@@ -560,10 +560,13 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
* Description
* For tracing programs, safely attempt to read *size* bytes from
- * address *src* and store the data in *dst*.
+ * kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
+ * instead.
* Return
* 0 on success, or a negative error in case of failure.
*
@@ -1425,45 +1428,14 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
- * Copy a NUL terminated string from an unsafe address
- * *unsafe_ptr* to *dst*. The *size* should include the
- * terminating NUL byte. In case the string length is smaller than
- * *size*, the target is not padded with further NUL bytes. If the
- * string length is larger than *size*, just *size*-1 bytes are
- * copied and the last byte is set to NUL.
- *
- * On success, the length of the copied string is returned. This
- * makes this helper useful in tracing programs for reading
- * strings, and more importantly to get its length at runtime. See
- * the following snippet:
- *
- * ::
+ * Copy a NUL terminated string from an unsafe kernel address
+ * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * more details.
*
- * SEC("kprobe/sys_open")
- * void bpf_sys_open(struct pt_regs *ctx)
- * {
- * char buf[PATHLEN]; // PATHLEN is defined to 256
- * int res = bpf_probe_read_str(buf, sizeof(buf),
- * ctx->di);
- *
- * // Consume buf, for example push it to
- * // userspace via bpf_perf_event_output(); we
- * // can use res (the string length) as event
- * // size, after checking its boundaries.
- * }
- *
- * In comparison, using **bpf_probe_read()** helper here instead
- * to read the string would require to estimate the length at
- * compile time, and would often result in copying more memory
- * than necessary.
- *
- * Another useful use case is when parsing individual process
- * arguments or individual environment variables navigating
- * *current*\ **->mm->arg_start** and *current*\
- * **->mm->env_start**: using this helper and the return value,
- * one can quickly iterate at the right offset of the memory area.
+ * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
+ * instead.
* Return
* On success, the strictly positive length of the string,
* including the trailing NUL character. On error, a negative
@@ -2862,7 +2834,12 @@ union bpf_attr {
FN(sk_storage_get), \
FN(sk_storage_delete), \
FN(send_signal), \
- FN(tcp_gen_syncookie),
+ FN(tcp_gen_syncookie), \
+ FN(skb_output), \
+ FN(probe_read_user), \
+ FN(probe_read_kernel), \
+ FN(probe_read_user_str), \
+ FN(probe_read_kernel_str),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -138,24 +138,140 @@ static const struct bpf_func_proto bpf_override_return_proto = {
};
#endif
-BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
+BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
+ const void __user *, unsafe_ptr)
{
- int ret;
+ int ret = probe_user_read(dst, unsafe_ptr, size);
- ret = security_locked_down(LOCKDOWN_BPF_READ);
- if (ret < 0)
- goto out;
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_user_proto = {
+ .func = bpf_probe_read_user,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
+ const void __user *, unsafe_ptr)
+{
+ int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size);
+
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
+ .func = bpf_probe_read_user_str,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
- ret = probe_kernel_read(dst, unsafe_ptr, size);
+static __always_inline int
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr,
+ const bool compat)
+{
+ int ret = security_locked_down(LOCKDOWN_BPF_READ);
+
+ if (unlikely(ret < 0))
+ goto out;
+ ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) :
+ probe_kernel_read_strict(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
out:
memset(dst, 0, size);
+ return ret;
+}
+
+BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false);
+}
+
+static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
+ .func = bpf_probe_read_kernel,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true);
+}
+static const struct bpf_func_proto bpf_probe_read_compat_proto = {
+ .func = bpf_probe_read_compat,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static __always_inline int
+bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,
+ const bool compat)
+{
+ int ret = security_locked_down(LOCKDOWN_BPF_READ);
+
+ if (unlikely(ret < 0))
+ goto out;
+ /*
+ * The strncpy_from_unsafe_*() call will likely not fill the entire
+ * buffer, but that's okay in this circumstance as we're probing
+ * arbitrary memory anyway similar to bpf_probe_read_*() and might
+ * as well probe the stack. Thus, memory is explicitly cleared
+ * only in error case, so that improper users ignoring return
+ * code altogether don't copy garbage; otherwise length of string
+ * is returned that can be used for bpf_perf_event_output() et al.
+ */
+ ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) :
+ strncpy_from_unsafe_strict(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0))
+out:
+ memset(dst, 0, size);
return ret;
}
-static const struct bpf_func_proto bpf_probe_read_proto = {
- .func = bpf_probe_read,
+BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false);
+}
+
+static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
+ .func = bpf_probe_read_kernel_str,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true);
+}
+
+static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
+ .func = bpf_probe_read_compat_str,
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
@@ -583,41 +699,6 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
.arg2_type = ARG_ANYTHING,
};
-BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size,
- const void *, unsafe_ptr)
-{
- int ret;
-
- ret = security_locked_down(LOCKDOWN_BPF_READ);
- if (ret < 0)
- goto out;
-
- /*
- * The strncpy_from_unsafe() call will likely not fill the entire
- * buffer, but that's okay in this circumstance as we're probing
- * arbitrary memory anyway similar to bpf_probe_read() and might
- * as well probe the stack. Thus, memory is explicitly cleared
- * only in error case, so that improper users ignoring return
- * code altogether don't copy garbage; otherwise length of string
- * is returned that can be used for bpf_perf_event_output() et al.
- */
- ret = strncpy_from_unsafe(dst, unsafe_ptr, size);
- if (unlikely(ret < 0))
-out:
- memset(dst, 0, size);
-
- return ret;
-}
-
-static const struct bpf_func_proto bpf_probe_read_str_proto = {
- .func = bpf_probe_read_str,
- .gpl_only = true,
- .ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_UNINIT_MEM,
- .arg2_type = ARG_CONST_SIZE_OR_ZERO,
- .arg3_type = ARG_ANYTHING,
-};
-
struct send_signal_irq_work {
struct irq_work irq_work;
struct task_struct *task;
@@ -697,8 +778,6 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_pop_elem_proto;
case BPF_FUNC_map_peek_elem:
return &bpf_map_peek_elem_proto;
- case BPF_FUNC_probe_read:
- return &bpf_probe_read_proto;
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_tail_call:
@@ -725,8 +804,18 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_current_task_under_cgroup_proto;
case BPF_FUNC_get_prandom_u32:
return &bpf_get_prandom_u32_proto;
+ case BPF_FUNC_probe_read_user:
+ return &bpf_probe_read_user_proto;
+ case BPF_FUNC_probe_read_kernel:
+ return &bpf_probe_read_kernel_proto;
+ case BPF_FUNC_probe_read:
+ return &bpf_probe_read_compat_proto;
+ case BPF_FUNC_probe_read_user_str:
+ return &bpf_probe_read_user_str_proto;
+ case BPF_FUNC_probe_read_kernel_str:
+ return &bpf_probe_read_kernel_str_proto;
case BPF_FUNC_probe_read_str:
- return &bpf_probe_read_str_proto;
+ return &bpf_probe_read_compat_str_proto;
#ifdef CONFIG_CGROUPS
case BPF_FUNC_get_current_cgroup_id:
return &bpf_get_current_cgroup_id_proto;
@@ -560,10 +560,13 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
* Description
* For tracing programs, safely attempt to read *size* bytes from
- * address *src* and store the data in *dst*.
+ * kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
+ * instead.
* Return
* 0 on success, or a negative error in case of failure.
*
@@ -1425,45 +1428,14 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
- * Copy a NUL terminated string from an unsafe address
- * *unsafe_ptr* to *dst*. The *size* should include the
- * terminating NUL byte. In case the string length is smaller than
- * *size*, the target is not padded with further NUL bytes. If the
- * string length is larger than *size*, just *size*-1 bytes are
- * copied and the last byte is set to NUL.
- *
- * On success, the length of the copied string is returned. This
- * makes this helper useful in tracing programs for reading
- * strings, and more importantly to get its length at runtime. See
- * the following snippet:
- *
- * ::
+ * Copy a NUL terminated string from an unsafe kernel address
+ * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * more details.
*
- * SEC("kprobe/sys_open")
- * void bpf_sys_open(struct pt_regs *ctx)
- * {
- * char buf[PATHLEN]; // PATHLEN is defined to 256
- * int res = bpf_probe_read_str(buf, sizeof(buf),
- * ctx->di);
- *
- * // Consume buf, for example push it to
- * // userspace via bpf_perf_event_output(); we
- * // can use res (the string length) as event
- * // size, after checking its boundaries.
- * }
- *
- * In comparison, using **bpf_probe_read()** helper here instead
- * to read the string would require to estimate the length at
- * compile time, and would often result in copying more memory
- * than necessary.
- *
- * Another useful use case is when parsing individual process
- * arguments or individual environment variables navigating
- * *current*\ **->mm->arg_start** and *current*\
- * **->mm->env_start**: using this helper and the return value,
- * one can quickly iterate at the right offset of the memory area.
+ * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
+ * instead.
* Return
* On success, the strictly positive length of the string,
* including the trailing NUL character. On error, a negative
@@ -2862,7 +2834,12 @@ union bpf_attr {
FN(sk_storage_get), \
FN(sk_storage_delete), \
FN(send_signal), \
- FN(tcp_gen_syncookie),
+ FN(tcp_gen_syncookie), \
+ FN(skb_output), \
+ FN(probe_read_user), \
+ FN(probe_read_kernel), \
+ FN(probe_read_user_str), \
+ FN(probe_read_kernel_str),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call