diff mbox series

[bpf-next,v8,04/10] bpf: hold module for bpf_struct_ops_map.

Message ID 20231030192810.382942-5-thinker.li@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series Registrating struct_ops types from modules | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR fail PR summary
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 fail Errors and warnings before: 1519 this patch: 1520
netdev/cc_maintainers warning 8 maintainers not CCed: jolsa@kernel.org sdf@google.com john.fastabend@gmail.com kpsingh@kernel.org yonghong.song@linux.dev netdev@vger.kernel.org haoluo@google.com daniel@iogearbox.net
netdev/build_clang fail Errors and warnings before: 170 this patch: 170
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 fail Errors and warnings before: 1571 this patch: 1572
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 184 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc fail Errors and warnings before: 0 this patch: 1
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-3 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-9 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-15 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-16 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-19 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-20 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-21 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-22 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-llvm-16 / build / build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-25 fail Logs for x86_64-llvm-16 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-llvm-16 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-llvm-16 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-16 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-16 / veristat
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc

Commit Message

Kui-Feng Lee Oct. 30, 2023, 7:28 p.m. UTC 
From: Kui-Feng Lee <thinker.li@gmail.com>

To ensure that a module remains accessible whenever a struct_ops object of
a struct_ops type provided by the module is still in use.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
---
 include/linux/bpf.h         |  1 +
 include/linux/btf.h         |  2 +-
 kernel/bpf/bpf_struct_ops.c | 70 ++++++++++++++++++++++++++++++-------
 3 files changed, 60 insertions(+), 13 deletions(-)

Comments

Martin KaFai Lau Oct. 31, 2023, 1:21 a.m. UTC | #1 
On 10/30/23 12:28 PM, thinker.li@gmail.com wrote:
> @@ -681,9 +697,17 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
>   	if (!st_ops_desc)
>   		return ERR_PTR(-ENOTSUPP);
>   
> +	if (st_ops_desc->btf != btf_vmlinux) {
> +		mod = btf_try_get_module(st_ops_desc->btf);
> +		if (!mod)
> +			return ERR_PTR(-EINVAL);
> +	}
> +
>   	vt = st_ops_desc->value_type;
> -	if (attr->value_size != vt->size)
> -		return ERR_PTR(-EINVAL);
> +	if (attr->value_size != vt->size) {
> +		ret = -EINVAL;
> +		goto errout;
> +	}
>   
>   	t = st_ops_desc->type;
>   
> @@ -694,17 +718,17 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
>   		(vt->size - sizeof(struct bpf_struct_ops_value));
>   
>   	st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
> -	if (!st_map)
> -		return ERR_PTR(-ENOMEM);
> +	if (!st_map) {
> +		ret = -ENOMEM;
> +		goto errout;
> +	}
>   
>   	st_map->st_ops_desc = st_ops_desc;
>   	map = &st_map->map;
>   
>   	ret = bpf_jit_charge_modmem(PAGE_SIZE);
> -	if (ret) {
> -		__bpf_struct_ops_map_free(map);
> -		return ERR_PTR(ret);
> -	}
> +	if (ret)
> +		goto errout_free;
>   
>   	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
>   	if (!st_map->image) {
> @@ -713,23 +737,32 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
>   		 * here.
>   		 */
>   		bpf_jit_uncharge_modmem(PAGE_SIZE);
> -		__bpf_struct_ops_map_free(map);
> -		return ERR_PTR(-ENOMEM);
> +		ret = -ENOMEM;
> +		goto errout_free;
>   	}
>   	st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
>   	st_map->links =
>   		bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
>   				   NUMA_NO_NODE);
>   	if (!st_map->uvalue || !st_map->links) {
> -		__bpf_struct_ops_map_free(map);
> -		return ERR_PTR(-ENOMEM);
> +		ret = -ENOMEM;
> +		goto errout_free;
>   	}
>   
>   	mutex_init(&st_map->lock);
>   	set_vm_flush_reset_perms(st_map->image);
>   	bpf_map_init_from_attr(map, attr);
>   
> +	module_put(mod);
> +
>   	return map;
> +
> +errout_free:
> +	__bpf_struct_ops_map_free(map);
> +	btf = NULL;		/* has been released */

btf is not defined. I don't think this patch compiles.
Something from a latter patch?

> +errout:
> +	module_put(mod);
> +	return ERR_PTR(ret);
>   }
Kui-Feng Lee Oct. 31, 2023, 5:46 p.m. UTC | #2 
On 10/30/23 18:21, Martin KaFai Lau wrote:
> On 10/30/23 12:28 PM, thinker.li@gmail.com wrote:
>> @@ -681,9 +697,17 @@ static struct bpf_map 
>> *bpf_struct_ops_map_alloc(union bpf_attr *attr)
>>       if (!st_ops_desc)
>>           return ERR_PTR(-ENOTSUPP);
>> +    if (st_ops_desc->btf != btf_vmlinux) {
>> +        mod = btf_try_get_module(st_ops_desc->btf);
>> +        if (!mod)
>> +            return ERR_PTR(-EINVAL);
>> +    }
>> +
>>       vt = st_ops_desc->value_type;
>> -    if (attr->value_size != vt->size)
>> -        return ERR_PTR(-EINVAL);
>> +    if (attr->value_size != vt->size) {
>> +        ret = -EINVAL;
>> +        goto errout;
>> +    }
>>       t = st_ops_desc->type;
>> @@ -694,17 +718,17 @@ static struct bpf_map 
>> *bpf_struct_ops_map_alloc(union bpf_attr *attr)
>>           (vt->size - sizeof(struct bpf_struct_ops_value));
>>       st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
>> -    if (!st_map)
>> -        return ERR_PTR(-ENOMEM);
>> +    if (!st_map) {
>> +        ret = -ENOMEM;
>> +        goto errout;
>> +    }
>>       st_map->st_ops_desc = st_ops_desc;
>>       map = &st_map->map;
>>       ret = bpf_jit_charge_modmem(PAGE_SIZE);
>> -    if (ret) {
>> -        __bpf_struct_ops_map_free(map);
>> -        return ERR_PTR(ret);
>> -    }
>> +    if (ret)
>> +        goto errout_free;
>>       st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
>>       if (!st_map->image) {
>> @@ -713,23 +737,32 @@ static struct bpf_map 
>> *bpf_struct_ops_map_alloc(union bpf_attr *attr)
>>            * here.
>>            */
>>           bpf_jit_uncharge_modmem(PAGE_SIZE);
>> -        __bpf_struct_ops_map_free(map);
>> -        return ERR_PTR(-ENOMEM);
>> +        ret = -ENOMEM;
>> +        goto errout_free;
>>       }
>>       st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
>>       st_map->links =
>>           bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct 
>> bpf_links *),
>>                      NUMA_NO_NODE);
>>       if (!st_map->uvalue || !st_map->links) {
>> -        __bpf_struct_ops_map_free(map);
>> -        return ERR_PTR(-ENOMEM);
>> +        ret = -ENOMEM;
>> +        goto errout_free;
>>       }
>>       mutex_init(&st_map->lock);
>>       set_vm_flush_reset_perms(st_map->image);
>>       bpf_map_init_from_attr(map, attr);
>> +    module_put(mod);
>> +
>>       return map;
>> +
>> +errout_free:
>> +    __bpf_struct_ops_map_free(map);
>> +    btf = NULL;        /* has been released */
> 
> btf is not defined. I don't think this patch compiles.
> Something from a latter patch?

Yes, it is defined in the next patch. I will fix it.

> 
>> +errout:
>> +    module_put(mod);
>> +    return ERR_PTR(ret);
>>   }
>
diff mbox series

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 77dd9a522d55..c993df3cf699 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1626,6 +1626,7 @@  struct bpf_struct_ops {
 	void (*unreg)(void *kdata);
 	int (*update)(void *kdata, void *old_kdata);
 	int (*validate)(void *kdata);
+	struct module *owner;
 	const char *name;
 	struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
 };
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 933a227573da..a8813605f2f6 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -576,7 +576,7 @@  struct bpf_struct_ops;
 struct bpf_struct_ops_desc;
 
 struct bpf_struct_ops_desc *
-btf_add_struct_ops(struct bpf_struct_ops *st_ops);
+btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops);
 const struct bpf_struct_ops_desc *
 btf_get_struct_ops(struct btf *btf, u32 *ret_cnt);
 
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 0bc21a39257d..b0b8cf9ed057 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -388,6 +388,7 @@  static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	const struct btf_member *member;
 	const struct btf_type *t = st_ops_desc->type;
 	struct bpf_tramp_links *tlinks;
+	struct module *mod = NULL;
 	void *udata, *kdata;
 	int prog_fd, err;
 	void *image, *image_end;
@@ -425,6 +426,14 @@  static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		goto unlock;
 	}
 
+	if (st_ops_desc->btf != btf_vmlinux) {
+		mod = btf_try_get_module(st_ops_desc->btf);
+		if (!mod) {
+			err = -EINVAL;
+			goto unlock;
+		}
+	}
+
 	memcpy(uvalue, value, map->value_size);
 
 	udata = &uvalue->data;
@@ -552,6 +561,10 @@  static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		 * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set.
 		 */
 		smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE);
+		/* Hold the owner module until the struct_ops is
+		 * unregistered
+		 */
+		mod = NULL;
 		goto unlock;
 	}
 
@@ -568,6 +581,7 @@  static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	memset(uvalue, 0, map->value_size);
 	memset(kvalue, 0, map->value_size);
 unlock:
+	module_put(mod);
 	kfree(tlinks);
 	mutex_unlock(&st_map->lock);
 	return err;
@@ -588,6 +602,7 @@  static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
 	switch (prev_state) {
 	case BPF_STRUCT_OPS_STATE_INUSE:
 		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data);
+		module_put(st_map->st_ops_desc->st_ops->owner);
 		bpf_map_put(map);
 		return 0;
 	case BPF_STRUCT_OPS_STATE_TOBEFREE:
@@ -674,6 +689,7 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	size_t st_map_size;
 	struct bpf_struct_ops_map *st_map;
 	const struct btf_type *t, *vt;
+	struct module *mod = NULL;
 	struct bpf_map *map;
 	int ret;
 
@@ -681,9 +697,17 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	if (!st_ops_desc)
 		return ERR_PTR(-ENOTSUPP);
 
+	if (st_ops_desc->btf != btf_vmlinux) {
+		mod = btf_try_get_module(st_ops_desc->btf);
+		if (!mod)
+			return ERR_PTR(-EINVAL);
+	}
+
 	vt = st_ops_desc->value_type;
-	if (attr->value_size != vt->size)
-		return ERR_PTR(-EINVAL);
+	if (attr->value_size != vt->size) {
+		ret = -EINVAL;
+		goto errout;
+	}
 
 	t = st_ops_desc->type;
 
@@ -694,17 +718,17 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		(vt->size - sizeof(struct bpf_struct_ops_value));
 
 	st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
-	if (!st_map)
-		return ERR_PTR(-ENOMEM);
+	if (!st_map) {
+		ret = -ENOMEM;
+		goto errout;
+	}
 
 	st_map->st_ops_desc = st_ops_desc;
 	map = &st_map->map;
 
 	ret = bpf_jit_charge_modmem(PAGE_SIZE);
-	if (ret) {
-		__bpf_struct_ops_map_free(map);
-		return ERR_PTR(ret);
-	}
+	if (ret)
+		goto errout_free;
 
 	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
 	if (!st_map->image) {
@@ -713,23 +737,32 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		 * here.
 		 */
 		bpf_jit_uncharge_modmem(PAGE_SIZE);
-		__bpf_struct_ops_map_free(map);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto errout_free;
 	}
 	st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
 	st_map->links =
 		bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
 				   NUMA_NO_NODE);
 	if (!st_map->uvalue || !st_map->links) {
-		__bpf_struct_ops_map_free(map);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto errout_free;
 	}
 
 	mutex_init(&st_map->lock);
 	set_vm_flush_reset_perms(st_map->image);
 	bpf_map_init_from_attr(map, attr);
 
+	module_put(mod);
+
 	return map;
+
+errout_free:
+	__bpf_struct_ops_map_free(map);
+	btf = NULL;		/* has been released */
+errout:
+	module_put(mod);
+	return ERR_PTR(ret);
 }
 
 static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map)
@@ -811,6 +844,7 @@  static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link)
 		 * bpf_struct_ops_link_create() fails to register.
 		 */
 		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data);
+		module_put(st_map->st_ops_desc->st_ops->owner);
 		bpf_map_put(&st_map->map);
 	}
 	kfree(st_link);
@@ -857,6 +891,10 @@  static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 	if (!bpf_struct_ops_valid_to_reg(new_map))
 		return -EINVAL;
 
+	/* The old map is holding the refcount for the owner module.  The
+	 * ownership of the owner module refcount is going to be
+	 * transferred from the old map to the new map.
+	 */
 	if (!st_map->st_ops_desc->st_ops->update)
 		return -EOPNOTSUPP;
 
@@ -902,6 +940,7 @@  int bpf_struct_ops_link_create(union bpf_attr *attr)
 	struct bpf_link_primer link_primer;
 	struct bpf_struct_ops_map *st_map;
 	struct bpf_map *map;
+	struct btf *btf;
 	int err;
 
 	map = bpf_map_get(attr->link_create.map_fd);
@@ -926,8 +965,15 @@  int bpf_struct_ops_link_create(union bpf_attr *attr)
 	if (err)
 		goto err_out;
 
+	/* Hold the owner module until the struct_ops is unregistered. */
+	btf = st_map->st_ops_desc->btf;
+	if (btf != btf_vmlinux && !btf_try_get_module(btf)) {
+		err = -EINVAL;
+		goto err_out;
+	}
 	err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data);
 	if (err) {
+		module_put(st_map->st_ops_desc->st_ops->owner);
 		bpf_link_cleanup(&link_primer);
 		link = NULL;
 		goto err_out;