Patch "mm: pmd dirty emulation in page fault handler" has been added to the 4.9-stable tree

This is a note to let you know that I've just added the patch titled

mm: pmd dirty emulation in page fault handler

to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
mm-pmd-dirty-emulation-in-page-fault-handler.patch
and it can be found in the queue-4.9 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

From: Minchan Kim <[email protected]>
Date: Tue, 10 Jan 2017 16:57:51 -0800
Subject: mm: pmd dirty emulation in page fault handler

From: Minchan Kim <[email protected]>

commit 20f664aabeb88d582b623a625f83b0454fa34f07 upstream.

Andreas reported [1] made a test in jemalloc hang in THP mode in arm64:

http://lkml.kernel.org/r/[email protected]

The problem is currently page fault handler doesn't supports dirty bit emulation of pmd for non-HW dirty-bit architecture so that application stucks until VM marked the pmd dirty.

How the emulation work depends on the architecture. In case of arm64, when it set up pte firstly, it sets pte PTE_RDONLY to get a chance to mark the pte dirty via triggering page fault when store access happens. Once the page fault occurs, VM marks the pmd dirty and arch code for setting pmd will clear PTE_RDONLY for application to proceed.

IOW, if VM doesn't mark the pmd dirty, application hangs forever by repeated fault(i.e., store op but the pmd is PTE_RDONLY).

This patch enables pmd dirty-bit emulation for those architectures.

[1] b8d3c4c3009d, mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called

---
 mm/huge_memory.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -872,15 +872,17 @@ void huge_pmd_set_accessed(struct fault_
 {
 	pmd_t entry;
 	unsigned long haddr;
+	bool write = fe->flags & FAULT_FLAG_WRITE;
 
 	fe->ptl = pmd_lock(fe->vma->vm_mm, fe->pmd);
 	if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
 		goto unlock;
 
 	entry = pmd_mkyoung(orig_pmd);
+	if (write)
+		entry = pmd_mkdirty(entry);
 	haddr = fe->address & HPAGE_PMD_MASK;
-	if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry,
-				fe->flags & FAULT_FLAG_WRITE))
+	if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry, write))
 		update_mmu_cache_pmd(fe->vma, fe->address, fe->pmd);
 
 unlock:

Patches currently in stable-queue which might be from [email protected] are

queue-4.9/zram-support-bdi_cap_stable_writes.patch queue-4.9/zram-revalidate-disk-under-init_lock.patch queue-4.9/mm-pmd-dirty-emulation-in-page-fault-handler.patch