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

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-04-29

We've added 147 non-merge commits during the last 32 day(s) which contain
a total of 158 files changed, 9400 insertions(+), 2213 deletions(-).

The main changes are:

1) Add an internal-only BPF per-CPU instruction for resolving per-CPU
   memory addresses and implement support in x86 BPF JIT. This allows
   inlining per-CPU array and hashmap lookups
   and the bpf_get_smp_processor_id() helper, from Andrii Nakryiko.

2) Add BPF link support for sk_msg and sk_skb programs, from Yonghong Song.

3) Optimize x86 BPF JIT's emit_mov_imm64, and add support for various
   atomics in bpf_arena which can be JITed as a single x86 instruction,
   from Alexei Starovoitov.

4) Add support for passing mark with bpf_fib_lookup helper,
   from Anton Protopopov.

5) Add a new bpf_wq API for deferring events and refactor sleepable
   bpf_timer code to keep common code where possible,
   from Benjamin Tissoires.

6) Fix BPF_PROG_TEST_RUN infra with regards to bpf_dummy_struct_ops programs
   to check when NULL is passed for non-NULLable parameters,
   from Eduard Zingerman.

7) Harden the BPF verifier's and/or/xor value tracking,
   from Harishankar Vishwanathan.

8) Introduce crypto kfuncs to make BPF programs able to utilize the kernel
   crypto subsystem, from Vadim Fedorenko.

9) Various improvements to the BPF instruction set standardization doc,
   from Dave Thaler.

10) Extend libbpf APIs to partially consume items from the BPF ringbuffer,
    from Andrea Righi.

11) Bigger batch of BPF selftests refactoring to use common network helpers
    and to drop duplicate code, from Geliang Tang.

12) Support bpf_tail_call_static() helper for BPF programs with GCC 13,
    from Jose E. Marchesi.

13) Add bpf_preempt_{disable,enable}() kfuncs in order to allow a BPF
    program to have code sections where preemption is disabled,
    from Kumar Kartikeya Dwivedi.

14) Allow invoking BPF kfuncs from BPF_PROG_TYPE_SYSCALL programs,
    from David Vernet.

15) Extend the BPF verifier to allow different input maps for a given
    bpf_for_each_map_elem() helper call in a BPF program, from Philo Lu.

16) Add support for PROBE_MEM32 and bpf_addr_space_cast instructions
    for riscv64 and arm64 JITs to enable BPF Arena, from Puranjay Mohan.

17) Shut up a false-positive KMSAN splat in interpreter mode by unpoison
    the stack memory, from Martin KaFai Lau.

18) Improve xsk selftest coverage with new tests on maximum and minimum
    hardware ring size configurations, from Tushar Vyavahare.

19) Various ReST man pages fixes as well as documentation and bash completion
    improvements for bpftool, from Rameez Rehman & Quentin Monnet.

20) Fix libbpf with regards to dumping subsequent char arrays,
    from Quentin Deslandes.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (147 commits)
  bpf, docs: Clarify PC use in instruction-set.rst
  bpf_helpers.h: Define bpf_tail_call_static when building with GCC
  bpf, docs: Add introduction for use in the ISA Internet Draft
  selftests/bpf: extend BPF_SOCK_OPS_RTT_CB test for srtt and mrtt_us
  bpf: add mrtt and srtt as BPF_SOCK_OPS_RTT_CB args
  selftests/bpf: dummy_st_ops should reject 0 for non-nullable params
  bpf: check bpf_dummy_struct_ops program params for test runs
  selftests/bpf: do not pass NULL for non-nullable params in dummy_st_ops
  selftests/bpf: adjust dummy_st_ops_success to detect additional error
  bpf: mark bpf_dummy_struct_ops.test_1 parameter as nullable
  selftests/bpf: Add ring_buffer__consume_n test.
  bpf: Add bpf_guard_preempt() convenience macro
  selftests: bpf: crypto: add benchmark for crypto functions
  selftests: bpf: crypto skcipher algo selftests
  bpf: crypto: add skcipher to bpf crypto
  bpf: make common crypto API for TC/XDP programs
  bpf: update the comment for BTF_FIELDS_MAX
  selftests/bpf: Fix wq test.
  selftests/bpf: Use make_sockaddr in test_sock_addr
  selftests/bpf: Use connect_to_addr in test_sock_addr
  ...
====================

Link: https://lore.kernel.org/r/20240429131657.19423-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 91 insertions, 1 deletions

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 788a3d6f6276..ff217cc35ce9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -816,9 +816,10 @@ done:
 static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
 			   const u32 imm32_hi, const u32 imm32_lo)
 {
+	u64 imm64 = ((u64)imm32_hi << 32) | (u32)imm32_lo;
 	u8 *prog = *pprog;
 
-	if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
+	if (is_uimm32(imm64)) {
 		/*
 		 * For emitting plain u32, where sign bit must not be
 		 * propagated LLVM tends to load imm64 over mov32
@@ -826,6 +827,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
 		 * 'mov %eax, imm32' instead.
 		 */
 		emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
+	} else if (is_simm32(imm64)) {
+		emit_mov_imm32(&prog, true, dst_reg, imm32_lo);
 	} else {
 		/* movabsq rax, imm64 */
 		EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
@@ -1169,6 +1172,54 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
 	return 0;
 }
 
+static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
+			     u32 dst_reg, u32 src_reg, u32 index_reg, int off)
+{
+	u8 *prog = *pprog;
+
+	EMIT1(0xF0); /* lock prefix */
+	switch (size) {
+	case BPF_W:
+		EMIT1(add_3mod(0x40, dst_reg, src_reg, index_reg));
+		break;
+	case BPF_DW:
+		EMIT1(add_3mod(0x48, dst_reg, src_reg, index_reg));
+		break;
+	default:
+		pr_err("bpf_jit: 1 and 2 byte atomics are not supported\n");
+		return -EFAULT;
+	}
+
+	/* emit opcode */
+	switch (atomic_op) {
+	case BPF_ADD:
+	case BPF_AND:
+	case BPF_OR:
+	case BPF_XOR:
+		/* lock *(u32/u64*)(dst_reg + idx_reg + off) <op>= src_reg */
+		EMIT1(simple_alu_opcodes[atomic_op]);
+		break;
+	case BPF_ADD | BPF_FETCH:
+		/* src_reg = atomic_fetch_add(dst_reg + idx_reg + off, src_reg); */
+		EMIT2(0x0F, 0xC1);
+		break;
+	case BPF_XCHG:
+		/* src_reg = atomic_xchg(dst_reg + idx_reg + off, src_reg); */
+		EMIT1(0x87);
+		break;
+	case BPF_CMPXCHG:
+		/* r0 = atomic_cmpxchg(dst_reg + idx_reg + off, r0, src_reg); */
+		EMIT2(0x0F, 0xB1);
+		break;
+	default:
+		pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op);
+		return -EFAULT;
+	}
+	emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off);
+	*pprog = prog;
+	return 0;
+}
+
 #define DONT_CLEAR 1
 
 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
@@ -1382,6 +1433,16 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 				maybe_emit_mod(&prog, AUX_REG, dst_reg, true);
 				EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg));
 				break;
+			} else if (insn_is_mov_percpu_addr(insn)) {
+				/* mov <dst>, <src> (if necessary) */
+				EMIT_mov(dst_reg, src_reg);
+#ifdef CONFIG_SMP
+				/* add <dst>, gs:[<off>] */
+				EMIT2(0x65, add_1mod(0x48, dst_reg));
+				EMIT3(0x03, add_2reg(0x04, 0, dst_reg), 0x25);
+				EMIT((u32)(unsigned long)&this_cpu_off, 4);
+#endif
+				break;
 			}
 			fallthrough;
 		case BPF_ALU | BPF_MOV | BPF_X:
@@ -1969,6 +2030,15 @@ populate_extable:
 				return err;
 			break;
 
+		case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
+		case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
+			start_of_ldx = prog;
+			err = emit_atomic_index(&prog, insn->imm, BPF_SIZE(insn->code),
+						dst_reg, src_reg, X86_REG_R12, insn->off);
+			if (err)
+				return err;
+			goto populate_extable;
+
 			/* call */
 		case BPF_JMP | BPF_CALL: {
 			u8 *ip = image + addrs[i - 1];
@@ -3362,6 +3432,11 @@ bool bpf_jit_supports_subprog_tailcalls(void)
 	return true;
 }
 
+bool bpf_jit_supports_percpu_insn(void)
+{
+	return true;
+}
+
 void bpf_jit_free(struct bpf_prog *prog)
 {
 	if (prog->jited) {
@@ -3465,6 +3540,21 @@ bool bpf_jit_supports_arena(void)
 	return true;
 }
 
+bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
+{
+	if (!in_arena)
+		return true;
+	switch (insn->code) {
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (insn->imm == (BPF_AND | BPF_FETCH) ||
+		    insn->imm == (BPF_OR | BPF_FETCH) ||
+		    insn->imm == (BPF_XOR | BPF_FETCH))
+			return false;
+	}
+	return true;
+}
+
 bool bpf_jit_supports_ptr_xchg(void)
 {
 	return true;