With DEVICE_COHERENT, we'll soon have vm_normal_pages() return device-managed anonymous pages that are not LRU pages. Although they behave like normal pages for purposes of mapping in CPU page, and for COW. They do not support LRU lists, NUMA migration or THP.

We also introduced a FOLL_LRU flag that adds the same behaviour to follow_page and related APIs, to allow callers to specify that they expect to put pages on an LRU list.

Signed-off-by: Alex Sierra alex.sierra@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com --- fs/proc/task_mmu.c | 2 +- include/linux/mm.h | 3 ++- mm/gup.c | 2 ++ mm/huge_memory.c | 2 +- mm/khugepaged.c | 9 ++++++--- mm/ksm.c | 6 +++--- mm/madvise.c | 4 ++-- mm/memory.c | 9 ++++++++- mm/mempolicy.c | 2 +- mm/migrate.c | 4 ++-- mm/mlock.c | 2 +- mm/mprotect.c | 2 +- 12 files changed, 30 insertions(+), 17 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f46060eb91b5..5d620733f173 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1785,7 +1785,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return NULL;

page = vm_normal_page(vma, addr, pte); - if (!page) + if (!page || is_zone_device_page(page)) return NULL;

if (PageReserved(page)) diff --git a/include/linux/mm.h b/include/linux/mm.h index 9f44254af8ce..d7f253a0c41e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -601,7 +601,7 @@ struct vm_operations_struct { #endif /* * Called by vm_normal_page() for special PTEs to find the - * page for @addr. This is useful if the default behavior + * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, @@ -2929,6 +2929,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ +#define FOLL_LRU 0x1000 /* return only LRU (anon or page cache) */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ diff --git a/mm/gup.c b/mm/gup.c index 501bc150792c..c9cbac06bcc5 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -479,6 +479,8 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, }

page = vm_normal_page(vma, address, pte); + if ((flags & FOLL_LRU) && page && is_zone_device_page(page)) + page = NULL; if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 910a138e9859..eed80696c5fd 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2856,7 +2856,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, }

/* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); + page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP | FOLL_LRU);

if (IS_ERR(page)) continue; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a4e5eaf3eb01..8bf4126b6b9c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -627,7 +627,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } page = vm_normal_page(vma, address, pteval); - if (unlikely(!page)) { + if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } @@ -1276,7 +1276,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, writable = true;

page = vm_normal_page(vma, _address, pteval); - if (unlikely(!page)) { + if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } @@ -1484,7 +1484,8 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) goto abort;

page = vm_normal_page(vma, addr, *pte); - + if (WARN_ON_ONCE(page && is_zone_device_page(page))) + page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. @@ -1502,6 +1503,8 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) if (pte_none(*pte)) continue; page = vm_normal_page(vma, addr, *pte); + if (WARN_ON_ONCE(page && is_zone_device_page(page))) + goto abort; page_remove_rmap(page, vma, false); }

diff --git a/mm/ksm.c b/mm/ksm.c index 063a48eeb5ee..f16056efca21 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -474,7 +474,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) do { cond_resched(); page = follow_page(vma, addr, - FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE); + FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE | FOLL_LRU); if (IS_ERR_OR_NULL(page)) break; if (PageKsm(page)) @@ -559,7 +559,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item) if (!vma) goto out;

- page = follow_page(vma, addr, FOLL_GET); + page = follow_page(vma, addr, FOLL_GET | FOLL_LRU); if (IS_ERR_OR_NULL(page)) goto out; if (PageAnon(page)) { @@ -2288,7 +2288,7 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) while (ksm_scan.address < vma->vm_end) { if (ksm_test_exit(mm)) break; - *page = follow_page(vma, ksm_scan.address, FOLL_GET); + *page = follow_page(vma, ksm_scan.address, FOLL_GET | FOLL_LRU); if (IS_ERR_OR_NULL(*page)) { ksm_scan.address += PAGE_SIZE; cond_resched(); diff --git a/mm/madvise.c b/mm/madvise.c index 1873616a37d2..e9c24c834e98 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -413,7 +413,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, continue;

page = vm_normal_page(vma, addr, ptent); - if (!page) + if (!page || is_zone_device_page(page)) continue;

/* @@ -628,7 +628,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, }

page = vm_normal_page(vma, addr, ptent); - if (!page) + if (!page || is_zone_device_page(page)) continue;

/* diff --git a/mm/memory.c b/mm/memory.c index 76e3af9639d9..571a26805ee1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -621,6 +621,13 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) +/* + * NOTE: New uers of ZONE_DEVICE will not set pte_devmap() and will have + * refcounts incremented on their struct pages when they are inserted into + * PTEs, thus they are safe to return here. Legacy ZONE_DEVICE pages that set + * pte_devmap() do not have refcounts. Example of legacy ZONE_DEVICE is + * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers. + */ return NULL;

print_bad_pte(vma, addr, pte, NULL); @@ -4422,7 +4429,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) pte = pte_modify(old_pte, vma->vm_page_prot);

page = vm_normal_page(vma, vmf->address, pte); - if (!page) + if (!page || is_zone_device_page(page)) goto out_map;

/* TODO: handle PTE-mapped THP */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8c74107a2b15..e32edbecb0cd 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -528,7 +528,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); - if (!page) + if (!page || is_zone_device_page(page)) continue; /* * vm_normal_page() filters out zero pages, but there might diff --git a/mm/migrate.c b/mm/migrate.c index 6c31ee1e1c9b..c5d50e96ecd7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1611,7 +1611,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, goto out;

/* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); + page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP | FOLL_LRU);

err = PTR_ERR(page); if (IS_ERR(page)) @@ -1802,7 +1802,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, goto set_status;

/* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_DUMP); + page = follow_page(vma, addr, FOLL_DUMP | FOLL_LRU);

err = PTR_ERR(page); if (IS_ERR(page)) diff --git a/mm/mlock.c b/mm/mlock.c index 716caf851043..b14e929084cc 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -333,7 +333,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); - if (!page) + if (!page || is_zone_device_page(page)) continue; if (PageTransCompound(page)) continue; diff --git a/mm/mprotect.c b/mm/mprotect.c index b69ce7a7b2b7..a6f3587ea29a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -91,7 +91,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, continue;

page = vm_normal_page(vma, addr, oldpte); - if (!page || PageKsm(page)) + if (!page || is_zone_device_page(page) || PageKsm(page)) continue;

/* Also skip shared copy-on-write pages */

This case is used to migrate pages from device memory, back to system memory. Device coherent type memory is cache coherent from device and CPU point of view.

Signed-off-by: Alex Sierra alex.sierra@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Alistair Poppple apopple@nvidia.com Signed-off-by: Christoph Hellwig hch@lst.de --- include/linux/migrate.h | 1 + mm/migrate_device.c | 12 +++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 90e75d5a54d6..a4a336fd81fc 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -138,6 +138,7 @@ static inline unsigned long migrate_pfn(unsigned long pfn) enum migrate_vma_direction { MIGRATE_VMA_SELECT_SYSTEM = 1 << 0, MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1, + MIGRATE_VMA_SELECT_DEVICE_COHERENT = 1 << 2, };

struct migrate_vma { diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 7e267142ea34..a0b997935cf9 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -148,15 +148,21 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, if (is_writable_device_private_entry(entry)) mpfn |= MIGRATE_PFN_WRITE; } else { - if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) - goto next; pfn = pte_pfn(pte); - if (is_zero_pfn(pfn)) { + if (is_zero_pfn(pfn) && + (migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) { mpfn = MIGRATE_PFN_MIGRATE; migrate->cpages++; goto next; } page = vm_normal_page(migrate->vma, addr, pte); + if (page && !is_zone_device_page(page) && + !(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) + goto next; + else if (page && is_device_coherent_page(page) && + (!(migrate->flags & MIGRATE_VMA_SELECT_DEVICE_COHERENT) || + page->pgmap->owner != migrate->pgmap_owner)) + goto next; mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0; }

From: Alistair Popple apopple@nvidia.com

Currently any attempts to pin a device coherent page will fail. This is because device coherent pages need to be managed by a device driver, and pinning them would prevent a driver from migrating them off the device.

However this is no reason to fail pinning of these pages. These are coherent and accessible from the CPU so can be migrated just like pinning ZONE_MOVABLE pages. So instead of failing all attempts to pin them first try migrating them out of ZONE_DEVICE.

Signed-off-by: Alistair Popple apopple@nvidia.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com [hch: rebased to the split device memory checks, moved migrate_device_page to migrate_device.c] Signed-off-by: Christoph Hellwig hch@lst.de --- mm/gup.c | 47 +++++++++++++++++++++++++++++++++++----- mm/internal.h | 1 + mm/migrate_device.c | 53 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 96 insertions(+), 5 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index c9cbac06bcc5..0f3cac7604d3 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1817,9 +1817,43 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, continue; prev_folio = folio;

- if (folio_is_pinnable(folio)) + /* + * Device private pages will get faulted in during gup so it + * shouldn't be possible to see one here. + */ + if (WARN_ON_ONCE(folio_is_device_private(folio))) { + ret = -EFAULT; + goto unpin_pages; + } + + /* + * Device coherent pages are managed by a driver and should not + * be pinned indefinitely as it prevents the driver moving the + * page. So when trying to pin with FOLL_LONGTERM instead try + * to migrate the page out of device memory. + */ + if (folio_is_device_coherent(folio)) { + WARN_ON_ONCE(PageCompound(&folio->page)); + + /* + * Migration will fail if the page is pinned, so convert + * the pin on the source page to a normal reference. + */ + if (gup_flags & FOLL_PIN) { + get_page(&folio->page); + unpin_user_page(&folio->page); + } + + pages[i] = migrate_device_page(&folio->page, gup_flags); + if (!pages[i]) { + ret = -EBUSY; + goto unpin_pages; + } continue; + }

+ if (folio_is_pinnable(folio)) + continue; /* * Try to move out any movable page before pinning the range. */ @@ -1855,10 +1889,13 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, return nr_pages;

unpin_pages: - if (gup_flags & FOLL_PIN) { - unpin_user_pages(pages, nr_pages); - } else { - for (i = 0; i < nr_pages; i++) + for (i = 0; i < nr_pages; i++) { + if (!pages[i]) + continue; + + if (gup_flags & FOLL_PIN) + unpin_user_page(pages[i]); + else put_page(pages[i]); }

diff --git a/mm/internal.h b/mm/internal.h index cf16280ce132..32c621416966 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -750,6 +750,7 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags);

void free_zone_device_page(struct page *page); +struct page *migrate_device_page(struct page *page, unsigned int gup_flags);

/* * mm/gup.c diff --git a/mm/migrate_device.c b/mm/migrate_device.c index b399c498f0aa..1e74aa7ab580 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -775,3 +775,56 @@ void migrate_vma_finalize(struct migrate_vma *migrate) } } EXPORT_SYMBOL(migrate_vma_finalize); + +/* + * Migrate a device coherent page back to normal memory. The caller should have + * a reference on page which will be copied to the new page if migration is + * successful or dropped on failure. + */ +struct page *migrate_device_page(struct page *page, unsigned int gup_flags) +{ + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma args; + struct page *dpage; + + lock_page(page); + src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; + args.src = &src_pfn; + args.dst = &dst_pfn; + args.cpages = 1; + args.npages = 1; + args.vma = NULL; + migrate_vma_setup(&args); + if (!(src_pfn & MIGRATE_PFN_MIGRATE)) + return NULL; + + dpage = alloc_pages(GFP_USER | __GFP_NOWARN, 0); + + /* + * get/pin the new page now so we don't have to retry gup after + * migrating. We already have a reference so this should never fail. + */ + if (dpage && WARN_ON_ONCE(!try_grab_page(dpage, gup_flags))) { + __free_pages(dpage, 0); + dpage = NULL; + } + + if (dpage) { + lock_page(dpage); + dst_pfn = migrate_pfn(page_to_pfn(dpage)); + } + + migrate_vma_pages(&args); + if (src_pfn & MIGRATE_PFN_MIGRATE) + copy_highpage(dpage, page); + migrate_vma_finalize(&args); + if (dpage && !(src_pfn & MIGRATE_PFN_MIGRATE)) { + if (gup_flags & FOLL_PIN) + unpin_user_page(dpage); + else + put_page(dpage); + dpage = NULL; + } + + return dpage; +}

new ioctl cmd added to query zone device type. This will be used once the test_hmm adds zone device coherent type.

Signed-off-by: Alex Sierra alex.sierra@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Alistair Poppple apopple@nvidia.com Signed-off-by: Christoph Hellwig hch@lst.de --- lib/test_hmm.c | 23 +++++++++++++++++++++-- lib/test_hmm_uapi.h | 8 ++++++++ 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c index cfe632047839..7a27584484ce 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -87,6 +87,7 @@ struct dmirror_chunk { struct dmirror_device { struct cdev cdevice; struct hmm_devmem *devmem; + unsigned int zone_device_type;

unsigned int devmem_capacity; unsigned int devmem_count; @@ -1026,6 +1027,15 @@ static int dmirror_snapshot(struct dmirror *dmirror, return ret; }

+static int dmirror_get_device_type(struct dmirror *dmirror, + struct hmm_dmirror_cmd *cmd) +{ + mutex_lock(&dmirror->mutex); + cmd->zone_device_type = dmirror->mdevice->zone_device_type; + mutex_unlock(&dmirror->mutex); + + return 0; +} static long dmirror_fops_unlocked_ioctl(struct file *filp, unsigned int command, unsigned long arg) @@ -1076,6 +1086,9 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp, ret = dmirror_snapshot(dmirror, &cmd); break;

+ case HMM_DMIRROR_GET_MEM_DEV_TYPE: + ret = dmirror_get_device_type(dmirror, &cmd); + break; default: return -EINVAL; } @@ -1260,14 +1273,20 @@ static void dmirror_device_remove(struct dmirror_device *mdevice) static int __init hmm_dmirror_init(void) { int ret; - int id; + int id = 0; + int ndevices = 0;

ret = alloc_chrdev_region(&dmirror_dev, 0, DMIRROR_NDEVICES, "HMM_DMIRROR"); if (ret) goto err_unreg;

- for (id = 0; id < DMIRROR_NDEVICES; id++) { + 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; + for (id = 0; id < ndevices; id++) { ret = dmirror_device_init(dmirror_devices + id, id); if (ret) goto err_chrdev; diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index f14dea5dcd06..17f842f1aa02 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -19,6 +19,7 @@ * @npages: (in) number of pages to read/write * @cpages: (out) number of pages copied * @faults: (out) number of device page faults seen + * @zone_device_type: (out) zone device memory type */ struct hmm_dmirror_cmd { __u64 addr; @@ -26,6 +27,7 @@ struct hmm_dmirror_cmd { __u64 npages; __u64 cpages; __u64 faults; + __u64 zone_device_type; };

/* Expose the address space of the calling process through hmm device file */ @@ -35,6 +37,7 @@ struct hmm_dmirror_cmd { #define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x03, struct hmm_dmirror_cmd) #define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x04, struct hmm_dmirror_cmd) #define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_GET_MEM_DEV_TYPE _IOWR('H', 0x06, struct hmm_dmirror_cmd)

/* * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT. @@ -62,4 +65,9 @@ enum { HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE = 0x30, };

+enum { + /* 0 is reserved to catch uninitialized type fields */ + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE = 1, +}; + #endif /* _LIB_TEST_HMM_UAPI_H */

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.

Signed-off-by: Alex Sierra alex.sierra@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Alistair Poppple apopple@nvidia.com --- lib/test_hmm.c | 253 +++++++++++++++++++++++++++++++++----------- lib/test_hmm_uapi.h | 15 ++- 2 files changed, 202 insertions(+), 66 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 15747f70c5bc..361a026c5d21 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -32,11 +32,22 @@

#include "test_hmm_uapi.h"

-#define DMIRROR_NDEVICES 2 +#define DMIRROR_NDEVICES 4 #define DMIRROR_RANGE_FAULT_TIMEOUT 1000 #define DEVMEM_CHUNK_SIZE (256 * 1024 * 1024U) #define DEVMEM_CHUNKS_RESERVE 16

+/* + * 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, @@ -125,6 +136,21 @@ static int dmirror_bounce_init(struct dmirror_bounce *bounce, return 0; }

+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); @@ -575,16 +601,19 @@ static int dmirror_allocate_chunk(struct dmirror_device *mdevice, static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) { struct page *dpage = NULL; - struct page *rpage; + struct page *rpage = NULL;

/* - * This is a fake device so we alloc real system memory to store - * our device memory. + * 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. */ - rpage = alloc_page(GFP_HIGHUSER); - if (!rpage) - return NULL; - + if (dmirror_is_private_zone(mdevice)) { + rpage = alloc_page(GFP_HIGHUSER); + if (!rpage) + return NULL; + } spin_lock(&mdevice->lock);

if (mdevice->free_pages) { @@ -603,7 +632,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) return dpage;

error: - __free_page(rpage); + if (rpage) + __free_page(rpage); return NULL; }

@@ -629,12 +659,16 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, * unallocated pte_none() or read-only zero page. */ spage = migrate_pfn_to_page(*src); + 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;

- rpage = dpage->zone_device_data; + rpage = BACKING_PAGE(dpage); if (spage) copy_highpage(rpage, spage); else @@ -648,6 +682,8 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, */ rpage->zone_device_data = dmirror;

+ 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)) @@ -725,11 +761,7 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args, if (!dpage) continue;

- /* - * Store the page that holds the data so the page table - * doesn't have to deal with ZONE_DEVICE private pages. - */ - entry = dpage->zone_device_data; + 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); @@ -809,15 +841,126 @@ static int dmirror_exclusive(struct dmirror *dmirror, return ret; }

-static int dmirror_migrate(struct dmirror *dmirror, - struct hmm_dmirror_cmd *cmd) +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; - unsigned long src_pfns[64]; - unsigned long dst_pfns[64]; + unsigned long src_pfns[64] = { 0 }; + unsigned long dst_pfns[64] = { 0 }; + struct migrate_vma args; + 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; struct migrate_vma args; unsigned long next; @@ -854,6 +997,7 @@ static int dmirror_migrate(struct dmirror *dmirror, if (ret) goto out;

+ 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); @@ -862,7 +1006,10 @@ static int dmirror_migrate(struct dmirror *dmirror, mmap_read_unlock(mm); mmput(mm);

- /* Return the migrated data for verification. */ + /* + * Return the migrated data for verification. + * Only for pages in device zone + */ ret = dmirror_bounce_init(&bounce, start, size); if (ret) return ret; @@ -905,6 +1052,12 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range, *perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL; else *perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE; + } 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 @@ -1101,8 +1254,12 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp, ret = dmirror_write(dmirror, &cmd); break;

- case HMM_DMIRROR_MIGRATE: - ret = dmirror_migrate(dmirror, &cmd); + 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: @@ -1167,14 +1324,13 @@ static const struct file_operations dmirror_fops = {

static void dmirror_devmem_free(struct page *page) { - struct page *rpage = page->zone_device_data; + struct page *rpage = BACKING_PAGE(page); struct dmirror_device *mdevice;

- if (rpage) + if (rpage != page) __free_page(rpage);

mdevice = dmirror_page_to_device(page); - spin_lock(&mdevice->lock); mdevice->cfree++; page->zone_device_data = mdevice->free_pages; @@ -1182,43 +1338,11 @@ static void dmirror_devmem_free(struct page *page) spin_unlock(&mdevice->lock); }

-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; - spage = spage->zone_device_data; - - dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr); - if (!dpage) - continue; - - 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 vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) { struct migrate_vma args; - unsigned long src_pfns; - unsigned long dst_pfns; + unsigned long src_pfns = 0; + unsigned long dst_pfns = 0; struct page *rpage; struct dmirror *dmirror; vm_fault_t ret; @@ -1238,7 +1362,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) args.src = &src_pfns; args.dst = &dst_pfns; args.pgmap_owner = dmirror->mdevice; - args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + args.flags = dmirror_select_device(dmirror);

if (migrate_vma_setup(&args)) return VM_FAULT_SIGBUS; @@ -1317,6 +1441,12 @@ static int __init hmm_dmirror_init(void) HMM_DMIRROR_MEMORY_DEVICE_PRIVATE; dmirror_devices[ndevices++].zone_device_type = HMM_DMIRROR_MEMORY_DEVICE_PRIVATE; + 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) @@ -1339,7 +1469,8 @@ static void __exit hmm_dmirror_exit(void) int id;

for (id = 0; id < DMIRROR_NDEVICES; id++) - dmirror_device_remove(dmirror_devices + id); + if (dmirror_devices[id].zone_device_type) + dmirror_device_remove(dmirror_devices + id); unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES); }

diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index 625f3690d086..e190b2ab6f19 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -33,11 +33,12 @@ struct hmm_dmirror_cmd { /* Expose the address space of the calling process through hmm device file */ #define HMM_DMIRROR_READ _IOWR('H', 0x00, struct hmm_dmirror_cmd) #define HMM_DMIRROR_WRITE _IOWR('H', 0x01, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_MIGRATE _IOWR('H', 0x02, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x03, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x04, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_GET_MEM_DEV_TYPE _IOWR('H', 0x06, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_MIGRATE_TO_DEV _IOWR('H', 0x02, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_MIGRATE_TO_SYS _IOWR('H', 0x03, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x04, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x06, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_GET_MEM_DEV_TYPE _IOWR('H', 0x07, struct hmm_dmirror_cmd)

/* * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT. @@ -52,6 +53,8 @@ struct hmm_dmirror_cmd { * device the ioctl() is made * HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE: Migrated device private page on some * other device + * HMM_DMIRROR_PROT_DEV_COHERENT: Migrate device coherent page on the device + * the ioctl() is made */ enum { HMM_DMIRROR_PROT_ERROR = 0xFF, @@ -63,6 +66,8 @@ enum { HMM_DMIRROR_PROT_ZERO = 0x10, HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL = 0x20, HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE = 0x30, + HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL = 0x40, + HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE = 0x50, };

enum {

Add two more parameters to set spm_addr_dev0 & spm_addr_dev1 addresses. These two parameters configure the start SP addresses for each device in test_hmm driver. Consequently, this configures zone device type as coherent.

Signed-off-by: Alex Sierra alex.sierra@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Alistair Popple apopple@nvidia.com Signed-off-by: Christoph Hellwig hch@lst.de --- tools/testing/selftests/vm/test_hmm.sh | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/vm/test_hmm.sh index 0647b525a625..539c9371e592 100755 --- a/tools/testing/selftests/vm/test_hmm.sh +++ b/tools/testing/selftests/vm/test_hmm.sh @@ -40,11 +40,26 @@ check_test_requirements()

load_driver() { - modprobe $DRIVER > /dev/null 2>&1 + if [ $# -eq 0 ]; then + modprobe $DRIVER > /dev/null 2>&1 + else + if [ $# -eq 2 ]; then + modprobe $DRIVER spm_addr_dev0=$1 spm_addr_dev1=$2 + > /dev/null 2>&1 + else + echo "Missing module parameters. Make sure pass"\ + "spm_addr_dev0 and spm_addr_dev1" + usage + fi + fi if [ $? == 0 ]; then major=$(awk "$2=="HMM_DMIRROR" {print $1}" /proc/devices) mknod /dev/hmm_dmirror0 c $major 0 mknod /dev/hmm_dmirror1 c $major 1 + if [ $# -eq 2 ]; then + mknod /dev/hmm_dmirror2 c $major 2 + mknod /dev/hmm_dmirror3 c $major 3 + fi fi }

@@ -58,7 +73,7 @@ run_smoke() { echo "Running smoke test. Note, this test provides basic coverage."

- load_driver + load_driver $1 $2 $(dirname "${BASH_SOURCE[0]}")/hmm-tests unload_driver } @@ -75,6 +90,9 @@ usage() echo "# Smoke testing" echo "./${TEST_NAME}.sh smoke" echo + echo "# Smoke testing with SPM enabled" + echo "./${TEST_NAME}.sh smoke <spm_addr_dev0> <spm_addr_dev1>" + echo exit 0 }

@@ -84,7 +102,7 @@ function run_test() usage else if [ "$1" = "smoke" ]; then - run_smoke + run_smoke $2 $3 else usage fi

The objective is to test device migration mechanism in pages marked as COW, for private and coherent device type. In case of writing to COW private page(s), a page fault will migrate pages back to system memory first. Then, these pages will be duplicated. In case of COW device coherent type, pages are duplicated directly from device memory.

Signed-off-by: Alex Sierra alex.sierra@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com --- tools/testing/selftests/vm/hmm-tests.c | 80 ++++++++++++++++++++++++++ 1 file changed, 80 insertions(+)

diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 61a02a6a3dea..76570030ba5b 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -1871,4 +1871,84 @@ TEST_F(hmm, hmm_gup_test) close(gup_fd); hmm_buffer_free(buffer); } + +/* + * Test copy-on-write in device pages. + * In case of writing to COW private page(s), a page fault will migrate pages + * back to system memory first. Then, these pages will be duplicated. In case + * of COW device coherent type, pages are duplicated directly from device + * memory. + */ +TEST_F(hmm, hmm_cow_in_device) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + unsigned char *m; + pid_t pid; + int status; + + npages = 4; + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + pid = fork(); + if (pid == -1) + ASSERT_EQ(pid, 0); + if (!pid) { + /* Child process waitd for SIGTERM from the parent. */ + while (1) { + } + perror("Should not reach this\n"); + exit(0); + } + /* Parent process writes to COW pages(s) and gets a + * new copy in system. In case of device private pages, + * this write causes a migration to system mem first. + */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Terminate child and wait */ + EXPECT_EQ(0, kill(pid, SIGTERM)); + EXPECT_EQ(pid, waitpid(pid, &status, 0)); + EXPECT_NE(0, WIFSIGNALED(status)); + EXPECT_EQ(SIGTERM, WTERMSIG(status)); + + /* Take snapshot to CPU pagetables */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + m = buffer->mirror; + for (i = 0; i < npages; i++) + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[i]); + + hmm_buffer_free(buffer); +} TEST_HARNESS_MAIN