diff mbox series

[bpf-next,v3,09/12] s390/bpf: Support arena atomics

Message ID 20240701234304.14336-10-iii@linux.ibm.com (mailing list archive)
State Accepted
Commit 2f9469484a3b52c66b799de73bd1ca75617bc8d5
Delegated to: BPF
Headers show
Series s390/bpf: Implement arena | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 8 this patch: 8
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 12 maintainers not CCed: yonghong.song@linux.dev svens@linux.ibm.com haoluo@google.com linux-s390@vger.kernel.org jolsa@kernel.org song@kernel.org john.fastabend@gmail.com eddyz87@gmail.com kpsingh@kernel.org martin.lau@linux.dev sdf@google.com borntraeger@linux.ibm.com
netdev/build_clang success Errors and warnings before: 8 this patch: 8
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 8 this patch: 8
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 158 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-7 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-8 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 fail Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / veristat

Commit Message

Ilya Leoshkevich July 1, 2024, 11:40 p.m. UTC
s390x supports most BPF atomics using single instructions, which
makes implementing arena support a matter of adding arena address to
the base register (unfortunately atomics do not support index
registers), and wrapping the respective native instruction in probing
sequences.

An exception is BPF_XCHG, which is implemented using two different
memory accesses and a loop. Make sure there is enough extable entries
for both instructions. Compute the base address once for both memory
accesses. Since on exception we need to land after the loop, emit the
nops manually.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
---
 arch/s390/net/bpf_jit_comp.c | 104 +++++++++++++++++++++++++++++++----
 1 file changed, 94 insertions(+), 10 deletions(-)
diff mbox series

Patch

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 1dd359c25ada..ddfc0e99872e 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -704,6 +704,10 @@  static void bpf_jit_probe_init(struct bpf_jit_probe *probe)
 static void bpf_jit_probe_emit_nop(struct bpf_jit *jit,
 				   struct bpf_jit_probe *probe)
 {
+	if (probe->prg == -1 || probe->nop_prg != -1)
+		/* The probe is not armed or nop is already emitted. */
+		return;
+
 	probe->nop_prg = jit->prg;
 	/* bcr 0,%0 */
 	_EMIT2(0x0700);
@@ -738,6 +742,21 @@  static void bpf_jit_probe_store_pre(struct bpf_jit *jit, struct bpf_insn *insn,
 	probe->prg = jit->prg;
 }
 
+static void bpf_jit_probe_atomic_pre(struct bpf_jit *jit,
+				     struct bpf_insn *insn,
+				     struct bpf_jit_probe *probe)
+{
+	if (BPF_MODE(insn->code) != BPF_PROBE_ATOMIC)
+		return;
+
+	/* lgrl %r1,kern_arena */
+	EMIT6_PCREL_RILB(0xc4080000, REG_W1, jit->kern_arena);
+	/* agr %r1,%dst */
+	EMIT4(0xb9080000, REG_W1, insn->dst_reg);
+	probe->arena_reg = REG_W1;
+	probe->prg = jit->prg;
+}
+
 static int bpf_jit_probe_post(struct bpf_jit *jit, struct bpf_prog *fp,
 			      struct bpf_jit_probe *probe)
 {
@@ -1523,15 +1542,30 @@  static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 	 */
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
 	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
 	{
 		bool is32 = BPF_SIZE(insn->code) == BPF_W;
 
+		/*
+		 * Unlike loads and stores, atomics have only a base register,
+		 * but no index register. For the non-arena case, simply use
+		 * %dst as a base. For the arena case, use the work register
+		 * %r1: first, load the arena base into it, and then add %dst
+		 * to it.
+		 */
+		probe.arena_reg = dst_reg;
+
 		switch (insn->imm) {
-/* {op32|op64} {%w0|%src},%src,off(%dst) */
 #define EMIT_ATOMIC(op32, op64) do {					\
+	bpf_jit_probe_atomic_pre(jit, insn, &probe);			\
+	/* {op32|op64} {%w0|%src},%src,off(%arena) */			\
 	EMIT6_DISP_LH(0xeb000000, is32 ? (op32) : (op64),		\
 		      (insn->imm & BPF_FETCH) ? src_reg : REG_W0,	\
-		      src_reg, dst_reg, off);				\
+		      src_reg, probe.arena_reg, off);			\
+	err = bpf_jit_probe_post(jit, fp, &probe);			\
+	if (err < 0)							\
+		return err;						\
 	if (insn->imm & BPF_FETCH) {					\
 		/* bcr 14,0 - see atomic_fetch_{add,and,or,xor}() */	\
 		_EMIT2(0x07e0);						\
@@ -1560,25 +1594,50 @@  static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 			EMIT_ATOMIC(0x00f7, 0x00e7);
 			break;
 #undef EMIT_ATOMIC
-		case BPF_XCHG:
-			/* {ly|lg} %w0,off(%dst) */
+		case BPF_XCHG: {
+			struct bpf_jit_probe load_probe = probe;
+			int loop_start;
+
+			bpf_jit_probe_atomic_pre(jit, insn, &load_probe);
+			/* {ly|lg} %w0,off(%arena) */
 			EMIT6_DISP_LH(0xe3000000,
 				      is32 ? 0x0058 : 0x0004, REG_W0, REG_0,
-				      dst_reg, off);
-			/* 0: {csy|csg} %w0,%src,off(%dst) */
+				      load_probe.arena_reg, off);
+			bpf_jit_probe_emit_nop(jit, &load_probe);
+			/* Reuse {ly|lg}'s arena_reg for {csy|csg}. */
+			if (load_probe.prg != -1) {
+				probe.prg = jit->prg;
+				probe.arena_reg = load_probe.arena_reg;
+			}
+			loop_start = jit->prg;
+			/* 0: {csy|csg} %w0,%src,off(%arena) */
 			EMIT6_DISP_LH(0xeb000000, is32 ? 0x0014 : 0x0030,
-				      REG_W0, src_reg, dst_reg, off);
+				      REG_W0, src_reg, probe.arena_reg, off);
+			bpf_jit_probe_emit_nop(jit, &probe);
 			/* brc 4,0b */
-			EMIT4_PCREL_RIC(0xa7040000, 4, jit->prg - 6);
+			EMIT4_PCREL_RIC(0xa7040000, 4, loop_start);
 			/* {llgfr|lgr} %src,%w0 */
 			EMIT4(is32 ? 0xb9160000 : 0xb9040000, src_reg, REG_W0);
+			/* Both probes should land here on exception. */
+			err = bpf_jit_probe_post(jit, fp, &load_probe);
+			if (err < 0)
+				return err;
+			err = bpf_jit_probe_post(jit, fp, &probe);
+			if (err < 0)
+				return err;
 			if (is32 && insn_is_zext(&insn[1]))
 				insn_count = 2;
 			break;
+		}
 		case BPF_CMPXCHG:
-			/* 0: {csy|csg} %b0,%src,off(%dst) */
+			bpf_jit_probe_atomic_pre(jit, insn, &probe);
+			/* 0: {csy|csg} %b0,%src,off(%arena) */
 			EMIT6_DISP_LH(0xeb000000, is32 ? 0x0014 : 0x0030,
-				      BPF_REG_0, src_reg, dst_reg, off);
+				      BPF_REG_0, src_reg,
+				      probe.arena_reg, off);
+			err = bpf_jit_probe_post(jit, fp, &probe);
+			if (err < 0)
+				return err;
 			break;
 		default:
 			pr_err("Unknown atomic operation %02x\n", insn->imm);
@@ -2142,9 +2201,25 @@  static struct bpf_binary_header *bpf_jit_alloc(struct bpf_jit *jit,
 					       struct bpf_prog *fp)
 {
 	struct bpf_binary_header *header;
+	struct bpf_insn *insn;
 	u32 extable_size;
 	u32 code_size;
+	int i;
 
+	for (i = 0; i < fp->len; i++) {
+		insn = &fp->insnsi[i];
+
+		if (BPF_CLASS(insn->code) == BPF_STX &&
+		    BPF_MODE(insn->code) == BPF_PROBE_ATOMIC &&
+		    (BPF_SIZE(insn->code) == BPF_DW ||
+		     BPF_SIZE(insn->code) == BPF_W) &&
+		    insn->imm == BPF_XCHG)
+			/*
+			 * bpf_jit_insn() emits a load and a compare-and-swap,
+			 * both of which need to be probed.
+			 */
+			fp->aux->num_exentries += 1;
+	}
 	/* We need two entries per insn. */
 	fp->aux->num_exentries *= 2;
 
@@ -2825,3 +2900,12 @@  bool bpf_jit_supports_arena(void)
 {
 	return true;
 }
+
+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.
+	 */
+	return true;
+}