From: yulei.kernel@gmail.com
To: akpm@linux-foundation.org, naoya.horiguchi@nec.com,
viro@zeniv.linux.org.uk, pbonzini@redhat.com
Cc: linux-fsdevel@vger.kernel.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, xiaoguangrong.eric@gmail.com,
kernellwp@gmail.com, lihaiwei.kernel@gmail.com,
Yulei Zhang <yuleixzhang@tencent.com>,
Chen Zhuo <sagazchen@tencent.com>
Subject: [PATCH 27/35] mm: add pud_special() to support dmem huge pud
Date: Thu, 8 Oct 2020 15:54:17 +0800 [thread overview]
Message-ID: <a77b21e35deef53f66eea81198fc48dbde63d86b.1602093760.git.yuleixzhang@tencent.com> (raw)
In-Reply-To: <cover.1602093760.git.yuleixzhang@tencent.com>
In-Reply-To: <cover.1602093760.git.yuleixzhang@tencent.com>
From: Yulei Zhang <yuleixzhang@tencent.com>
Add pud_special() and follow_special_pud() to support dmem
huge pud as we do for dmem huge pmd.
Signed-off-by: Chen Zhuo <sagazchen@tencent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
arch/x86/include/asm/pgtable.h | 2 +-
include/linux/huge_mm.h | 2 +-
mm/gup.c | 46 ++++++++++++++++++++++++++++++++++
mm/huge_memory.c | 11 +++++---
mm/memory.c | 4 +--
mm/mprotect.c | 2 ++
6 files changed, 59 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 313fb4fd6645..c9a3b1f79cd5 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -266,7 +266,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static inline int pud_trans_huge(pud_t pud)
{
- return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+ return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP|_PAGE_DMEM)) == _PAGE_PSE;
}
#endif
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b7381e5aafe5..ac8eb3e39575 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -254,7 +254,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
struct vm_area_struct *vma)
{
- if (pud_trans_huge(*pud) || pud_devmap(*pud))
+ if (pud_trans_huge(*pud) || pud_devmap(*pud) || pud_special(*pud))
return __pud_trans_huge_lock(pud, vma);
else
return NULL;
diff --git a/mm/gup.c b/mm/gup.c
index a8edbb6a2b2f..fdcaeb163bc4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -416,6 +416,42 @@ follow_special_pmd(struct vm_area_struct *vma, unsigned long address,
return ERR_PTR(-EEXIST);
}
+static struct page *
+follow_special_pud(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pud, unsigned int flags)
+{
+ spinlock_t *ptl;
+
+ if (flags & FOLL_DUMP)
+ /* Avoid special (like zero) pages in core dumps */
+ return ERR_PTR(-EFAULT);
+
+ /* No page to get reference */
+ if (flags & FOLL_GET)
+ return ERR_PTR(-EFAULT);
+
+ if (flags & FOLL_TOUCH) {
+ pud_t _pud;
+
+ ptl = pud_lock(vma->vm_mm, pud);
+ if (!pud_special(*pud)) {
+ spin_unlock(ptl);
+ return NULL;
+ }
+ _pud = pud_mkyoung(*pud);
+ if (flags & FOLL_WRITE)
+ _pud = pud_mkdirty(_pud);
+ if (pudp_set_access_flags(vma, address & HPAGE_PMD_MASK,
+ pud, _pud,
+ flags & FOLL_WRITE))
+ update_mmu_cache_pud(vma, address, pud);
+ spin_unlock(ptl);
+ }
+
+ /* Proper page table entry exists, but no corresponding struct page */
+ return ERR_PTR(-EEXIST);
+}
+
/*
* FOLL_FORCE can write to even unwritable pte's, but only
* after we've gone through a COW cycle and they are dirty.
@@ -716,6 +752,12 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
return page;
return no_page_table(vma, flags);
}
+ if (pud_special(*pud)) {
+ page = follow_special_pud(vma, address, pud, flags);
+ if (page)
+ return page;
+ return no_page_table(vma, flags);
+ }
if (is_hugepd(__hugepd(pud_val(*pud)))) {
page = follow_huge_pd(vma, address,
__hugepd(pud_val(*pud)), flags,
@@ -2478,6 +2520,10 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
if (!pud_access_permitted(orig, flags & FOLL_WRITE))
return 0;
+ /* Bypass dmem pud. It will be handled in outside routine. */
+ if (pud_special(orig))
+ return 0;
+
if (pud_devmap(orig)) {
if (unlikely(flags & FOLL_LONGTERM))
return 0;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a24601c93713..29e1ab959c90 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -883,6 +883,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
entry = pud_mkhuge(pfn_t_pud(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pud_mkdevmap(entry);
+ if (pfn_t_dmem(pfn))
+ entry = pud_mkdmem(entry);
if (write) {
entry = pud_mkyoung(pud_mkdirty(entry));
entry = maybe_pud_mkwrite(entry, vma);
@@ -919,7 +921,7 @@ vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn,
* can't support a 'special' bit.
*/
BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
- !pfn_t_devmap(pfn));
+ !pfn_t_devmap(pfn) && !pfn_t_dmem(pfn));
BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
(VM_PFNMAP|VM_MIXEDMAP));
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
@@ -1883,7 +1885,7 @@ spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
spinlock_t *ptl;
ptl = pud_lock(vma->vm_mm, pud);
- if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
+ if (likely(pud_trans_huge(*pud) || pud_devmap(*pud) || pud_special(*pud)))
return ptl;
spin_unlock(ptl);
return NULL;
@@ -1894,6 +1896,7 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
pud_t *pud, unsigned long addr)
{
spinlock_t *ptl;
+ pud_t orig_pud;
ptl = __pud_trans_huge_lock(pud, vma);
if (!ptl)
@@ -1904,9 +1907,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
* pgtable_trans_huge_withdraw after finishing pudp related
* operations.
*/
- pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm);
+ orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm);
tlb_remove_pud_tlb_entry(tlb, pud, addr);
- if (vma_is_special_huge(vma)) {
+ if (vma_is_special_huge(vma) || pud_special(orig_pud)) {
spin_unlock(ptl);
/* No zero page support yet */
} else {
diff --git a/mm/memory.c b/mm/memory.c
index ca42a6e56e9b..3748fab7cc2a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -922,7 +922,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
src_pud = pud_offset(src_p4d, addr);
do {
next = pud_addr_end(addr, end);
- if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
+ if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud) || pud_special(*src_pud)) {
int err;
VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma);
@@ -1215,7 +1215,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
- if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
+ if (pud_trans_huge(*pud) || pud_devmap(*pud) || pud_special(*pud)) {
if (next - addr != HPAGE_PUD_SIZE) {
mmap_assert_locked(tlb->mm);
split_huge_pud(vma, pud, addr);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 36f885cbbb30..cae78c0c5160 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -292,6 +292,8 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
+ if (pud_special(*pud))
+ continue;
if (pud_none_or_clear_bad(pud))
continue;
pages += change_pmd_range(vma, pud, addr, next, newprot,
--
2.28.0
next prev parent reply other threads:[~2020-10-08 7:56 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-08 7:53 [PATCH 00/35] Enhance memory utilization with DMEMFS yulei.kernel
2020-10-08 7:53 ` [PATCH 01/35] fs: introduce dmemfs module yulei.kernel
2020-11-10 20:04 ` Al Viro
2020-11-11 8:53 ` yulei zhang
2020-11-11 23:09 ` Al Viro
2020-11-12 10:03 ` yulei zhang
2020-10-08 7:53 ` [PATCH 02/35] mm: support direct memory reservation yulei.kernel
2020-10-08 20:27 ` Randy Dunlap
2020-10-08 20:34 ` Randy Dunlap
2020-10-08 7:53 ` [PATCH 03/35] dmem: implement dmem memory management yulei.kernel
2020-10-08 7:53 ` [PATCH 04/35] dmem: let pat recognize dmem yulei.kernel
2020-10-13 7:27 ` Paolo Bonzini
2020-10-13 9:53 ` yulei zhang
2020-10-08 7:53 ` [PATCH 05/35] dmemfs: support mmap yulei.kernel
2020-10-08 7:53 ` [PATCH 06/35] dmemfs: support truncating inode down yulei.kernel
2020-10-08 7:53 ` [PATCH 07/35] dmem: trace core functions yulei.kernel
2020-10-08 7:53 ` [PATCH 08/35] dmem: show some statistic in debugfs yulei.kernel
2020-10-08 20:23 ` Randy Dunlap
2020-10-09 11:49 ` yulei zhang
2020-10-08 7:53 ` [PATCH 09/35] dmemfs: support remote access yulei.kernel
2020-10-08 7:54 ` [PATCH 10/35] dmemfs: introduce max_alloc_try_dpages parameter yulei.kernel
2020-10-08 7:54 ` [PATCH 11/35] mm: export mempolicy interfaces to serve dmem allocator yulei.kernel
2020-10-08 7:54 ` [PATCH 12/35] dmem: introduce mempolicy support yulei.kernel
2020-10-08 7:54 ` [PATCH 13/35] mm, dmem: introduce PFN_DMEM and pfn_t_dmem yulei.kernel
2020-10-08 7:54 ` [PATCH 14/35] mm, dmem: dmem-pmd vs thp-pmd yulei.kernel
2020-10-08 7:54 ` [PATCH 15/35] mm: add pmd_special() check for pmd_trans_huge_lock() yulei.kernel
2020-10-08 7:54 ` [PATCH 16/35] dmemfs: introduce ->split() to dmemfs_vm_ops yulei.kernel
2020-10-08 7:54 ` [PATCH 17/35] mm, dmemfs: support unmap_page_range() for dmemfs pmd yulei.kernel
2020-10-08 7:54 ` [PATCH 18/35] mm: follow_pmd_mask() for dmem huge pmd yulei.kernel
2020-10-08 7:54 ` [PATCH 19/35] mm: gup_huge_pmd() " yulei.kernel
2020-10-08 7:54 ` [PATCH 20/35] mm: support dmem huge pmd for vmf_insert_pfn_pmd() yulei.kernel
2020-10-08 7:54 ` [PATCH 21/35] mm: support dmem huge pmd for follow_pfn() yulei.kernel
2020-10-08 7:54 ` [PATCH 22/35] kvm, x86: Distinguish dmemfs page from mmio page yulei.kernel
2020-10-09 0:58 ` Sean Christopherson
2020-10-09 10:28 ` Joao Martins
2020-10-09 11:42 ` yulei zhang
2020-10-08 7:54 ` [PATCH 23/35] kvm, x86: introduce VM_DMEM yulei.kernel
2020-10-08 7:54 ` [PATCH 24/35] dmemfs: support hugepage for dmemfs yulei.kernel
2020-10-08 7:54 ` [PATCH 25/35] mm, x86, dmem: fix estimation of reserved page for vaddr_get_pfn() yulei.kernel
2020-10-08 7:54 ` [PATCH 26/35] mm, dmem: introduce pud_special() yulei.kernel
2020-10-08 7:54 ` yulei.kernel [this message]
2020-10-08 7:54 ` [PATCH 28/35] mm, dmemfs: support huge_fault() for dmemfs yulei.kernel
2020-10-08 7:54 ` [PATCH 29/35] mm: add follow_pte_pud() yulei.kernel
2020-10-08 7:54 ` [PATCH 30/35] dmem: introduce dmem_bitmap_alloc() and dmem_bitmap_free() yulei.kernel
2020-10-08 7:54 ` [PATCH 31/35] dmem: introduce mce handler yulei.kernel
2020-10-08 7:54 ` [PATCH 32/35] mm, dmemfs: register and handle the dmem mce yulei.kernel
2020-10-08 7:54 ` [PATCH 33/35] kvm, x86: temporary disable record_steal_time for dmem yulei.kernel
2020-10-08 7:54 ` [PATCH 34/35] dmem: add dmem unit tests yulei.kernel
2020-10-08 7:54 ` [PATCH 35/35] Add documentation for dmemfs yulei.kernel
2020-10-09 1:26 ` Randy Dunlap
2020-10-08 19:01 ` [PATCH 00/35] Enhance memory utilization with DMEMFS Joao Martins
2020-10-09 11:39 ` yulei zhang
2020-10-09 11:53 ` Joao Martins
2020-10-10 8:15 ` yulei zhang
2020-10-12 10:59 ` Joao Martins
2020-10-14 22:25 ` Dan Williams
2020-10-19 13:37 ` Paolo Bonzini
2020-10-19 19:03 ` Joao Martins
2020-10-20 15:22 ` yulei zhang
2020-10-12 11:57 ` Zengtao (B)
2020-10-13 2:45 ` yulei zhang
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=a77b21e35deef53f66eea81198fc48dbde63d86b.1602093760.git.yuleixzhang@tencent.com \
--to=yulei.kernel@gmail.com \
--cc=akpm@linux-foundation.org \
--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=naoya.horiguchi@nec.com \
--cc=pbonzini@redhat.com \
--cc=sagazchen@tencent.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).