diff mbox series

[bpf-next,2/2] bpf, riscv: use prog pack allocator in the BPF JIT

Message ID 20230720154941.1504-3-puranjay12@gmail.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series bpf, riscv: use BPF prog pack allocator in BPF JIT | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
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: 9 this patch: 9
netdev/cc_maintainers warning 6 maintainers not CCed: xi.wang@gmail.com luke.r.nels@gmail.com john.fastabend@gmail.com sdf@google.com jolsa@kernel.org haoluo@google.com
netdev/build_clang success Errors and warnings before: 9 this patch: 9
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: 9 this patch: 9
netdev/checkpatch warning WARNING: line length of 92 exceeds 80 columns WARNING: line length of 94 exceeds 80 columns WARNING: line length of 96 exceeds 80 columns
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-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-4 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-5 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-6 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-18 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-19 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-22 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-25 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for veristat
bpf/vmtest-bpf-next-VM_Test-11 success Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-15 success Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-26 fail Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-next-PR fail PR summary
bpf/vmtest-bpf-next-VM_Test-8 success Logs for test_maps on s390x with gcc

Commit Message

Puranjay Mohan July 20, 2023, 3:49 p.m. UTC
Use bpf_jit_binary_pack_alloc() for memory management of JIT binaries in
RISCV BPF JIT. The bpf_jit_binary_pack_alloc creates a pair of RW and RX
buffers. The JIT writes the program into the RW buffer. When the JIT is
done, the program is copied to the final RX buffer with
bpf_jit_binary_pack_finalize.

Implement bpf_arch_text_copy() and bpf_arch_text_invalidate() for RISCV
JIT as these functions are required by bpf_jit_binary_pack allocator.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
---
 arch/riscv/net/bpf_jit.h        |   3 +
 arch/riscv/net/bpf_jit_comp64.c |  56 ++++++++++++---
 arch/riscv/net/bpf_jit_core.c   | 117 +++++++++++++++++++++++++++-----
 3 files changed, 150 insertions(+), 26 deletions(-)
diff mbox series

Patch

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 2717f5490428..ad69319c8ea7 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -68,6 +68,7 @@  static inline bool is_creg(u8 reg)
 struct rv_jit_context {
 	struct bpf_prog *prog;
 	u16 *insns;		/* RV insns */
+	u16 *ro_insns;
 	int ninsns;
 	int prologue_len;
 	int epilogue_offset;
@@ -85,7 +86,9 @@  static inline int ninsns_rvoff(int ninsns)
 
 struct rv_jit_data {
 	struct bpf_binary_header *header;
+	struct bpf_binary_header *ro_header;
 	u8 *image;
+	u8 *ro_image;
 	struct rv_jit_context ctx;
 };
 
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index c648864c8cd1..3d6165c6608b 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -142,7 +142,11 @@  static bool in_auipc_jalr_range(s64 val)
 /* Emit fixed-length instructions for address */
 static int emit_addr(u8 rd, u64 addr, bool extra_pass, struct rv_jit_context *ctx)
 {
-	u64 ip = (u64)(ctx->insns + ctx->ninsns);
+	/*
+	 * Use the ro_insns(RX) to calculate the offset as the BPF program will
+	 * finally run from this memory region.
+	 */
+	u64 ip = (u64)(ctx->ro_insns + ctx->ninsns);
 	s64 off = addr - ip;
 	s64 upper = (off + (1 << 11)) >> 12;
 	s64 lower = off & 0xfff;
@@ -463,7 +467,11 @@  static int emit_call(u64 addr, bool fixed_addr, struct rv_jit_context *ctx)
 	u64 ip;
 
 	if (addr && ctx->insns) {
-		ip = (u64)(long)(ctx->insns + ctx->ninsns);
+		/*
+		 * Use the ro_insns(RX) to calculate the offset as the BPF
+		 * program will finally run from this memory region.
+		 */
+		ip = (u64)(long)(ctx->ro_insns + ctx->ninsns);
 		off = addr - ip;
 	}
 
@@ -576,7 +584,8 @@  static int add_exception_handler(const struct bpf_insn *insn,
 {
 	struct exception_table_entry *ex;
 	unsigned long pc;
-	off_t offset;
+	off_t ins_offset;
+	off_t fixup_offset;
 
 	if (!ctx->insns || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM)
 		return 0;
@@ -591,12 +600,17 @@  static int add_exception_handler(const struct bpf_insn *insn,
 		return -EINVAL;
 
 	ex = &ctx->prog->aux->extable[ctx->nexentries];
-	pc = (unsigned long)&ctx->insns[ctx->ninsns - insn_len];
+	pc = (unsigned long)&ctx->ro_insns[ctx->ninsns - insn_len];
 
-	offset = pc - (long)&ex->insn;
-	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+	/*
+	 * This is the relative offset of the instruction that may fault from
+	 * the exception table itself. This will be written to the exception
+	 * table and if this instruction faults, the destination register will
+	 * be set to '0' and the execution will jump to the next instruction.
+	 */
+	ins_offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN))
 		return -ERANGE;
-	ex->insn = offset;
 
 	/*
 	 * Since the extable follows the program, the fixup offset is always
@@ -605,12 +619,25 @@  static int add_exception_handler(const struct bpf_insn *insn,
 	 * bits. We don't need to worry about buildtime or runtime sort
 	 * modifying the upper bits because the table is already sorted, and
 	 * isn't part of the main exception table.
+	 *
+	 * The fixup_offset is set to the next instruction from the instruction
+	 * that may fault. The execution will jump to this after handling the
+	 * fault.
 	 */
-	offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16));
-	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+	fixup_offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16));
+	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset))
 		return -ERANGE;
 
-	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+	/*
+	 * The offsets above have been calculated using the RO buffer but we
+	 * need to use the R/W buffer for writes.
+	 * switch ex to rw buffer for writing.
+	 */
+	ex = (void *)ctx->insns + ((void *)ex - (void *)ctx->ro_insns);
+
+	ex->insn = ins_offset;
+
+	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) |
 		FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
 	ex->type = EX_TYPE_BPF;
 
@@ -995,6 +1022,7 @@  int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 
 	ctx.ninsns = 0;
 	ctx.insns = NULL;
+	ctx.ro_insns = NULL;
 	ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
 	if (ret < 0)
 		return ret;
@@ -1003,7 +1031,15 @@  int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 		return -EFBIG;
 
 	ctx.ninsns = 0;
+	/*
+	 * The bpf_int_jit_compile() uses a RW buffer (ctx.insns) to write the
+	 * JITed instructions and later copies it to a RX region (ctx.ro_insns).
+	 * It also uses ctx.ro_insns to calculate offsets for jumps etc. As the
+	 * trampoline image uses the same memory area for writing and execution,
+	 * both ctx.insns and ctx.ro_insns can be set to image.
+	 */
 	ctx.insns = image;
+	ctx.ro_insns = image;
 	ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
 	if (ret < 0)
 		return ret;
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 7a26a3e1c73c..b0fa0084f493 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -8,6 +8,8 @@ 
 
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/memory.h>
+#include <asm/patch.h>
 #include "bpf_jit.h"
 
 /* Number of iterations to try until offsets converge. */
@@ -117,16 +119,27 @@  struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 				sizeof(struct exception_table_entry);
 			prog_size = sizeof(*ctx->insns) * ctx->ninsns;
 
-			jit_data->header =
-				bpf_jit_binary_alloc(prog_size + extable_size,
-						     &jit_data->image,
-						     sizeof(u32),
-						     bpf_fill_ill_insns);
-			if (!jit_data->header) {
+			jit_data->ro_header =
+				bpf_jit_binary_pack_alloc(prog_size +
+							  extable_size,
+							  &jit_data->ro_image,
+							  sizeof(u32),
+							  &jit_data->header,
+							  &jit_data->image,
+							  bpf_fill_ill_insns);
+			if (!jit_data->ro_header) {
 				prog = orig_prog;
 				goto out_offset;
 			}
 
+			/*
+			 * Use the image(RW) for writing the JITed instructions. But also save
+			 * the ro_image(RX) for calculating the offsets in the image. The RW
+			 * image will be later copied to the RX image from where the program
+			 * will run. The bpf_jit_binary_pack_finalize() will do this copy in the
+			 * final step.
+			 */
+			ctx->ro_insns = (u16 *)jit_data->ro_image;
 			ctx->insns = (u16 *)jit_data->image;
 			/*
 			 * Now, when the image is allocated, the image can
@@ -138,14 +151,12 @@  struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (i == NR_JIT_ITERATIONS) {
 		pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
-		if (jit_data->header)
-			bpf_jit_binary_free(jit_data->header);
 		prog = orig_prog;
-		goto out_offset;
+		goto out_free_hdr;
 	}
 
 	if (extable_size)
-		prog->aux->extable = (void *)ctx->insns + prog_size;
+		prog->aux->extable = (void *)ctx->ro_insns + prog_size;
 
 skip_init_ctx:
 	pass++;
@@ -154,23 +165,35 @@  struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	bpf_jit_build_prologue(ctx);
 	if (build_body(ctx, extra_pass, NULL)) {
-		bpf_jit_binary_free(jit_data->header);
 		prog = orig_prog;
-		goto out_offset;
+		goto out_free_hdr;
 	}
 	bpf_jit_build_epilogue(ctx);
 
 	if (bpf_jit_enable > 1)
 		bpf_jit_dump(prog->len, prog_size, pass, ctx->insns);
 
-	prog->bpf_func = (void *)ctx->insns;
+	prog->bpf_func = (void *)ctx->ro_insns;
 	prog->jited = 1;
 	prog->jited_len = prog_size;
 
-	bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
-
 	if (!prog->is_func || extra_pass) {
-		bpf_jit_binary_lock_ro(jit_data->header);
+		if (WARN_ON(bpf_jit_binary_pack_finalize(prog,
+							 jit_data->ro_header,
+							 jit_data->header))) {
+			/* ro_header has been freed */
+			jit_data->ro_header = NULL;
+			prog = orig_prog;
+			goto out_offset;
+		}
+		/*
+		 * The instructions have now been copied to the ROX region from
+		 * where they will execute.
+		 * Write any modified data cache blocks out to memory and
+		 * invalidate the corresponding blocks in the instruction cache.
+		 */
+		bpf_flush_icache(jit_data->ro_header,
+				 ctx->ro_insns + ctx->ninsns);
 		for (i = 0; i < prog->len; i++)
 			ctx->offset[i] = ninsns_rvoff(ctx->offset[i]);
 		bpf_prog_fill_jited_linfo(prog, ctx->offset);
@@ -185,6 +208,15 @@  struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
 					   tmp : orig_prog);
 	return prog;
+
+out_free_hdr:
+	if (jit_data->header) {
+		bpf_arch_text_copy(&jit_data->ro_header->size,
+				   &jit_data->header->size,
+				   sizeof(jit_data->header->size));
+		bpf_jit_binary_pack_free(jit_data->ro_header, jit_data->header);
+	}
+	goto out_offset;
 }
 
 u64 bpf_jit_alloc_exec_limit(void)
@@ -204,3 +236,56 @@  void bpf_jit_free_exec(void *addr)
 {
 	return vfree(addr);
 }
+
+void *bpf_arch_text_copy(void *dst, void *src, size_t len)
+{
+	int ret;
+
+	mutex_lock(&text_mutex);
+	ret = patch_text_nosync(dst, src, len);
+	mutex_unlock(&text_mutex);
+
+	if (ret)
+		return ERR_PTR(-EINVAL);
+
+	return dst;
+}
+
+int bpf_arch_text_invalidate(void *dst, size_t len)
+{
+	__le32 *ptr;
+	int ret = 0;
+	u32 inval = 0;
+
+	for (ptr = dst; ret == 0 && len >= sizeof(u32); len -= sizeof(u32)) {
+		mutex_lock(&text_mutex);
+		ret = patch_text_nosync(ptr++, &inval, sizeof(u32));
+		mutex_unlock(&text_mutex);
+	}
+
+	return ret;
+}
+
+void bpf_jit_free(struct bpf_prog *prog)
+{
+	if (prog->jited) {
+		struct rv_jit_data *jit_data = prog->aux->jit_data;
+		struct bpf_binary_header *hdr;
+
+		/*
+		 * If we fail the final pass of JIT (from jit_subprogs),
+		 * the program may not be finalized yet. Call finalize here
+		 * before freeing it.
+		 */
+		if (jit_data) {
+			bpf_jit_binary_pack_finalize(prog, jit_data->ro_header,
+						     jit_data->header);
+			kfree(jit_data);
+		}
+		hdr = bpf_jit_binary_pack_hdr(prog);
+		bpf_jit_binary_pack_free(hdr, NULL);
+		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
+	}
+
+	bpf_prog_unlock_free(prog);
+}