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 [thread overview]
Message-ID: <43e14d8a452789e5321b93810a50acfe95672e99.1607332046.git.yuleixzhang@tencent.com> (raw)
In-Reply-To: <cover.1607332046.git.yuleixzhang@tencent.com>
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
next prev parent reply other threads:[~2020-12-07 11:35 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-07 11:30 [RFC V2 00/37] Enhance memory utilization with DMEMFS yulei.kernel
2020-12-07 11:30 ` [RFC V2 01/37] fs: introduce dmemfs module yulei.kernel
2020-12-07 11:30 ` [RFC V2 02/37] mm: support direct memory reservation yulei.kernel
2020-12-07 11:30 ` [RFC V2 03/37] dmem: implement dmem memory management yulei.kernel
2020-12-07 11:30 ` [RFC V2 04/37] dmem: let pat recognize dmem yulei.kernel
2020-12-07 11:30 ` [RFC V2 05/37] dmemfs: support mmap for dmemfs yulei.kernel
2020-12-07 11:30 ` [RFC V2 06/37] dmemfs: support truncating inode down yulei.kernel
2020-12-07 11:31 ` [RFC V2 07/37] dmem: trace core functions yulei.kernel
2020-12-07 11:31 ` [RFC V2 08/37] dmem: show some statistic in debugfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 09/37] dmemfs: support remote access yulei.kernel
2020-12-07 11:31 ` [RFC V2 10/37] dmemfs: introduce max_alloc_try_dpages parameter yulei.kernel
2020-12-07 11:31 ` [RFC V2 11/37] mm: export mempolicy interfaces to serve dmem allocator yulei.kernel
2020-12-07 11:31 ` [RFC V2 12/37] dmem: introduce mempolicy support yulei.kernel
2020-12-07 11:31 ` [RFC V2 13/37] mm, dmem: introduce PFN_DMEM and pfn_t_dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 14/37] mm, dmem: differentiate dmem-pmd and thp-pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 15/37] mm: add pmd_special() check for pmd_trans_huge_lock() yulei.kernel
2020-12-07 11:31 ` [RFC V2 16/37] dmemfs: introduce ->split() to dmemfs_vm_ops yulei.kernel
2020-12-07 11:31 ` [RFC V2 17/37] mm, dmemfs: support unmap_page_range() for dmemfs pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 18/37] mm: follow_pmd_mask() for dmem huge pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 19/37] mm: gup_huge_pmd() " yulei.kernel
2020-12-07 11:31 ` [RFC V2 20/37] mm: support dmem huge pmd for vmf_insert_pfn_pmd() yulei.kernel
2020-12-07 11:31 ` [RFC V2 21/37] mm: support dmem huge pmd for follow_pfn() yulei.kernel
2020-12-07 11:31 ` [RFC V2 22/37] kvm, x86: Distinguish dmemfs page from mmio page yulei.kernel
2020-12-07 11:31 ` [RFC V2 23/37] kvm, x86: introduce VM_DMEM for syscall support usage yulei.kernel
2020-12-07 11:31 ` [RFC V2 24/37] dmemfs: support hugepage for dmemfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 25/37] mm, x86, dmem: fix estimation of reserved page for vaddr_get_pfn() yulei.kernel
2020-12-07 11:31 ` [RFC V2 26/37] mm, dmem: introduce pud_special() for dmem huge pud support yulei.kernel
2020-12-07 11:31 ` [RFC V2 27/37] mm: add pud_special() check to support dmem huge pud yulei.kernel
2020-12-07 11:31 ` [RFC V2 28/37] mm, dmemfs: support huge_fault() for dmemfs yulei.kernel
2020-12-07 11:31 ` yulei.kernel [this message]
2020-12-07 11:31 ` [RFC V2 30/37] dmem: introduce dmem_bitmap_alloc() and dmem_bitmap_free() yulei.kernel
2020-12-07 11:31 ` [RFC V2 31/37] dmem: introduce mce handler yulei.kernel
2020-12-07 11:31 ` [RFC V2 32/37] mm, dmemfs: register and handle the dmem mce yulei.kernel
2020-12-07 11:31 ` [RFC V2 33/37] kvm, x86: enable record_steal_time for dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 34/37] dmem: add dmem unit tests yulei.kernel
2020-12-07 11:31 ` [RFC V2 35/37] mm, dmem: introduce dregion->memmap for dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 36/37] vfio: support dmempage refcount for vfio yulei.kernel
2020-12-07 11:31 ` [RFC V2 37/37] Add documentation for dmemfs yulei.kernel
2020-12-24 18:27 ` Randy Dunlap
2020-12-07 12:02 ` [RFC V2 00/37] Enhance memory utilization with DMEMFS David Hildenbrand
2020-12-07 19:32 ` Dan Williams
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=43e14d8a452789e5321b93810a50acfe95672e99.1607332046.git.yuleixzhang@tencent.com \
--to=yulei.kernel@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=joao.m.martins@oracle.com \
--cc=kernellwp@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=lihaiwei.kernel@gmail.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=naoya.horiguchi@nec.com \
--cc=pbonzini@redhat.com \
--cc=rdunlap@infradead.org \
--cc=sagazchen@tencent.com \
--cc=sean.j.christopherson@intel.com \
--cc=viro@zeniv.linux.org.uk \
--cc=xiaoguangrong.eric@gmail.com \
--cc=yuleixzhang@tencent.com \
/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;
as well as URLs for NNTP newsgroup(s).