mm: device exclusive memory access

Some devices require exclusive write access to shared virtual memory (SVM)
ranges to perform atomic operations on that memory.  This requires CPU
page tables to be updated to deny access whilst atomic operations are
occurring.

In order to do this introduce a new swap entry type
(SWP_DEVICE_EXCLUSIVE).  When a SVM range needs to be marked for exclusive
access by a device all page table mappings for the particular range are
replaced with device exclusive swap entries.  This causes any CPU access
to the page to result in a fault.

Faults are resovled by replacing the faulting entry with the original
mapping.  This results in MMU notifiers being called which a driver uses
to update access permissions such as revoking atomic access.  After
notifiers have been called the device will no longer have exclusive access
to the region.

Walking of the page tables to find the target pages is handled by
get_user_pages() rather than a direct page table walk.  A direct page
table walk similar to what migrate_vma_collect()/unmap() does could also
have been utilised.  However this resulted in more code similar in
functionality to what get_user_pages() provides as page faulting is
required to make the PTEs present and to break COW.

[dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()]
  Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda

Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 328 insertions, 7 deletions

diff --git a/mm/hmm.c b/mm/hmm.c
index 11df3ca30b82..fad6be2bf072 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -26,6 +26,8 @@
 #include <linux/mmu_notifier.h>
 #include <linux/memory_hotplug.h>
 
+#include "internal.h"
+
 struct hmm_vma_walk {
 	struct hmm_range	*range;
 	unsigned long		last;
@@ -271,6 +273,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		if (!non_swap_entry(entry))
 			goto fault;
 
+		if (is_device_exclusive_entry(entry))
+			goto fault;
+
 		if (is_migration_entry(entry)) {
 			pte_unmap(ptep);
 			hmm_vma_walk->last = addr;
diff --git a/mm/memory.c b/mm/memory.c
index 75feddbf0190..747a01d495f2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -699,6 +699,68 @@ out:
 }
 #endif
 
+static void restore_exclusive_pte(struct vm_area_struct *vma,
+				  struct page *page, unsigned long address,
+				  pte_t *ptep)
+{
+	pte_t pte;
+	swp_entry_t entry;
+
+	pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
+	if (pte_swp_soft_dirty(*ptep))
+		pte = pte_mksoft_dirty(pte);
+
+	entry = pte_to_swp_entry(*ptep);
+	if (pte_swp_uffd_wp(*ptep))
+		pte = pte_mkuffd_wp(pte);
+	else if (is_writable_device_exclusive_entry(entry))
+		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
+
+	set_pte_at(vma->vm_mm, address, ptep, pte);
+
+	/*
+	 * No need to take a page reference as one was already
+	 * created when the swap entry was made.
+	 */
+	if (PageAnon(page))
+		page_add_anon_rmap(page, vma, address, false);
+	else
+		/*
+		 * Currently device exclusive access only supports anonymous
+		 * memory so the entry shouldn't point to a filebacked page.
+		 */
+		WARN_ON_ONCE(!PageAnon(page));
+
+	if (vma->vm_flags & VM_LOCKED)
+		mlock_vma_page(page);
+
+	/*
+	 * No need to invalidate - it was non-present before. However
+	 * secondary CPUs may have mappings that need invalidating.
+	 */
+	update_mmu_cache(vma, address, ptep);
+}
+
+/*
+ * Tries to restore an exclusive pte if the page lock can be acquired without
+ * sleeping.
+ */
+static int
+try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma,
+			unsigned long addr)
+{
+	swp_entry_t entry = pte_to_swp_entry(*src_pte);
+	struct page *page = pfn_swap_entry_to_page(entry);
+
+	if (trylock_page(page)) {
+		restore_exclusive_pte(vma, page, addr, src_pte);
+		unlock_page(page);
+		return 0;
+	}
+
+	return -EBUSY;
+}
+
 /*
  * copy one vm_area from one task to the other. Assumes the page tables
  * already present in the new task to be cleared in the whole range
@@ -780,6 +842,17 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 				pte = pte_swp_mkuffd_wp(pte);
 			set_pte_at(src_mm, addr, src_pte, pte);
 		}
+	} else if (is_device_exclusive_entry(entry)) {
+		/*
+		 * Make device exclusive entries present by restoring the
+		 * original entry then copying as for a present pte. Device
+		 * exclusive entries currently only support private writable
+		 * (ie. COW) mappings.
+		 */
+		VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags));
+		if (try_restore_exclusive_pte(src_pte, src_vma, addr))
+			return -EBUSY;
+		return -ENOENT;
 	}
 	if (!userfaultfd_wp(dst_vma))
 		pte = pte_swp_clear_uffd_wp(pte);
@@ -980,9 +1053,18 @@ again:
 			if (ret == -EIO) {
 				entry = pte_to_swp_entry(*src_pte);
 				break;
+			} else if (ret == -EBUSY) {
+				break;
+			} else if (!ret) {
+				progress += 8;
+				continue;
 			}
-			progress += 8;
-			continue;
+
+			/*
+			 * Device exclusive entry restored, continue by copying
+			 * the now present pte.
+			 */
+			WARN_ON_ONCE(ret != -ENOENT);
 		}
 		/* copy_present_pte() will clear `*prealloc' if consumed */
 		ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte,
@@ -1020,6 +1102,8 @@ again:
 			goto out;
 		}
 		entry.val = 0;
+	} else if (ret == -EBUSY) {
+		goto out;
 	} else if (ret ==  -EAGAIN) {
 		prealloc = page_copy_prealloc(src_mm, src_vma, addr);
 		if (!prealloc)
@@ -1287,7 +1371,8 @@ again:
 		}
 
 		entry = pte_to_swp_entry(ptent);
-		if (is_device_private_entry(entry)) {
+		if (is_device_private_entry(entry) ||
+		    is_device_exclusive_entry(entry)) {
 			struct page *page = pfn_swap_entry_to_page(entry);
 
 			if (unlikely(details && details->check_mapping)) {
@@ -1303,7 +1388,10 @@ again:
 
 			pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 			rss[mm_counter(page)]--;
-			page_remove_rmap(page, false);
+
+			if (is_device_private_entry(entry))
+				page_remove_rmap(page, false);
+
 			put_page(page);
 			continue;
 		}
@@ -3352,6 +3440,34 @@ void unmap_mapping_range(struct address_space *mapping,
 EXPORT_SYMBOL(unmap_mapping_range);
 
 /*
+ * Restore a potential device exclusive pte to a working pte entry
+ */
+static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
+{
+	struct page *page = vmf->page;
+	struct vm_area_struct *vma = vmf->vma;
+	struct mmu_notifier_range range;
+
+	if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags))
+		return VM_FAULT_RETRY;
+	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
+				vma->vm_mm, vmf->address & PAGE_MASK,
+				(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
+	mmu_notifier_invalidate_range_start(&range);
+
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
+				&vmf->ptl);
+	if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
+		restore_exclusive_pte(vma, page, vmf->address, vmf->pte);
+
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
+	unlock_page(page);
+
+	mmu_notifier_invalidate_range_end(&range);
+	return 0;
+}
+
+/*
  * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with pte unmapped and unlocked.
@@ -3379,6 +3495,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		if (is_migration_entry(entry)) {
 			migration_entry_wait(vma->vm_mm, vmf->pmd,
 					     vmf->address);
+		} else if (is_device_exclusive_entry(entry)) {
+			vmf->page = pfn_swap_entry_to_page(entry);
+			ret = remove_device_exclusive_entry(vmf);
 		} else if (is_device_private_entry(entry)) {
 			vmf->page = pfn_swap_entry_to_page(entry);
 			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ee5961888e70..883e2cc85cad 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -165,6 +165,14 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);
+			} else if (is_writable_device_exclusive_entry(entry)) {
+				entry = make_readable_device_exclusive_entry(
+							swp_offset(entry));
+				newpte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(oldpte))
+					newpte = pte_swp_mksoft_dirty(newpte);
+				if (pte_swp_uffd_wp(oldpte))
+					newpte = pte_swp_mkuffd_wp(newpte);
 			} else {
 				newpte = oldpte;
 			}
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 4df6093e759b..f7b331081791 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -41,7 +41,8 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
 
 				/* Handle un-addressable ZONE_DEVICE memory */
 				entry = pte_to_swp_entry(*pvmw->pte);
-				if (!is_device_private_entry(entry))
+				if (!is_device_private_entry(entry) &&
+				    !is_device_exclusive_entry(entry))
 					return false;
 			} else if (!pte_present(*pvmw->pte))
 				return false;
@@ -93,7 +94,8 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 			return false;
 		entry = pte_to_swp_entry(*pvmw->pte);
 
-		if (!is_migration_entry(entry))
+		if (!is_migration_entry(entry) &&
+		    !is_device_exclusive_entry(entry))
 			return false;
 
 		pfn = swp_offset(entry);
@@ -102,7 +104,8 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 
 		/* Handle un-addressable ZONE_DEVICE memory */
 		entry = pte_to_swp_entry(*pvmw->pte);
-		if (!is_device_private_entry(entry))
+		if (!is_device_private_entry(entry) &&
+		    !is_device_exclusive_entry(entry))
 			return false;
 
 		pfn = swp_offset(entry);
diff --git a/mm/rmap.c b/mm/rmap.c
index b922c7074cdd..37c24672125c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2028,6 +2028,192 @@ void page_mlock(struct page *page)
 	rmap_walk(page, &rwc);
 }
 
+#ifdef CONFIG_DEVICE_PRIVATE
+struct make_exclusive_args {
+	struct mm_struct *mm;
+	unsigned long address;
+	void *owner;
+	bool valid;
+};
+
+static bool page_make_device_exclusive_one(struct page *page,
+		struct vm_area_struct *vma, unsigned long address, void *priv)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+		.address = address,
+	};
+	struct make_exclusive_args *args = priv;
+	pte_t pteval;
+	struct page *subpage;
+	bool ret = true;
+	struct mmu_notifier_range range;
+	swp_entry_t entry;
+	pte_t swp_pte;
+
+	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
+				      vma->vm_mm, address, min(vma->vm_end,
+				      address + page_size(page)), args->owner);
+	mmu_notifier_invalidate_range_start(&range);
+
+	while (page_vma_mapped_walk(&pvmw)) {
+		/* Unexpected PMD-mapped THP? */
+		VM_BUG_ON_PAGE(!pvmw.pte, page);
+
+		if (!pte_present(*pvmw.pte)) {
+			ret = false;
+			page_vma_mapped_walk_done(&pvmw);
+			break;
+		}
+
+		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		address = pvmw.address;
+
+		/* Nuke the page table entry. */
+		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+		pteval = ptep_clear_flush(vma, address, pvmw.pte);
+
+		/* Move the dirty bit to the page. Now the pte is gone. */
+		if (pte_dirty(pteval))
+			set_page_dirty(page);
+
+		/*
+		 * Check that our target page is still mapped at the expected
+		 * address.
+		 */
+		if (args->mm == mm && args->address == address &&
+		    pte_write(pteval))
+			args->valid = true;
+
+		/*
+		 * Store the pfn of the page in a special migration
+		 * pte. do_swap_page() will wait until the migration
+		 * pte is removed and then restart fault handling.
+		 */
+		if (pte_write(pteval))
+			entry = make_writable_device_exclusive_entry(
+							page_to_pfn(subpage));
+		else
+			entry = make_readable_device_exclusive_entry(
+							page_to_pfn(subpage));
+		swp_pte = swp_entry_to_pte(entry);
+		if (pte_soft_dirty(pteval))
+			swp_pte = pte_swp_mksoft_dirty(swp_pte);
+		if (pte_uffd_wp(pteval))
+			swp_pte = pte_swp_mkuffd_wp(swp_pte);
+
+		set_pte_at(mm, address, pvmw.pte, swp_pte);
+
+		/*
+		 * There is a reference on the page for the swap entry which has
+		 * been removed, so shouldn't take another.
+		 */
+		page_remove_rmap(subpage, false);
+	}
+
+	mmu_notifier_invalidate_range_end(&range);
+
+	return ret;
+}
+
+/**
+ * page_make_device_exclusive - mark the page exclusively owned by a device
+ * @page: the page to replace page table entries for
+ * @mm: the mm_struct where the page is expected to be mapped
+ * @address: address where the page is expected to be mapped
+ * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks
+ *
+ * Tries to remove all the page table entries which are mapping this page and
+ * replace them with special device exclusive swap entries to grant a device
+ * exclusive access to the page. Caller must hold the page lock.
+ *
+ * Returns false if the page is still mapped, or if it could not be unmapped
+ * from the expected address. Otherwise returns true (success).
+ */
+static bool page_make_device_exclusive(struct page *page, struct mm_struct *mm,
+				unsigned long address, void *owner)
+{
+	struct make_exclusive_args args = {
+		.mm = mm,
+		.address = address,
+		.owner = owner,
+		.valid = false,
+	};
+	struct rmap_walk_control rwc = {
+		.rmap_one = page_make_device_exclusive_one,
+		.done = page_not_mapped,
+		.anon_lock = page_lock_anon_vma_read,
+		.arg = &args,
+	};
+
+	/*
+	 * Restrict to anonymous pages for now to avoid potential writeback
+	 * issues. Also tail pages shouldn't be passed to rmap_walk so skip
+	 * those.
+	 */
+	if (!PageAnon(page) || PageTail(page))
+		return false;
+
+	rmap_walk(page, &rwc);
+
+	return args.valid && !page_mapcount(page);
+}
+
+/**
+ * make_device_exclusive_range() - Mark a range for exclusive use by a device
+ * @mm: mm_struct of assoicated target process
+ * @start: start of the region to mark for exclusive device access
+ * @end: end address of region
+ * @pages: returns the pages which were successfully marked for exclusive access
+ * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering
+ *
+ * Returns: number of pages found in the range by GUP. A page is marked for
+ * exclusive access only if the page pointer is non-NULL.
+ *
+ * This function finds ptes mapping page(s) to the given address range, locks
+ * them and replaces mappings with special swap entries preventing userspace CPU
+ * access. On fault these entries are replaced with the original mapping after
+ * calling MMU notifiers.
+ *
+ * A driver using this to program access from a device must use a mmu notifier
+ * critical section to hold a device specific lock during programming. Once
+ * programming is complete it should drop the page lock and reference after
+ * which point CPU access to the page will revoke the exclusive access.
+ */
+int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, struct page **pages,
+				void *owner)
+{
+	long npages = (end - start) >> PAGE_SHIFT;
+	long i;
+
+	npages = get_user_pages_remote(mm, start, npages,
+				       FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD,
+				       pages, NULL, NULL);
+	if (npages < 0)
+		return npages;
+
+	for (i = 0; i < npages; i++, start += PAGE_SIZE) {
+		if (!trylock_page(pages[i])) {
+			put_page(pages[i]);
+			pages[i] = NULL;
+			continue;
+		}
+
+		if (!page_make_device_exclusive(pages[i], mm, start, owner)) {
+			unlock_page(pages[i]);
+			put_page(pages[i]);
+			pages[i] = NULL;
+		}
+	}
+
+	return npages;
+}
+EXPORT_SYMBOL_GPL(make_device_exclusive_range);
+#endif
+
 void __put_anon_vma(struct anon_vma *anon_vma)
 {
 	struct anon_vma *root = anon_vma->root;