lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220210072828.2930359-27-hch@lst.de>
Date:   Thu, 10 Feb 2022 08:28:27 +0100
From:   Christoph Hellwig <hch@....de>
To:     Andrew Morton <akpm@...ux-foundation.org>,
        Dan Williams <dan.j.williams@...el.com>
Cc:     Felix Kuehling <Felix.Kuehling@....com>,
        Alex Deucher <alexander.deucher@....com>,
        Christian König <christian.koenig@....com>,
        "Pan, Xinhui" <Xinhui.Pan@....com>,
        Ben Skeggs <bskeggs@...hat.com>,
        Karol Herbst <kherbst@...hat.com>,
        Lyude Paul <lyude@...hat.com>, Jason Gunthorpe <jgg@...pe.ca>,
        Alistair Popple <apopple@...dia.com>,
        Logan Gunthorpe <logang@...tatee.com>,
        Ralph Campbell <rcampbell@...dia.com>,
        linux-kernel@...r.kernel.org, amd-gfx@...ts.freedesktop.org,
        dri-devel@...ts.freedesktop.org, nouveau@...ts.freedesktop.org,
        nvdimm@...ts.linux.dev, linux-mm@...ck.org
Subject: [PATCH 26/27] mm/gup: migrate device coherent pages when pinning instead of failing

From: Alistair Popple <apopple@...dia.com>

Currently any attempts to pin a device coherent page will fail. This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.

However this is no reason to fail pinning of these pages. These are
coherent and accessible from the CPU so can be migrated just like
pinning ZONE_MOVABLE pages. So instead of failing all attempts to pin
them first try migrating them out of ZONE_DEVICE.

Signed-off-by: Alistair Popple <apopple@...dia.com>
Acked-by: Felix Kuehling <Felix.Kuehling@....com>
[hch: rebased to the split device memory checks,
      moved migrate_device_page to migrate_device.c]
Signed-off-by: Christoph Hellwig <hch@....de>
---
 mm/gup.c            | 37 ++++++++++++++++++++++++++-----
 mm/internal.h       |  1 +
 mm/migrate_device.c | 53 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 85 insertions(+), 6 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 39b23ad39a7bde..41349b685eafb4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1889,9 +1889,31 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 			ret = -EFAULT;
 			goto unpin_pages;
 		}
+
+		/*
+		 * Device coherent pages are managed by a driver and should not
+		 * be pinned indefinitely as it prevents the driver moving the
+		 * page. So when trying to pin with FOLL_LONGTERM instead try
+		 * to migrate the page out of device memory.
+		 */
 		if (is_device_coherent_page(head)) {
-			ret = -EFAULT;
-			goto unpin_pages;
+			WARN_ON_ONCE(PageCompound(head));
+
+			/*
+			 * Migration will fail if the page is pinned, so convert
+			 * the pin on the source page to a normal reference.
+			 */
+			if (gup_flags & FOLL_PIN) {
+				get_page(head);
+				unpin_user_page(head);
+			}
+
+			pages[i] = migrate_device_page(head, gup_flags);
+			if (!pages[i]) {
+				ret = -EBUSY;
+				goto unpin_pages;
+			}
+			continue;
 		}
 
 		if (is_pinnable_page(head))
@@ -1931,10 +1953,13 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 	return nr_pages;
 
 unpin_pages:
-	if (gup_flags & FOLL_PIN) {
-		unpin_user_pages(pages, nr_pages);
-	} else {
-		for (i = 0; i < nr_pages; i++)
+	for (i = 0; i < nr_pages; i++) {
+		if (!pages[i])
+			continue;
+
+		if (gup_flags & FOLL_PIN)
+			unpin_user_page(pages[i]);
+		else
 			put_page(pages[i]);
 	}
 
diff --git a/mm/internal.h b/mm/internal.h
index a67222d17e5987..1bded5d7f41a9d 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -719,5 +719,6 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
 		      unsigned long addr, int page_nid, int *flags);
 
 void free_zone_device_page(struct page *page);
+struct page *migrate_device_page(struct page *page, unsigned int gup_flags);
 
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 03e182f9fc7865..3373b535d5c9d9 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -767,3 +767,56 @@ void migrate_vma_finalize(struct migrate_vma *migrate)
 	}
 }
 EXPORT_SYMBOL(migrate_vma_finalize);
+
+/*
+ * Migrate a device coherent page back to normal memory.  The caller should have
+ * a reference on page which will be copied to the new page if migration is
+ * successful or dropped on failure.
+ */
+struct page *migrate_device_page(struct page *page, unsigned int gup_flags)
+{
+	unsigned long src_pfn, dst_pfn = 0;
+	struct migrate_vma args;
+	struct page *dpage;
+
+	lock_page(page);
+	src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE;
+	args.src = &src_pfn;
+	args.dst = &dst_pfn;
+	args.cpages = 1;
+	args.npages = 1;
+	args.vma = NULL;
+	migrate_vma_setup(&args);
+	if (!(src_pfn & MIGRATE_PFN_MIGRATE))
+		return NULL;
+
+	dpage = alloc_pages(GFP_USER | __GFP_NOWARN, 0);
+
+	/*
+	 * get/pin the new page now so we don't have to retry gup after
+	 * migrating. We already have a reference so this should never fail.
+	 */
+	if (dpage && WARN_ON_ONCE(!try_grab_page(dpage, gup_flags))) {
+		__free_pages(dpage, 0);
+		dpage = NULL;
+	}
+
+	if (dpage) {
+		lock_page(dpage);
+		dst_pfn = migrate_pfn(page_to_pfn(dpage));
+	}
+
+	migrate_vma_pages(&args);
+	if (src_pfn & MIGRATE_PFN_MIGRATE)
+		copy_highpage(dpage, page);
+	migrate_vma_finalize(&args);
+	if (dpage && !(src_pfn & MIGRATE_PFN_MIGRATE)) {
+		if (gup_flags & FOLL_PIN)
+			unpin_user_page(dpage);
+		else
+			put_page(dpage);
+		dpage = NULL;
+	}
+
+	return dpage;
+}
-- 
2.30.2

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ