x86, kaslr: Prevent .bss from overlaping initrd

When choosing a random address, the current implementation does not take into
account the reversed space for .bss and .brk sections. Thus the relocated kernel
may overlap other components in memory. Here is an example of the overlap from a
x86_64 kernel in qemu (the ranges of physical addresses are presented):

 Physical Address

    0x0fe00000                  --+--------------------+  <-- randomized base
                               /  |  relocated kernel  |
                   vmlinux.bin    | (from vmlinux.bin) |
    0x1336d000    (an ELF file)   +--------------------+--
                               \  |                    |  \
    0x1376d870                  --+--------------------+   |
                                  |    relocs table    |   |
    0x13c1c2a8                    +--------------------+   .bss and .brk
                                  |                    |   |
    0x13ce6000                    +--------------------+   |
                                  |                    |  /
    0x13f77000                    |       initrd       |--
                                  |                    |
    0x13fef374                    +--------------------+

The initrd image will then be overwritten by the memset during early
initialization:

[    1.655204] Unpacking initramfs...
[    1.662831] Initramfs unpacking failed: junk in compressed archive

This patch prevents the above situation by requiring a larger space when looking
for a random kernel base, so that existing logic can effectively avoids the
overlap.

[kees: switched to perl to avoid hex translation pain in mawk vs gawk]
[kees: calculated overlap without relocs table]

Fixes: 82fa963 ("x86, kaslr: Select random position from e820 maps")
Reported-by: Fengguang Wu <[email protected]>
Signed-off-by: Junjie Mao <[email protected]>
Signed-off-by: Kees Cook <[email protected]>
Cc: Josh Triplett <[email protected]>
Cc: Matt Fleming <[email protected]>
Cc: Ard Biesheuvel <[email protected]>
Cc: Vivek Goyal <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Thomas Gleixner <[email protected]>

Author: Junjie Mao

arch/x86/boot/compressed/Makefile

@@ -76,8 +76,10 @@ suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
+RUN_SIZE = $(shell objdump -h vmlinux | \
+	     perl $(srctree)/arch/x86/tools/calc_run_size.pl)
 quiet_cmd_mkpiggy = MKPIGGY $@
-      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
+      cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
 
 targets += piggy.S
 $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE

arch/x86/boot/compressed/head_32.S

@@ -207,7 +207,8 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
 				/* push arguments for decompress_kernel: */
-	pushl	$z_output_len	/* decompressed length */
+	pushl	$z_run_size	/* size of kernel with .bss and .brk */
+	pushl	$z_output_len	/* decompressed length, end of relocs */
 	leal	z_extract_offset_negative(%ebx), %ebp
 	pushl	%ebp		/* output address */
 	pushl	$z_input_len	/* input_len */
@@ -217,7 +218,7 @@ relocated:
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
 	call	decompress_kernel /* returns kernel location in %eax */
-	addl	$24, %esp
+	addl	$28, %esp
 
 /*
  * Jump to the decompressed kernel.

arch/x86/boot/compressed/head_64.S

@@ -402,13 +402,16 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
 	pushq	%rsi			/* Save the real mode argument */
+	movq	$z_run_size, %r9	/* size of kernel with .bss and .brk */
+	pushq	%r9
 	movq	%rsi, %rdi		/* real mode address */
 	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
 	leaq	input_data(%rip), %rdx  /* input_data */
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
-	movq	$z_output_len, %r9	/* decompressed length */
+	movq	$z_output_len, %r9	/* decompressed length, end of relocs */
 	call	decompress_kernel	/* returns kernel location in %rax */
+	popq	%r9
 	popq	%rsi
 
 /*

arch/x86/boot/compressed/misc.c

@@ -358,7 +358,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
-				  unsigned long output_len)
+				  unsigned long output_len,
+				  unsigned long run_size)
 {
 	real_mode = rmode;
 
@@ -381,8 +382,14 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
-	output = choose_kernel_location(input_data, input_len,
-					output, output_len);
+	/*
+	 * The memory hole needed for the kernel is the larger of either
+	 * the entire decompressed kernel plus relocation table, or the
+	 * entire decompressed kernel plus .bss and .brk sections.
+	 */
+	output = choose_kernel_location(input_data, input_len, output,
+					output_len > run_size ? output_len
+							      : run_size);
 
 	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))

arch/x86/boot/compressed/mkpiggy.c

@@ -36,11 +36,13 @@ int main(int argc, char *argv[])
 	uint32_t olen;
 	long ilen;
 	unsigned long offs;
+	unsigned long run_size;
 	FILE *f = NULL;
 	int retval = 1;
 
-	if (argc < 2) {
-		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
+	if (argc < 3) {
+		fprintf(stderr, "Usage: %s compressed_file run_size\n",
+				argv[0]);
 		goto bail;
 	}
 
@@ -74,6 +76,7 @@ int main(int argc, char *argv[])
 	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
 	offs += 64*1024 + 128;	/* Add 64K + 128 bytes slack */
 	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+	run_size = atoi(argv[2]);
 
 	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
 	printf(".globl z_input_len\n");
@@ -85,6 +88,8 @@ int main(int argc, char *argv[])
 	/* z_extract_offset_negative allows simplification of head_32.S */
 	printf(".globl z_extract_offset_negative\n");
 	printf("z_extract_offset_negative = -0x%lx\n", offs);
+	printf(".globl z_run_size\n");
+	printf("z_run_size = %lu\n", run_size);
 
 	printf(".globl input_data, input_data_end\n");
 	printf("input_data:\n");

arch/x86/tools/calc_run_size.pl

@@ -0,0 +1,30 @@
+#!/usr/bin/perl
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | perl calc_run_size.pl
+use strict;
+
+my $mem_size = 0;
+my $file_offset = 0;
+
+my $sections=" *[0-9]+ \.(?:bss|brk) +";
+while (<>) {
+	if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
+		my $size = hex($1);
+		my $offset = hex($2);
+		$mem_size += $size;
+		if ($file_offset == 0) {
+			$file_offset = $offset;
+		} elsif ($file_offset != $offset) {
+			die ".bss and .brk lack common file offset\n";
+		}
+	}
+}
+
+if ($file_offset == 0) {
+	die "Never found .bss or .brk file offset\n";
+}
+printf("%d\n", $mem_size + $file_offset);