From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/drivers/nvdimm/pfn_devs.c | 395 +++++++++++++++++++++++++++++++++++---------------------
1 files changed, 248 insertions(+), 147 deletions(-)
diff --git a/kernel/drivers/nvdimm/pfn_devs.c b/kernel/drivers/nvdimm/pfn_devs.c
index 86ed09b..b499df6 100644
--- a/kernel/drivers/nvdimm/pfn_devs.c
+++ b/kernel/drivers/nvdimm/pfn_devs.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
*/
#include <linux/memremap.h>
#include <linux/blkdev.h>
@@ -33,17 +25,6 @@
kfree(nd_pfn->uuid);
kfree(nd_pfn);
}
-
-static struct device_type nd_pfn_device_type = {
- .name = "nd_pfn",
- .release = nd_pfn_release,
-};
-
-bool is_nd_pfn(struct device *dev)
-{
- return dev ? dev->type == &nd_pfn_device_type : false;
-}
-EXPORT_SYMBOL(is_nd_pfn);
struct nd_pfn *to_nd_pfn(struct device *dev)
{
@@ -75,7 +56,7 @@
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc = 0;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
if (dev->driver)
rc = -EBUSY;
@@ -97,7 +78,7 @@
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
@@ -111,43 +92,46 @@
return sprintf(buf, "%ld\n", nd_pfn->align);
}
-static const unsigned long *nd_pfn_supported_alignments(void)
+static unsigned long *nd_pfn_supported_alignments(unsigned long *alignments)
{
- /*
- * This needs to be a non-static variable because the *_SIZE
- * macros aren't always constants.
- */
- const unsigned long supported_alignments[] = {
- PAGE_SIZE,
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- HPAGE_PMD_SIZE,
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
- HPAGE_PUD_SIZE,
-#endif
-#endif
- 0,
- };
- static unsigned long data[ARRAY_SIZE(supported_alignments)];
- memcpy(data, supported_alignments, sizeof(data));
+ alignments[0] = PAGE_SIZE;
- return data;
+ if (has_transparent_hugepage()) {
+ alignments[1] = HPAGE_PMD_SIZE;
+ if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+ alignments[2] = HPAGE_PUD_SIZE;
+ }
+
+ return alignments;
+}
+
+/*
+ * Use pmd mapping if supported as default alignment
+ */
+static unsigned long nd_pfn_default_alignment(void)
+{
+
+ if (has_transparent_hugepage())
+ return HPAGE_PMD_SIZE;
+ return PAGE_SIZE;
}
static ssize_t align_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
+ unsigned long aligns[MAX_NVDIMM_ALIGN] = { [0] = 0, };
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_size_select_store(dev, buf, &nd_pfn->align,
- nd_pfn_supported_alignments());
+ nd_pfn_supported_alignments(aligns));
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
@@ -169,11 +153,11 @@
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
@@ -198,13 +182,13 @@
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
@@ -216,7 +200,7 @@
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
@@ -230,11 +214,11 @@
/* no address to convey if the pfn instance is disabled */
rc = -ENXIO;
}
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
-static DEVICE_ATTR_RO(resource);
+static DEVICE_ATTR_ADMIN_RO(resource);
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -242,7 +226,7 @@
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
@@ -258,7 +242,7 @@
/* no size to convey if the pfn instance is disabled */
rc = -ENXIO;
}
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
@@ -267,7 +251,10 @@
static ssize_t supported_alignments_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return nd_size_select_show(0, nd_pfn_supported_alignments(), buf);
+ unsigned long aligns[MAX_NVDIMM_ALIGN] = { [0] = 0, };
+
+ return nd_size_select_show(0,
+ nd_pfn_supported_alignments(aligns), buf);
}
static DEVICE_ATTR_RO(supported_alignments);
@@ -282,24 +269,28 @@
NULL,
};
-static umode_t pfn_visible(struct kobject *kobj, struct attribute *a, int n)
-{
- if (a == &dev_attr_resource.attr)
- return 0400;
- return a->mode;
-}
-
-struct attribute_group nd_pfn_attribute_group = {
+static struct attribute_group nd_pfn_attribute_group = {
.attrs = nd_pfn_attributes,
- .is_visible = pfn_visible,
};
-static const struct attribute_group *nd_pfn_attribute_groups[] = {
+const struct attribute_group *nd_pfn_attribute_groups[] = {
&nd_pfn_attribute_group,
&nd_device_attribute_group,
&nd_numa_attribute_group,
NULL,
};
+
+static const struct device_type nd_pfn_device_type = {
+ .name = "nd_pfn",
+ .release = nd_pfn_release,
+ .groups = nd_pfn_attribute_groups,
+};
+
+bool is_nd_pfn(struct device *dev)
+{
+ return dev ? dev->type == &nd_pfn_device_type : false;
+}
+EXPORT_SYMBOL(is_nd_pfn);
struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
struct nd_namespace_common *ndns)
@@ -310,7 +301,7 @@
return NULL;
nd_pfn->mode = PFN_MODE_NONE;
- nd_pfn->align = PFN_DEFAULT_ALIGNMENT;
+ nd_pfn->align = nd_pfn_default_alignment();
dev = &nd_pfn->dev;
device_initialize(&nd_pfn->dev);
if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
@@ -339,7 +330,6 @@
dev = &nd_pfn->dev;
dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id);
- dev->groups = nd_pfn_attribute_groups;
dev->type = &nd_pfn_device_type;
dev->parent = &nd_region->dev;
@@ -361,6 +351,89 @@
return dev;
}
+/*
+ * nd_pfn_clear_memmap_errors() clears any errors in the volatile memmap
+ * space associated with the namespace. If the memmap is set to DRAM, then
+ * this is a no-op. Since the memmap area is freshly initialized during
+ * probe, we have an opportunity to clear any badblocks in this area.
+ */
+static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn)
+{
+ struct nd_region *nd_region = to_nd_region(nd_pfn->dev.parent);
+ struct nd_namespace_common *ndns = nd_pfn->ndns;
+ void *zero_page = page_address(ZERO_PAGE(0));
+ struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+ int num_bad, meta_num, rc, bb_present;
+ sector_t first_bad, meta_start;
+ struct nd_namespace_io *nsio;
+
+ if (nd_pfn->mode != PFN_MODE_PMEM)
+ return 0;
+
+ nsio = to_nd_namespace_io(&ndns->dev);
+ meta_start = (SZ_4K + sizeof(*pfn_sb)) >> 9;
+ meta_num = (le64_to_cpu(pfn_sb->dataoff) >> 9) - meta_start;
+
+ /*
+ * re-enable the namespace with correct size so that we can access
+ * the device memmap area.
+ */
+ devm_namespace_disable(&nd_pfn->dev, ndns);
+ rc = devm_namespace_enable(&nd_pfn->dev, ndns, le64_to_cpu(pfn_sb->dataoff));
+ if (rc)
+ return rc;
+
+ do {
+ unsigned long zero_len;
+ u64 nsoff;
+
+ bb_present = badblocks_check(&nd_region->bb, meta_start,
+ meta_num, &first_bad, &num_bad);
+ if (bb_present) {
+ dev_dbg(&nd_pfn->dev, "meta: %x badblocks at %llx\n",
+ num_bad, first_bad);
+ nsoff = ALIGN_DOWN((nd_region->ndr_start
+ + (first_bad << 9)) - nsio->res.start,
+ PAGE_SIZE);
+ zero_len = ALIGN(num_bad << 9, PAGE_SIZE);
+ while (zero_len) {
+ unsigned long chunk = min(zero_len, PAGE_SIZE);
+
+ rc = nvdimm_write_bytes(ndns, nsoff, zero_page,
+ chunk, 0);
+ if (rc)
+ break;
+
+ zero_len -= chunk;
+ nsoff += chunk;
+ }
+ if (rc) {
+ dev_err(&nd_pfn->dev,
+ "error clearing %x badblocks at %llx\n",
+ num_bad, first_bad);
+ return rc;
+ }
+ }
+ } while (bb_present);
+
+ return 0;
+}
+
+static bool nd_supported_alignment(unsigned long align)
+{
+ int i;
+ unsigned long supported[MAX_NVDIMM_ALIGN] = { [0] = 0, };
+
+ if (align == 0)
+ return false;
+
+ nd_pfn_supported_alignments(supported);
+ for (i = 0; supported[i]; i++)
+ if (align == supported[i])
+ return true;
+ return false;
+}
+
/**
* nd_pfn_validate - read and validate info-block
* @nd_pfn: fsdax namespace runtime state / properties
@@ -373,6 +446,7 @@
int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
{
u64 checksum, offset;
+ struct resource *res;
enum nd_pfn_mode mode;
struct nd_namespace_io *nsio;
unsigned long align, start_pad;
@@ -409,6 +483,11 @@
if (__le16_to_cpu(pfn_sb->version_minor) < 2)
pfn_sb->align = 0;
+ if (__le16_to_cpu(pfn_sb->version_minor) < 4) {
+ pfn_sb->page_struct_size = cpu_to_le16(64);
+ pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
+ }
+
switch (le32_to_cpu(pfn_sb->mode)) {
case PFN_MODE_RAM:
case PFN_MODE_PMEM:
@@ -423,6 +502,34 @@
if (align == 0)
align = 1UL << ilog2(offset);
mode = le32_to_cpu(pfn_sb->mode);
+
+ if ((le32_to_cpu(pfn_sb->page_size) > PAGE_SIZE) &&
+ (mode == PFN_MODE_PMEM)) {
+ dev_err(&nd_pfn->dev,
+ "init failed, page size mismatch %d\n",
+ le32_to_cpu(pfn_sb->page_size));
+ return -EOPNOTSUPP;
+ }
+
+ if ((le16_to_cpu(pfn_sb->page_struct_size) < sizeof(struct page)) &&
+ (mode == PFN_MODE_PMEM)) {
+ dev_err(&nd_pfn->dev,
+ "init failed, struct page size mismatch %d\n",
+ le16_to_cpu(pfn_sb->page_struct_size));
+ return -EOPNOTSUPP;
+ }
+
+ /*
+ * Check whether the we support the alignment. For Dax if the
+ * superblock alignment is not matching, we won't initialize
+ * the device.
+ */
+ if (!nd_supported_alignment(align) &&
+ !memcmp(pfn_sb->signature, DAX_SIG, PFN_SIG_LEN)) {
+ dev_err(&nd_pfn->dev, "init failed, alignment mismatch: "
+ "%ld:%ld\n", nd_pfn->align, align);
+ return -EOPNOTSUPP;
+ }
if (!nd_pfn->uuid) {
/*
@@ -455,14 +562,14 @@
dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
nd_pfn->align, align, nd_pfn->mode,
mode);
- return -EINVAL;
+ return -EOPNOTSUPP;
}
}
if (align > nvdimm_namespace_capacity(ndns)) {
dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
align, nvdimm_namespace_capacity(ndns));
- return -EINVAL;
+ return -EOPNOTSUPP;
}
/*
@@ -472,18 +579,31 @@
* established.
*/
nsio = to_nd_namespace_io(&ndns->dev);
- if (offset >= resource_size(&nsio->res)) {
+ res = &nsio->res;
+ if (offset >= resource_size(res)) {
dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
dev_name(&ndns->dev));
- return -EBUSY;
+ return -EOPNOTSUPP;
}
- if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align))
+ if ((align && !IS_ALIGNED(res->start + offset + start_pad, align))
|| !IS_ALIGNED(offset, PAGE_SIZE)) {
dev_err(&nd_pfn->dev,
"bad offset: %#llx dax disabled align: %#lx\n",
offset, align);
- return -ENXIO;
+ return -EOPNOTSUPP;
+ }
+
+ if (!IS_ALIGNED(res->start + le32_to_cpu(pfn_sb->start_pad),
+ memremap_compat_align())) {
+ dev_err(&nd_pfn->dev, "resource start misaligned\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (!IS_ALIGNED(res->end + 1 - le32_to_cpu(pfn_sb->end_trunc),
+ memremap_compat_align())) {
+ dev_err(&nd_pfn->dev, "resource end misaligned\n");
+ return -EOPNOTSUPP;
}
return 0;
@@ -531,117 +651,79 @@
EXPORT_SYMBOL(nd_pfn_probe);
/*
- * 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)
{
- unsigned long reserve = PFN_UP(SZ_8K);
+ unsigned long reserve = nd_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;
}
static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
{
- struct resource *res = &pgmap->res;
+ struct range *range = &pgmap->range;
struct vmem_altmap *altmap = &pgmap->altmap;
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = le64_to_cpu(pfn_sb->dataoff);
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+ u32 reserve = nd_info_block_reserve();
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
resource_size_t base = nsio->res.start + start_pad;
+ resource_size_t end = nsio->res.end - end_trunc;
struct vmem_altmap __altmap = {
.base_pfn = init_altmap_base(base),
.reserve = init_altmap_reserve(base),
+ .end_pfn = PHYS_PFN(end),
};
- memcpy(res, &nsio->res, sizeof(*res));
- res->start += start_pad;
- res->end -= end_trunc;
-
+ *range = (struct range) {
+ .start = nsio->res.start + start_pad,
+ .end = nsio->res.end - end_trunc,
+ };
+ pgmap->nr_range = 1;
if (nd_pfn->mode == PFN_MODE_RAM) {
- if (offset < SZ_8K)
+ if (offset < reserve)
return -EINVAL;
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((range_len(range) - 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",
le64_to_cpu(nd_pfn->pfn_sb->npfns),
nd_pfn->npfns);
memcpy(altmap, &__altmap, sizeof(*altmap));
- altmap->free = PHYS_PFN(offset - SZ_8K);
+ altmap->free = PHYS_PFN(offset - reserve);
altmap->alloc = 0;
- pgmap->altmap_valid = true;
+ pgmap->flags |= PGMAP_ALTMAP_VALID;
} else
return -ENXIO;
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)
{
- u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0;
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
resource_size_t start, size;
struct nd_region *nd_region;
- u32 start_pad, end_trunc;
+ unsigned long npfns, align;
+ u32 end_trunc;
struct nd_pfn_sb *pfn_sb;
- unsigned long npfns;
phys_addr_t offset;
const char *sig;
u64 checksum;
@@ -658,6 +740,8 @@
sig = PFN_SIG;
rc = nd_pfn_validate(nd_pfn, sig);
+ if (rc == 0)
+ return nd_pfn_clear_memmap_errors(nd_pfn);
if (rc != -ENODEV)
return rc;
@@ -672,44 +756,56 @@
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 - SZ_8K)
- / PAGE_SIZE);
+ npfns = PHYS_PFN(size - SZ_8K);
+ align = max(nd_pfn->align, memremap_compat_align());
+
+ /*
+ * When @start is misaligned fail namespace creation. See
+ * the 'struct nd_pfn_sb' commentary on why ->start_pad is not
+ * an option.
+ */
+ if (!IS_ALIGNED(start, memremap_compat_align())) {
+ dev_err(&nd_pfn->dev, "%s: start %pa misaligned to %#lx\n",
+ dev_name(&ndns->dev), &start,
+ memremap_compat_align());
+ return -EINVAL;
+ }
+ end_trunc = start + size - ALIGN_DOWN(start + size, align);
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.
+ *
+ * Also make sure size of struct page is less than 64. We
+ * want to make sure we use large enough size here so that
+ * we don't have a dynamic reserve space depending on
+ * struct page size. But we also want to make sure we notice
+ * when we end up adding new elements to struct page.
*/
- offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
- max(nd_pfn->align, PMD_SIZE)) - start;
+ BUILD_BUG_ON(sizeof(struct page) > MAX_STRUCT_PAGE_SIZE);
+ offset = ALIGN(start + SZ_8K + MAX_STRUCT_PAGE_SIZE * npfns, align)
+ - start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
- offset = ALIGN(start + SZ_8K + dax_label_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 - end_trunc);
pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
pfn_sb->dataoff = cpu_to_le64(offset);
pfn_sb->npfns = cpu_to_le64(npfns);
@@ -717,13 +813,18 @@
memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
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->version_minor = cpu_to_le16(4);
pfn_sb->end_trunc = cpu_to_le32(end_trunc);
pfn_sb->align = cpu_to_le32(nd_pfn->align);
+ pfn_sb->page_struct_size = cpu_to_le16(MAX_STRUCT_PAGE_SIZE);
+ pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
+ rc = nd_pfn_clear_memmap_errors(nd_pfn);
+ if (rc)
+ return rc;
+
return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0);
}
--
Gitblit v1.6.2