linux/drivers/dax/pmem.c

154 lines
3.9 KiB
C
Raw Normal View History

/*
* Copyright(c) 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/percpu-refcount.h>
#include <linux/memremap.h>
#include <linux/module.h>
#include <linux/pfn_t.h>
#include "../nvdimm/pfn.h"
#include "../nvdimm/nd.h"
#include "device-dax.h"
struct dax_pmem {
struct device *dev;
struct percpu_ref ref;
struct dev_pagemap pgmap;
struct completion cmp;
};
static struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
{
return container_of(ref, struct dax_pmem, ref);
}
static void dax_pmem_percpu_release(struct percpu_ref *ref)
{
struct dax_pmem *dax_pmem = to_dax_pmem(ref);
dev_dbg(dax_pmem->dev, "trace\n");
complete(&dax_pmem->cmp);
}
static void dax_pmem_percpu_exit(void *data)
{
struct percpu_ref *ref = data;
struct dax_pmem *dax_pmem = to_dax_pmem(ref);
dev_dbg(dax_pmem->dev, "trace\n");
mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash The x86 conversion to the generic GUP code included a small change which causes crashes and data corruption in the pmem code - not good. The root cause is that the /dev/pmem driver code implicitly relies on the x86 get_user_pages() implementation doing a get_page() on the page refcount, because get_page() does a get_zone_device_page() which properly refcounts pmem's separate page struct arrays that are not present in the regular page struct structures. (The pmem driver does this because it can cover huge memory areas.) But the x86 conversion to the generic GUP code changed the get_page() to page_cache_get_speculative() which is faster but doesn't do the get_zone_device_page() call the pmem code relies on. One way to solve the regression would be to change the generic GUP code to use get_page(), but that would slow things down a bit and punish other generic-GUP using architectures for an x86-ism they did not care about. (Arguably the pmem driver was probably not working reliably for them: but nvdimm is an Intel feature, so non-x86 exposure is probably still limited.) So restructure the pmem code's interface with the MM instead: get rid of the get/put_zone_device_page() distinction, integrate put_zone_device_page() into __put_page() and and restructure the pmem completion-wait and teardown machinery: Kirill points out that the calls to {get,put}_dev_pagemap() can be removed from the mm fast path if we take a single get_dev_pagemap() reference to signify that the page is alive and use the final put of the page to drop that reference. This does require some care to make sure that any waits for the percpu_ref to drop to zero occur *after* devm_memremap_page_release(), since it now maintains its own elevated reference. This speeds up things while also making the pmem refcounting more robust going forward. Suggested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/149339998297.24933.1129582806028305912.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-29 01:23:37 +08:00
wait_for_completion(&dax_pmem->cmp);
percpu_ref_exit(ref);
}
mm, devm_memremap_pages: fix shutdown handling The last step before devm_memremap_pages() returns success is to allocate a release action, devm_memremap_pages_release(), to tear the entire setup down. However, the result from devm_add_action() is not checked. Checking the error from devm_add_action() is not enough. The api currently relies on the fact that the percpu_ref it is using is killed by the time the devm_memremap_pages_release() is run. Rather than continue this awkward situation, offload the responsibility of killing the percpu_ref to devm_memremap_pages_release() directly. This allows devm_memremap_pages() to do the right thing relative to init failures and shutdown. Without this change we could fail to register the teardown of devm_memremap_pages(). The likelihood of hitting this failure is tiny as small memory allocations almost always succeed. However, the impact of the failure is large given any future reconfiguration, or disable/enable, of an nvdimm namespace will fail forever as subsequent calls to devm_memremap_pages() will fail to setup the pgmap_radix since there will be stale entries for the physical address range. An argument could be made to require that the ->kill() operation be set in the @pgmap arg rather than passed in separately. However, it helps code readability, tracking the lifetime of a given instance, to be able to grep the kill routine directly at the devm_memremap_pages() call site. Link: http://lkml.kernel.org/r/154275558526.76910.7535251937849268605.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Fixes: e8d513483300 ("memremap: change devm_memremap_pages interface...") Reviewed-by: "Jérôme Glisse" <jglisse@redhat.com> Reported-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 16:34:57 +08:00
static void dax_pmem_percpu_kill(struct percpu_ref *ref)
{
struct dax_pmem *dax_pmem = to_dax_pmem(ref);
dev_dbg(dax_pmem->dev, "trace\n");
percpu_ref_kill(ref);
}
static int dax_pmem_probe(struct device *dev)
{
void *addr;
struct resource res;
int rc, id, region_id;
struct nd_pfn_sb *pfn_sb;
struct dev_dax *dev_dax;
struct dax_pmem *dax_pmem;
struct nd_namespace_io *nsio;
struct dax_region *dax_region;
struct nd_namespace_common *ndns;
struct nd_dax *nd_dax = to_nd_dax(dev);
struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
ndns = nvdimm_namespace_common_probe(dev);
if (IS_ERR(ndns))
return PTR_ERR(ndns);
nsio = to_nd_namespace_io(&ndns->dev);
dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL);
if (!dax_pmem)
return -ENOMEM;
/* parse the 'pfn' info block via ->rw_bytes */
rc = devm_nsio_enable(dev, nsio);
if (rc)
return rc;
rc = nvdimm_setup_pfn(nd_pfn, &dax_pmem->pgmap);
if (rc)
return rc;
devm_nsio_disable(dev, nsio);
pfn_sb = nd_pfn->pfn_sb;
if (!devm_request_mem_region(dev, nsio->res.start,
resource_size(&nsio->res),
dev_name(&ndns->dev))) {
dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
return -EBUSY;
}
dax_pmem->dev = dev;
init_completion(&dax_pmem->cmp);
rc = percpu_ref_init(&dax_pmem->ref, dax_pmem_percpu_release, 0,
GFP_KERNEL);
if (rc)
return rc;
rc = devm_add_action(dev, dax_pmem_percpu_exit, &dax_pmem->ref);
if (rc) {
percpu_ref_exit(&dax_pmem->ref);
return rc;
}
dax_pmem->pgmap.ref = &dax_pmem->ref;
mm, devm_memremap_pages: fix shutdown handling The last step before devm_memremap_pages() returns success is to allocate a release action, devm_memremap_pages_release(), to tear the entire setup down. However, the result from devm_add_action() is not checked. Checking the error from devm_add_action() is not enough. The api currently relies on the fact that the percpu_ref it is using is killed by the time the devm_memremap_pages_release() is run. Rather than continue this awkward situation, offload the responsibility of killing the percpu_ref to devm_memremap_pages_release() directly. This allows devm_memremap_pages() to do the right thing relative to init failures and shutdown. Without this change we could fail to register the teardown of devm_memremap_pages(). The likelihood of hitting this failure is tiny as small memory allocations almost always succeed. However, the impact of the failure is large given any future reconfiguration, or disable/enable, of an nvdimm namespace will fail forever as subsequent calls to devm_memremap_pages() will fail to setup the pgmap_radix since there will be stale entries for the physical address range. An argument could be made to require that the ->kill() operation be set in the @pgmap arg rather than passed in separately. However, it helps code readability, tracking the lifetime of a given instance, to be able to grep the kill routine directly at the devm_memremap_pages() call site. Link: http://lkml.kernel.org/r/154275558526.76910.7535251937849268605.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Fixes: e8d513483300 ("memremap: change devm_memremap_pages interface...") Reviewed-by: "Jérôme Glisse" <jglisse@redhat.com> Reported-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 16:34:57 +08:00
dax_pmem->pgmap.kill = dax_pmem_percpu_kill;
addr = devm_memremap_pages(dev, &dax_pmem->pgmap);
mm, devm_memremap_pages: fix shutdown handling The last step before devm_memremap_pages() returns success is to allocate a release action, devm_memremap_pages_release(), to tear the entire setup down. However, the result from devm_add_action() is not checked. Checking the error from devm_add_action() is not enough. The api currently relies on the fact that the percpu_ref it is using is killed by the time the devm_memremap_pages_release() is run. Rather than continue this awkward situation, offload the responsibility of killing the percpu_ref to devm_memremap_pages_release() directly. This allows devm_memremap_pages() to do the right thing relative to init failures and shutdown. Without this change we could fail to register the teardown of devm_memremap_pages(). The likelihood of hitting this failure is tiny as small memory allocations almost always succeed. However, the impact of the failure is large given any future reconfiguration, or disable/enable, of an nvdimm namespace will fail forever as subsequent calls to devm_memremap_pages() will fail to setup the pgmap_radix since there will be stale entries for the physical address range. An argument could be made to require that the ->kill() operation be set in the @pgmap arg rather than passed in separately. However, it helps code readability, tracking the lifetime of a given instance, to be able to grep the kill routine directly at the devm_memremap_pages() call site. Link: http://lkml.kernel.org/r/154275558526.76910.7535251937849268605.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Fixes: e8d513483300 ("memremap: change devm_memremap_pages interface...") Reviewed-by: "Jérôme Glisse" <jglisse@redhat.com> Reported-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 16:34:57 +08:00
if (IS_ERR(addr))
return PTR_ERR(addr);
/* adjust the dax_region resource to the start of data */
memcpy(&res, &dax_pmem->pgmap.res, sizeof(res));
res.start += le64_to_cpu(pfn_sb->dataoff);
rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", &region_id, &id);
if (rc != 2)
return -EINVAL;
dax_region = alloc_dax_region(dev, region_id, &res,
le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
if (!dax_region)
return -ENOMEM;
/* TODO: support for subdividing a dax region... */
dev_dax = devm_create_dev_dax(dax_region, id, &res, 1);
/* child dev_dax instances now own the lifetime of the dax_region */
dax_region_put(dax_region);
return PTR_ERR_OR_ZERO(dev_dax);
}
static struct nd_device_driver dax_pmem_driver = {
.probe = dax_pmem_probe,
.drv = {
.name = "dax_pmem",
},
.type = ND_DRIVER_DAX_PMEM,
};
module_nd_driver(dax_pmem_driver);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Intel Corporation");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);