mm: pagewalk: add p4d_entry() and pgd_entry()

pgd_entry() and pud_entry() were removed by commit 0b1fbfe500
("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no
users.  We're about to add users so reintroduce them, along with
p4d_entry() as we now have 5 levels of tables.

Note that commit a00cc7d9dd ("mm, x86: add support for PUD-sized
transparent hugepages") already re-added pud_entry() but with different
semantics to the other callbacks.  This commit reverts the semantics back
to match the other callbacks.

To support hmm.c which now uses the new semantics of pud_entry() a new
member ('action') of struct mm_walk is added which allows the callbacks to
either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or
repeat the callback (ACTION_AGAIN).  hmm.c is then updated to call
pud_trans_huge_lock() itself and make use of the splitting/retry logic of
the core code.

After this change pud_entry() is called for all entries, not just
transparent huge pages.

[arnd@arndb.de: fix unused variable warning]
 Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com
Signed-off-by: Steven Price <steven.price@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zong Li <zong.li@sifive.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/pagewalk.h

@@ -8,15 +8,15 @@ struct mm_walk;
 
 /**
  * mm_walk_ops - callbacks for walk_page_range
- * @pud_entry:		if set, called for each non-empty PUD (2nd-level) entry
+ * @pgd_entry:		if set, called for each non-empty PGD (top-level) entry
- *			this handler should only handle pud_trans_huge() puds.
+ * @p4d_entry:		if set, called for each non-empty P4D entry
- *			the pmd_entry or pte_entry callbacks will be used for
+ * @pud_entry:		if set, called for each non-empty PUD entry
- *			regular PUDs.
+ * @pmd_entry:		if set, called for each non-empty PMD entry
- * @pmd_entry:		if set, called for each non-empty PMD (3rd-level) entry
  *			this handler is required to be able to handle
  *			pmd_trans_huge() pmds.  They may simply choose to
  *			split_huge_page() instead of handling it explicitly.
- * @pte_entry:		if set, called for each non-empty PTE (4th-level) entry
+ * @pte_entry:		if set, called for each non-empty PTE (lowest-level)
+ *			entry
  * @pte_hole:		if set, called for each hole at all levels
  * @hugetlb_entry:	if set, called for each hugetlb entry
  * @test_walk:		caller specific callback function to determine whether
@@ -27,8 +27,15 @@ struct mm_walk;
  * @pre_vma:            if set, called before starting walk on a non-null vma.
  * @post_vma:           if set, called after a walk on a non-null vma, provided
  *                      that @pre_vma and the vma walk succeeded.
+ *
+ * p?d_entry callbacks are called even if those levels are folded on a
+ * particular architecture/configuration.
  */
 struct mm_walk_ops {
+	int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
+	int (*p4d_entry)(p4d_t *p4d, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
 	int (*pud_entry)(pud_t *pud, unsigned long addr,
 			 unsigned long next, struct mm_walk *walk);
 	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
@@ -47,11 +54,25 @@ struct mm_walk_ops {
 	void (*post_vma)(struct mm_walk *walk);
 };
 
+/*
+ * Action for pud_entry / pmd_entry callbacks.
+ * ACTION_SUBTREE is the default
+ */
+enum page_walk_action {
+	/* Descend to next level, splitting huge pages if needed and possible */
+	ACTION_SUBTREE = 0,
+	/* Continue to next entry at this level (ignoring any subtree) */
+	ACTION_CONTINUE = 1,
+	/* Call again for this entry */
+	ACTION_AGAIN = 2
+};
+
 /**
  * mm_walk - walk_page_range data
  * @ops:	operation to call during the walk
  * @mm:		mm_struct representing the target process of page table walk
  * @vma:	vma currently walked (NULL if walking outside vmas)
+ * @action:	next action to perform (see enum page_walk_action)
  * @private:	private data for callbacks' usage
  *
  * (see the comment on walk_page_range() for more details)
@@ -60,6 +81,7 @@ struct mm_walk {
 	const struct mm_walk_ops *ops;
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
+	enum page_walk_action action;
 	void *private;
 };
 

mm/hmm.c

@@ -474,23 +474,32 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
-	unsigned long addr = start, next;
+	unsigned long addr = start;
-	pmd_t *pmdp;
 	pud_t pud;
-	int ret;
+	int ret = 0;
+	spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);
+
+	if (!ptl)
+		return 0;
+
+	/* Normally we don't want to split the huge page */
+	walk->action = ACTION_CONTINUE;
 
-again:
 	pud = READ_ONCE(*pudp);
-	if (pud_none(pud))
+	if (pud_none(pud)) {
-		return hmm_vma_walk_hole(start, end, walk);
+		ret = hmm_vma_walk_hole(start, end, walk);
+		goto out_unlock;
+	}
 
 	if (pud_huge(pud) && pud_devmap(pud)) {
 		unsigned long i, npages, pfn;
 		uint64_t *pfns, cpu_flags;
 		bool fault, write_fault;
 
-		if (!pud_present(pud))
+		if (!pud_present(pud)) {
-			return hmm_vma_walk_hole(start, end, walk);
+			ret = hmm_vma_walk_hole(start, end, walk);
+			goto out_unlock;
+		}
 
 		i = (addr - range->start) >> PAGE_SHIFT;
 		npages = (end - addr) >> PAGE_SHIFT;
@@ -499,16 +508,20 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 		cpu_flags = pud_to_hmm_pfn_flags(range, pud);
 		hmm_range_need_fault(hmm_vma_walk, pfns, npages,
 				     cpu_flags, &fault, &write_fault);
-		if (fault || write_fault)
+		if (fault || write_fault) {
-			return hmm_vma_walk_hole_(addr, end, fault,
+			ret = hmm_vma_walk_hole_(addr, end, fault,
 						 write_fault, walk);
+			goto out_unlock;
+		}
 
 		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 		for (i = 0; i < npages; ++i, ++pfn) {
 			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
 					      hmm_vma_walk->pgmap);
-			if (unlikely(!hmm_vma_walk->pgmap))
+			if (unlikely(!hmm_vma_walk->pgmap)) {
-				return -EBUSY;
+				ret = -EBUSY;
+				goto out_unlock;
+			}
 			pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
 				  cpu_flags;
 		}
@@ -517,22 +530,15 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 			hmm_vma_walk->pgmap = NULL;
 		}
 		hmm_vma_walk->last = end;
-		return 0;
+		goto out_unlock;
 	}
 
-	split_huge_pud(walk->vma, pudp, addr);
+	/* Ask for the PUD to be split */
-	if (pud_none(*pudp))
+	walk->action = ACTION_SUBTREE;
-		goto again;
 
-	pmdp = pmd_offset(pudp, addr);
+out_unlock:
-	do {
+	spin_unlock(ptl);
-		next = pmd_addr_end(addr, end);
-		ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
-		if (ret)
 	return ret;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 0;
 }
 #else
 #define hmm_vma_walk_pud	NULL

mm/pagewalk.c

@@ -46,6 +46,9 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 				break;
 			continue;
 		}
+
+		walk->action = ACTION_SUBTREE;
+
 		/*
 		 * This implies that each ->pmd_entry() handler
 		 * needs to know about pmd_trans_huge() pmds
@@ -55,16 +58,21 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 		if (err)
 			break;
 
+		if (walk->action == ACTION_AGAIN)
+			goto again;
+
 		/*
 		 * Check this here so we only break down trans_huge
 		 * pages when we _need_ to
 		 */
-		if (!ops->pte_entry)
+		if (walk->action == ACTION_CONTINUE ||
+		    !(ops->pte_entry))
 			continue;
 
 		split_huge_pmd(walk->vma, pmd, addr);
 		if (pmd_trans_unstable(pmd))
 			goto again;
+
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
 			break;
@@ -93,23 +101,24 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 			continue;
 		}
 
-		if (ops->pud_entry) {
+		walk->action = ACTION_SUBTREE;
-			spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
 
-			if (ptl) {
+		if (ops->pud_entry)
 			err = ops->pud_entry(pud, addr, next, walk);
-				spin_unlock(ptl);
 		if (err)
 			break;
+
+		if (walk->action == ACTION_AGAIN)
+			goto again;
+
+		if (walk->action == ACTION_CONTINUE ||
+		    !(ops->pmd_entry || ops->pte_entry))
 			continue;
-			}
-		}
 
 		split_huge_pud(walk->vma, pud, addr);
 		if (pud_none(*pud))
 			goto again;
 
-		if (ops->pmd_entry || ops->pte_entry)
 		err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
@@ -136,7 +145,12 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 				break;
 			continue;
 		}
-		if (ops->pmd_entry || ops->pte_entry)
+		if (ops->p4d_entry) {
+			err = ops->p4d_entry(p4d, addr, next, walk);
+			if (err)
+				break;
+		}
+		if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
 			err = walk_pud_range(p4d, addr, next, walk);
 		if (err)
 			break;
@@ -163,7 +177,13 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
 				break;
 			continue;
 		}
-		if (ops->pmd_entry || ops->pte_entry)
+		if (ops->pgd_entry) {
+			err = ops->pgd_entry(pgd, addr, next, walk);
+			if (err)
+				break;
+		}
+		if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry ||
+		    ops->pte_entry)
 			err = walk_p4d_range(pgd, addr, next, walk);
 		if (err)
 			break;