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 29/37] mm: add follow_pte_pud() to support huge pud look up
Date:   Mon,  7 Dec 2020 19:31:22 +0800
Message-Id: <43e14d8a452789e5321b93810a50acfe95672e99.1607332046.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>

Since we had supported dmem huge pud, here support dmem huge pud for
hva_to_pfn().

Similar to follow_pte_pmd(), follow_pte_pud() allows a PTE lead or a
huge page PMD or huge page PUD to be found and returned.

Signed-off-by: Chen Zhuo <sagazchen@tencent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
 mm/memory.c | 52 ++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 44 insertions(+), 8 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 01f3b05..dfc95be 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4698,9 +4698,9 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+static int __follow_pte_pud(struct mm_struct *mm, unsigned long address,
 			    struct mmu_notifier_range *range,
-			    pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+			    pte_t **ptepp, pmd_t **pmdpp, pud_t **pudpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -4717,6 +4717,26 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		goto out;
 
 	pud = pud_offset(p4d, address);
+	VM_BUG_ON(pud_trans_huge(*pud));
+	if (pud_huge(*pud)) {
+		if (!pudpp)
+			goto out;
+
+		if (range) {
+			mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0,
+						NULL, mm, address & PUD_MASK,
+						(address & PUD_MASK) + PUD_SIZE);
+			mmu_notifier_invalidate_range_start(range);
+		}
+		*ptlp = pud_lock(mm, pud);
+		if (pud_huge(*pud)) {
+			*pudpp = pud;
+			return 0;
+		}
+		spin_unlock(*ptlp);
+		if (range)
+			mmu_notifier_invalidate_range_end(range);
+	}
 	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
 		goto out;
 
@@ -4772,8 +4792,8 @@ static inline int follow_pte(struct mm_struct *mm, unsigned long address,
 
 	/* (void) is needed to make gcc happy */
 	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, NULL,
-						    ptepp, NULL, ptlp)));
+			   !(res = __follow_pte_pud(mm, address, NULL,
+						    ptepp, NULL, NULL, ptlp)));
 	return res;
 }
 
@@ -4785,12 +4805,24 @@ int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 
 	/* (void) is needed to make gcc happy */
 	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, range,
-						    ptepp, pmdpp, ptlp)));
+			   !(res = __follow_pte_pud(mm, address, range,
+						    ptepp, pmdpp, NULL, ptlp)));
 	return res;
 }
 EXPORT_SYMBOL(follow_pte_pmd);
 
+int follow_pte_pud(struct mm_struct *mm, unsigned long address,
+		   struct mmu_notifier_range *range,
+		   pte_t **ptepp, pmd_t **pmdpp, pud_t **pudpp, spinlock_t **ptlp)
+{
+	int res;
+
+	/* (void) is needed to make gcc happy */
+	(void) __cond_lock(*ptlp,
+			   !(res = __follow_pte_pud(mm, address, range,
+						    ptepp, pmdpp, pudpp, ptlp)));
+	return res;
+}
 /**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
@@ -4808,15 +4840,19 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	spinlock_t *ptl;
 	pte_t *ptep;
 	pmd_t *pmdp = NULL;
+	pud_t *pudp = NULL;
 
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
 		return ret;
 
-	ret = follow_pte_pmd(vma->vm_mm, address, NULL, &ptep, &pmdp, &ptl);
+	ret = follow_pte_pud(vma->vm_mm, address, NULL, &ptep, &pmdp, &pudp, &ptl);
 	if (ret)
 		return ret;
 
-	if (pmdp) {
+	if (pudp) {
+		*pfn = pud_pfn(*pudp) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
+		spin_unlock(ptl);
+	} else if (pmdp) {
 		*pfn = pmd_pfn(*pmdp) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
 		spin_unlock(ptl);
 	} else {
-- 
1.8.3.1