Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 79 files changed, 5275 insertions(+), 600 deletions(-).

The main changes are:

1) Basic BTF validation in libbpf, from Andrii Nakryiko.

2) bpf_assert(), bpf_throw(), exceptions in bpf progs, from Kumar Kartikeya Dwivedi.

3) next_thread cleanups, from Oleg Nesterov.

4) Add mcpu=v4 support to arm32, from Puranjay Mohan.

5) Add support for __percpu pointers in bpf progs, from Yonghong Song.

6) Fix bpf tailcall interaction with bpf trampoline, from Leon Hwang.

7) Raise irq_work in bpf_mem_alloc while irqs are disabled to improve refill probabablity, from Hou Tao.

Please consider pulling these changes from:

  git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git

Thanks a lot!

Also thanks to reporters, reviewers and testers of commits in this pull-request:

Alan Maguire, Andrey Konovalov, Dave Marchevsky, "Eric W. Biederman",
Jiri Olsa, Maciej Fijalkowski, Quentin Monnet, Russell King (Oracle),
Song Liu, Stanislav Fomichev, Yonghong Song
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

79 files changed, 5275 insertions, 600 deletions

diff --git a/Documentation/bpf/prog_flow_dissector.rst b/Documentation/bpf/prog_flow_dissector.rst
index 4d86780ab0f1..f24270b8b034 100644
--- a/Documentation/bpf/prog_flow_dissector.rst
+++ b/Documentation/bpf/prog_flow_dissector.rst
@@ -113,7 +113,7 @@ Flags
   used by ``eth_get_headlen`` to estimate length of all headers for GRO.
 * ``BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL`` - tells BPF flow dissector to
   stop parsing as soon as it reaches IPv6 flow label; used by
-  ``___skb_get_hash`` and ``__skb_get_hash_symmetric`` to get flow hash.
+  ``___skb_get_hash`` to get flow hash.
 * ``BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP`` - tells BPF flow dissector to stop
   parsing as soon as it reaches encapsulated headers; used by routing
   infrastructure.
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 1c7284fd535b..c46fcc78fc04 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -42,6 +42,19 @@ definitions:
         doc:
           This feature informs if netdev implements non-linear XDP buffer
           support in ndo_xdp_xmit callback.
+  -
+    type: flags
+    name: xdp-rx-metadata
+    render-max: true
+    entries:
+      -
+        name: timestamp
+        doc:
+          Device is capable of exposing receive HW timestamp via bpf_xdp_metadata_rx_timestamp().
+      -
+        name: hash
+        doc:
+          Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
 
 attribute-sets:
   -
@@ -68,6 +81,13 @@ attribute-sets:
         type: u32
         checks:
           min: 1
+      -
+        name: xdp-rx-metadata-features
+        doc: Bitmask of supported XDP receive metadata features.
+             See Documentation/networking/xdp-rx-metadata.rst for more details.
+        type: u64
+        enum: xdp-rx-metadata
+        enum-as-flags: true
 
 operations:
   list:
@@ -84,6 +104,7 @@ operations:
             - ifindex
             - xdp-features
             - xdp-zc-max-segs
+            - xdp-rx-metadata-features
       dump:
         reply: *dev-all
     -
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index 25ce72af81c2..205696780b78 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -105,6 +105,13 @@ bpf_tail_call
 Adding programs that access metadata kfuncs to the ``BPF_MAP_TYPE_PROG_ARRAY``
 is currently not supported.
 
+Supported Devices
+=================
+
+It is possible to query which kfunc the particular netdev implements via
+netlink. See ``xdp-rx-metadata-features`` attribute set in
+``Documentation/netlink/specs/netdev.yaml``.
+
 Example
 =======
 
diff --git a/MAINTAINERS b/MAINTAINERS
index c94489dff2fd..3dde038545d8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3596,9 +3596,10 @@ F:	Documentation/devicetree/bindings/iio/accel/bosch,bma400.yaml
 F:	drivers/iio/accel/bma400*
 
 BPF JIT for ARM
-M:	Shubham Bansal <illusionist.neo@gmail.com>
+M:	Russell King <linux@armlinux.org.uk>
+M:	Puranjay Mohan <puranjay12@gmail.com>
 L:	bpf@vger.kernel.org
-S:	Odd Fixes
+S:	Maintained
 F:	arch/arm/net/
 
 BPF JIT for ARM64
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6a1c9fca5260..1d672457d02f 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -2,6 +2,7 @@
 /*
  * Just-In-Time compiler for eBPF filters on 32bit ARM
  *
+ * Copyright (c) 2023 Puranjay Mohan <puranjay12@gmail.com>
  * Copyright (c) 2017 Shubham Bansal <illusionist.neo@gmail.com>
  * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com>
  */
@@ -15,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/if_vlan.h>
+#include <linux/math64.h>
 
 #include <asm/cacheflush.h>
 #include <asm/hwcap.h>
@@ -228,6 +230,44 @@ static u32 jit_mod32(u32 dividend, u32 divisor)
 	return dividend % divisor;
 }
 
+static s32 jit_sdiv32(s32 dividend, s32 divisor)
+{
+	return dividend / divisor;
+}
+
+static s32 jit_smod32(s32 dividend, s32 divisor)
+{
+	return dividend % divisor;
+}
+
+/* Wrappers for 64-bit div/mod */
+static u64 jit_udiv64(u64 dividend, u64 divisor)
+{
+	return div64_u64(dividend, divisor);
+}
+
+static u64 jit_mod64(u64 dividend, u64 divisor)
+{
+	u64 rem;
+
+	div64_u64_rem(dividend, divisor, &rem);
+	return rem;
+}
+
+static s64 jit_sdiv64(s64 dividend, s64 divisor)
+{
+	return div64_s64(dividend, divisor);
+}
+
+static s64 jit_smod64(s64 dividend, s64 divisor)
+{
+	u64 q;
+
+	q = div64_s64(dividend, divisor);
+
+	return dividend - q * divisor;
+}
+
 static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
 {
 	inst |= (cond << 28);
@@ -333,6 +373,9 @@ static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
 #define ARM_LDRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRD_I, rt, rn, off)
 #define ARM_LDRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off)
 
+#define ARM_LDRSH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRSH_I, rt, rn, off)
+#define ARM_LDRSB_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRSB_I, rt, rn, off)
+
 #define ARM_STR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off)
 #define ARM_STRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off)
 #define ARM_STRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_STRD_I, rt, rn, off)
@@ -474,17 +517,18 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 	return to - from - 2;
 }
 
-static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
+static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op, u8 sign)
 {
 	const int exclude_mask = BIT(ARM_R0) | BIT(ARM_R1);
 	const s8 *tmp = bpf2a32[TMP_REG_1];
+	u32 dst;
 
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
-		if (op == BPF_DIV)
-			emit(ARM_UDIV(rd, rm, rn), ctx);
-		else {
-			emit(ARM_UDIV(ARM_IP, rm, rn), ctx);
+		if (op == BPF_DIV) {
+			emit(sign ? ARM_SDIV(rd, rm, rn) : ARM_UDIV(rd, rm, rn), ctx);
+		} else {
+			emit(sign ? ARM_SDIV(ARM_IP, rm, rn) : ARM_UDIV(ARM_IP, rm, rn), ctx);
 			emit(ARM_MLS(rd, rn, ARM_IP, rm), ctx);
 		}
 		return;
@@ -512,8 +556,19 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 	emit(ARM_PUSH(CALLER_MASK & ~exclude_mask), ctx);
 
 	/* Call appropriate function */
-	emit_mov_i(ARM_IP, op == BPF_DIV ?
-		   (u32)jit_udiv32 : (u32)jit_mod32, ctx);
+	if (sign) {
+		if (op == BPF_DIV)
+			dst = (u32)jit_sdiv32;
+		else
+			dst = (u32)jit_smod32;
+	} else {
+		if (op == BPF_DIV)
+			dst = (u32)jit_udiv32;
+		else
+			dst = (u32)jit_mod32;
+	}
+
+	emit_mov_i(ARM_IP, dst, ctx);
 	emit_blx_r(ARM_IP, ctx);
 
 	/* Restore caller-saved registers from stack */
@@ -530,6 +585,78 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 		emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx);
 }
 
+static inline void emit_udivmod64(const s8 *rd, const s8 *rm, const s8 *rn, struct jit_ctx *ctx,
+				  u8 op, u8 sign)
+{
+	u32 dst;
+
+	/* Push caller-saved registers on stack */
+	emit(ARM_PUSH(CALLER_MASK), ctx);
+
+	/*
+	 * As we are implementing 64-bit div/mod as function calls, We need to put the dividend in
+	 * R0-R1 and the divisor in R2-R3. As we have already pushed these registers on the stack,
+	 * we can recover them later after returning from the function call.
+	 */
+	if (rm[1] != ARM_R0 || rn[1] != ARM_R2) {
+		/*
+		 * Move Rm to {R1, R0} if it is not already there.
+		 */
+		if (rm[1] != ARM_R0) {
+			if (rn[1] == ARM_R0)
+				emit(ARM_PUSH(BIT(ARM_R0) | BIT(ARM_R1)), ctx);
+			emit(ARM_MOV_R(ARM_R1, rm[0]), ctx);
+			emit(ARM_MOV_R(ARM_R0, rm[1]), ctx);
+			if (rn[1] == ARM_R0) {
+				emit(ARM_POP(BIT(ARM_R2) | BIT(ARM_R3)), ctx);
+				goto cont;
+			}
+		}
+		/*
+		 * Move Rn to {R3, R2} if it is not already there.
+		 */
+		if (rn[1] != ARM_R2) {
+			emit(ARM_MOV_R(ARM_R3, rn[0]), ctx);
+			emit(ARM_MOV_R(ARM_R2, rn[1]), ctx);
+		}
+	}
+
+cont:
+
+	/* Call appropriate function */
+	if (sign) {
+		if (op == BPF_DIV)
+			dst = (u32)jit_sdiv64;
+		else
+			dst = (u32)jit_smod64;
+	} else {
+		if (op == BPF_DIV)
+			dst = (u32)jit_udiv64;
+		else
+			dst = (u32)jit_mod64;
+	}
+
+	emit_mov_i(ARM_IP, dst, ctx);
+	emit_blx_r(ARM_IP, ctx);
+
+	/* Save return value */
+	if (rd[1] != ARM_R0) {
+		emit(ARM_MOV_R(rd[0], ARM_R1), ctx);
+		emit(ARM_MOV_R(rd[1], ARM_R0), ctx);
+	}
+
+	/* Recover {R3, R2} and {R1, R0} from stack if they are not Rd */
+	if (rd[1] != ARM_R0 && rd[1] != ARM_R2) {
+		emit(ARM_POP(CALLER_MASK), ctx);
+	} else if (rd[1] != ARM_R0) {
+		emit(ARM_POP(BIT(ARM_R0) | BIT(ARM_R1)), ctx);
+		emit(ARM_ADD_I(ARM_SP, ARM_SP, 8), ctx);
+	} else {
+		emit(ARM_ADD_I(ARM_SP, ARM_SP, 8), ctx);
+		emit(ARM_POP(BIT(ARM_R2) | BIT(ARM_R3)), ctx);
+	}
+}
+
 /* Is the translated BPF register on stack? */
 static bool is_stacked(s8 reg)
 {
@@ -744,12 +871,16 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 }
 
 /* dst = src (4 bytes)*/
-static inline void emit_a32_mov_r(const s8 dst, const s8 src,
+static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off,
 				  struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	s8 rt;
 
 	rt = arm_bpf_get_reg32(src, tmp[0], ctx);
+	if (off && off != 32) {
+		emit(ARM_LSL_I(rt, rt, 32 - off), ctx);
+		emit(ARM_ASR_I(rt, rt, 32 - off), ctx);
+	}
 	arm_bpf_put_reg32(dst, rt, ctx);
 }
 
@@ -758,15 +889,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  const s8 src[],
 				  struct jit_ctx *ctx) {
 	if (!is64) {
-		emit_a32_mov_r(dst_lo, src_lo, ctx);
+		emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
 		if (!ctx->prog->aux->verifier_zext)
 			/* Zero out high 4 bytes */
 			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else if (__LINUX_ARM_ARCH__ < 6 &&
 		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
-		emit_a32_mov_r(dst_lo, src_lo, ctx);
-		emit_a32_mov_r(dst_hi, src_hi, ctx);
+		emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
+		emit_a32_mov_r(dst_hi, src_hi, 0, ctx);
 	} else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
 		const u8 *tmp = bpf2a32[TMP_REG_1];
 
@@ -782,6 +913,24 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 	}
 }
 
+/* dst = (signed)src */
+static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[],
+				      struct jit_ctx *ctx) {
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rt;
+
+	rt = arm_bpf_get_reg64(dst, tmp, ctx);
+
+	emit_a32_mov_r(dst_lo, src_lo, off, ctx);
+	if (!is64) {
+		if (!ctx->prog->aux->verifier_zext)
+			/* Zero out high 4 bytes */
+			emit_a32_mov_i(dst_hi, 0, ctx);
+	} else {
+		emit(ARM_ASR_I(rt[0], rt[1], 31), ctx);
+	}
+}
+
 /* Shift operations */
 static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 				struct jit_ctx *ctx, const u8 op) {
@@ -1026,6 +1175,24 @@ static bool is_ldst_imm(s16 off, const u8 size)
 	return -off_max <= off && off <= off_max;
 }
 
+static bool is_ldst_imm8(s16 off, const u8 size)
+{
+	s16 off_max = 0;
+
+	switch (size) {
+	case BPF_B:
+		off_max = 0xff;
+		break;
+	case BPF_W:
+		off_max = 0xfff;
+		break;
+	case BPF_H:
+		off_max = 0xff;
+		break;
+	}
+	return -off_max <= off && off <= off_max;
+}
+
 /* *(size *)(dst + off) = src */
 static inline void emit_str_r(const s8 dst, const s8 src[],
 			      s16 off, struct jit_ctx *ctx, const u8 sz){
@@ -1105,6 +1272,50 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
+/* dst = *(signed size*)(src + off) */
+static inline void emit_ldsx_r(const s8 dst[], const s8 src,
+			       s16 off, struct jit_ctx *ctx, const u8 sz){
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+	s8 rm = src;
+	int add_off;
+
+	if (!is_ldst_imm8(off, sz)) {
+		/*
+		 * offset does not fit in the load/store immediate,
+		 * construct an ADD instruction to apply the offset.
+		 */
+		add_off = imm8m(off);
+		if (add_off > 0) {
+			emit(ARM_ADD_I(tmp[0], src, add_off), ctx);
+			rm = tmp[0];
+		} else {
+			emit_a32_mov_i(tmp[0], off, ctx);
+			emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
+			rm = tmp[0];
+		}
+		off = 0;
+	}
+
+	switch (sz) {
+	case BPF_B:
+		/* Load a Byte with sign extension*/
+		emit(ARM_LDRSB_I(rd[1], rm, off), ctx);
+		break;
+	case BPF_H:
+		/* Load a HalfWord with sign extension*/
+		emit(ARM_LDRSH_I(rd[1], rm, off), ctx);
+		break;
+	case BPF_W:
+		/* Load a Word*/
+		emit(ARM_LDR_I(rd[1], rm, off), ctx);
+		break;
+	}
+	/* Carry the sign extension to upper 32 bits */