linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
To: naveen.n.rao@linux.ibm.com, mpe@ellerman.id.au, ast@kernel.org,
	daniel@iogearbox.net
Cc: ravi.bangoria@linux.ibm.com, sandipan@linux.ibm.com,
	paulus@samba.org, andrii@kernel.org, kafai@fb.com,
	songliubraving@fb.com, yhs@fb.com, john.fastabend@gmail.com,
	kpsingh@kernel.org, netdev@vger.kernel.org, bpf@vger.kernel.org,
	linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Subject: [PATCH 3/4] bpf powerpc: Add BPF_PROBE_MEM support for 64bit JIT
Date: Tue,  6 Jul 2021 13:02:10 +0530	[thread overview]
Message-ID: <20210706073211.349889-4-ravi.bangoria@linux.ibm.com> (raw)
In-Reply-To: <20210706073211.349889-1-ravi.bangoria@linux.ibm.com>

BPF load instruction with BPF_PROBE_MEM mode can cause a fault
inside kernel. Append exception table for such instructions
within BPF program.

Unlike other archs which uses extable 'fixup' field to pass dest_reg
and nip, BPF exception table on PowerPC follows the generic PowerPC
exception table design, where it populates both fixup and extable
sections witin BPF program. fixup section contains two instructions,
first instruction clears dest_reg and 2nd jumps to next instruction
in the BPF code. extable 'insn' field contains relative offset of
the instruction and 'fixup' field contains relative offset of the
fixup entry. Example layout of BPF program with extable present:

             +------------------+
             |                  |
             |                  |
   0x4020 -->| ld   r27,4(r3)   |
             |                  |
             |                  |
   0x40ac -->| lwz  r3,0(r4)    |
             |                  |
             |                  |
             |------------------|
   0x4280 -->| xor r27,r27,r27  |  \ fixup entry
             | b   0x4024       |  /
   0x4288 -->| xor r3,r3,r3     |
             | b   0x40b0       |
             |------------------|
   0x4290 -->| insn=0xfffffd90  |  \ extable entry
             | fixup=0xffffffec |  /
   0x4298 -->| insn=0xfffffe14  |
             | fixup=0xffffffec |
             +------------------+

   (Addresses shown here are chosen random, not real)

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h        |  5 ++-
 arch/powerpc/net/bpf_jit_comp.c   | 25 +++++++++----
 arch/powerpc/net/bpf_jit_comp32.c |  2 +-
 arch/powerpc/net/bpf_jit_comp64.c | 60 ++++++++++++++++++++++++++++++-
 4 files changed, 83 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 411c63d945c7..e9408ad190d3 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -141,8 +141,11 @@ struct codegen_context {
 	unsigned int idx;
 	unsigned int stack_size;
 	int b2p[ARRAY_SIZE(b2p)];
+	unsigned int exentry_idx;
 };
 
+#define BPF_FIXUP_LEN	8 /* Two instructions */
+
 static inline void bpf_flush_icache(void *start, void *end)
 {
 	smp_wmb();	/* smp write barrier */
@@ -166,7 +169,7 @@ static inline void bpf_clear_seen_register(struct codegen_context *ctx, int i)
 
 void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func);
 int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
-		       u32 *addrs);
+		       u32 *addrs, int pass);
 void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
 void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
 void bpf_jit_realloc_regs(struct codegen_context *ctx);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index a9585e52a88d..3ebd8897cf09 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -89,6 +89,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 {
 	u32 proglen;
 	u32 alloclen;
+	u32 extable_len = 0;
+	u32 fixup_len = 0;
 	u8 *image = NULL;
 	u32 *code_base;
 	u32 *addrs;
@@ -131,7 +133,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		image = jit_data->image;
 		bpf_hdr = jit_data->header;
 		proglen = jit_data->proglen;
-		alloclen = proglen + FUNCTION_DESCR_SIZE;
 		extra_pass = true;
 		goto skip_init_ctx;
 	}
@@ -149,7 +150,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
 
 	/* Scouting faux-generate pass 0 */
-	if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) {
+	if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0)) {
 		/* We hit something illegal or unsupported. */
 		fp = org_fp;
 		goto out_addrs;
@@ -162,7 +163,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	 */
 	if (cgctx.seen & SEEN_TAILCALL) {
 		cgctx.idx = 0;
-		if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) {
+		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0)) {
 			fp = org_fp;
 			goto out_addrs;
 		}
@@ -177,8 +178,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	bpf_jit_build_prologue(0, &cgctx);
 	bpf_jit_build_epilogue(0, &cgctx);
 
+	fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN;
+	extable_len = fp->aux->num_exentries * sizeof(struct exception_table_entry);
+
 	proglen = cgctx.idx * 4;
-	alloclen = proglen + FUNCTION_DESCR_SIZE;
+	alloclen = proglen + FUNCTION_DESCR_SIZE + fixup_len + extable_len;
 
 	bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4, bpf_jit_fill_ill_insns);
 	if (!bpf_hdr) {
@@ -186,6 +190,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		goto out_addrs;
 	}
 
+	if (extable_len) {
+		fp->aux->extable = (void *)image + FUNCTION_DESCR_SIZE +
+				   proglen + fixup_len;
+	}
+
 skip_init_ctx:
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
 
@@ -210,7 +219,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		/* Now build the prologue, body code & epilogue for real. */
 		cgctx.idx = 0;
 		bpf_jit_build_prologue(code_base, &cgctx);
-		bpf_jit_build_body(fp, code_base, &cgctx, addrs);
+		if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, pass)) {
+			bpf_jit_binary_free(bpf_hdr);
+			fp = org_fp;
+			goto out_addrs;
+		}
 		bpf_jit_build_epilogue(code_base, &cgctx);
 
 		if (bpf_jit_enable > 1)
@@ -234,7 +247,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 
 	fp->bpf_func = (void *)image;
 	fp->jited = 1;
-	fp->jited_len = alloclen;
+	fp->jited_len = proglen + FUNCTION_DESCR_SIZE;
 
 	bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
 	if (!fp->is_func || extra_pass) {
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 1f81bea35aab..23ab5620a45a 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -266,7 +266,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 
 /* Assemble the body code between the prologue & epilogue */
 int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
-		       u32 *addrs)
+		       u32 *addrs, int pass)
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 984177d9d394..1884c6dca89a 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -270,9 +270,51 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	/* out: */
 }
 
+static int add_extable_entry(struct bpf_prog *fp, u32 *image, int pass,
+			     u32 code, struct codegen_context *ctx, int dst_reg)
+{
+	off_t offset;
+	unsigned long pc;
+	struct exception_table_entry *ex;
+	u32 *fixup;
+
+	/* Populate extable entries only in the last pass */
+	if (pass != 2 || BPF_MODE(code) != BPF_PROBE_MEM)
+		return 0;
+
+	if (!fp->aux->extable ||
+	    WARN_ON_ONCE(ctx->exentry_idx >= fp->aux->num_exentries))
+		return -EINVAL;
+
+	pc = (unsigned long)&image[ctx->idx - 1];
+
+	fixup = (void *)fp->aux->extable -
+		(fp->aux->num_exentries * BPF_FIXUP_LEN) +
+		(ctx->exentry_idx * BPF_FIXUP_LEN);
+
+	fixup[0] = PPC_RAW_XOR(dst_reg, dst_reg, dst_reg);
+	fixup[1] = (PPC_INST_BRANCH |
+		   (((long)(pc + 4) - (long)&fixup[1]) & 0x03fffffc));
+
+	ex = &fp->aux->extable[ctx->exentry_idx];
+
+	offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+		return -ERANGE;
+	ex->insn = offset;
+
+	offset = (long)fixup - (long)&ex->fixup;
+	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+		return -ERANGE;
+	ex->fixup = offset;
+
+	ctx->exentry_idx++;
+	return 0;
+}
+
 /* Assemble the body code between the prologue & epilogue */
 int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
-		       u32 *addrs)
+		       u32 *addrs, int pass)
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
@@ -710,25 +752,41 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		 */
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 			EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
+			ret = add_extable_entry(fp, image, pass, code, ctx, dst_reg);
+			if (ret)
+				return ret;
 			break;
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
 			EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
+			ret = add_extable_entry(fp, image, pass, code, ctx, dst_reg);
+			if (ret)
+				return ret;
 			break;
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 			EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
+			ret = add_extable_entry(fp, image, pass, code, ctx, dst_reg);
+			if (ret)
+				return ret;
 			break;
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
 			PPC_BPF_LL(dst_reg, src_reg, off);
+			ret = add_extable_entry(fp, image, pass, code, ctx, dst_reg);
+			if (ret)
+				return ret;
 			break;
 
 		/*
-- 
2.26.3


  parent reply	other threads:[~2021-07-06  7:33 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-06  7:32 [PATCH 0/4] bpf powerpc: Add BPF_PROBE_MEM support for 64bit JIT Ravi Bangoria
2021-07-06  7:32 ` [PATCH 1/4] bpf powerpc: Remove unused SEEN_STACK Ravi Bangoria
2021-07-06  7:32 ` [PATCH 2/4] bpf powerpc: Remove extra_pass from bpf_jit_build_body() Ravi Bangoria
2021-07-06  7:32 ` Ravi Bangoria [this message]
2021-07-06  9:53   ` [PATCH 3/4] bpf powerpc: Add BPF_PROBE_MEM support for 64bit JIT Christophe Leroy
2021-07-07  4:01     ` Ravi Bangoria
2021-07-06  7:32 ` [PATCH 4/4] bpf powerpc: Add addr > TASK_SIZE_MAX explicit check Ravi Bangoria
2021-07-06 10:00   ` Christophe Leroy
2021-07-07  4:06     ` Ravi Bangoria

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210706073211.349889-4-ravi.bangoria@linux.ibm.com \
    --to=ravi.bangoria@linux.ibm.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=john.fastabend@gmail.com \
    --cc=kafai@fb.com \
    --cc=kpsingh@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=naveen.n.rao@linux.ibm.com \
    --cc=netdev@vger.kernel.org \
    --cc=paulus@samba.org \
    --cc=sandipan@linux.ibm.com \
    --cc=songliubraving@fb.com \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).