diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst
index 8ebe46b1af39d88171acc6055759db0b8799ff20..5dfcc4592b23efe335673ea13ba34fbbe4da6338 100644
--- a/Documentation/core-api/printk-formats.rst
+++ b/Documentation/core-api/printk-formats.rst
@@ -112,6 +112,20 @@ used when printing stack backtraces. The specifier takes into
consideration the effect of compiler optimisations which may occur
when tail-calls are used and marked with the noreturn GCC attribute.
+Probed Pointers from BPF / tracing
+----------------------------------
+
+::
+
+ %pks kernel string
+ %pus user string
+
+The ``k`` and ``u`` specifiers are used for printing prior probed memory from
+either kernel memory (k) or user memory (u). The subsequent ``s`` specifier
+results in printing a string. For direct use in regular vsnprintf() the (k)
+and (u) annotation is ignored, however, when used out of BPF's bpf_trace_printk(),
+for example, it reads the memory it is pointing to without faulting.
+
Kernel Pointers
---------------
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 66a04f6f477530090070fb46a26baa7cc240165c..c77c93c485a081745acdd98c39d693ffc6eae3a6 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -12,6 +12,7 @@ config ARM
select ARCH_HAS_KEEPINITRD
select ARCH_HAS_KCOV
select ARCH_HAS_MEMBARRIER_SYNC_CORE
+ select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
select ARCH_HAS_PHYS_TO_DMA
select ARCH_HAS_SETUP_DMA_OPS
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 40fb05d96c6072c9357cf69965ca006c0a5fdb27..5d513f461957b5e416113bada2688a8ee7f34179 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -20,6 +20,7 @@ config ARM64
select ARCH_HAS_KCOV
select ARCH_HAS_KEEPINITRD
select ARCH_HAS_MEMBARRIER_SYNC_CORE
+ select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PTE_DEVMAP
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SETUP_DMA_OPS
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1197b5596d5ad8959d242bd5f1666690e368de7d..2d3f963fd6f13e14c943d9e732abded33e532c3f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -68,6 +68,7 @@ config X86
select ARCH_HAS_KCOV if X86_64
select ARCH_HAS_MEM_ENCRYPT
select ARCH_HAS_MEMBARRIER_SYNC_CORE
+ select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_PTE_DEVMAP if X86_64
select ARCH_HAS_PTE_SPECIAL
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 9cd4455528e507c9e5b05cf5c63e7e7a1e7ec25b..21f4fff9e4cd3a71ca5b6fbff07a6769087658b3 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -243,7 +243,7 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name,
char **value)
LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size)
LSM_HOOK(int, 0, ismaclabel, const char *name)
-LSM_HOOK(int, 0, secid_to_secctx, u32 secid, char **secdata,
+LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata,
u32 *seclen)
LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid)
LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen)
diff --git a/init/Kconfig b/init/Kconfig
index 9e22ee8fbd75e2dbe2d80fa0952e0393e4ee01dd..6fd13a051342e4371373f4c45fa7c441fe07f8b2 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2279,6 +2279,9 @@ config ASN1
source "kernel/Kconfig.locks"
+config ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ bool
+
config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
bool
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 95d77770353c9bb5af0311f5813471e11d70c86e..1d6120fd5ba687293cef2bda8902d9c97f64d22f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -486,7 +486,12 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
if (!(map->map_flags & BPF_F_MMAPABLE))
return -EINVAL;
- return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
+ if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) >
+ PAGE_ALIGN((u64)array->map.max_entries * array->elem_size))
+ return -EINVAL;
+
+ return remap_vmalloc_range(vma, array_map_vmalloc_addr(array),
+ vma->vm_pgoff + pgoff);
}
const struct bpf_map_ops array_map_ops = {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fa1d8245b9257fe6f0f40dfca35702ebe7662000..8d7ee40e2748441bd0036f9fc0528e37255c8d27 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4340,7 +4340,9 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
if (ret_type != RET_INTEGER ||
(func_id != BPF_FUNC_get_stack &&
- func_id != BPF_FUNC_probe_read_str))
+ func_id != BPF_FUNC_probe_read_str &&
+ func_id != BPF_FUNC_probe_read_kernel_str &&
+ func_id != BPF_FUNC_probe_read_user_str))
return;
ret_reg->smax_value = meta->msize_max_value;
@@ -7059,6 +7061,23 @@ static int check_return_code(struct bpf_verifier_env *env)
return 0;
range = tnum_const(0);
break;
+ case BPF_PROG_TYPE_TRACING:
+ switch (env->prog->expected_attach_type) {
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ range = tnum_const(0);
+ break;
+ case BPF_TRACE_RAW_TP:
+ case BPF_MODIFY_RETURN:
+ return 0;
+ default:
+ return -ENOTSUPP;
+ }
+ break;
+ case BPF_PROG_TYPE_EXT:
+ /* freplace program can return anything as its return value
+ * depends on the to-be-replaced kernel func or bpf program.
+ */
default:
return 0;
}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ca1796747a773baf4079405fcf0e0e93dd4cf050..a010edc37ee02577011f5b385399e9f5376a217f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -323,17 +323,15 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
/*
* Only limited trace_printk() conversion specifiers allowed:
- * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
*/
BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
u64, arg2, u64, arg3)
{
+ int i, mod[3] = {}, fmt_cnt = 0;
+ char buf[64], fmt_ptype;
+ void *unsafe_ptr = NULL;
bool str_seen = false;
- int mod[3] = {};
- int fmt_cnt = 0;
- u64 unsafe_addr;
- char buf[64];
- int i;
/*
* bpf_check()->check_func_arg()->check_stack_boundary()
@@ -359,40 +357,71 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
if (fmt[i] == 'l') {
mod[fmt_cnt]++;
i++;
- } else if (fmt[i] == 'p' || fmt[i] == 's') {
+ } else if (fmt[i] == 'p') {
mod[fmt_cnt]++;
+ if ((fmt[i + 1] == 'k' ||
+ fmt[i + 1] == 'u') &&
+ fmt[i + 2] == 's') {
+ fmt_ptype = fmt[i + 1];
+ i += 2;
+ goto fmt_str;
+ }
+
/* disallow any further format extensions */
if (fmt[i + 1] != 0 &&
!isspace(fmt[i + 1]) &&
!ispunct(fmt[i + 1]))
return -EINVAL;
- fmt_cnt++;
- if (fmt[i] == 's') {
- if (str_seen)
- /* allow only one '%s' per fmt string */
- return -EINVAL;
- str_seen = true;
-
- switch (fmt_cnt) {
- case 1:
- unsafe_addr = arg1;
- arg1 = (long) buf;
- break;
- case 2:
- unsafe_addr = arg2;
- arg2 = (long) buf;
- break;
- case 3:
- unsafe_addr = arg3;
- arg3 = (long) buf;
- break;
- }
- buf[0] = 0;
- strncpy_from_unsafe(buf,
- (void *) (long) unsafe_addr,
+
+ goto fmt_next;
+ } else if (fmt[i] == 's') {
+ mod[fmt_cnt]++;
+ fmt_ptype = fmt[i];
+fmt_str:
+ if (str_seen)
+ /* allow only one '%s' per fmt string */
+ return -EINVAL;
+ str_seen = true;
+
+ if (fmt[i + 1] != 0 &&
+ !isspace(fmt[i + 1]) &&
+ !ispunct(fmt[i + 1]))
+ return -EINVAL;
+
+ switch (fmt_cnt) {
+ case 0:
+ unsafe_ptr = (void *)(long)arg1;
+ arg1 = (long)buf;
+ break;
+ case 1:
+ unsafe_ptr = (void *)(long)arg2;
+ arg2 = (long)buf;
+ break;
+ case 2:
+ unsafe_ptr = (void *)(long)arg3;
+ arg3 = (long)buf;
+ break;
+ }
+
+ buf[0] = 0;
+ switch (fmt_ptype) {
+ case 's':
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ strncpy_from_unsafe(buf, unsafe_ptr,
sizeof(buf));
+ break;
+#endif
+ case 'k':
+ strncpy_from_unsafe_strict(buf, unsafe_ptr,
+ sizeof(buf));
+ break;
+ case 'u':
+ strncpy_from_unsafe_user(buf,
+ (__force void __user *)unsafe_ptr,
+ sizeof(buf));
+ break;
}
- continue;
+ goto fmt_next;
}
if (fmt[i] == 'l') {
@@ -403,6 +432,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
if (fmt[i] != 'i' && fmt[i] != 'd' &&
fmt[i] != 'u' && fmt[i] != 'x')
return -EINVAL;
+fmt_next:
fmt_cnt++;
}
@@ -825,14 +855,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
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;
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ case BPF_FUNC_probe_read:
+ return &bpf_probe_read_compat_proto;
case BPF_FUNC_probe_read_str:
return &bpf_probe_read_compat_str_proto;
+#endif
#ifdef CONFIG_CGROUPS
case BPF_FUNC_get_current_cgroup_id:
return &bpf_get_current_cgroup_id_proto;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 7c488a1ce318cc52c375b0db7d9db2e353dfa836..532b6606a18a605c34335b81cdb371d0d04a8b45 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -2168,6 +2168,10 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
* f full name
* P node name, including a possible unit address
* - 'x' For printing the address. Equivalent to "%lx".
+ * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of
+ * bpf_trace_printk() where [ku] prefix specifies either kernel (k)
+ * or user (u) memory to probe, and:
+ * s a string, equivalent to "%s" on direct vsnprintf() use
*
* ** When making changes please also update:
* Documentation/core-api/printk-formats.rst
@@ -2251,6 +2255,14 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
if (!IS_ERR(ptr))
break;
return err_ptr(buf, end, ptr, spec);
+ case 'u':
+ case 'k':
+ switch (fmt[1]) {
+ case 's':
+ return string(buf, end, ptr, spec);
+ default:
+ return error_string(buf, end, "(einval)", spec);
+ }
}
/* default is to _not_ leak addresses, hash before printing */
diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c
index 587b68b1f8dde6f4758dd16f8bb68a88f1816c84..430a4b7e353e662b8cbe4b896f9ad292aac8eeed 100644
--- a/samples/bpf/lwt_len_hist_user.c
+++ b/samples/bpf/lwt_len_hist_user.c
@@ -15,8 +15,6 @@
#define MAX_INDEX 64
#define MAX_STARS 38
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
static void stars(char *str, long val, long max, int width)
{
int i;
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index f3f3c3fb98cbf0fe24a7fa24aab1b050e51b4d8c..48a9c7c69ef1f78fadd64d0128307c0d67c60e1c 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -148,11 +148,11 @@ struct pt_regs;
#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
#elif defined(bpf_target_arm)
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 56d80adcf4bdec8d074d1036a87333901e2bfa59..6b9dce431d4165425981adbfc65f1ca4fde19328 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -217,6 +217,14 @@ void test_mmap(void)
munmap(tmp2, 4 * page_size);
+ /* map all 4 pages, but with pg_off=1 page, should fail */
+ tmp1 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
+ data_map_fd, page_size /* initial page shift */);
+ if (CHECK(tmp1 != MAP_FAILED, "adv_mmap7", "unexpected success")) {
+ munmap(tmp1, 4 * page_size);
+ goto cleanup;
+ }
+
tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0);
if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index 56a50b25cd33bd13668881bc2969fcfb1a35a3bb..abb7344b531f4536fd000ba716c8d953188f0307 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -30,13 +30,13 @@ int prog3(struct bpf_raw_tracepoint_args *ctx)
SEC("fentry/__set_task_comm")
int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec)
{
- return !tsk;
+ return 0;
}
SEC("fexit/__set_task_comm")
int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
{
- return !tsk;
+ return 0;
}
char _license[] SEC("license") = "GPL";