From: Dan Williams <dan.j.williams@intel.com>
To: akpm@linux-foundation.org
Cc: Jeff Moyer <jmoyer@redhat.com>,
linux-mm@kvack.org, linux-nvdimm@lists.01.org,
linux-kernel@vger.kernel.org, mhocko@suse.com, david@redhat.com
Subject: [PATCH v6 12/12] libnvdimm/pfn: Stop padding pmem namespaces to section alignment
Date: Wed, 17 Apr 2019 11:39:58 -0700 [thread overview]
Message-ID: <155552639846.2015392.14832585852837457293.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <155552633539.2015392.2477781120122237934.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 | 11 ++-----
drivers/nvdimm/pfn_devs.c | 75 +++++++--------------------------------------
include/linux/mmzone.h | 4 ++
3 files changed, 19 insertions(+), 71 deletions(-)
diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index e901e3a3b04c..ae589cc528f2 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -41,18 +41,13 @@ 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)
+#ifndef SUB_SECTION_ALIGN_DOWN
+#define SUB_SECTION_ALIGN_DOWN(x) (x)
+#define SUB_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..7bdaaf3dc77e 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 SUB_SECTION_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 - SUB_SECTION_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",
@@ -658,50 +657,10 @@ 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;
struct nd_pfn_sb *pfn_sb;
@@ -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);
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,
+ max(nd_pfn->align, SECTION_ACTIVE_SIZE)) - start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
- offset = ALIGN(start + reserve, nd_pfn->align) - start;
+ offset = ALIGN(start + SZ_8K, nd_pfn->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 3237c5e456df..d2445c483ad4 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1155,6 +1155,10 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
#define PAGES_PER_SUB_SECTION (SECTION_ACTIVE_SIZE / PAGE_SIZE)
#define PAGE_SUB_SECTION_MASK (~(PAGES_PER_SUB_SECTION-1))
+#define SUB_SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SUB_SECTION - 1) \
+ & PAGE_SUB_SECTION_MASK)
+#define SUB_SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUB_SECTION_MASK)
+
struct mem_section_usage {
/*
* SECTION_ACTIVE_SIZE portions of the section that are populated in
next prev parent reply other threads:[~2019-04-17 18:53 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-17 18:38 [PATCH v6 00/12] mm: Sub-section memory hotplug support Dan Williams
2019-04-17 18:39 ` [PATCH v6 01/12] mm/sparsemem: Introduce struct mem_section_usage Dan Williams
2019-05-01 23:25 ` Pavel Tatashin
2019-05-02 6:07 ` Dan Williams
2019-05-02 14:16 ` Pavel Tatashin
2019-05-04 0:22 ` Dan Williams
2019-05-04 15:55 ` Pavel Tatashin
2019-04-17 18:39 ` [PATCH v6 02/12] mm/sparsemem: Introduce common definitions for the size and mask of a section Dan Williams
2019-05-02 14:53 ` Pavel Tatashin
2019-05-03 0:41 ` Dan Williams
2019-05-03 10:35 ` Robin Murphy
2019-05-03 12:57 ` Pavel Tatashin
2019-05-03 13:00 ` Oscar Salvador
2019-04-17 18:39 ` [PATCH v6 03/12] mm/sparsemem: Add helpers track active portions of a section at boot Dan Williams
2019-04-25 14:33 ` Oscar Salvador
2019-04-25 14:43 ` Oscar Salvador
2019-04-26 12:57 ` Oscar Salvador
2019-05-02 16:12 ` Pavel Tatashin
2019-05-04 19:26 ` Dan Williams
2019-04-17 18:39 ` [PATCH v6 04/12] mm/hotplug: Prepare shrink_{zone, pgdat}_span for sub-section removal Dan Williams
2019-04-19 23:09 ` Ralph Campbell
2019-04-19 23:13 ` Dan Williams
2019-04-26 13:59 ` Oscar Salvador
2019-04-26 14:00 ` Oscar Salvador
2019-05-02 19:18 ` Pavel Tatashin
2019-04-17 18:39 ` [PATCH v6 05/12] mm/sparsemem: Convert kmalloc_section_memmap() to populate_section_memmap() Dan Williams
2019-05-02 19:28 ` Pavel Tatashin
2019-04-17 18:39 ` [PATCH v6 06/12] mm/hotplug: Add mem-hotplug restrictions for remove_memory() Dan Williams
2019-04-23 21:21 ` David Hildenbrand
2019-04-24 18:07 ` Dan Williams
2019-04-17 18:39 ` [PATCH v6 07/12] mm: Kill is_dev_zone() helper Dan Williams
2019-04-17 20:17 ` David Hildenbrand
2019-04-26 14:04 ` Oscar Salvador
2019-05-02 20:37 ` Pavel Tatashin
2019-04-17 18:39 ` [PATCH v6 08/12] mm/sparsemem: Prepare for sub-section ranges Dan Williams
2019-05-02 21:25 ` Pavel Tatashin
2019-04-17 18:39 ` [PATCH v6 09/12] mm/sparsemem: Support sub-section hotplug Dan Williams
2019-04-17 18:39 ` [PATCH v6 10/12] mm/devm_memremap_pages: Enable sub-section remap Dan Williams
2019-04-17 18:39 ` [PATCH v6 11/12] libnvdimm/pfn: Fix fsdax-mode namespace info-block zero-fields Dan Williams
2019-04-17 22:02 ` Andrew Morton
2019-04-17 22:09 ` Dan Williams
2019-04-17 18:39 ` Dan Williams [this message]
2019-04-17 22:03 ` [PATCH v6 00/12] mm: Sub-section memory hotplug support Andrew Morton
2019-04-17 22:59 ` Dan Williams
2019-04-18 2:09 ` Dan Williams
2019-04-18 12:45 ` Jeff Moyer
2019-04-19 3:25 ` Dan Williams
2019-04-23 13:16 ` Oscar Salvador
2019-04-24 20:43 ` Pavel Tatashin
2019-05-02 22:46 ` Pavel Tatashin
2019-05-02 23:20 ` Dan Williams
2019-05-02 23:21 ` Dan Williams
2019-05-03 10:48 ` 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=155552639846.2015392.14832585852837457293.stgit@dwillia2-desk3.amr.corp.intel.com \
--to=dan.j.williams@intel.com \
--cc=akpm@linux-foundation.org \
--cc=david@redhat.com \
--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 \
/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).