mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>,
	Matthew Wilcox <willy@infradead.org>, Guo Ren <guoren@kernel.org>,
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	Heiko Carstens <hca@linux.ibm.com>,
	Vasily Gorbik <gor@linux.ibm.com>,
	Alexander Gordeev <agordeev@linux.ibm.com>,
	Christian Borntraeger <borntraeger@linux.ibm.com>,
	Sven Schnelle <svens@linux.ibm.com>,
	"David S . Miller" <davem@davemloft.net>,
	Andreas Larsson <andreas@gaisler.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Dan Williams <dan.j.williams@intel.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	Dave Jiang <dave.jiang@intel.com>,
	Nicolas Pitre <nico@fluxnic.net>,
	Muchun Song <muchun.song@linux.dev>,
	Oscar Salvador <osalvador@suse.de>,
	David Hildenbrand <david@redhat.com>,
	Konstantin Komarov <almaz.alexandrovich@paragon-software.com>,
	Baoquan He <bhe@redhat.com>, Vivek Goyal <vgoyal@redhat.com>,
	Dave Young <dyoung@redhat.com>, Tony Luck <tony.luck@intel.com>,
	Reinette Chatre <reinette.chatre@intel.com>,
	Dave Martin <Dave.Martin@arm.com>,
	James Morse <james.morse@arm.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christian Brauner <brauner@kernel.org>, Jan Kara <jack@suse.cz>,
	"Liam R . Howlett" <Liam.Howlett@oracle.com>,
	Vlastimil Babka <vbabka@suse.cz>, Mike Rapoport <rppt@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Michal Hocko <mhocko@suse.com>, Hugh Dickins <hughd@google.com>,
	Baolin Wang <baolin.wang@linux.alibaba.com>,
	Uladzislau Rezki <urezki@gmail.com>,
	Dmitry Vyukov <dvyukov@google.com>,
	Andrey Konovalov <andreyknvl@gmail.com>,
	Jann Horn <jannh@google.com>, Pedro Falcato <pfalcato@suse.de>,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, linux-csky@vger.kernel.org,
	linux-mips@vger.kernel.org, linux-s390@vger.kernel.org,
	sparclinux@vger.kernel.org, nvdimm@lists.linux.dev,
	linux-cxl@vger.kernel.org, linux-mm@kvack.org,
	ntfs3@lists.linux.dev, kexec@lists.infradead.org,
	kasan-dev@googlegroups.com, Jason Gunthorpe <jgg@nvidia.com>
Subject: [PATCH 13/16] mm: update cramfs to use mmap_prepare, mmap_complete
Date: Mon,  8 Sep 2025 12:10:44 +0100	[thread overview]
Message-ID: <e2fb74b295b60bcb591aba5cc521cbe1b7901cd3.1757329751.git.lorenzo.stoakes@oracle.com> (raw)
In-Reply-To: <cover.1757329751.git.lorenzo.stoakes@oracle.com>

We thread the state through the mmap_context, allowing for both PFN map and
mixed mapped pre-population.

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
 fs/cramfs/inode.c | 134 +++++++++++++++++++++++++++++++---------------
 1 file changed, 92 insertions(+), 42 deletions(-)

diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index b002e9b734f9..11a11213304d 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -59,6 +59,12 @@ static const struct address_space_operations cramfs_aops;
 
 static DEFINE_MUTEX(read_mutex);
 
+/* How should the mapping be completed? */
+enum cramfs_mmap_state {
+	NO_PREPOPULATE,
+	PREPOPULATE_PFNMAP,
+	PREPOPULATE_MIXEDMAP,
+};
 
 /* These macros may change in future, to provide better st_ino semantics. */
 #define OFFSET(x)	((x)->i_ino)
@@ -342,34 +348,89 @@ static bool cramfs_last_page_is_shared(struct inode *inode)
 	return memchr_inv(tail_data, 0, PAGE_SIZE - partial) ? true : false;
 }
 
-static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
+static int cramfs_physmem_mmap_complete(struct file *file, struct vm_area_struct *vma,
+					const void *context)
 {
 	struct inode *inode = file_inode(file);
 	struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb);
-	unsigned int pages, max_pages, offset;
 	unsigned long address, pgoff = vma->vm_pgoff;
-	char *bailout_reason;
-	int ret;
+	unsigned int pages, offset;
+	enum cramfs_mmap_state mmap_state = (enum cramfs_mmap_state)context;
+	int ret = 0;
 
-	ret = generic_file_readonly_mmap(file, vma);
-	if (ret)
-		return ret;
+	if (mmap_state == NO_PREPOPULATE)
+		return 0;
+
+	offset = cramfs_get_block_range(inode, pgoff, &pages);
+	address = sbi->linear_phys_addr + offset;
 
 	/*
 	 * Now try to pre-populate ptes for this vma with a direct
 	 * mapping avoiding memory allocation when possible.
 	 */
 
+	if (mmap_state == PREPOPULATE_PFNMAP) {
+		/*
+		 * The entire vma is mappable. remap_pfn_range() will
+		 * make it distinguishable from a non-direct mapping
+		 * in /proc/<pid>/maps by substituting the file offset
+		 * with the actual physical address.
+		 */
+		ret = remap_pfn_range_complete(vma, vma->vm_start, address >> PAGE_SHIFT,
+				pages * PAGE_SIZE, vma->vm_page_prot);
+	} else {
+		/*
+		 * Let's create a mixed map if we can't map it all.
+		 * The normal paging machinery will take care of the
+		 * unpopulated ptes via cramfs_read_folio().
+		 */
+		int i;
+
+		for (i = 0; i < pages && !ret; i++) {
+			vm_fault_t vmf;
+			unsigned long off = i * PAGE_SIZE;
+
+			vmf = vmf_insert_mixed(vma, vma->vm_start + off,
+					address + off);
+			if (vmf & VM_FAULT_ERROR)
+				ret = vm_fault_to_errno(vmf, 0);
+		}
+	}
+
+	if (!ret)
+		pr_debug("mapped %pD[%lu] at 0x%08lx (%u/%lu pages) "
+			 "to vma 0x%08lx, page_prot 0x%llx\n", file,
+			 pgoff, address, pages, vma_pages(vma), vma->vm_start,
+			 (unsigned long long)pgprot_val(vma->vm_page_prot));
+	return ret;
+}
+
+static int cramfs_physmem_mmap_prepare(struct vm_area_desc *desc)
+{
+	struct file *file = desc->file;
+	struct inode *inode = file_inode(file);
+	struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb);
+	unsigned int pages, max_pages, offset, mapped_pages;
+	unsigned long address, pgoff = desc->pgoff;
+	enum cramfs_mmap_state mmap_state;
+	char *bailout_reason;
+	int ret;
+
+	ret = generic_file_readonly_mmap_prepare(desc);
+	if (ret)
+		return ret;
+
 	/* Could COW work here? */
 	bailout_reason = "vma is writable";
-	if (vma->vm_flags & VM_WRITE)
+	if (desc->vm_flags & VM_WRITE)
 		goto bailout;
 
 	max_pages = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	bailout_reason = "beyond file limit";
 	if (pgoff >= max_pages)
 		goto bailout;
-	pages = min(vma_pages(vma), max_pages - pgoff);
+	mapped_pages = vma_desc_pages(desc);
+	pages = min(mapped_pages, max_pages - pgoff);
 
 	offset = cramfs_get_block_range(inode, pgoff, &pages);
 	bailout_reason = "unsuitable block layout";
@@ -391,41 +452,23 @@ static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
 		goto bailout;
 	}
 
-	if (pages == vma_pages(vma)) {
-		/*
-		 * The entire vma is mappable. remap_pfn_range() will
-		 * make it distinguishable from a non-direct mapping
-		 * in /proc/<pid>/maps by substituting the file offset
-		 * with the actual physical address.
-		 */
-		ret = remap_pfn_range(vma, vma->vm_start, address >> PAGE_SHIFT,
-				      pages * PAGE_SIZE, vma->vm_page_prot);
+	if (mapped_pages == pages)
+		mmap_state = PREPOPULATE_PFNMAP;
+	else
+		mmap_state = PREPOPULATE_MIXEDMAP;
+	desc->mmap_context = (void *)mmap_state;
+
+	if (mmap_state == PREPOPULATE_PFNMAP) {
+		/* No CoW allowed, so no need to provide PFN. */
+		remap_pfn_range_prepare(desc, 0);
 	} else {
-		/*
-		 * Let's create a mixed map if we can't map it all.
-		 * The normal paging machinery will take care of the
-		 * unpopulated ptes via cramfs_read_folio().
-		 */
-		int i;
-		vm_flags_set(vma, VM_MIXEDMAP);
-		for (i = 0; i < pages && !ret; i++) {
-			vm_fault_t vmf;
-			unsigned long off = i * PAGE_SIZE;
-			vmf = vmf_insert_mixed(vma, vma->vm_start + off,
-					address + off);
-			if (vmf & VM_FAULT_ERROR)
-				ret = vm_fault_to_errno(vmf, 0);
-		}
+		desc->vm_flags |= VM_MIXEDMAP;
 	}
 
-	if (!ret)
-		pr_debug("mapped %pD[%lu] at 0x%08lx (%u/%lu pages) "
-			 "to vma 0x%08lx, page_prot 0x%llx\n", file,
-			 pgoff, address, pages, vma_pages(vma), vma->vm_start,
-			 (unsigned long long)pgprot_val(vma->vm_page_prot));
-	return ret;
+	return 0;
 
 bailout:
+	desc->mmap_context = (void *)NO_PREPOPULATE;
 	pr_debug("%pD[%lu]: direct mmap impossible: %s\n",
 		 file, pgoff, bailout_reason);
 	/* Didn't manage any direct map, but normal paging is still possible */
@@ -434,9 +477,15 @@ static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
 
 #else /* CONFIG_MMU */
 
-static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
+static int cramfs_physmem_mmap_prepare(struct vm_area_desc *desc)
 {
-	return is_nommu_shared_mapping(vma->vm_flags) ? 0 : -ENOSYS;
+	return is_nommu_shared_mapping(desc->vm_flags) ? 0 : -ENOSYS;
+}
+
+static int cramfs_physmem_mmap_complete(struct file *file,
+					struct vm_area_struct *vma)
+{
+	return 0;
 }
 
 static unsigned long cramfs_physmem_get_unmapped_area(struct file *file,
@@ -474,7 +523,8 @@ static const struct file_operations cramfs_physmem_fops = {
 	.llseek			= generic_file_llseek,
 	.read_iter		= generic_file_read_iter,
 	.splice_read		= filemap_splice_read,
-	.mmap			= cramfs_physmem_mmap,
+	.mmap_prepare		= cramfs_physmem_mmap_prepare,
+	.mmap_complete		= cramfs_physmem_mmap_complete,
 #ifndef CONFIG_MMU
 	.get_unmapped_area	= cramfs_physmem_get_unmapped_area,
 	.mmap_capabilities	= cramfs_physmem_mmap_capabilities,
-- 
2.51.0


  parent reply	other threads:[~2025-09-08 11:12 UTC|newest]

Thread overview: 84+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-08 11:10 [PATCH 00/16] expand mmap_prepare functionality, port more users Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 01/16] mm/shmem: update shmem to use mmap_prepare Lorenzo Stoakes
2025-09-08 14:59   ` David Hildenbrand
2025-09-08 15:28     ` Lorenzo Stoakes
2025-09-09  3:19   ` Baolin Wang
2025-09-09  9:08     ` Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 02/16] device/dax: update devdax " Lorenzo Stoakes
2025-09-08 15:03   ` David Hildenbrand
2025-09-08 15:28     ` Lorenzo Stoakes
2025-09-08 15:31       ` David Hildenbrand
2025-09-08 11:10 ` [PATCH 03/16] mm: add vma_desc_size(), vma_desc_pages() helpers Lorenzo Stoakes
2025-09-08 12:51   ` Jason Gunthorpe
2025-09-08 13:12     ` Lorenzo Stoakes
2025-09-08 13:32       ` Jason Gunthorpe
2025-09-08 14:09         ` Lorenzo Stoakes
2025-09-08 14:20           ` Jason Gunthorpe
2025-09-08 14:47             ` Lorenzo Stoakes
2025-09-08 15:07               ` David Hildenbrand
2025-09-08 15:35                 ` Lorenzo Stoakes
2025-09-08 17:30                   ` David Hildenbrand
2025-09-09  9:21                     ` Lorenzo Stoakes
2025-09-08 15:16               ` Jason Gunthorpe
2025-09-08 15:24                 ` David Hildenbrand
2025-09-08 15:33                   ` Jason Gunthorpe
2025-09-08 15:46                     ` David Hildenbrand
2025-09-08 15:50                       ` David Hildenbrand
2025-09-08 15:56                         ` Jason Gunthorpe
2025-09-08 17:36                           ` David Hildenbrand
2025-09-08 20:24                             ` Lorenzo Stoakes
2025-09-08 15:33                   ` Lorenzo Stoakes
2025-09-08 15:10   ` David Hildenbrand
2025-09-08 11:10 ` [PATCH 04/16] relay: update relay to use mmap_prepare Lorenzo Stoakes
2025-09-08 15:15   ` David Hildenbrand
2025-09-08 15:29     ` Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 05/16] mm/vma: rename mmap internal functions to avoid confusion Lorenzo Stoakes
2025-09-08 15:19   ` David Hildenbrand
2025-09-08 15:31     ` Lorenzo Stoakes
2025-09-08 17:38       ` David Hildenbrand
2025-09-09  9:04         ` Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 06/16] mm: introduce the f_op->mmap_complete, mmap_abort hooks Lorenzo Stoakes
2025-09-08 12:55   ` Jason Gunthorpe
2025-09-08 13:19     ` Lorenzo Stoakes
2025-09-08 15:27   ` David Hildenbrand
2025-09-09  9:13     ` Lorenzo Stoakes
2025-09-09  9:26       ` David Hildenbrand
2025-09-09  9:37         ` Lorenzo Stoakes
2025-09-09 16:43           ` Suren Baghdasaryan
2025-09-09 17:36             ` Lorenzo Stoakes
2025-09-09 16:44   ` Suren Baghdasaryan
2025-09-08 11:10 ` [PATCH 07/16] doc: update porting, vfs documentation for mmap_[complete, abort] Lorenzo Stoakes
2025-09-08 23:17   ` Randy Dunlap
2025-09-09  9:02     ` Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 08/16] mm: add remap_pfn_range_prepare(), remap_pfn_range_complete() Lorenzo Stoakes
2025-09-08 13:00   ` Jason Gunthorpe
2025-09-08 13:27     ` Lorenzo Stoakes
2025-09-08 13:35       ` Jason Gunthorpe
2025-09-08 14:18         ` Lorenzo Stoakes
2025-09-08 16:03           ` Jason Gunthorpe
2025-09-08 16:07             ` Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 09/16] mm: introduce io_remap_pfn_range_prepare, complete Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 10/16] mm/hugetlb: update hugetlbfs to use mmap_prepare, mmap_complete Lorenzo Stoakes
2025-09-08 13:11   ` Jason Gunthorpe
2025-09-08 13:37     ` Lorenzo Stoakes
2025-09-08 13:52       ` Jason Gunthorpe
2025-09-08 14:19         ` Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 11/16] mm: update mem char driver " Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 12/16] mm: update resctl to use mmap_prepare, mmap_complete, mmap_abort Lorenzo Stoakes
2025-09-08 13:24   ` Jason Gunthorpe
2025-09-08 13:40     ` Lorenzo Stoakes
2025-09-08 14:27     ` Lorenzo Stoakes
2025-09-08 11:10 ` Lorenzo Stoakes [this message]
2025-09-08 13:27   ` [PATCH 13/16] mm: update cramfs to use mmap_prepare, mmap_complete Jason Gunthorpe
2025-09-08 13:44     ` Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 14/16] fs/proc: add proc_mmap_[prepare, complete] hooks for procfs Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 15/16] fs/proc: update vmcore to use .proc_mmap_[prepare, complete] Lorenzo Stoakes
2025-09-08 11:10 ` [PATCH 16/16] kcov: update kcov to use mmap_prepare, mmap_complete Lorenzo Stoakes
2025-09-08 13:30   ` Jason Gunthorpe
2025-09-08 13:47     ` Lorenzo Stoakes
2025-09-08 13:27 ` [PATCH 00/16] expand mmap_prepare functionality, port more users Jan Kara
2025-09-08 14:48   ` Lorenzo Stoakes
2025-09-08 15:04     ` Jason Gunthorpe
2025-09-08 15:15       ` Lorenzo Stoakes
2025-09-09  8:31 ` Alexander Gordeev
2025-09-09  8:59   ` Lorenzo Stoakes

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e2fb74b295b60bcb591aba5cc521cbe1b7901cd3.1757329751.git.lorenzo.stoakes@oracle.com \
    --to=lorenzo.stoakes@oracle.com \
    --cc=Dave.Martin@arm.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=agordeev@linux.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=almaz.alexandrovich@paragon-software.com \
    --cc=andreas@gaisler.com \
    --cc=andreyknvl@gmail.com \
    --cc=arnd@arndb.de \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=bhe@redhat.com \
    --cc=borntraeger@linux.ibm.com \
    --cc=brauner@kernel.org \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=davem@davemloft.net \
    --cc=david@redhat.com \
    --cc=dvyukov@google.com \
    --cc=dyoung@redhat.com \
    --cc=gor@linux.ibm.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=guoren@kernel.org \
    --cc=hca@linux.ibm.com \
    --cc=hughd@google.com \
    --cc=jack@suse.cz \
    --cc=james.morse@arm.com \
    --cc=jannh@google.com \
    --cc=jgg@nvidia.com \
    --cc=kasan-dev@googlegroups.com \
    --cc=kexec@lists.infradead.org \
    --cc=linux-csky@vger.kernel.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mips@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=mhocko@suse.com \
    --cc=muchun.song@linux.dev \
    --cc=nico@fluxnic.net \
    --cc=ntfs3@lists.linux.dev \
    --cc=nvdimm@lists.linux.dev \
    --cc=osalvador@suse.de \
    --cc=pfalcato@suse.de \
    --cc=reinette.chatre@intel.com \
    --cc=rppt@kernel.org \
    --cc=sparclinux@vger.kernel.org \
    --cc=surenb@google.com \
    --cc=svens@linux.ibm.com \
    --cc=tony.luck@intel.com \
    --cc=tsbogend@alpha.franken.de \
    --cc=urezki@gmail.com \
    --cc=vbabka@suse.cz \
    --cc=vgoyal@redhat.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=vishal.l.verma@intel.com \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®