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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-04-27

We've added 85 non-merge commits during the last 18 day(s) which contain
a total of 163 files changed, 4499 insertions(+), 1521 deletions(-).

The main changes are:

1) Teach libbpf to enhance BPF verifier log with human-readable and relevant
   information about failed CO-RE relocations, from Andrii Nakryiko.

2) Add typed pointer support in BPF maps and enable it for unreferenced pointers
   (via probe read) and referenced ones that can be passed to in-kernel helpers,
   from Kumar Kartikeya Dwivedi.

3) Improve xsk to break NAPI loop when rx queue gets full to allow for forward
   progress to consume descriptors, from Maciej Fijalkowski & Björn Töpel.

4) Fix a small RCU read-side race in BPF_PROG_RUN routines which dereferenced
   the effective prog array before the rcu_read_lock, from Stanislav Fomichev.

5) Implement BPF atomic operations for RV64 JIT, and add libbpf parsing logic
   for USDT arguments under riscv{32,64}, from Pu Lehui.

6) Implement libbpf parsing of USDT arguments under aarch64, from Alan Maguire.

7) Enable bpftool build for musl and remove nftw with FTW_ACTIONRETVAL usage
   so it can be shipped under Alpine which is musl-based, from Dominique Martinet.

8) Clean up {sk,task,inode} local storage trace RCU handling as they do not
   need to use call_rcu_tasks_trace() barrier, from KP Singh.

9) Improve libbpf API documentation and fix error return handling of various
   API functions, from Grant Seltzer.

10) Enlarge offset check for bpf_skb_{load,store}_bytes() helpers given data
    length of frags + frag_list may surpass old offset limit, from Liu Jian.

11) Various improvements to prog_tests in area of logging, test execution
    and by-name subtest selection, from Mykola Lysenko.

12) Simplify map_btf_id generation for all map types by moving this process
    to build time with help of resolve_btfids infra, from Menglong Dong.

13) Fix a libbpf bug in probing when falling back to legacy bpf_probe_read*()
    helpers; the probing caused always to use old helpers, from Runqing Yang.

14) Add support for ARCompact and ARCv2 platforms for libbpf's PT_REGS
    tracing macros, from Vladimir Isaev.

15) Cleanup BPF selftests to remove old & unneeded rlimit code given kernel
    switched to memcg-based memory accouting a while ago, from Yafang Shao.

16) Refactor of BPF sysctl handlers to move them to BPF core, from Yan Zhu.

17) Fix BPF selftests in two occasions to work around regressions caused by latest
    LLVM to unblock CI until their fixes are worked out, from Yonghong Song.

18) Misc cleanups all over the place, from various others.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (85 commits)
  selftests/bpf: Add libbpf's log fixup logic selftests
  libbpf: Fix up verifier log for unguarded failed CO-RE relos
  libbpf: Simplify bpf_core_parse_spec() signature
  libbpf: Refactor CO-RE relo human description formatting routine
  libbpf: Record subprog-resolved CO-RE relocations unconditionally
  selftests/bpf: Add CO-RE relos and SEC("?...") to linked_funcs selftests
  libbpf: Avoid joining .BTF.ext data with BPF programs by section name
  libbpf: Fix logic for finding matching program for CO-RE relocation
  libbpf: Drop unhelpful "program too large" guess
  libbpf: Fix anonymous type check in CO-RE logic
  bpf: Compute map_btf_id during build time
  selftests/bpf: Add test for strict BTF type check
  selftests/bpf: Add verifier tests for kptr
  selftests/bpf: Add C tests for kptr
  libbpf: Add kptr type tag macros to bpf_helpers.h
  bpf: Make BTF type match stricter for release arguments
  bpf: Teach verifier about kptr_get kfunc helpers
  bpf: Wire up freeing of referenced kptr
  bpf: Populate pairs of btf_id and destructor kfunc in btf
  bpf: Adapt copy_map_value for multiple offset case
  ...
====================

Link: https://lore.kernel.org/r/20220427224758.20976-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 153 insertions, 24 deletions

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index f42d9cd3b64d..2a3715bf29fe 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -535,6 +535,43 @@ static inline u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
 	return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f);
 }
 
+static inline u32 rv_amoand_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0xc, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_amoor_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x8, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_amoxor_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x4, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_amoswap_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x1, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_lr_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x2, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_sc_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x3, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_fence(u8 pred, u8 succ)
+{
+	u16 imm11_0 = pred << 4 | succ;
+
+	return rv_i_insn(imm11_0, 0, 0, 0, 0xf);
+}
+
 /* RVC instrutions. */
 
 static inline u16 rvc_addi4spn(u8 rd, u32 imm10)
@@ -753,6 +790,36 @@ static inline u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
 	return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f);
 }
 
+static inline u32 rv_amoand_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0xc, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_amoor_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x8, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_amoxor_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x4, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_amoswap_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x1, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_lr_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x2, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_sc_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x3, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
 /* RV64-only RVC instructions. */
 
 static inline u16 rvc_ld(u8 rd, u32 imm8, u8 rs1)
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 0bcda99d1d68..00df3a8f92ac 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -455,6 +455,90 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
 	return 0;
 }
 
+static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
+			struct rv_jit_context *ctx)
+{
+	u8 r0;
+	int jmp_offset;
+
+	if (off) {
+		if (is_12b_int(off)) {
+			emit_addi(RV_REG_T1, rd, off, ctx);
+		} else {
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		}
+		rd = RV_REG_T1;
+	}
+
+	switch (imm) {
+	/* lock *(u32/u64 *)(dst_reg + off16) <op>= src_reg */
+	case BPF_ADD:
+		emit(is64 ? rv_amoadd_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoadd_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		break;
+	case BPF_AND:
+		emit(is64 ? rv_amoand_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoand_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		break;
+	case BPF_OR:
+		emit(is64 ? rv_amoor_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		break;
+	case BPF_XOR:
+		emit(is64 ? rv_amoxor_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoxor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		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);
+		if (!is64)
+			emit_zext_32(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);
+		if (!is64)
+			emit_zext_32(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);
+		if (!is64)
+			emit_zext_32(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);
+		if (!is64)
+			emit_zext_32(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);
+		if (!is64)
+			emit_zext_32(rs, ctx);
+		break;
+	/* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */
+	case BPF_CMPXCHG:
+		r0 = bpf_to_rv_reg(BPF_REG_0, ctx);
+		emit(is64 ? rv_addi(RV_REG_T2, r0, 0) :
+		     rv_addiw(RV_REG_T2, r0, 0), ctx);
+		emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) :
+		     rv_lr_w(r0, 0, rd, 0, 0), ctx);
+		jmp_offset = ninsns_rvoff(8);
+		emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx);
+		emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 0) :
+		     rv_sc_w(RV_REG_T3, rs, rd, 0, 0), ctx);
+		jmp_offset = ninsns_rvoff(-6);
+		emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx);
+		emit(rv_fence(0x3, 0x3), ctx);
+		break;
+	}
+}
+
 #define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
 #define BPF_FIXUP_REG_MASK      GENMASK(31, 27)
 
@@ -1146,30 +1230,8 @@ out_be:
 		break;
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		if (insn->imm != BPF_ADD) {
-			pr_err("bpf-jit: not supported: atomic operation %02x ***\n",
-			       insn->imm);
-			return -EINVAL;
-		}
-
-		/* atomic_add: lock *(u32 *)(dst + off) += src
-		 * atomic_add: lock *(u64 *)(dst + off) += src
-		 */
-
-		if (off) {
-			if (is_12b_int(off)) {
-				emit_addi(RV_REG_T1, rd, off, ctx);
-			} else {
-				emit_imm(RV_REG_T1, off, ctx);
-				emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-			}
-
-			rd = RV_REG_T1;
-		}
-
-		emit(BPF_SIZE(code) == BPF_W ?
-		     rv_amoadd_w(RV_REG_ZERO, rs, rd, 0, 0) :
-		     rv_amoadd_d(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		emit_atomic(rd, rs, off, imm,
+			    BPF_SIZE(code) == BPF_DW, ctx);
 		break;
 	default:
 		pr_err("bpf-jit: unknown opcode %02x\n", code);