[PATCH 1/4] x86/mm: Factor out CR3-building code

From: Andy Lutomirski
Date: Sun Sep 17 2017 - 12:04:42 EST


Current, the code that assembles a value to load into CR3 is
open-coded everywhere. Factor it out into helpers build_cr3() and
build_cr3_noflush().

This makes one semantic change: __get_current_cr3_fast() was wrong
on SME systems. No one noticed because the only caller is in the
VMX code, and there are no CPUs with both SME and VMX.

Cc: Tom Lendacky <Thomas.Lendacky@xxxxxxx>
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
arch/x86/include/asm/mmu_context.h | 15 +++++++++++----
arch/x86/mm/tlb.c | 11 +++++------
2 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 7ae318c340d9..a999ba6b721f 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -286,6 +286,15 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
return __pkru_allows_pkey(vma_pkey(vma), write);
}

+static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
+{
+ return __sme_pa(mm->pgd) | asid;
+}
+
+static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
+{
+ return __sme_pa(mm->pgd) | asid | CR3_NOFLUSH;
+}

/*
* This can be used from process context to figure out what the value of
@@ -296,10 +305,8 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
*/
static inline unsigned long __get_current_cr3_fast(void)
{
- unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd);
-
- if (static_cpu_has(X86_FEATURE_PCID))
- cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+ unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+ this_cpu_read(cpu_tlbstate.loaded_mm_asid));

/* For now, be very restrictive about when this can be called. */
VM_WARN_ON(in_nmi() || preemptible());
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1ab3821f9e26..93fe97cce581 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -126,8 +126,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* isn't free.
*/
#ifdef CONFIG_DEBUG_VM
- if (WARN_ON_ONCE(__read_cr3() !=
- (__sme_pa(real_prev->pgd) | prev_asid))) {
+ if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) {
/*
* If we were to BUG here, we'd be very likely to kill
* the system so hard that we don't see the call trace.
@@ -172,7 +171,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
*/
this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen,
next_tlb_gen);
- write_cr3(__sme_pa(next->pgd) | prev_asid);
+ write_cr3(build_cr3(next, prev_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
TLB_FLUSH_ALL);
}
@@ -216,12 +215,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- write_cr3(__sme_pa(next->pgd) | new_asid);
+ write_cr3(build_cr3(next, new_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH);
+ write_cr3(build_cr3_noflush(next, new_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
}

@@ -265,7 +264,7 @@ void initialize_tlbstate_and_flush(void)
!(cr4_read_shadow() & X86_CR4_PCIDE));

/* Force ASID 0 and force a TLB flush. */
- write_cr3(cr3 & ~CR3_PCID_MASK);
+ write_cr3(build_cr3(mm, 0));

/* Reinitialize tlbstate. */
this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
--
2.13.5