Re: [PATCH V4 2/2] mm/khugepaged: retry with sync writeback for MADV_COLLAPSE

["David Hildenbrand (Red Hat)" <david@kernel.org>]

On 12/15/25 09:46, Shivank Garg wrote:
> When MADV_COLLAPSE is called on file-backed mappings (e.g., executable
> text sections), the pages may still be dirty from recent writes.
> collapse_file() will trigger async writeback and fail with
> SCAN_PAGE_DIRTY_OR_WRITEBACK (-EAGAIN).
> 
> MADV_COLLAPSE is a synchronous operation where userspace expects
> immediate results. If the collapse fails due to dirty pages, perform
> synchronous writeback on the specific range and retry once.
> 
> This avoids spurious failures for freshly written executables while
> avoiding unnecessary synchronous I/O for mappings that are already clean.
> 
> Reported-by: Branden Moore <Branden.Moore@amd.com>
> Closes: https://lore.kernel.org/all/4e26fe5e-7374-467c-a333-9dd48f85d7cc@amd.com
> Fixes: 34488399fa08 ("mm/madvise: add file and shmem support to MADV_COLLAPSE")
> Suggested-by: David Hildenbrand <david@kernel.org>
> Tested-by: Lance Yang <lance.yang@linux.dev>
> Signed-off-by: Shivank Garg <shivankg@amd.com>
> ---
>   mm/khugepaged.c | 40 ++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 40 insertions(+)
> 
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 219dfa2e523c..6c8c35d3e0c9 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -22,6 +22,7 @@
>   #include <linux/dax.h>
>   #include <linux/ksm.h>
>   #include <linux/pgalloc.h>
> +#include <linux/backing-dev.h>
>   
>   #include <asm/tlb.h>
>   #include "internal.h"
> @@ -2787,9 +2788,11 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
>   	hend = end & HPAGE_PMD_MASK;
>   
>   	for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) {
> +		bool retried = false;
>   		int result = SCAN_FAIL;
>   
>   		if (!mmap_locked) {
> +retry:

Jumping into an if block is nasty :)

>   			cond_resched();
>   			mmap_read_lock(mm);
>   			mmap_locked = true;
> @@ -2819,6 +2822,43 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
>   		if (!mmap_locked)
>   			*lock_dropped = true;
>   
> +		/*
> +		 * If the file-backed VMA has dirty pages, the scan triggers
> +		 * async writeback and returns SCAN_PAGE_DIRTY_OR_WRITEBACK.
> +		 * Since MADV_COLLAPSE is sync, we force sync writeback and
> +		 * retry once.
> +		 */
> +		if (result == SCAN_PAGE_DIRTY_OR_WRITEBACK && !retried) {
> +			/*
> +			 * File scan drops the lock. We must re-acquire it to
> +			 * safely inspect the VMA and hold the file reference.
> +			 */
> +			if (!mmap_locked) {
> +				cond_resched();
> +				mmap_read_lock(mm);
> +				mmap_locked = true;
> +				result = hugepage_vma_revalidate(mm, addr, false, &vma, cc);
> +				if (result != SCAN_SUCCEED)
> +					goto handle_result;
> +			}
> +
> +			if (!vma_is_anonymous(vma) && vma->vm_file &&
> +			    mapping_can_writeback(vma->vm_file->f_mapping)) {
> +				struct file *file = get_file(vma->vm_file);
> +				pgoff_t pgoff = linear_page_index(vma, addr);
> +				loff_t lstart = (loff_t)pgoff << PAGE_SHIFT;
> +				loff_t lend = lstart + HPAGE_PMD_SIZE - 1;
> +
> +				mmap_read_unlock(mm);
> +				mmap_locked = false;
> +				*lock_dropped = true;
> +				filemap_write_and_wait_range(file->f_mapping, lstart, lend);
> +				fput(file);
> +				retried = true;
> +				goto retry;
> +			}
> +		}
> +

This looks a bit complicated. Can't we move that handing up, where we have most of that
information already? Or am I missing something important?

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 97d1b2824386f..c7271877c5220 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -22,6 +22,7 @@
  #include <linux/dax.h>
  #include <linux/ksm.h>
  #include <linux/pgalloc.h>
+#include <linux/backing-dev.h>
  
  #include <asm/tlb.h>
  #include "internal.h"
@@ -2786,7 +2787,9 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
  
         for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) {
                 int result = SCAN_FAIL;
+               bool triggered_wb = false;
  
+retry:
                 if (!mmap_locked) {
                         cond_resched();
                         mmap_read_lock(mm);
@@ -2809,6 +2812,16 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
                         mmap_locked = false;
                         result = hpage_collapse_scan_file(mm, addr, file, pgoff,
                                                           cc);
+
+                       if (result == SCAN_PAGE_DIRTY_OR_WRITEBACK && !triggered_wb &&
+                           mapping_can_writeback(file->f_mapping)) {
+                               loff_t lstart = (loff_t)pgoff << PAGE_SHIFT;
+                               loff_t lend = lstart + HPAGE_PMD_SIZE - 1;
+
+                               filemap_write_and_wait_range(file->f_mapping, lstart, lend);
+                               triggered_wb = true;
+                               goto retry;
+                       }
                         fput(file);
                 } else {
                         result = hpage_collapse_scan_pmd(mm, vma, addr,


-- 
Cheers

David