On Mon, Dec 04, 2017 at 03:07:33PM +0100, Thomas Gleixner wrote:
> From: Thomas Gleixner <t...@linutronix.de>
>
> Many x86 CPUs leak information to user space due to missing isolation of
> user space and kernel space page tables. There are many well documented
> ways to exploit that.
>
> The upcoming software migitation of isolating the user and kernel space
> page tables needs a misfeature flag so code can be made runtime
> conditional.
>
> Add two BUG bits: One which indicates that the CPU is affected and one that
> the software migitation is enabled.
>
> Assume for now that _ALL_ x86 CPUs are affected by this. Exceptions can be
> made later.
>
> Signed-off-by: Thomas Gleixner <t...@linutronix.de>
>
> ---
> arch/x86/include/asm/cpufeatures.h | 2 ++
> arch/x86/kernel/cpu/common.c | 4 ++++
> 2 files changed, 6 insertions(+)
>
> --- a/arch/x86/include/asm/cpufeatures.h
> +++ b/arch/x86/include/asm/cpufeatures.h
> @@ -340,5 +340,7 @@
> #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep
> on GS */
> #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to
> wake up remote CPU */
> #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the
> affected by Erratum 400 */
> +#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and
> needs kernel page table isolation */
> +#define X86_BUG_CPU_SECURE_MODE_KPTI X86_BUG(15) /* Kernel Page Table
> Isolation enabled*/
Right, if this second one is going to denote that the workaround is
enabled, let's make it a feature bit and shorter:
#define X86_FEATURE_KPTI
Delta diff below.
---
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 4dd0bda9fe09..604b62a5a2fe 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -212,7 +212,7 @@ For 32-bit we have the following conventions - kernel is
built with
.endm
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
- ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_CPU_SECURE_MODE_KPTI
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KPTI
mov %cr3, \scratch_reg
ADJUST_KERNEL_CR3 \scratch_reg
mov \scratch_reg, %cr3
@@ -223,7 +223,7 @@ For 32-bit we have the following conventions - kernel is
built with
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_BUG_CPU_SECURE_MODE_KPTI
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KPTI
mov %cr3, \scratch_reg
ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
@@ -259,7 +259,7 @@ For 32-bit we have the following conventions - kernel is
built with
.endm
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
- ALTERNATIVE "jmp .Ldone_\@", "", X86_BUG_CPU_SECURE_MODE_KPTI
+ ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_KPTI
movq %cr3, \scratch_reg
movq \scratch_reg, \save_reg
/*
@@ -282,7 +282,7 @@ For 32-bit we have the following conventions - kernel is
built with
.endm
.macro RESTORE_CR3 scratch_reg:req save_reg:req
- ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_CPU_SECURE_MODE_KPTI
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KPTI
ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
diff --git a/arch/x86/include/asm/cpufeatures.h
b/arch/x86/include/asm/cpufeatures.h
index 6e905acb4e97..b367c23e7d83 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -198,10 +198,10 @@
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation
Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data
Prioritization L3 */
#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID &&
CR4.PCIDE=1 */
-
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface
*/
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory
Encryption */
+#define X86_FEATURE_KPTI ( 7*32+11) /* Kernel Page Table
Isolation enabled */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory
Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
@@ -342,6 +342,5 @@
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to
wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the
affected by Erratum 400 */
#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and
needs kernel page table isolation */
-#define X86_BUG_CPU_SECURE_MODE_KPTI X86_BUG(15) /* Kernel Page Table
Isolation enabled*/
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/pgtable_64.h
b/arch/x86/include/asm/pgtable_64.h
index 0405960cee25..d1bf0b3a8232 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -210,7 +210,7 @@ static inline bool pgd_userspace_access(pgd_t pgd)
static inline pgd_t kpti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
{
#ifdef CONFIG_KERNEL_PAGE_TABLE_ISOLATION
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (!static_cpu_has(X86_FEATURE_KPTI))
return pgd;
if (pgd_userspace_access(pgd)) {
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 55ebfd144f18..d84167c036c0 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -330,7 +330,7 @@ static inline void invalidate_pcid_other(void)
* are set as _PAGE_GLOBAL. We have no shared nonglobals
* and nothing to do here.
*/
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (!static_cpu_has(X86_FEATURE_KPTI))
return;
this_cpu_write(cpu_tlbstate.invalidate_other, true);
@@ -374,7 +374,7 @@ static inline void invalidate_user_asid(u16 asid)
if (!cpu_feature_enabled(X86_FEATURE_PCID))
return;
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (!static_cpu_has(X86_FEATURE_KPTI))
return;
__set_bit(kern_pcid(asid),
@@ -438,7 +438,7 @@ static inline void __native_flush_tlb_single(unsigned long
addr)
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (!static_cpu_has(X86_FEATURE_KPTI))
return;
/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b38a426a9855..4aa7b1efa6d8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1481,7 +1481,7 @@ void syscall_init(void)
(entry_SYSCALL_64_trampoline - _entry_trampoline);
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
- if (static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (static_cpu_has(X86_FEATURE_KPTI))
wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
else
wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index f63a2b00d775..15dfdb76523d 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -53,7 +53,7 @@ static void set_ldt_and_map(struct ldt_struct *ldt)
void *fixva;
int idx, i;
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI)) {
+ if (!static_cpu_has(X86_FEATURE_KPTI)) {
set_ldt(ldt->entries_va, ldt->nr_entries);
return;
}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index f9dfc20234e9..f18041e7d4d2 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -504,7 +504,7 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
{
#ifdef CONFIG_KERNEL_PAGE_TABLE_ISOLATION
- if (user && static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (user && static_cpu_has(X86_FEATURE_KPTI))
pgd = kernel_to_user_pgdp(pgd);
#endif
ptdump_walk_pgd_level_core(m, pgd, false, false);
@@ -516,7 +516,7 @@ static void ptdump_walk_user_pgd_level_checkwx(void)
#ifdef CONFIG_KERNEL_PAGE_TABLE_ISOLATION
pgd_t *pgd = (pgd_t *) &init_top_pgt;
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (!static_cpu_has(X86_FEATURE_KPTI))
return;
pr_info("x86/mm: Checking user space page tables\n");
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ffd55531206e..d65bc503da44 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -164,7 +164,7 @@ static int page_size_mask;
static void enable_global_pages(void)
{
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (!static_cpu_has(X86_FEATURE_KPTI))
__supported_pte_mask |= _PAGE_GLOBAL;
}
diff --git a/arch/x86/mm/kpti.c b/arch/x86/mm/kpti.c
index a3b39c01e028..b8f2e300e26c 100644
--- a/arch/x86/mm/kpti.c
+++ b/arch/x86/mm/kpti.c
@@ -61,7 +61,7 @@ void __init kpti_check_boottime_disable(void)
enable = false;
}
if (enable)
- setup_force_cpu_bug(X86_BUG_CPU_SECURE_MODE_KPTI);
+ setup_force_cpu_cap(X86_FEATURE_KPTI);
}
/*
@@ -236,7 +236,7 @@ static void __init kpti_init_all_pgds(void)
*/
void __init kpti_init(void)
{
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
+ if (!static_cpu_has(X86_FEATURE_KPTI))
return;
pr_info("enabled\n");
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 20f6cc4e49b8..430c6ba24ad7 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -42,7 +42,7 @@ void clear_asid_other(void)
* This is only expected to be set if we have disabled
* kernel _PAGE_GLOBAL pages.
*/
- if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI)) {
+ if (!static_cpu_has(X86_FEATURE_KPTI)) {
WARN_ON_ONCE(1);
return;
}
--
Regards/Gruss,
Boris.
SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284
(AG Nürnberg)
--
