Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Steven Price <steven.price@arm.com>
To:     linux-mm@kvack.org
Cc:     Steven Price <steven.price@arm.com>,
        Andy Lutomirski <luto@kernel.org>,
        Ard Biesheuvel <ard.biesheuvel@linaro.org>,
        Arnd Bergmann <arnd@arndb.de>, Borislav Petkov <bp@alien8.de>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Ingo Molnar <mingo@redhat.com>,
        James Morse <james.morse@arm.com>,
        =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= <jglisse@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Will Deacon <will.deacon@arm.com>, x86@kernel.org,
        "H. Peter Anvin" <hpa@zytor.com>,
        linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [PATCH 07/13] mm: pagewalk: Add test_p?d callbacks
Date:   Fri, 15 Feb 2019 17:02:28 +0000
Message-Id: <20190215170235.23360-8-steven.price@arm.com>
In-Reply-To: <20190215170235.23360-1-steven.price@arm.com>
References: <20190215170235.23360-1-steven.price@arm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

It is useful to be able to skip parts of the page table tree even when
walking without VMAs. Add test_p?d callbacks similar to test_walk but
which are called just before a table at that level is walked. If the
callback returns non-zero then the entire table is skipped.

Signed-off-by: Steven Price <steven.price@arm.com>
---
 include/linux/mm.h | 11 +++++++++++
 mm/pagewalk.c      | 24 ++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0418a018d7b3..0e4c9b6b554d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1428,6 +1428,11 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
  *             value means "do page table walk over the current vma,"
  *             and a negative one means "abort current page table walk
  *             right now." 1 means "skip the current vma."
+ * @test_pmd:  similar to test_walk(), but called for every pmd.
+ * @test_pud:  similar to test_walk(), but called for every pud.
+ * @test_p4d:  similar to test_walk(), but called for every p4d.
+ *             Returning 0 means walk this part of the page tables,
+ *             returning 1 means to skip this range.
  * @mm:        mm_struct representing the target process of page table walk
  * @vma:       vma currently walked (NULL if walking outside vmas)
  * @private:   private data for callbacks' usage
@@ -1452,6 +1457,12 @@ struct mm_walk {
 			     struct mm_walk *walk);
 	int (*test_walk)(unsigned long addr, unsigned long next,
 			struct mm_walk *walk);
+	int (*test_pmd)(unsigned long addr, unsigned long next,
+			pmd_t *pmd_start, struct mm_walk *walk);
+	int (*test_pud)(unsigned long addr, unsigned long next,
+			pud_t *pud_start, struct mm_walk *walk);
+	int (*test_p4d)(unsigned long addr, unsigned long next,
+			p4d_t *p4d_start, struct mm_walk *walk);
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	void *private;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index b8038f852f06..bce7571c6563 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -32,6 +32,14 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	unsigned long next;
 	int err = 0;
 
+	if (walk->test_pmd) {
+		err = walk->test_pmd(addr, end, pmd_offset(pud, 0), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	pmd = pmd_offset(pud, addr);
 	do {
 again:
@@ -82,6 +90,14 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	unsigned long next;
 	int err = 0;
 
+	if (walk->test_pud) {
+		err = walk->test_pud(addr, end, pud_offset(p4d, 0), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	pud = pud_offset(p4d, addr);
 	do {
  again:
@@ -128,6 +144,14 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	 */
 	int depth = (PTRS_PER_P4D == 1)?0:1;
 
+	if (walk->test_p4d) {
+		err = walk->test_p4d(addr, end, p4d_offset(pgd, 0), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	p4d = p4d_offset(pgd, addr);
 	do {
 		next = p4d_addr_end(addr, end);
-- 
2.20.1