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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-06-17

We've added 72 non-merge commits during the last 15 day(s) which contain
a total of 92 files changed, 4582 insertions(+), 834 deletions(-).

The main changes are:

1) Add 64 bit enum value support to BTF, from Yonghong Song.

2) Implement support for sleepable BPF uprobe programs, from Delyan Kratunov.

3) Add new BPF helpers to issue and check TCP SYN cookies without binding to a
   socket especially useful in synproxy scenarios, from Maxim Mikityanskiy.

4) Fix libbpf's internal USDT address translation logic for shared libraries as
   well as uprobe's symbol file offset calculation, from Andrii Nakryiko.

5) Extend libbpf to provide an API for textual representation of the various
   map/prog/attach/link types and use it in bpftool, from Daniel Müller.

6) Provide BTF line info for RV64 and RV32 JITs, and fix a put_user bug in the
   core seen in 32 bit when storing BPF function addresses, from Pu Lehui.

7) Fix libbpf's BTF pointer size guessing by adding a list of various aliases
   for 'long' types, from Douglas Raillard.

8) Fix bpftool to readd setting rlimit since probing for memcg-based accounting
   has been unreliable and caused a regression on COS, from Quentin Monnet.

9) Fix UAF in BPF cgroup's effective program computation triggered upon BPF link
   detachment, from Tadeusz Struk.

10) Fix bpftool build bootstrapping during cross compilation which was pointing
    to the wrong AR process, from Shahab Vahedi.

11) Fix logic bug in libbpf's is_pow_of_2 implementation, from Yuze Chi.

12) BPF hash map optimization to avoid grabbing spinlocks of all CPUs when there
    is no free element. Also add a benchmark as reproducer, from Feng Zhou.

13) Fix bpftool's codegen to bail out when there's no BTF, from Michael Mullin.

14) Various minor cleanup and improvements all over the place.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (72 commits)
  bpf: Fix bpf_skc_lookup comment wrt. return type
  bpf: Fix non-static bpf_func_proto struct definitions
  selftests/bpf: Don't force lld on non-x86 architectures
  selftests/bpf: Add selftests for raw syncookie helpers in TC mode
  bpf: Allow the new syncookie helpers to work with SKBs
  selftests/bpf: Add selftests for raw syncookie helpers
  bpf: Add helpers to issue and check SYN cookies in XDP
  bpf: Allow helpers to accept pointers with a fixed size
  bpf: Fix documentation of th_len in bpf_tcp_{gen,check}_syncookie
  selftests/bpf: add tests for sleepable (uk)probes
  libbpf: add support for sleepable uprobe programs
  bpf: allow sleepable uprobe programs to attach
  bpf: implement sleepable uprobes by chaining gps
  bpf: move bpf_prog to bpf.h
  libbpf: Fix internal USDT address translation logic for shared libraries
  samples/bpf: Check detach prog exist or not in xdp_fwd
  selftests/bpf: Avoid skipping certain subtests
  selftests/bpf: Fix test_varlen verification failure with latest llvm
  bpftool: Do not check return value from libbpf_set_strict_mode()
  Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK"
  ...
====================

Link: https://lore.kernel.org/r/20220617220836.7373-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

92 files changed, 4582 insertions, 834 deletions

diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst
index 7940da9bc6c1..f49aeef62d0c 100644
--- a/Documentation/bpf/btf.rst
+++ b/Documentation/bpf/btf.rst
@@ -74,7 +74,7 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_ARRAY          3       /* Array        */
     #define BTF_KIND_STRUCT         4       /* Struct       */
     #define BTF_KIND_UNION          5       /* Union        */
-    #define BTF_KIND_ENUM           6       /* Enumeration  */
+    #define BTF_KIND_ENUM           6       /* Enumeration up to 32-bit values */
     #define BTF_KIND_FWD            7       /* Forward      */
     #define BTF_KIND_TYPEDEF        8       /* Typedef      */
     #define BTF_KIND_VOLATILE       9       /* Volatile     */
@@ -87,6 +87,7 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_FLOAT          16      /* Floating point       */
     #define BTF_KIND_DECL_TAG       17      /* Decl Tag     */
     #define BTF_KIND_TYPE_TAG       18      /* Type Tag     */
+    #define BTF_KIND_ENUM64         19      /* Enumeration up to 64-bit values */
 
 Note that the type section encodes debug info, not just pure types.
 ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@@ -101,10 +102,10 @@ 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 and fwd
+         *             struct, union, fwd, enum and enum64.
          */
         __u32 info;
-        /* "size" is used by INT, ENUM, STRUCT and UNION.
+        /* "size" is used by INT, ENUM, STRUCT, UNION and ENUM64.
          * "size" tells the size of the type it is describing.
          *
          * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
@@ -281,10 +282,10 @@ modes exist:
 
 ``struct btf_type`` encoding requirement:
   * ``name_off``: 0 or offset to a valid C identifier
-  * ``info.kind_flag``: 0
+  * ``info.kind_flag``: 0 for unsigned, 1 for signed
   * ``info.kind``: BTF_KIND_ENUM
   * ``info.vlen``: number of enum values
-  * ``size``: 4
+  * ``size``: 1/2/4/8
 
 ``btf_type`` is followed by ``info.vlen`` number of ``struct btf_enum``.::
 
@@ -297,6 +298,10 @@ The ``btf_enum`` encoding:
   * ``name_off``: offset to a valid C identifier
   * ``val``: any value
 
+If the original enum value is signed and the size is less than 4,
+that value will be sign extended into 4 bytes. If the size is 8,
+the value will be truncated into 4 bytes.
+
 2.2.7 BTF_KIND_FWD
 ~~~~~~~~~~~~~~~~~~
 
@@ -493,7 +498,7 @@ 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.
 
-2.2.17 BTF_KIND_TYPE_TAG
+2.2.18 BTF_KIND_TYPE_TAG
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
 ``struct btf_type`` encoding requirement:
@@ -516,6 +521,32 @@ 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.
 
+2.2.19 BTF_KIND_ENUM64
+~~~~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: 0 or offset to a valid C identifier
+  * ``info.kind_flag``: 0 for unsigned, 1 for signed
+  * ``info.kind``: BTF_KIND_ENUM64
+  * ``info.vlen``: number of enum values
+  * ``size``: 1/2/4/8
+
+``btf_type`` is followed by ``info.vlen`` number of ``struct btf_enum64``.::
+
+    struct btf_enum64 {
+        __u32   name_off;
+        __u32   val_lo32;
+        __u32   val_hi32;
+    };
+
+The ``btf_enum64`` encoding:
+  * ``name_off``: offset to a valid C identifier
+  * ``val_lo32``: lower 32-bit value for a 64-bit value
+  * ``val_hi32``: high 32-bit value for a 64-bit value
+
+If the original enum value is signed and the size is less than 8,
+that value will be sign extended into 8 bytes.
+
 3. BTF Kernel API
 =================
 
diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst
index 1de6a57c7e1e..9e27fbdb2206 100644
--- a/Documentation/bpf/instruction-set.rst
+++ b/Documentation/bpf/instruction-set.rst
@@ -127,7 +127,7 @@ BPF_XOR | BPF_K | BPF_ALU64 means::
 Byte swap instructions
 ----------------------
 
-The byte swap instructions use an instruction class of ``BFP_ALU`` and a 4-bit
+The byte swap instructions use an instruction class of ``BPF_ALU`` and a 4-bit
 code field of ``BPF_END``.
 
 The byte swap instructions operate on the destination register
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 9e457156ad4d..6a1c9fca5260 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -712,22 +712,6 @@ static inline void emit_alu_r(const u8 dst, const u8 src, const bool is64,
 	}
 }
 
-/* ALU operation (32 bit)
- * dst = dst (op) src
- */
-static inline void emit_a32_alu_r(const s8 dst, const s8 src,
-				  struct jit_ctx *ctx, const bool is64,
-				  const bool hi, const u8 op) {
-	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rn, rd;
-
-	rn = arm_bpf_get_reg32(src, tmp[1], ctx);
-	rd = arm_bpf_get_reg32(dst, tmp[0], ctx);
-	/* ALU operation */
-	emit_alu_r(rd, rn, is64, hi, op, ctx);
-	arm_bpf_put_reg32(dst, rd, ctx);
-}
-
 /* ALU operation (64 bit) */
 static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 				  const s8 src[], struct jit_ctx *ctx,
diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 2a3715bf29fe..d926e0f7ef57 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -69,6 +69,7 @@ struct rv_jit_context {
 	struct bpf_prog *prog;
 	u16 *insns;		/* RV insns */
 	int ninsns;
+	int body_len;
 	int epilogue_offset;
 	int *offset;		/* BPF to RV */
 	int nexentries;
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index be743d700aa7..737baf8715da 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -44,7 +44,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	unsigned int prog_size = 0, extable_size = 0;
 	bool tmp_blinded = false, extra_pass = false;
 	struct bpf_prog *tmp, *orig_prog = prog;
-	int pass = 0, prev_ninsns = 0, i;
+	int pass = 0, prev_ninsns = 0, prologue_len, i;
 	struct rv_jit_data *jit_data;
 	struct rv_jit_context *ctx;
 
@@ -95,6 +95,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 			prog = orig_prog;
 			goto out_offset;
 		}
+		ctx->body_len = ctx->ninsns;
 		bpf_jit_build_prologue(ctx);
 		ctx->epilogue_offset = ctx->ninsns;
 		bpf_jit_build_epilogue(ctx);
@@ -161,6 +162,11 @@ skip_init_ctx:
 
 	if (!prog->is_func || extra_pass) {
 		bpf_jit_binary_lock_ro(jit_data->header);
+		prologue_len = ctx->epilogue_offset - ctx->body_len;
+		for (i = 0; i < prog->len; i++)
+			ctx->offset[i] = ninsns_rvoff(prologue_len +
+						      ctx->offset[i]);
+		bpf_prog_fill_jited_linfo(prog, ctx->offset);
 out_offset:
 		kfree(ctx->offset);
 		kfree(jit_data);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2b914a56a2c5..0edd7d2c0064 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -5,6 +5,7 @@
 #define _LINUX_BPF_H 1
 
 #include <uapi/linux/bpf.h>
+#include <uapi/linux/filter.h>
 
 #include <linux/workqueue.h>
 #include <linux/file.h>
@@ -22,8 +23,10 @@
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
+#include <linux/stddef.h>
 #include <linux/bpfptr.h>
 #include <linux/btf.h>
+#include <linux/rcupdate_trace.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -398,6 +401,9 @@ enum bpf_type_flag {
 	/* DYNPTR points to a ringbuf record. */
 	DYNPTR_TYPE_RINGBUF	= BIT(9 + BPF_BASE_TYPE_BITS),
 
+	/* Size is known at compile time. */
+	MEM_FIXED_SIZE		= BIT(10 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -461,6 +467,8 @@ enum bpf_arg_type {
 	 * all bytes or clear them in error case.
 	 */
 	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | ARG_PTR_TO_MEM,
+	/* Pointer to valid memory of size known at compile time. */
+	ARG_PTR_TO_FIXED_SIZE_MEM	= MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
@@ -526,6 +534,14 @@ struct bpf_func_proto {
 			u32 *arg5_btf_id;
 		};
 		u32 *arg_btf_id[5];
+		struct {
+			size_t arg1_size;
+			size_t arg2_size;
+			size_t arg3_size;
+			size_t arg4_size;
+			size_t arg5_size;
+		};
+		size_t arg_size[5];
 	};
 	int *ret_btf_id; /* return value btf_id */
 	bool (*allowed)(const struct bpf_prog *prog);
@@ -1084,6 +1100,40 @@ struct bpf_prog_aux {
 	};
 };
 
+struct bpf_prog {
+	u16			pages;		/* Number of allocated pages */
+	u16			jited:1,	/* Is our filter JIT'ed? */
+				jit_requested:1,/* archs need to JIT the prog */
+				gpl_compatible:1, /* Is filter GPL compatible? */
+				cb_access:1,	/* Is control block accessed? */
+				dst_needed:1,	/* Do we need dst entry? */
+				blin