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: <4d6038207c6472a0dd3084cbc77e70554fb9de91.1602093760.git.yuleixzhang@tencent.com>
Date:   Thu,  8 Oct 2020 15:54:14 +0800
From:   yulei.kernel@...il.com
To:     akpm@...ux-foundation.org, naoya.horiguchi@....com,
        viro@...iv.linux.org.uk, pbonzini@...hat.com
Cc:     linux-fsdevel@...r.kernel.org, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, xiaoguangrong.eric@...il.com,
        kernellwp@...il.com, lihaiwei.kernel@...il.com,
        Yulei Zhang <yuleixzhang@...cent.com>,
        Chen Zhuo <sagazchen@...cent.com>
Subject: [PATCH 24/35] dmemfs: support hugepage for dmemfs

From: Yulei Zhang <yuleixzhang@...cent.com>

It add hugepage support for dmemfs. We use PFN_DMEM to notify
vmf_insert_pfn_pmd, and dmem huge pmd will be marked with
_PAGE_SPECIAL and _PAGE_DMEM. So that GUP-fast can separate
dmemfs page from other page type and handle it correctly.

Signed-off-by: Chen Zhuo <sagazchen@...cent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@...cent.com>
---
 fs/dmemfs/inode.c | 113 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 111 insertions(+), 2 deletions(-)

diff --git a/fs/dmemfs/inode.c b/fs/dmemfs/inode.c
index b3e394f33b42..53a9bf214e0d 100644
--- a/fs/dmemfs/inode.c
+++ b/fs/dmemfs/inode.c
@@ -460,7 +460,7 @@ static int dmemfs_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
-static vm_fault_t dmemfs_fault(struct vm_fault *vmf)
+static vm_fault_t __dmemfs_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
@@ -488,6 +488,63 @@ static vm_fault_t dmemfs_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+static vm_fault_t  __dmemfs_pmd_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	unsigned long page_addr;
+	struct inode *inode = file_inode(vma->vm_file);
+	void *entry;
+	phys_addr_t phys;
+	pfn_t pfn;
+	int ret;
+
+	if (dmem_page_size(inode) < PMD_SIZE)
+		return VM_FAULT_FALLBACK;
+
+	WARN_ON(pmd_addr < vma->vm_start ||
+		vma->vm_end < pmd_addr + PMD_SIZE);
+
+	page_addr = vmf->address & ~(dmem_page_size(inode) - 1);
+	entry = radix_get_create_entry(vma, page_addr, inode,
+				       linear_page_index(vma, page_addr));
+	if (IS_ERR(entry))
+		return (PTR_ERR(entry) == -ENOMEM) ?
+			VM_FAULT_OOM : VM_FAULT_SIGBUS;
+
+	phys = dmem_addr_to_pfn(inode, dmem_entry_to_addr(inode, entry),
+				linear_page_index(vma, pmd_addr), PMD_SHIFT);
+	phys <<= PAGE_SHIFT;
+	pfn = phys_to_pfn_t(phys, PFN_DMEM);
+	ret = vmf_insert_pfn_pmd(vmf, pfn, !!(vma->vm_flags & VM_WRITE));
+
+	radix_put_entry();
+	return ret;
+}
+
+static vm_fault_t dmemfs_huge_fault(struct vm_fault *vmf, enum page_entry_size pe_size)
+{
+	int ret;
+
+	switch (pe_size) {
+	case PE_SIZE_PTE:
+		ret = __dmemfs_fault(vmf);
+		break;
+	case PE_SIZE_PMD:
+		ret = __dmemfs_pmd_fault(vmf);
+		break;
+	default:
+		ret = VM_FAULT_SIGBUS;
+	}
+
+	return ret;
+}
+
+static vm_fault_t dmemfs_fault(struct vm_fault *vmf)
+{
+	return dmemfs_huge_fault(vmf, PE_SIZE_PTE);
+}
+
 static unsigned long dmemfs_pagesize(struct vm_area_struct *vma)
 {
 	return dmem_page_size(file_inode(vma->vm_file));
@@ -498,6 +555,7 @@ static const struct vm_operations_struct dmemfs_vm_ops = {
 	.fault = dmemfs_fault,
 	.pagesize = dmemfs_pagesize,
 	.access = dmemfs_access_dmem,
+	.huge_fault = dmemfs_huge_fault,
 };
 
 int dmemfs_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -510,15 +568,66 @@ int dmemfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma->vm_flags |= VM_PFNMAP | VM_DMEM | VM_IO;
+	vma->vm_flags |= VM_PFNMAP | VM_DONTCOPY | VM_DMEM | VM_IO;
+
+	if (dmem_page_size(inode) != PAGE_SIZE)
+		vma->vm_flags |= VM_HUGEPAGE;
 
 	file_accessed(file);
 	vma->vm_ops = &dmemfs_vm_ops;
 	return 0;
 }
 
+/*
+ * If the size of area returned by mm->get_unmapped_area() is one
+ * dmem pagesize larger than 'len', the returned addr by
+ * mm->get_unmapped_area() could be aligned to dmem pagesize to
+ * meet alignment demand.
+ */
+static unsigned long
+dmemfs_get_unmapped_area(struct file *file, unsigned long addr,
+			 unsigned long len, unsigned long pgoff,
+			 unsigned long flags)
+{
+	unsigned long len_pad;
+	unsigned long off = pgoff << PAGE_SHIFT;
+	unsigned long align;
+
+	align = dmem_page_size(file_inode(file));
+
+	/* For pud or pmd pagesize, could not support fault fallback. */
+	if (len & (align - 1))
+		return -EINVAL;
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED) {
+		if (addr & (align - 1))
+			return -EINVAL;
+		return addr;
+	}
+
+	/*
+	 * Pad a extra align space for 'len', as we want to find a unmapped
+	 * area which is larger enough to align with dmemfs pagesize, if
+	 * pagesize of dmem is larger than 4K.
+	 */
+	len_pad = (align == PAGE_SIZE) ? len : len + align;
+
+	/* 'len' or 'off' is too large for pad. */
+	if (len_pad < len || (off + len_pad) < off)
+		return -EINVAL;
+
+	addr = current->mm->get_unmapped_area(file, addr, len_pad,
+					      pgoff, flags);
+
+	/* Now 'addr' could be aligned to upper boundary. */
+	return IS_ERR_VALUE(addr) ? addr : round_up(addr, align);
+}
+
 static const struct file_operations dmemfs_file_operations = {
 	.mmap = dmemfs_file_mmap,
+	.get_unmapped_area = dmemfs_get_unmapped_area,
 };
 
 static int dmemfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
-- 
2.28.0

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ