Merge tag 'bpf-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:
 "For this merge window we're splitting BPF pull request into three for
  higher visibility: main changes, res_spin_lock, try_alloc_pages.

  These are the main BPF changes:

   - Add DFA-based live registers analysis to improve verification of
     programs with loops (Eduard Zingerman)

   - Introduce load_acquire and store_release BPF instructions and add
     x86, arm64 JIT support (Peilin Ye)

   - Fix loop detection logic in the verifier (Eduard Zingerman)

   - Drop unnecesary lock in bpf_map_inc_not_zero() (Eric Dumazet)

   - Add kfunc for populating cpumask bits (Emil Tsalapatis)

   - Convert various shell based tests to selftests/bpf/test_progs
     format (Bastien Curutchet)

   - Allow passing referenced kptrs into struct_ops callbacks (Amery
     Hung)

   - Add a flag to LSM bpf hook to facilitate bpf program signing
     (Blaise Boscaccy)

   - Track arena arguments in kfuncs (Ihor Solodrai)

   - Add copy_remote_vm_str() helper for reading strings from remote VM
     and bpf_copy_from_user_task_str() kfunc (Jordan Rome)

   - Add support for timed may_goto instruction (Kumar Kartikeya
     Dwivedi)

   - Allow bpf_get_netns_cookie() int cgroup_skb programs (Mahe Tardy)

   - Reduce bpf_cgrp_storage_busy false positives when accessing cgroup
     local storage (Martin KaFai Lau)

   - Introduce bpf_dynptr_copy() kfunc (Mykyta Yatsenko)

   - Allow retrieving BTF data with BTF token (Mykyta Yatsenko)

   - Add BPF kfuncs to set and get xattrs with 'security.bpf.' prefix
     (Song Liu)

   - Reject attaching programs to noreturn functions (Yafang Shao)

   - Introduce pre-order traversal of cgroup bpf programs (Yonghong
     Song)"

* tag 'bpf-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (186 commits)
  selftests/bpf: Add selftests for load-acquire/store-release when register number is invalid
  bpf: Fix out-of-bounds read in check_atomic_load/store()
  libbpf: Add namespace for errstr making it libbpf_errstr
  bpf: Add struct_ops context information to struct bpf_prog_aux
  selftests/bpf: Sanitize pointer prior fclose()
  selftests/bpf: Migrate test_xdp_vlan.sh into test_progs
  selftests/bpf: test_xdp_vlan: Rename BPF sections
  bpf: clarify a misleading verifier error message
  selftests/bpf: Add selftest for attaching fexit to __noreturn functions
  bpf: Reject attaching fexit/fmod_ret to __noreturn functions
  bpf: Only fails the busy counter check in bpf_cgrp_storage_get if it creates storage
  bpf: Make perf_event_read_output accessible in all program types.
  bpftool: Using the right format specifiers
  bpftool: Add -Wformat-signedness flag to detect format errors
  selftests/bpf: Test freplace from user namespace
  libbpf: Pass BPF token from find_prog_btf_id to BPF_BTF_GET_FD_BY_ID
  bpf: Return prog btf_id without capable check
  bpf: BPF token support for BPF_BTF_GET_FD_BY_ID
  bpf, x86: Fix objtool warning for timed may_goto
  bpf: Check map->record at the beginning of check_and_free_fields()
  ...

Author: torvalds

Documentation/bpf/bpf_iterators.rst

@@ -86,7 +86,7 @@ following steps:
 The following are a few examples of selftest BPF iterator programs:
 
 * `bpf_iter_tcp4.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c>`_
-* `bpf_iter_task_vma.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c>`_
+* `bpf_iter_task_vmas.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c>`_
 * `bpf_iter_task_file.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c>`_
 
 Let us look at ``bpf_iter_task_file.c``, which runs in kernel space:

Documentation/bpf/btf.rst

@@ -102,7 +102,8 @@ Each type contains the following common data::
          * bits 24-28: kind (e.g. int, ptr, array...etc)
          * bits 29-30: unused
          * bit     31: kind_flag, currently used by
-         *             struct, union, fwd, enum and enum64.
+         *             struct, union, enum, fwd, enum64,
+         *             decl_tag and type_tag
          */
         __u32 info;
         /* "size" is used by INT, ENUM, STRUCT, UNION and ENUM64.
@@ -478,7 +479,7 @@ No additional type data follow ``btf_type``.
 
 ``struct btf_type`` encoding requirement:
  * ``name_off``: offset to a non-empty string
- * ``info.kind_flag``: 0
+ * ``info.kind_flag``: 0 or 1
  * ``info.kind``: BTF_KIND_DECL_TAG
  * ``info.vlen``: 0
  * ``type``: ``struct``, ``union``, ``func``, ``var`` or ``typedef``
@@ -489,7 +490,6 @@ No additional type data follow ``btf_type``.
         __u32   component_idx;
     };
 
-The ``name_off`` encodes btf_decl_tag attribute string.
 The ``type`` should be ``struct``, ``union``, ``func``, ``var`` or ``typedef``.
 For ``var`` or ``typedef`` type, ``btf_decl_tag.component_idx`` must be ``-1``.
 For the other three types, if the btf_decl_tag attribute is
@@ -499,12 +499,21 @@ the attribute is applied to a ``struct``/``union`` member or
 a ``func`` argument, and ``btf_decl_tag.component_idx`` should be a
 valid index (starting from 0) pointing to a member or an argument.
 
+If ``info.kind_flag`` is 0, then this is a normal decl tag, and the
+``name_off`` encodes btf_decl_tag attribute string.
+
+If ``info.kind_flag`` is 1, then the decl tag represents an arbitrary
+__attribute__. In this case, ``name_off`` encodes a string
+representing the attribute-list of the attribute specifier. For
+example, for an ``__attribute__((aligned(4)))`` the string's contents
+is ``aligned(4)``.
+
 2.2.18 BTF_KIND_TYPE_TAG
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
 ``struct btf_type`` encoding requirement:
  * ``name_off``: offset to a non-empty string
- * ``info.kind_flag``: 0
+ * ``info.kind_flag``: 0 or 1
  * ``info.kind``: BTF_KIND_TYPE_TAG
  * ``info.vlen``: 0
  * ``type``: the type with ``btf_type_tag`` attribute
@@ -522,6 +531,14 @@ type_tag, then zero or more const/volatile/restrict/typedef
 and finally the base type. The base type is one of
 int, ptr, array, struct, union, enum, func_proto and float types.
 
+Similarly to decl tags, if the ``info.kind_flag`` is 0, then this is a
+normal type tag, and the ``name_off`` encodes btf_type_tag attribute
+string.
+
+If ``info.kind_flag`` is 1, then the type tag represents an arbitrary
+__attribute__, and the ``name_off`` encodes a string representing the
+attribute-list of the attribute specifier.
+
 2.2.19 BTF_KIND_ENUM64
 ~~~~~~~~~~~~~~~~~~~~~~
 

Documentation/bpf/standardization/instruction-set.rst

@@ -324,34 +324,42 @@ register.
 
 .. table:: Arithmetic instructions
 
-  =====  =====  =======  ==========================================================
+  =====  =====  =======  ===================================================================================
   name   code   offset   description
-  =====  =====  =======  ==========================================================
+  =====  =====  =======  ===================================================================================
   ADD    0x0    0        dst += src
   SUB    0x1    0        dst -= src
   MUL    0x2    0        dst \*= src
   DIV    0x3    0        dst = (src != 0) ? (dst / src) : 0
-  SDIV   0x3    1        dst = (src != 0) ? (dst s/ src) : 0
+  SDIV   0x3    1        dst = (src == 0) ? 0 : ((src == -1 && dst == LLONG_MIN) ? LLONG_MIN : (dst s/ src))
   OR     0x4    0        dst \|= src
   AND    0x5    0        dst &= src
   LSH    0x6    0        dst <<= (src & mask)
   RSH    0x7    0        dst >>= (src & mask)
   NEG    0x8    0        dst = -dst
   MOD    0x9    0        dst = (src != 0) ? (dst % src) : dst
-  SMOD   0x9    1        dst = (src != 0) ? (dst s% src) : dst
+  SMOD   0x9    1        dst = (src == 0) ? dst : ((src == -1 && dst == LLONG_MIN) ? 0: (dst s% src))
   XOR    0xa    0        dst ^= src
   MOV    0xb    0        dst = src
   MOVSX  0xb    8/16/32  dst = (s8,s16,s32)src
   ARSH   0xc    0        :term:`sign extending<Sign Extend>` dst >>= (src & mask)
   END    0xd    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 BPF program execution would
 result in division by zero, the destination register is instead set to zero.
+Otherwise, for ``ALU64``, if execution would result in ``LLONG_MIN``
+dividing -1, the desination register is instead set to ``LLONG_MIN``. For
+``ALU``, if execution would result in ``INT_MIN`` dividing -1, the
+desination register is instead set to ``INT_MIN``.
+
 If execution would result in modulo by zero, for ``ALU64`` the value of
 the destination register is unchanged whereas for ``ALU`` the upper
-32 bits of the destination register are zeroed.
+32 bits of the destination register are zeroed. Otherwise, for ``ALU64``,
+if execution would resuslt in ``LLONG_MIN`` modulo -1, the destination
+register is instead set to 0. For ``ALU``, if execution would result in
+``INT_MIN`` modulo -1, the destination register is instead set to 0.
 
 ``{ADD, X, ALU}``, where 'code' = ``ADD``, 'source' = ``X``, and 'class' = ``ALU``, means::
 

arch/arm64/include/asm/insn.h

@@ -188,8 +188,10 @@ enum aarch64_insn_ldst_type {
 	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
 	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
 	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_LOAD_ACQ,
 	AARCH64_INSN_LDST_LOAD_EX,
 	AARCH64_INSN_LDST_LOAD_ACQ_EX,
+	AARCH64_INSN_LDST_STORE_REL,
 	AARCH64_INSN_LDST_STORE_EX,
 	AARCH64_INSN_LDST_STORE_REL_EX,
 	AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET,
@@ -351,8 +353,10 @@ __AARCH64_INSN_FUNCS(ldr_imm,	0x3FC00000, 0x39400000)
 __AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
 __AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
 __AARCH64_INSN_FUNCS(exclusive,	0x3F800000, 0x08000000)
-__AARCH64_INSN_FUNCS(load_ex,	0x3F400000, 0x08400000)
-__AARCH64_INSN_FUNCS(store_ex,	0x3F400000, 0x08000000)
+__AARCH64_INSN_FUNCS(load_acq,  0x3FDFFC00, 0x08DFFC00)
+__AARCH64_INSN_FUNCS(store_rel, 0x3FDFFC00, 0x089FFC00)
+__AARCH64_INSN_FUNCS(load_ex,	0x3FC00000, 0x08400000)
+__AARCH64_INSN_FUNCS(store_ex,	0x3FC00000, 0x08000000)
 __AARCH64_INSN_FUNCS(mops,	0x3B200C00, 0x19000400)
 __AARCH64_INSN_FUNCS(stp,	0x7FC00000, 0x29000000)
 __AARCH64_INSN_FUNCS(ldp,	0x7FC00000, 0x29400000)
@@ -602,6 +606,10 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 				     int offset,
 				     enum aarch64_insn_variant variant,
 				     enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type);
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,

arch/arm64/lib/insn.c

@@ -540,6 +540,35 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 					     offset >> shift);
 }
 
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_ACQ:
+		insn = aarch64_insn_get_load_acq_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_REL:
+		insn = aarch64_insn_get_store_rel_value();
+		break;
+	default:
+		pr_err("%s: unknown load-acquire/store-release encoding %d\n",
+		       __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+}
+
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,

arch/arm64/net/bpf_jit.h

@@ -119,6 +119,26 @@
 	aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
 				       AARCH64_INSN_LDST_STORE_REL_EX)
 
+/* Load-acquire & store-release */
+#define A64_LDAR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_LOAD_ACQ)
+#define A64_STLR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_STORE_REL)
+
+/* Rt = [Rn] (load acquire) */
+#define A64_LDARB(Wt, Xn)	A64_LDAR(Wt, Xn, 8)
+#define A64_LDARH(Wt, Xn)	A64_LDAR(Wt, Xn, 16)
+#define A64_LDAR32(Wt, Xn)	A64_LDAR(Wt, Xn, 32)
+#define A64_LDAR64(Xt, Xn)	A64_LDAR(Xt, Xn, 64)
+
+/* [Rn] = Rt (store release) */
+#define A64_STLRB(Wt, Xn)	A64_STLR(Wt, Xn, 8)
+#define A64_STLRH(Wt, Xn)	A64_STLR(Wt, Xn, 16)
+#define A64_STLR32(Wt, Xn)	A64_STLR(Wt, Xn, 32)
+#define A64_STLR64(Xt, Xn)	A64_STLR(Xt, Xn, 64)
+
 /*
  * LSE atomics
  *

arch/arm64/net/bpf_jit_comp.c

@@ -272,7 +272,7 @@ static inline void emit_a64_add_i(const bool is64, const int dst, const int src,
 {
 	if (is_addsub_imm(imm)) {
 		emit(A64_ADD_I(is64, dst, src, imm), ctx);
-	} else if (is_addsub_imm(-imm)) {
+	} else if (is_addsub_imm(-(u32)imm)) {
 		emit(A64_SUB_I(is64, dst, src, -imm), ctx);
 	} else {
 		emit_a64_mov_i(is64, tmp, imm, ctx);
@@ -647,6 +647,81 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	return 0;
 }
 
+static int emit_atomic_ld_st(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const s32 imm = insn->imm;
+	const s16 off = insn->off;
+	const u8 code = insn->code;
+	const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC;
+	const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
+	const u8 dst = bpf2a64[insn->dst_reg];
+	const u8 src = bpf2a64[insn->src_reg];
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	u8 reg;
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		reg = src;
+		break;
+	case BPF_STORE_REL:
+		reg = dst;
+		break;
+	default:
+		pr_err_once("unknown atomic load/store op code %02x\n", imm);
+		return -EINVAL;
+	}
+
+	if (off) {
+		emit_a64_add_i(1, tmp, reg, tmp, off, ctx);
+		reg = tmp;
+	}
+	if (arena) {
+		emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx);
+		reg = tmp;
+	}
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_LDARB(dst, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_LDARH(dst, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_LDAR32(dst, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_LDAR64(dst, reg), ctx);
+			break;
+		}
+		break;
+	case BPF_STORE_REL:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_STLRB(src, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STLRH(src, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_STLR32(src, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STLR64(src, reg), ctx);
+			break;
+		}
+		break;
+	default:
+		pr_err_once("unexpected atomic load/store op code %02x\n",
+			    imm);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_ARM64_LSE_ATOMICS
 static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
 {
@@ -1159,7 +1234,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	case BPF_ALU64 | BPF_SUB | BPF_K:
 		if (is_addsub_imm(imm)) {
 			emit(A64_SUB_I(is64, dst, dst, imm), ctx);
-		} else if (is_addsub_imm(-imm)) {
+		} else if (is_addsub_imm(-(u32)imm)) {
 			emit(A64_ADD_I(is64, dst, dst, -imm), ctx);
 		} else {
 			emit_a64_mov_i(is64, tmp, imm, ctx);
@@ -1330,7 +1405,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
 		if (is_addsub_imm(imm)) {
 			emit(A64_CMP_I(is64, dst, imm), ctx);
-		} else if (is_addsub_imm(-imm)) {
+		} else if (is_addsub_imm(-(u32)imm)) {
 			emit(A64_CMN_I(is64, dst, -imm), ctx);
 		} else {
 			emit_a64_mov_i(is64, tmp, imm, ctx);
@@ -1641,11 +1716,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			return ret;
 		break;
 
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
-		if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(insn, ctx);
+		else if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			ret = emit_lse_atomic(insn, ctx);
 		else
 			ret = emit_ll_sc_atomic(insn, ctx);
@@ -2669,7 +2750,8 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 	switch (insn->code) {
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (!bpf_atomic_is_load_store(insn) &&
+		    !cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			return false;
 	}
 	return true;

arch/s390/net/bpf_jit_comp.c

@@ -2919,10 +2919,16 @@ bool bpf_jit_supports_arena(void)
 
 bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 {
-	/*
-	 * Currently the verifier uses this function only to check which
-	 * atomic stores to arena are supported, and they all are.
-	 */
+	if (!in_arena)
+		return true;
+	switch (insn->code) {
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (bpf_atomic_is_load_store(insn))
+			return false;
+	}
 	return true;
 }
 

arch/x86/net/Makefile

@@ -6,5 +6,5 @@
 ifeq ($(CONFIG_X86_32),y)
         obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
 else
-        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o
 endif