Re: [PATCH] Revert "mm/vunmap: add cond_resched() in vunmap_pmd_range"

[Uladzislau Rezki <urezki@gmail.com>]

> 
> Let's cc Uladzislau on vmalloc things?
> 
> > How about this?
> 
> Well, lol, that's a simple approach to avoiding the problem ;)
> 
To me it looks like a specific workaround for a specific one user.

> > unmap_kernel_range had been atomic operation and zsmalloc has used
> > it in atomic context in zs_unmap_object.
> > However, ("e47110e90584, mm/vunmap: add cond_resched() in vunmap_pmd_range")
> > changed it into non-atomic operation via adding cond_resched.
> > It causes zram decompresion failure by corrupting compressed buffer
> > in atomic context.
> > 
> > This patch introduces unmap_kernel_range_atomic which works for
> > only range less than PMD_SIZE to prevent cond_resched call.
> > 
> > ...
> >
> > --- a/include/linux/vmalloc.h
> > +++ b/include/linux/vmalloc.h
> > @@ -180,6 +180,7 @@ int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
> >  		struct page **pages);
> >  extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
> >  extern void unmap_kernel_range(unsigned long addr, unsigned long size);
> > +extern void unmap_kernel_range_atomic(unsigned long addr, unsigned long size);
> >  static inline void set_vm_flush_reset_perms(void *addr)
> >  {
> >  	struct vm_struct *vm = find_vm_area(addr);
> > @@ -200,6 +201,7 @@ unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
> >  {
> >  }
> >  #define unmap_kernel_range unmap_kernel_range_noflush
> > +#define unmap_kernel_range_atomic unmap_kernel_range_noflush
> >  static inline void set_vm_flush_reset_perms(void *addr)
> >  {
> >  }
> > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > index d7075ad340aa..714e5425dc45 100644
> > --- a/mm/vmalloc.c
> > +++ b/mm/vmalloc.c
> > @@ -88,6 +88,7 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
> >  	pmd_t *pmd;
> >  	unsigned long next;
> >  	int cleared;
> > +	bool check_resched = (end - addr) > PMD_SIZE;
> >  
> >  	pmd = pmd_offset(pud, addr);
> >  	do {
> > @@ -102,8 +103,8 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
> >  		if (pmd_none_or_clear_bad(pmd))
> >  			continue;
> >  		vunmap_pte_range(pmd, addr, next, mask);
> > -
> > -		cond_resched();
> > +		if (check_resched)
> > +			cond_resched();
> >  	} while (pmd++, addr = next, addr != end);
> >  }
> >  
> > @@ -2024,6 +2025,24 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)
> >  	flush_tlb_kernel_range(addr, end);
> >  }
> >  
> > +/**
> > + * unmap_kernel_range_atomic - unmap kernel VM area and flush cache and TLB
> > + * @addr: start of the VM area to unmap
> > + * @size: size of the VM area to unmap
> > + *
> > + * Similar to unmap_kernel_range_noflush() but it's atomic. @size should be
> > + * less than PMD_SIZE.
> > + */
> > +void unmap_kernel_range_atomic(unsigned long addr, unsigned long size)
> > +{
> > +	unsigned long end = addr + size;
> > +
> > +	flush_cache_vunmap(addr, end);
> > +	WARN_ON(size > PMD_SIZE);
> 
> WARN_ON_ONCE() would be better here - no point in creating a million
> warnings where one would suffice.
> 
> > +	unmap_kernel_range_noflush(addr, size);
> > +	flush_tlb_kernel_range(addr, end);
> > +}
> > +
> >  static inline void setup_vmalloc_vm_locked(struct vm_struct *vm,
> >  	struct vmap_area *va, unsigned long flags, const void *caller)
> >  {
> > diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
> > index 662ee420706f..9decc7634852 100644
> > --- a/mm/zsmalloc.c
> > +++ b/mm/zsmalloc.c
> > @@ -1154,7 +1154,7 @@ static inline void __zs_unmap_object(struct mapping_area *area,
> >  {
> >  	unsigned long addr = (unsigned long)area->vm_addr;
> >  
> > -	unmap_kernel_range(addr, PAGE_SIZE * 2);
> > +	unmap_kernel_range_atomic(addr, PAGE_SIZE * 2);
> >  }
> 
> I suppose we could live with it if no better solutions are forthcoming.
>
Maybe solve it on zsmalloc side? For example to add __zs_unmap_object_deferred(),
so it schedules the work that calls unmap_kernel_range() on a list of mapping_area
objects.

--
Vlad Rezki