linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: akpm@linux-foundation.org
Cc: Jeff Moyer <jmoyer@redhat.com>,
	linux-nvdimm@lists.01.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, osalvador@suse.de, mhocko@suse.com
Subject: [PATCH v8 12/12] libnvdimm/pfn: Stop padding pmem namespaces to section alignment
Date: Mon, 06 May 2019 16:40:30 -0700	[thread overview]
Message-ID: <155718603019.130019.12886712685677568035.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <155718596657.130019.17139634728875079809.stgit@dwillia2-desk3.amr.corp.intel.com>

Now that the mm core supports section-unaligned hotplug of ZONE_DEVICE
memory, we no longer need to add padding at pfn/dax device creation
time. The kernel will still honor padding established by older kernels.

Reported-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/pfn.h      |   14 --------
 drivers/nvdimm/pfn_devs.c |   77 ++++++++-------------------------------------
 include/linux/mmzone.h    |    3 ++
 3 files changed, 16 insertions(+), 78 deletions(-)

diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index e901e3a3b04c..cc042a98758f 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -41,18 +41,4 @@ struct nd_pfn_sb {
 	__le64 checksum;
 };
 
-#ifdef CONFIG_SPARSEMEM
-#define PFN_SECTION_ALIGN_DOWN(x) SECTION_ALIGN_DOWN(x)
-#define PFN_SECTION_ALIGN_UP(x) SECTION_ALIGN_UP(x)
-#else
-/*
- * In this case ZONE_DEVICE=n and we will disable 'pfn' device support,
- * but we still want pmem to compile.
- */
-#define PFN_SECTION_ALIGN_DOWN(x) (x)
-#define PFN_SECTION_ALIGN_UP(x) (x)
-#endif
-
-#define PHYS_SECTION_ALIGN_DOWN(x) PFN_PHYS(PFN_SECTION_ALIGN_DOWN(PHYS_PFN(x)))
-#define PHYS_SECTION_ALIGN_UP(x) PFN_PHYS(PFN_SECTION_ALIGN_UP(PHYS_PFN(x)))
 #endif /* __NVDIMM_PFN_H */
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index a2406253eb70..7f54374b082f 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -595,14 +595,14 @@ static u32 info_block_reserve(void)
 }
 
 /*
- * We hotplug memory at section granularity, pad the reserved area from
- * the previous section base to the namespace base address.
+ * We hotplug memory at sub-section granularity, pad the reserved area
+ * from the previous section base to the namespace base address.
  */
 static unsigned long init_altmap_base(resource_size_t base)
 {
 	unsigned long base_pfn = PHYS_PFN(base);
 
-	return PFN_SECTION_ALIGN_DOWN(base_pfn);
+	return SUBSECTION_ALIGN_DOWN(base_pfn);
 }
 
 static unsigned long init_altmap_reserve(resource_size_t base)
@@ -610,7 +610,7 @@ static unsigned long init_altmap_reserve(resource_size_t base)
 	unsigned long reserve = info_block_reserve() >> PAGE_SHIFT;
 	unsigned long base_pfn = PHYS_PFN(base);
 
-	reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
+	reserve += base_pfn - SUBSECTION_ALIGN_DOWN(base_pfn);
 	return reserve;
 }
 
@@ -641,8 +641,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
 		pgmap->altmap_valid = false;
 	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
-		nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res)
-					- offset) / PAGE_SIZE);
+		nd_pfn->npfns = PHYS_PFN((resource_size(res) - offset));
 		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
 			dev_info(&nd_pfn->dev,
 					"number of pfns truncated from %lld to %ld\n",
@@ -658,54 +657,14 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 	return 0;
 }
 
-static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys)
-{
-	return min_t(u64, PHYS_SECTION_ALIGN_DOWN(phys),
-			ALIGN_DOWN(phys, nd_pfn->align));
-}
-
-/*
- * Check if pmem collides with 'System RAM', or other regions when
- * section aligned.  Trim it accordingly.
- */
-static void trim_pfn_device(struct nd_pfn *nd_pfn, u32 *start_pad, u32 *end_trunc)
-{
-	struct nd_namespace_common *ndns = nd_pfn->ndns;
-	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	struct nd_region *nd_region = to_nd_region(nd_pfn->dev.parent);
-	const resource_size_t start = nsio->res.start;
-	const resource_size_t end = start + resource_size(&nsio->res);
-	resource_size_t adjust, size;
-
-	*start_pad = 0;
-	*end_trunc = 0;
-
-	adjust = start - PHYS_SECTION_ALIGN_DOWN(start);
-	size = resource_size(&nsio->res) + adjust;
-	if (region_intersects(start - adjust, size, IORESOURCE_SYSTEM_RAM,
-				IORES_DESC_NONE) == REGION_MIXED
-			|| nd_region_conflict(nd_region, start - adjust, size))
-		*start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
-
-	/* Now check that end of the range does not collide. */
-	adjust = PHYS_SECTION_ALIGN_UP(end) - end;
-	size = resource_size(&nsio->res) + adjust;
-	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
-				IORES_DESC_NONE) == REGION_MIXED
-			|| !IS_ALIGNED(end, nd_pfn->align)
-			|| nd_region_conflict(nd_region, start, size))
-		*end_trunc = end - phys_pmem_align_down(nd_pfn, end);
-}
-
 static int nd_pfn_init(struct nd_pfn *nd_pfn)
 {
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	u32 start_pad, end_trunc, reserve = info_block_reserve();
 	resource_size_t start, size;
 	struct nd_region *nd_region;
+	unsigned long npfns, align;
 	struct nd_pfn_sb *pfn_sb;
-	unsigned long npfns;
 	phys_addr_t offset;
 	const char *sig;
 	u64 checksum;
@@ -736,43 +695,35 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 		return -ENXIO;
 	}
 
-	memset(pfn_sb, 0, sizeof(*pfn_sb));
-
-	trim_pfn_device(nd_pfn, &start_pad, &end_trunc);
-	if (start_pad + end_trunc)
-		dev_info(&nd_pfn->dev, "%s alignment collision, truncate %d bytes\n",
-				dev_name(&ndns->dev), start_pad + end_trunc);
-
 	/*
 	 * Note, we use 64 here for the standard size of struct page,
 	 * debugging options may cause it to be larger in which case the
 	 * implementation will limit the pfns advertised through
 	 * ->direct_access() to those that are included in the memmap.
 	 */
-	start = nsio->res.start + start_pad;
+	start = nsio->res.start;
 	size = resource_size(&nsio->res);
-	npfns = PFN_SECTION_ALIGN_UP((size - start_pad - end_trunc - reserve)
-			/ PAGE_SIZE);
+	npfns = PHYS_PFN(size - SZ_8K);
+	align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT));
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
 		/*
 		 * The altmap should be padded out to the block size used
 		 * when populating the vmemmap. This *should* be equal to
 		 * PMD_SIZE for most architectures.
 		 */
-		offset = ALIGN(start + reserve + 64 * npfns,
-				max(nd_pfn->align, PMD_SIZE)) - start;
+		offset = ALIGN(start + SZ_8K + 64 * npfns, align) - start;
 	} else if (nd_pfn->mode == PFN_MODE_RAM)
-		offset = ALIGN(start + reserve, nd_pfn->align) - start;
+		offset = ALIGN(start + SZ_8K, align) - start;
 	else
 		return -ENXIO;
 
-	if (offset + start_pad + end_trunc >= size) {
+	if (offset >= size) {
 		dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
 				dev_name(&ndns->dev));
 		return -ENXIO;
 	}
 
-	npfns = (size - offset - start_pad - end_trunc) / SZ_4K;
+	npfns = PHYS_PFN(size - offset);
 	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
 	pfn_sb->dataoff = cpu_to_le64(offset);
 	pfn_sb->npfns = cpu_to_le64(npfns);
@@ -781,8 +732,6 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
 	pfn_sb->version_major = cpu_to_le16(1);
 	pfn_sb->version_minor = cpu_to_le16(3);
-	pfn_sb->start_pad = cpu_to_le32(start_pad);
-	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
 	pfn_sb->align = cpu_to_le32(nd_pfn->align);
 	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
 	pfn_sb->checksum = cpu_to_le64(checksum);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 49e7fb452dfd..15e07f007ba2 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1181,6 +1181,9 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT))
 #endif
 
+#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION)
+#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
+
 struct mem_section_usage {
 	DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
 	/* See declaration of similar field in struct zone */


  parent reply	other threads:[~2019-05-06 23:54 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-06 23:39 [PATCH v8 00/12] mm: Sub-section memory hotplug support Dan Williams
2019-05-06 23:39 ` [PATCH v8 01/12] mm/sparsemem: Introduce struct mem_section_usage Dan Williams
2019-05-10 13:30   ` osalvador
2019-05-10 19:38     ` Dan Williams
2019-05-06 23:39 ` [PATCH v8 02/12] mm/memremap: Rename and consolidate SECTION_SIZE Dan Williams
2019-05-06 23:39 ` [PATCH v8 03/12] mm/sparsemem: Add helpers track active portions of a section at boot Dan Williams
2019-05-10 12:56   ` osalvador
2019-05-06 23:39 ` [PATCH v8 04/12] mm/hotplug: Prepare shrink_{zone, pgdat}_span for sub-section removal Dan Williams
2019-05-06 23:39 ` [PATCH v8 05/12] mm/sparsemem: Convert kmalloc_section_memmap() to populate_section_memmap() Dan Williams
2019-05-06 23:39 ` [PATCH v8 06/12] mm/hotplug: Kill is_dev_zone() usage in __remove_pages() Dan Williams
2019-05-06 23:40 ` [PATCH v8 07/12] mm: Kill is_dev_zone() helper Dan Williams
2019-05-06 23:40 ` [PATCH v8 08/12] mm/sparsemem: Prepare for sub-section ranges Dan Williams
2019-05-10 13:00   ` osalvador
2019-05-06 23:40 ` [PATCH v8 09/12] mm/sparsemem: Support sub-section hotplug Dan Williams
2019-05-08 23:15   ` Oscar Salvador
2019-05-13 13:54   ` Oscar Salvador
2019-06-04  4:47     ` Dan Williams
2019-05-06 23:40 ` [PATCH v8 10/12] mm/devm_memremap_pages: Enable sub-section remap Dan Williams
2019-05-06 23:40 ` [PATCH v8 11/12] libnvdimm/pfn: Fix fsdax-mode namespace info-block zero-fields Dan Williams
2019-05-06 23:40 ` Dan Williams [this message]
2019-05-13 21:01 ` [PATCH v8 00/12] mm: Sub-section memory hotplug support Mike Rapoport
2019-05-13 21:11   ` Dan Williams
2019-06-04  7:41 ` Oscar Salvador

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=155718603019.130019.12886712685677568035.stgit@dwillia2-desk3.amr.corp.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=jmoyer@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=mhocko@suse.com \
    --cc=osalvador@suse.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).