All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexei Starovoitov <alexei.starovoitov@gmail.com>
To: bpf@vger.kernel.org
Cc: daniel@iogearbox.net, andrii@kernel.org,
	torvalds@linux-foundation.org, brho@google.com,
	hannes@cmpxchg.org, akpm@linux-foundation.org, urezki@gmail.com,
	hch@infradead.org, linux-mm@kvack.org, kernel-team@fb.com
Subject: [PATCH v3 bpf-next 05/14] bpf: Recognize addr_space_cast instruction in the verifier.
Date: Thu,  7 Mar 2024 17:08:03 -0800	[thread overview]
Message-ID: <20240308010812.89848-6-alexei.starovoitov@gmail.com> (raw)
In-Reply-To: <20240308010812.89848-1-alexei.starovoitov@gmail.com>

From: Alexei Starovoitov <ast@kernel.org>

rY = addr_space_cast(rX, 0, 1) tells the verifier that rY->type = PTR_TO_ARENA.
Any further operations on PTR_TO_ARENA register have to be in 32-bit domain.

The verifier will mark load/store through PTR_TO_ARENA with PROBE_MEM32.
JIT will generate them as kern_vm_start + 32bit_addr memory accesses.

rY = addr_space_cast(rX, 1, 0) tells the verifier that rY->type = unknown scalar.
If arena->map_flags has BPF_F_NO_USER_CONV set then convert cast_user to mov32 as well.
Otherwise JIT will convert it to:
  rY = (u32)rX;
  if (rY)
     rY |= arena->user_vm_start & ~(u64)~0U;

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |   1 +
 include/linux/bpf_verifier.h |   1 +
 kernel/bpf/log.c             |   3 +
 kernel/bpf/syscall.c         |   6 ++
 kernel/bpf/verifier.c        | 107 ++++++++++++++++++++++++++++++++---
 5 files changed, 109 insertions(+), 9 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8904d1606125..d0c836ba009d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -883,6 +883,7 @@ enum bpf_reg_type {
 	 * an explicit null check is required for this struct.
 	 */
 	PTR_TO_MEM,		 /* reg points to valid memory region */
+	PTR_TO_ARENA,
 	PTR_TO_BUF,		 /* reg points to a read/write buffer */
 	PTR_TO_FUNC,		 /* reg points to a bpf program function */
 	CONST_PTR_TO_DYNPTR,	 /* reg points to a const struct bpf_dynptr */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 4b0f6600e499..7cb1b75eee38 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -548,6 +548,7 @@ struct bpf_insn_aux_data {
 	u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
 	bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
 	bool zext_dst; /* this insn zero extends dst reg */
+	bool needs_zext; /* alu op needs to clear upper bits */
 	bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
 	bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
 	bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 63c34e7b0715..2a243cf37c60 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -458,6 +458,7 @@ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type)
 		[PTR_TO_XDP_SOCK]	= "xdp_sock",
 		[PTR_TO_BTF_ID]		= "ptr_",
 		[PTR_TO_MEM]		= "mem",
+		[PTR_TO_ARENA]		= "arena",
 		[PTR_TO_BUF]		= "buf",
 		[PTR_TO_FUNC]		= "func",
 		[PTR_TO_MAP_KEY]	= "map_key",
@@ -693,6 +694,8 @@ static void print_reg_state(struct bpf_verifier_env *env,
 	}
 
 	verbose(env, "%s", reg_type_str(env, t));
+	if (t == PTR_TO_ARENA)
+		return;
 	if (t == PTR_TO_STACK) {
 		if (state->frameno != reg->frameno)
 			verbose(env, "[%d]", reg->frameno);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 67923e41a07e..07f2a4db4511 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4453,6 +4453,12 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
 			continue;
 		}
 
+		if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX ||
+		     BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) {
+			insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM;
+			continue;
+		}
+
 		if (code != (BPF_LD | BPF_IMM | BPF_DW))
 			continue;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fbcf2e5e635a..1358e20d315a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4386,6 +4386,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_MEM:
 	case PTR_TO_FUNC:
 	case PTR_TO_MAP_KEY:
+	case PTR_TO_ARENA:
 		return true;
 	default:
 		return false;
@@ -5828,6 +5829,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 	case PTR_TO_XDP_SOCK:
 		pointer_desc = "xdp_sock ";
 		break;
+	case PTR_TO_ARENA:
+		return 0;
 	default:
 		break;
 	}
@@ -6937,6 +6940,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 
 		if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ))
 			mark_reg_unknown(env, regs, value_regno);
+	} else if (reg->type == PTR_TO_ARENA) {
+		if (t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str(env, reg->type));
@@ -8408,6 +8414,7 @@ static int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	case PTR_TO_MEM | MEM_RINGBUF:
 	case PTR_TO_BUF:
 	case PTR_TO_BUF | MEM_RDONLY:
+	case PTR_TO_ARENA:
 	case SCALAR_VALUE:
 		return 0;
 	/* All the rest must be rejected, except PTR_TO_BTF_ID which allows
@@ -13852,6 +13859,21 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 
 	dst_reg = &regs[insn->dst_reg];
 	src_reg = NULL;
+
+	if (dst_reg->type == PTR_TO_ARENA) {
+		struct bpf_insn_aux_data *aux = cur_aux(env);
+
+		if (BPF_CLASS(insn->code) == BPF_ALU64)
+			/*
+			 * 32-bit operations zero upper bits automatically.
+			 * 64-bit operations need to be converted to 32.
+			 */
+			aux->needs_zext = true;
+
+		/* Any arithmetic operations are allowed on arena pointers */
+		return 0;
+	}
+
 	if (dst_reg->type != SCALAR_VALUE)
 		ptr_reg = dst_reg;
 	else
@@ -13969,19 +13991,20 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	} else if (opcode == BPF_MOV) {
 
 		if (BPF_SRC(insn->code) == BPF_X) {
-			if (insn->imm != 0) {
-				verbose(env, "BPF_MOV uses reserved fields\n");
-				return -EINVAL;
-			}
-
 			if (BPF_CLASS(insn->code) == BPF_ALU) {
-				if (insn->off != 0 && insn->off != 8 && insn->off != 16) {
+				if ((insn->off != 0 && insn->off != 8 && insn->off != 16) ||
+				    insn->imm) {
 					verbose(env, "BPF_MOV uses reserved fields\n");
 					return -EINVAL;
 				}
+			} else if (insn->off == BPF_ADDR_SPACE_CAST) {
+				if (insn->imm != 1 && insn->imm != 1u << 16) {
+					verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n");
+					return -EINVAL;
+				}
 			} else {
-				if (insn->off != 0 && insn->off != 8 && insn->off != 16 &&
-				    insn->off != 32) {
+				if ((insn->off != 0 && insn->off != 8 && insn->off != 16 &&
+				     insn->off != 32) || insn->imm) {
 					verbose(env, "BPF_MOV uses reserved fields\n");
 					return -EINVAL;
 				}
@@ -14008,7 +14031,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			struct bpf_reg_state *dst_reg = regs + insn->dst_reg;
 
 			if (BPF_CLASS(insn->code) == BPF_ALU64) {
-				if (insn->off == 0) {
+				if (insn->imm) {
+					/* off == BPF_ADDR_SPACE_CAST */
+					mark_reg_unknown(env, regs, insn->dst_reg);
+					if (insn->imm == 1) /* cast from as(1) to as(0) */
+						dst_reg->type = PTR_TO_ARENA;
+				} else if (insn->off == 0) {
 					/* case: R1 = R2
 					 * copy register state to dest reg
 					 */
@@ -15182,6 +15210,10 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE ||
 	    insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) {
+		if (map->map_type == BPF_MAP_TYPE_ARENA) {
+			__mark_reg_unknown(env, dst_reg);
+			return 0;
+		}
 		dst_reg->type = PTR_TO_MAP_VALUE;
 		dst_reg->off = aux->map_off;
 		WARN_ON_ONCE(map->max_entries != 1);
@@ -16568,6 +16600,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		 * the same stack frame, since fp-8 in foo != fp-8 in bar
 		 */
 		return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno;
+	case PTR_TO_ARENA:
+		return true;
 	default:
 		return regs_exact(rold, rcur, idmap);
 	}
@@ -17443,6 +17477,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type)
 	case PTR_TO_TCP_SOCK:
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
+	case PTR_TO_ARENA:
 		return false;
 	default:
 		return true;
@@ -18296,6 +18331,31 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 				fdput(f);
 				return -EBUSY;
 			}
+			if (map->map_type == BPF_MAP_TYPE_ARENA) {
+				if (env->prog->aux->arena) {
+					verbose(env, "Only one arena per program\n");
+					fdput(f);
+					return -EBUSY;
+				}
+				if (!env->allow_ptr_leaks || !env->bpf_capable) {
+					verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n");
+					fdput(f);
+					return -EPERM;
+				}
+				if (!env->prog->jit_requested) {
+					verbose(env, "JIT is required to use arena\n");
+					return -EOPNOTSUPP;
+				}
+				if (!bpf_jit_supports_arena()) {
+					verbose(env, "JIT doesn't support arena\n");
+					return -EOPNOTSUPP;
+				}
+				env->prog->aux->arena = (void *)map;
+				if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) {
+					verbose(env, "arena's user address must be set via map_extra or mmap()\n");
+					return -EINVAL;
+				}
+			}
 
 			fdput(f);
 next_insn:
@@ -18917,6 +18977,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 				env->prog->aux->num_exentries++;
 			}
 			continue;
+		case PTR_TO_ARENA:
+			if (BPF_MODE(insn->code) == BPF_MEMSX) {
+				verbose(env, "sign extending loads from arena are not supported yet\n");
+				return -EOPNOTSUPP;
+			}
+			insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32 | BPF_SIZE(insn->code);
+			env->prog->aux->num_exentries++;
+			continue;
 		default:
 			continue;
 		}
@@ -19102,13 +19170,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->nr_linfo = prog->aux->nr_linfo;
 		func[i]->aux->jited_linfo = prog->aux->jited_linfo;
 		func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx;
+		func[i]->aux->arena = prog->aux->arena;
 		num_exentries = 0;
 		insn = func[i]->insnsi;
 		for (j = 0; j < func[i]->len; j++, insn++) {
 			if (BPF_CLASS(insn->code) == BPF_LDX &&
 			    (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+			     BPF_MODE(insn->code) == BPF_PROBE_MEM32 ||
 			     BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
 				num_exentries++;
+			if ((BPF_CLASS(insn->code) == BPF_STX ||
+			     BPF_CLASS(insn->code) == BPF_ST) &&
+			     BPF_MODE(insn->code) == BPF_PROBE_MEM32)
+				num_exentries++;
 		}
 		func[i]->aux->num_exentries = num_exentries;
 		func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
@@ -19507,6 +19581,21 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 	}
 
 	for (i = 0; i < insn_cnt;) {
+		if (insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->imm) {
+			if ((insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1) ||
+			    (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) {
+				/* convert to 32-bit mov that clears upper 32-bit */
+				insn->code = BPF_ALU | BPF_MOV | BPF_X;
+				/* clear off, so it's a normal 'wX = wY' from JIT pov */
+				insn->off = 0;
+			} /* cast from as(0) to as(1) should be handled by JIT */
+			goto next_insn;
+		}
+
+		if (env->insn_aux_data[i + delta].needs_zext)
+			/* Convert BPF_CLASS(insn->code) == BPF_ALU64 to 32-bit ALU */
+			insn->code = BPF_ALU | BPF_OP(insn->code) | BPF_SRC(insn->code);
+
 		/* Make divide-by-zero exceptions impossible. */
 		if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
 		    insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
-- 
2.43.0


  parent reply	other threads:[~2024-03-08  1:08 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-03-08  1:07 [PATCH v3 bpf-next 00/14] bpf: Introduce BPF arena Alexei Starovoitov
2024-03-08  1:07 ` [PATCH v3 bpf-next 01/14] bpf: Introduce bpf_arena Alexei Starovoitov
2024-03-11 22:01   ` Andrii Nakryiko
2024-03-11 22:41     ` Alexei Starovoitov
2024-03-11 22:59       ` Andrii Nakryiko
2024-03-12  0:47         ` Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 02/14] bpf: Disasm support for addr_space_cast instruction Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 03/14] bpf: Add x86-64 JIT support for PROBE_MEM32 pseudo instructions Alexei Starovoitov
2024-03-11 22:05   ` Andrii Nakryiko
2024-03-11 22:44     ` Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 04/14] bpf: Add x86-64 JIT support for bpf_addr_space_cast instruction Alexei Starovoitov
2024-03-08  1:08 ` Alexei Starovoitov [this message]
2024-03-08  1:08 ` [PATCH v3 bpf-next 06/14] bpf: Recognize btf_decl_tag("arg:arena") as PTR_TO_ARENA Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 07/14] libbpf: Add __arg_arena to bpf_helpers.h Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 08/14] libbpf: Add support for bpf_arena Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 09/14] bpftool: Recognize arena map type Alexei Starovoitov
2024-03-11 17:08   ` Quentin Monnet
2024-03-08  1:08 ` [PATCH v3 bpf-next 10/14] libbpf: Recognize __arena global varaibles Alexei Starovoitov
2024-03-11 17:09   ` Quentin Monnet
2024-03-08  1:08 ` [PATCH v3 bpf-next 11/14] bpf: Add helper macro bpf_addr_space_cast() Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 12/14] selftests/bpf: Add unit tests for bpf_arena_alloc/free_pages Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 13/14] selftests/bpf: Add bpf_arena_list test Alexei Starovoitov
2024-03-08  1:08 ` [PATCH v3 bpf-next 14/14] selftests/bpf: Add bpf_arena_htab test Alexei Starovoitov
2024-03-11 22:45 ` [PATCH v3 bpf-next 00/14] bpf: Introduce BPF arena Andrii Nakryiko
2024-03-11 23:02   ` Alexei Starovoitov
2024-03-11 22:50 ` patchwork-bot+netdevbpf

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=20240308010812.89848-6-alexei.starovoitov@gmail.com \
    --to=alexei.starovoitov@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=andrii@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brho@google.com \
    --cc=daniel@iogearbox.net \
    --cc=hannes@cmpxchg.org \
    --cc=hch@infradead.org \
    --cc=kernel-team@fb.com \
    --cc=linux-mm@kvack.org \
    --cc=torvalds@linux-foundation.org \
    --cc=urezki@gmail.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.