Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/memory.c b/mm/memory.c
index b1ca51a..4bb7c6a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -118,6 +118,18 @@
 					2;
 #endif
 
+#ifndef arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+	/*
+	 * Those arches which don't have hw access flag feature need to
+	 * implement their own helper. By default, "true" means pagefault
+	 * will be hit on old pte.
+	 */
+	return true;
+}
+#endif
+
 static int __init disable_randmaps(char *s)
 {
 	randomize_va_space = 0;
@@ -138,7 +150,7 @@
 	zero_pfn = page_to_pfn(ZERO_PAGE(0));
 	return 0;
 }
-core_initcall(init_zero_pfn);
+early_initcall(init_zero_pfn);
 
 
 #if defined(SPLIT_RSS_COUNTING)
@@ -1153,7 +1165,18 @@
 			else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
 			/* fall through */
+		} else if (details && details->single_page &&
+			   PageTransCompound(details->single_page) &&
+			   next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
+			spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
+			/*
+			 * Take and drop THP pmd lock so that we cannot return
+			 * prematurely, while zap_huge_pmd() has cleared *pmd,
+			 * but not yet decremented compound_mapcount().
+			 */
+			spin_unlock(ptl);
 		}
+
 		/*
 		 * Here there can be other concurrent MADV_DONTNEED or
 		 * trans huge page faults running, and if the pmd is
@@ -1792,11 +1815,11 @@
 			unsigned long addr, unsigned long end,
 			unsigned long pfn, pgprot_t prot)
 {
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	spinlock_t *ptl;
 	int err = 0;
 
-	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
+	mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
 	arch_enter_lazy_mmu_mode();
@@ -1810,7 +1833,7 @@
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(pte - 1, ptl);
+	pte_unmap_unlock(mapped_pte, ptl);
 	return err;
 }
 
@@ -2145,32 +2168,101 @@
 	return same;
 }
 
-static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
+static inline bool cow_user_page(struct page *dst, struct page *src,
+				 struct vm_fault *vmf)
 {
+	bool ret;
+	void *kaddr;
+	void __user *uaddr;
+	bool locked = false;
+	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long addr = vmf->address;
+
 	debug_dma_assert_idle(src);
 
+	if (likely(src)) {
+		copy_user_highpage(dst, src, addr, vma);
+		return true;
+	}
+
 	/*
 	 * If the source page was a PFN mapping, we don't have
 	 * a "struct page" for it. We do a best-effort copy by
 	 * just copying from the original user address. If that
 	 * fails, we just zero-fill it. Live with it.
 	 */
-	if (unlikely(!src)) {
-		void *kaddr = kmap_atomic(dst);
-		void __user *uaddr = (void __user *)(va & PAGE_MASK);
+	kaddr = kmap_atomic(dst);
+	uaddr = (void __user *)(addr & PAGE_MASK);
+
+	/*
+	 * On architectures with software "accessed" bits, we would
+	 * take a double page fault, so mark it accessed here.
+	 */
+	if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
+		pte_t entry;
+
+		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		locked = true;
+		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+			/*
+			 * Other thread has already handled the fault
+			 * and we don't need to do anything. If it's
+			 * not the case, the fault will be triggered
+			 * again on the same address.
+			 */
+			ret = false;
+			goto pte_unlock;
+		}
+
+		entry = pte_mkyoung(vmf->orig_pte);
+		if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
+			update_mmu_cache(vma, addr, vmf->pte);
+	}
+
+	/*
+	 * This really shouldn't fail, because the page is there
+	 * in the page tables. But it might just be unreadable,
+	 * in which case we just give up and fill the result with
+	 * zeroes.
+	 */
+	if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+		if (locked)
+			goto warn;
+
+		/* Re-validate under PTL if the page is still mapped */
+		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		locked = true;
+		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+			/* The PTE changed under us. Retry page fault. */
+			ret = false;
+			goto pte_unlock;
+		}
 
 		/*
-		 * This really shouldn't fail, because the page is there
-		 * in the page tables. But it might just be unreadable,
-		 * in which case we just give up and fill the result with
-		 * zeroes.
+		 * The same page can be mapped back since last copy attampt.
+		 * Try to copy again under PTL.
 		 */
-		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
+		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+			/*
+			 * Give a warn in case there can be some obscure
+			 * use-case
+			 */
+warn:
+			WARN_ON_ONCE(1);
 			clear_page(kaddr);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(dst);
-	} else
-		copy_user_highpage(dst, src, va, vma);
+		}
+	}
+
+	ret = true;
+
+pte_unlock:
+	if (locked)
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+	kunmap_atomic(kaddr);
+	flush_dcache_page(dst);
+
+	return ret;
 }
 
 static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
@@ -2227,10 +2319,11 @@
  *
  * The function expects the page to be locked and unlocks it.
  */
-static void fault_dirty_shared_page(struct vm_area_struct *vma,
-				    struct page *page)
+static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping;
+	struct page *page = vmf->page;
 	bool dirtied;
 	bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite;
 
@@ -2245,16 +2338,30 @@
 	mapping = page_rmapping(page);
 	unlock_page(page);
 
-	if ((dirtied || page_mkwrite) && mapping) {
-		/*
-		 * Some device drivers do not set page.mapping
-		 * but still dirty their pages
-		 */
-		balance_dirty_pages_ratelimited(mapping);
-	}
-
 	if (!page_mkwrite)
 		file_update_time(vma->vm_file);
+
+	/*
+	 * Throttle page dirtying rate down to writeback speed.
+	 *
+	 * mapping may be NULL here because some device drivers do not
+	 * set page.mapping but still dirty their pages
+	 *
+	 * Drop the mmap_sem before waiting on IO, if we can. The file
+	 * is pinning the mapping, as per above.
+	 */
+	if ((dirtied || page_mkwrite) && mapping) {
+		struct file *fpin;
+
+		fpin = maybe_unlock_mmap_for_io(vmf, NULL);
+		balance_dirty_pages_ratelimited(mapping);
+		if (fpin) {
+			fput(fpin);
+			return VM_FAULT_RETRY;
+		}
+	}
+
+	return 0;
 }
 
 /*
@@ -2327,7 +2434,19 @@
 				vmf->address);
 		if (!new_page)
 			goto oom;
-		cow_user_page(new_page, old_page, vmf->address, vma);
+
+		if (!cow_user_page(new_page, old_page, vmf)) {
+			/*
+			 * COW failed, if the fault was solved by other,
+			 * it's fine. If not, userspace would re-fault on
+			 * the same address and we will handle the fault
+			 * from the second attempt.
+			 */
+			put_page(new_page);
+			if (old_page)
+				put_page(old_page);
+			return 0;
+		}
 	}
 
 	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
@@ -2497,6 +2616,7 @@
 	__releases(vmf->ptl)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	vm_fault_t ret = VM_FAULT_WRITE;
 
 	get_page(vmf->page);
 
@@ -2520,10 +2640,10 @@
 		wp_page_reuse(vmf);
 		lock_page(vmf->page);
 	}
-	fault_dirty_shared_page(vma, vmf->page);
+	ret |= fault_dirty_shared_page(vmf);
 	put_page(vmf->page);
 
-	return VM_FAULT_WRITE;
+	return ret;
 }
 
 /*
@@ -2661,6 +2781,36 @@
 }
 
 /**
+ * unmap_mapping_page() - Unmap single page from processes.
+ * @page: The locked page to be unmapped.
+ *
+ * Unmap this page from any userspace process which still has it mmaped.
+ * Typically, for efficiency, the range of nearby pages has already been
+ * unmapped by unmap_mapping_pages() or unmap_mapping_range().  But once
+ * truncation or invalidation holds the lock on a page, it may find that
+ * the page has been remapped again: and then uses unmap_mapping_page()
+ * to unmap it finally.
+ */
+void unmap_mapping_page(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct zap_details details = { };
+
+	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON(PageTail(page));
+
+	details.check_mapping = mapping;
+	details.first_index = page->index;
+	details.last_index = page->index + hpage_nr_pages(page) - 1;
+	details.single_page = page;
+
+	i_mmap_lock_write(mapping);
+	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
+		unmap_mapping_range_tree(&mapping->i_mmap, &details);
+	i_mmap_unlock_write(mapping);
+}
+
+/**
  * unmap_mapping_pages() - Unmap pages from processes.
  * @mapping: The address space containing pages to be unmapped.
  * @start: Index of first page to be unmapped.
@@ -3567,7 +3717,7 @@
 		return ret;
 	}
 
-	fault_dirty_shared_page(vma, vmf->page);
+	ret |= fault_dirty_shared_page(vmf);
 	return ret;
 }
 
@@ -4113,9 +4263,9 @@
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-			    struct mmu_notifier_range *range,
-			    pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
+			  struct mmu_notifier_range *range, pte_t **ptepp,
+			  pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -4180,31 +4330,33 @@
 	return -EINVAL;
 }
 
-static inline int follow_pte(struct mm_struct *mm, unsigned long address,
-			     pte_t **ptepp, spinlock_t **ptlp)
+/**
+ * follow_pte - look up PTE at a user virtual address
+ * @mm: the mm_struct of the target address space
+ * @address: user virtual address
+ * @ptepp: location to store found PTE
+ * @ptlp: location to store the lock for the PTE
+ *
+ * On a successful return, the pointer to the PTE is stored in @ptepp;
+ * the corresponding lock is taken and its location is stored in @ptlp.
+ * The contents of the PTE are only stable until @ptlp is released;
+ * any further use, if any, must be protected against invalidation
+ * with MMU notifiers.
+ *
+ * Only IO mappings and raw PFN mappings are allowed.  The mmap semaphore
+ * should be taken for read.
+ *
+ * KVM uses this function.  While it is arguably less bad than ``follow_pfn``,
+ * it is not a good general-purpose API.
+ *
+ * Return: zero on success, -ve otherwise.
+ */
+int follow_pte(struct mm_struct *mm, unsigned long address,
+	       pte_t **ptepp, spinlock_t **ptlp)
 {
-	int res;
-
-	/* (void) is needed to make gcc happy */
-	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, NULL,
-						    ptepp, NULL, ptlp)));
-	return res;
+	return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp);
 }
-
-int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-		   struct mmu_notifier_range *range,
-		   pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
-{
-	int res;
-
-	/* (void) is needed to make gcc happy */
-	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, range,
-						    ptepp, pmdpp, ptlp)));
-	return res;
-}
-EXPORT_SYMBOL(follow_pte_pmd);
+EXPORT_SYMBOL_GPL(follow_pte);
 
 /**
  * follow_pfn - look up PFN at a user virtual address
@@ -4214,6 +4366,9 @@
  *
  * Only IO mappings and raw PFN mappings are allowed.
  *
+ * This function does not allow the caller to read the permissions
+ * of the PTE.  Do not use it.
+ *
  * Return: zero and the pfn at @pfn on success, -ve otherwise.
  */
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
@@ -4604,17 +4759,19 @@
 	void *page_kaddr;
 	unsigned long i, rc = 0;
 	unsigned long ret_val = pages_per_huge_page * PAGE_SIZE;
+	struct page *subpage = dst_page;
 
-	for (i = 0; i < pages_per_huge_page; i++) {
+	for (i = 0; i < pages_per_huge_page;
+	     i++, subpage = mem_map_next(subpage, dst_page, i)) {
 		if (allow_pagefault)
-			page_kaddr = kmap(dst_page + i);
+			page_kaddr = kmap(subpage);
 		else
-			page_kaddr = kmap_atomic(dst_page + i);
+			page_kaddr = kmap_atomic(subpage);
 		rc = copy_from_user(page_kaddr,
 				(const void __user *)(src + i * PAGE_SIZE),
 				PAGE_SIZE);
 		if (allow_pagefault)
-			kunmap(dst_page + i);
+			kunmap(subpage);
 		else
 			kunmap_atomic(page_kaddr);