From: Peter Zijlstra peterz@infradead.org
stable inclusion from stable-v4.19.266 commit 9e03416b022e83c73bbbdc275f1df1c3e88e3155 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5GZ2Z CVE: CVE=2022-29901
--------------------------------
commit 2dbb887e875b1de3ca8f40ddf26bcfe55798c609 upstream.
Implement Kernel IBRS - currently the only known option to mitigate RSB underflow speculation issues on Skylake hardware.
Note: since IBRS_ENTER requires fuller context established than UNTRAIN_RET, it must be placed after it. However, since UNTRAIN_RET itself implies a RET, it must come after IBRS_ENTER. This means IBRS_ENTER needs to also move UNTRAIN_RET.
Note 2: KERNEL_IBRS is sub-optimal for XenPV.
Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: conflict at arch/x86/entry/entry_64.S, skip_r11rcx] [cascardo: conflict at arch/x86/entry/entry_64_compat.S] [cascardo: conflict fixups, no ANNOTATE_NOENDBR] [cascardo: entry fixups because of missing UNTRAIN_RET] [cascardo: conflicts on fsgsbase] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Suleiman Souhlal suleiman@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com Reviewed-by: Liao Chang liaochang1@huawei.com Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com --- arch/x86/entry/calling.h | 58 ++++++++++++++++++++++++++++++ arch/x86/entry/entry_64.S | 29 ++++++++++++++- arch/x86/entry/entry_64_compat.S | 11 +++++- arch/x86/include/asm/cpufeatures.h | 2 +- 4 files changed, 97 insertions(+), 3 deletions(-)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index a71b5f1f92c8..b1cf149d62ed 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -6,6 +6,8 @@ #include <asm/percpu.h> #include <asm/asm-offsets.h> #include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/nospec-branch.h>
/*
@@ -321,6 +323,62 @@ For 32-bit we have the following conventions - kernel is built with
#endif
+/* + * IBRS kernel mitigation for Spectre_v2. + * + * Assumes full context is established (PUSH_REGS, CR3 and GS) and it clobbers + * the regs it uses (AX, CX, DX). Must be called before the first RET + * instruction (NOTE! UNTRAIN_RET includes a RET instruction) + * + * The optional argument is used to save/restore the current value, + * which is used on the paranoid paths. + * + * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. + */ +.macro IBRS_ENTER save_reg + ALTERNATIVE "jmp .Lend_@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + rdmsr + shl $32, %rdx + or %rdx, %rax + mov %rax, \save_reg + test $SPEC_CTRL_IBRS, %eax + jz .Ldo_wrmsr_@ + lfence + jmp .Lend_@ +.Ldo_wrmsr_@: +.endif + + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_@: +.endm + +/* + * Similar to IBRS_ENTER, requires KERNEL GS,CR3 and clobbers (AX, CX, DX) + * regs. Must be called after the last RET. + */ +.macro IBRS_EXIT save_reg + ALTERNATIVE "jmp .Lend_@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + mov \save_reg, %rdx +.else + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + andl $(~SPEC_CTRL_IBRS), %edx +.endif + + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_@: +.endm + /* * Mitigate Spectre v1 for conditional swapgs code paths. * diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index aa045266fb1d..443728959303 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -235,6 +235,10 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) /* IRQs are off. */ movq %rax, %rdi movq %rsp, %rsi + + /* clobbers %rax, make sure it is after saving the syscall nr */ + IBRS_ENTER + call do_syscall_64 /* returns with IRQs disabled */
TRACE_IRQS_IRETQ /* we're about to change IF */ @@ -311,6 +315,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: + IBRS_EXIT POP_REGS pop_rdi=0
/* @@ -684,6 +689,7 @@ GLOBAL(retint_user) TRACE_IRQS_IRETQ
GLOBAL(swapgs_restore_regs_and_return_to_usermode) + IBRS_EXIT #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ testb $3, CS(%rsp) @@ -1249,7 +1255,13 @@ ENTRY(paranoid_entry) */ FENCE_SWAPGS_KERNEL_ENTRY
- ret + /* + * Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like + * CR3 above, keep the old value in a callee saved register. + */ + IBRS_ENTER save_reg=%r15 + + RET END(paranoid_entry)
/* @@ -1277,12 +1289,20 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + + /* + * Must restore IBRS state before both CR3 and %GS since we need access + * to the per-CPU x86_spec_ctrl_shadow variable. + */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit)
+ /* * Save all registers in pt_regs, and switch GS if needed. */ @@ -1302,6 +1322,7 @@ ENTRY(error_entry) FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER
.Lerror_entry_from_usermode_after_swapgs: /* Put us onto the real thread stack. */ @@ -1366,6 +1387,7 @@ ENTRY(error_entry) SWAPGS FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER
/* * Pretend that the exception came from user mode: set up pt_regs @@ -1471,6 +1493,8 @@ ENTRY(nmi) PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER
+ IBRS_ENTER + /* * At this point we no longer need to worry about stack damage * due to nesting -- we're on the normal thread stack and we're @@ -1694,6 +1718,9 @@ end_repeat_nmi: movq $-1, %rsi call do_nmi
+ /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index f326e0c6e8dd..a46e70aa603d 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -4,7 +4,6 @@ * * Copyright 2000-2002 Andi Kleen, SuSE Labs. */ -#include "calling.h" #include <asm/asm-offsets.h> #include <asm/current.h> #include <asm/errno.h> @@ -17,6 +16,8 @@ #include <linux/linkage.h> #include <linux/err.h>
+#include "calling.h" + .section .entry.text, "ax"
/* @@ -112,6 +113,8 @@ ENTRY(entry_SYSENTER_compat)
cld
+ IBRS_ENTER + /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -262,6 +265,8 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) */ TRACE_IRQS_OFF
+ IBRS_ENTER + movq %rsp, %rdi call do_fast_syscall_32 /* XEN PV guests always use IRET path */ @@ -271,6 +276,9 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) /* Opportunistic SYSRET */ sysret32_from_system_call: TRACE_IRQS_ON /* User mode traces as IRQs on. */ + + IBRS_EXIT + movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ @@ -416,6 +424,7 @@ ENTRY(entry_INT80_compat) * gate turned them off. */ TRACE_IRQS_OFF + IBRS_ENTER
movq %rsp, %rdi call do_int80_syscall_32 diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8f5e099bdbf0..a8704b861a01 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -223,7 +223,7 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -/* FREE! ( 7*32+12) */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ /* FREE! ( 7*32+13) */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */