device-dax: make pgmap optional for instance creation

The passed in dev_pagemap is only required in the pmem case as the
libnvdimm core may have reserved a vmem_altmap for dev_memremap_pages() to
place the memmap in pmem directly.  In the hmem case there is no agent
reserving an altmap so it can all be handled by a core internal default.

Pass the resource range via a new @range property of 'struct
dev_dax_data'.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643099958.4062302.10379230791041872886.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106110513.30709.4303239334850606031.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Dan Williams 2020-10-13 16:49:43 -07:00 коммит произвёл Linus Torvalds
Родитель 174ebece37
Коммит f5516ec5ef
8 изменённых файлов: 62 добавлений и 38 удалений

Просмотреть файл

@ -271,7 +271,7 @@ static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
unsigned long long size = resource_size(&dev_dax->region->res);
unsigned long long size = range_len(&dev_dax->range);
return sprintf(buf, "%llu\n", size);
}
@ -293,19 +293,12 @@ static ssize_t target_node_show(struct device *dev,
}
static DEVICE_ATTR_RO(target_node);
static unsigned long long dev_dax_resource(struct dev_dax *dev_dax)
{
struct dax_region *dax_region = dev_dax->region;
return dax_region->res.start;
}
static ssize_t resource_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
return sprintf(buf, "%#llx\n", dev_dax_resource(dev_dax));
return sprintf(buf, "%#llx\n", dev_dax->range.start);
}
static DEVICE_ATTR(resource, 0400, resource_show, NULL);
@ -376,6 +369,7 @@ static void dev_dax_release(struct device *dev)
dax_region_put(dax_region);
put_dax(dax_dev);
kfree(dev_dax->pgmap);
kfree(dev_dax);
}
@ -412,7 +406,12 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
if (!dev_dax)
return ERR_PTR(-ENOMEM);
memcpy(&dev_dax->pgmap, data->pgmap, sizeof(struct dev_pagemap));
if (data->pgmap) {
dev_dax->pgmap = kmemdup(data->pgmap,
sizeof(struct dev_pagemap), GFP_KERNEL);
if (!dev_dax->pgmap)
goto err_pgmap;
}
/*
* No 'host' or dax_operations since there is no access to this
@ -421,18 +420,19 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
if (IS_ERR(dax_dev)) {
rc = PTR_ERR(dax_dev);
goto err;
goto err_alloc_dax;
}
/* a device_dax instance is dead while the driver is not attached */
kill_dax(dax_dev);
/* from here on we're committed to teardown via dax_dev_release() */
/* from here on we're committed to teardown via dev_dax_release() */
dev = &dev_dax->dev;
device_initialize(dev);
dev_dax->dax_dev = dax_dev;
dev_dax->region = dax_region;
dev_dax->range = data->range;
dev_dax->target_node = dax_region->target_node;
kref_get(&dax_region->kref);
@ -458,8 +458,9 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
return ERR_PTR(rc);
return dev_dax;
err:
err_alloc_dax:
kfree(dev_dax->pgmap);
err_pgmap:
kfree(dev_dax);
return ERR_PTR(rc);

Просмотреть файл

@ -3,6 +3,7 @@
#ifndef __DAX_BUS_H__
#define __DAX_BUS_H__
#include <linux/device.h>
#include <linux/range.h>
struct dev_dax;
struct resource;
@ -21,6 +22,7 @@ struct dev_dax_data {
struct dax_region *dax_region;
struct dev_pagemap *pgmap;
enum dev_dax_subsys subsys;
struct range range;
int id;
};

Просмотреть файл

@ -41,6 +41,7 @@ struct dax_region {
* @target_node: effective numa node if dev_dax memory range is onlined
* @dev - device core
* @pgmap - pgmap for memmap setup / lifetime (driver owned)
* @range: resource range for the instance
* @dax_mem_res: physical address range of hotadded DAX memory
* @dax_mem_name: name for hotadded DAX memory via add_memory_driver_managed()
*/
@ -49,10 +50,16 @@ struct dev_dax {
struct dax_device *dax_dev;
int target_node;
struct device dev;
struct dev_pagemap pgmap;
struct dev_pagemap *pgmap;
struct range range;
struct resource *dax_kmem_res;
};
static inline u64 range_len(struct range *range)
{
return range->end - range->start + 1;
}
static inline struct dev_dax *to_dev_dax(struct device *dev)
{
return container_of(dev, struct dev_dax, dev);

Просмотреть файл

@ -55,12 +55,12 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
__weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
unsigned long size)
{
struct resource *res = &dev_dax->region->res;
struct range *range = &dev_dax->range;
phys_addr_t phys;
phys = pgoff * PAGE_SIZE + res->start;
if (phys >= res->start && phys <= res->end) {
if (phys + size - 1 <= res->end)
phys = pgoff * PAGE_SIZE + range->start;
if (phys >= range->start && phys <= range->end) {
if (phys + size - 1 <= range->end)
return phys;
}
@ -396,21 +396,31 @@ int dev_dax_probe(struct device *dev)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
struct dax_device *dax_dev = dev_dax->dax_dev;
struct resource *res = &dev_dax->region->res;
struct range *range = &dev_dax->range;
struct dev_pagemap *pgmap;
struct inode *inode;
struct cdev *cdev;
void *addr;
int rc;
/* 1:1 map region resource range to device-dax instance range */
if (!devm_request_mem_region(dev, res->start, resource_size(res),
if (!devm_request_mem_region(dev, range->start, range_len(range),
dev_name(dev))) {
dev_warn(dev, "could not reserve region %pR\n", res);
dev_warn(dev, "could not reserve range: %#llx - %#llx\n",
range->start, range->end);
return -EBUSY;
}
dev_dax->pgmap.type = MEMORY_DEVICE_GENERIC;
addr = devm_memremap_pages(dev, &dev_dax->pgmap);
pgmap = dev_dax->pgmap;
if (!pgmap) {
pgmap = devm_kzalloc(dev, sizeof(*pgmap), GFP_KERNEL);
if (!pgmap)
return -ENOMEM;
pgmap->res.start = range->start;
pgmap->res.end = range->end;
}
pgmap->type = MEMORY_DEVICE_GENERIC;
addr = devm_memremap_pages(dev, pgmap);
if (IS_ERR(addr))
return PTR_ERR(addr);

Просмотреть файл

@ -8,7 +8,6 @@
static int dax_hmem_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct dev_pagemap pgmap = { };
struct dax_region *dax_region;
struct memregion_info *mri;
struct dev_dax_data data;
@ -20,8 +19,6 @@ static int dax_hmem_probe(struct platform_device *pdev)
return -ENOMEM;
mri = dev->platform_data;
memcpy(&pgmap.res, res, sizeof(*res));
dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
PMD_SIZE);
if (!dax_region)
@ -30,7 +27,10 @@ static int dax_hmem_probe(struct platform_device *pdev)
data = (struct dev_dax_data) {
.dax_region = dax_region,
.id = 0,
.pgmap = &pgmap,
.range = {
.start = res->start,
.end = res->end,
},
};
dev_dax = devm_create_dev_dax(&data);
if (IS_ERR(dev_dax))

Просмотреть файл

@ -22,7 +22,7 @@ static bool any_hotremove_failed;
int dev_dax_kmem_probe(struct device *dev)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
struct resource *res = &dev_dax->region->res;
struct range *range = &dev_dax->range;
resource_size_t kmem_start;
resource_size_t kmem_size;
resource_size_t kmem_end;
@ -39,17 +39,17 @@ int dev_dax_kmem_probe(struct device *dev)
*/
numa_node = dev_dax->target_node;
if (numa_node < 0) {
dev_warn(dev, "rejecting DAX region %pR with invalid node: %d\n",
res, numa_node);
dev_warn(dev, "rejecting DAX region with invalid node: %d\n",
numa_node);
return -EINVAL;
}
/* Hotplug starting at the beginning of the next block: */
kmem_start = ALIGN(res->start, memory_block_size_bytes());
kmem_start = ALIGN(range->start, memory_block_size_bytes());
kmem_size = resource_size(res);
kmem_size = range_len(range);
/* Adjust the size down to compensate for moving up kmem_start: */
kmem_size -= kmem_start - res->start;
kmem_size -= kmem_start - range->start;
/* Align the size down to cover only complete blocks: */
kmem_size &= ~(memory_block_size_bytes() - 1);
kmem_end = kmem_start + kmem_size;

Просмотреть файл

@ -63,6 +63,10 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
.id = id,
.pgmap = &pgmap,
.subsys = subsys,
.range = {
.start = res.start,
.end = res.end,
},
};
dev_dax = devm_create_dev_dax(&data);

Просмотреть файл

@ -9,12 +9,12 @@
phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
unsigned long size)
{
struct resource *res = &dev_dax->region->res;
struct range *range = &dev_dax->range;
phys_addr_t addr;
addr = pgoff * PAGE_SIZE + res->start;
if (addr >= res->start && addr <= res->end) {
if (addr + size - 1 <= res->end) {
addr = pgoff * PAGE_SIZE + range->start;
if (addr >= range->start && addr <= range->end) {
if (addr + size - 1 <= range->end) {
if (get_nfit_res(addr)) {
struct page *page;