From 3fb0fdb3bbe7aed495109b3296b06c2409734023 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sat, 13 Feb 2021 11:19:44 -0800 Subject: x86/stackprotector/32: Make the canary into a regular percpu variable On 32-bit kernels, the stackprotector canary is quite nasty -- it is stored at %gs:(20), which is nasty because 32-bit kernels use %fs for percpu storage. It's even nastier because it means that whether %gs contains userspace state or kernel state while running kernel code depends on whether stackprotector is enabled (this is CONFIG_X86_32_LAZY_GS), and this setting radically changes the way that segment selectors work. Supporting both variants is a maintenance and testing mess. Merely rearranging so that percpu and the stack canary share the same segment would be messy as the 32-bit percpu address layout isn't currently compatible with putting a variable at a fixed offset. Fortunately, GCC 8.1 added options that allow the stack canary to be accessed as %fs:__stack_chk_guard, effectively turning it into an ordinary percpu variable. This lets us get rid of all of the code to manage the stack canary GDT descriptor and the CONFIG_X86_32_LAZY_GS mess. (That name is special. We could use any symbol we want for the %fs-relative mode, but for CONFIG_SMP=n, gcc refuses to let us use any name other than __stack_chk_guard.) Forcibly disable stackprotector on older compilers that don't support the new options and turn the stack canary into a percpu variable. The "lazy GS" approach is now used for all 32-bit configurations. Also makes load_gs_index() work on 32-bit kernels. On 64-bit kernels, it loads the GS selector and updates the user GSBASE accordingly. (This is unchanged.) On 32-bit kernels, it loads the GS selector and updates GSBASE, which is now always the user base. This means that the overall effect is the same on 32-bit and 64-bit, which avoids some ifdeffery. [ bp: Massage commit message. ] Signed-off-by: Andy Lutomirski Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/c0ff7dba14041c7e5d1cae5d4df052f03759bef3.1613243844.git.luto@kernel.org --- arch/x86/entry/entry_32.S | 56 ++++------------------------------------------- 1 file changed, 4 insertions(+), 52 deletions(-) (limited to 'arch/x86/entry') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index df8c017e6161..eb0cb662bca5 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -20,7 +20,7 @@ * 1C(%esp) - %ds * 20(%esp) - %es * 24(%esp) - %fs - * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS + * 28(%esp) - unused -- was %gs on old stackprotector kernels * 2C(%esp) - orig_eax * 30(%esp) - %eip * 34(%esp) - %cs @@ -56,14 +56,9 @@ /* * User gs save/restore * - * %gs is used for userland TLS and kernel only uses it for stack - * canary which is required to be at %gs:20 by gcc. Read the comment - * at the top of stackprotector.h for more info. - * - * Local labels 98 and 99 are used. + * This is leftover junk from CONFIG_X86_32_LAZY_GS. A subsequent patch + * will remove it entirely. */ -#ifdef CONFIG_X86_32_LAZY_GS - /* unfortunately push/pop can't be no-op */ .macro PUSH_GS pushl $0 @@ -86,49 +81,6 @@ .macro SET_KERNEL_GS reg .endm -#else /* CONFIG_X86_32_LAZY_GS */ - -.macro PUSH_GS - pushl %gs -.endm - -.macro POP_GS pop=0 -98: popl %gs - .if \pop <> 0 - add $\pop, %esp - .endif -.endm -.macro POP_GS_EX -.pushsection .fixup, "ax" -99: movl $0, (%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b, 99b) -.endm - -.macro PTGS_TO_GS -98: mov PT_GS(%esp), %gs -.endm -.macro PTGS_TO_GS_EX -.pushsection .fixup, "ax" -99: movl $0, PT_GS(%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b, 99b) -.endm - -.macro GS_TO_REG reg - movl %gs, \reg -.endm -.macro REG_TO_PTGS reg - movl \reg, PT_GS(%esp) -.endm -.macro SET_KERNEL_GS reg - movl $(__KERNEL_STACK_CANARY), \reg - movl \reg, %gs -.endm - -#endif /* CONFIG_X86_32_LAZY_GS */ /* Unconditionally switch to user cr3 */ .macro SWITCH_TO_USER_CR3 scratch_reg:req @@ -779,7 +731,7 @@ SYM_CODE_START(__switch_to_asm) #ifdef CONFIG_STACKPROTECTOR movl TASK_stack_canary(%edx), %ebx - movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset + movl %ebx, PER_CPU_VAR(__stack_chk_guard) #endif #ifdef CONFIG_RETPOLINE -- cgit v1.2.3 From d0962f2b24c99889a386f0658c71535f56358f77 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sat, 13 Feb 2021 11:19:45 -0800 Subject: x86/entry/32: Remove leftover macros after stackprotector cleanups Now that nonlazy-GS mode is gone, remove the macros from entry_32.S that obfuscated^Wabstracted GS handling. The assembled output is identical before and after this patch. Signed-off-by: Andy Lutomirski Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/b1543116f0f0e68f1763d90d5f7fcec27885dff5.1613243844.git.luto@kernel.org --- arch/x86/entry/entry_32.S | 43 ++----------------------------------------- 1 file changed, 2 insertions(+), 41 deletions(-) (limited to 'arch/x86/entry') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index eb0cb662bca5..bee9101e211e 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -53,35 +53,6 @@ #define PTI_SWITCH_MASK (1 << PAGE_SHIFT) -/* - * User gs save/restore - * - * This is leftover junk from CONFIG_X86_32_LAZY_GS. A subsequent patch - * will remove it entirely. - */ - /* unfortunately push/pop can't be no-op */ -.macro PUSH_GS - pushl $0 -.endm -.macro POP_GS pop=0 - addl $(4 + \pop), %esp -.endm -.macro POP_GS_EX -.endm - - /* all the rest are no-op */ -.macro PTGS_TO_GS -.endm -.macro PTGS_TO_GS_EX -.endm -.macro GS_TO_REG reg -.endm -.macro REG_TO_PTGS reg -.endm -.macro SET_KERNEL_GS reg -.endm - - /* Unconditionally switch to user cr3 */ .macro SWITCH_TO_USER_CR3 scratch_reg:req ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI @@ -234,7 +205,7 @@ .macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0 cld .if \skip_gs == 0 - PUSH_GS + pushl $0 .endif pushl %fs @@ -259,9 +230,6 @@ movl $(__USER_DS), %edx movl %edx, %ds movl %edx, %es -.if \skip_gs == 0 - SET_KERNEL_GS %edx -.endif /* Switch to kernel stack if necessary */ .if \switch_stacks > 0 SWITCH_TO_KERNEL_STACK @@ -300,7 +268,7 @@ 1: popl %ds 2: popl %es 3: popl %fs - POP_GS \pop + addl $(4 + \pop), %esp /* pop the unused "gs" slot */ IRET_FRAME .pushsection .fixup, "ax" 4: movl $0, (%esp) @@ -313,7 +281,6 @@ _ASM_EXTABLE(1b, 4b) _ASM_EXTABLE(2b, 5b) _ASM_EXTABLE(3b, 6b) - POP_GS_EX .endm .macro RESTORE_ALL_NMI cr3_reg:req pop=0 @@ -928,7 +895,6 @@ SYM_FUNC_START(entry_SYSENTER_32) movl PT_EIP(%esp), %edx /* pt_regs->ip */ movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */ 1: mov PT_FS(%esp), %fs - PTGS_TO_GS popl %ebx /* pt_regs->bx */ addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */ @@ -964,7 +930,6 @@ SYM_FUNC_START(entry_SYSENTER_32) jmp 1b .popsection _ASM_EXTABLE(1b, 2b) - PTGS_TO_GS_EX .Lsysenter_fix_flags: pushl $X86_EFLAGS_FIXED @@ -1106,11 +1071,7 @@ SYM_CODE_START_LOCAL_NOALIGN(handle_exception) SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1 ENCODE_FRAME_POINTER - /* fixup %gs */ - GS_TO_REG %ecx movl PT_GS(%esp), %edi # get the function address - REG_TO_PTGS %ecx - SET_KERNEL_GS %ecx /* fixup orig %eax */ movl PT_ORIG_EAX(%esp), %edx # get the error code -- cgit v1.2.3