mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2025-01-03 20:34:58 +08:00
2d6bb6adb7
- Introduces the stackleak gcc plugin ported from grsecurity by Alexander Popov, with x86 and arm64 support. -----BEGIN PGP SIGNATURE----- Comment: Kees Cook <kees@outflux.net> iQJKBAABCgA0FiEEpcP2jyKd1g9yPm4TiXL039xtwCYFAlvQvn4WHGtlZXNjb29r QGNocm9taXVtLm9yZwAKCRCJcvTf3G3AJpSfD/sErFreuPT1beSw994Lr9Zx4k9v ERsuXxWBENaJOJXbOOHMfVEcEeG/1uhPSp7hlw/dpHfh0anATTrcYqm8RNKbfK+k o06+JK14OJfpm5Ghq/7OizhdNLCMT8wMU3XZtWfy65VSJGjEFx8Y48vMeQtpWtUK ylSzi9JV6j2iUBF9oibtiT53+yqsqAtX80X1G7HRCgv9kxuKMhZr+Q5oGV6+ViyQ Azj8mNn06iRnhHKd17WxDJr0GjSibzz4weS/9XgP3t3EcNWJo1EgBlD2KV3tOfP5 nzmqfqTqrcjxs/tyjdh6vVCSlYucNtyCQGn63qyShQYSg6mZwclR2fY8YSTw6PWw GfYWFOWru9z+qyQmwFkQ9bSQS2R+JIT0oBCj9VmtF9XmPCy7K2neJsQclzSPBiCW wPgXVQS4IA4684O5CmDOVMwmDpGvhdBNUR6cqSzGLxQOHY1csyXubMNUsqU3g9xk Ob4pEy/xrrIw4WpwHcLHSEW5gV1/OLhsT0fGRJJiC947L3cN5s9EZp7FLbIS0zlk qzaXUcLmn6AgcfkYwg5cI3RMLaN2V0eDCMVTWZJ1wbrmUV9chAaOnTPTjNqLOTht v3b1TTxXG4iCpMmOFf59F8pqgAwbBDlfyNSbySZ/Pq5QH69udz3Z9pIUlYQnSJHk u6q++2ReDpJXF81rBw== =Ks6B -----END PGP SIGNATURE----- Merge tag 'stackleak-v4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux Pull stackleak gcc plugin from Kees Cook: "Please pull this new GCC plugin, stackleak, for v4.20-rc1. This plugin was ported from grsecurity by Alexander Popov. It provides efficient stack content poisoning at syscall exit. This creates a defense against at least two classes of flaws: - Uninitialized stack usage. (We continue to work on improving the compiler to do this in other ways: e.g. unconditional zero init was proposed to GCC and Clang, and more plugin work has started too). - Stack content exposure. By greatly reducing the lifetime of valid stack contents, exposures via either direct read bugs or unknown cache side-channels become much more difficult to exploit. This complements the existing buddy and heap poisoning options, but provides the coverage for stacks. The x86 hooks are included in this series (which have been reviewed by Ingo, Dave Hansen, and Thomas Gleixner). The arm64 hooks have already been merged through the arm64 tree (written by Laura Abbott and reviewed by Mark Rutland and Will Deacon). With VLAs having been removed this release, there is no need for alloca() protection, so it has been removed from the plugin" * tag 'stackleak-v4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: arm64: Drop unneeded stackleak_check_alloca() stackleak: Allow runtime disabling of kernel stack erasing doc: self-protection: Add information about STACKLEAK feature fs/proc: Show STACKLEAK metrics in the /proc file system lkdtm: Add a test for STACKLEAK gcc-plugins: Add STACKLEAK plugin for tracking the kernel stack x86/entry: Add STACKLEAK erasing the kernel stack at the end of syscalls
361 lines
10 KiB
C
361 lines
10 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#include <linux/jump_label.h>
|
|
#include <asm/unwind_hints.h>
|
|
#include <asm/cpufeatures.h>
|
|
#include <asm/page_types.h>
|
|
#include <asm/percpu.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/processor-flags.h>
|
|
|
|
/*
|
|
|
|
x86 function call convention, 64-bit:
|
|
-------------------------------------
|
|
arguments | callee-saved | extra caller-saved | return
|
|
[callee-clobbered] | | [callee-clobbered] |
|
|
---------------------------------------------------------------------------
|
|
rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11 | rax, rdx [**]
|
|
|
|
( rsp is obviously invariant across normal function calls. (gcc can 'merge'
|
|
functions when it sees tail-call optimization possibilities) rflags is
|
|
clobbered. Leftover arguments are passed over the stack frame.)
|
|
|
|
[*] In the frame-pointers case rbp is fixed to the stack frame.
|
|
|
|
[**] for struct return values wider than 64 bits the return convention is a
|
|
bit more complex: up to 128 bits width we return small structures
|
|
straight in rax, rdx. For structures larger than that (3 words or
|
|
larger) the caller puts a pointer to an on-stack return struct
|
|
[allocated in the caller's stack frame] into the first argument - i.e.
|
|
into rdi. All other arguments shift up by one in this case.
|
|
Fortunately this case is rare in the kernel.
|
|
|
|
For 32-bit we have the following conventions - kernel is built with
|
|
-mregparm=3 and -freg-struct-return:
|
|
|
|
x86 function calling convention, 32-bit:
|
|
----------------------------------------
|
|
arguments | callee-saved | extra caller-saved | return
|
|
[callee-clobbered] | | [callee-clobbered] |
|
|
-------------------------------------------------------------------------
|
|
eax edx ecx | ebx edi esi ebp [*] | <none> | eax, edx [**]
|
|
|
|
( here too esp is obviously invariant across normal function calls. eflags
|
|
is clobbered. Leftover arguments are passed over the stack frame. )
|
|
|
|
[*] In the frame-pointers case ebp is fixed to the stack frame.
|
|
|
|
[**] We build with -freg-struct-return, which on 32-bit means similar
|
|
semantics as on 64-bit: edx can be used for a second return value
|
|
(i.e. covering integer and structure sizes up to 64 bits) - after that
|
|
it gets more complex and more expensive: 3-word or larger struct returns
|
|
get done in the caller's frame and the pointer to the return struct goes
|
|
into regparm0, i.e. eax - the other arguments shift up and the
|
|
function's register parameters degenerate to regparm=2 in essence.
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_X86_64
|
|
|
|
/*
|
|
* 64-bit system call stack frame layout defines and helpers,
|
|
* for assembly code:
|
|
*/
|
|
|
|
/* The layout forms the "struct pt_regs" on the stack: */
|
|
/*
|
|
* C ABI says these regs are callee-preserved. They aren't saved on kernel entry
|
|
* unless syscall needs a complete, fully filled "struct pt_regs".
|
|
*/
|
|
#define R15 0*8
|
|
#define R14 1*8
|
|
#define R13 2*8
|
|
#define R12 3*8
|
|
#define RBP 4*8
|
|
#define RBX 5*8
|
|
/* These regs are callee-clobbered. Always saved on kernel entry. */
|
|
#define R11 6*8
|
|
#define R10 7*8
|
|
#define R9 8*8
|
|
#define R8 9*8
|
|
#define RAX 10*8
|
|
#define RCX 11*8
|
|
#define RDX 12*8
|
|
#define RSI 13*8
|
|
#define RDI 14*8
|
|
/*
|
|
* On syscall entry, this is syscall#. On CPU exception, this is error code.
|
|
* On hw interrupt, it's IRQ number:
|
|
*/
|
|
#define ORIG_RAX 15*8
|
|
/* Return frame for iretq */
|
|
#define RIP 16*8
|
|
#define CS 17*8
|
|
#define EFLAGS 18*8
|
|
#define RSP 19*8
|
|
#define SS 20*8
|
|
|
|
#define SIZEOF_PTREGS 21*8
|
|
|
|
.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
|
|
/*
|
|
* Push registers and sanitize registers of values that a
|
|
* speculation attack might otherwise want to exploit. The
|
|
* lower registers are likely clobbered well before they
|
|
* could be put to use in a speculative execution gadget.
|
|
* Interleave XOR with PUSH for better uop scheduling:
|
|
*/
|
|
.if \save_ret
|
|
pushq %rsi /* pt_regs->si */
|
|
movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */
|
|
movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */
|
|
.else
|
|
pushq %rdi /* pt_regs->di */
|
|
pushq %rsi /* pt_regs->si */
|
|
.endif
|
|
pushq \rdx /* pt_regs->dx */
|
|
xorl %edx, %edx /* nospec dx */
|
|
pushq %rcx /* pt_regs->cx */
|
|
xorl %ecx, %ecx /* nospec cx */
|
|
pushq \rax /* pt_regs->ax */
|
|
pushq %r8 /* pt_regs->r8 */
|
|
xorl %r8d, %r8d /* nospec r8 */
|
|
pushq %r9 /* pt_regs->r9 */
|
|
xorl %r9d, %r9d /* nospec r9 */
|
|
pushq %r10 /* pt_regs->r10 */
|
|
xorl %r10d, %r10d /* nospec r10 */
|
|
pushq %r11 /* pt_regs->r11 */
|
|
xorl %r11d, %r11d /* nospec r11*/
|
|
pushq %rbx /* pt_regs->rbx */
|
|
xorl %ebx, %ebx /* nospec rbx*/
|
|
pushq %rbp /* pt_regs->rbp */
|
|
xorl %ebp, %ebp /* nospec rbp*/
|
|
pushq %r12 /* pt_regs->r12 */
|
|
xorl %r12d, %r12d /* nospec r12*/
|
|
pushq %r13 /* pt_regs->r13 */
|
|
xorl %r13d, %r13d /* nospec r13*/
|
|
pushq %r14 /* pt_regs->r14 */
|
|
xorl %r14d, %r14d /* nospec r14*/
|
|
pushq %r15 /* pt_regs->r15 */
|
|
xorl %r15d, %r15d /* nospec r15*/
|
|
UNWIND_HINT_REGS
|
|
.if \save_ret
|
|
pushq %rsi /* return address on top of stack */
|
|
.endif
|
|
.endm
|
|
|
|
.macro POP_REGS pop_rdi=1 skip_r11rcx=0
|
|
popq %r15
|
|
popq %r14
|
|
popq %r13
|
|
popq %r12
|
|
popq %rbp
|
|
popq %rbx
|
|
.if \skip_r11rcx
|
|
popq %rsi
|
|
.else
|
|
popq %r11
|
|
.endif
|
|
popq %r10
|
|
popq %r9
|
|
popq %r8
|
|
popq %rax
|
|
.if \skip_r11rcx
|
|
popq %rsi
|
|
.else
|
|
popq %rcx
|
|
.endif
|
|
popq %rdx
|
|
popq %rsi
|
|
.if \pop_rdi
|
|
popq %rdi
|
|
.endif
|
|
.endm
|
|
|
|
/*
|
|
* This is a sneaky trick to help the unwinder find pt_regs on the stack. The
|
|
* frame pointer is replaced with an encoded pointer to pt_regs. The encoding
|
|
* is just setting the LSB, which makes it an invalid stack address and is also
|
|
* a signal to the unwinder that it's a pt_regs pointer in disguise.
|
|
*
|
|
* NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts
|
|
* the original rbp.
|
|
*/
|
|
.macro ENCODE_FRAME_POINTER ptregs_offset=0
|
|
#ifdef CONFIG_FRAME_POINTER
|
|
leaq 1+\ptregs_offset(%rsp), %rbp
|
|
#endif
|
|
.endm
|
|
|
|
#ifdef CONFIG_PAGE_TABLE_ISOLATION
|
|
|
|
/*
|
|
* PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
|
|
* halves:
|
|
*/
|
|
#define PTI_USER_PGTABLE_BIT PAGE_SHIFT
|
|
#define PTI_USER_PGTABLE_MASK (1 << PTI_USER_PGTABLE_BIT)
|
|
#define PTI_USER_PCID_BIT X86_CR3_PTI_PCID_USER_BIT
|
|
#define PTI_USER_PCID_MASK (1 << PTI_USER_PCID_BIT)
|
|
#define PTI_USER_PGTABLE_AND_PCID_MASK (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
|
|
|
|
.macro SET_NOFLUSH_BIT reg:req
|
|
bts $X86_CR3_PCID_NOFLUSH_BIT, \reg
|
|
.endm
|
|
|
|
.macro ADJUST_KERNEL_CR3 reg:req
|
|
ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
|
|
/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
|
|
andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
|
|
.endm
|
|
|
|
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
|
|
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
|
|
mov %cr3, \scratch_reg
|
|
ADJUST_KERNEL_CR3 \scratch_reg
|
|
mov \scratch_reg, %cr3
|
|
.Lend_\@:
|
|
.endm
|
|
|
|
#define THIS_CPU_user_pcid_flush_mask \
|
|
PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
|
|
|
|
.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
|
|
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
|
|
mov %cr3, \scratch_reg
|
|
|
|
ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
|
|
|
|
/*
|
|
* Test if the ASID needs a flush.
|
|
*/
|
|
movq \scratch_reg, \scratch_reg2
|
|
andq $(0x7FF), \scratch_reg /* mask ASID */
|
|
bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
|
|
jnc .Lnoflush_\@
|
|
|
|
/* Flush needed, clear the bit */
|
|
btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
|
|
movq \scratch_reg2, \scratch_reg
|
|
jmp .Lwrcr3_pcid_\@
|
|
|
|
.Lnoflush_\@:
|
|
movq \scratch_reg2, \scratch_reg
|
|
SET_NOFLUSH_BIT \scratch_reg
|
|
|
|
.Lwrcr3_pcid_\@:
|
|
/* Flip the ASID to the user version */
|
|
orq $(PTI_USER_PCID_MASK), \scratch_reg
|
|
|
|
.Lwrcr3_\@:
|
|
/* Flip the PGD to the user version */
|
|
orq $(PTI_USER_PGTABLE_MASK), \scratch_reg
|
|
mov \scratch_reg, %cr3
|
|
.Lend_\@:
|
|
.endm
|
|
|
|
.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
|
|
pushq %rax
|
|
SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
|
|
popq %rax
|
|
.endm
|
|
|
|
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
|
|
ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
|
|
movq %cr3, \scratch_reg
|
|
movq \scratch_reg, \save_reg
|
|
/*
|
|
* Test the user pagetable bit. If set, then the user page tables
|
|
* are active. If clear CR3 already has the kernel page table
|
|
* active.
|
|
*/
|
|
bt $PTI_USER_PGTABLE_BIT, \scratch_reg
|
|
jnc .Ldone_\@
|
|
|
|
ADJUST_KERNEL_CR3 \scratch_reg
|
|
movq \scratch_reg, %cr3
|
|
|
|
.Ldone_\@:
|
|
.endm
|
|
|
|
.macro RESTORE_CR3 scratch_reg:req save_reg:req
|
|
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
|
|
|
|
ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
|
|
|
|
/*
|
|
* KERNEL pages can always resume with NOFLUSH as we do
|
|
* explicit flushes.
|
|
*/
|
|
bt $PTI_USER_PGTABLE_BIT, \save_reg
|
|
jnc .Lnoflush_\@
|
|
|
|
/*
|
|
* Check if there's a pending flush for the user ASID we're
|
|
* about to set.
|
|
*/
|
|
movq \save_reg, \scratch_reg
|
|
andq $(0x7FF), \scratch_reg
|
|
bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
|
|
jnc .Lnoflush_\@
|
|
|
|
btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
|
|
jmp .Lwrcr3_\@
|
|
|
|
.Lnoflush_\@:
|
|
SET_NOFLUSH_BIT \save_reg
|
|
|
|
.Lwrcr3_\@:
|
|
/*
|
|
* The CR3 write could be avoided when not changing its value,
|
|
* but would require a CR3 read *and* a scratch register.
|
|
*/
|
|
movq \save_reg, %cr3
|
|
.Lend_\@:
|
|
.endm
|
|
|
|
#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
|
|
|
|
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
|
|
.endm
|
|
.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
|
|
.endm
|
|
.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
|
|
.endm
|
|
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
|
|
.endm
|
|
.macro RESTORE_CR3 scratch_reg:req save_reg:req
|
|
.endm
|
|
|
|
#endif
|
|
|
|
.macro STACKLEAK_ERASE_NOCLOBBER
|
|
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
|
|
PUSH_AND_CLEAR_REGS
|
|
call stackleak_erase
|
|
POP_REGS
|
|
#endif
|
|
.endm
|
|
|
|
#endif /* CONFIG_X86_64 */
|
|
|
|
.macro STACKLEAK_ERASE
|
|
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
|
|
call stackleak_erase
|
|
#endif
|
|
.endm
|
|
|
|
/*
|
|
* This does 'call enter_from_user_mode' unless we can avoid it based on
|
|
* kernel config or using the static jump infrastructure.
|
|
*/
|
|
.macro CALL_enter_from_user_mode
|
|
#ifdef CONFIG_CONTEXT_TRACKING
|
|
#ifdef HAVE_JUMP_LABEL
|
|
STATIC_BRANCH_JMP l_yes=.Lafter_call_\@, key=context_tracking_enabled, branch=1
|
|
#endif
|
|
call enter_from_user_mode
|
|
.Lafter_call_\@:
|
|
#endif
|
|
.endm
|