mm/hmm: let users to tag specific PFN with DMA mapped bit

JIRA: https://issues.redhat.com/browse/RHEL-110100

commit 285e871
Author: Leon Romanovsky <leon@kernel.org>
Date:   Mon Apr 28 12:22:16 2025 +0300

    mm/hmm: let users to tag specific PFN with DMA mapped bit

    Introduce new sticky flag (HMM_PFN_DMA_MAPPED), which isn't overwritten
    by HMM range fault. Such flag allows users to tag specific PFNs with
    information if this specific PFN was already DMA mapped.

    Tested-by: Jens Axboe <axboe@kernel.dk>
    Reviewed-by: Christoph Hellwig <hch@lst.de>
    Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
    Signed-off-by: Leon Romanovsky <leonro@nvidia.com>

Signed-off-by: Kamal Heib <kheib@redhat.com>

Author: Kamalheib

include/linux/hmm.h

@@ -23,6 +23,8 @@ struct mmu_interval_notifier;
  * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID)
  * HMM_PFN_ERROR - accessing the pfn is impossible and the device should
  *                 fail. ie poisoned memory, special pages, no vma, etc
+ * HMM_PFN_DMA_MAPPED - Flag preserved on input-to-output transformation
+ *                      to mark that page is already DMA mapped
  *
  * On input:
  * 0                 - Return the current state of the page, do not fault it.
@@ -36,13 +38,19 @@ enum hmm_pfn_flags {
 	HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
 	HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
 	HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
-	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8),
+	/*
+	 * Sticky flags, carried from input to output,
+	 * don't forget to update HMM_PFN_INOUT_FLAGS
+	 */
+	HMM_PFN_DMA_MAPPED = 1UL << (BITS_PER_LONG - 4),
+
+	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 9),
 
 	/* Input flags */
 	HMM_PFN_REQ_FAULT = HMM_PFN_VALID,
 	HMM_PFN_REQ_WRITE = HMM_PFN_WRITE,
 
-	HMM_PFN_FLAGS = 0xFFUL << HMM_PFN_ORDER_SHIFT,
+	HMM_PFN_FLAGS = ~((1UL << HMM_PFN_ORDER_SHIFT) - 1),
 };
 
 /*
@@ -57,6 +65,14 @@ static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn)
 	return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS);
 }
 
+/*
+ * hmm_pfn_to_phys() - return physical address pointed to by a device entry
+ */
+static inline phys_addr_t hmm_pfn_to_phys(unsigned long hmm_pfn)
+{
+	return __pfn_to_phys(hmm_pfn & ~HMM_PFN_FLAGS);
+}
+
 /*
  * hmm_pfn_to_map_order() - return the CPU mapping size order
  *

mm/hmm.c

@@ -39,13 +39,20 @@ 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,
+};
+
 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;
 }
 
@@ -202,8 +209,10 @@ 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 */
@@ -230,14 +239,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 	unsigned long cpu_flags;
 	pte_t pte = ptep_get(ptep);
 	uint64_t pfn_req_flags = *hmm_pfn;
+	uint64_t new_pfn_flags = 0;
 
 	if (pte_none_mostly(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)) {
@@ -253,16 +262,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			cpu_flags = HMM_PFN_VALID;
 			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
-			*hmm_pfn = swp_offset_pfn(entry) | cpu_flags;
-			return 0;
+			new_pfn_flags = swp_offset_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))
 			goto fault;
@@ -304,11 +311,13 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			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:
@@ -453,8 +462,10 @@ 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;
 	}
 
@@ -512,8 +523,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	}
 
 	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;