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

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-05-13

We've added 119 non-merge commits during the last 14 day(s) which contain
a total of 134 files changed, 9462 insertions(+), 4742 deletions(-).

The main changes are:

1) Add BPF JIT support for 32-bit ARCv2 processors, from Shahab Vahedi.

2) Add BPF range computation improvements to the verifier in particular
   around XOR and OR operators, refactoring of checks for range computation
   and relaxing MUL range computation so that src_reg can also be an unknown
   scalar, from Cupertino Miranda.

3) Add support to attach kprobe BPF programs through kprobe_multi link in
   a session mode, meaning, a BPF program is attached to both function entry
   and return, the entry program can decide if the return program gets
   executed and the entry program can share u64 cookie value with return
   program. Session mode is a common use-case for tetragon and bpftrace,
   from Jiri Olsa.

4) Fix a potential overflow in libbpf's ring__consume_n() and improve libbpf
   as well as BPF selftest's struct_ops handling, from Andrii Nakryiko.

5) Improvements to BPF selftests in context of BPF gcc backend,
   from Jose E. Marchesi & David Faust.

6) Migrate remaining BPF selftest tests from test_sock_addr.c to prog_test-
   -style in order to retire the old test, run it in BPF CI and additionally
   expand test coverage, from Jordan Rife.

7) Big batch for BPF selftest refactoring in order to remove duplicate code
   around common network helpers, from Geliang Tang.

8) Another batch of improvements to BPF selftests to retire obsolete
   bpf_tcp_helpers.h as everything is available vmlinux.h,
   from Martin KaFai Lau.

9) Fix BPF map tear-down to not walk the map twice on free when both timer
   and wq is used, from Benjamin Tissoires.

10) Fix BPF verifier assumptions about socket->sk that it can be non-NULL,
    from Alexei Starovoitov.

11) Change BTF build scripts to using --btf_features for pahole v1.26+,
    from Alan Maguire.

12) Small improvements to BPF reusing struct_size() and krealloc_array(),
    from Andy Shevchenko.

13) Fix s390 JIT to emit a barrier for BPF_FETCH instructions,
    from Ilya Leoshkevich.

14) Extend TCP ->cong_control() callback in order to feed in ack and
    flag parameters and allow write-access to tp->snd_cwnd_stamp
    from BPF program, from Miao Xu.

15) Add support for internal-only per-CPU instructions to inline
    bpf_get_smp_processor_id() helper call for arm64 and riscv64 BPF JITs,
    from Puranjay Mohan.

16) Follow-up to remove the redundant ethtool.h from tooling infrastructure,
    from Tushar Vyavahare.

17) Extend libbpf to support "module:<function>" syntax for tracing
    programs, from Viktor Malik.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (119 commits)
  bpf: make list_for_each_entry portable
  bpf: ignore expected GCC warning in test_global_func10.c
  bpf: disable strict aliasing in test_global_func9.c
  selftests/bpf: Free strdup memory in xdp_hw_metadata
  selftests/bpf: Fix a few tests for GCC related warnings.
  bpf: avoid gcc overflow warning in test_xdp_vlan.c
  tools: remove redundant ethtool.h from tooling infra
  selftests/bpf: Expand ATTACH_REJECT tests
  selftests/bpf: Expand getsockname and getpeername tests
  sefltests/bpf: Expand sockaddr hook deny tests
  selftests/bpf: Expand sockaddr program return value tests
  selftests/bpf: Retire test_sock_addr.(c|sh)
  selftests/bpf: Remove redundant sendmsg test cases
  selftests/bpf: Migrate ATTACH_REJECT test cases
  selftests/bpf: Migrate expected_attach_type tests
  selftests/bpf: Migrate wildcard destination rewrite test
  selftests/bpf: Migrate sendmsg6 v4 mapped address tests
  selftests/bpf: Migrate sendmsg deny test cases
  selftests/bpf: Migrate WILDCARD_IP test
  selftests/bpf: Handle SYSCALL_EPERM and SYSCALL_ENOTSUPP test cases
  ...
====================

Link: https://lore.kernel.org/r/20240513134114.17575-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 62 insertions, 12 deletions

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 5fc374ed98ea..fdbf88ca8b70 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -608,7 +608,7 @@ static inline u32 rv_nop(void)
 	return rv_i_insn(0, 0, 0, 0, 0x13);
 }
 
-/* RVC instrutions. */
+/* RVC instructions. */
 
 static inline u16 rvc_addi4spn(u8 rd, u32 imm10)
 {
@@ -737,7 +737,7 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
 	return rv_css_insn(0x6, imm, rs2, 0x2);
 }
 
-/* RVZBB instrutions. */
+/* RVZBB instructions. */
 static inline u32 rvzbb_sextb(u8 rd, u8 rs1)
 {
 	return rv_i_insn(0x604, rs1, 1, rd, 0x13);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index e713704be837..79a001d5533e 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -12,6 +12,7 @@
 #include <linux/stop_machine.h>
 #include <asm/patch.h>
 #include <asm/cfi.h>
+#include <asm/percpu.h>
 #include "bpf_jit.h"
 
 #define RV_FENTRY_NINSNS 2
@@ -503,33 +504,33 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
 		break;
 	/* src_reg = atomic_fetch_<op>(dst_reg + off16, src_reg) */
 	case BPF_ADD | BPF_FETCH:
-		emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) :
-		     rv_amoadd_w(rs, rs, rd, 0, 0), ctx);
+		emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) :
+		     rv_amoadd_w(rs, rs, rd, 1, 1), ctx);
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_AND | BPF_FETCH:
-		emit(is64 ? rv_amoand_d(rs, rs, rd, 0, 0) :
-		     rv_amoand_w(rs, rs, rd, 0, 0), ctx);
+		emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) :
+		     rv_amoand_w(rs, rs, rd, 1, 1), ctx);
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_OR | BPF_FETCH:
-		emit(is64 ? rv_amoor_d(rs, rs, rd, 0, 0) :
-		     rv_amoor_w(rs, rs, rd, 0, 0), ctx);
+		emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) :
+		     rv_amoor_w(rs, rs, rd, 1, 1), ctx);
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_XOR | BPF_FETCH:
-		emit(is64 ? rv_amoxor_d(rs, rs, rd, 0, 0) :
-		     rv_amoxor_w(rs, rs, rd, 0, 0), ctx);
+		emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) :
+		     rv_amoxor_w(rs, rs, rd, 1, 1), ctx);
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	/* src_reg = atomic_xchg(dst_reg + off16, src_reg); */
 	case BPF_XCHG:
-		emit(is64 ? rv_amoswap_d(rs, rs, rd, 0, 0) :
-		     rv_amoswap_w(rs, rs, rd, 0, 0), ctx);
+		emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) :
+		     rv_amoswap_w(rs, rs, rd, 1, 1), ctx);
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
@@ -1089,6 +1090,24 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_or(RV_REG_T1, rd, RV_REG_T1, ctx);
 			emit_mv(rd, RV_REG_T1, ctx);
 			break;
+		} else if (insn_is_mov_percpu_addr(insn)) {
+			if (rd != rs)
+				emit_mv(rd, rs, ctx);
+#ifdef CONFIG_SMP
+			/* Load current CPU number in T1 */
+			emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
+				RV_REG_TP, ctx);
+			/* << 3 because offsets are 8 bytes */
+			emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
+			/* Load address of __per_cpu_offset array in T2 */
+			emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
+			/* Add offset of current CPU to  __per_cpu_offset */
+			emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
+			/* Load __per_cpu_offset[cpu] in T1 */
+			emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
+			/* Add the offset to Rd */
+			emit_add(rd, rd, RV_REG_T1, ctx);
+#endif
 		}
 		if (imm == 1) {
 			/* Special mov32 for zext */
@@ -1474,6 +1493,22 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		bool fixed_addr;
 		u64 addr;
 
+		/* Inline calls to bpf_get_smp_processor_id()
+		 *
+		 * RV_REG_TP holds the address of the current CPU's task_struct and thread_info is
+		 * at offset 0 in task_struct.
+		 * Load cpu from thread_info:
+		 *     Set R0 to ((struct thread_info *)(RV_REG_TP))->cpu
+		 *
+		 * This replicates the implementation of raw_smp_processor_id() on RISCV
+		 */
+		if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
+			/* Load current CPU number in R0 */
+			emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu),
+				RV_REG_TP, ctx);
+			break;
+		}
+
 		mark_call(ctx);
 		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
 					    &addr, &fixed_addr);
@@ -2038,3 +2073,18 @@ bool bpf_jit_supports_arena(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_percpu_insn(void)
+{
+	return true;
+}
+
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+	switch (imm) {
+	case BPF_FUNC_get_smp_processor_id:
+		return true;
+	default:
+		return false;
+	}
+}