maccess: always use strict semantics for probe_kernel_read

Except for historical confusion in the kprobes/uprobes and bpf tracers,
which has been fixed now, there is no good reason to ever allow user
memory accesses from probe_kernel_read.  Switch probe_kernel_read to only
read from kernel memory.

[akpm@linux-foundation.org: update it for "mm, dump_page(): do not crash with invalid mapping pointer"]

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20200521152301.2587579-17-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index 5b75c35d1da0d5039b4509b78ed8551729f61d7d..94a9fe2702c2f4922418084b28c74c26b35edc6c 100644 (file)
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -57,7 +57,7 @@ void * memcpy(void * dst,const void *src, size_t count)
 EXPORT_SYMBOL(raw_copy_in_user);
 EXPORT_SYMBOL(memcpy);
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, bool strict)
+bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 {
        if ((unsigned long)unsafe_src < PAGE_SIZE)
                return false;

diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
index ad2c538ce497c6e2d530ff9a8854e10713ff0c9e..e929c0966696c4dd4ee230a55a4efd2cef12a4ff 100644 (file)
--- a/arch/um/kernel/maccess.c
+++ b/arch/um/kernel/maccess.c
@@ -7,7 +7,7 @@
 #include <linux/kernel.h>
 #include <os.h>
 
-bool probe_kernel_read_allowed(const void *src, size_t size, bool strict)
+bool probe_kernel_read_allowed(const void *src, size_t size)
 {
        void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
 

diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 86000c1150e867b689d43c00711f9fbb8cc20ea0..e1d7d7477c22dc46bd6f56ed0a9ea2cb94975b5c 100644 (file)
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -9,13 +9,10 @@ static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
        return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
 }
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, bool strict)
+bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 {
        unsigned long vaddr = (unsigned long)unsafe_src;
 
-       if (!strict)
-               return true;
-
        /*
         * Range covering the highest possible canonical userspace address
         * as well as non-canonical address range. For the canonical range
@@ -25,10 +22,8 @@ bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, bool strict)
               canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr;
 }
 #else
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, bool strict)
+bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 {
-       if (!strict)
-               return true;
        return (unsigned long)unsafe_src >= TASK_SIZE_MAX;
 }
 #endif

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 4183e585dee6d7ef126813920e7a6b8e1e1433ee..dac1db05bf7e5af72d51b71ea035ee52b452399a 100644 (file)
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -301,11 +301,9 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
        return 0;
 }
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size,
-               bool strict);
+bool probe_kernel_read_allowed(const void *unsafe_src, size_t size);
 
 extern long probe_kernel_read(void *dst, const void *src, size_t size);
-extern long probe_kernel_read_strict(void *dst, const void *src, size_t size);
 extern long probe_user_read(void *dst, const void __user *src, size_t size);
 
 extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 59cb1988889182567d996881e1c6626a47e42c1f..e729c9e587a076a57d8dc652481da8423a58d2f4 100644 (file)
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -196,7 +196,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
 
        if (unlikely(ret < 0))
                goto fail;
-       ret = probe_kernel_read_strict(dst, unsafe_ptr, size);
+       ret = probe_kernel_read(dst, unsafe_ptr, size);
        if (unlikely(ret < 0))
                goto fail;
        return ret;

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6a23b45613a2da638b32cd9289971fee06a74d0a..ea8d0b094f1b51bac391c2460e2a2ca010de9d0b 100644 (file)
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1222,7 +1222,7 @@ fetch_store_strlen(unsigned long addr)
 #endif
 
        do {
-               ret = probe_kernel_read_strict(&c, (u8 *)addr + len, 1);
+               ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
                len++;
        } while (c && ret == 0 && len < MAX_STRING_SIZE);
 
@@ -1300,7 +1300,7 @@ probe_mem_read(void *dest, void *src, size_t size)
        if ((unsigned long)src < TASK_SIZE)
                return probe_mem_read_user(dest, src, size);
 #endif
-       return probe_kernel_read_strict(dest, src, size);
+       return probe_kernel_read(dest, src, size);
 }
 
 /* Note that we don't verify it, since the code does not come from user space */

diff --git a/mm/debug.c b/mm/debug.c
index f2ede2df585a9640f033224231339199ad576071..b5b1de8c71ac517cc9c957a43379dfacfb52e8d9 100644 (file)
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -120,9 +120,9 @@ void __dump_page(struct page *page, const char *reason)
                 * mapping can be invalid pointer and we don't want to crash
                 * accessing it, so probe everything depending on it carefully
                 */
-               if (probe_kernel_read_strict(&host, &mapping->host,
-                                               sizeof(struct inode *)) ||
-                   probe_kernel_read_strict(&a_ops, &mapping->a_ops,
+               if (probe_kernel_read(&host, &mapping->host,
+                                       sizeof(struct inode *)) ||
+                   probe_kernel_read(&a_ops, &mapping->a_ops,
                                sizeof(struct address_space_operations *))) {
                        pr_warn("failed to read mapping->host or a_ops, mapping not a valid kernel address?\n");
                        goto out_mapping;
@@ -133,7 +133,7 @@ void __dump_page(struct page *page, const char *reason)
                        goto out_mapping;
                }
 
-               if (probe_kernel_read_strict(&dentry_first,
+               if (probe_kernel_read(&dentry_first,
                        &host->i_dentry.first, sizeof(struct hlist_node *))) {
                        pr_warn("mapping->a_ops:%ps with invalid mapping->host inode address %px\n",
                                a_ops, host);
@@ -146,7 +146,7 @@ void __dump_page(struct page *page, const char *reason)
                }
 
                dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
-               if (probe_kernel_read_strict(&dentry, dentry_ptr,
+               if (probe_kernel_read(&dentry, dentry_ptr,
                                                        sizeof(struct dentry))) {
                        pr_warn("mapping->aops:%ps with invalid mapping->host->i_dentry.first %px\n",
                                a_ops, dentry_ptr);

diff --git a/mm/maccess.c b/mm/maccess.c
index 85d124628b0efbfa788dd78a30bb3d0c75e94327..253b786b2bf1779bf61c4a675efa83583582b20a 100644 (file)
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -6,36 +6,13 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 
-static long __probe_kernel_read(void *dst, const void *src, size_t size,
-               bool strict);
-
-bool __weak probe_kernel_read_allowed(const void *unsafe_src, size_t size,
-               bool strict)
+bool __weak probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 {
        return true;
 }
 
 /**
- * probe_kernel_read(): safely attempt to read from any location
- * @dst: pointer to the buffer that shall take the data
- * @src: address to read from
- * @size: size of the data chunk
- *
- * Same as probe_kernel_read_strict() except that for architectures with
- * not fully separated user and kernel address spaces this function also works
- * for user address tanges.
- *
- * DO NOT USE THIS FUNCTION - it is broken on architectures with entirely
- * separate kernel and user address spaces, and also a bad idea otherwise.
- */
-long probe_kernel_read(void *dst, const void *src, size_t size)
-{
-       return __probe_kernel_read(dst, src, size, false);
-}
-EXPORT_SYMBOL_GPL(probe_kernel_read);
-
-/**
- * probe_kernel_read_strict(): safely attempt to read from kernel-space
+ * probe_kernel_read(): safely attempt to read from kernel-space
  * @dst: pointer to the buffer that shall take the data
  * @src: address to read from
  * @size: size of the data chunk
@@ -48,18 +25,12 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * probe_kernel_read() suitable for use within regions where the caller
  * already holds mmap_lock, or other locks which nest inside mmap_lock.
  */
-long probe_kernel_read_strict(void *dst, const void *src, size_t size)
-{
-       return __probe_kernel_read(dst, src, size, true);
-}
-
-static long __probe_kernel_read(void *dst, const void *src, size_t size,
-               bool strict)
+long probe_kernel_read(void *dst, const void *src, size_t size)
 {
        long ret;
        mm_segment_t old_fs = get_fs();
 
-       if (!probe_kernel_read_allowed(src, size, strict))
+       if (!probe_kernel_read_allowed(src, size))
                return -EFAULT;
 
        set_fs(KERNEL_DS);
@@ -73,6 +44,7 @@ static long __probe_kernel_read(void *dst, const void *src, size_t size,
                return -EFAULT;
        return 0;
 }
+EXPORT_SYMBOL_GPL(probe_kernel_read);
 
 /**
  * probe_user_read(): safely attempt to read from a user-space location
@@ -181,7 +153,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
 
        if (unlikely(count <= 0))
                return 0;
-       if (!probe_kernel_read_allowed(unsafe_addr, count, true))
+       if (!probe_kernel_read_allowed(unsafe_addr, count))
                return -EFAULT;
 
        set_fs(KERNEL_DS);