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;
Subject: [PATCH v9 10/12] mm/devm_memremap_pages: Enable sub-section remap
From:   Dan Williams <dan.j.williams@intel.com>
To:     akpm@linux-foundation.org
Cc:     Michal Hocko <mhocko@suse.com>, Toshi Kani <toshi.kani@hpe.com>,
        =?utf-8?b?SsOpcsO0bWU=?= Glisse <jglisse@redhat.com>,
        Logan Gunthorpe <logang@deltatee.com>,
        Oscar Salvador <osalvador@suse.de>,
        Pavel Tatashin <pasha.tatashin@soleen.com>, linux-mm@kvack.org,
        linux-nvdimm@lists.01.org, linux-kernel@vger.kernel.org,
        osalvador@suse.de, mhocko@suse.com
Date:   Wed, 05 Jun 2019 14:58:53 -0700
Message-ID: <155977193326.2443951.14201009973429527491.stgit@dwillia2-desk3.amr.corp.intel.com>
In-Reply-To: <155977186863.2443951.9036044808311959913.stgit@dwillia2-desk3.amr.corp.intel.com>
References: <155977186863.2443951.9036044808311959913.stgit@dwillia2-desk3.amr.corp.intel.com>
User-Agent: StGit/0.18-2-gc94f
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Teach devm_memremap_pages() about the new sub-section capabilities of
arch_{add,remove}_memory(). Effectively, just replace all usage of
align_start, align_end, and align_size with res->start, res->end, and
resource_size(res). The existing sanity check will still make sure that
the two separate remap attempts do not collide within a sub-section (2MB
on x86).

Cc: Michal Hocko <mhocko@suse.com>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 kernel/memremap.c |   61 +++++++++++++++++++++--------------------------------
 1 file changed, 24 insertions(+), 37 deletions(-)

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 57980ed4e571..a0e5f6b91b04 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -58,7 +58,7 @@ static unsigned long pfn_first(struct dev_pagemap *pgmap)
 	struct vmem_altmap *altmap = &pgmap->altmap;
 	unsigned long pfn;
 
-	pfn = res->start >> PAGE_SHIFT;
+	pfn = PHYS_PFN(res->start);
 	if (pgmap->altmap_valid)
 		pfn += vmem_altmap_offset(altmap);
 	return pfn;
@@ -86,7 +86,6 @@ static void devm_memremap_pages_release(void *data)
 	struct dev_pagemap *pgmap = data;
 	struct device *dev = pgmap->dev;
 	struct resource *res = &pgmap->res;
-	resource_size_t align_start, align_size;
 	unsigned long pfn;
 	int nid;
 
@@ -96,25 +95,21 @@ static void devm_memremap_pages_release(void *data)
 	pgmap->cleanup(pgmap->ref);
 
 	/* pages are dead and unused, undo the arch mapping */
-	align_start = res->start & ~(PA_SECTION_SIZE - 1);
-	align_size = ALIGN(res->start + resource_size(res), PA_SECTION_SIZE)
-		- align_start;
-
-	nid = page_to_nid(pfn_to_page(align_start >> PAGE_SHIFT));
+	nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
 
 	mem_hotplug_begin();
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		pfn = align_start >> PAGE_SHIFT;
+		pfn = PHYS_PFN(res->start);
 		__remove_pages(page_zone(pfn_to_page(pfn)), pfn,
-				align_size >> PAGE_SHIFT, NULL);
+				PHYS_PFN(resource_size(res)), NULL);
 	} else {
-		arch_remove_memory(nid, align_start, align_size,
+		arch_remove_memory(nid, res->start, resource_size(res),
 				pgmap->altmap_valid ? &pgmap->altmap : NULL);
-		kasan_remove_zero_shadow(__va(align_start), align_size);
+		kasan_remove_zero_shadow(__va(res->start), resource_size(res));
 	}
 	mem_hotplug_done();
 
-	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
 	pgmap_array_delete(res);
 	dev_WARN_ONCE(dev, pgmap->altmap.alloc,
 		      "%s: failed to free all reserved pages\n", __func__);
@@ -141,16 +136,13 @@ static void devm_memremap_pages_release(void *data)
  */
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
-	resource_size_t align_start, align_size, align_end;
-	struct vmem_altmap *altmap = pgmap->altmap_valid ?
-			&pgmap->altmap : NULL;
 	struct resource *res = &pgmap->res;
 	struct dev_pagemap *conflict_pgmap;
 	struct mhp_restrictions restrictions = {
 		/*
 		 * We do not want any optional features only our own memmap
 		*/
-		.altmap = altmap,
+		.altmap = pgmap->altmap_valid ? &pgmap->altmap : NULL,
 	};
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
@@ -160,12 +152,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		return ERR_PTR(-EINVAL);
 	}
 
-	align_start = res->start & ~(PA_SECTION_SIZE - 1);
-	align_size = ALIGN(res->start + resource_size(res), PA_SECTION_SIZE)
-		- align_start;
-	align_end = align_start + align_size - 1;
-
-	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
 	if (conflict_pgmap) {
 		dev_WARN(dev, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
@@ -173,7 +160,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		goto err_array;
 	}
 
-	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
 	if (conflict_pgmap) {
 		dev_WARN(dev, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
@@ -181,7 +168,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		goto err_array;
 	}
 
-	is_ram = region_intersects(align_start, align_size,
+	is_ram = region_intersects(res->start, resource_size(res),
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
 	if (is_ram != REGION_DISJOINT) {
@@ -202,8 +189,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
-			align_size);
+	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
+			resource_size(res));
 	if (error)
 		goto err_pfn_remap;
 
@@ -221,25 +208,25 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	 * arch_add_memory().
 	 */
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		error = add_pages(nid, align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT, &restrictions);
+		error = add_pages(nid, PHYS_PFN(res->start),
+				PHYS_PFN(resource_size(res)), &restrictions);
 	} else {
-		error = kasan_add_zero_shadow(__va(align_start), align_size);
+		error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
 		if (error) {
 			mem_hotplug_done();
 			goto err_kasan;
 		}
 
-		error = arch_add_memory(nid, align_start, align_size,
-					&restrictions);
+		error = arch_add_memory(nid, res->start, resource_size(res),
+				&restrictions);
 	}
 
 	if (!error) {
 		struct zone *zone;
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
-		move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT, altmap);
+		move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
+				PHYS_PFN(resource_size(res)), restrictions.altmap);
 	}
 
 	mem_hotplug_done();
@@ -251,8 +238,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	 * to allow us to do the work while not holding the hotplug lock.
 	 */
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
-				align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT, pgmap);
+				PHYS_PFN(res->start),
+				PHYS_PFN(resource_size(res)), pgmap);
 	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
 
 	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
@@ -263,9 +250,9 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	return __va(res->start);
 
  err_add_memory:
-	kasan_remove_zero_shadow(__va(align_start), align_size);
+	kasan_remove_zero_shadow(__va(res->start), resource_size(res));
  err_kasan:
-	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
  err_pfn_remap:
 	pgmap_array_delete(res);
  err_array: