Re: [RFC PATCH v8 03/14] mm, x86: Add support for eXclusive Page Frame Ownership (XPFO)

[Peter Zijlstra]

On Wed, Feb 13, 2019 at 05:01:26PM -0700, Khalid Aziz wrote:
>  static inline void *kmap_atomic(struct page *page)
>  {
> +	void *kaddr;
> +
>  	preempt_disable();
>  	pagefault_disable();
> +	kaddr = page_address(page);
> +	xpfo_kmap(kaddr, page);
> +	return kaddr;
>  }
>  #define kmap_atomic_prot(page, prot)	kmap_atomic(page)
>  
>  static inline void __kunmap_atomic(void *addr)
>  {
> +	xpfo_kunmap(addr, virt_to_page(addr));
>  	pagefault_enable();
>  	preempt_enable();
>  }

How is that supposed to work; IIRC kmap_atomic was supposed to be
IRQ-safe.

> +/* Per-page XPFO house-keeping data */
> +struct xpfo {
> +	unsigned long flags;	/* Page state */
> +	bool inited;		/* Map counter and lock initialized */

What's sizeof(_Bool) ? Why can't you use a bit in that flags word?

> +	atomic_t mapcount;	/* Counter for balancing map/unmap requests */
> +	spinlock_t maplock;	/* Lock to serialize map/unmap requests */
> +};

Without that bool, the structure would be 16 bytes on 64bit, which seems
like a good number.

> +void xpfo_kmap(void *kaddr, struct page *page)
> +{
> +	struct xpfo *xpfo;
> +
> +	if (!static_branch_unlikely(&xpfo_inited))
> +		return;
> +
> +	xpfo = lookup_xpfo(page);
> +
> +	/*
> +	 * The page was allocated before page_ext was initialized (which means
> +	 * it's a kernel page) or it's allocated to the kernel, so nothing to
> +	 * do.
> +	 */
> +	if (!xpfo || unlikely(!xpfo->inited) ||
> +	    !test_bit(XPFO_PAGE_USER, &xpfo->flags))
> +		return;
> +
> +	spin_lock(&xpfo->maplock);
> +
> +	/*
> +	 * The page was previously allocated to user space, so map it back
> +	 * into the kernel. No TLB flush required.
> +	 */
> +	if ((atomic_inc_return(&xpfo->mapcount) == 1) &&
> +	    test_and_clear_bit(XPFO_PAGE_UNMAPPED, &xpfo->flags))
> +		set_kpte(kaddr, page, PAGE_KERNEL);
> +
> +	spin_unlock(&xpfo->maplock);
> +}
> +EXPORT_SYMBOL(xpfo_kmap);
> +
> +void xpfo_kunmap(void *kaddr, struct page *page)
> +{
> +	struct xpfo *xpfo;
> +
> +	if (!static_branch_unlikely(&xpfo_inited))
> +		return;
> +
> +	xpfo = lookup_xpfo(page);
> +
> +	/*
> +	 * The page was allocated before page_ext was initialized (which means
> +	 * it's a kernel page) or it's allocated to the kernel, so nothing to
> +	 * do.
> +	 */
> +	if (!xpfo || unlikely(!xpfo->inited) ||
> +	    !test_bit(XPFO_PAGE_USER, &xpfo->flags))
> +		return;
> +
> +	spin_lock(&xpfo->maplock);
> +
> +	/*
> +	 * The page is to be allocated back to user space, so unmap it from the
> +	 * kernel, flush the TLB and tag it as a user page.
> +	 */
> +	if (atomic_dec_return(&xpfo->mapcount) == 0) {
> +		WARN(test_bit(XPFO_PAGE_UNMAPPED, &xpfo->flags),
> +		     "xpfo: unmapping already unmapped page\n");
> +		set_bit(XPFO_PAGE_UNMAPPED, &xpfo->flags);
> +		set_kpte(kaddr, page, __pgprot(0));
> +		xpfo_flush_kernel_tlb(page, 0);
> +	}
> +
> +	spin_unlock(&xpfo->maplock);
> +}
> +EXPORT_SYMBOL(xpfo_kunmap);

And these here things are most definitely not IRQ-safe.