Re: [PATCHv11.1 04/16] x86/mm: Handle LAM on context switch

[kirill]

On Tue, Nov 08, 2022 at 07:54:35PM -0800, Andy Lutomirski wrote:
> On 11/7/22 13:35, Kirill A. Shutemov wrote:
> > Linear Address Masking mode for userspace pointers encoded in CR3 bits.
> > The mode is selected per-process and stored in mm_context_t.
> > 
> > switch_mm_irqs_off() now respects selected LAM mode and constructs CR3
> > accordingly.
> > 
> > The active LAM mode gets recorded in the tlb_state.
> > 
> 
> > +static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
> > +{
> > +	return mm->context.lam_cr3_mask;
> 
> READ_ONCE -- otherwise this has a data race and might generate sanitizer
> complaints.

Yep, thanks for pointing it out.

> > +}
> 
> > @@ -491,6 +496,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
> >   {
> >   	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
> >   	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
> > +	unsigned long prev_lam = tlbstate_lam_cr3_mask();
> > +	unsigned long new_lam = mm_lam_cr3_mask(next);
> 
> So I'm reading this again after drinking a cup of coffee.  new_lam is next's
> LAM mask according to mm_struct (and thus can change asynchronously due to a
> remote CPU).  prev_lam is based on tlbstate and can't change asynchronously,
> at least not with IRQs off.
> 
> 
> >   	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
> >   	unsigned cpu = smp_processor_id();
> >   	u64 next_tlb_gen;
> > @@ -520,7 +527,7 @@ 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() != build_cr3(real_prev->pgd, prev_asid))) {
> > +	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid, prev_lam))) {
> 
> So is the only purpose of tlbstate_lam_cr3_mask() to enable this warning to
> work?

Right. And disabling CONFIG_DEBUG_VM leads to warning. See the fixup
below.

> >   		/*
> >   		 * 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.
> > @@ -552,9 +559,15 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
> >   	 * instruction.
> >   	 */
> >   	if (real_prev == next) {
> > +		/* Not actually switching mm's */
> >   		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
> >   			   next->context.ctx_id);
> > +		/*
> > +		 * If this races with another thread that enables lam, 'new_lam'
> > +		 * might not match 'prev_lam'.
> > +		 */
> > +
> 
> Indeed.
> 
> >   		/*
> >   		 * Even in lazy TLB mode, the CPU should stay set in the
> >   		 * mm_cpumask. The TLB shootdown code can figure out from
> > @@ -622,15 +635,16 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
> >   		barrier();
> >   	}
> 
> > @@ -691,6 +705,10 @@ void initialize_tlbstate_and_flush(void)
> >   	/* Assert that CR3 already references the right mm. */
> >   	WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));
> > +	/* LAM expected to be disabled in CR3 and init_mm */
> > +	WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57));
> > +	WARN_ON(mm_lam_cr3_mask(&init_mm));
> > +
> 
> I think the callers all have init_mm selected, but the rest of this function
> is not really written with this assumption.  (But it does force ASID 0,
> which is at least a bizarre thing to do for non-init-mm.)

Hm. It uses tlb_gen of init_mm, so I assumed &init_mm == mm, but yeah it
is not strictly correct.

> What's the purpose of this warning?  I'm okay with keeping it, but maybe
> also add a warning that fires if mm != &init_mm.

Just to make sure we are in sane state. I can drop init_mm reference if it
helps.

The fixup based on your feedback:

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 1ab7ecf61659..6f5b58a5f951 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -94,7 +94,7 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 #ifdef CONFIG_X86_64
 static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
 {
-	return mm->context.lam_cr3_mask;
+	return READ_ONCE(mm->context.lam_cr3_mask);
 }
 
 static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4380776b3c61..ab66a48f38ce 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -496,7 +496,6 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 {
 	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
-	unsigned long prev_lam = tlbstate_lam_cr3_mask();
 	unsigned long new_lam = mm_lam_cr3_mask(next);
 	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
 	unsigned cpu = smp_processor_id();
@@ -527,7 +526,8 @@ 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() != build_cr3(real_prev->pgd, prev_asid, prev_lam))) {
+	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid,
+						   tlbstate_lam_cr3_mask()))) {
 		/*
 		 * 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.
@@ -565,7 +565,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 
 		/*
 		 * If this races with another thread that enables lam, 'new_lam'
-		 * might not match 'prev_lam'.
+		 * might not match tlbstate_lam_cr3_mask().
 		 */
 
 		/*
@@ -705,9 +705,9 @@ void initialize_tlbstate_and_flush(void)
 	/* Assert that CR3 already references the right mm. */
 	WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));
 
-	/* LAM expected to be disabled in CR3 and init_mm */
+	/* LAM expected to be disabled */
 	WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57));
-	WARN_ON(mm_lam_cr3_mask(&init_mm));
+	WARN_ON(mm_lam_cr3_mask(mm));
 
 	/*
 	 * Assert that CR4.PCIDE is set if needed.  (CR4.PCIDE initialization
-- 
  Kiryl Shutsemau / Kirill A. Shutemov