linux-kernel - [PATCH 2/2] Add /proc/PID/{smaps, numa

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1508891255-15427-2-git-send-email-fan.du@intel.com>
Date:   Wed, 25 Oct 2017 08:27:35 +0800
From:   Fan Du <fan.du@...el.com>
To:     akpm@...ux-foundation.org, hch@....de, dan.j.williams@...el.com,
        dave.hansen@...el.com, mhocko@...nel.org
Cc:     linux-kernel@...r.kernel.org, linux-api@...r.kernel.org,
        Fan Du <fan.du@...el.com>
Subject: [PATCH 2/2] Add /proc/PID/{smaps, numa_maps} support for DAX

So user could check those interface for more detailed
information about how much DAX mappings are currently
created.

Here we use vma_is_dax method to find specific page
struture with DAX {huge, normal}page mappings,
vm_normal_page routine works as before without any
impact on the existing logical where _vm_normal_page
are called.

With this patch, user could check Device DAX usage at Ptes@ readings,
fox example, statistics from a Device DAX algined by 2MB:

7f6c17800000-7f6c17e00000 rw-s 00000000 00:06 20559  /dev/dax12.0
Size:               6144 kB
.
.
.
Ptes@2MB:      		6144 kB

Signed-off-by: Fan Du <fan.du@...el.com>
---
v3:
* Elaborate more about the usage suggested by Michal Hocko

v2:
* Using pte_devmap to check valid pfn page structure,
  Pointed out by Dan. thx!

---
 fs/proc/task_mmu.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 30dbf37..5c4535c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -531,7 +531,10 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	struct page *page = NULL;
 
 	if (pte_present(*pte)) {
-		page = vm_normal_page(vma, addr, *pte);
+		if (!vma_is_dax(vma))
+			page = vm_normal_page(vma, addr, *pte);
+		else if (pte_devmap(*pte))
+			page = pte_page(*pte);
 		mss->rss_pte += PAGE_SIZE;
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
@@ -583,7 +586,11 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 
 	/* FOLL_DUMP will return -EFAULT on huge zero page */
-	page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+	if (!vma_is_dax(vma))
+		page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+	else if (pmd_devmap(*pmd))
+		page = pmd_page(*pmd);
+
 	if (IS_ERR_OR_NULL(page))
 		return;
 	if (PageAnon(page))
@@ -1770,13 +1777,15 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	pte_t *orig_pte;
 	pte_t *pte;
+	struct page *page;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
-		struct page *page;
-
-		page = can_gather_numa_stats_pmd(*pmd, vma, addr);
+		if (!vma_is_dax(vma))
+			page = can_gather_numa_stats_pmd(*pmd, vma, addr);
+		else if (pmd_devmap(*pmd))
+			page = pmd_page(*pmd);
 		if (page)
 			gather_stats(page, md, pmd_dirty(*pmd),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
@@ -1789,7 +1798,10 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 #endif
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
-		struct page *page = can_gather_numa_stats(*pte, vma, addr);
+		if (!vma_is_dax(vma))
+			page = can_gather_numa_stats(*pte, vma, addr);
+		else if (pte_devmap(*pte))
+			page = pte_page(*pte);
 		if (!page)
 			continue;
 		gather_stats(page, md, pte_dirty(*pte), 1);
-- 
1.8.3.1