Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

2 files changed, 55 insertions, 30 deletions

diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index de10800cd4..37d51cfd77 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -14,7 +14,7 @@
  * memory ranges: uncached, write-combining, write-through, write-protected,
  * and the most commonly used and default attribute: write-back caching.
  *
- * PAT support supercedes and augments MTRR support in a compatible fashion: MTRR is
+ * PAT support supersedes and augments MTRR support in a compatible fashion: MTRR is
  * a hardware interface to enumerate a limited number of physical memory ranges
  * and set their caching attributes explicitly, programmed into the CPU via MSRs.
  * Even modern CPUs have MTRRs enabled - but these are typically not touched
@@ -950,6 +950,38 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 		memtype_free(paddr, paddr + size);
 }
 
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+		pgprot_t *pgprot)
+{
+	unsigned long prot;
+
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+	/*
+	 * We need the starting PFN and cachemode used for track_pfn_remap()
+	 * that covered the whole VMA. For most mappings, we can obtain that
+	 * information from the page tables. For COW mappings, we might now
+	 * suddenly have anon folios mapped and follow_phys() will fail.
+	 *
+	 * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+	 * detect the PFN. If we need the cachemode as well, we're out of luck
+	 * for now and have to fail fork().
+	 */
+	if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+		if (pgprot)
+			*pgprot = __pgprot(prot);
+		return 0;
+	}
+	if (is_cow_mapping(vma->vm_flags)) {
+		if (pgprot)
+			return -EINVAL;
+		*paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		return 0;
+	}
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
 /*
  * track_pfn_copy is called when vma that is covering the pfnmap gets
  * copied through copy_page_range().
@@ -960,20 +992,13 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 int track_pfn_copy(struct vm_area_struct *vma)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
 
 	if (vma->vm_flags & VM_PAT) {
-		/*
-		 * reserve the whole chunk covered by vma. We need the
-		 * starting address and protection from pte.
-		 */
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, &pgprot))
 			return -EINVAL;
-		}
-		pgprot = __pgprot(prot);
+		/* reserve the whole chunk covered by vma. */
 		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
@@ -1048,7 +1073,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 		 unsigned long size, bool mm_wr_locked)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 
 	if (vma && !(vma->vm_flags & VM_PAT))
 		return;
@@ -1056,11 +1080,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	/* free the chunk starting from pfn or the whole chunk */
 	paddr = (resource_size_t)pfn << PAGE_SHIFT;
 	if (!paddr && !size) {
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, NULL))
 			return;
-		}
-
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index bda9f12983..135bb594df 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -684,7 +684,7 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 		return NULL;
 
 	*level = PG_LEVEL_1G;
-	if (pud_large(*pud) || !pud_present(*pud))
+	if (pud_leaf(*pud) || !pud_present(*pud))
 		return (pte_t *)pud;
 
 	pmd = pmd_offset(pud, address);
@@ -743,7 +743,7 @@ pmd_t *lookup_pmd_address(unsigned long address)
 		return NULL;
 
 	pud = pud_offset(p4d, address);
-	if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud))
+	if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud))
 		return NULL;
 
 	return pmd_offset(pud, address);
@@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address)
  * areas on 32-bit NUMA systems.  The percpu areas can
  * end up in this kind of memory, for instance.
  *
- * This could be optimized, but it is only intended to be
- * used at initialization time, and keeping it
- * unoptimized should increase the testing coverage for
- * the more obscure platforms.
+ * Note that as long as the PTEs are well-formed with correct PFNs, this
+ * works without checking the PRESENT bit in the leaf PTE.  This is unlike
+ * the similar vmalloc_to_page() and derivatives.  Callers may depend on
+ * this behavior.
+ *
+ * This could be optimized, but it is only used in paths that are not perf
+ * sensitive, and keeping it unoptimized should increase the testing coverage
+ * for the more obscure platforms.
  */
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
@@ -1274,7 +1278,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end)
 	 */
 	while (end - start >= PUD_SIZE) {
 
-		if (pud_large(*pud))
+		if (pud_leaf(*pud))
 			pud_clear(pud);
 		else
 			unmap_pmd_range(pud, start, start + PUD_SIZE);
@@ -1621,7 +1625,7 @@ repeat:
 
 		/*
 		 * We need to keep the pfn from the existing PTE,
-		 * after all we're only going to change it's attributes
+		 * after all we're only going to change its attributes
 		 * not the memory it points to
 		 */
 		new_pte = pfn_pte(pfn, new_prot);
@@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn)
 	return rc;
 }
 
-static int set_memory_p(unsigned long *addr, int numpages)
-{
-	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
-}
-
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)
 {
 	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
 
-	return set_memory_p(&addr, 1);
+	return set_memory_p(addr, 1);
 }
 EXPORT_SYMBOL_GPL(clear_mce_nospec);
 #endif /* CONFIG_X86_64 */
@@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages)
 					CPA_NO_CHECK_ALIAS, NULL);
 }
 
+int set_memory_p(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
@@ -2447,7 +2451,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 	/*
 	 * The typical sequence for unmapping is to find a pte through
 	 * lookup_address_in_pgd() (ideally, it should never return NULL because
-	 * the address is already mapped) and change it's protections. As pfn is
+	 * the address is already mapped) and change its protections. As pfn is
 	 * the *target* of a mapping, it's not useful while unmapping.
 	 */
 	struct cpa_data cpa = {