[REGRESSION] Re: [PATCH v8 15/19] mm: don't allow huge faults for files with pre content watches

[Alex Williamson <alex.williamson@redhat.com>]

20bf82a898b6 ("mm: don't allow huge faults for files with pre content watches")

This breaks huge_fault support for PFNMAPs that was recently added in
v6.12 and is used by vfio-pci to fault device memory using PMD and PUD
order mappings.  Thanks,

Alex


On Fri, 15 Nov 2024 10:30:28 -0500
Josef Bacik <josef@toxicpanda.com> wrote:

> There's nothing stopping us from supporting this, we could simply pass
> the order into the helper and emit the proper length.  However currently
> there's no tests to validate this works properly, so disable it until
> there's a desire to support this along with the appropriate tests.
> 
> Reviewed-by: Christian Brauner <brauner@kernel.org>
> Signed-off-by: Josef Bacik <josef@toxicpanda.com>
> ---
>  mm/memory.c | 22 ++++++++++++++++++++++
>  1 file changed, 22 insertions(+)
> 
> diff --git a/mm/memory.c b/mm/memory.c
> index bdf77a3ec47b..843ad75a4148 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -78,6 +78,7 @@
>  #include <linux/ptrace.h>
>  #include <linux/vmalloc.h>
>  #include <linux/sched/sysctl.h>
> +#include <linux/fsnotify.h>
>  
>  #include <trace/events/kmem.h>
>  
> @@ -5637,8 +5638,17 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
>  static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
>  {
>  	struct vm_area_struct *vma = vmf->vma;
> +	struct file *file = vma->vm_file;
>  	if (vma_is_anonymous(vma))
>  		return do_huge_pmd_anonymous_page(vmf);
> +	/*
> +	 * Currently we just emit PAGE_SIZE for our fault events, so don't allow
> +	 * a huge fault if we have a pre content watch on this file.  This would
> +	 * be trivial to support, but there would need to be tests to ensure
> +	 * this works properly and those don't exist currently.
> +	 */
> +	if (fsnotify_file_has_pre_content_watches(file))
> +		return VM_FAULT_FALLBACK;
>  	if (vma->vm_ops->huge_fault)
>  		return vma->vm_ops->huge_fault(vmf, PMD_ORDER);
>  	return VM_FAULT_FALLBACK;
> @@ -5648,6 +5658,7 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
>  static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
>  {
>  	struct vm_area_struct *vma = vmf->vma;
> +	struct file *file = vma->vm_file;
>  	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
>  	vm_fault_t ret;
>  
> @@ -5662,6 +5673,9 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
>  	}
>  
>  	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
> +		/* See comment in create_huge_pmd. */
> +		if (fsnotify_file_has_pre_content_watches(file))
> +			goto split;
>  		if (vma->vm_ops->huge_fault) {
>  			ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER);
>  			if (!(ret & VM_FAULT_FALLBACK))
> @@ -5681,9 +5695,13 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
>  #if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
>  	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
>  	struct vm_area_struct *vma = vmf->vma;
> +	struct file *file = vma->vm_file;
>  	/* No support for anonymous transparent PUD pages yet */
>  	if (vma_is_anonymous(vma))
>  		return VM_FAULT_FALLBACK;
> +	/* See comment in create_huge_pmd. */
> +	if (fsnotify_file_has_pre_content_watches(file))
> +		return VM_FAULT_FALLBACK;
>  	if (vma->vm_ops->huge_fault)
>  		return vma->vm_ops->huge_fault(vmf, PUD_ORDER);
>  #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
> @@ -5695,12 +5713,16 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
>  #if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
>  	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
>  	struct vm_area_struct *vma = vmf->vma;
> +	struct file *file = vma->vm_file;
>  	vm_fault_t ret;
>  
>  	/* No support for anonymous transparent PUD pages yet */
>  	if (vma_is_anonymous(vma))
>  		goto split;
>  	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
> +		/* See comment in create_huge_pmd. */
> +		if (fsnotify_file_has_pre_content_watches(file))
> +			goto split;
>  		if (vma->vm_ops->huge_fault) {
>  			ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER);
>  			if (!(ret & VM_FAULT_FALLBACK))