diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-27 14:39:29 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-27 14:39:29 -0700 |
commit | ed8780e3f2ecc82645342d070c6b4e530532e680 (patch) | |
tree | 3a9b69695e08bab76dc283286404b52ff8c3c1bc | |
parent | 8c2ab803e565f994b897573f6f2f6520eef41159 (diff) | |
parent | abee7c494d8c41bb388839bccc47e06247f0d7de (diff) |
Merge tag 'x86-urgent-2020-10-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Thomas Gleixner:
"A couple of x86 fixes which missed rc1 due to my stupidity:
- Drop lazy TLB mode before switching to the temporary address space
for text patching.
text_poke() switches to the temporary mm which clears the lazy mode
and restores the original mm afterwards. Due to clearing lazy mode
this might restore a already dead mm if exit_mmap() runs in
parallel on another CPU.
- Document the x32 syscall design fail vs. syscall numbers 512-547
properly.
- Fix the ORC unwinder to handle the inactive task frame correctly.
This was unearthed due to the slightly different code generation of
gcc-10.
- Use an up to date screen_info for the boot params of kexec instead
of the possibly stale and invalid version which happened to be
valid when the kexec kernel was loaded"
* tag 'x86-urgent-2020-10-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/alternative: Don't call text_poke() in lazy TLB mode
x86/syscalls: Document the fact that syscalls 512-547 are a legacy mistake
x86/unwind/orc: Fix inactive tasks with stack pointer in %sp on GCC 10 compiled kernels
hyperv_fb: Update screen_info after removing old framebuffer
x86/kexec: Use up-to-dated screen_info copy to fill boot params
-rw-r--r-- | arch/x86/entry/syscalls/syscall_64.tbl | 10 | ||||
-rw-r--r-- | arch/x86/kernel/alternative.c | 9 | ||||
-rw-r--r-- | arch/x86/kernel/kexec-bzimage64.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/unwind_orc.c | 9 | ||||
-rw-r--r-- | drivers/video/fbdev/hyperv_fb.c | 9 |
5 files changed, 25 insertions, 15 deletions
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 1f47e24fb65c..379819244b91 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,10 +364,10 @@ 440 common process_madvise sys_process_madvise # -# x32-specific system call numbers start at 512 to avoid cache impact -# for native 64-bit operation. The __x32_compat_sys stubs are created -# on-the-fly for compat_sys_*() compatibility system calls if X86_X32 -# is defined. +# Due to a historical design error, certain syscalls are numbered differently +# in x32 as compared to native x86_64. These syscalls have numbers 512-547. +# Do not add new syscalls to this range. Numbers 548 and above are available +# for non-x32 use. # 512 x32 rt_sigaction compat_sys_rt_sigaction 513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn @@ -405,3 +405,5 @@ 545 x32 execveat compat_sys_execveat 546 x32 preadv2 compat_sys_preadv64v2 547 x32 pwritev2 compat_sys_pwritev64v2 +# This is the end of the legacy x32 range. Numbers 548 and above are +# not special and are not to be used for x32-specific syscalls. diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4adbe65afe23..2400ad62f330 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -807,6 +807,15 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) temp_mm_state_t temp_state; lockdep_assert_irqs_disabled(); + + /* + * Make sure not to be in TLB lazy mode, as otherwise we'll end up + * with a stale address space WITHOUT being in lazy mode after + * restoring the previous mm. + */ + if (this_cpu_read(cpu_tlbstate.is_lazy)) + leave_mm(smp_processor_id()); + temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm); switch_mm_irqs_off(NULL, mm, current); diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 57c2ecf43134..ce831f9448e7 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -200,8 +200,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch; /* Copying screen_info will do? */ - memcpy(¶ms->screen_info, &boot_params.screen_info, - sizeof(struct screen_info)); + memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info)); /* Fill in memsize later */ params->screen_info.ext_mem_k = 0; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 6a339ce328e0..73f800100066 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -321,19 +321,12 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) { - struct task_struct *task = state->task; - if (unwind_done(state)) return NULL; if (state->regs) return &state->regs->ip; - if (task != current && state->sp == task->thread.sp) { - struct inactive_task_frame *frame = (void *)task->thread.sp; - return &frame->ret_addr; - } - if (state->sp) return (unsigned long *)state->sp - 1; @@ -663,7 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } else { struct inactive_task_frame *frame = (void *)task->thread.sp; - state->sp = task->thread.sp; + state->sp = task->thread.sp + sizeof(*frame); state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); state->signal = (void *)state->ip == ret_from_fork; diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 02411d89cb46..e36fb1a0ecdb 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1114,8 +1114,15 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) getmem_done: remove_conflicting_framebuffers(info->apertures, KBUILD_MODNAME, false); - if (!gen2vm) + + if (gen2vm) { + /* framebuffer is reallocated, clear screen_info to avoid misuse from kexec */ + screen_info.lfb_size = 0; + screen_info.lfb_base = 0; + screen_info.orig_video_isVGA = 0; + } else { pci_dev_put(pdev); + } kfree(info->apertures); return 0; |