diff options
Diffstat (limited to 'mm/hmm.c')
| -rw-r--r-- | mm/hmm.c | 407 |
1 files changed, 352 insertions, 55 deletions
@@ -10,6 +10,7 @@ */ #include <linux/pagewalk.h> #include <linux/hmm.h> +#include <linux/hmm-dma.h> #include <linux/init.h> #include <linux/rmap.h> #include <linux/swap.h> @@ -17,12 +18,13 @@ #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/pagemap.h> -#include <linux/swapops.h> +#include <linux/leafops.h> #include <linux/hugetlb.h> #include <linux/memremap.h> #include <linux/sched/mm.h> #include <linux/jump_label.h> #include <linux/dma-mapping.h> +#include <linux/pci-p2pdma.h> #include <linux/mmu_notifier.h> #include <linux/memory_hotplug.h> @@ -39,13 +41,21 @@ enum { HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT, }; +enum { + /* These flags are carried from input-to-output */ + HMM_PFN_INOUT_FLAGS = HMM_PFN_DMA_MAPPED | HMM_PFN_P2PDMA | + HMM_PFN_P2PDMA_BUS, +}; + static int hmm_pfns_fill(unsigned long addr, unsigned long end, struct hmm_range *range, unsigned long cpu_flags) { unsigned long i = (addr - range->start) >> PAGE_SHIFT; - for (; addr < end; addr += PAGE_SIZE, i++) - range->hmm_pfns[i] = cpu_flags; + for (; addr < end; addr += PAGE_SIZE, i++) { + range->hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS; + range->hmm_pfns[i] |= cpu_flags; + } return 0; } @@ -173,6 +183,7 @@ static inline unsigned long hmm_pfn_flags_order(unsigned long order) return order << HMM_PFN_ORDER_SHIFT; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd) { @@ -183,7 +194,6 @@ static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range, hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, unsigned long end, unsigned long hmm_pfns[], pmd_t pmd) @@ -202,8 +212,10 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, return hmm_vma_fault(addr, end, required_fault, walk); pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) - hmm_pfns[i] = pfn | cpu_flags; + for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) { + hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS; + hmm_pfns[i] |= pfn | cpu_flags; + } return 0; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -228,52 +240,55 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, struct hmm_range *range = hmm_vma_walk->range; unsigned int required_fault; unsigned long cpu_flags; - pte_t pte = *ptep; + pte_t pte = ptep_get(ptep); uint64_t pfn_req_flags = *hmm_pfn; + uint64_t new_pfn_flags = 0; - if (pte_none_mostly(pte)) { + /* + * Any other marker than a UFFD WP marker will result in a fault error + * that will be correctly handled, so we need only check for UFFD WP + * here. + */ + if (pte_none(pte) || pte_is_uffd_wp_marker(pte)) { required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); if (required_fault) goto fault; - *hmm_pfn = 0; - return 0; + goto out; } if (!pte_present(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); + const softleaf_t entry = softleaf_from_pte(pte); /* * Don't fault in device private pages owned by the caller, * just report the PFN. */ - if (is_device_private_entry(entry) && - pfn_swap_entry_to_page(entry)->pgmap->owner == + if (softleaf_is_device_private(entry) && + page_pgmap(softleaf_to_page(entry))->owner == range->dev_private_owner) { cpu_flags = HMM_PFN_VALID; - if (is_writable_device_private_entry(entry)) + if (softleaf_is_device_private_write(entry)) cpu_flags |= HMM_PFN_WRITE; - *hmm_pfn = swp_offset_pfn(entry) | cpu_flags; - return 0; + new_pfn_flags = softleaf_to_pfn(entry) | cpu_flags; + goto out; } required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); - if (!required_fault) { - *hmm_pfn = 0; - return 0; - } + if (!required_fault) + goto out; - if (!non_swap_entry(entry)) + if (softleaf_is_swap(entry)) goto fault; - if (is_device_private_entry(entry)) + if (softleaf_is_device_private(entry)) goto fault; - if (is_device_exclusive_entry(entry)) + if (softleaf_is_device_exclusive(entry)) goto fault; - if (is_migration_entry(entry)) { + if (softleaf_is_migration(entry)) { pte_unmap(ptep); hmm_vma_walk->last = addr; migration_entry_wait(walk->mm, pmdp, addr); @@ -292,23 +307,22 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, goto fault; /* - * Bypass devmap pte such as DAX page when all pfn requested - * flags(pfn_req_flags) are fulfilled. * Since each architecture defines a struct page for the zero page, just * fall through and treat it like a normal page. */ if (!vm_normal_page(walk->vma, addr, pte) && - !pte_devmap(pte) && !is_zero_pfn(pte_pfn(pte))) { if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) { pte_unmap(ptep); return -EFAULT; } - *hmm_pfn = HMM_PFN_ERROR; - return 0; + new_pfn_flags = HMM_PFN_ERROR; + goto out; } - *hmm_pfn = pte_pfn(pte) | cpu_flags; + new_pfn_flags = pte_pfn(pte) | cpu_flags; +out: + *hmm_pfn = (*hmm_pfn & HMM_PFN_INOUT_FLAGS) | new_pfn_flags; return 0; fault: @@ -317,6 +331,68 @@ fault: return hmm_vma_fault(addr, end, required_fault, walk); } +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +static int hmm_vma_handle_absent_pmd(struct mm_walk *walk, unsigned long start, + unsigned long end, unsigned long *hmm_pfns, + pmd_t pmd) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + unsigned long npages = (end - start) >> PAGE_SHIFT; + const softleaf_t entry = softleaf_from_pmd(pmd); + unsigned long addr = start; + unsigned int required_fault; + + if (softleaf_is_device_private(entry) && + softleaf_to_folio(entry)->pgmap->owner == + range->dev_private_owner) { + unsigned long cpu_flags = HMM_PFN_VALID | + hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT); + unsigned long pfn = softleaf_to_pfn(entry); + unsigned long i; + + if (softleaf_is_device_private_write(entry)) + cpu_flags |= HMM_PFN_WRITE; + + /* + * Fully populate the PFN list though subsequent PFNs could be + * inferred, because drivers which are not yet aware of large + * folios probably do not support sparsely populated PFN lists. + */ + for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) { + hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS; + hmm_pfns[i] |= pfn | cpu_flags; + } + + return 0; + } + + required_fault = hmm_range_need_fault(hmm_vma_walk, hmm_pfns, + npages, 0); + if (required_fault) { + if (softleaf_is_device_private(entry)) + return hmm_vma_fault(addr, end, required_fault, walk); + else + return -EFAULT; + } + + return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); +} +#else +static int hmm_vma_handle_absent_pmd(struct mm_walk *walk, unsigned long start, + unsigned long end, unsigned long *hmm_pfns, + pmd_t pmd) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + unsigned long npages = (end - start) >> PAGE_SHIFT; + + if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) + return -EFAULT; + return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); +} +#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ + static int hmm_vma_walk_pmd(pmd_t *pmdp, unsigned long start, unsigned long end, @@ -332,11 +408,11 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp, pmd_t pmd; again: - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get_lockless(pmdp); if (pmd_none(pmd)) return hmm_vma_walk_hole(start, end, -1, walk); - if (thp_migration_supported() && is_pmd_migration_entry(pmd)) { + if (thp_migration_supported() && pmd_is_migration_entry(pmd)) { if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) { hmm_vma_walk->last = addr; pmd_migration_entry_wait(walk->mm, pmdp); @@ -345,13 +421,11 @@ again: return hmm_pfns_fill(start, end, range, 0); } - if (!pmd_present(pmd)) { - if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) - return -EFAULT; - return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); - } + if (!pmd_present(pmd)) + return hmm_vma_handle_absent_pmd(walk, start, end, hmm_pfns, + pmd); - if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) { + if (pmd_trans_huge(pmd)) { /* * No need to take pmd_lock here, even if some other thread * is splitting the huge pmd we will get that event through @@ -362,7 +436,7 @@ again: * values. */ pmd = pmdp_get_lockless(pmdp); - if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd)) + if (!pmd_trans_huge(pmd)) goto again; return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd); @@ -381,6 +455,8 @@ again: } ptep = pte_offset_map(pmdp, addr); + if (!ptep) + goto again; for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) { int r; @@ -394,8 +470,7 @@ again: return 0; } -#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \ - defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) +#if defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud) { @@ -421,23 +496,18 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end, /* Normally we don't want to split the huge page */ walk->action = ACTION_CONTINUE; - pud = READ_ONCE(*pudp); - if (pud_none(pud)) { + pud = pudp_get(pudp); + if (!pud_present(pud)) { spin_unlock(ptl); return hmm_vma_walk_hole(start, end, -1, walk); } - if (pud_huge(pud) && pud_devmap(pud)) { + if (pud_leaf(pud)) { unsigned long i, npages, pfn; unsigned int required_fault; unsigned long *hmm_pfns; unsigned long cpu_flags; - if (!pud_present(pud)) { - spin_unlock(ptl); - return hmm_vma_walk_hole(start, end, -1, walk); - } - i = (addr - range->start) >> PAGE_SHIFT; npages = (end - addr) >> PAGE_SHIFT; hmm_pfns = &range->hmm_pfns[i]; @@ -451,8 +521,10 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end, } pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - for (i = 0; i < npages; ++i, ++pfn) - hmm_pfns[i] = pfn | cpu_flags; + for (i = 0; i < npages; ++i, ++pfn) { + hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS; + hmm_pfns[i] |= pfn | cpu_flags; + } goto out_unlock; } @@ -483,7 +555,7 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, pte_t entry; ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); - entry = huge_ptep_get(pte); + entry = huge_ptep_get(walk->mm, addr, pte); i = (start - range->start) >> PAGE_SHIFT; pfn_req_flags = range->hmm_pfns[i]; @@ -492,13 +564,28 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); if (required_fault) { + int ret; + spin_unlock(ptl); - return hmm_vma_fault(addr, end, required_fault, walk); + hugetlb_vma_unlock_read(vma); + /* + * Avoid deadlock: drop the vma lock before calling + * hmm_vma_fault(), which will itself potentially take and + * drop the vma lock. This is also correct from a + * protection point of view, because there is no further + * use here of either pte or ptl after dropping the vma + * lock. + */ + ret = hmm_vma_fault(addr, end, required_fault, walk); + hugetlb_vma_lock_read(vma); + return ret; } pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT); - for (; addr < end; addr += PAGE_SIZE, i++, pfn++) - range->hmm_pfns[i] = pfn | cpu_flags; + for (; addr < end; addr += PAGE_SIZE, i++, pfn++) { + range->hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS; + range->hmm_pfns[i] |= pfn | cpu_flags; + } spin_unlock(ptl); return 0; @@ -547,6 +634,7 @@ static const struct mm_walk_ops hmm_walk_ops = { .pte_hole = hmm_vma_walk_hole, .hugetlb_entry = hmm_vma_walk_hugetlb_entry, .test_walk = hmm_vma_walk_test, + .walk_lock = PGWALK_RDLOCK, }; /** @@ -596,3 +684,212 @@ int hmm_range_fault(struct hmm_range *range) return ret; } EXPORT_SYMBOL(hmm_range_fault); + +/** + * hmm_dma_map_alloc - Allocate HMM map structure + * @dev: device to allocate structure for + * @map: HMM map to allocate + * @nr_entries: number of entries in the map + * @dma_entry_size: size of the DMA entry in the map + * + * Allocate the HMM map structure and all the lists it contains. + * Return 0 on success, -ENOMEM on failure. + */ +int hmm_dma_map_alloc(struct device *dev, struct hmm_dma_map *map, + size_t nr_entries, size_t dma_entry_size) +{ + bool dma_need_sync = false; + bool use_iova; + + WARN_ON_ONCE(!(nr_entries * PAGE_SIZE / dma_entry_size)); + + /* + * The HMM API violates our normal DMA buffer ownership rules and can't + * transfer buffer ownership. The dma_addressing_limited() check is a + * best approximation to ensure no swiotlb buffering happens. + */ +#ifdef CONFIG_DMA_NEED_SYNC + dma_need_sync = !dev->dma_skip_sync; +#endif /* CONFIG_DMA_NEED_SYNC */ + if (dma_need_sync || dma_addressing_limited(dev)) + return -EOPNOTSUPP; + + map->dma_entry_size = dma_entry_size; + map->pfn_list = kvcalloc(nr_entries, sizeof(*map->pfn_list), + GFP_KERNEL | __GFP_NOWARN); + if (!map->pfn_list) + return -ENOMEM; + + use_iova = dma_iova_try_alloc(dev, &map->state, 0, + nr_entries * PAGE_SIZE); + if (!use_iova && dma_need_unmap(dev)) { + map->dma_list = kvcalloc(nr_entries, sizeof(*map->dma_list), + GFP_KERNEL | __GFP_NOWARN); + if (!map->dma_list) + goto err_dma; + } + return 0; + +err_dma: + kvfree(map->pfn_list); + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(hmm_dma_map_alloc); + +/** + * hmm_dma_map_free - iFree HMM map structure + * @dev: device to free structure from + * @map: HMM map containing the various lists and state + * + * Free the HMM map structure and all the lists it contains. + */ +void hmm_dma_map_free(struct device *dev, struct hmm_dma_map *map) +{ + if (dma_use_iova(&map->state)) + dma_iova_free(dev, &map->state); + kvfree(map->pfn_list); + kvfree(map->dma_list); +} +EXPORT_SYMBOL_GPL(hmm_dma_map_free); + +/** + * hmm_dma_map_pfn - Map a physical HMM page to DMA address + * @dev: Device to map the page for + * @map: HMM map + * @idx: Index into the PFN and dma address arrays + * @p2pdma_state: PCI P2P state. + * + * dma_alloc_iova() allocates IOVA based on the size specified by their use in + * iova->size. Call this function after IOVA allocation to link whole @page + * to get the DMA address. Note that very first call to this function + * will have @offset set to 0 in the IOVA space allocated from + * dma_alloc_iova(). For subsequent calls to this function on same @iova, + * @offset needs to be advanced by the caller with the size of previous + * page that was linked + DMA address returned for the previous page that was + * linked by this function. + */ +dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map, + size_t idx, + struct pci_p2pdma_map_state *p2pdma_state) +{ + struct dma_iova_state *state = &map->state; + dma_addr_t *dma_addrs = map->dma_list; + unsigned long *pfns = map->pfn_list; + struct page *page = hmm_pfn_to_page(pfns[idx]); + phys_addr_t paddr = hmm_pfn_to_phys(pfns[idx]); + size_t offset = idx * map->dma_entry_size; + unsigned long attrs = 0; + dma_addr_t dma_addr; + int ret; + + if ((pfns[idx] & HMM_PFN_DMA_MAPPED) && + !(pfns[idx] & HMM_PFN_P2PDMA_BUS)) { + /* + * We are in this flow when there is a need to resync flags, + * for example when page was already linked in prefetch call + * with READ flag and now we need to add WRITE flag + * + * This page was already programmed to HW and we don't want/need + * to unlink and link it again just to resync flags. + */ + if (dma_use_iova(state)) + return state->addr + offset; + + /* + * Without dma_need_unmap, the dma_addrs array is NULL, thus we + * need to regenerate the address below even if there already + * was a mapping. But !dma_need_unmap implies that the + * mapping stateless, so this is fine. + */ + if (dma_need_unmap(dev)) + return dma_addrs[idx]; + + /* Continue to remapping */ + } + + switch (pci_p2pdma_state(p2pdma_state, dev, page)) { + case PCI_P2PDMA_MAP_NONE: + break; + case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: + attrs |= DMA_ATTR_MMIO; + pfns[idx] |= HMM_PFN_P2PDMA; + break; + case PCI_P2PDMA_MAP_BUS_ADDR: + pfns[idx] |= HMM_PFN_P2PDMA_BUS | HMM_PFN_DMA_MAPPED; + return pci_p2pdma_bus_addr_map(p2pdma_state->mem, paddr); + default: + return DMA_MAPPING_ERROR; + } + + if (dma_use_iova(state)) { + ret = dma_iova_link(dev, state, paddr, offset, + map->dma_entry_size, DMA_BIDIRECTIONAL, + attrs); + if (ret) + goto error; + + ret = dma_iova_sync(dev, state, offset, map->dma_entry_size); + if (ret) { + dma_iova_unlink(dev, state, offset, map->dma_entry_size, + DMA_BIDIRECTIONAL, attrs); + goto error; + } + + dma_addr = state->addr + offset; + } else { + if (WARN_ON_ONCE(dma_need_unmap(dev) && !dma_addrs)) + goto error; + + dma_addr = dma_map_phys(dev, paddr, map->dma_entry_size, + DMA_BIDIRECTIONAL, attrs); + if (dma_mapping_error(dev, dma_addr)) + goto error; + + if (dma_need_unmap(dev)) + dma_addrs[idx] = dma_addr; + } + pfns[idx] |= HMM_PFN_DMA_MAPPED; + return dma_addr; +error: + pfns[idx] &= ~HMM_PFN_P2PDMA; + return DMA_MAPPING_ERROR; + +} +EXPORT_SYMBOL_GPL(hmm_dma_map_pfn); + +/** + * hmm_dma_unmap_pfn - Unmap a physical HMM page from DMA address + * @dev: Device to unmap the page from + * @map: HMM map + * @idx: Index of the PFN to unmap + * + * Returns true if the PFN was mapped and has been unmapped, false otherwise. + */ +bool hmm_dma_unmap_pfn(struct device *dev, struct hmm_dma_map *map, size_t idx) +{ + const unsigned long valid_dma = HMM_PFN_VALID | HMM_PFN_DMA_MAPPED; + struct dma_iova_state *state = &map->state; + dma_addr_t *dma_addrs = map->dma_list; + unsigned long *pfns = map->pfn_list; + unsigned long attrs = 0; + + if ((pfns[idx] & valid_dma) != valid_dma) + return false; + + if (pfns[idx] & HMM_PFN_P2PDMA) + attrs |= DMA_ATTR_MMIO; + + if (pfns[idx] & HMM_PFN_P2PDMA_BUS) + ; /* no need to unmap bus address P2P mappings */ + else if (dma_use_iova(state)) + dma_iova_unlink(dev, state, idx * map->dma_entry_size, + map->dma_entry_size, DMA_BIDIRECTIONAL, attrs); + else if (dma_need_unmap(dev)) + dma_unmap_phys(dev, dma_addrs[idx], map->dma_entry_size, + DMA_BIDIRECTIONAL, attrs); + + pfns[idx] &= + ~(HMM_PFN_DMA_MAPPED | HMM_PFN_P2PDMA | HMM_PFN_P2PDMA_BUS); + return true; +} +EXPORT_SYMBOL_GPL(hmm_dma_unmap_pfn); |