From: Peter Xu <peterx@redhat.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: David Hildenbrand <david@redhat.com>,
Hugh Dickins <hughd@google.com>, Maya Gokhale <gokhale2@llnl.gov>,
Jerome Glisse <jglisse@redhat.com>,
Pavel Emelyanov <xemul@virtuozzo.com>,
Johannes Weiner <hannes@cmpxchg.org>,
peterx@redhat.com, Martin Cracauer <cracauer@cons.org>,
Shaohua Li <shli@fb.com>, Andrea Arcangeli <aarcange@redhat.com>,
Mike Kravetz <mike.kravetz@oracle.com>,
Denis Plotnikov <dplotnikov@virtuozzo.com>,
Mike Rapoport <rppt@linux.vnet.ibm.com>,
Marty McFadden <mcfadden8@llnl.gov>, Mel Gorman <mgorman@suse.de>,
"Kirill A . Shutemov" <kirill@shutemov.name>,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>
Subject: [PATCH v3 11/28] mm: merge parameters for change_protection()
Date: Wed, 20 Mar 2019 10:06:25 +0800 [thread overview]
Message-ID: <20190320020642.4000-12-peterx@redhat.com> (raw)
In-Reply-To: <20190320020642.4000-1-peterx@redhat.com>
change_protection() was used by either the NUMA or mprotect() code,
there's one parameter for each of the callers (dirty_accountable and
prot_numa). Further, these parameters are passed along the calls:
- change_protection_range()
- change_p4d_range()
- change_pud_range()
- change_pmd_range()
- ...
Now we introduce a flag for change_protect() and all these helpers to
replace these parameters. Then we can avoid passing multiple parameters
multiple times along the way.
More importantly, it'll greatly simplify the work if we want to
introduce any new parameters to change_protection(). In the follow up
patches, a new parameter for userfaultfd write protection will be
introduced.
No functional change at all.
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
include/linux/huge_mm.h | 2 +-
include/linux/mm.h | 14 +++++++++++++-
mm/huge_memory.c | 3 ++-
mm/mempolicy.c | 2 +-
mm/mprotect.c | 29 ++++++++++++++++-------------
5 files changed, 33 insertions(+), 17 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 381e872bfde0..1550fb12dbd4 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -46,7 +46,7 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
pmd_t *old_pmd, pmd_t *new_pmd);
extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, pgprot_t newprot,
- int prot_numa);
+ unsigned long cp_flags);
vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, pfn_t pfn, bool write);
vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f73dbc4a1957..937559a74dc4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1682,9 +1682,21 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
unsigned long old_addr, struct vm_area_struct *new_vma,
unsigned long new_addr, unsigned long len,
bool need_rmap_locks);
+
+/*
+ * Flags used by change_protection(). For now we make it a bitmap so
+ * that we can pass in multiple flags just like parameters. However
+ * for now all the callers are only use one of the flags at the same
+ * time.
+ */
+/* Whether we should allow dirty bit accounting */
+#define MM_CP_DIRTY_ACCT (1UL << 0)
+/* Whether this protection change is for NUMA hints */
+#define MM_CP_PROT_NUMA (1UL << 1)
+
extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgprot_t newprot,
- int dirty_accountable, int prot_numa);
+ unsigned long cp_flags);
extern int mprotect_fixup(struct vm_area_struct *vma,
struct vm_area_struct **pprev, unsigned long start,
unsigned long end, unsigned long newflags);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index faf357eaf0ce..8d65b0f041f9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1860,13 +1860,14 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
* - HPAGE_PMD_NR is protections changed and TLB flush necessary
*/
int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, pgprot_t newprot, int prot_numa)
+ unsigned long addr, pgprot_t newprot, unsigned long cp_flags)
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
pmd_t entry;
bool preserve_write;
int ret;
+ bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ee2bce59d2bf..55aed31b4f04 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -554,7 +554,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
{
int nr_updated;
- nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
+ nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA);
if (nr_updated)
count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 36cb358db170..a6ba448c8565 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,13 +37,15 @@
static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot,
- int dirty_accountable, int prot_numa)
+ unsigned long cp_flags)
{
struct mm_struct *mm = vma->vm_mm;
pte_t *pte, oldpte;
spinlock_t *ptl;
unsigned long pages = 0;
int target_node = NUMA_NO_NODE;
+ bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT;
+ bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
/*
* Can be called with only the mmap_sem for reading by
@@ -164,7 +166,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
pud_t *pud, unsigned long addr, unsigned long end,
- pgprot_t newprot, int dirty_accountable, int prot_numa)
+ pgprot_t newprot, unsigned long cp_flags)
{
pmd_t *pmd;
unsigned long next;
@@ -194,7 +196,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
__split_huge_pmd(vma, pmd, addr, false, NULL);
} else {
int nr_ptes = change_huge_pmd(vma, pmd, addr,
- newprot, prot_numa);
+ newprot, cp_flags);
if (nr_ptes) {
if (nr_ptes == HPAGE_PMD_NR) {
@@ -209,7 +211,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
/* fall through, the trans huge pmd just split */
}
this_pages = change_pte_range(vma, pmd, addr, next, newprot,
- dirty_accountable, prot_numa);
+ cp_flags);
pages += this_pages;
next:
cond_resched();
@@ -225,7 +227,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
static inline unsigned long change_pud_range(struct vm_area_struct *vma,
p4d_t *p4d, unsigned long addr, unsigned long end,
- pgprot_t newprot, int dirty_accountable, int prot_numa)
+ pgprot_t newprot, unsigned long cp_flags)
{
pud_t *pud;
unsigned long next;
@@ -237,7 +239,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
if (pud_none_or_clear_bad(pud))
continue;
pages += change_pmd_range(vma, pud, addr, next, newprot,
- dirty_accountable, prot_numa);
+ cp_flags);
} while (pud++, addr = next, addr != end);
return pages;
@@ -245,7 +247,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
pgd_t *pgd, unsigned long addr, unsigned long end,
- pgprot_t newprot, int dirty_accountable, int prot_numa)
+ pgprot_t newprot, unsigned long cp_flags)
{
p4d_t *p4d;
unsigned long next;
@@ -257,7 +259,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
if (p4d_none_or_clear_bad(p4d))
continue;
pages += change_pud_range(vma, p4d, addr, next, newprot,
- dirty_accountable, prot_numa);
+ cp_flags);
} while (p4d++, addr = next, addr != end);
return pages;
@@ -265,7 +267,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end, pgprot_t newprot,
- int dirty_accountable, int prot_numa)
+ unsigned long cp_flags)
{
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
@@ -282,7 +284,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
if (pgd_none_or_clear_bad(pgd))
continue;
pages += change_p4d_range(vma, pgd, addr, next, newprot,
- dirty_accountable, prot_numa);
+ cp_flags);
} while (pgd++, addr = next, addr != end);
/* Only flush the TLB if we actually modified any entries: */
@@ -295,14 +297,15 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgprot_t newprot,
- int dirty_accountable, int prot_numa)
+ unsigned long cp_flags)
{
unsigned long pages;
if (is_vm_hugetlb_page(vma))
pages = hugetlb_change_protection(vma, start, end, newprot);
else
- pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
+ pages = change_protection_range(vma, start, end, newprot,
+ cp_flags);
return pages;
}
@@ -430,7 +433,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
vma_set_page_prot(vma);
change_protection(vma, start, end, vma->vm_page_prot,
- dirty_accountable, 0);
+ dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
/*
* Private VM_LOCKED VMA becoming writable: trigger COW to avoid major
--
2.17.1
next prev parent reply other threads:[~2019-03-20 2:08 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-20 2:06 [PATCH v3 00/28] userfaultfd: write protection support Peter Xu
2019-03-20 2:06 ` [PATCH v3 01/28] mm: gup: rename "nonblocking" to "locked" where proper Peter Xu
2019-03-20 2:06 ` [PATCH v3 02/28] mm: userfault: return VM_FAULT_RETRY on signals Peter Xu
2019-03-20 2:06 ` [PATCH v3 03/28] userfaultfd: don't retake mmap_sem to emulate NOPAGE Peter Xu
2019-03-20 2:06 ` [PATCH v3 04/28] mm: allow VM_FAULT_RETRY for multiple times Peter Xu
2019-04-18 20:11 ` Jerome Glisse
2019-04-19 6:00 ` Peter Xu
2019-03-20 2:06 ` [PATCH v3 05/28] mm: gup: " Peter Xu
2019-03-20 2:06 ` [PATCH v3 06/28] userfaultfd: wp: add helper for writeprotect check Peter Xu
2019-03-20 2:06 ` [PATCH v3 07/28] userfaultfd: wp: hook userfault handler to write protection fault Peter Xu
2019-04-18 20:03 ` Jerome Glisse
2019-03-20 2:06 ` [PATCH v3 08/28] userfaultfd: wp: add WP pagetable tracking to x86 Peter Xu
2019-03-20 2:06 ` [PATCH v3 09/28] userfaultfd: wp: userfaultfd_pte/huge_pmd_wp() helpers Peter Xu
2019-03-20 2:06 ` [PATCH v3 10/28] userfaultfd: wp: add UFFDIO_COPY_MODE_WP Peter Xu
2019-03-20 2:06 ` Peter Xu [this message]
2019-03-20 2:06 ` [PATCH v3 12/28] userfaultfd: wp: apply _PAGE_UFFD_WP bit Peter Xu
2019-03-20 2:06 ` [PATCH v3 13/28] mm: export wp_page_copy() Peter Xu
2019-03-20 2:06 ` [PATCH v3 14/28] userfaultfd: wp: handle COW properly for uffd-wp Peter Xu
2019-04-18 20:51 ` Jerome Glisse
2019-04-19 6:26 ` Peter Xu
2019-04-19 15:02 ` Jerome Glisse
2019-04-22 12:20 ` Peter Xu
2019-04-22 14:54 ` Jerome Glisse
2019-04-23 3:00 ` Peter Xu
2019-04-23 15:34 ` Jerome Glisse
2019-04-24 8:38 ` Peter Xu
2019-03-20 2:06 ` [PATCH v3 15/28] userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork Peter Xu
2019-03-20 2:06 ` [PATCH v3 16/28] userfaultfd: wp: add pmd_swp_*uffd_wp() helpers Peter Xu
2019-03-20 2:06 ` [PATCH v3 17/28] userfaultfd: wp: support swap and page migration Peter Xu
2019-04-18 20:59 ` Jerome Glisse
2019-04-19 7:42 ` Peter Xu
2019-04-19 15:08 ` Jerome Glisse
2019-04-22 12:23 ` Peter Xu
2019-03-20 2:06 ` [PATCH v3 18/28] khugepaged: skip collapse if uffd-wp detected Peter Xu
2019-03-20 2:06 ` [PATCH v3 19/28] userfaultfd: introduce helper vma_find_uffd Peter Xu
2019-03-20 2:06 ` [PATCH v3 20/28] userfaultfd: wp: support write protection for userfault vma range Peter Xu
2019-03-20 2:06 ` [PATCH v3 21/28] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl Peter Xu
2019-03-20 2:06 ` [PATCH v3 22/28] userfaultfd: wp: enabled write protection in userfaultfd API Peter Xu
2019-03-22 21:37 ` Mike Rapoport
2019-03-20 2:06 ` [PATCH v3 23/28] userfaultfd: wp: don't wake up when doing write protect Peter Xu
2019-03-20 2:06 ` [PATCH v3 24/28] userfaultfd: wp: UFFDIO_REGISTER_MODE_WP documentation update Peter Xu
2019-03-22 21:46 ` Mike Rapoport
2019-03-20 2:06 ` [PATCH v3 25/28] userfaultfd: wp: fixup swap entries in change_pte_range Peter Xu
2019-04-18 21:01 ` Jerome Glisse
2019-03-20 2:06 ` [PATCH v3 26/28] userfaultfd: wp: declare _UFFDIO_WRITEPROTECT conditionally Peter Xu
2019-03-22 21:43 ` Mike Rapoport
2019-03-20 2:06 ` [PATCH v3 27/28] userfaultfd: selftests: refactor statistics Peter Xu
2019-03-20 2:06 ` [PATCH v3 28/28] userfaultfd: selftests: add write-protect test Peter Xu
2019-04-09 6:08 ` [PATCH v3 00/28] userfaultfd: write protection support Peter Xu
2019-04-18 21:07 ` Jerome Glisse
2019-04-19 7:53 ` Peter Xu
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=20190320020642.4000-12-peterx@redhat.com \
--to=peterx@redhat.com \
--cc=aarcange@redhat.com \
--cc=cracauer@cons.org \
--cc=david@redhat.com \
--cc=dgilbert@redhat.com \
--cc=dplotnikov@virtuozzo.com \
--cc=gokhale2@llnl.gov \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jglisse@redhat.com \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mcfadden8@llnl.gov \
--cc=mgorman@suse.de \
--cc=mike.kravetz@oracle.com \
--cc=rppt@linux.vnet.ibm.com \
--cc=shli@fb.com \
--cc=xemul@virtuozzo.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).