@@ -85,8 +85,23 @@ startup_64:
popq %rsi
/* Form the CR3 value being sure to include the CR3 modifier */
- addq $(early_top_pgt - __START_KERNEL_map), %rax
+ addq _early_top_pgt_offset(%rip), %rax
jmp 1f
+
+ /*
+ * Position Independent Code takes only relative references in code
+ * meaning a global variable address is relative to RIP and not its
+ * future virtual address. Global variables can be used instead as they
+ * are still relocated on the expected kernel mapping address.
+ */
+ .align 8
+_early_top_pgt_offset:
+ .quad early_top_pgt - __START_KERNEL_map
+_init_top_offset:
+ .quad init_top_pgt - __START_KERNEL_map
+_va_jump:
+ .quad 2f
+
ENTRY(secondary_startup_64)
/*
* At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0,
@@ -114,7 +129,7 @@ ENTRY(secondary_startup_64)
popq %rsi
/* Form the CR3 value being sure to include the CR3 modifier */
- addq $(init_top_pgt - __START_KERNEL_map), %rax
+ addq _init_top_offset(%rip), %rax
1:
/* Enable PAE mode, PGE and LA57 */
@@ -129,9 +144,8 @@ ENTRY(secondary_startup_64)
movq %rax, %cr3
/* Ensure I am executing from virtual addresses */
- movq $1f, %rax
- jmp *%rax
-1:
+ jmp *_va_jump(%rip)
+2:
/* Check if nx is implemented */
movl $0x80000001, %eax
@@ -227,11 +241,12 @@ ENTRY(secondary_startup_64)
* REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
* address given in m16:64.
*/
- pushq $.Lafter_lret # put return address on stack for unwinder
+ leaq .Lafter_lret(%rip), %rax
+ pushq %rax # put return address on stack for unwinder
xorq %rbp, %rbp # clear frame pointer
- movq initial_code(%rip), %rax
+ leaq initial_code(%rip), %rax
pushq $__KERNEL_CS # set correct cs
- pushq %rax # target address in negative space
+ pushq (%rax) # target address in negative space
lretq
.Lafter_lret:
ENDPROC(secondary_startup_64)
Change the assembly code to use only relative references of symbols for the kernel to be PIE compatible. Early at boot, the kernel is mapped at a temporary address while preparing the page table. To know the changes needed for the page table with KASLR, the boot code calculate the difference between the expected address of the kernel and the one chosen by KASLR. It does not work with PIE because all symbols in code are relatives. Instead of getting the future relocated virtual address, you will get the current temporary mapping. The solution is using global variables that will be relocated as expected. Position Independent Executable (PIE) support will allow to extended the KASLR randomization range below the -2G memory limit. Signed-off-by: Thomas Garnier <thgarnie@google.com> --- arch/x86/kernel/head_64.S | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-)