_div(AX, abs((s32)SRC));
+ if (((s32)DST < 0) == ((s32)SRC < 0))
+ DST = (u32)AX;
+ else
+ DST = (u32)-AX;
+ break;
+ }
CONT;
ALU64_DIV_K:
- DST = div64_u64(DST, IMM);
+ switch (OFF) {
+ case 0:
+ DST = div64_u64(DST, IMM);
+ break;
+ case 1:
+ DST = div64_s64(DST, IMM);
+ break;
+ }
CONT;
ALU_DIV_K:
- AX = (u32) DST;
- do_div(AX, (u32) IMM);
- DST = (u32) AX;
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ do_div(AX, (u32) IMM);
+ DST = (u32) AX;
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ do_div(AX, abs((s32)IMM));
+ if (((s32)DST < 0) == ((s32)IMM < 0))
+ DST = (u32)AX;
+ else
+ DST = (u32)-AX;
+ break;
+ }
CONT;
ALU_END_TO_BE:
switch (IMM) {
@@ -1818,6 +1931,19 @@ select_insn:
break;
}
CONT;
+ ALU64_END_TO_LE:
+ switch (IMM) {
+ case 16:
+ DST = (__force u16) __swab16(DST);
+ break;
+ case 32:
+ DST = (__force u32) __swab32(DST);
+ break;
+ case 64:
+ DST = (__force u64) __swab64(DST);
+ break;
+ }
+ CONT;
/* CALL */
JMP_CALL:
@@ -1867,6 +1993,9 @@ out:
JMP_JA:
insn += insn->off;
CONT;
+ JMP32_JA:
+ insn += insn->imm;
+ CONT;
JMP_EXIT:
return BPF_R0;
/* JMP */
@@ -1931,8 +2060,8 @@ out:
DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
CONT; \
LDX_PROBE_MEM_##SIZEOP: \
- bpf_probe_read_kernel(&DST, sizeof(SIZE), \
- (const void *)(long) (SRC + insn->off)); \
+ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
DST = *((SIZE *)&DST); \
CONT;
@@ -1942,6 +2071,21 @@ out:
LDST(DW, u64)
#undef LDST
+#define LDSX(SIZEOP, SIZE) \
+ LDX_MEMSX_##SIZEOP: \
+ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
+ CONT; \
+ LDX_PROBE_MEMSX_##SIZEOP: \
+ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
+ DST = *((SIZE *)&DST); \
+ CONT;
+
+ LDSX(B, s8)
+ LDSX(H, s16)
+ LDSX(W, s32)
+#undef LDSX
+
#define ATOMIC_ALU_OP(BOP, KOP) \
case BOP: \
if (BPF_SIZE(insn->code) == BPF_W) \
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 286ab3db0fde..ef28c64f1eb1 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -61,8 +61,6 @@ struct bpf_cpu_map_entry {
/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
struct xdp_bulk_queue __percpu *bulkq;
- struct bpf_cpu_map *cmap;
-
/* Queue with potential multi-producers, and single-consumer kthread */
struct ptr_ring *queue;
struct task_struct *kthread;
@@ -595,7 +593,6 @@ static long cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
if (!rcpu)
return -ENOMEM;
- rcpu->cmap = cmap;
}
rcu_read_lock();
__cpu_map_entry_replace(cmap, key_cpu, rcpu);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 49cc0b5671c6..4d42f6ed6c11 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -65,7 +65,6 @@ struct xdp_dev_bulk_queue {
struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
- struct bpf_dtab *dtab;
struct bpf_prog *xdp_prog;
struct rcu_head rcu;
unsigned int idx;
@@ -874,7 +873,6 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
}
dev->idx = idx;
- dev->dtab = dtab;
if (prog) {
dev->xdp_prog = prog;
dev->val.bpf_prog.id = prog->aux->id;
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 7b4afb7d96db..ef7c107c7b8f 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -87,6 +87,17 @@ const char *const bpf_alu_string[16] = {
[BPF_END >> 4] = "endian",
};
+const char *const bpf_alu_sign_string[16] = {
+ [BPF_DIV >> 4] = "s/=",
+ [BPF_MOD >> 4] = "s%=",
+};
+
+const char *const bpf_movsx_string[4] = {
+ [0] = "(s8)",
+ [1] = "(s16)",
+ [3] = "(s32)",
+};
+
static const char *const bpf_atomic_alu_string[16] = {
[BPF_ADD >> 4] = "add",
[BPF_AND >> 4] = "and",
@@ -101,6 +112,12 @@ static const char *const bpf_ldst_string[] = {
[BPF_DW >> 3] = "u64",
};
+static const char *const bpf_ldsx_string[] = {
+ [BPF_W >> 3] = "s32",
+ [BPF_H >> 3] = "s16",
+ [BPF_B >> 3] = "s8",
+};
+
static const char *const bpf_jmp_string[16] = {
[BPF_JA >> 4] = "jmp",
[BPF_JEQ >> 4] = "==",
@@ -128,6 +145,27 @@ static void print_bpf_end_insn(bpf_insn_print_t verbose,
insn->imm, insn->dst_reg);
}
+static void print_bpf_bswap_insn(bpf_insn_print_t verbose,
+ void *private_data,
+ const struct bpf_insn *insn)
+{
+ verbose(private_data, "(%02x) r%d = bswap%d r%d\n",
+ insn->code, insn->dst_reg,
+ insn->imm, insn->dst_reg);
+}
+
+static bool is_sdiv_smod(const struct bpf_insn *insn)
+{
+ return (BPF_OP(insn->code) == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) &&
+ insn->off == 1;
+}
+
+static bool is_movsx(const struct bpf_insn *insn)
+{
+ return BPF_OP(insn->code) == BPF_MOV &&
+ (insn->off == 8 || insn->off == 16 || insn->off == 32);
+}
+
void print_bpf_insn(const struct bpf_insn_cbs *cbs,
const struct bpf_insn *insn,
bool allow_ptr_leaks)
@@ -138,7 +176,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
if (class == BPF_ALU || class == BPF_ALU64) {
if (BPF_OP(insn->code) == BPF_END) {
if (class == BPF_ALU64)
- verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code);
+ print_bpf_bswap_insn(verbose, cbs->private_data, insn);
else
print_bpf_end_insn(verbose, cbs->private_data, insn);
} else if (BPF_OP(insn->code) == BPF_NEG) {
@@ -147,17 +185,20 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
insn->dst_reg, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg);
} else if (BPF_SRC(insn->code) == BPF_X) {
- verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n",
+ verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n",
insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+ : bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "",
class == BPF_ALU ? 'w' : 'r',
insn->src_reg);
} else {
verbose(cbs->private_data, "(%02x) %c%d %s %d\n",
insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+ : bpf_alu_string[BPF_OP(insn->code) >> 4],
insn->imm);
}
} else if (class == BPF_STX) {
@@ -218,13 +259,15 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
}
} else if (class == BPF_LDX) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
+ if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
return;
}
verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n",
insn->code, insn->dst_reg,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ BPF_MODE(insn->code) == BPF_MEM ?
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3] :
+ bpf_ldsx_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->off);
} else if (class == BPF_LD) {
if (BPF_MODE(insn->code) == BPF_ABS) {
@@ -279,6 +322,9 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
} else if (insn->code == (BPF_JMP | BPF_JA)) {
verbose(cbs->private_data, "(%02x) goto pc%+d\n",
insn->code, insn->off);
+ } else if (insn->code == (BPF_JMP32 | BPF_JA)) {
+ verbose(cbs->private_data, "(%02x) gotol pc%+d\n",
+ insn->code, insn->imm);
} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
verbose(cbs->private_data, "(%02x) exit\n", insn->code);
} else if (BPF_SRC(insn->code) == BPF_X) {
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 51d6389e5152..9c49ae53deaf 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -183,11 +183,11 @@ static void inc_active(struct bpf_mem_cache *c, unsigned long *flags)
WARN_ON_ONCE(local_inc_return(&c->active) != 1);
}
-static void dec_active(struct bpf_mem_cache *c, unsigned long flags)
+static void dec_active(struct bpf_mem_cache *c, unsigned long *flags)
{
local_dec(&c->active);
if (IS_ENABLED(CONFIG_PREEMPT_RT))
- local_irq_restore(flags);
+ local_irq_restore(*flags);
}
static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
@@ -197,16 +197,20 @@ static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
inc_active(c, &flags);
__llist_add(obj, &c->free_llist);
c->free_cnt++;
- dec_active(c, flags);
+ dec_active(c, &flags);
}
/* Mostly runs from irq_work except __init phase. */
-static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
+static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic)
{
struct mem_cgroup *memcg = NULL, *old_memcg;
+ gfp_t gfp;
void *obj;
int i;
+ gfp = __GFP_NOWARN | __GFP_ACCOUNT;
+ gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL;
+
for (i = 0; i < cnt; i++) {
/*
* For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is
@@ -238,7 +242,7 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
* will allocate from the current numa node which is what we
* want here.
*/
- obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
+ obj = __alloc(c, node, gfp);
if (!obj)
break;
add_obj_to_free_list(c, obj);
@@ -344,7 +348,7 @@ static void free_bulk(struct bpf_mem_cache *c)
cnt = --c->free_cnt;
else
cnt = 0;
- dec_active(c, flags);
+ dec_active(c, &flags);
if (llnode)
enque_to_free(tgt, llnode);
} while (cnt > (c->high_watermark + c->low_watermark) / 2);
@@ -384,7 +388,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c)
llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu))
if (__llist_add(llnode, &c->free_by_rcu))
c->free_by_rcu_tail = llnode;
- dec_active(c, flags);
+ dec_active(c, &flags);
}
if (llist_empty(&c->free_by_rcu))
@@ -408,7 +412,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c)
inc_active(c, &flags);
WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu));
c->waiting_for_gp_tail = c->free_by_rcu_tail;
- dec_active(c, flags);
+ dec_active(c, &flags);
if (unlikely(READ_ONCE(c->draining))) {
free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
@@ -429,7 +433,7 @@ static void bpf_mem_refill(struct irq_work *work)
/* irq_work runs on this cpu and kmalloc will allocate
* from the current numa node which is what we want here.
*/
- alloc_bulk(c, c->batch, NUMA_NO_NODE);
+ alloc_bulk(c, c->batch, NUMA_NO_NODE, true);
else if (cnt > c->high_watermark)
free_bulk(c);
@@ -477,7 +481,7 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
* prog won't be doing more than 4 map_update_elem from
* irq disabled region
*/
- alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
+ alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
}
/* When size != 0 bpf_mem_cache for each cpu.
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 8a26cd8814c1..3e4f2ec1af06 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -25,6 +25,7 @@
#include <linux/rhashtable.h>
#include <linux/rtnetlink.h>
#include <linux/rwsem.h>
+#include <net/xdp.h>
/* Protects offdevs, members of bpf_offload_netdev and offload members
* of all progs.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 71473c19093d..132f25dab931 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
#include <linux/poison.h>
#include <linux/module.h>
#include <linux/cpumask.h>
+#include <net/xdp.h>
#include "disasm.h"
@@ -2855,7 +2856,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
- off = i + insn[i].off + 1;
+ if (code == (BPF_JMP32 | BPF_JA))
+ off = i + insn[i].imm + 1;
+ else
+ off = i + insn[i].off + 1;
if (off < subprog_start || off >= subprog_end) {
verbose(env, "jump out of range from insn %d to %d\n", i, off);
return -EINVAL;
@@ -2867,6 +2871,7 @@ next:
* or unconditional jump back
*/
if (code != (BPF_JMP | BPF_EXIT) &&
+ code != (BPF_JMP32 | BPF_JA) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
return -EINVAL;
@@ -3012,8 +3017,10 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
}
}
+ if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32))
+ return false;
+
if (class == BPF_ALU64 || class == BPF_JMP ||
- /* BPF_END always use BPF_ALU class. */
(class == BPF_ALU && op == BPF_END && insn->imm == 64))
return true;
@@ -3421,7 +3428,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
return 0;
if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- /* dreg = sreg
+ /* dreg = sreg or dreg = (s8, s16, s32)sreg
* dreg needs precision after this insn
* sreg needs precision before this insn
*/
@@ -5827,6 +5834,147 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
__reg_combine_64_into_32(reg);
}
+static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->smin_value = reg->s32_min_value = S8_MIN;
+ reg->smax_value = reg->s32_max_value = S8_MAX;
+ } else if (size == 2) {
+ reg->smin_value = reg->s32_min_value = S16_MIN;
+ reg->smax_value = reg->s32_max_value = S16_MAX;
+ } else {
+ /* size == 4 */
+ reg->smin_value = reg->s32_min_value = S32_MIN;
+ reg->smax_value = reg->s32_max_value = S32_MAX;
+ }
+ reg->umin_value = reg->u32_min_value = 0;
+ reg->umax_value = U64_MAX;
+ reg->u32_max_value = U32_MAX;
+ reg->var_off = tnum_unknown;
+}
+
+static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval;
+ u64 top_smax_value, top_smin_value;
+ u64 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u64_cval = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u64_cval);
+ else if (size == 2)
+ reg->var_off = tnum_const((s16)u64_cval);
+ else
+ /* size == 4 */
+ reg->var_off = tnum_const((s32)u64_cval);
+
+ u64_cval = reg->var_off.value;
+ reg->smax_value = reg->smin_value = u64_cval;
+ reg->umax_value = reg->umin_value = u64_cval;
+ reg->s32_max_value = reg->s32_min_value = u64_cval;
+ reg->u32_max_value = reg->u32_min_value = u64_cval;
+ return;
+ }
+
+ top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits;
+ top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s64_min and s64_min after sign extension */
+ if (size == 1) {
+ init_s64_max = (s8)reg->smax_value;
+ init_s64_min = (s8)reg->smin_value;
+ } else if (size == 2) {
+ init_s64_max = (s16)reg->smax_value;
+ init_s64_min = (s16)reg->smin_value;
+ } else {
+ init_s64_max = (s32)reg->smax_value;
+ init_s64_min = (s32)reg->smin_value;
+ }
+
+ s64_max = max(init_s64_max, init_s64_min);
+ s64_min = min(init_s64_max, init_s64_min);
+
+ /* both of s64_max/s64_min positive or negative */
+ if ((s64_max >= 0) == (s64_min >= 0)) {
+ reg->smin_value = reg->s32_min_value = s64_min;
+ reg->smax_value = reg->s32_max_value = s64_max;
+ reg->umin_value = reg->u32_min_value = s64_min;
+ reg->umax_value = reg->u32_max_value = s64_max;
+ reg->var_off = tnum_range(s64_min, s64_max);
+ return;
+ }
+
+out:
+ set_sext64_default_val(reg, size);
+}
+
+static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->s32_min_value = S8_MIN;
+ reg->s32_max_value = S8_MAX;
+ } else {
+ /* size == 2 */
+ reg->s32_min_value = S16_MIN;
+ reg->s32_max_value = S16_MAX;
+ }
+ reg->u32_min_value = 0;
+ reg->u32_max_value = U32_MAX;
+}
+
+static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val;
+ u32 top_smax_value, top_smin_value;
+ u32 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u32_val = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u32_val);
+ else
+ reg->var_off = tnum_const((s16)u32_val);
+
+ u32_val = reg->var_off.value;
+ reg->s32_min_value = reg->s32_max_value = u32_val;
+ reg->u32_min_value = reg->u32_max_value = u32_val;
+ return;
+ }
+
+ top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits;
+ top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s32_min and s32_min after sign extension */
+ if (size == 1) {
+ init_s32_max = (s8)reg->s32_max_value;
+ init_s32_min = (s8)reg->s32_min_value;
+ } else {
+ /* size == 2 */
+ init_s32_max = (s16)reg->s32_max_value;
+ init_s32_min = (s16)reg->s32_min_value;
+ }
+ s32_max = max(init_s32_max, init_s32_min);
+ s32_min = min(init_s32_max, init_s32_min);
+
+ if ((s32_min >= 0) == (s32_max >= 0)) {
+ reg->s32_min_value = s32_min;
+ reg->s32_max_value = s32_max;
+ reg->u32_min_value = (u32)s32_min;
+ reg->u32_max_value = (u32)s32_max;
+ return;
+ }
+
+out:
+ set_sext32_default_val(reg, size);
+}
+
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
/* A map is considered read-only if the following condition are true:
@@ -5847,7 +5995,8 @@ static bool bpf_map_is_rdonly(const struct bpf_map *map)
!bpf_map_write_active(map);
}
-static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
+ bool is_ldsx)
{
void *ptr;
u64 addr;
@@ -5860,13 +6009,13 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
switch (size) {
case sizeof(u8):
- *val = (u64)*(u8 *)ptr;
+ *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr;
break;
case sizeof(u16):
- *val = (u64)*(u16 *)ptr;
+ *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr;
break;
case sizeof(u32):
- *val = (u64)*(u32 *)ptr;
+ *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr;
break;
case sizeof(u64):
*val = *(u64 *)ptr;
@@ -6285,7 +6434,7 @@ static int check_stack_access_within_bounds(
*/
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
int off, int bpf_size, enum bpf_access_type t,
- int value_regno, bool strict_alignment_once)
+ int value_regno, bool strict_alignment_once, bool is_ldsx)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
@@ -6346,7 +6495,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
u64 val = 0;
err = bpf_map_direct_read(map, map_off, size,
- &val);
+ &val, is_ldsx);
if (err)
return err;
@@ -6516,8 +6665,11 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
regs[value_regno].type == SCALAR_VALUE) {
- /* b/h/w load zero-extends, mark upper bits as known 0 */
- coerce_reg_to_size(®s[value_regno], size);
+ if (!is_ldsx)
+ /* b/h/w load zero-extends, mark upper bits as known 0 */
+ coerce_reg_to_size(®s[value_regno], size);
+ else
+ coerce_reg_to_size_sx(®s[value_regno], size);
}
return err;
}
@@ -6609,17 +6761,17 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
* case to simulate the register fill.
*/
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_READ, -1, true);
+ BPF_SIZE(insn->code), BPF_READ, -1, true, false);
if (!err && load_reg >= 0)
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, load_reg,
- true);
+ true, false);
if (err)
return err;
/* Check whether we can write into the same memory. */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+ BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
if (err)
return err;
@@ -6865,7 +7017,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return zero_size_allowed ? 0 : -EACCES;
return check_mem_access(env, env->insn_idx, regno, offset, BPF_B,
- atype, -1, false);
+ atype, -1, false, false);
}
fallthrough;
@@ -7237,7 +7389,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
/* we write BPF_DW bits (8 bytes) at a time */
for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -7330,7 +7482,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -9474,7 +9626,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
*/
for (i = 0; i < meta.access_size; i++) {
err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -12931,7 +13083,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
(insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
- BPF_CLASS(insn->code) == BPF_ALU64) {
+ (BPF_CLASS(insn->code) == BPF_ALU64 &&
+ BPF_SRC(insn->code) != BPF_TO_LE)) {
verbose(env, "BPF_END uses reserved fields\n");
return -EINVAL;
}
@@ -12956,11 +13109,24 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
+ if (BPF_CLASS(insn->code) == BPF_ALU) {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ } else {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16 &&
+ insn->off != 32) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
@@ -12984,18 +13150,33 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
!tnum_is_const(src_reg->var_off);
if (BPF_CLASS(insn->code) == BPF_ALU64) {
- /* case: R1 = R2
- * copy register state to dest reg
- */
- if (need_id)
- /* Assign src and dst registers the same ID
- * that will be used by find_equal_scalars()
- * to propagate min/max range.
+ if (insn->off == 0) {
+ /* case: R1 = R2
+ * copy register state to dest reg
*/
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = DEF_NOT_SUBREG;
+ if (need_id)
+ /* Assign src and dst registers the same ID
+ * that will be used by find_equal_scalars()
+ * to propagate min/max range.
+ */
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ } else {
+ /* case: R1 = (s8, s16 s32)R2 */
+ bool no_sext;
+
+ no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ }
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
@@ -13004,19 +13185,33 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
- bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
+ if (insn->off == 0) {
+ bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
- if (is_src_reg_u32 && need_id)
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- /* Make sure ID is cleared if src_reg is not in u32 range otherwise
- * dst_reg min/max could be incorrectly
- * propagated into src_reg by find_equal_scalars()
- */
- if (!is_src_reg_u32)
- dst_reg->id = 0;
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = env->insn_idx + 1;
+ if (is_src_reg_u32 && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ /* Make sure ID is cleared if src_reg is not in u32
+ * range otherwise dst_reg min/max could be incorrectly
+ * propagated into src_reg by find_equal_scalars()
+ */
+ if (!is_src_reg_u32)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ } else {
+ /* case: W1 = (s8, s16)W2 */
+ bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ coerce_subreg_to_size_sx(dst_reg, insn->off >> 3);
+ }
} else {
mark_reg_unknown(env, regs,
insn->dst_reg);
@@ -13047,7 +13242,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else { /* all other ALU ops: and, sub, xor, add, ... */
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -13056,7 +13252,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (err)
return err;
} else {
- if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+ if (insn->src_reg != BPF_REG_0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -14600,7 +14797,7 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
static int visit_insn(int t, struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
- int ret;
+ int ret, off;
if (bpf_pseudo_func(insn))
return visit_func_call_insn(t, insns, env, true);
@@ -14648,14 +14845,19 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
if (BPF_SRC(insn->code) != BPF_K)
return -EINVAL;
+ if (BPF_CLASS(insn->code) == BPF_JMP)
+ off = insn->off;
+ else
+ off = insn->imm;
+
/* unconditional jump with single edge */
- ret = push_insn(t, t + insn->off + 1, FALLTHROUGH, env,
+ ret = push_insn(t, t + off + 1, FALLTHROUGH, env,
true);
if (ret)
return ret;
- mark_prune_point(env, t + insn->off + 1);
- mark_jmp_point(env, t + insn->off + 1);
+ mark_prune_point(env, t + off + 1);
+ mark_jmp_point(env, t + off + 1);
return ret;
@@ -16202,7 +16404,7 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
* Have to support a use case when one path through
* the program yields TRUSTED pointer while another
* is UNTRUSTED. Fallback to UNTRUSTED to generate
- * BPF_PROBE_MEM.
+ * BPF_PROBE_MEM/BPF_PROBE_MEMSX.
*/
*prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
} else {
@@ -16343,7 +16545,8 @@ static int do_check(struct bpf_verifier_env *env)
*/
err = check_mem_access(env, env->insn_idx, insn->src_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_READ, insn->dst_reg, false);
+ BPF_READ, insn->dst_reg, false,
+ BPF_MODE(insn->code) == BPF_MEMSX);
if (err)
return err;
@@ -16380,7 +16583,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, insn->src_reg, false);
+ BPF_WRITE, insn->src_reg, false, false);
if (err)
return err;
@@ -16405,7 +16608,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
@@ -16450,15 +16653,18 @@ static int do_check(struct bpf_verifier_env *env)
mark_reg_scratched(env, BPF_REG_0);
} else if (opcode == BPF_JA) {
if (BPF_SRC(insn->code) != BPF_K ||
- insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0 ||
- class == BPF_JMP32) {
+ (class == BPF_JMP && insn->imm != 0) ||
+ (class == BPF_JMP32 && insn->off != 0)) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
- env->insn_idx += insn->off + 1;
+ if (class == BPF_JMP)
+ env->insn_idx += insn->off + 1;
+ else
+ env->insn_idx += insn->imm + 1;
continue;
} else if (opcode == BPF_EXIT) {
@@ -16833,7 +17039,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
+ ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) ||
+ insn->imm != 0)) {
verbose(env, "BPF_LDX uses reserved fields\n");
return -EINVAL;
}
@@ -17304,13 +17511,13 @@ static bool insn_is_cond_jump(u8 code)
{
u8 op;
+ op = BPF_OP(code);
if (BPF_CLASS(code) == BPF_JMP32)
- return true;
+ return op != BPF_JA;
if (BPF_CLASS(code) != BPF_JMP)
return false;
- op = BPF_OP(code);
return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
}
@@ -17527,11 +17734,15 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
+ u8 mode;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) {
type = BPF_READ;
} else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
@@ -17590,8 +17801,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
*/
case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
if (type == BPF_READ) {
- insn->code = BPF_LDX | BPF_PROBE_MEM |
- BPF_SIZE((insn)->code);
+ if (BPF_MODE(insn->code) == BPF_MEM)
+ insn->code = BPF_LDX | BPF_PROBE_MEM |
+ BPF_SIZE((insn)->code);
+ else
+ insn->code = BPF_LDX | BPF_PROBE_MEMSX |
+ BPF_SIZE((insn)->code);
env->prog->aux->num_exentries++;
}
continue;
@@ -17601,6 +17816,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
size = BPF_LDST_BYTES(insn);
+ mode = BPF_MODE(insn->code);
/* If the read access is a narrower load of the field,
* convert to a 4/8-byte load, to minimum program type specific
@@ -17660,6 +17876,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
(1ULL << size * 8) - 1);
}
}
+ if (mode == BPF_MEMSX)
+ insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X,
+ insn->dst_reg, insn->dst_reg,
+ size * 8, 0);
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
@@ -17779,7 +17999,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- BPF_MODE(insn->code) == BPF_PROBE_MEM)
+ (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
num_exentries++;
}
func[i]->aux->num_exentries = num_exentries;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 79719979a635..d6296d51a826 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -223,17 +223,6 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = {
.arg3_type = ARG_ANYTHING,
};
-static __always_inline int
-bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
-{
- int ret;
-
- ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
- if (unlikely(ret < 0))
- memset(dst, 0, size);
- return ret;
-}
-
BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
const void *, unsafe_ptr)
{
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 942ddbdace4a..de753403cdaf 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -555,12 +555,15 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
struct syscall_trace_enter *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
+ struct trace_entry ent;
unsigned long syscall_nr;
unsigned long args[SYSCALL_DEFINE_MAXARGS];
- } param;
+ } __aligned(8) param;
int i;
+ BUILD_BUG_ON(sizeof(param.ent) < sizeof(void *));
+
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. ¶m) */
*(struct pt_regs **)¶m = regs;
param.syscall_nr = rec->nr;
for (i = 0; i < sys_data->nb_args; i++)
@@ -657,11 +660,12 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
struct syscall_trace_exit *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
+ struct trace_entry ent;
unsigned long syscall_nr;
unsigned long ret;
- } param;
+ } __aligned(8) param;
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. ¶m) */
*(struct pt_regs **)¶m = regs;
param.syscall_nr = rec->nr;
param.ret = rec->ret;
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 7d47f53f20c1..0aac76c13fd4 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -20,6 +20,7 @@
#include <linux/smp.h>
#include <linux/sock_diag.h>
#include <linux/netfilter.h>
+#include <net/netdev_rx_queue.h>
#include <net/xdp.h>
#include <net/netfilter/nf_bpf_link.h>
diff --git a/net/core/dev.c b/net/core/dev.c
index 10e5a036c706..636b41f0b32d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -133,6 +133,7 @@
#include <trace/events/net.h>
#include <trace/events/skb.h>
#include <trace/events/qdisc.h>
+#include <trace/events/xdp.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
@@ -151,6 +152,7 @@
#include <linux/pm_runtime.h>
#include <linux/prandom.h>
#include <linux/once_lite.h>
+#include <net/netdev_rx_queue.h>
#include "dev.h"
#include "net-sysfs.h"
@@ -9475,6 +9477,7 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct net *net = current->nsproxy->net_ns;
struct bpf_link_primer link_primer;
+ struct netlink_ext_ack extack = {};
struct bpf_xdp_link *link;
struct net_device *dev;
int err, fd;
@@ -9502,12 +9505,13 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
goto unlock;
}
- err = dev_xdp_attach_link(dev, NULL, link);
+ err = dev_xdp_attach_link(dev, &extack, link);
rtnl_unlock();
if (err) {
link->dev = NULL;
bpf_link_cleanup(&link_primer);
+ trace_bpf_xdp_link_attach_failed(extack._msg);
goto out_put_dev;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 797e8f039696..7c37f4646c20 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7351,8 +7351,8 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
return -EOPNOTSUPP;
if (unlikely(dev_net(skb->dev) != sock_net(sk)))
return -ENETUNREACH;
- if (unlikely(sk_fullsock(sk) && sk->sk_reuseport))
- return -ESOCKTNOSUPPORT;
+ if (sk_unhashed(sk))
+ return -EOPNOTSUPP;
if (sk_is_refcounted(sk) &&
unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
return -ENOENT;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 15e3f4606b5f..fccaa5bac0ed 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -23,6 +23,7 @@
#include <linux/of.h>
#include <linux/of_net.h>
#include <linux/cpu.h>
+#include <net/netdev_rx_queue.h>
#include "dev.h"
#include "net-sysfs.h"
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 0819d6001b9a..7876b7d703cb 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -28,9 +28,9 @@
#include <net/tcp.h>
#include <net/sock_reuseport.h>
-static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
- const __u16 lport, const __be32 faddr,
- const __be16 fport)
+u32 inet_ehashfn(const struct net *net, const __be32 laddr,
+ const __u16 lport, const __be32 faddr,
+ const __be16 fport)
{
static u32 inet_ehash_secret __read_mostly;
@@ -39,6 +39,7 @@ static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
return __inet_ehashfn(laddr, lport, faddr, fport,
inet_ehash_secret + net_hash_mix(net));
}
+EXPORT_SYMBOL_GPL(inet_ehashfn);
/* This function handles inet_sock, but also timewait and request sockets
* for IPv4/IPv6.
@@ -332,20 +333,38 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
-static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb, int doff,
- __be32 saddr, __be16 sport,
- __be32 daddr, unsigned short hnum)
+/**
+ * inet_lookup_reuseport() - execute reuseport logic on AF_INET socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ * the selected sock or an error.
+ */
+struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned short hnum,
+ inet_ehashfn_t *ehashfn)
{
struct sock *reuse_sk = NULL;
u32 phash;
if (sk->sk_reuseport) {
- phash = inet_ehashfn(net, daddr, hnum, saddr, sport);
+ phash = INDIRECT_CALL_2(ehashfn, udp_ehashfn, inet_ehashfn,
+ net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
}
return reuse_sk;
}
+EXPORT_SYMBOL_GPL(inet_lookup_reuseport);
/*
* Here are some nice properties to exploit here. The BSD API
@@ -369,8 +388,8 @@ static struct sock *inet_lhash2_lookup(struct net *net,
sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
- result = lookup_reuseport(net, sk, skb, doff,
- saddr, sport, daddr, hnum);
+ result = inet_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum, inet_ehashfn);
if (result)
return result;
@@ -382,24 +401,23 @@ static struct sock *inet_lhash2_lookup(struct net *net,
return result;
}
-static inline struct sock *inet_lookup_run_bpf(struct net *net,
- struct inet_hashinfo *hashinfo,
- struct sk_buff *skb, int doff,
- __be32 saddr, __be16 sport,
- __be32 daddr, u16 hnum, const int dif)
+struct sock *inet_lookup_run_sk_lookup(struct net *net,
+ int protocol,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, u16 hnum, const int dif,
+ inet_ehashfn_t *ehashfn)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
- if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
- return NULL; /* only TCP is supported */
-
- no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport,
+ no_reuseport = bpf_sk_lookup_run_v4(net, protocol, saddr, sport,
daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
- reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+ reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum,
+ ehashfn);
if (reuse_sk)
sk = reuse_sk;
return sk;
@@ -417,9 +435,11 @@ struct sock *__inet_lookup_listener(struct net *net,
unsigned int hash2;
/* Lookup redirect from BPF */
- if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
- result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
- saddr, sport, daddr, hnum, dif);
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+ hashinfo == net->ipv4.tcp_death_row.hashinfo) {
+ result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+ saddr, sport, daddr, hnum, dif,
+ inet_ehashfn);
if (result)
goto done;
}
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index e61ea428ea18..a9ba7de092c4 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -7,6 +7,7 @@
#include <linux/ip.h>
#include <linux/netfilter.h>
#include <linux/module.h>
+#include <linux/rcupdate.h>
#include <linux/skbuff.h>
#include <net/netns/generic.h>
#include <net/route.h>
@@ -113,17 +114,31 @@ static void __net_exit defrag4_net_exit(struct net *net)
}
}
+static const struct nf_defrag_hook defrag_hook = {
+ .owner = THIS_MODULE,
+ .enable = nf_defrag_ipv4_enable,
+ .disable = nf_defrag_ipv4_disable,
+};
+
static struct pernet_operations defrag4_net_ops = {
.exit = defrag4_net_exit,
};
static int __init nf_defrag_init(void)
{
- return register_pernet_subsys(&defrag4_net_ops);
+ int err;
+
+ err = register_pernet_subsys(&defrag4_net_ops);
+ if (err)
+ return err;
+
+ rcu_assign_pointer(nf_defrag_v4_hook, &defrag_hook);
+ return err;
}
static void __exit nf_defrag_fini(void)
{
+ rcu_assign_pointer(nf_defrag_v4_hook, NULL);
unregister_pernet_subsys(&defrag4_net_ops);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1ee9e56dc79a..3e2f29c14fa8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -407,9 +407,9 @@ static int compute_score(struct sock *sk, struct net *net,
return score;
}
-static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
- const __u16 lport, const __be32 faddr,
- const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport,
+ const __be32 faddr, const __be16 fport)
{
static u32 udp_ehash_secret __read_mostly;
@@ -419,22 +419,6 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
udp_ehash_secret + net_hash_mix(net));
}
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb,
- __be32 saddr, __be16 sport,
- __be32 daddr, unsigned short hnum)
-{
- struct sock *reuse_sk = NULL;
- u32 hash;
-
- if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
- hash = udp_ehashfn(net, daddr, hnum, saddr, sport);
- reuse_sk = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- }
- return reuse_sk;
-}
-
/* called with rcu_read_lock() */
static struct sock *udp4_lib_lookup2(struct net *net,
__be32 saddr, __be16 sport,
@@ -452,42 +436,36 @@ static struct sock *udp4_lib_lookup2(struct net *net,
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
- result = lookup_reuseport(net, sk, skb,
- saddr, sport, daddr, hnum);
+ badness = score;
+
+ if (sk->sk_state == TCP_ESTABLISHED) {
+ result = sk;
+ continue;
+ }
+
+ result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, udp_ehashfn);
+ if (!result) {
+ result = sk;
+ continue;
+ }
+
/* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk))
+ if (!reuseport_has_conns(sk))
return result;
- result = result ? : sk;
- badness = score;
+ /* Reuseport logic returned an error, keep original score. */
+ if (IS_ERR(result))
+ continue;
+
+ badness = compute_score(result, net, saddr, sport,
+ daddr, hnum, dif, sdif);
+
}
}
return result;
}
-static struct sock *udp4_lookup_run_bpf(struct net *net,
- struct udp_table *udptable,
- struct sk_buff *skb,
- __be32 saddr, __be16 sport,
- __be32 daddr, u16 hnum, const int dif)
-{
- struct sock *sk, *reuse_sk;
- bool no_reuseport;
-
- if (udptable != net->ipv4.udp_table)
- return NULL; /* only UDP is supported */
-
- no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
- daddr, hnum, dif, &sk);
- if (no_reuseport || IS_ERR_OR_NULL(sk))
- return sk;
-
- reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
- if (reuse_sk)
- sk = reuse_sk;
- return sk;
-}
-
/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
* harder than this. -DaveM
*/
@@ -512,9 +490,11 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
goto done;
/* Lookup redirect from BPF */
- if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
- sk = udp4_lookup_run_bpf(net, udptable, skb,
- saddr, sport, daddr, hnum, dif);
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+ udptable == net->ipv4.udp_table) {
+ sk = inet_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, dif,
+ udp_ehashfn);
if (sk) {
result = sk;
goto done;
@@ -2412,7 +2392,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
- sk = skb_steal_sock(skb, &refcounted);
+ sk = inet_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+ &refcounted, udp_ehashfn);
+ if (IS_ERR(sk))
+ goto no_sk;
+
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
@@ -2433,7 +2417,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk)
return udp_unicast_rcv_skb(sk, skb, uh);
-
+no_sk:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
nf_reset_ct(skb);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b64b49012655..b0e8d278e8a9 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -39,6 +39,7 @@ u32 inet6_ehashfn(const struct net *net,
return __inet6_ehashfn(lhash, lport, fhash, fport,
inet6_ehash_secret + net_hash_mix(net));
}
+EXPORT_SYMBOL_GPL(inet6_ehashfn);
/*
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
@@ -111,22 +112,40 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
-static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb, int doff,
- const struct in6_addr *saddr,
- __be16 sport,
- const struct in6_addr *daddr,
- unsigned short hnum)
+/**
+ * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ * the selected sock or an error.
+ */
+struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr,
+ __be16 sport,
+ const struct in6_addr *daddr,
+ unsigned short hnum,
+ inet6_ehashfn_t *ehashfn)
{
struct sock *reuse_sk = NULL;
u32 phash;
if (sk->sk_reuseport) {
- phash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+ phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn,
+ net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
}
return reuse_sk;
}
+EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
/* called with rcu_read_lock() */
static struct sock *inet6_lhash2_lookup(struct net *net,
@@ -143,8 +162,8 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
- result = lookup_reuseport(net, sk, skb, doff,
- saddr, sport, daddr, hnum);
+ result = inet6_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum, inet6_ehashfn);
if (result)
return result;
@@ -156,30 +175,30 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
return result;
}
-static inline struct sock *inet6_lookup_run_bpf(struct net *net,
- struct inet_hashinfo *hashinfo,
- struct sk_buff *skb, int doff,
- const struct in6_addr *saddr,
- const __be16 sport,
- const struct in6_addr *daddr,
- const u16 hnum, const int dif)
+struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+ int protocol,
+ struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr,
+ const __be16 sport,
+ const struct in6_addr *daddr,
+ const u16 hnum, const int dif,
+ inet6_ehashfn_t *ehashfn)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
- if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
- return NULL; /* only TCP is supported */
-
- no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport,
+ no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
- reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+ reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum, ehashfn);
if (reuse_sk)
sk = reuse_sk;
return sk;
}
+EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
@@ -193,9 +212,11 @@ struct sock *inet6_lookup_listener(struct net *net,
unsigned int hash2;
/* Lookup redirect from BPF */
- if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
- result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
- saddr, sport, daddr, hnum, dif);
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+ hashinfo == net->ipv4.tcp_death_row.hashinfo) {
+ result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+ saddr, sport, daddr, hnum, dif,
+ inet6_ehashfn);
if (result)
goto done;
}
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index cb4eb1d2c620..d59b296b4f51 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/icmp.h>
+#include <linux/rcupdate.h>
#include <linux/sysctl.h>
#include <net/ipv6_frag.h>
@@ -96,6 +97,12 @@ static void __net_exit defrag6_net_exit(struct net *net)
}
}
+static const struct nf_defrag_hook defrag_hook = {
+ .owner = THIS_MODULE,
+ .enable = nf_defrag_ipv6_enable,
+ .disable = nf_defrag_ipv6_disable,
+};
+
static struct pernet_operations defrag6_net_ops = {
.exit = defrag6_net_exit,
};
@@ -114,6 +121,9 @@ static int __init nf_defrag_init(void)
pr_err("nf_defrag_ipv6: can't register pernet ops\n");
goto cleanup_frag6;
}
+
+ rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook);
+
return ret;
cleanup_frag6:
@@ -124,6 +134,7 @@ cleanup_frag6:
static void __exit nf_defrag_fini(void)
{
+ rcu_assign_pointer(nf_defrag_v6_hook, NULL);
unregister_pernet_subsys(&defrag6_net_ops);
nf_ct_frag6_cleanup();
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 486d893b8e3c..1ea01b0d9be3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -72,11 +72,12 @@ int udpv6_init_sock(struct sock *sk)
return 0;
}
-static u32 udp6_ehashfn(const struct net *net,
- const struct in6_addr *laddr,
- const u16 lport,
- const struct in6_addr *faddr,
- const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp6_ehashfn(const struct net *net,
+ const struct in6_addr *laddr,
+ const u16 lport,
+ const struct in6_addr *faddr,
+ const __be16 fport)
{
static u32 udp6_ehash_secret __read_mostly;
static u32 udp_ipv6_hash_secret __read_mostly;
@@ -161,24 +162,6 @@ static int compute_score(struct sock *sk, struct net *net,
return score;
}
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb,
- const struct in6_addr *saddr,
- __be16 sport,
- const struct in6_addr *daddr,
- unsigned int hnum)
-{
- struct sock *reuse_sk = NULL;
- u32 hash;
-
- if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
- hash = udp6_ehashfn(net, daddr, hnum, saddr, sport);
- reuse_sk = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- }
- return reuse_sk;
-}
-
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -195,44 +178,35 @@ static struct sock *udp6_lib_lookup2(struct net *net,
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
- result = lookup_reuseport(net, sk, skb,
- saddr, sport, daddr, hnum);
+ badness = score;
+
+ if (sk->sk_state == TCP_ESTABLISHED) {
+ result = sk;
+ continue;
+ }
+
+ result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, udp6_ehashfn);
+ if (!result) {
+ result = sk;
+ continue;
+ }
+
/* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk))
+ if (!reuseport_has_conns(sk))
return result;
- result = result ? : sk;
- badness = score;
+ /* Reuseport logic returned an error, keep original score. */
+ if (IS_ERR(result))
+ continue;
+
+ badness = compute_score(sk, net, saddr, sport,
+ daddr, hnum, dif, sdif);
}
}
return result;
}
-static inline struct sock *udp6_lookup_run_bpf(struct net *net,
- struct udp_table *udptable,
- struct sk_buff *skb,
- const struct in6_addr *saddr,
- __be16 sport,
- const struct in6_addr *daddr,
- u16 hnum, const int dif)
-{
- struct sock *sk, *reuse_sk;
- bool no_reuseport;
-
- if (udptable != net->ipv4.udp_table)
- return NULL; /* only UDP is supported */
-
- no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport,
- daddr, hnum, dif, &sk);
- if (no_reuseport || IS_ERR_OR_NULL(sk))
- return sk;
-
- reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
- if (reuse_sk)
- sk = reuse_sk;
- return sk;
-}
-
/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -257,9 +231,11 @@ struct sock *__udp6_lib_lookup(struct net *net,
goto done;
/* Lookup redirect from BPF */
- if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
- sk = udp6_lookup_run_bpf(net, udptable, skb,
- saddr, sport, daddr, hnum, dif);
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+ udptable == net->ipv4.udp_table) {
+ sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, dif,
+ udp6_ehashfn);
if (sk) {
result = sk;
goto done;
@@ -992,7 +968,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
goto csum_error;
/* Check if the socket is already available, e.g. due to early demux */
- sk = skb_steal_sock(skb, &refcounted);
+ sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+ &refcounted, udp6_ehashfn);
+ if (IS_ERR(sk))
+ goto no_sk;
+
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
@@ -1026,7 +1006,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
goto report_csum_error;
return udp6_unicast_rcv_skb(sk, skb, uh);
}
-
+no_sk:
reason = SKB_DROP_REASON_NO_SOCKET;
if (!uh->check)
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 5f76ae86a656..ef4e76e5aef9 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -680,6 +680,12 @@ EXPORT_SYMBOL_GPL(nfnl_ct_hook);
const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_hook);
+const struct nf_defrag_hook __rcu *nf_defrag_v4_hook __read_mostly;
+EXPORT_SYMBOL_GPL(nf_defrag_v4_hook);
+
+const struct nf_defrag_hook __rcu *nf_defrag_v6_hook __read_mostly;
+EXPORT_SYMBOL_GPL(nf_defrag_v6_hook);
+
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
u8 nf_ctnetlink_has_listener;
EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener);
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index c36da56d756f..e502ec00b2fe 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/kmod.h>
+#include <linux/module.h>
#include <linux/netfilter.h>
#include <net/netfilter/nf_bpf_link.h>
@@ -23,8 +25,90 @@ struct bpf_nf_link {
struct nf_hook_ops hook_ops;
struct net *net;
u32 dead;
+ const struct nf_defrag_hook *defrag_hook;
};
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+static const struct nf_defrag_hook *
+get_proto_defrag_hook(struct bpf_nf_link *link,
+ const struct nf_defrag_hook __rcu *global_hook,
+ const char *mod)
+{
+ const struct nf_defrag_hook *hook;
+ int err;
+
+ /* RCU protects us from races against module unloading */
+ rcu_read_lock();
+ hook = rcu_dereference(global_hook);
+ if (!hook) {
+ rcu_read_unlock();
+ err = request_module(mod);
+ if (err)
+ return ERR_PTR(err < 0 ? err : -EINVAL);
+
+ rcu_read_lock();
+ hook = rcu_dereference(global_hook);
+ }
+
+ if (hook && try_module_get(hook->owner)) {
+ /* Once we have a refcnt on the module, we no longer need RCU */
+ hook = rcu_pointer_handoff(hook);
+ } else {
+ WARN_ONCE(!hook, "%s has bad registration", mod);
+ hook = ERR_PTR(-ENOENT);
+ }
+ rcu_read_unlock();
+
+ if (!IS_ERR(hook)) {
+ err = hook->enable(link->net);
+ if (err) {
+ module_put(hook->owner);
+ hook = ERR_PTR(err);
+ }
+ }
+
+ return hook;
+}
+#endif
+
+static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
+{
+ const struct nf_defrag_hook __maybe_unused *hook;
+
+ switch (link->hook_ops.pf) {
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+ case NFPROTO_IPV4:
+ hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4");
+ if (IS_ERR(hook))
+ return PTR_ERR(hook);
+
+ link->defrag_hook = hook;
+ return 0;
+#endif
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+ case NFPROTO_IPV6:
+ hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6");
+ if (IS_ERR(hook))
+ return PTR_ERR(hook);
+
+ link->defrag_hook = hook;
+ return 0;
+#endif
+ default:
+ return -EAFNOSUPPORT;
+ }
+}
+
+static void bpf_nf_disable_defrag(struct bpf_nf_link *link)
+{
+ const struct nf_defrag_hook *hook = link->defrag_hook;
+
+ if (!hook)
+ return;
+ hook->disable(link->net);
+ module_put(hook->owner);
+}
+
static void bpf_nf_link_release(struct bpf_link *link)
{
struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
@@ -32,11 +116,11 @@ static void bpf_nf_link_release(struct bpf_link *link)
if (nf_link->dead)
return;
- /* prevent hook-not-found warning splat from netfilter core when
- * .detach was already called
- */
- if (!cmpxchg(&nf_link->dead, 0, 1))
+ /* do not double release in case .detach was already called */
+ if (!cmpxchg(&nf_link->dead, 0, 1)) {
nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops);
+ bpf_nf_disable_defrag(nf_link);
+ }
}
static void bpf_nf_link_dealloc(struct bpf_link *link)
@@ -92,6 +176,8 @@ static const struct bpf_link_ops bpf_nf_link_lops = {
static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr)
{
+ int prio;
+
switch (attr->link_create.netfilter.pf) {
case NFPROTO_IPV4:
case NFPROTO_IPV6:
@@ -102,19 +188,18 @@ static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr)
return -EAFNOSUPPORT;
}
- if (attr->link_create.netfilter.flags)
+ if (attr->link_create.netfilter.flags & ~BPF_F_NETFILTER_IP_DEFRAG)
return -EOPNOTSUPP;
- /* make sure conntrack confirm is always last.
- *
- * In the future, if userspace can e.g. request defrag, then
- * "defrag_requested && prio before NF_IP_PRI_CONNTRACK_DEFRAG"
- * should fail.
- */
- switch (attr->link_create.netfilter.priority) {
- case NF_IP_PRI_FIRST: return -ERANGE; /* sabotage_in and other warts */
- case NF_IP_PRI_LAST: return -ERANGE; /* e.g. conntrack confirm */
- }
+ /* make sure conntrack confirm is always last */
+ prio = attr->link_create.netfilter.priority;
+ if (prio == NF_IP_PRI_FIRST)
+ return -ERANGE; /* sabotage_in and other warts */
+ else if (prio == NF_IP_PRI_LAST)
+ return -ERANGE; /* e.g. conntrack confirm */
+ else if ((attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) &&
+ prio <= NF_IP_PRI_CONNTRACK_DEFRAG)
+ return -ERANGE; /* cannot use defrag if prog runs before nf_defrag */
return 0;
}
@@ -149,6 +234,7 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
link->net = net;
link->dead = false;
+ link->defrag_hook = NULL;
err = bpf_link_prime(&link->link, &link_primer);
if (err) {
@@ -156,8 +242,17 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
return err;
}
+ if (attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) {
+ err = bpf_nf_enable_defrag(link);
+ if (err) {
+ bpf_link_cleanup(&link_primer);
+ return err;
+ }
+ }
+
err = nf_register_net_hook(net, &link->hook_ops);
if (err) {
+ bpf_nf_disable_defrag(link);
bpf_link_cleanup(&link_primer);
return err;
}
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index 0d36d7285e3f..c7a6114091ae 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/btf_ids.h>
#include <linux/net_namespace.h>
+#include <net/xdp.h>
#include <net/netfilter/nf_conntrack_bpf.h>
#include <net/netfilter/nf_conntrack_core.h>
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index d4ccffcab982..47796a5a79b3 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -25,6 +25,7 @@
#include <linux/vmalloc.h>
#include <net/xdp_sock_drv.h>
#include <net/busy_poll.h>
+#include <net/netdev_rx_queue.h>
#include <net/xdp.h>
#include "xsk_queue.h"
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 739c15906a65..70da85200695 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -19,6 +19,7 @@
/* ld/ldx fields */
#define BPF_DW 0x18 /* double word (64-bit) */
+#define BPF_MEMSX 0x80 /* load with sign extension */
#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */
#define BPF_XADD 0xc0 /* exclusive add - legacy name */
@@ -1187,6 +1188,11 @@ enum bpf_perf_event_type {
*/
#define BPF_F_KPROBE_MULTI_RETURN (1U << 0)
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* the following extensions:
*
@@ -4198,9 +4204,6 @@ union bpf_attr {
* **-EOPNOTSUPP** if the operation is not supported, for example
* a call from outside of TC ingress.
*
- * **-ESOCKTNOSUPPORT** if the socket type is not supported
- * (reuseport).
- *
* long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
* Description
* Helper is overloaded depending on BPF program type. This
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index cf7f02c67968..4be7144e4803 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -293,11 +293,11 @@ help:
@echo ' HINT: use "V=1" to enable verbose build'
@echo ' all - build libraries and pkgconfig'
@echo ' clean - remove all generated files'
- @echo ' check - check abi and version info'
+ @echo ' check - check ABI and version info'
@echo ''
@echo 'libbpf install targets:'
@echo ' HINT: use "prefix"(defaults to "/usr/local") or "DESTDIR" (defaults to "/")'
- @echo ' to adjust target desitantion, e.g. "make prefix=/usr/local install"'
+ @echo ' to adjust target destination, e.g. "make prefix=/usr/local install"'
@echo ' install - build and install all headers, libraries and pkgconfig'
@echo ' install_headers - install only headers to include/bpf'
@echo ''
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 116fecf80ca1..110518ba4804 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -13,6 +13,7 @@ test_dev_cgroup
/test_progs
/test_progs-no_alu32
/test_progs-bpf_gcc
+/test_progs-cpuv4
test_verifier_log
feature
test_sock
@@ -36,6 +37,7 @@ test_cpp
*.lskel.h
/no_alu32
/bpf_gcc
+/cpuv4
/host-tools
/tools
/runqslower
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 882be03b179f..e4e1e6492268 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -33,11 +33,16 @@ CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \
LDFLAGS += $(SAN_LDFLAGS)
LDLIBS += -lelf -lz -lrt -lpthread
-# Silence some warnings when compiled with clang
ifneq ($(LLVM),)
+# Silence some warnings when compiled with clang
CFLAGS += -Wno-unused-command-line-argument
endif
+# Check whether bpf cpu=v4 is supported or not by clang
+ifneq ($(shell $(CLANG) --target=bpf -mcpu=help 2>&1 | grep 'v4'),)
+CLANG_CPUV4 := 1
+endif
+
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_dev_cgroup \
@@ -51,6 +56,10 @@ ifneq ($(BPF_GCC),)
TEST_GEN_PROGS += test_progs-bpf_gcc
endif
+ifneq ($(CLANG_CPUV4),)
+TEST_GEN_PROGS += test_progs-cpuv4
+endif
+
TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
@@ -383,6 +392,11 @@ define CLANG_NOALU32_BPF_BUILD_RULE
$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
endef
+# Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4
+define CLANG_CPUV4_BPF_BUILD_RULE
+ $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+ $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v4 -o $2
+endef
# Build BPF object using GCC
define GCC_BPF_BUILD_RULE
$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
@@ -425,7 +439,7 @@ LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(ske
# $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
# Parameters:
# $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc)
define DEFINE_TEST_RUNNER
TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2
@@ -453,7 +467,7 @@ endef
# Using TRUNNER_XXX variables, provided by callers of DEFINE_TEST_RUNNER and
# set up by DEFINE_TEST_RUNNER itself, create test runner build rules with:
# $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc)
define DEFINE_TEST_RUNNER_RULES
ifeq ($($(TRUNNER_OUTPUT)-dir),)
@@ -565,8 +579,8 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \
network_helpers.c testing_helpers.c \
btf_helpers.c flow_dissector_load.h \
cap_helpers.c test_loader.c xsk.c disasm.c \
- json_writer.c unpriv_helpers.c
-
+ json_writer.c unpriv_helpers.c \
+ ip_check_defrag_frags.h
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \
$(OUTPUT)/liburandom_read.so \
$(OUTPUT)/xdp_synproxy \
@@ -584,6 +598,13 @@ TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE
TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
$(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
+# Define test_progs-cpuv4 test runner.
+ifneq ($(CLANG_CPUV4),)
+TRUNNER_BPF_BUILD_RULE := CLANG_CPUV4_BPF_BUILD_RULE
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
+$(eval $(call DEFINE_TEST_RUNNER,test_progs,cpuv4))
+endif
+
# Define test_progs BPF-GCC-flavored test runner.
ifneq ($(BPF_GCC),)
TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE
@@ -681,7 +702,7 @@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
feature bpftool \
$(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h \
- no_alu32 bpf_gcc bpf_testmod.ko \
+ no_alu32 cpuv4 bpf_gcc bpf_testmod.ko \
liburandom_read.so)
.PHONY: docs docs-clean
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index a6f991b56345..cefc5dd72573 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -98,6 +98,12 @@ bpf_testmod_test_struct_arg_8(u64 a, void *b, short c, int d, void *e,
return bpf_testmod_test_struct_arg_result;
}
+noinline int
+bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) {
+ bpf_testmod_test_struct_arg_result = a->a;
+ return bpf_testmod_test_struct_arg_result;
+}
+
__bpf_kfunc void
bpf_testmod_test_mod_kfunc(int i)
{
@@ -240,7 +246,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
.off = off,
.len = len,
};
- struct bpf_testmod_struct_arg_1 struct_arg1 = {10};
+ struct bpf_testmod_struct_arg_1 struct_arg1 = {10}, struct_arg1_2 = {-1};
struct bpf_testmod_struct_arg_2 struct_arg2 = {2, 3};
struct bpf_testmod_struct_arg_3 *struct_arg3;
struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22};
@@ -259,6 +265,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
(void)bpf_testmod_test_struct_arg_8(16, (void *)17, 18, 19,
(void *)20, struct_arg4, 23);
+ (void)bpf_testmod_test_arg_ptr_to_struct(&struct_arg1_2);
struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) +
sizeof(int)), GFP_KERNEL);
diff --git a/tools/testing/selftests/bpf/generate_udp_fragments.py b/tools/testing/selftests/bpf/generate_udp_fragments.py
new file mode 100755
index 000000000000..2b8a1187991c
--- /dev/null
+++ b/tools/testing/selftests/bpf/generate_udp_fragments.py
@@ -0,0 +1,90 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+This script helps generate fragmented UDP packets.
+
+While it is technically possible to dynamically generate
+fragmented packets in C, it is much harder to read and write
+said code. `scapy` is relatively industry standard and really
+easy to read / write.
+
+So we choose to write this script that generates a valid C
+header. Rerun script and commit generated file after any
+modifications.
+"""
+
+import argparse
+import os
+
+from scapy.all import *
+
+
+# These constants must stay in sync with `ip_check_defrag.c`
+VETH1_ADDR = "172.16.1.200"
+VETH0_ADDR6 = "fc00::100"
+VETH1_ADDR6 = "fc00::200"
+CLIENT_PORT = 48878
+SERVER_PORT = 48879
+MAGIC_MESSAGE = "THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+
+def print_header(f):
+ f.write("// SPDX-License-Identifier: GPL-2.0\n")
+ f.write("/* DO NOT EDIT -- this file is generated */\n")
+ f.write("\n")
+ f.write("#ifndef _IP_CHECK_DEFRAG_FRAGS_H\n")
+ f.write("#define _IP_CHECK_DEFRAG_FRAGS_H\n")
+ f.write("\n")
+ f.write("#include <stdint.h>\n")
+ f.write("\n")
+
+
+def print_frags(f, frags, v6):
+ for idx, frag in enumerate(frags):
+ # 10 bytes per line to keep width in check
+ chunks = [frag[i : i + 10] for i in range(0, len(frag), 10)]
+ chunks_fmted = [", ".join([str(hex(b)) for b in chunk]) for chunk in chunks]
+ suffix = "6" if v6 else ""
+
+ f.write(f"static uint8_t frag{suffix}_{idx}[] = {{\n")
+ for chunk in chunks_fmted:
+ f.write(f"\t{chunk},\n")
+ f.write(f"}};\n")
+
+
+def print_trailer(f):
+ f.write("\n")
+ f.write("#endif /* _IP_CHECK_DEFRAG_FRAGS_H */\n")
+
+
+def main(f):
+ # srcip of 0 is filled in by IP_HDRINCL
+ sip = "0.0.0.0"
+ sip6 = VETH0_ADDR6
+ dip = VETH1_ADDR
+ dip6 = VETH1_ADDR6
+ sport = CLIENT_PORT
+ dport = SERVER_PORT
+ payload = MAGIC_MESSAGE.encode()
+
+ # Disable UDPv4 checksums to keep code simpler
+ pkt = IP(src=sip,dst=dip) / UDP(sport=sport,dport=dport,chksum=0) / Raw(load=payload)
+ # UDPv6 requires a checksum
+ # Also pin the ipv6 fragment header ID, otherwise it's a random value
+ pkt6 = IPv6(src=sip6,dst=dip6) / IPv6ExtHdrFragment(id=0xBEEF) / UDP(sport=sport,dport=dport) / Raw(load=payload)
+
+ frags = [f.build() for f in pkt.fragment(24)]
+ frags6 = [f.build() for f in fragment6(pkt6, 72)]
+
+ print_header(f)
+ print_frags(f, frags, False)
+ print_frags(f, frags6, True)
+ print_trailer(f)
+
+
+if __name__ == "__main__":
+ dir = os.path.dirname(os.path.realpath(__file__))
+ header = f"{dir}/ip_check_defrag_frags.h"
+ with open(header, "w") as f:
+ main(f)
diff --git a/tools/testing/selftests/bpf/ip_check_defrag_frags.h b/tools/testing/selftests/bpf/ip_check_defrag_frags.h
new file mode 100644
index 000000000000..70ab7e9fa22b
--- /dev/null
+++ b/tools/testing/selftests/bpf/ip_check_defrag_frags.h
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* DO NOT EDIT -- this file is generated */
+
+#ifndef _IP_CHECK_DEFRAG_FRAGS_H
+#define _IP_CHECK_DEFRAG_FRAGS_H
+
+#include <stdint.h>
+
+static uint8_t frag_0[] = {
+ 0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x0, 0x40, 0x11,
+ 0xac, 0xe8, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+ 0xbe, 0xee, 0xbe, 0xef, 0x0, 0x3a, 0x0, 0x0, 0x54, 0x48,
+ 0x49, 0x53, 0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20,
+ 0x4f, 0x52, 0x49, 0x47,
+};
+static uint8_t frag_1[] = {
+ 0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x3, 0x40, 0x11,
+ 0xac, 0xe5, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+ 0x49, 0x4e, 0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41,
+ 0x47, 0x45, 0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45,
+ 0x20, 0x52, 0x45, 0x41,
+};
+static uint8_t frag_2[] = {
+ 0x45, 0x0, 0x0, 0x1e, 0x0, 0x1, 0x0, 0x6, 0x40, 0x11,
+ 0xcc, 0xf0, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+ 0x53, 0x53, 0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+static uint8_t frag6_0[] = {
+ 0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+ 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+ 0x11, 0x0, 0x0, 0x1, 0x0, 0x0, 0xbe, 0xef, 0xbe, 0xee,
+ 0xbe, 0xef, 0x0, 0x3a, 0xd0, 0xf8, 0x54, 0x48, 0x49, 0x53,
+ 0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20, 0x4f, 0x52,
+ 0x49, 0x47,
+};
+static uint8_t frag6_1[] = {
+ 0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+ 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+ 0x11, 0x0, 0x0, 0x19, 0x0, 0x0, 0xbe, 0xef, 0x49, 0x4e,
+ 0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41, 0x47, 0x45,
+ 0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45, 0x20, 0x52,
+ 0x45, 0x41,
+};
+static uint8_t frag6_2[] = {
+ 0x60, 0x0, 0x0, 0x0, 0x0, 0x12, 0x2c, 0x40, 0xfc, 0x0,
+ 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+ 0x11, 0x0, 0x0, 0x30, 0x0, 0x0, 0xbe, 0xef, 0x53, 0x53,
+ 0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+
+#endif /* _IP_CHECK_DEFRAG_FRAGS_H */
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index a105c0cd008a..da72a3a66230 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -270,14 +270,23 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
opts = &default_opts;
optlen = sizeof(type);
- if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
- log_err("getsockopt(SOL_TYPE)");
- return -1;
+
+ if (opts->type) {
+ type = opts->type;
+ } else {
+ if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
+ log_err("getsockopt(SOL_TYPE)");
+ return -1;
+ }
}
- if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
- log_err("getsockopt(SOL_PROTOCOL)");
- return -1;
+ if (opts->proto) {
+ protocol = opts->proto;
+ } else {
+ if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
+ log_err("getsockopt(SOL_PROTOCOL)");
+ return -1;
+ }
}
addrlen = sizeof(addr);
@@ -301,8 +310,9 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
strlen(opts->cc) + 1))
goto error_close;
- if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
- goto error_close;
+ if (!opts->noconnect)
+ if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
+ goto error_close;
return fd;
@@ -423,6 +433,9 @@ fail:
void close_netns(struct nstoken *token)
{
+ if (!token)
+ return;
+
ASSERT_OK(setns(token->orig_netns_fd, CLONE_NEWNET), "setns");
close(token->orig_netns_fd);
free(token);
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 694185644da6..5eccc67d1a99 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -21,6 +21,9 @@ struct network_helper_opts {
const char *cc;
int timeout_ms;
bool must_fail;
+ bool noconnect;
+ int type;
+ int proto;
};
/* ipv4 test vector */
diff --git a/tools/testing/selftests/bpf/prog_tests/assign_reuse.c b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c
new file mode 100644
index 000000000000..989ee4d9785b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <test_progs.h>
+
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+
+#include "network_helpers.h"
+#include "test_assign_reuse.skel.h"
+
+#define NS_TEST "assign_reuse"
+#define LOOPBACK 1
+#define PORT 4443
+
+static int attach_reuseport(int sock_fd, int prog_fd)
+{
+ return setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF,
+ &prog_fd, sizeof(prog_fd));
+}
+
+static __u64 cookie(int fd)
+{
+ __u64 cookie = 0;
+ socklen_t cookie_len = sizeof(cookie);
+ int ret;
+
+ ret = getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+ ASSERT_OK(ret, "cookie");
+ ASSERT_GT(cookie, 0, "cookie_invalid");
+
+ return cookie;
+}
+
+static int echo_test_udp(int fd_sv)
+{
+ struct sockaddr_storage addr = {};
+ socklen_t len = sizeof(addr);
+ char buff[1] = {};
+ int fd_cl = -1, ret;
+
+ fd_cl = connect_to_fd(fd_sv, 100);
+ ASSERT_GT(fd_cl, 0, "create_client");
+ ASSERT_EQ(getsockname(fd_cl, (void *)&addr, &len), 0, "getsockname");
+
+ ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client");
+
+ ret = recv(fd_sv, buff, sizeof(buff), 0);
+ if (ret < 0) {
+ close(fd_cl);
+ return errno;
+ }
+
+ ASSERT_EQ(ret, 1, "recv_server");
+ ASSERT_EQ(sendto(fd_sv, buff, sizeof(buff), 0, (void *)&addr, len), 1, "send_server");
+ ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client");
+ close(fd_cl);
+ return 0;
+}
+
+static int echo_test_tcp(int fd_sv)
+{
+ char buff[1] = {};
+ int fd_cl = -1, fd_sv_cl = -1;
+
+ fd_cl = connect_to_fd(fd_sv, 100);
+ if (fd_cl < 0)
+ return errno;
+
+ fd_sv_cl = accept(fd_sv, NULL, NULL);
+ ASSERT_GE(fd_sv_cl, 0, "accept_fd");
+
+ ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client");
+ ASSERT_EQ(recv(fd_sv_cl, buff, sizeof(buff), 0), 1, "recv_server");
+ ASSERT_EQ(send(fd_sv_cl, buff, sizeof(buff), 0), 1, "send_server");
+ ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client");
+ close(fd_sv_cl);
+ close(fd_cl);
+ return 0;
+}
+
+void run_assign_reuse(int family, int sotype, const char *ip, __u16 port)
+{
+ DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+ .ifindex = LOOPBACK,
+ .attach_point = BPF_TC_INGRESS,
+ );
+ DECLARE_LIBBPF_OPTS(bpf_tc_opts, tc_opts,
+ .handle = 1,
+ .priority = 1,
+ );
+ bool hook_created = false, tc_attached = false;
+ int ret, fd_tc, fd_accept, fd_drop, fd_map;
+ int *fd_sv = NULL;
+ __u64 fd_val;
+ struct test_assign_reuse *skel;
+ const int zero = 0;
+
+ skel = test_assign_reuse__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ goto cleanup;
+
+ skel->rodata->dest_port = port;
+
+ ret = test_assign_reuse__load(skel);
+ if (!ASSERT_OK(ret, "skel_load"))
+ goto cleanup;
+
+ ASSERT_EQ(skel->bss->sk_cookie_seen, 0, "cookie_init");
+
+ fd_tc = bpf_program__fd(skel->progs.tc_main);
+ fd_accept = bpf_program__fd(skel->progs.reuse_accept);
+ fd_drop = bpf_program__fd(skel->progs.reuse_drop);
+ fd_map = bpf_map__fd(skel->maps.sk_map);
+
+ fd_sv = start_reuseport_server(family, sotype, ip, port, 100, 1);
+ if (!ASSERT_NEQ(fd_sv, NULL, "start_reuseport_server"))
+ goto cleanup;
+
+ ret = attach_reuseport(*fd_sv, fd_drop);
+ if (!ASSERT_OK(ret, "attach_reuseport"))
+ goto cleanup;
+
+ fd_val = *fd_sv;
+ ret = bpf_map_update_elem(fd_map, &zero, &fd_val, BPF_NOEXIST);
+ if (!ASSERT_OK(ret, "bpf_sk_map"))
+ goto cleanup;
+
+ ret = bpf_tc_hook_create(&tc_hook);
+ if (ret == 0)
+ hook_created = true;
+ ret = ret == -EEXIST ? 0 : ret;
+ if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+ goto cleanup;
+
+ tc_opts.prog_fd = fd_tc;
+ ret = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(ret, "bpf_tc_attach"))
+ goto cleanup;
+ tc_attached = true;
+
+ if (sotype == SOCK_STREAM)
+ ASSERT_EQ(echo_test_tcp(*fd_sv), ECONNREFUSED, "drop_tcp");
+ else
+ ASSERT_EQ(echo_test_udp(*fd_sv), EAGAIN, "drop_udp");
+ ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once");
+
+ skel->bss->sk_cookie_seen = 0;
+ skel->bss->reuseport_executed = 0;
+ ASSERT_OK(attach_reuseport(*fd_sv, fd_accept), "attach_reuseport(accept)");
+
+ if (sotype == SOCK_STREAM)
+ ASSERT_EQ(echo_test_tcp(*fd_sv), 0, "echo_tcp");
+ else
+ ASSERT_EQ(echo_test_udp(*fd_sv), 0, "echo_udp");
+
+ ASSERT_EQ(skel->bss->sk_cookie_seen, cookie(*fd_sv),
+ "cookie_mismatch");
+ ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once");
+cleanup:
+ if (tc_attached) {
+ tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+ ret = bpf_tc_detach(&tc_hook, &tc_opts);
+ ASSERT_OK(ret, "bpf_tc_detach");
+ }
+ if (hook_created) {
+ tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+ bpf_tc_hook_destroy(&tc_hook);
+ }
+ test_assign_reuse__destroy(skel);
+ free_fds(fd_sv, 1);
+}
+
+void test_assign_reuse(void)
+{
+ struct nstoken *tok = NULL;
+
+ SYS(out, "ip netns add %s", NS_TEST);
+ SYS(cleanup, "ip -net %s link set dev lo up", NS_TEST);
+
+ tok = open_netns(NS_TEST);
+ if (!ASSERT_OK_PTR(tok, "netns token"))
+ return;
+
+ if (test__start_subtest("tcpv4"))
+ run_assign_reuse(AF_INET, SOCK_STREAM, "127.0.0.1", PORT);
+ if (test__start_subtest("tcpv6"))
+ run_assign_reuse(AF_INET6, SOCK_STREAM, "::1", PORT);
+ if (test__start_subtest("udpv4"))
+ run_assign_reuse(AF_INET, SOCK_DGRAM, "127.0.0.1", PORT);
+ if (test__start_subtest("udpv6"))
+ run_assign_reuse(AF_INET6, SOCK_DGRAM, "::1", PORT);
+
+cleanup:
+ close_netns(tok);
+ SYS_NOFAIL("ip netns delete %s", NS_TEST);
+out:
+ return;
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
new file mode 100644
index 000000000000..57c814f5f6a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include <linux/netfilter.h>
+#include <network_helpers.h>
+#include "ip_check_defrag.skel.h"
+#include "ip_check_defrag_frags.h"
+
+/*
+ * This selftest spins up a client and an echo server, each in their own
+ * network namespace. The client will send a fragmented message to the server.
+ * The prog attached to the server will shoot down any fragments. Thus, if
+ * the server is able to correctly echo back the message to the client, we will
+ * have verified that netfilter is reassembling packets for us.
+ *
+ * Topology:
+ * =========
+ * NS0 | NS1
+ * |
+ * client | server
+ * ---------- | ----------
+ * | veth0 | --------- | veth1 |
+ * ---------- peer ----------
+ * |
+ * | with bpf
+ */
+
+#define NS0 "defrag_ns0"
+#define NS1 "defrag_ns1"
+#define VETH0 "veth0"
+#define VETH1 "veth1"
+#define VETH0_ADDR "172.16.1.100"
+#define VETH0_ADDR6 "fc00::100"
+/* The following constants must stay in sync with `generate_udp_fragments.py` */
+#define VETH1_ADDR "172.16.1.200"
+#define VETH1_ADDR6 "fc00::200"
+#define CLIENT_PORT 48878
+#define SERVER_PORT 48879
+#define MAGIC_MESSAGE "THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+static int setup_topology(bool ipv6)
+{
+ bool up;
+ int i;
+
+ SYS(fail, "ip netns add " NS0);
+ SYS(fail, "ip netns add " NS1);
+ SYS(fail, "ip link add " VETH0 " netns " NS0 " type veth peer name " VETH1 " netns " NS1);
+ if (ipv6) {
+ SYS(fail, "ip -6 -net " NS0 " addr add " VETH0_ADDR6 "/64 dev " VETH0 " nodad");
+ SYS(fail, "ip -6 -net " NS1 " addr add " VETH1_ADDR6 "/64 dev " VETH1 " nodad");
+ } else {
+ SYS(fail, "ip -net " NS0 " addr add " VETH0_ADDR "/24 dev " VETH0);
+ SYS(fail, "ip -net " NS1 " addr add " VETH1_ADDR "/24 dev " VETH1);
+ }
+ SYS(fail, "ip -net " NS0 " link set dev " VETH0 " up");
+ SYS(fail, "ip -net " NS1 " link set dev " VETH1 " up");
+
+ /* Wait for up to 5s for links to come up */
+ for (i = 0; i < 5; ++i) {
+ if (ipv6)
+ up = !system("ip netns exec " NS0 " ping -6 -c 1 -W 1 " VETH1_ADDR6 " &>/dev/null");
+ else
+ up = !system("ip netns exec " NS0 " ping -c 1 -W 1 " VETH1_ADDR " &>/dev/null");
+
+ if (up)
+ break;
+ }
+
+ return 0;
+fail:
+ return -1;
+}
+
+static void cleanup_topology(void)
+{
+ SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete " NS0);
+ SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete " NS1);
+}
+
+static int attach(struct ip_check_defrag *skel, bool ipv6)
+{
+ LIBBPF_OPTS(bpf_netfilter_opts, opts,
+ .pf = ipv6 ? NFPROTO_IPV6 : NFPROTO_IPV4,
+ .priority = 42,
+ .flags = BPF_F_NETFILTER_IP_DEFRAG);
+ struct nstoken *nstoken;
+ int err = -1;
+
+ nstoken = open_netns(NS1);
+
+ skel->links.defrag = bpf_program__attach_netfilter(skel->progs.defrag, &opts);
+ if (!ASSERT_OK_PTR(skel->links.defrag, "program attach"))
+ goto out;
+
+ err = 0;
+out:
+ close_netns(nstoken);
+ return err;
+}
+
+static int send_frags(int client)
+{
+ struct sockaddr_storage saddr;
+ struct sockaddr *saddr_p;
+ socklen_t saddr_len;
+ int err;
+
+ saddr_p = (struct sockaddr *)&saddr;
+ err = make_sockaddr(AF_INET, VETH1_ADDR, SERVER_PORT, &saddr, &saddr_len);
+ if (!ASSERT_OK(err, "make_sockaddr"))
+ return -1;
+
+ err = sendto(client, frag_0, sizeof(frag_0), 0, saddr_p, saddr_len);
+ if (!ASSERT_GE(err, 0, "sendto frag_0"))
+ return -1;
+
+ err = sendto(client, frag_1, sizeof(frag_1), 0, saddr_p, saddr_len);
+ if (!ASSERT_GE(err, 0, "sendto frag_1"))
+ return -1;
+
+ err = sendto(client, frag_2, sizeof(frag_2), 0, saddr_p, saddr_len);
+ if (!ASSERT_GE(err, 0, "sendto frag_2"))
+ return -1;
+
+ return 0;
+}
+
+static int send_frags6(int client)
+{
+ struct sockaddr_storage saddr;
+ struct sockaddr *saddr_p;
+ socklen_t saddr_len;
+ int err;
+
+ saddr_p = (struct sockaddr *)&saddr;
+ /* Port needs to be set to 0 for raw ipv6 socket for some reason */
+ err = make_sockaddr(AF_INET6, VETH1_ADDR6, 0, &saddr, &saddr_len);
+ if (!ASSERT_OK(err, "make_sockaddr"))
+ return -1;
+
+ err = sendto(client, frag6_0, sizeof(frag6_0), 0, saddr_p, saddr_len);
+ if (!ASSERT_GE(err, 0, "sendto frag6_0"))
+ return -1;
+
+ err = sendto(client, frag6_1, sizeof(frag6_1), 0, saddr_p, saddr_len);
+ if (!ASSERT_GE(err, 0, "sendto frag6_1"))
+ return -1;
+
+ err = sendto(client, frag6_2, sizeof(frag6_2), 0, saddr_p, saddr_len);
+ if (!ASSERT_GE(err, 0, "sendto frag6_2"))
+ return -1;
+
+ return 0;
+}
+
+void test_bpf_ip_check_defrag_ok(bool ipv6)
+{
+ struct network_helper_opts rx_opts = {
+ .timeout_ms = 1000,
+ .noconnect = true,
+ };
+ struct network_helper_opts tx_ops = {
+ .timeout_ms = 1000,
+ .type = SOCK_RAW,
+ .proto = IPPROTO_RAW,
+ .noconnect = true,
+ };
+ struct sockaddr_storage caddr;
+ struct ip_check_defrag *skel;
+ struct nstoken *nstoken;
+ int client_tx_fd = -1;
+ int client_rx_fd = -1;
+ socklen_t caddr_len;
+ int srv_fd = -1;
+ char buf[1024];
+ int len, err;
+
+ skel = ip_check_defrag__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ if (!ASSERT_OK(setup_topology(ipv6), "setup_topology"))
+ goto out;
+
+ if (!ASSERT_OK(attach(skel, ipv6), "attach"))
+ goto out;
+
+ /* Start server in ns1 */
+ nstoken = open_netns(NS1);
+ if (!ASSERT_OK_PTR(nstoken, "setns ns1"))
+ goto out;
+ srv_fd = start_server(ipv6 ? AF_INET6 : AF_INET, SOCK_DGRAM, NULL, SERVER_PORT, 0);
+ close_netns(nstoken);
+ if (!ASSERT_GE(srv_fd, 0, "start_server"))
+ goto out;
+
+ /* Open tx raw socket in ns0 */
+ nstoken = open_netns(NS0);
+ if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+ goto out;
+ client_tx_fd = connect_to_fd_opts(srv_fd, &tx_ops);
+ close_netns(nstoken);
+ if (!ASSERT_GE(client_tx_fd, 0, "connect_to_fd_opts"))
+ goto out;
+
+ /* Open rx socket in ns0 */
+ nstoken = open_netns(NS0);
+ if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+ goto out;
+ client_rx_fd = connect_to_fd_opts(srv_fd, &rx_opts);
+ close_netns(nstoken);
+ if (!ASSERT_GE(client_rx_fd, 0, "connect_to_fd_opts"))
+ goto out;
+
+ /* Bind rx socket to a premeditated port */
+ memset(&caddr, 0, sizeof(caddr));
+ nstoken = open_netns(NS0);
+ if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+ goto out;
+ if (ipv6) {
+ struct sockaddr_in6 *c = (struct sockaddr_in6 *)&caddr;
+
+ c->sin6_family = AF_INET6;
+ inet_pton(AF_INET6, VETH0_ADDR6, &c->sin6_addr);
+ c->sin6_port = htons(CLIENT_PORT);
+ err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+ } else {
+ struct sockaddr_in *c = (struct sockaddr_in *)&caddr;
+
+ c->sin_family = AF_INET;
+ inet_pton(AF_INET, VETH0_ADDR, &c->sin_addr);
+ c->sin_port = htons(CLIENT_PORT);
+ err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+ }
+ close_netns(nstoken);
+ if (!ASSERT_OK(err, "bind"))
+ goto out;
+
+ /* Send message in fragments */
+ if (ipv6) {
+ if (!ASSERT_OK(send_frags6(client_tx_fd), "send_frags6"))
+ goto out;
+ } else {
+ if (!ASSERT_OK(send_frags(client_tx_fd), "send_frags"))
+ goto out;
+ }
+
+ if (!ASSERT_EQ(skel->bss->shootdowns, 0, "shootdowns"))
+ goto out;
+
+ /* Receive reassembled msg on server and echo back to client */
+ caddr_len = sizeof(caddr);
+ len = recvfrom(srv_fd, buf, sizeof(buf), 0, (struct sockaddr *)&caddr, &caddr_len);
+ if (!ASSERT_GE(len, 0, "server recvfrom"))
+ goto out;
+ len = sendto(srv_fd, buf, len, 0, (struct sockaddr *)&caddr, caddr_len);
+ if (!ASSERT_GE(len, 0, "server sendto"))
+ goto out;
+
+ /* Expect reassembed message to be echoed back */
+ len = recvfrom(client_rx_fd, buf, sizeof(buf), 0, NULL, NULL);
+ if (!ASSERT_EQ(len, sizeof(MAGIC_MESSAGE) - 1, "client short read"))
+ goto out;
+
+out:
+ if (client_rx_fd != -1)
+ close(client_rx_fd);
+ if (client_tx_fd != -1)
+ close(client_tx_fd);
+ if (srv_fd != -1)
+ close(srv_fd);
+ cleanup_topology();
+ ip_check_defrag__destroy(skel);
+}
+
+void test_bpf_ip_check_defrag(void)
+{
+ if (test__start_subtest("v4"))
+ test_bpf_ip_check_defrag_ok(false);
+ if (test__start_subtest("v6"))
+ test_bpf_ip_check_defrag_ok(true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c
new file mode 100644
index 000000000000..375677c19146
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates.*/
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_ldsx_insn.skel.h"
+
+static void test_map_val_and_probed_memory(void)
+{
+ struct test_ldsx_insn *skel;
+ int err;
+
+ skel = test_ldsx_insn__open();
+ if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+ return;
+
+ if (skel->rodata->skip) {
+ test__skip();
+ goto out;
+ }
+
+ bpf_program__set_autoload(skel->progs.rdonly_map_prog, true);
+ bpf_program__set_autoload(skel->progs.map_val_prog, true);
+ bpf_program__set_autoload(skel->progs.test_ptr_struct_arg, true);
+
+ err = test_ldsx_insn__load(skel);
+ if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+ goto out;
+
+ err = test_ldsx_insn__attach(skel);
+ if (!ASSERT_OK(err, "test_ldsx_insn__attach"))
+ goto out;
+
+ ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+ ASSERT_EQ(skel->bss->done1, 1, "done1");
+ ASSERT_EQ(skel->bss->ret1, 1, "ret1");
+ ASSERT_EQ(skel->bss->done2, 1, "done2");
+ ASSERT_EQ(skel->bss->ret2, 1, "ret2");
+ ASSERT_EQ(skel->bss->int_member, -1, "int_member");
+
+out:
+ test_ldsx_insn__destroy(skel);
+}
+
+static void test_ctx_member_sign_ext(void)
+{
+ struct test_ldsx_insn *skel;
+ int err, fd, cgroup_fd;
+ char buf[16] = {0};
+ socklen_t optlen;
+
+ cgroup_fd = test__join_cgroup("/ldsx_test");
+ if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /ldsx_test"))
+ return;
+
+ skel = test_ldsx_insn__open();
+ if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+ goto close_cgroup_fd;
+
+ if (skel->rodata->skip) {
+ test__skip();
+ goto destroy_skel;
+ }
+
+ bpf_program__set_autoload(skel->progs._getsockopt, true);
+
+ err = test_ldsx_insn__load(skel);
+ if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+ goto destroy_skel;
+
+ skel->links._getsockopt =
+ bpf_program__attach_cgroup(skel->progs._getsockopt, cgroup_fd);
+ if (!ASSERT_OK_PTR(skel->links._getsockopt, "getsockopt_link"))
+ goto destroy_skel;
+
+ fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (!ASSERT_GE(fd, 0, "socket"))
+ goto destroy_skel;
+
+ optlen = sizeof(buf);
+ (void)getsockopt(fd, SOL_IP, IP_TTL, buf, &optlen);
+
+ ASSERT_EQ(skel->bss->set_optlen, -1, "optlen");
+ ASSERT_EQ(skel->bss->set_retval, -1, "retval");
+
+ close(fd);
+destroy_skel:
+ test_ldsx_insn__destroy(skel);
+close_cgroup_fd:
+ close(cgroup_fd);
+}
+
+static void test_ctx_member_narrow_sign_ext(void)
+{
+ struct test_ldsx_insn *skel;
+ struct __sk_buff skb = {};
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .ctx_in = &skb,
+ .ctx_size_in = sizeof(skb),
+ );
+ int err, prog_fd;
+
+ skel = test_ldsx_insn__open();
+ if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+ return;
+
+ if (skel->rodata->skip) {
+ test__skip();
+ goto out;
+ }
+
+ bpf_program__set_autoload(skel->progs._tc, true);
+
+ err = test_ldsx_insn__load(skel);
+ if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+ goto out;
+
+ prog_fd = bpf_program__fd(skel->progs._tc);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "test_run");
+
+ ASSERT_EQ(skel->bss->set_mark, -2, "set_mark");
+
+out:
+ test_ldsx_insn__destroy(skel);
+}
+
+void test_ldsx_insn(void)
+{
+ if (test__start_subtest("map_val and probed_memory"))
+ test_map_val_and_probed_memory();
+ if (test__start_subtest("ctx_member_sign_ext"))
+ test_ctx_member_sign_ext();
+ if (test__start_subtest("ctx_member_narrow_sign_ext"))
+ test_ctx_member_narrow_sign_ext();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index c375e59ff28d..e3e68c97b40c 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -11,6 +11,7 @@
#include "verifier_bounds_deduction_non_const.skel.h"
#include "verifier_bounds_mix_sign_unsign.skel.h"
#include "verifier_bpf_get_stack.skel.h"
+#include "verifier_bswap.skel.h"
#include "verifier_btf_ctx_access.skel.h"
#include "verifier_cfg.skel.h"
#include "verifier_cgroup_inv_retcode.skel.h"
@@ -24,6 +25,7 @@
#include "verifier_direct_stack_access_wraparound.skel.h"
#include "verifier_div0.skel.h"
#include "verifier_div_overflow.skel.h"
+#include "verifier_gotol.skel.h"
#include "verifier_helper_access_var_len.skel.h"
#include "verifier_helper_packet_access.skel.h"
#include "verifier_helper_restricted.skel.h"
@@ -31,6 +33,7 @@
#include "verifier_int_ptr.skel.h"
#include "verifier_jeq_infer_not_null.skel.h"
#include "verifier_ld_ind.skel.h"
+#include "verifier_ldsx.skel.h"
#include "verifier_leak_ptr.skel.h"
#include "verifier_loops1.skel.h"
#include "verifier_lwt.skel.h"
@@ -40,6 +43,7 @@
#include "verifier_map_ret_val.skel.h"
#include "verifier_masking.skel.h"
#include "verifier_meta_access.skel.h"
+#include "verifier_movsx.skel.h"
#include "verifier_netfilter_ctx.skel.h"
#include "verifier_netfilter_retcode.skel.h"
#include "verifier_prevent_map_lookup.skel.h"
@@ -51,6 +55,7 @@
#include "verifier_ringbuf.skel.h"
#include "verifier_runtime_jit.skel.h"
#include "verifier_scalar_ids.skel.h"
+#include "verifier_sdiv.skel.h"
#include "verifier_search_pruning.skel.h"
#include "verifier_sock.skel.h"
#include "verifier_spill_fill.skel.h"
@@ -113,6 +118,7 @@ void test_verifier_bounds_deduction(void) { RUN(verifier_bounds_deduction);
void test_verifier_bounds_deduction_non_const(void) { RUN(verifier_bounds_deduction_non_const); }
void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_unsign); }
void test_verifier_bpf_get_stack(void) { RUN(verifier_bpf_get_stack); }
+void test_verifier_bswap(void) { RUN(verifier_bswap); }
void test_verifier_btf_ctx_access(void) { RUN(verifier_btf_ctx_access); }
void test_verifier_cfg(void) { RUN(verifier_cfg); }
void test_verifier_cgroup_inv_retcode(void) { RUN(verifier_cgroup_inv_retcode); }
@@ -126,6 +132,7 @@ void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_acces
void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); }
void test_verifier_div0(void) { RUN(verifier_div0); }
void test_verifier_div_overflow(void) { RUN(verifier_div_overflow); }
+void test_verifier_gotol(void) { RUN(verifier_gotol); }
void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); }
void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); }
void test_verifier_helper_restricted(void) { RUN(verifier_helper_restricted); }
@@ -133,6 +140,7 @@ void test_verifier_helper_value_access(void) { RUN(verifier_helper_value_access
void test_verifier_int_ptr(void) { RUN(verifier_int_ptr); }
void test_verifier_jeq_infer_not_null(void) { RUN(verifier_jeq_infer_not_null); }
void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); }
+void test_verifier_ldsx(void) { RUN(verifier_ldsx); }
void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); }
void test_verifier_loops1(void) { RUN(verifier_loops1); }
void test_verifier_lwt(void) { RUN(verifier_lwt); }
@@ -142,6 +150,7 @@ void test_verifier_map_ptr_mixing(void) { RUN(verifier_map_ptr_mixing); }
void test_verifier_map_ret_val(void) { RUN(verifier_map_ret_val); }
void test_verifier_masking(void) { RUN(verifier_masking); }
void test_verifier_meta_access(void) { RUN(verifier_meta_access); }
+void test_verifier_movsx(void) { RUN(verifier_movsx); }
void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); }
void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); }
void test_verifier_prevent_map_lookup(void) { RUN(verifier_prevent_map_lookup); }
@@ -153,6 +162,7 @@ void test_verifier_regalloc(void) { RUN(verifier_regalloc); }
void test_verifier_ringbuf(void) { RUN(verifier_ringbuf); }
void test_verifier_runtime_jit(void) { RUN(verifier_runtime_jit); }
void test_verifier_scalar_ids(void) { RUN(verifier_scalar_ids); }
+void test_verifier_sdiv(void) { RUN(verifier_sdiv); }
void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); }
void test_verifier_sock(void) { RUN(verifier_sock); }
void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
index fa3cac5488f5..e6bcb6051402 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include "test_xdp_attach_fail.skel.h"
#define IFINDEX_LO 1
#define XDP_FLAGS_REPLACE (1U << 4)
@@ -85,10 +86,74 @@ out_1:
bpf_object__close(obj1);
}
+#define ERRMSG_LEN 64
+
+struct xdp_errmsg {
+ char msg[ERRMSG_LEN];
+};
+
+static void on_xdp_errmsg(void *ctx, int cpu, void *data, __u32 size)
+{
+ struct xdp_errmsg *ctx_errmg = ctx, *tp_errmsg = data;
+
+ memcpy(&ctx_errmg->msg, &tp_errmsg->msg, ERRMSG_LEN);
+}
+
+static const char tgt_errmsg[] = "Invalid XDP flags for BPF link attachment";
+
+static void test_xdp_attach_fail(const char *file)
+{
+ struct test_xdp_attach_fail *skel = NULL;
+ struct xdp_errmsg errmsg = {};
+ struct perf_buffer *pb = NULL;
+ struct bpf_object *obj = NULL;
+ int err, fd_xdp;
+
+ LIBBPF_OPTS(bpf_link_create_opts, opts);
+
+ skel = test_xdp_attach_fail__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_xdp_attach_fail__open_and_load"))
+ goto out_close;
+
+ err = test_xdp_attach_fail__attach(skel);
+ if (!ASSERT_EQ(err, 0, "test_xdp_attach_fail__attach"))
+ goto out_close;
+
+ /* set up perf buffer */
+ pb = perf_buffer__new(bpf_map__fd(skel->maps.xdp_errmsg_pb), 1,
+ on_xdp_errmsg, NULL, &errmsg, NULL);
+ if (!ASSERT_OK_PTR(pb, "perf_buffer__new"))
+ goto out_close;
+
+ err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &fd_xdp);
+ if (!ASSERT_EQ(err, 0, "bpf_prog_test_load"))
+ goto out_close;
+
+ opts.flags = 0xFF; // invalid flags to fail to attach XDP prog
+ err = bpf_link_create(fd_xdp, IFINDEX_LO, BPF_XDP, &opts);
+ if (!ASSERT_EQ(err, -EINVAL, "bpf_link_create"))
+ goto out_close;
+
+ /* read perf buffer */
+ err = perf_buffer__poll(pb, 100);
+ if (!ASSERT_GT(err, -1, "perf_buffer__poll"))
+ goto out_close;
+
+ ASSERT_STRNEQ((const char *) errmsg.msg, tgt_errmsg,
+ 42 /* strlen(tgt_errmsg) */, "check error message");
+
+out_close:
+ perf_buffer__free(pb);
+ bpf_object__close(obj);
+ test_xdp_attach_fail__destroy(skel);
+}
+
void serial_test_xdp_attach(void)
{
if (test__start_subtest("xdp_attach"))
test_xdp_attach("./test_xdp.bpf.o");
if (test__start_subtest("xdp_attach_dynptr"))
test_xdp_attach("./test_xdp_dynptr.bpf.o");
+ if (test__start_subtest("xdp_attach_failed"))
+ test_xdp_attach_fail("./xdp_dummy.bpf.o");
}
diff --git a/tools/testing/selftests/bpf/progs/ip_check_defrag.c b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
new file mode 100644
index 000000000000..1c2b6c1616b0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+
+#define NF_DROP 0
+#define NF_ACCEPT 1
+#define ETH_P_IP 0x0800
+#define ETH_P_IPV6 0x86DD
+#define IP_MF 0x2000
+#define IP_OFFSET 0x1FFF
+#define NEXTHDR_FRAGMENT 44
+
+extern int bpf_dynptr_from_skb(struct sk_buff *skb, __u64 flags,
+ struct bpf_dynptr *ptr__uninit) __ksym;
+extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset,
+ void *buffer, uint32_t buffer__sz) __ksym;
+
+volatile int shootdowns = 0;
+
+static bool is_frag_v4(struct iphdr *iph)
+{
+ int offset;
+ int flags;
+
+ offset = bpf_ntohs(iph->frag_off);
+ flags = offset & ~IP_OFFSET;
+ offset &= IP_OFFSET;
+ offset <<= 3;
+
+ return (flags & IP_MF) || offset;
+}
+
+static bool is_frag_v6(struct ipv6hdr *ip6h)
+{
+ /* Simplifying assumption that there are no extension headers
+ * between fixed header and fragmentation header. This assumption
+ * is only valid in this test case. It saves us the hassle of
+ * searching all potential extension headers.
+ */
+ return ip6h->nexthdr == NEXTHDR_FRAGMENT;
+}
+
+static int handle_v4(struct sk_buff *skb)
+{
+ struct bpf_dynptr ptr;
+ u8 iph_buf[20] = {};
+ struct iphdr *iph;
+
+ if (bpf_dynptr_from_skb(skb, 0, &ptr))
+ return NF_DROP;
+
+ iph = bpf_dynptr_slice(&ptr, 0, iph_buf, sizeof(iph_buf));
+ if (!iph)
+ return NF_DROP;
+
+ /* Shootdown any frags */
+ if (is_frag_v4(iph)) {
+ shootdowns++;
+ return NF_DROP;
+ }
+
+ return NF_ACCEPT;
+}
+
+static int handle_v6(struct sk_buff *skb)
+{
+ struct bpf_dynptr ptr;
+ struct ipv6hdr *ip6h;
+ u8 ip6h_buf[40] = {};
+
+ if (bpf_dynptr_from_skb(skb, 0, &ptr))
+ return NF_DROP;
+
+ ip6h = bpf_dynptr_slice(&ptr, 0, ip6h_buf, sizeof(ip6h_buf));
+ if (!ip6h)
+ return NF_DROP;
+
+ /* Shootdown any frags */
+ if (is_frag_v6(ip6h)) {
+ shootdowns++;
+ return NF_DROP;
+ }
+
+ return NF_ACCEPT;
+}
+
+SEC("netfilter")
+int defrag(struct bpf_nf_ctx *ctx)
+{
+ struct sk_buff *skb = ctx->skb;
+
+ switch (bpf_ntohs(skb->protocol)) {
+ case ETH_P_IP:
+ return handle_v4(skb);
+ case ETH_P_IPV6:
+ return handle_v6(skb);
+ default:
+ return NF_ACCEPT;
+ }
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_assign_reuse.c b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
new file mode 100644
index 000000000000..4f2e2321ea06
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/pkt_cls.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+__u64 sk_cookie_seen;
+__u64 reuseport_executed;
+union {
+ struct tcphdr tcp;
+ struct udphdr udp;
+} headers;
+
+const volatile __u16 dest_port;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} sk_map SEC(".maps");
+
+SEC("sk_reuseport")
+int reuse_accept(struct sk_reuseport_md *ctx)
+{
+ reuseport_executed++;
+
+ if (ctx->ip_protocol == IPPROTO_TCP) {
+ if (ctx->data + sizeof(headers.tcp) > ctx->data_end)
+ return SK_DROP;
+
+ if (__builtin_memcmp(&headers.tcp, ctx->data, sizeof(headers.tcp)) != 0)
+ return SK_DROP;
+ } else if (ctx->ip_protocol == IPPROTO_UDP) {
+ if (ctx->data + sizeof(headers.udp) > ctx->data_end)
+ return SK_DROP;
+
+ if (__builtin_memcmp(&headers.udp, ctx->data, sizeof(headers.udp)) != 0)
+ return SK_DROP;
+ } else {
+ return SK_DROP;
+ }
+
+ sk_cookie_seen = bpf_get_socket_cookie(ctx->sk);
+ return SK_PASS;
+}
+
+SEC("sk_reuseport")
+int reuse_drop(struct sk_reuseport_md *ctx)
+{
+ reuseport_executed++;
+ sk_cookie_seen = 0;
+ return SK_DROP;
+}
+
+static int
+assign_sk(struct __sk_buff *skb)
+{
+ int zero = 0, ret = 0;
+ struct bpf_sock *sk;
+
+ sk = bpf_map_lookup_elem(&sk_map, &zero);
+ if (!sk)
+ return TC_ACT_SHOT;
+ ret = bpf_sk_assign(skb, sk, 0);
+ bpf_sk_release(sk);
+ return ret ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+static bool
+maybe_assign_tcp(struct __sk_buff *skb, struct tcphdr *th)
+{
+ if (th + 1 > (void *)(long)(skb->data_end))
+ return TC_ACT_SHOT;
+
+ if (!th->syn || th->ack || th->dest != bpf_htons(dest_port))
+ return TC_ACT_OK;
+
+ __builtin_memcpy(&headers.tcp, th, sizeof(headers.tcp));
+ return assign_sk(skb);
+}
+
+static bool
+maybe_assign_udp(struct __sk_buff *skb, struct udphdr *uh)
+{
+ if (uh + 1 > (void *)(long)(skb->data_end))
+ return TC_ACT_SHOT;
+
+ if (uh->dest != bpf_htons(dest_port))
+ return TC_ACT_OK;
+
+ __builtin_memcpy(&headers.udp, uh, sizeof(headers.udp));
+ return assign_sk(skb);
+}
+
+SEC("tc")
+int tc_main(struct __sk_buff *skb)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct ethhdr *eth;
+
+ eth = (struct ethhdr *)(data);
+ if (eth + 1 > data_end)
+ return TC_ACT_SHOT;
+
+ if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+ struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth));
+
+ if (iph + 1 > data_end)
+ return TC_ACT_SHOT;
+
+ if (iph->protocol == IPPROTO_TCP)
+ return maybe_assign_tcp(skb, (struct tcphdr *)(iph + 1));
+ else if (iph->protocol == IPPROTO_UDP)
+ return maybe_assign_udp(skb, (struct udphdr *)(iph + 1));
+ else
+ return TC_ACT_SHOT;
+ } else {
+ struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth));
+
+ if (ip6h + 1 > data_end)
+ return TC_ACT_SHOT;
+
+ if (ip6h->nexthdr == IPPROTO_TCP)
+ return maybe_assign_tcp(skb, (struct tcphdr *)(ip6h + 1));
+ else if (ip6h->nexthdr == IPPROTO_UDP)
+ return maybe_assign_udp(skb, (struct udphdr *)(ip6h + 1));
+ else
+ return TC_ACT_SHOT;
+ }
+}
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
index 76eab0aacba0..233b089d1fba 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.h
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
@@ -12,6 +12,15 @@
#include <linux/ipv6.h>
#include <linux/udp.h>
+/* offsetof() is used in static asserts, and the libbpf-redefined CO-RE
+ * friendly version breaks compilation for older clang versions <= 15
+ * when invoked in a static assert. Restore original here.
+ */
+#ifdef offsetof
+#undef offsetof
+#define offsetof(type, member) __builtin_offsetof(type, member)
+#endif
+
struct gre_base_hdr {
uint16_t flags;
uint16_t protocol;
diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
new file mode 100644
index 000000000000..321abf862801
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+const volatile int skip = 0;
+#else
+const volatile int skip = 1;
+#endif
+
+volatile const short val1 = -1;
+volatile const int val2 = -1;
+short val3 = -1;
+int val4 = -1;
+int done1, done2, ret1, ret2;
+
+SEC("?raw_tp/sys_enter")
+int rdonly_map_prog(const void *ctx)
+{
+ if (done1)
+ return 0;
+
+ done1 = 1;
+ /* val1/val2 readonly map */
+ if (val1 == val2)
+ ret1 = 1;
+ return 0;
+
+}
+
+SEC("?raw_tp/sys_enter")
+int map_val_prog(const void *ctx)
+{
+ if (done2)
+ return 0;
+
+ done2 = 1;
+ /* val1/val2 regular read/write map */
+ if (val3 == val4)
+ ret2 = 1;
+ return 0;
+
+}
+
+struct bpf_testmod_struct_arg_1 {
+ int a;
+};
+
+long long int_member;
+
+SEC("?fentry/bpf_testmod_test_arg_ptr_to_struct")
+int BPF_PROG2(test_ptr_struct_arg, struct bpf_testmod_struct_arg_1 *, p)
+{
+ /* probed memory access */
+ int_member = p->a;
+ return 0;
+}
+
+long long set_optlen, set_retval;
+
+SEC("?cgroup/getsockopt")
+int _getsockopt(volatile struct bpf_sockopt *ctx)
+{
+ int old_optlen, old_retval;
+
+ old_optlen = ctx->optlen;
+ old_retval = ctx->retval;
+
+ ctx->optlen = -1;
+ ctx->retval = -1;
+
+ /* sign extension for ctx member */
+ set_optlen = ctx->optlen;
+ set_retval = ctx->retval;
+
+ ctx->optlen = old_optlen;
+ ctx->retval = old_retval;
+
+ return 0;
+}
+
+long long set_mark;
+
+SEC("?tc")
+int _tc(volatile struct __sk_buff *skb)
+{
+ long long tmp_mark;
+ int old_mark;
+
+ old_mark = skb->mark;
+
+ skb->mark = 0xf6fe;
+
+ /* narrowed sign extension for ctx member */
+#if __clang_major__ >= 18
+ /* force narrow one-byte signed load. Otherwise, compiler may
+ * generate a 32-bit unsigned load followed by an s8 movsx.
+ */
+ asm volatile ("r1 = *(s8 *)(%[ctx] + %[off_mark])\n\t"
+ "%[tmp_mark] = r1"
+ : [tmp_mark]"=r"(tmp_mark)
+ : [ctx]"r"(skb),
+ [off_mark]"i"(offsetof(struct __sk_buff, mark))
+ : "r1");
+#else
+ tmp_mark = (char)skb->mark;
+#endif
+ set_mark = tmp_mark;
+
+ skb->mark = old_mark;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c
new file mode 100644
index 000000000000..2ff1b596e87e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define ERRMSG_LEN 64
+
+struct xdp_errmsg {
+ char msg[ERRMSG_LEN];
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __type(key, int);
+ __type(value, int);
+} xdp_errmsg_pb SEC(".maps");
+
+struct xdp_attach_error_ctx {
+ unsigned long unused;
+
+ /*
+ * bpf does not support tracepoint __data_loc directly.
+ *
+ * Actually, this field is a 32 bit integer whose value encodes
+ * information on where to find the actual data. The first 2 bytes is
+ * the size of the data. The last 2 bytes is the offset from the start
+ * of the tracepoint struct where the data begins.
+ * -- https://github.com/iovisor/bpftrace/pull/1542
+ */
+ __u32 msg; // __data_loc char[] msg;
+};
+
+/*
+ * Catch the error message at the tracepoint.
+ */
+
+SEC("tp/xdp/bpf_xdp_link_attach_failed")
+int tp__xdp__bpf_xdp_link_attach_failed(struct xdp_attach_error_ctx *ctx)
+{
+ char *msg = (void *)(__u64) ((void *) ctx + (__u16) ctx->msg);
+ struct xdp_errmsg errmsg = {};
+
+ bpf_probe_read_kernel_str(&errmsg.msg, ERRMSG_LEN, msg);
+ bpf_perf_event_output(ctx, &xdp_errmsg_pb, BPF_F_CURRENT_CPU, &errmsg,
+ ERRMSG_LEN);
+ return 0;
+}
+
+/*
+ * Reuse the XDP program in xdp_dummy.c.
+ */
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
new file mode 100644
index 000000000000..724bb38988b5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("BSWAP, 16")
+__success __success_unpriv __retval(0x23ff)
+__naked void bswap_16(void)
+{
+ asm volatile (" \
+ r0 = 0xff23; \
+ r0 = bswap16 r0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("BSWAP, 32")
+__success __success_unpriv __retval(0x23ff0000)
+__naked void bswap_32(void)
+{
+ asm volatile (" \
+ r0 = 0xff23; \
+ r0 = bswap32 r0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("BSWAP, 64")
+__success __success_unpriv __retval(0x34ff12ff)
+__naked void bswap_64(void)
+{
+ asm volatile (" \
+ r0 = %[u64_val] ll; \
+ r0 = bswap64 r0; \
+ exit; \
+" :
+ : [u64_val]"i"(0xff12ff34ff56ff78ull)
+ : __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+ return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
new file mode 100644
index 000000000000..ce48f7757db2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("gotol, small_imm")
+__success __success_unpriv __retval(1)
+__naked void gotol_small_imm(void)
+{
+ asm volatile (" \
+ call %[bpf_ktime_get_ns]; \
+ if r0 == 0 goto l0_%=; \
+ gotol l1_%=; \
+l2_%=: \
+ gotol l3_%=; \
+l1_%=: \
+ r0 = 1; \
+ gotol l2_%=; \
+l0_%=: \
+ r0 = 2; \
+l3_%=: \
+ exit; \
+" :
+ : __imm(bpf_ktime_get_ns)
+ : __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+ return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
new file mode 100644
index 000000000000..3c3d1bddd67f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("LDSX, S8")
+__success __success_unpriv __retval(-2)
+__naked void ldsx_s8(void)
+{
+ asm volatile (" \
+ r1 = 0x3fe; \
+ *(u64 *)(r10 - 8) = r1; \
+ r0 = *(s8 *)(r10 - 8); \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S16")
+__success __success_unpriv __retval(-2)
+__naked void ldsx_s16(void)
+{
+ asm volatile (" \
+ r1 = 0x3fffe; \
+ *(u64 *)(r10 - 8) = r1; \
+ r0 = *(s16 *)(r10 - 8); \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S32")
+__success __success_unpriv __retval(-1)
+__naked void ldsx_s32(void)
+{
+ asm volatile (" \
+ r1 = 0xfffffffe; \
+ *(u64 *)(r10 - 8) = r1; \
+ r0 = *(s32 *)(r10 - 8); \
+ r0 >>= 1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S8 range checking, privileged")
+__log_level(2) __success __retval(1)
+__msg("R1_w=scalar(smin=-128,smax=127)")
+__naked void ldsx_s8_range_priv(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ *(u64 *)(r10 - 8) = r0; \
+ r1 = *(s8 *)(r10 - 8); \
+ /* r1 with s8 range */ \
+ if r1 s> 0x7f goto l0_%=; \
+ if r1 s< -0x80 goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S16 range checking")
+__success __success_unpriv __retval(1)
+__naked void ldsx_s16_range(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ *(u64 *)(r10 - 8) = r0; \
+ r1 = *(s16 *)(r10 - 8); \
+ /* r1 with s16 range */ \
+ if r1 s> 0x7fff goto l0_%=; \
+ if r1 s< -0x8000 goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S32 range checking")
+__success __success_unpriv __retval(1)
+__naked void ldsx_s32_range(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ *(u64 *)(r10 - 8) = r0; \
+ r1 = *(s32 *)(r10 - 8); \
+ /* r1 with s16 range */ \
+ if r1 s> 0x7fffFFFF goto l0_%=; \
+ if r1 s< -0x80000000 goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+ return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
new file mode 100644
index 000000000000..9568089932d7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("MOV32SX, S8")
+__success __success_unpriv __retval(0x23)
+__naked void mov32sx_s8(void)
+{
+ asm volatile (" \
+ w0 = 0xff23; \
+ w0 = (s8)w0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16")
+__success __success_unpriv __retval(0xFFFFff23)
+__naked void mov32sx_s16(void)
+{
+ asm volatile (" \
+ w0 = 0xff23; \
+ w0 = (s16)w0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S8")
+__success __success_unpriv __retval(-2)
+__naked void mov64sx_s8(void)
+{
+ asm volatile (" \
+ r0 = 0x1fe; \
+ r0 = (s8)r0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S16")
+__success __success_unpriv __retval(0xf23)
+__naked void mov64sx_s16(void)
+{
+ asm volatile (" \
+ r0 = 0xf0f23; \
+ r0 = (s16)r0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S32")
+__success __success_unpriv __retval(-1)
+__naked void mov64sx_s32(void)
+{
+ asm volatile (" \
+ r0 = 0xfffffffe; \
+ r0 = (s32)r0; \
+ r0 >>= 1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s8_range(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ w1 = (s8)w0; \
+ /* w1 with s8 range */ \
+ if w1 s> 0x7f goto l0_%=; \
+ if w1 s< -0x80 goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s16_range(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ w1 = (s16)w0; \
+ /* w1 with s16 range */ \
+ if w1 s> 0x7fff goto l0_%=; \
+ if w1 s< -0x80ff goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16, range_check 2")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s16_range_2(void)
+{
+ asm volatile (" \
+ r1 = 65535; \
+ w2 = (s16)w1; \
+ r2 >>= 1; \
+ if r2 != 0x7fffFFFF goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 0; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S8, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s8_range(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ r1 = (s8)r0; \
+ /* r1 with s8 range */ \
+ if r1 s> 0x7f goto l0_%=; \
+ if r1 s< -0x80 goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S16, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s16_range(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ r1 = (s16)r0; \
+ /* r1 with s16 range */ \
+ if r1 s> 0x7fff goto l0_%=; \
+ if r1 s< -0x8000 goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S32, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s32_range(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ r1 = (s32)r0; \
+ /* r1 with s32 range */ \
+ if r1 s> 0x7fffffff goto l0_%=; \
+ if r1 s< -0x80000000 goto l0_%=; \
+ r0 = 1; \
+l1_%=: \
+ exit; \
+l0_%=: \
+ r0 = 2; \
+ goto l1_%=; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+ return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
new file mode 100644
index 000000000000..f61a9a1058c8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -0,0 +1,781 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_imm_1(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w0 s/= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_imm_2(void)
+{
+ asm volatile (" \
+ w0 = 41; \
+ w0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_imm_3(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_imm_4(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w0 s/= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_imm_5(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_imm_6(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 7")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_imm_7(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w0 s/= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 8")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_imm_8(void)
+{
+ asm volatile (" \
+ w0 = 41; \
+ w0 s/= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_reg_1(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w1 = 2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_reg_2(void)
+{
+ asm volatile (" \
+ w0 = 41; \
+ w1 = -2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_reg_3(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w1 = -2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_reg_4(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w1 = 2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_reg_5(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w1 = -2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_reg_6(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w1 = -2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 7")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_reg_7(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w1 = 2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 8")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_reg_8(void)
+{
+ asm volatile (" \
+ w0 = 41; \
+ w1 = 2; \
+ w0 s/= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_imm_1(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r0 s/= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_imm_2(void)
+{
+ asm volatile (" \
+ r0 = 41; \
+ r0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv64_non_zero_imm_3(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_imm_4(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r0 s/= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_imm_5(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv64_non_zero_imm_6(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r0 s/= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_reg_1(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r1 = 2; \
+ r0 s/= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_reg_2(void)
+{
+ asm volatile (" \
+ r0 = 41; \
+ r1 = -2; \
+ r0 s/= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv64_non_zero_reg_3(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r1 = -2; \
+ r0 s/= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_reg_4(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r1 = 2; \
+ r0 s/= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_reg_5(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r1 = -2; \
+ r0 s/= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv64_non_zero_reg_6(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r1 = -2; \
+ r0 s/= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_imm_1(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w0 s%%= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod32_non_zero_imm_2(void)
+{
+ asm volatile (" \
+ w0 = 41; \
+ w0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_imm_3(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_4(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w0 s%%= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_5(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_6(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_reg_1(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w1 = 2; \
+ w0 s%%= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod32_non_zero_reg_2(void)
+{
+ asm volatile (" \
+ w0 = 41; \
+ w1 = -2; \
+ w0 s%%= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_reg_3(void)
+{
+ asm volatile (" \
+ w0 = -41; \
+ w1 = -2; \
+ w0 s%%= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_4(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w1 = 2; \
+ w0 s%%= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_5(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w1 = -2; \
+ w0 s%%= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_6(void)
+{
+ asm volatile (" \
+ w0 = -42; \
+ w1 = -2; \
+ w0 s%%= w1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_imm_1(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r0 s%%= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_imm_2(void)
+{
+ asm volatile (" \
+ r0 = 41; \
+ r0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_imm_3(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_4(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r0 s%%= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-0)
+__naked void smod64_non_zero_imm_5(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_6(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r0 s%%= -2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 7")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_7(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r0 s%%= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 8")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_imm_8(void)
+{
+ asm volatile (" \
+ r0 = 41; \
+ r0 s%%= 2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_reg_1(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r1 = 2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_reg_2(void)
+{
+ asm volatile (" \
+ r0 = 41; \
+ r1 = -2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_reg_3(void)
+{
+ asm volatile (" \
+ r0 = -41; \
+ r1 = -2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_4(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r1 = 2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_5(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r1 = -2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_6(void)
+{
+ asm volatile (" \
+ r0 = -42; \
+ r1 = -2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 7")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_7(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r1 = 2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 8")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_reg_8(void)
+{
+ asm volatile (" \
+ r0 = 41; \
+ r1 = 2; \
+ r0 s%%= r1; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, zero divisor")
+__success __success_unpriv __retval(0)
+__naked void sdiv32_zero_divisor(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w1 = 0; \
+ w2 = -1; \
+ w2 s/= w1; \
+ w0 = w2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, zero divisor")
+__success __success_unpriv __retval(0)
+__naked void sdiv64_zero_divisor(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r1 = 0; \
+ r2 = -1; \
+ r2 s/= r1; \
+ r0 = r2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, zero divisor")
+__success __success_unpriv __retval(-1)
+__naked void smod32_zero_divisor(void)
+{
+ asm volatile (" \
+ w0 = 42; \
+ w1 = 0; \
+ w2 = -1; \
+ w2 s%%= w1; \
+ w0 = w2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, zero divisor")
+__success __success_unpriv __retval(-1)
+__naked void smod64_zero_divisor(void)
+{
+ asm volatile (" \
+ r0 = 42; \
+ r1 = 0; \
+ r2 = -1; \
+ r2 s%%= r1; \
+ r0 = r2; \
+ exit; \
+" ::: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+ return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/verifier/basic_instr.c b/tools/testing/selftests/bpf/verifier/basic_instr.c
index 071dbc889e8c..bd928a72ad73 100644
--- a/tools/testing/selftests/bpf/verifier/basic_instr.c
+++ b/tools/testing/selftests/bpf/verifier/basic_instr.c
@@ -176,11 +176,11 @@
.retval = 1,
},
{
- "invalid 64-bit BPF_END",
+ "invalid 64-bit BPF_END with BPF_TO_BE",
.insns = {
BPF_MOV32_IMM(BPF_REG_0, 0),
{
- .code = BPF_ALU64 | BPF_END | BPF_TO_LE,
+ .code = BPF_ALU64 | BPF_END | BPF_TO_BE,
.dst_reg = BPF_REG_0,
.src_reg = 0,
.off = 0,
@@ -188,7 +188,7 @@
},
BPF_EXIT_INSN(),
},
- .errstr = "unknown opcode d7",
+ .errstr = "unknown opcode df",
.result = REJECT,
},
{
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 3ff436706640..2827f2d7cf30 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -2076,7 +2076,7 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts);
if (err) {
- ksft_print_msg("Error querrying XDP capabilities\n");
+ ksft_print_msg("Error querying XDP capabilities\n");
exit_with_error(-err);
}
if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG)