/* * hmm_vma_fault() - fault in a range lacking valid pmd or pte(s) * @addr: range virtual start address (inclusive) * @end: range virtual end address (exclusive) * @required_fault: HMM_NEED_* flags * @walk: mm_walk structure * Return: -EBUSY after page fault, or page fault error * * This function will be called whenever pmd_none() or pte_none() returns true, * or whenever there is no page directory covering the virtual address range.
*/ staticint hmm_vma_fault(unsignedlong addr, unsignedlong end, unsignedint required_fault, struct mm_walk *walk)
{ struct hmm_vma_walk *hmm_vma_walk = walk->private; struct vm_area_struct *vma = walk->vma; unsignedint fault_flags = FAULT_FLAG_REMOTE;
/* * So we not only consider the individual per page request we also * consider the default flags requested for the range. The API can * be used 2 ways. The first one where the HMM user coalesces * multiple page faults into one request and sets flags per pfn for * those faults. The second one where the HMM user wants to pre- * fault a range with specific flags. For the latter one it is a * waste to have the user pre-fill the pfn arrays with a default * flags value.
*/
pfn_req_flags &= range->pfn_flags_mask;
pfn_req_flags |= range->default_flags;
/* We aren't ask to do anything ... */ if (!(pfn_req_flags & HMM_PFN_REQ_FAULT)) return 0;
/* Need to write fault ? */ if ((pfn_req_flags & HMM_PFN_REQ_WRITE) &&
!(cpu_flags & HMM_PFN_WRITE)) return HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT;
/* If CPU page table is not valid then we need to fault */ if (!(cpu_flags & HMM_PFN_VALID)) return HMM_NEED_FAULT; return 0;
}
/* * If the default flags do not request to fault pages, and the mask does * not allow for individual pages to be faulted, then * hmm_pte_need_fault() will always return 0.
*/ if (!((range->default_flags | range->pfn_flags_mask) &
HMM_PFN_REQ_FAULT)) return 0;
for (i = 0; i < npages; ++i) {
required_fault |= hmm_pte_need_fault(hmm_vma_walk, hmm_pfns[i],
cpu_flags); if (required_fault == HMM_NEED_ALL_BITS) return required_fault;
} return required_fault;
}
/* * 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) &&
!is_zero_pfn(pte_pfn(pte))) { if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) {
pte_unmap(ptep); return -EFAULT;
}
new_pfn_flags = HMM_PFN_ERROR; goto out;
}
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_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 * mmu_notifier callback. * * So just read pmd value and check again it's a transparent * huge or device mapping one and compute corresponding pfn * values.
*/
pmd = pmdp_get_lockless(pmdp); if (!pmd_trans_huge(pmd)) goto again;
/* * We have handled all the valid cases above ie either none, migration, * huge or transparent huge. At this point either it is a valid pmd * entry pointing to pte directory or it is a bad pmd that will not * recover.
*/ if (pmd_bad(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);
}
ptep = pte_offset_map(pmdp, addr); if (!ptep) goto again; for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) { int r;
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, hmm_pfns); if (r) { /* hmm_vma_handle_pte() did pte_unmap() */ return r;
}
}
pte_unmap(ptep - 1); return 0;
}
i = (start - range->start) >> PAGE_SHIFT;
pfn_req_flags = range->hmm_pfns[i];
cpu_flags = pte_to_hmm_pfn_flags(range, entry) |
hmm_pfn_flags_order(huge_page_order(hstate_vma(vma)));
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); if (required_fault) { int ret;
spin_unlock(ptl);
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;
}
/* * vma ranges that don't have struct page backing them or map I/O * devices directly cannot be handled by hmm_range_fault(). * * If the vma does not allow read access, then assume that it does not * allow write access either. HMM does not support architectures that * allow write without read. * * If a fault is requested for an unsupported range then it is a hard * failure.
*/ if (hmm_range_need_fault(hmm_vma_walk,
range->hmm_pfns +
((start - range->start) >> PAGE_SHIFT),
(end - start) >> PAGE_SHIFT, 0)) return -EFAULT;
hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
/* Skip this vma and continue processing the next vma. */ return 1;
}
/** * hmm_range_fault - try to fault some address in a virtual address range * @range: argument structure * * Returns 0 on success or one of the following error codes: * * -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma * (e.g., device file vma). * -ENOMEM: Out of memory. * -EPERM: Invalid permission (e.g., asking for write and range is read * only). * -EBUSY: The range has been invalidated and the caller needs to wait for * the invalidation to finish. * -EFAULT: A page was requested to be valid and could not be made valid * ie it has no backing VMA or it is illegal to access * * This is similar to get_user_pages(), except that it can read the page tables * without mutating them (ie causing faults).
*/ int hmm_range_fault(struct hmm_range *range)
{ struct hmm_vma_walk hmm_vma_walk = {
.range = range,
.last = range->start,
}; struct mm_struct *mm = range->notifier->mm; int ret;
mmap_assert_locked(mm);
do { /* If range is no longer valid force retry. */ if (mmu_interval_check_retry(range->notifier,
range->notifier_seq)) return -EBUSY;
ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
&hmm_walk_ops, &hmm_vma_walk); /* * When -EBUSY is returned the loop restarts with * hmm_vma_walk.last set to an address that has not been stored * in pfns. All entries < last in the pfn array are set to their * output, and all >= are still at their input values.
*/
} while (ret == -EBUSY); 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;
/* * 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;
/** * 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; unsignedlong *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; unsignedlong 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];
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.