[Devel] [PATCH RHEL7 COMMIT] ms/mm: add debugfs tunable for fault_around_order

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-1062.12.1.vz7.131.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-1062.12.1.vz7.131.4
------>
commit 2a74e8fec8e8d535f7558a0fb5036a64e09cfcd5
Author: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
Date:   Thu Feb 27 19:07:33 2020 +0300

    ms/mm: add debugfs tunable for fault_around_order
    
    Let's allow people to tweak faultaround at runtime.
    
    [akpm at linux-foundation.org: coding-style fixes]
    Signed-off-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
    Cc: Linus Torvalds <torvalds at linux-foundation.org>
    Cc: Mel Gorman <mgorman at suse.de>
    Cc: Rik van Riel <riel at redhat.com>
    Cc: Andi Kleen <ak at linux.intel.com>
    Cc: Matthew Wilcox <matthew.r.wilcox at intel.com>
    Cc: Dave Hansen <dave.hansen at linux.intel.com>
    Cc: Alexander Viro <viro at zeniv.linux.org.uk>
    Cc: Dave Chinner <david at fromorbit.com>
    Cc: Ning Qu <quning at gmail.com>
    Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
    
    https://jira.sw.ru/browse/PSBM-101300
    (cherry picked from commit 1592eef01505177ed50149795a1560ec5a139df1)
    Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 mm/memory.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 61 insertions(+), 7 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 9ea5d21d7f5d6..a745f8bb7fb52 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -62,6 +62,7 @@
 #include <linux/gfp.h>
 #include <linux/migrate.h>
 #include <linux/string.h>
+#include <linux/debugfs.h>
 #include <linux/dma-debug.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
@@ -3123,8 +3124,63 @@ int finish_fault(struct vm_fault *vmf)
 }
 
 #define FAULT_AROUND_ORDER 4
-#define FAULT_AROUND_PAGES (1UL << FAULT_AROUND_ORDER)
-#define FAULT_AROUND_MASK ~((1UL << (PAGE_SHIFT + FAULT_AROUND_ORDER)) - 1)
+
+#ifdef CONFIG_DEBUG_FS
+static unsigned int fault_around_order = FAULT_AROUND_ORDER;
+
+static int fault_around_order_get(void *data, u64 *val)
+{
+	*val = fault_around_order;
+	return 0;
+}
+
+static int fault_around_order_set(void *data, u64 val)
+{
+	BUILD_BUG_ON((1UL << FAULT_AROUND_ORDER) > PTRS_PER_PTE);
+	if (1UL << val > PTRS_PER_PTE)
+		return -EINVAL;
+	fault_around_order = val;
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fault_around_order_fops,
+		fault_around_order_get, fault_around_order_set, "%llu\n");
+
+static int __init fault_around_debugfs(void)
+{
+	void *ret;
+
+	ret = debugfs_create_file("fault_around_order",	0644, NULL, NULL,
+			&fault_around_order_fops);
+	if (!ret)
+		pr_warn("Failed to create fault_around_order in debugfs");
+	return 0;
+}
+late_initcall(fault_around_debugfs);
+
+static inline unsigned long fault_around_pages(void)
+{
+	return 1UL << fault_around_order;
+}
+
+static inline unsigned long fault_around_mask(void)
+{
+	return ~((1UL << (PAGE_SHIFT + fault_around_order)) - 1);
+}
+#else
+static inline unsigned long fault_around_pages(void)
+{
+	unsigned long nr_pages;
+
+	nr_pages = 1UL << FAULT_AROUND_ORDER;
+	BUILD_BUG_ON(nr_pages > PTRS_PER_PTE);
+	return nr_pages;
+}
+
+static inline unsigned long fault_around_mask(void)
+{
+	return ~((1UL << (PAGE_SHIFT + FAULT_AROUND_ORDER)) - 1);
+}
+#endif
 
 static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
 		pte_t *pte, pgoff_t pgoff, unsigned int flags)
@@ -3134,21 +3190,19 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
 	struct vm_fault vmf;
 	int off;
 
-	BUILD_BUG_ON(FAULT_AROUND_PAGES > PTRS_PER_PTE);
-
-	start_addr = max(address & FAULT_AROUND_MASK, vma->vm_start);
+	start_addr = max(address & fault_around_mask(), vma->vm_start);
 	off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
 	pte -= off;
 	pgoff -= off;
 
 	/*
 	 *  max_pgoff is either end of page table or end of vma
-	 *  or FAULT_AROUND_PAGES from pgoff, depending what is neast.
+	 *  or fault_around_pages() from pgoff, depending what is neast.
 	 */
 	max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
 		PTRS_PER_PTE - 1;
 	max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1,
-			pgoff + FAULT_AROUND_PAGES - 1);
+			pgoff + fault_around_pages() - 1);
 
 	/* Check if it makes any sense to call ->map_pages */
 	while (!pte_none(*pte)) {