kexec: introduce a protection mechanism for the crashkernel reserved …

…memory

For the cases that some kernel (module) path stamps the crash reserved
memory(already mapped by the kernel) where has been loaded the second
kernel data, the kdump kernel will probably fail to boot when panic
happens (or even not happens) leaving the culprit at large, this is
unacceptable.

The patch introduces a mechanism for detecting such cases:

1) After each crash kexec loading, it simply marks the reserved memory
   regions readonly since we no longer access it after that.  When someone
   stamps the region, the first kernel will panic and trigger the kdump.
   The weak arch_kexec_protect_crashkres() is introduced to do the actual
   protection.

2) To allow multiple loading, once 1) was done we also need to remark
   the reserved memory to readwrite each time a system call related to
   kdump is made.  The weak arch_kexec_unprotect_crashkres() is introduced
   to do the actual protection.

The architecture can make its specific implementation by overriding
arch_kexec_protect_crashkres() and arch_kexec_unprotect_crashkres().

Signed-off-by: Xunlei Pang <[email protected]>
Cc: Eric Biederman <[email protected]>
Cc: Dave Young <[email protected]>
Cc: Minfei Huang <[email protected]>
Cc: Vivek Goyal <[email protected]>
Cc: Baoquan He <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/kexec.h

@@ -317,6 +317,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
 					Elf_Shdr *sechdrs, unsigned int relsec);
 int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 					unsigned int relsec);
+void arch_kexec_protect_crashkres(void);
+void arch_kexec_unprotect_crashkres(void);
 
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;

kernel/kexec.c

@@ -167,8 +167,12 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
 		return -EBUSY;
 
 	dest_image = &kexec_image;
-	if (flags & KEXEC_ON_CRASH)
+	if (flags & KEXEC_ON_CRASH) {
 		dest_image = &kexec_crash_image;
+		if (kexec_crash_image)
+			arch_kexec_unprotect_crashkres();
+	}
+
 	if (nr_segments > 0) {
 		unsigned long i;
 
@@ -211,6 +215,9 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
 	image = xchg(dest_image, image);
 
 out:
+	if ((flags & KEXEC_ON_CRASH) && kexec_crash_image)
+		arch_kexec_protect_crashkres();
+
 	mutex_unlock(&kexec_mutex);
 	kimage_free(image);
 

kernel/kexec_core.c

@@ -1563,3 +1563,9 @@ void __weak crash_map_reserved_pages(void)
 
 void __weak crash_unmap_reserved_pages(void)
 {}
+
+void __weak arch_kexec_protect_crashkres(void)
+{}
+
+void __weak arch_kexec_unprotect_crashkres(void)
+{}

kernel/kexec_file.c

@@ -274,8 +274,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 		return -EBUSY;
 
 	dest_image = &kexec_image;
-	if (flags & KEXEC_FILE_ON_CRASH)
+	if (flags & KEXEC_FILE_ON_CRASH) {
 		dest_image = &kexec_crash_image;
+		if (kexec_crash_image)
+			arch_kexec_unprotect_crashkres();
+	}
 
 	if (flags & KEXEC_FILE_UNLOAD)
 		goto exchange;
@@ -324,6 +327,9 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 exchange:
 	image = xchg(dest_image, image);
 out:
+	if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
+		arch_kexec_protect_crashkres();
+
 	mutex_unlock(&kexec_mutex);
 	kimage_free(image);
 	return ret;