mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2025-01-01 10:45:49 +00:00
872bb37f68
The codgen for adding architecture-specific stack alignment to the effective alloca() usage is somewhat inefficient and allows a bit to get carried beyond the desired entropy range. This isn't really a problem, but it's unexpected and the codegen is kind of bad. Quoting Mark[1], the disassembly for arm64's invoke_syscall() looks like: // offset = raw_cpu_read(kstack_offset) mov x4, sp adrp x0, kstack_offset mrs x5, tpidr_el1 add x0, x0, #:lo12:kstack_offset ldr w0, [x0, x5] // offset = KSTACK_OFFSET_MAX(offset) and x0, x0, #0x3ff // alloca(offset) add x0, x0, #0xf and x0, x0, #0x7f0 sub sp, x4, x0 ... which in C would be: offset = raw_cpu_read(kstack_offset) offset &= 0x3ff; // [0x0, 0x3ff] offset += 0xf; // [0xf, 0x40e] offset &= 0x7f0; // [0x0, ... so when *all* bits [3:0] are 0, they'll have no impact, and when *any* of bits [3:0] are 1 they'll trigger a carry into bit 4, which could ripple all the way up and spill into bit 10. Switch the masking in KSTACK_OFFSET_MAX() to explicitly clear the bottom bits to avoid the rounding by using 0b1111110000 instead of 0b1111111111: // offset = raw_cpu_read(kstack_offset) mov x4, sp adrp x0, 0 <kstack_offset> mrs x5, tpidr_el1 add x0, x0, #:lo12:kstack_offset ldr w0, [x0, x5] // offset = KSTACK_OFFSET_MAX(offset) and x0, x0, #0x3f0 // alloca(offset) sub sp, x4, x0 Suggested-by: Mark Rutland <mark.rutland@arm.com> Link: https://lore.kernel.org/lkml/ZnVfOnIuFl2kNWkT@J2N7QTR9R3/ [1] Link: https://lore.kernel.org/r/20240702211612.work.576-kees@kernel.org Signed-off-by: Kees Cook <kees@kernel.org> |
||
---|---|---|
.. | ||
acpi | ||
asm-generic | ||
clocksource | ||
crypto | ||
drm | ||
dt-bindings | ||
keys | ||
kunit | ||
kvm | ||
linux | ||
math-emu | ||
media | ||
memory | ||
misc | ||
net | ||
pcmcia | ||
ras | ||
rdma | ||
rv | ||
scsi | ||
soc | ||
sound | ||
target | ||
trace | ||
uapi | ||
ufs | ||
vdso | ||
video | ||
xen |