Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   yulei.kernel@gmail.com
To:     linux-mm@kvack.org, akpm@linux-foundation.org,
        linux-fsdevel@vger.kernel.org, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org, naoya.horiguchi@nec.com,
        viro@zeniv.linux.org.uk, pbonzini@redhat.com
Cc:     joao.m.martins@oracle.com, rdunlap@infradead.org,
        sean.j.christopherson@intel.com, xiaoguangrong.eric@gmail.com,
        kernellwp@gmail.com, lihaiwei.kernel@gmail.com,
        Yulei Zhang <yuleixzhang@tencent.com>,
        Chen Zhuo <sagazchen@tencent.com>
Subject: [RFC V2 28/37] mm, dmemfs: support huge_fault() for dmemfs
Date:   Mon,  7 Dec 2020 19:31:21 +0800
Message-Id: <c70e7ffb9052b9798d38f2d1525ad0ba429ec073.1607332046.git.yuleixzhang@tencent.com>
In-Reply-To: <cover.1607332046.git.yuleixzhang@tencent.com>
References: <cover.1607332046.git.yuleixzhang@tencent.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Yulei Zhang <yuleixzhang@tencent.com>

Introduce __dmemfs_huge_fault() to handle 1G huge pud for dmemfs.

Signed-off-by: Chen Zhuo <sagazchen@tencent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
 fs/dmemfs/inode.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/fs/dmemfs/inode.c b/fs/dmemfs/inode.c
index 17a518c..f698b9d 100644
--- a/fs/dmemfs/inode.c
+++ b/fs/dmemfs/inode.c
@@ -519,6 +519,43 @@ static vm_fault_t  __dmemfs_pmd_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static vm_fault_t __dmemfs_huge_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long pud_addr = vmf->address & PUD_MASK;
+	struct inode *inode = file_inode(vma->vm_file);
+	void *entry;
+	phys_addr_t phys;
+	pfn_t pfn;
+	int ret;
+
+	if (dmem_page_size(inode) < PUD_SIZE)
+		return VM_FAULT_FALLBACK;
+
+	WARN_ON(pud_addr < vma->vm_start ||
+		vma->vm_end < pud_addr + PUD_SIZE);
+
+	entry = radix_get_create_entry(vma, pud_addr, inode,
+				       linear_page_index(vma, pud_addr));
+	if (IS_ERR(entry))
+		return (PTR_ERR(entry) == -ENOMEM) ?
+			VM_FAULT_OOM : VM_FAULT_SIGBUS;
+
+	phys = dmem_entry_to_addr(inode, entry);
+	pfn = phys_to_pfn_t(phys, PFN_DMEM);
+	ret = vmf_insert_pfn_pud(vmf, pfn, !!(vma->vm_flags & VM_WRITE));
+
+	radix_put_entry();
+	return ret;
+}
+#else
+static vm_fault_t __dmemfs_huge_fault(struct vm_fault *vmf)
+{
+	return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 static vm_fault_t dmemfs_huge_fault(struct vm_fault *vmf, enum page_entry_size pe_size)
 {
 	int ret;
@@ -530,6 +567,9 @@ static vm_fault_t dmemfs_huge_fault(struct vm_fault *vmf, enum page_entry_size p
 	case PE_SIZE_PMD:
 		ret = __dmemfs_pmd_fault(vmf);
 		break;
+	case PE_SIZE_PUD:
+		ret = __dmemfs_huge_fault(vmf);
+		break;
 	default:
 		ret = VM_FAULT_SIGBUS;
 	}
-- 
1.8.3.1