diff mbox series

[bpf-next,v4,5/8] bpf: teach the verifier to enforce css_iter and task_iter in RCU CS

Message ID 20231007124522.34834-6-zhouchuyi@bytedance.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series Add Open-coded task, css_task and css iters | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next
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 fail Errors and warnings before: 1477 this patch: 1477
netdev/cc_maintainers warning 8 maintainers not CCed: song@kernel.org yonghong.song@linux.dev jolsa@kernel.org kpsingh@kernel.org john.fastabend@gmail.com sdf@google.com haoluo@google.com martin.lau@linux.dev
netdev/build_clang success Errors and warnings before: 1528 this patch: 1528
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: 2933 this patch: 2933
netdev/checkpatch warning CHECK: Alignment should match open parenthesis CHECK: Macro argument 'frame' may be better as '(frame)' to avoid precedence issues CHECK: Macro argument 'slot' may be better as '(slot)' to avoid precedence issues CHECK: Prefer using the BIT macro WARNING: line length of 81 exceeds 80 columns WARNING: line length of 82 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 88 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns WARNING: line length of 92 exceeds 80 columns WARNING: line length of 98 exceeds 80 columns WARNING: line length of 99 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-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-6 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-5 fail Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-0 success Logs for ${{ matrix.test }} on ${{ matrix.arch }} with ${{ matrix.toolchain_full }}
bpf/vmtest-bpf-next-VM_Test-4 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for veristat

Commit Message

Chuyi Zhou Oct. 7, 2023, 12:45 p.m. UTC 
css_iter and task_iter should be used in rcu section. Specifically, in
sleepable progs explicit bpf_rcu_read_lock() is needed before use these
iters. In normal bpf progs that have implicit rcu_read_lock(), it's OK to
use them directly.

This patch adds a new a KF flag KF_RCU_PROTECTED for bpf_iter_task_new and
bpf_iter_css_new. It means the kfunc should be used in RCU CS. We check
whether we are in rcu cs before we want to invoke this kfunc. If the rcu
protection is guaranteed, we would let st->type = PTR_TO_STACK | MEM_RCU.
Once user do rcu_unlock during the iteration, state MEM_RCU of regs would
be cleared. is_iter_reg_valid_init() will reject if reg->type is UNTRUSTED.

It is worth noting that currently, bpf_rcu_read_unlock does not
clear the state of the STACK_ITER reg, since bpf_for_each_spilled_reg
only considers STACK_SPILL. This patch also let bpf_for_each_spilled_reg
search STACK_ITER.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
---
 include/linux/bpf_verifier.h | 19 ++++++++------
 include/linux/btf.h          |  1 +
 kernel/bpf/helpers.c         |  4 +--
 kernel/bpf/verifier.c        | 50 ++++++++++++++++++++++++++++--------
 4 files changed, 53 insertions(+), 21 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 94ec766432f5..e67cd45a85be 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -386,19 +386,18 @@  struct bpf_verifier_state {
 	u32 jmp_history_cnt;
 };
 
-#define bpf_get_spilled_reg(slot, frame)				\
+#define bpf_get_spilled_reg(slot, frame, mask)				\
 	(((slot < frame->allocated_stack / BPF_REG_SIZE) &&		\
-	  (frame->stack[slot].slot_type[0] == STACK_SPILL))		\
+	  ((1 << frame->stack[slot].slot_type[0]) & (mask))) \
 	 ? &frame->stack[slot].spilled_ptr : NULL)
 
 /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */
-#define bpf_for_each_spilled_reg(iter, frame, reg)			\
-	for (iter = 0, reg = bpf_get_spilled_reg(iter, frame);		\
+#define bpf_for_each_spilled_reg(iter, frame, reg, mask)			\
+	for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask);		\
 	     iter < frame->allocated_stack / BPF_REG_SIZE;		\
-	     iter++, reg = bpf_get_spilled_reg(iter, frame))
+	     iter++, reg = bpf_get_spilled_reg(iter, frame, mask))
 
-/* Invoke __expr over regsiters in __vst, setting __state and __reg */
-#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr)   \
+#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr)   \
 	({                                                               \
 		struct bpf_verifier_state *___vstate = __vst;            \
 		int ___i, ___j;                                          \
@@ -410,7 +409,7 @@  struct bpf_verifier_state {
 				__reg = &___regs[___j];                  \
 				(void)(__expr);                          \
 			}                                                \
-			bpf_for_each_spilled_reg(___j, __state, __reg) { \
+			bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \
 				if (!__reg)                              \
 					continue;                        \
 				(void)(__expr);                          \
@@ -418,6 +417,10 @@  struct bpf_verifier_state {
 		}                                                        \
 	})
 
+/* Invoke __expr over regsiters in __vst, setting __state and __reg */
+#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \
+	bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr)
+
 /* linked list of verifier states used to prune search */
 struct bpf_verifier_state_list {
 	struct bpf_verifier_state state;
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 928113a80a95..c2231c64d60b 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -74,6 +74,7 @@ 
 #define KF_ITER_NEW     (1 << 8) /* kfunc implements BPF iter constructor */
 #define KF_ITER_NEXT    (1 << 9) /* kfunc implements BPF iter next method */
 #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */
+#define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */
 
 /*
  * Tag marking a kernel function as a kfunc. This is meant to minimize the
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 7596e83d6715..fb345507b12b 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2552,10 +2552,10 @@  BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
-BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
-BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 528d375c17ee..3a60cc87520e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1173,7 +1173,12 @@  static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg
 
 static void __mark_reg_known_zero(struct bpf_reg_state *reg);
 
+static bool in_rcu_cs(struct bpf_verifier_env *env);
+
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta);
+
 static int mark_stack_slots_iter(struct bpf_verifier_env *env,
+				 struct bpf_kfunc_call_arg_meta *meta,
 				 struct bpf_reg_state *reg, int insn_idx,
 				 struct btf *btf, u32 btf_id, int nr_slots)
 {
@@ -1194,6 +1199,12 @@  static int mark_stack_slots_iter(struct bpf_verifier_env *env,
 
 		__mark_reg_known_zero(st);
 		st->type = PTR_TO_STACK; /* we don't have dedicated reg type */
+		if (is_kfunc_rcu_protected(meta)) {
+			if (in_rcu_cs(env))
+				st->type |= MEM_RCU;
+			else
+				st->type |= PTR_UNTRUSTED;
+		}
 		st->live |= REG_LIVE_WRITTEN;
 		st->ref_obj_id = i == 0 ? id : 0;
 		st->iter.btf = btf;
@@ -1268,7 +1279,7 @@  static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env,
 	return true;
 }
 
-static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 				   struct btf *btf, u32 btf_id, int nr_slots)
 {
 	struct bpf_func_state *state = func(env, reg);
@@ -1276,26 +1287,28 @@  static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_
 
 	spi = iter_get_spi(env, reg, nr_slots);
 	if (spi < 0)
-		return false;
+		return -EINVAL;
 
 	for (i = 0; i < nr_slots; i++) {
 		struct bpf_stack_state *slot = &state->stack[spi - i];
 		struct bpf_reg_state *st = &slot->spilled_ptr;
 
+		if (st->type & PTR_UNTRUSTED)
+			return -EPROTO;
 		/* only main (first) slot has ref_obj_id set */
 		if (i == 0 && !st->ref_obj_id)
-			return false;
+			return -EINVAL;
 		if (i != 0 && st->ref_obj_id)
-			return false;
+			return -EINVAL;
 		if (st->iter.btf != btf || st->iter.btf_id != btf_id)
-			return false;
+			return -EINVAL;
 
 		for (j = 0; j < BPF_REG_SIZE; j++)
 			if (slot->slot_type[j] != STACK_ITER)
-				return false;
+				return -EINVAL;
 	}
 
-	return true;
+	return 0;
 }
 
 /* Check if given stack slot is "special":
@@ -7618,15 +7631,24 @@  static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
 				return err;
 		}
 
-		err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots);
+		err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots);
 		if (err)
 			return err;
 	} else {
 		/* iter_next() or iter_destroy() expect initialized iter state*/
-		if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) {
+		err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots);
+		switch (err) {
+		case 0:
+			break;
+		case -EINVAL:
 			verbose(env, "expected an initialized iter_%s as arg #%d\n",
 				iter_type_str(meta->btf, btf_id), regno);
-			return -EINVAL;
+			return err;
+		case -EPROTO:
+			verbose(env, "expected an RCU CS when using %s\n", meta->func_name);
+			return err;
+		default:
+			return err;
 		}
 
 		spi = iter_get_spi(env, reg, nr_slots);
@@ -10209,6 +10231,11 @@  static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta)
 	return meta->kfunc_flags & KF_RCU;
 }
 
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta)
+{
+	return meta->kfunc_flags & KF_RCU_PROTECTED;
+}
+
 static bool __kfunc_param_match_suffix(const struct btf *btf,
 				       const struct btf_param *arg,
 				       const char *suffix)
@@ -11560,6 +11587,7 @@  static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	if (env->cur_state->active_rcu_lock) {
 		struct bpf_func_state *state;
 		struct bpf_reg_state *reg;
+		u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER);
 
 		if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) {
 			verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n");
@@ -11570,7 +11598,7 @@  static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			verbose(env, "nested rcu read lock (kernel function %s)\n", func_name);
 			return -EINVAL;
 		} else if (rcu_unlock) {
-			bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+			bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({
 				if (reg->type & MEM_RCU) {
 					reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL);
 					reg->type |= PTR_UNTRUSTED;