Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Muhammad Usama Anjum <usama.anjum@collabora.com>
To:     Jonathan Corbet <corbet@lwn.net>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Andrew Morton <akpm@linux-foundation.org>,
        Shuah Khan <shuah@kernel.org>,
        linux-doc@vger.kernel.org (open list:DOCUMENTATION),
        linux-kernel@vger.kernel.org (open list),
        linux-fsdevel@vger.kernel.org (open list:PROC FILESYSTEM),
        linux-mm@kvack.org (open list:MEMORY MANAGEMENT),
        linux-kselftest@vger.kernel.org (open list:KERNEL SELFTEST FRAMEWORK)
Cc:     Muhammad Usama Anjum <usama.anjum@collabora.com>,
        kernel@collabora.com,
        Gabriel Krisman Bertazi <krisman@collabora.com>,
        David Hildenbrand <david@redhat.com>,
        Peter Enderborg <peter.enderborg@sony.com>,
        Greg KH <gregkh@linuxfoundation.org>
Subject: [PATCH v3 1/4] fs/proc/task_mmu: update functions to clear the soft-dirty PTE bit
Date:   Fri, 26 Aug 2022 11:45:32 +0500
Message-Id: <20220826064535.1941190-2-usama.anjum@collabora.com>
In-Reply-To: <20220826064535.1941190-1-usama.anjum@collabora.com>
References: <20220826064535.1941190-1-usama.anjum@collabora.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Update the clear_soft_dirty() and clear_soft_dirty_pmd() to optionally
clear and return the status if page is dirty.

Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
---
Changes in v2:
- Move back the functions back to their original file
---
 fs/proc/task_mmu.c | 82 ++++++++++++++++++++++++++++------------------
 1 file changed, 51 insertions(+), 31 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 8b4f3073f8f5..f66674033207 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1095,8 +1095,8 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr,
 	return page_maybe_dma_pinned(page);
 }
 
-static inline void clear_soft_dirty(struct vm_area_struct *vma,
-		unsigned long addr, pte_t *pte)
+static inline bool check_soft_dirty(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *pte, bool clear)
 {
 	/*
 	 * The soft-dirty tracker uses #PF-s to catch writes
@@ -1105,55 +1105,75 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	 * of how soft-dirty works.
 	 */
 	pte_t ptent = *pte;
+	int dirty = 0;
 
 	if (pte_present(ptent)) {
 		pte_t old_pte;
 
-		if (pte_is_pinned(vma, addr, ptent))
-			return;
-		old_pte = ptep_modify_prot_start(vma, addr, pte);
-		ptent = pte_wrprotect(old_pte);
-		ptent = pte_clear_soft_dirty(ptent);
-		ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent);
+		dirty = pte_soft_dirty(ptent);
+
+		if (dirty && clear && !pte_is_pinned(vma, addr, ptent)) {
+			old_pte = ptep_modify_prot_start(vma, addr, pte);
+			ptent = pte_wrprotect(old_pte);
+			ptent = pte_clear_soft_dirty(ptent);
+			ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent);
+		}
 	} else if (is_swap_pte(ptent)) {
-		ptent = pte_swp_clear_soft_dirty(ptent);
-		set_pte_at(vma->vm_mm, addr, pte, ptent);
+		dirty = pte_swp_soft_dirty(ptent);
+
+		if (dirty && clear) {
+			ptent = pte_swp_clear_soft_dirty(ptent);
+			set_pte_at(vma->vm_mm, addr, pte, ptent);
+		}
 	}
+
+	return !!dirty;
 }
 #else
-static inline void clear_soft_dirty(struct vm_area_struct *vma,
-		unsigned long addr, pte_t *pte)
+static inline bool check_soft_dirty(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *pte, bool clear)
 {
+	return false;
 }
 #endif
 
 #if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
-		unsigned long addr, pmd_t *pmdp)
+static inline bool check_soft_dirty_pmd(struct vm_area_struct *vma,
+					unsigned long addr, pmd_t *pmdp, bool clear)
 {
 	pmd_t old, pmd = *pmdp;
+	int dirty = 0;
 
 	if (pmd_present(pmd)) {
-		/* See comment in change_huge_pmd() */
-		old = pmdp_invalidate(vma, addr, pmdp);
-		if (pmd_dirty(old))
-			pmd = pmd_mkdirty(pmd);
-		if (pmd_young(old))
-			pmd = pmd_mkyoung(pmd);
-
-		pmd = pmd_wrprotect(pmd);
-		pmd = pmd_clear_soft_dirty(pmd);
-
-		set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+		dirty = pmd_soft_dirty(pmd);
+		if (dirty && clear) {
+			/* See comment in change_huge_pmd() */
+			old = pmdp_invalidate(vma, addr, pmdp);
+			if (pmd_dirty(old))
+				pmd = pmd_mkdirty(pmd);
+			if (pmd_young(old))
+				pmd = pmd_mkyoung(pmd);
+
+			pmd = pmd_wrprotect(pmd);
+			pmd = pmd_clear_soft_dirty(pmd);
+
+			set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+		}
 	} else if (is_migration_entry(pmd_to_swp_entry(pmd))) {
-		pmd = pmd_swp_clear_soft_dirty(pmd);
-		set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+		dirty = pmd_swp_soft_dirty(pmd);
+
+		if (dirty && clear) {
+			pmd = pmd_swp_clear_soft_dirty(pmd);
+			set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+		}
 	}
+	return !!dirty;
 }
 #else
-static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
-		unsigned long addr, pmd_t *pmdp)
+static inline bool check_soft_dirty_pmd(struct vm_area_struct *vma,
+					unsigned long addr, pmd_t *pmdp, bool clear)
 {
+	return false;
 }
 #endif
 
@@ -1169,7 +1189,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
-			clear_soft_dirty_pmd(vma, addr, pmd);
+			check_soft_dirty_pmd(vma, addr, pmd, true);
 			goto out;
 		}
 
@@ -1195,7 +1215,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		ptent = *pte;
 
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
-			clear_soft_dirty(vma, addr, pte);
+			check_soft_dirty(vma, addr, pte, true);
 			continue;
 		}
 
-- 
2.30.2