diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-03-14 12:48:10 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-03-14 12:48:10 -0700 |
commit | 0a7c10df49eb69dd888ea8b8ddd29bde2aa2fd48 (patch) | |
tree | 433e5a9f1252cea52ff4a5dac2ec4b9d8be09a34 /arch/x86/kernel | |
parent | c3c7579f5e3b4826d32af0521e53d5d565ed5a73 (diff) | |
parent | bffe30dd9f1f3b2608a87ac909a224d6be472485 (diff) |
Merge tag 'x86_urgent_for_v5.12_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Borislav Petkov:
- A couple of SEV-ES fixes and robustifications: verify usermode stack
pointer in NMI is not coming from the syscall gap, correctly track
IRQ states in the #VC handler and access user insn bytes atomically
in same handler as latter cannot sleep.
- Balance 32-bit fast syscall exit path to do the proper work on exit
and thus not confuse audit and ptrace frameworks.
- Two fixes for the ORC unwinder going "off the rails" into KASAN
redzones and when ORC data is missing.
* tag 'x86_urgent_for_v5.12_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/sev-es: Use __copy_from_user_inatomic()
x86/sev-es: Correctly track IRQ states in runtime #VC handler
x86/sev-es: Check regs->sp is trusted before adjusting #VC IST stack
x86/sev-es: Introduce ip_within_syscall_gap() helper
x86/entry: Fix entry/exit mismatch on failed fast 32-bit syscalls
x86/unwind/orc: Silence warnings caused by missing ORC data
x86/unwind/orc: Disable KASAN checking in the ORC unwinder, part 2
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/sev-es.c | 22 | ||||
-rw-r--r-- | arch/x86/kernel/traps.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/unwind_orc.c | 14 |
3 files changed, 25 insertions, 14 deletions
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 84c1821819af..04a780abb512 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -121,8 +121,18 @@ static void __init setup_vc_stacks(int cpu) cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); } -static __always_inline bool on_vc_stack(unsigned long sp) +static __always_inline bool on_vc_stack(struct pt_regs *regs) { + unsigned long sp = regs->sp; + + /* User-mode RSP is not trusted */ + if (user_mode(regs)) + return false; + + /* SYSCALL gap still has user-mode RSP */ + if (ip_within_syscall_gap(regs)) + return false; + return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC))); } @@ -144,7 +154,7 @@ void noinstr __sev_es_ist_enter(struct pt_regs *regs) old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); /* Make room on the IST stack */ - if (on_vc_stack(regs->sp)) + if (on_vc_stack(regs)) new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist); else new_ist = old_ist - sizeof(old_ist); @@ -248,7 +258,7 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) int res; if (user_mode(ctxt->regs)) { - res = insn_fetch_from_user(ctxt->regs, buffer); + res = insn_fetch_from_user_inatomic(ctxt->regs, buffer); if (!res) { ctxt->fi.vector = X86_TRAP_PF; ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER; @@ -1248,13 +1258,12 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs) DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) { struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + irqentry_state_t irq_state; struct ghcb_state state; struct es_em_ctxt ctxt; enum es_result result; struct ghcb *ghcb; - lockdep_assert_irqs_disabled(); - /* * Handle #DB before calling into !noinstr code to avoid recursive #DB. */ @@ -1263,6 +1272,8 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) return; } + irq_state = irqentry_nmi_enter(regs); + lockdep_assert_irqs_disabled(); instrumentation_begin(); /* @@ -1325,6 +1336,7 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) out: instrumentation_end(); + irqentry_nmi_exit(regs, irq_state); return; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 7f5aec758f0e..ac1874a2a70e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -694,8 +694,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r * In the SYSCALL entry path the RSP value comes from user-space - don't * trust it and switch to the current kernel stack */ - if (regs->ip >= (unsigned long)entry_SYSCALL_64 && - regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack) { + if (ip_within_syscall_gap(regs)) { sp = this_cpu_read(cpu_current_top_of_stack); goto sync; } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 2a1d47f47eee..a1202536fc57 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -13,7 +13,7 @@ #define orc_warn_current(args...) \ ({ \ - if (state->task == current) \ + if (state->task == current && !state->error) \ orc_warn(args); \ }) @@ -367,8 +367,8 @@ static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, if (!stack_access_ok(state, addr, sizeof(struct pt_regs))) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } @@ -380,8 +380,8 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr if (!stack_access_ok(state, addr, IRET_FRAME_SIZE)) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } @@ -402,12 +402,12 @@ static bool get_reg(struct unwind_state *state, unsigned int reg_off, return false; if (state->full_regs) { - *val = ((unsigned long *)state->regs)[reg]; + *val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]); return true; } if (state->prev_regs) { - *val = ((unsigned long *)state->prev_regs)[reg]; + *val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]); return true; } |