Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Martin KaFai Lau says:

====================
pull-request: bpf-next 2023-08-03

We've added 54 non-merge commits during the last 10 day(s) which contain
a total of 84 files changed, 4026 insertions(+), 562 deletions(-).

The main changes are:

1) Add SO_REUSEPORT support for TC bpf_sk_assign from Lorenz Bauer,
   Daniel Borkmann

2) Support new insns from cpu v4 from Yonghong Song

3) Non-atomically allocate freelist during prefill from YiFei Zhu

4) Support defragmenting IPv(4|6) packets in BPF from Daniel Xu

5) Add tracepoint to xdp attaching failure from Leon Hwang

6) struct netdev_rx_queue and xdp.h reshuffling to reduce
   rebuild time from Jakub Kicinski

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (54 commits)
  net: invert the netdevice.h vs xdp.h dependency
  net: move struct netdev_rx_queue out of netdevice.h
  eth: add missing xdp.h includes in drivers
  selftests/bpf: Add testcase for xdp attaching failure tracepoint
  bpf, xdp: Add tracepoint to xdp attaching failure
  selftests/bpf: fix static assert compilation issue for test_cls_*.c
  bpf: fix bpf_probe_read_kernel prototype mismatch
  riscv, bpf: Adapt bpf trampoline to optimized riscv ftrace framework
  libbpf: fix typos in Makefile
  tracing: bpf: use struct trace_entry in struct syscall_tp_t
  bpf, devmap: Remove unused dtab field from bpf_dtab_netdev
  bpf, cpumap: Remove unused cmap field from bpf_cpu_map_entry
  netfilter: bpf: Only define get_proto_defrag_hook() if necessary
  bpf: Fix an array-index-out-of-bounds issue in disasm.c
  net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
  docs/bpf: Fix malformed documentation
  bpf: selftests: Add defrag selftests
  bpf: selftests: Support custom type and proto for client sockets
  bpf: selftests: Support not connecting client socket
  netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link
  ...
====================

Link: https://lore.kernel.org/r/20230803174845.825419-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 117 insertions, 24 deletions

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) {
 				/*