linux/lib/test_hmm.c

1554 lines
38 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* This is a module to test the HMM (Heterogeneous Memory Management)
* mirror and zone device private memory migration APIs of the kernel.
* Userspace programs can register with the driver to mirror their own address
* space and can use the device to read/write any valid virtual address.
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/cdev.h>
#include <linux/device.h>
#include <linux/memremap.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/delay.h>
#include <linux/pagemap.h>
#include <linux/hmm.h>
#include <linux/vmalloc.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/sched/mm.h>
#include <linux/platform_device.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include "test_hmm_uapi.h"
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
#define DMIRROR_NDEVICES 4
#define DMIRROR_RANGE_FAULT_TIMEOUT 1000
#define DEVMEM_CHUNK_SIZE (256 * 1024 * 1024U)
#define DEVMEM_CHUNKS_RESERVE 16
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
/*
* For device_private pages, dpage is just a dummy struct page
* representing a piece of device memory. dmirror_devmem_alloc_page
* allocates a real system memory page as backing storage to fake a
* real device. zone_device_data points to that backing page. But
* for device_coherent memory, the struct page represents real
* physical CPU-accessible memory that we can use directly.
*/
#define BACKING_PAGE(page) (is_device_private_page((page)) ? \
(page)->zone_device_data : (page))
static unsigned long spm_addr_dev0;
module_param(spm_addr_dev0, long, 0644);
MODULE_PARM_DESC(spm_addr_dev0,
"Specify start address for SPM (special purpose memory) used for device 0. By setting this Coherent device type will be used. Make sure spm_addr_dev1 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
static unsigned long spm_addr_dev1;
module_param(spm_addr_dev1, long, 0644);
MODULE_PARM_DESC(spm_addr_dev1,
"Specify start address for SPM (special purpose memory) used for device 1. By setting this Coherent device type will be used. Make sure spm_addr_dev0 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
static const struct dev_pagemap_ops dmirror_devmem_ops;
static const struct mmu_interval_notifier_ops dmirror_min_ops;
static dev_t dmirror_dev;
struct dmirror_device;
struct dmirror_bounce {
void *ptr;
unsigned long size;
unsigned long addr;
unsigned long cpages;
};
#define DPT_XA_TAG_ATOMIC 1UL
#define DPT_XA_TAG_WRITE 3UL
/*
* Data structure to track address ranges and register for mmu interval
* notifier updates.
*/
struct dmirror_interval {
struct mmu_interval_notifier notifier;
struct dmirror *dmirror;
};
/*
* Data attached to the open device file.
* Note that it might be shared after a fork().
*/
struct dmirror {
struct dmirror_device *mdevice;
struct xarray pt;
struct mmu_interval_notifier notifier;
struct mutex mutex;
};
/*
* ZONE_DEVICE pages for migration and simulating device memory.
*/
struct dmirror_chunk {
struct dev_pagemap pagemap;
struct dmirror_device *mdevice;
bool remove;
};
/*
* Per device data.
*/
struct dmirror_device {
struct cdev cdevice;
unsigned int zone_device_type;
struct device device;
unsigned int devmem_capacity;
unsigned int devmem_count;
struct dmirror_chunk **devmem_chunks;
struct mutex devmem_lock; /* protects the above */
unsigned long calloc;
unsigned long cfree;
struct page *free_pages;
spinlock_t lock; /* protects the above */
};
static struct dmirror_device dmirror_devices[DMIRROR_NDEVICES];
static int dmirror_bounce_init(struct dmirror_bounce *bounce,
unsigned long addr,
unsigned long size)
{
bounce->addr = addr;
bounce->size = size;
bounce->cpages = 0;
bounce->ptr = vmalloc(size);
if (!bounce->ptr)
return -ENOMEM;
return 0;
}
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
{
return (mdevice->zone_device_type ==
HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ? true : false;
}
static enum migrate_vma_direction
dmirror_select_device(struct dmirror *dmirror)
{
return (dmirror->mdevice->zone_device_type ==
HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ?
MIGRATE_VMA_SELECT_DEVICE_PRIVATE :
MIGRATE_VMA_SELECT_DEVICE_COHERENT;
}
static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
{
vfree(bounce->ptr);
}
static int dmirror_fops_open(struct inode *inode, struct file *filp)
{
struct cdev *cdev = inode->i_cdev;
struct dmirror *dmirror;
int ret;
/* Mirror this process address space */
dmirror = kzalloc(sizeof(*dmirror), GFP_KERNEL);
if (dmirror == NULL)
return -ENOMEM;
dmirror->mdevice = container_of(cdev, struct dmirror_device, cdevice);
mutex_init(&dmirror->mutex);
xa_init(&dmirror->pt);
ret = mmu_interval_notifier_insert(&dmirror->notifier, current->mm,
0, ULONG_MAX & PAGE_MASK, &dmirror_min_ops);
if (ret) {
kfree(dmirror);
return ret;
}
filp->private_data = dmirror;
return 0;
}
static int dmirror_fops_release(struct inode *inode, struct file *filp)
{
struct dmirror *dmirror = filp->private_data;
mmu_interval_notifier_remove(&dmirror->notifier);
xa_destroy(&dmirror->pt);
kfree(dmirror);
return 0;
}
static struct dmirror_chunk *dmirror_page_to_chunk(struct page *page)
{
return container_of(page->pgmap, struct dmirror_chunk, pagemap);
}
static struct dmirror_device *dmirror_page_to_device(struct page *page)
{
return dmirror_page_to_chunk(page)->mdevice;
}
static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range)
{
unsigned long *pfns = range->hmm_pfns;
unsigned long pfn;
for (pfn = (range->start >> PAGE_SHIFT);
pfn < (range->end >> PAGE_SHIFT);
pfn++, pfns++) {
struct page *page;
void *entry;
/*
* Since we asked for hmm_range_fault() to populate pages,
* it shouldn't return an error entry on success.
*/
WARN_ON(*pfns & HMM_PFN_ERROR);
WARN_ON(!(*pfns & HMM_PFN_VALID));
page = hmm_pfn_to_page(*pfns);
WARN_ON(!page);
entry = page;
if (*pfns & HMM_PFN_WRITE)
entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
else if (WARN_ON(range->default_flags & HMM_PFN_WRITE))
return -EFAULT;
entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
if (xa_is_err(entry))
return xa_err(entry);
}
return 0;
}
static void dmirror_do_update(struct dmirror *dmirror, unsigned long start,
unsigned long end)
{
unsigned long pfn;
void *entry;
/*
* The XArray doesn't hold references to pages since it relies on
* the mmu notifier to clear page pointers when they become stale.
* Therefore, it is OK to just clear the entry.
*/
xa_for_each_range(&dmirror->pt, pfn, entry, start >> PAGE_SHIFT,
end >> PAGE_SHIFT)
xa_erase(&dmirror->pt, pfn);
}
static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
const struct mmu_notifier_range *range,
unsigned long cur_seq)
{
struct dmirror *dmirror = container_of(mni, struct dmirror, notifier);
/*
* Ignore invalidation callbacks for device private pages since
* the invalidation is handled as part of the migration process.
*/
if (range->event == MMU_NOTIFY_MIGRATE &&
range->owner == dmirror->mdevice)
return true;
if (mmu_notifier_range_blockable(range))
mutex_lock(&dmirror->mutex);
else if (!mutex_trylock(&dmirror->mutex))
return false;
mmu_interval_set_seq(mni, cur_seq);
dmirror_do_update(dmirror, range->start, range->end);
mutex_unlock(&dmirror->mutex);
return true;
}
static const struct mmu_interval_notifier_ops dmirror_min_ops = {
.invalidate = dmirror_interval_invalidate,
};
static int dmirror_range_fault(struct dmirror *dmirror,
struct hmm_range *range)
{
struct mm_struct *mm = dmirror->notifier.mm;
unsigned long timeout =
jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
int ret;
while (true) {
if (time_after(jiffies, timeout)) {
ret = -EBUSY;
goto out;
}
range->notifier_seq = mmu_interval_read_begin(range->notifier);
mmap_read_lock(mm);
ret = hmm_range_fault(range);
mmap_read_unlock(mm);
if (ret) {
if (ret == -EBUSY)
continue;
goto out;
}
mutex_lock(&dmirror->mutex);
if (mmu_interval_read_retry(range->notifier,
range->notifier_seq)) {
mutex_unlock(&dmirror->mutex);
continue;
}
break;
}
ret = dmirror_do_fault(dmirror, range);
mutex_unlock(&dmirror->mutex);
out:
return ret;
}
static int dmirror_fault(struct dmirror *dmirror, unsigned long start,
unsigned long end, bool write)
{
struct mm_struct *mm = dmirror->notifier.mm;
unsigned long addr;
unsigned long pfns[64];
struct hmm_range range = {
.notifier = &dmirror->notifier,
.hmm_pfns = pfns,
.pfn_flags_mask = 0,
.default_flags =
HMM_PFN_REQ_FAULT | (write ? HMM_PFN_REQ_WRITE : 0),
.dev_private_owner = dmirror->mdevice,
};
int ret = 0;
/* Since the mm is for the mirrored process, get a reference first. */
if (!mmget_not_zero(mm))
return 0;
for (addr = start; addr < end; addr = range.end) {
range.start = addr;
range.end = min(addr + (ARRAY_SIZE(pfns) << PAGE_SHIFT), end);
ret = dmirror_range_fault(dmirror, &range);
if (ret)
break;
}
mmput(mm);
return ret;
}
static int dmirror_do_read(struct dmirror *dmirror, unsigned long start,
unsigned long end, struct dmirror_bounce *bounce)
{
unsigned long pfn;
void *ptr;
ptr = bounce->ptr + ((start - bounce->addr) & PAGE_MASK);
for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
void *entry;
struct page *page;
entry = xa_load(&dmirror->pt, pfn);
page = xa_untag_pointer(entry);
if (!page)
return -ENOENT;
memcpy_from_page(ptr, page, 0, PAGE_SIZE);
ptr += PAGE_SIZE;
bounce->cpages++;
}
return 0;
}
static int dmirror_read(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd)
{
struct dmirror_bounce bounce;
unsigned long start, end;
unsigned long size = cmd->npages << PAGE_SHIFT;
int ret;
start = cmd->addr;
end = start + size;
if (end < start)
return -EINVAL;
ret = dmirror_bounce_init(&bounce, start, size);
if (ret)
return ret;
while (1) {
mutex_lock(&dmirror->mutex);
ret = dmirror_do_read(dmirror, start, end, &bounce);
mutex_unlock(&dmirror->mutex);
if (ret != -ENOENT)
break;
start = cmd->addr + (bounce.cpages << PAGE_SHIFT);
ret = dmirror_fault(dmirror, start, end, false);
if (ret)
break;
cmd->faults++;
}
if (ret == 0) {
if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
bounce.size))
ret = -EFAULT;
}
cmd->cpages = bounce.cpages;
dmirror_bounce_fini(&bounce);
return ret;
}
static int dmirror_do_write(struct dmirror *dmirror, unsigned long start,
unsigned long end, struct dmirror_bounce *bounce)
{
unsigned long pfn;
void *ptr;
ptr = bounce->ptr + ((start - bounce->addr) & PAGE_MASK);
for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
void *entry;
struct page *page;
entry = xa_load(&dmirror->pt, pfn);
page = xa_untag_pointer(entry);
if (!page || xa_pointer_tag(entry) != DPT_XA_TAG_WRITE)
return -ENOENT;
memcpy_to_page(page, 0, ptr, PAGE_SIZE);
ptr += PAGE_SIZE;
bounce->cpages++;
}
return 0;
}
static int dmirror_write(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd)
{
struct dmirror_bounce bounce;
unsigned long start, end;
unsigned long size = cmd->npages << PAGE_SHIFT;
int ret;
start = cmd->addr;
end = start + size;
if (end < start)
return -EINVAL;
ret = dmirror_bounce_init(&bounce, start, size);
if (ret)
return ret;
if (copy_from_user(bounce.ptr, u64_to_user_ptr(cmd->ptr),
bounce.size)) {
ret = -EFAULT;
goto fini;
}
while (1) {
mutex_lock(&dmirror->mutex);
ret = dmirror_do_write(dmirror, start, end, &bounce);
mutex_unlock(&dmirror->mutex);
if (ret != -ENOENT)
break;
start = cmd->addr + (bounce.cpages << PAGE_SHIFT);
ret = dmirror_fault(dmirror, start, end, true);
if (ret)
break;
cmd->faults++;
}
fini:
cmd->cpages = bounce.cpages;
dmirror_bounce_fini(&bounce);
return ret;
}
static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
struct page **ppage)
{
struct dmirror_chunk *devmem;
struct resource *res = NULL;
unsigned long pfn;
unsigned long pfn_first;
unsigned long pfn_last;
void *ptr;
int ret = -ENOMEM;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
if (!devmem)
return ret;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
switch (mdevice->zone_device_type) {
case HMM_DMIRROR_MEMORY_DEVICE_PRIVATE:
res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
"hmm_dmirror");
if (IS_ERR_OR_NULL(res))
goto err_devmem;
devmem->pagemap.range.start = res->start;
devmem->pagemap.range.end = res->end;
devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
break;
case HMM_DMIRROR_MEMORY_DEVICE_COHERENT:
devmem->pagemap.range.start = (MINOR(mdevice->cdevice.dev) - 2) ?
spm_addr_dev0 :
spm_addr_dev1;
devmem->pagemap.range.end = devmem->pagemap.range.start +
DEVMEM_CHUNK_SIZE - 1;
devmem->pagemap.type = MEMORY_DEVICE_COHERENT;
break;
default:
ret = -EINVAL;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
goto err_devmem;
}
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
mm/memremap_pages: support multiple ranges per invocation In support of device-dax growing the ability to front physically dis-contiguous ranges of memory, update devm_memremap_pages() to track multiple ranges with a single reference counter and devm instance. Convert all [devm_]memremap_pages() users to specify the number of ranges they are mapping in their 'struct dev_pagemap' instance. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.co Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:34 +08:00
devmem->pagemap.nr_range = 1;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
devmem->pagemap.ops = &dmirror_devmem_ops;
devmem->pagemap.owner = mdevice;
mutex_lock(&mdevice->devmem_lock);
if (mdevice->devmem_count == mdevice->devmem_capacity) {
struct dmirror_chunk **new_chunks;
unsigned int new_capacity;
new_capacity = mdevice->devmem_capacity +
DEVMEM_CHUNKS_RESERVE;
new_chunks = krealloc(mdevice->devmem_chunks,
sizeof(new_chunks[0]) * new_capacity,
GFP_KERNEL);
if (!new_chunks)
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
goto err_release;
mdevice->devmem_capacity = new_capacity;
mdevice->devmem_chunks = new_chunks;
}
ptr = memremap_pages(&devmem->pagemap, numa_node_id());
if (IS_ERR_OR_NULL(ptr)) {
if (ptr)
ret = PTR_ERR(ptr);
else
ret = -EFAULT;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
goto err_release;
}
devmem->mdevice = mdevice;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
pfn_first = devmem->pagemap.range.start >> PAGE_SHIFT;
pfn_last = pfn_first + (range_len(&devmem->pagemap.range) >> PAGE_SHIFT);
mdevice->devmem_chunks[mdevice->devmem_count++] = devmem;
mutex_unlock(&mdevice->devmem_lock);
pr_info("added new %u MB chunk (total %u chunks, %u MB) PFNs [0x%lx 0x%lx)\n",
DEVMEM_CHUNK_SIZE / (1024 * 1024),
mdevice->devmem_count,
mdevice->devmem_count * (DEVMEM_CHUNK_SIZE / (1024 * 1024)),
pfn_first, pfn_last);
spin_lock(&mdevice->lock);
for (pfn = pfn_first; pfn < pfn_last; pfn++) {
struct page *page = pfn_to_page(pfn);
page->zone_device_data = mdevice->free_pages;
mdevice->free_pages = page;
}
if (ppage) {
*ppage = mdevice->free_pages;
mdevice->free_pages = (*ppage)->zone_device_data;
mdevice->calloc++;
}
spin_unlock(&mdevice->lock);
return 0;
err_release:
mutex_unlock(&mdevice->devmem_lock);
if (res && devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
release_mem_region(devmem->pagemap.range.start,
range_len(&devmem->pagemap.range));
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> 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: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
err_devmem:
kfree(devmem);
return ret;
}
static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
{
struct page *dpage = NULL;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
struct page *rpage = NULL;
/*
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
* For ZONE_DEVICE private type, this is a fake device so we allocate
* real system memory to store our device memory.
* For ZONE_DEVICE coherent type we use the actual dpage to store the
* data and ignore rpage.
*/
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
if (dmirror_is_private_zone(mdevice)) {
rpage = alloc_page(GFP_HIGHUSER);
if (!rpage)
return NULL;
}
spin_lock(&mdevice->lock);
if (mdevice->free_pages) {
dpage = mdevice->free_pages;
mdevice->free_pages = dpage->zone_device_data;
mdevice->calloc++;
spin_unlock(&mdevice->lock);
} else {
spin_unlock(&mdevice->lock);
if (dmirror_allocate_chunk(mdevice, &dpage))
goto error;
}
mm: free device private pages have zero refcount Since 27674ef6c73f ("mm: remove the extra ZONE_DEVICE struct page refcount") device private pages have no longer had an extra reference count when the page is in use. However before handing them back to the owning device driver we add an extra reference count such that free pages have a reference count of one. This makes it difficult to tell if a page is free or not because both free and in use pages will have a non-zero refcount. Instead we should return pages to the drivers page allocator with a zero reference count. Kernel code can then safely use kernel functions such as get_page_unless_zero(). Link: https://lkml.kernel.org/r/cf70cf6f8c0bdb8aaebdbfb0d790aea4c683c3c6.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Lyude Paul <lyude@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-28 20:01:16 +08:00
zone_device_page_init(dpage);
dpage->zone_device_data = rpage;
return dpage;
error:
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
if (rpage)
__free_page(rpage);
return NULL;
}
static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
struct dmirror *dmirror)
{
struct dmirror_device *mdevice = dmirror->mdevice;
const unsigned long *src = args->src;
unsigned long *dst = args->dst;
unsigned long addr;
for (addr = args->start; addr < args->end; addr += PAGE_SIZE,
src++, dst++) {
struct page *spage;
struct page *dpage;
struct page *rpage;
if (!(*src & MIGRATE_PFN_MIGRATE))
continue;
/*
* Note that spage might be NULL which is OK since it is an
* unallocated pte_none() or read-only zero page.
*/
spage = migrate_pfn_to_page(*src);
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
if (WARN(spage && is_zone_device_page(spage),
"page already in device spage pfn: 0x%lx\n",
page_to_pfn(spage)))
continue;
dpage = dmirror_devmem_alloc_page(mdevice);
if (!dpage)
continue;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
rpage = BACKING_PAGE(dpage);
if (spage)
copy_highpage(rpage, spage);
else
clear_highpage(rpage);
/*
* Normally, a device would use the page->zone_device_data to
* point to the mirror but here we use it to hold the page for
* the simulated device memory and that page holds the pointer
* to the mirror.
*/
rpage->zone_device_data = dmirror;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
pr_debug("migrating from sys to dev pfn src: 0x%lx pfn dst: 0x%lx\n",
page_to_pfn(spage), page_to_pfn(dpage));
*dst = migrate_pfn(page_to_pfn(dpage));
if ((*src & MIGRATE_PFN_WRITE) ||
(!spage && args->vma->vm_flags & VM_WRITE))
*dst |= MIGRATE_PFN_WRITE;
}
}
static int dmirror_check_atomic(struct dmirror *dmirror, unsigned long start,
unsigned long end)
{
unsigned long pfn;
for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
void *entry;
entry = xa_load(&dmirror->pt, pfn);
if (xa_pointer_tag(entry) == DPT_XA_TAG_ATOMIC)
return -EPERM;
}
return 0;
}
static int dmirror_atomic_map(unsigned long start, unsigned long end,
struct page **pages, struct dmirror *dmirror)
{
unsigned long pfn, mapped = 0;
int i;
/* Map the migrated pages into the device's page tables. */
mutex_lock(&dmirror->mutex);
for (i = 0, pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++, i++) {
void *entry;
if (!pages[i])
continue;
entry = pages[i];
entry = xa_tag_pointer(entry, DPT_XA_TAG_ATOMIC);
entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
if (xa_is_err(entry)) {
mutex_unlock(&dmirror->mutex);
return xa_err(entry);
}
mapped++;
}
mutex_unlock(&dmirror->mutex);
return mapped;
}
static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
struct dmirror *dmirror)
{
unsigned long start = args->start;
unsigned long end = args->end;
const unsigned long *src = args->src;
const unsigned long *dst = args->dst;
unsigned long pfn;
/* Map the migrated pages into the device's page tables. */
mutex_lock(&dmirror->mutex);
for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++,
src++, dst++) {
struct page *dpage;
void *entry;
if (!(*src & MIGRATE_PFN_MIGRATE))
continue;
dpage = migrate_pfn_to_page(*dst);
if (!dpage)
continue;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
entry = BACKING_PAGE(dpage);
if (*dst & MIGRATE_PFN_WRITE)
entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
if (xa_is_err(entry)) {
mutex_unlock(&dmirror->mutex);
return xa_err(entry);
}
}
mutex_unlock(&dmirror->mutex);
return 0;
}
static int dmirror_exclusive(struct dmirror *dmirror,
struct hmm_dmirror_cmd *cmd)
{
unsigned long start, end, addr;
unsigned long size = cmd->npages << PAGE_SHIFT;
struct mm_struct *mm = dmirror->notifier.mm;
struct page *pages[64];
struct dmirror_bounce bounce;
unsigned long next;
int ret;
start = cmd->addr;
end = start + size;
if (end < start)
return -EINVAL;
/* Since the mm is for the mirrored process, get a reference first. */
if (!mmget_not_zero(mm))
return -EINVAL;
mmap_read_lock(mm);
for (addr = start; addr < end; addr = next) {
unsigned long mapped = 0;
int i;
if (end < addr + (ARRAY_SIZE(pages) << PAGE_SHIFT))
next = end;
else
next = addr + (ARRAY_SIZE(pages) << PAGE_SHIFT);
ret = make_device_exclusive_range(mm, addr, next, pages, NULL);
/*
* Do dmirror_atomic_map() iff all pages are marked for
* exclusive access to avoid accessing uninitialized
* fields of pages.
*/
if (ret == (next - addr) >> PAGE_SHIFT)
mapped = dmirror_atomic_map(addr, next, pages, dmirror);
for (i = 0; i < ret; i++) {
if (pages[i]) {
unlock_page(pages[i]);
put_page(pages[i]);
}
}
if (addr + (mapped << PAGE_SHIFT) < next) {
mmap_read_unlock(mm);
mmput(mm);
return -EBUSY;
}
}
mmap_read_unlock(mm);
mmput(mm);
/* Return the migrated data for verification. */
ret = dmirror_bounce_init(&bounce, start, size);
if (ret)
return ret;
mutex_lock(&dmirror->mutex);
ret = dmirror_do_read(dmirror, start, end, &bounce);
mutex_unlock(&dmirror->mutex);
if (ret == 0) {
if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
bounce.size))
ret = -EFAULT;
}
cmd->cpages = bounce.cpages;
dmirror_bounce_fini(&bounce);
return ret;
}
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
struct dmirror *dmirror)
{
const unsigned long *src = args->src;
unsigned long *dst = args->dst;
unsigned long start = args->start;
unsigned long end = args->end;
unsigned long addr;
for (addr = start; addr < end; addr += PAGE_SIZE,
src++, dst++) {
struct page *dpage, *spage;
spage = migrate_pfn_to_page(*src);
if (!spage || !(*src & MIGRATE_PFN_MIGRATE))
continue;
if (WARN_ON(!is_device_private_page(spage) &&
!is_device_coherent_page(spage)))
continue;
spage = BACKING_PAGE(spage);
dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
if (!dpage)
continue;
pr_debug("migrating from dev to sys pfn src: 0x%lx pfn dst: 0x%lx\n",
page_to_pfn(spage), page_to_pfn(dpage));
lock_page(dpage);
xa_erase(&dmirror->pt, addr >> PAGE_SHIFT);
copy_highpage(dpage, spage);
*dst = migrate_pfn(page_to_pfn(dpage));
if (*src & MIGRATE_PFN_WRITE)
*dst |= MIGRATE_PFN_WRITE;
}
return 0;
}
static unsigned long
dmirror_successful_migrated_pages(struct migrate_vma *migrate)
{
unsigned long cpages = 0;
unsigned long i;
for (i = 0; i < migrate->npages; i++) {
if (migrate->src[i] & MIGRATE_PFN_VALID &&
migrate->src[i] & MIGRATE_PFN_MIGRATE)
cpages++;
}
return cpages;
}
static int dmirror_migrate_to_system(struct dmirror *dmirror,
struct hmm_dmirror_cmd *cmd)
{
unsigned long start, end, addr;
unsigned long size = cmd->npages << PAGE_SHIFT;
struct mm_struct *mm = dmirror->notifier.mm;
struct vm_area_struct *vma;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
unsigned long src_pfns[64] = { 0 };
unsigned long dst_pfns[64] = { 0 };
mm/memory.c: fix race when faulting a device private page Patch series "Fix several device private page reference counting issues", v2 This series aims to fix a number of page reference counting issues in drivers dealing with device private ZONE_DEVICE pages. These result in use-after-free type bugs, either from accessing a struct page which no longer exists because it has been removed or accessing fields within the struct page which are no longer valid because the page has been freed. During normal usage it is unlikely these will cause any problems. However without these fixes it is possible to crash the kernel from userspace. These crashes can be triggered either by unloading the kernel module or unbinding the device from the driver prior to a userspace task exiting. In modules such as Nouveau it is also possible to trigger some of these issues by explicitly closing the device file-descriptor prior to the task exiting and then accessing device private memory. This involves some minor changes to both PowerPC and AMD GPU code. Unfortunately I lack hardware to test either of those so any help there would be appreciated. The changes mimic what is done in for both Nouveau and hmm-tests though so I doubt they will cause problems. This patch (of 8): When the CPU tries to access a device private page the migrate_to_ram() callback associated with the pgmap for the page is called. However no reference is taken on the faulting page. Therefore a concurrent migration of the device private page can free the page and possibly the underlying pgmap. This results in a race which can crash the kernel due to the migrate_to_ram() function pointer becoming invalid. It also means drivers can't reliably read the zone_device_data field because the page may have been freed with memunmap_pages(). Close the race by getting a reference on the page while holding the ptl to ensure it has not been freed. Unfortunately the elevated reference count will cause the migration required to handle the fault to fail. To avoid this failure pass the faulting page into the migrate_vma functions so that if an elevated reference count is found it can be checked to see if it's expected or not. [mpe@ellerman.id.au: fix build] Link: https://lkml.kernel.org/r/87fsgbf3gh.fsf@mpe.ellerman.id.au Link: https://lkml.kernel.org/r/cover.60659b549d8509ddecafad4f498ee7f03bb23c69.1664366292.git-series.apopple@nvidia.com Link: https://lkml.kernel.org/r/d3e813178a59e565e8d78d9b9a4e2562f6494f90.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Lyude Paul <lyude@redhat.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Christian König <christian.koenig@amd.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-28 20:01:15 +08:00
struct migrate_vma args = { 0 };
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
unsigned long next;
int ret;
start = cmd->addr;
end = start + size;
if (end < start)
return -EINVAL;
/* Since the mm is for the mirrored process, get a reference first. */
if (!mmget_not_zero(mm))
return -EINVAL;
cmd->cpages = 0;
mmap_read_lock(mm);
for (addr = start; addr < end; addr = next) {
vma = vma_lookup(mm, addr);
if (!vma || !(vma->vm_flags & VM_READ)) {
ret = -EINVAL;
goto out;
}
next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT));
if (next > vma->vm_end)
next = vma->vm_end;
args.vma = vma;
args.src = src_pfns;
args.dst = dst_pfns;
args.start = addr;
args.end = next;
args.pgmap_owner = dmirror->mdevice;
args.flags = dmirror_select_device(dmirror);
ret = migrate_vma_setup(&args);
if (ret)
goto out;
pr_debug("Migrating from device mem to sys mem\n");
dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
migrate_vma_pages(&args);
cmd->cpages += dmirror_successful_migrated_pages(&args);
migrate_vma_finalize(&args);
}
out:
mmap_read_unlock(mm);
mmput(mm);
return ret;
}
static int dmirror_migrate_to_device(struct dmirror *dmirror,
struct hmm_dmirror_cmd *cmd)
{
unsigned long start, end, addr;
unsigned long size = cmd->npages << PAGE_SHIFT;
struct mm_struct *mm = dmirror->notifier.mm;
struct vm_area_struct *vma;
unsigned long src_pfns[64] = { 0 };
unsigned long dst_pfns[64] = { 0 };
struct dmirror_bounce bounce;
mm/memory.c: fix race when faulting a device private page Patch series "Fix several device private page reference counting issues", v2 This series aims to fix a number of page reference counting issues in drivers dealing with device private ZONE_DEVICE pages. These result in use-after-free type bugs, either from accessing a struct page which no longer exists because it has been removed or accessing fields within the struct page which are no longer valid because the page has been freed. During normal usage it is unlikely these will cause any problems. However without these fixes it is possible to crash the kernel from userspace. These crashes can be triggered either by unloading the kernel module or unbinding the device from the driver prior to a userspace task exiting. In modules such as Nouveau it is also possible to trigger some of these issues by explicitly closing the device file-descriptor prior to the task exiting and then accessing device private memory. This involves some minor changes to both PowerPC and AMD GPU code. Unfortunately I lack hardware to test either of those so any help there would be appreciated. The changes mimic what is done in for both Nouveau and hmm-tests though so I doubt they will cause problems. This patch (of 8): When the CPU tries to access a device private page the migrate_to_ram() callback associated with the pgmap for the page is called. However no reference is taken on the faulting page. Therefore a concurrent migration of the device private page can free the page and possibly the underlying pgmap. This results in a race which can crash the kernel due to the migrate_to_ram() function pointer becoming invalid. It also means drivers can't reliably read the zone_device_data field because the page may have been freed with memunmap_pages(). Close the race by getting a reference on the page while holding the ptl to ensure it has not been freed. Unfortunately the elevated reference count will cause the migration required to handle the fault to fail. To avoid this failure pass the faulting page into the migrate_vma functions so that if an elevated reference count is found it can be checked to see if it's expected or not. [mpe@ellerman.id.au: fix build] Link: https://lkml.kernel.org/r/87fsgbf3gh.fsf@mpe.ellerman.id.au Link: https://lkml.kernel.org/r/cover.60659b549d8509ddecafad4f498ee7f03bb23c69.1664366292.git-series.apopple@nvidia.com Link: https://lkml.kernel.org/r/d3e813178a59e565e8d78d9b9a4e2562f6494f90.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Lyude Paul <lyude@redhat.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Christian König <christian.koenig@amd.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-28 20:01:15 +08:00
struct migrate_vma args = { 0 };
unsigned long next;
int ret;
start = cmd->addr;
end = start + size;
if (end < start)
return -EINVAL;
/* Since the mm is for the mirrored process, get a reference first. */
if (!mmget_not_zero(mm))
return -EINVAL;
mmap_read_lock(mm);
for (addr = start; addr < end; addr = next) {
vma = vma_lookup(mm, addr);
if (!vma || !(vma->vm_flags & VM_READ)) {
ret = -EINVAL;
goto out;
}
next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT));
if (next > vma->vm_end)
next = vma->vm_end;
args.vma = vma;
args.src = src_pfns;
args.dst = dst_pfns;
args.start = addr;
args.end = next;
args.pgmap_owner = dmirror->mdevice;
args.flags = MIGRATE_VMA_SELECT_SYSTEM;
ret = migrate_vma_setup(&args);
if (ret)
goto out;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
pr_debug("Migrating from sys mem to device mem\n");
dmirror_migrate_alloc_and_copy(&args, dmirror);
migrate_vma_pages(&args);
dmirror_migrate_finalize_and_map(&args, dmirror);
migrate_vma_finalize(&args);
}
mmap_read_unlock(mm);
mmput(mm);
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
/*
* Return the migrated data for verification.
* Only for pages in device zone
*/
ret = dmirror_bounce_init(&bounce, start, size);
if (ret)
return ret;
mutex_lock(&dmirror->mutex);
ret = dmirror_do_read(dmirror, start, end, &bounce);
mutex_unlock(&dmirror->mutex);
if (ret == 0) {
if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
bounce.size))
ret = -EFAULT;
}
cmd->cpages = bounce.cpages;
dmirror_bounce_fini(&bounce);
return ret;
out:
mmap_read_unlock(mm);
mmput(mm);
return ret;
}
static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
unsigned char *perm, unsigned long entry)
{
struct page *page;
if (entry & HMM_PFN_ERROR) {
*perm = HMM_DMIRROR_PROT_ERROR;
return;
}
if (!(entry & HMM_PFN_VALID)) {
*perm = HMM_DMIRROR_PROT_NONE;
return;
}
page = hmm_pfn_to_page(entry);
if (is_device_private_page(page)) {
/* Is the page migrated to this device or some other? */
if (dmirror->mdevice == dmirror_page_to_device(page))
*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL;
else
*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
} else if (is_device_coherent_page(page)) {
/* Is the page migrated to this device or some other? */
if (dmirror->mdevice == dmirror_page_to_device(page))
*perm = HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL;
else
*perm = HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE;
} else if (is_zero_pfn(page_to_pfn(page)))
*perm = HMM_DMIRROR_PROT_ZERO;
else
*perm = HMM_DMIRROR_PROT_NONE;
if (entry & HMM_PFN_WRITE)
*perm |= HMM_DMIRROR_PROT_WRITE;
else
*perm |= HMM_DMIRROR_PROT_READ;
if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PMD_SHIFT)
*perm |= HMM_DMIRROR_PROT_PMD;
else if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PUD_SHIFT)
*perm |= HMM_DMIRROR_PROT_PUD;
}
static bool dmirror_snapshot_invalidate(struct mmu_interval_notifier *mni,
const struct mmu_notifier_range *range,
unsigned long cur_seq)
{
struct dmirror_interval *dmi =
container_of(mni, struct dmirror_interval, notifier);
struct dmirror *dmirror = dmi->dmirror;
if (mmu_notifier_range_blockable(range))
mutex_lock(&dmirror->mutex);
else if (!mutex_trylock(&dmirror->mutex))
return false;
/*
* Snapshots only need to set the sequence number since any
* invalidation in the interval invalidates the whole snapshot.
*/
mmu_interval_set_seq(mni, cur_seq);
mutex_unlock(&dmirror->mutex);
return true;
}
static const struct mmu_interval_notifier_ops dmirror_mrn_ops = {
.invalidate = dmirror_snapshot_invalidate,
};
static int dmirror_range_snapshot(struct dmirror *dmirror,
struct hmm_range *range,
unsigned char *perm)
{
struct mm_struct *mm = dmirror->notifier.mm;
struct dmirror_interval notifier;
unsigned long timeout =
jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
unsigned long i;
unsigned long n;
int ret = 0;
notifier.dmirror = dmirror;
range->notifier = &notifier.notifier;
ret = mmu_interval_notifier_insert(range->notifier, mm,
range->start, range->end - range->start,
&dmirror_mrn_ops);
if (ret)
return ret;
while (true) {
if (time_after(jiffies, timeout)) {
ret = -EBUSY;
goto out;
}
range->notifier_seq = mmu_interval_read_begin(range->notifier);
mmap_read_lock(mm);
ret = hmm_range_fault(range);
mmap_read_unlock(mm);
if (ret) {
if (ret == -EBUSY)
continue;
goto out;
}
mutex_lock(&dmirror->mutex);
if (mmu_interval_read_retry(range->notifier,
range->notifier_seq)) {
mutex_unlock(&dmirror->mutex);
continue;
}
break;
}
n = (range->end - range->start) >> PAGE_SHIFT;
for (i = 0; i < n; i++)
dmirror_mkentry(dmirror, range, perm + i, range->hmm_pfns[i]);
mutex_unlock(&dmirror->mutex);
out:
mmu_interval_notifier_remove(range->notifier);
return ret;
}
static int dmirror_snapshot(struct dmirror *dmirror,
struct hmm_dmirror_cmd *cmd)
{
struct mm_struct *mm = dmirror->notifier.mm;
unsigned long start, end;
unsigned long size = cmd->npages << PAGE_SHIFT;
unsigned long addr;
unsigned long next;
unsigned long pfns[64];
unsigned char perm[64];
char __user *uptr;
struct hmm_range range = {
.hmm_pfns = pfns,
.dev_private_owner = dmirror->mdevice,
};
int ret = 0;
start = cmd->addr;
end = start + size;
if (end < start)
return -EINVAL;
/* Since the mm is for the mirrored process, get a reference first. */
if (!mmget_not_zero(mm))
return -EINVAL;
/*
* Register a temporary notifier to detect invalidations even if it
* overlaps with other mmu_interval_notifiers.
*/
uptr = u64_to_user_ptr(cmd->ptr);
for (addr = start; addr < end; addr = next) {
unsigned long n;
next = min(addr + (ARRAY_SIZE(pfns) << PAGE_SHIFT), end);
range.start = addr;
range.end = next;
ret = dmirror_range_snapshot(dmirror, &range, perm);
if (ret)
break;
n = (range.end - range.start) >> PAGE_SHIFT;
if (copy_to_user(uptr, perm, n)) {
ret = -EFAULT;
break;
}
cmd->cpages += n;
uptr += n;
}
mmput(mm);
return ret;
}
static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk)
{
unsigned long start_pfn = chunk->pagemap.range.start >> PAGE_SHIFT;
unsigned long end_pfn = chunk->pagemap.range.end >> PAGE_SHIFT;
unsigned long npages = end_pfn - start_pfn + 1;
unsigned long i;
unsigned long *src_pfns;
unsigned long *dst_pfns;
src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
migrate_device_range(src_pfns, start_pfn, npages);
for (i = 0; i < npages; i++) {
struct page *dpage, *spage;
spage = migrate_pfn_to_page(src_pfns[i]);
if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE))
continue;
if (WARN_ON(!is_device_private_page(spage) &&
!is_device_coherent_page(spage)))
continue;
spage = BACKING_PAGE(spage);
dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL);
lock_page(dpage);
copy_highpage(dpage, spage);
dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));
if (src_pfns[i] & MIGRATE_PFN_WRITE)
dst_pfns[i] |= MIGRATE_PFN_WRITE;
}
migrate_device_pages(src_pfns, dst_pfns, npages);
migrate_device_finalize(src_pfns, dst_pfns, npages);
kfree(src_pfns);
kfree(dst_pfns);
}
/* Removes free pages from the free list so they can't be re-allocated */
static void dmirror_remove_free_pages(struct dmirror_chunk *devmem)
{
struct dmirror_device *mdevice = devmem->mdevice;
struct page *page;
for (page = mdevice->free_pages; page; page = page->zone_device_data)
if (dmirror_page_to_chunk(page) == devmem)
mdevice->free_pages = page->zone_device_data;
}
static void dmirror_device_remove_chunks(struct dmirror_device *mdevice)
{
unsigned int i;
mutex_lock(&mdevice->devmem_lock);
if (mdevice->devmem_chunks) {
for (i = 0; i < mdevice->devmem_count; i++) {
struct dmirror_chunk *devmem =
mdevice->devmem_chunks[i];
spin_lock(&mdevice->lock);
devmem->remove = true;
dmirror_remove_free_pages(devmem);
spin_unlock(&mdevice->lock);
dmirror_device_evict_chunk(devmem);
memunmap_pages(&devmem->pagemap);
if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
release_mem_region(devmem->pagemap.range.start,
range_len(&devmem->pagemap.range));
kfree(devmem);
}
mdevice->devmem_count = 0;
mdevice->devmem_capacity = 0;
mdevice->free_pages = NULL;
kfree(mdevice->devmem_chunks);
mdevice->devmem_chunks = NULL;
}
mutex_unlock(&mdevice->devmem_lock);
}
static long dmirror_fops_unlocked_ioctl(struct file *filp,
unsigned int command,
unsigned long arg)
{
void __user *uarg = (void __user *)arg;
struct hmm_dmirror_cmd cmd;
struct dmirror *dmirror;
int ret;
dmirror = filp->private_data;
if (!dmirror)
return -EINVAL;
if (copy_from_user(&cmd, uarg, sizeof(cmd)))
return -EFAULT;
if (cmd.addr & ~PAGE_MASK)
return -EINVAL;
if (cmd.addr >= (cmd.addr + (cmd.npages << PAGE_SHIFT)))
return -EINVAL;
cmd.cpages = 0;
cmd.faults = 0;
switch (command) {
case HMM_DMIRROR_READ:
ret = dmirror_read(dmirror, &cmd);
break;
case HMM_DMIRROR_WRITE:
ret = dmirror_write(dmirror, &cmd);
break;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
case HMM_DMIRROR_MIGRATE_TO_DEV:
ret = dmirror_migrate_to_device(dmirror, &cmd);
break;
case HMM_DMIRROR_MIGRATE_TO_SYS:
ret = dmirror_migrate_to_system(dmirror, &cmd);
break;
case HMM_DMIRROR_EXCLUSIVE:
ret = dmirror_exclusive(dmirror, &cmd);
break;
case HMM_DMIRROR_CHECK_EXCLUSIVE:
ret = dmirror_check_atomic(dmirror, cmd.addr,
cmd.addr + (cmd.npages << PAGE_SHIFT));
break;
case HMM_DMIRROR_SNAPSHOT:
ret = dmirror_snapshot(dmirror, &cmd);
break;
case HMM_DMIRROR_RELEASE:
dmirror_device_remove_chunks(dmirror->mdevice);
ret = 0;
break;
default:
return -EINVAL;
}
if (ret)
return ret;
if (copy_to_user(uarg, &cmd, sizeof(cmd)))
return -EFAULT;
return 0;
}
static int dmirror_fops_mmap(struct file *file, struct vm_area_struct *vma)
{
unsigned long addr;
for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
struct page *page;
int ret;
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!page)
return -ENOMEM;
ret = vm_insert_page(vma, addr, page);
if (ret) {
__free_page(page);
return ret;
}
put_page(page);
}
return 0;
}
static const struct file_operations dmirror_fops = {
.open = dmirror_fops_open,
.release = dmirror_fops_release,
.mmap = dmirror_fops_mmap,
.unlocked_ioctl = dmirror_fops_unlocked_ioctl,
.llseek = default_llseek,
.owner = THIS_MODULE,
};
static void dmirror_devmem_free(struct page *page)
{
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
struct page *rpage = BACKING_PAGE(page);
struct dmirror_device *mdevice;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
if (rpage != page)
__free_page(rpage);
mdevice = dmirror_page_to_device(page);
spin_lock(&mdevice->lock);
/* Return page to our allocator if not freeing the chunk */
if (!dmirror_page_to_chunk(page)->remove) {
mdevice->cfree++;
page->zone_device_data = mdevice->free_pages;
mdevice->free_pages = page;
}
spin_unlock(&mdevice->lock);
}
static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
{
mm/memory.c: fix race when faulting a device private page Patch series "Fix several device private page reference counting issues", v2 This series aims to fix a number of page reference counting issues in drivers dealing with device private ZONE_DEVICE pages. These result in use-after-free type bugs, either from accessing a struct page which no longer exists because it has been removed or accessing fields within the struct page which are no longer valid because the page has been freed. During normal usage it is unlikely these will cause any problems. However without these fixes it is possible to crash the kernel from userspace. These crashes can be triggered either by unloading the kernel module or unbinding the device from the driver prior to a userspace task exiting. In modules such as Nouveau it is also possible to trigger some of these issues by explicitly closing the device file-descriptor prior to the task exiting and then accessing device private memory. This involves some minor changes to both PowerPC and AMD GPU code. Unfortunately I lack hardware to test either of those so any help there would be appreciated. The changes mimic what is done in for both Nouveau and hmm-tests though so I doubt they will cause problems. This patch (of 8): When the CPU tries to access a device private page the migrate_to_ram() callback associated with the pgmap for the page is called. However no reference is taken on the faulting page. Therefore a concurrent migration of the device private page can free the page and possibly the underlying pgmap. This results in a race which can crash the kernel due to the migrate_to_ram() function pointer becoming invalid. It also means drivers can't reliably read the zone_device_data field because the page may have been freed with memunmap_pages(). Close the race by getting a reference on the page while holding the ptl to ensure it has not been freed. Unfortunately the elevated reference count will cause the migration required to handle the fault to fail. To avoid this failure pass the faulting page into the migrate_vma functions so that if an elevated reference count is found it can be checked to see if it's expected or not. [mpe@ellerman.id.au: fix build] Link: https://lkml.kernel.org/r/87fsgbf3gh.fsf@mpe.ellerman.id.au Link: https://lkml.kernel.org/r/cover.60659b549d8509ddecafad4f498ee7f03bb23c69.1664366292.git-series.apopple@nvidia.com Link: https://lkml.kernel.org/r/d3e813178a59e565e8d78d9b9a4e2562f6494f90.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Lyude Paul <lyude@redhat.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Christian König <christian.koenig@amd.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-28 20:01:15 +08:00
struct migrate_vma args = { 0 };
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
unsigned long src_pfns = 0;
unsigned long dst_pfns = 0;
struct page *rpage;
struct dmirror *dmirror;
vm_fault_t ret;
/*
* Normally, a device would use the page->zone_device_data to point to
* the mirror but here we use it to hold the page for the simulated
* device memory and that page holds the pointer to the mirror.
*/
rpage = vmf->page->zone_device_data;
dmirror = rpage->zone_device_data;
/* FIXME demonstrate how we can adjust migrate range */
args.vma = vmf->vma;
args.start = vmf->address;
args.end = args.start + PAGE_SIZE;
args.src = &src_pfns;
args.dst = &dst_pfns;
args.pgmap_owner = dmirror->mdevice;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
args.flags = dmirror_select_device(dmirror);
mm/memory.c: fix race when faulting a device private page Patch series "Fix several device private page reference counting issues", v2 This series aims to fix a number of page reference counting issues in drivers dealing with device private ZONE_DEVICE pages. These result in use-after-free type bugs, either from accessing a struct page which no longer exists because it has been removed or accessing fields within the struct page which are no longer valid because the page has been freed. During normal usage it is unlikely these will cause any problems. However without these fixes it is possible to crash the kernel from userspace. These crashes can be triggered either by unloading the kernel module or unbinding the device from the driver prior to a userspace task exiting. In modules such as Nouveau it is also possible to trigger some of these issues by explicitly closing the device file-descriptor prior to the task exiting and then accessing device private memory. This involves some minor changes to both PowerPC and AMD GPU code. Unfortunately I lack hardware to test either of those so any help there would be appreciated. The changes mimic what is done in for both Nouveau and hmm-tests though so I doubt they will cause problems. This patch (of 8): When the CPU tries to access a device private page the migrate_to_ram() callback associated with the pgmap for the page is called. However no reference is taken on the faulting page. Therefore a concurrent migration of the device private page can free the page and possibly the underlying pgmap. This results in a race which can crash the kernel due to the migrate_to_ram() function pointer becoming invalid. It also means drivers can't reliably read the zone_device_data field because the page may have been freed with memunmap_pages(). Close the race by getting a reference on the page while holding the ptl to ensure it has not been freed. Unfortunately the elevated reference count will cause the migration required to handle the fault to fail. To avoid this failure pass the faulting page into the migrate_vma functions so that if an elevated reference count is found it can be checked to see if it's expected or not. [mpe@ellerman.id.au: fix build] Link: https://lkml.kernel.org/r/87fsgbf3gh.fsf@mpe.ellerman.id.au Link: https://lkml.kernel.org/r/cover.60659b549d8509ddecafad4f498ee7f03bb23c69.1664366292.git-series.apopple@nvidia.com Link: https://lkml.kernel.org/r/d3e813178a59e565e8d78d9b9a4e2562f6494f90.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Lyude Paul <lyude@redhat.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Christian König <christian.koenig@amd.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-28 20:01:15 +08:00
args.fault_page = vmf->page;
if (migrate_vma_setup(&args))
return VM_FAULT_SIGBUS;
ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
if (ret)
return ret;
migrate_vma_pages(&args);
/*
* No device finalize step is needed since
* dmirror_devmem_fault_alloc_and_copy() will have already
* invalidated the device page table.
*/
migrate_vma_finalize(&args);
return 0;
}
static const struct dev_pagemap_ops dmirror_devmem_ops = {
.page_free = dmirror_devmem_free,
.migrate_to_ram = dmirror_devmem_fault,
};
static int dmirror_device_init(struct dmirror_device *mdevice, int id)
{
dev_t dev;
int ret;
dev = MKDEV(MAJOR(dmirror_dev), id);
mutex_init(&mdevice->devmem_lock);
spin_lock_init(&mdevice->lock);
cdev_init(&mdevice->cdevice, &dmirror_fops);
mdevice->cdevice.owner = THIS_MODULE;
device_initialize(&mdevice->device);
mdevice->device.devt = dev;
ret = dev_set_name(&mdevice->device, "hmm_dmirror%u", id);
if (ret)
return ret;
ret = cdev_device_add(&mdevice->cdevice, &mdevice->device);
if (ret)
return ret;
/* Build a list of free ZONE_DEVICE struct pages */
return dmirror_allocate_chunk(mdevice, NULL);
}
static void dmirror_device_remove(struct dmirror_device *mdevice)
{
dmirror_device_remove_chunks(mdevice);
cdev_device_del(&mdevice->cdevice, &mdevice->device);
}
static int __init hmm_dmirror_init(void)
{
int ret;
int id = 0;
int ndevices = 0;
ret = alloc_chrdev_region(&dmirror_dev, 0, DMIRROR_NDEVICES,
"HMM_DMIRROR");
if (ret)
goto err_unreg;
memset(dmirror_devices, 0, DMIRROR_NDEVICES * sizeof(dmirror_devices[0]));
dmirror_devices[ndevices++].zone_device_type =
HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
dmirror_devices[ndevices++].zone_device_type =
HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
if (spm_addr_dev0 && spm_addr_dev1) {
dmirror_devices[ndevices++].zone_device_type =
HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
dmirror_devices[ndevices++].zone_device_type =
HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
}
for (id = 0; id < ndevices; id++) {
ret = dmirror_device_init(dmirror_devices + id, id);
if (ret)
goto err_chrdev;
}
pr_info("HMM test module loaded. This is only for testing HMM.\n");
return 0;
err_chrdev:
while (--id >= 0)
dmirror_device_remove(dmirror_devices + id);
unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
err_unreg:
return ret;
}
static void __exit hmm_dmirror_exit(void)
{
int id;
for (id = 0; id < DMIRROR_NDEVICES; id++)
lib: add support for device coherent type in test_hmm Device Coherent type uses device memory that is coherently accesible by the CPU. This could be shown as SP (special purpose) memory range at the BIOS-e820 memory enumeration. If no SP memory is supported in system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP. Currently, test_hmm only supports two different SP ranges of at least 256MB size. This could be specified in the kernel parameter variable efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 & 0x140000000 physical address. Ex. efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000 Private and coherent device mirror instances can be created in the same probed. This is done by passing the module parameters spm_addr_dev0 & spm_addr_dev1. In this case, it will create four instances of device_mirror. The first two correspond to private device type, the last two to coherent type. Then, they can be easily accessed from user space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1 are for private, and 2 and 3 for coherent types. If no module parameters are passed, two instances of private type device_mirror will be created only. Link: https://lkml.kernel.org/r/20220715150521.18165-11-alex.sierra@amd.com Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alistair Poppple <apopple@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-15 23:05:17 +08:00
if (dmirror_devices[id].zone_device_type)
dmirror_device_remove(dmirror_devices + id);
unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
}
module_init(hmm_dmirror_init);
module_exit(hmm_dmirror_exit);
MODULE_LICENSE("GPL");