From: ira.weiny@intel.com
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>,
Dan Williams <dan.j.williams@intel.com>,
Matthew Wilcox <willy@infradead.org>, Jan Kara <jack@suse.cz>,
"Theodore Ts'o" <tytso@mit.edu>,
John Hubbard <jhubbard@nvidia.com>,
Michal Hocko <mhocko@suse.com>,
Dave Chinner <david@fromorbit.com>,
linux-xfs@vger.kernel.org, linux-rdma@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-nvdimm@lists.01.org, linux-ext4@vger.kernel.org,
linux-mm@kvack.org, Ira Weiny <ira.weiny@intel.com>
Subject: [RFC PATCH v2 11/19] mm/gup: Pass follow_page_context further down the call stack
Date: Fri, 9 Aug 2019 15:58:25 -0700 [thread overview]
Message-ID: <20190809225833.6657-12-ira.weiny@intel.com> (raw)
In-Reply-To: <20190809225833.6657-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
In preparation for passing more information (vaddr_pin) into
follow_page_pte(), follow_devmap_pud(), and follow_devmap_pmd().
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
include/linux/huge_mm.h | 17 -----------------
mm/gup.c | 31 +++++++++++++++----------------
mm/huge_memory.c | 6 ++++--
mm/internal.h | 28 ++++++++++++++++++++++++++++
4 files changed, 47 insertions(+), 35 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 45ede62aa85b..b01a20ce0bb9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -233,11 +233,6 @@ static inline int hpage_nr_pages(struct page *page)
return 1;
}
-struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, int flags, struct dev_pagemap **pgmap);
-struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud, int flags, struct dev_pagemap **pgmap);
-
extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
extern struct page *huge_zero_page;
@@ -375,18 +370,6 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm)
return;
}
-static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
- unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
-{
- return NULL;
-}
-
-static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
- unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap)
-{
- return NULL;
-}
-
static inline bool thp_migration_supported(void)
{
return false;
diff --git a/mm/gup.c b/mm/gup.c
index 504af3e9a942..a7a9d2f5278c 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -24,11 +24,6 @@
#include "internal.h"
-struct follow_page_context {
- struct dev_pagemap *pgmap;
- unsigned int page_mask;
-};
-
/**
* put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
* @pages: array of pages to be maybe marked dirty, and definitely released.
@@ -172,8 +167,9 @@ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
static struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags,
- struct dev_pagemap **pgmap)
+ struct follow_page_context *ctx)
{
+ struct dev_pagemap **pgmap = &ctx->pgmap;
struct mm_struct *mm = vma->vm_mm;
struct page *page;
spinlock_t *ptl;
@@ -363,13 +359,13 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
}
if (pmd_devmap(pmdval)) {
ptl = pmd_lock(mm, pmd);
- page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
+ page = follow_devmap_pmd(vma, address, pmd, flags, ctx);
spin_unlock(ptl);
if (page)
return page;
}
if (likely(!pmd_trans_huge(pmdval)))
- return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
+ return follow_page_pte(vma, address, pmd, flags, ctx);
if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
return no_page_table(vma, flags);
@@ -389,7 +385,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
}
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
- return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
+ return follow_page_pte(vma, address, pmd, flags, ctx);
}
if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
int ret;
@@ -419,7 +415,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
}
return ret ? ERR_PTR(ret) :
- follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
+ follow_page_pte(vma, address, pmd, flags, ctx);
}
page = follow_trans_huge_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
@@ -456,7 +452,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
}
if (pud_devmap(*pud)) {
ptl = pud_lock(mm, pud);
- page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
+ page = follow_devmap_pud(vma, address, pud, flags, ctx);
spin_unlock(ptl);
if (page)
return page;
@@ -786,7 +782,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas, int *nonblocking)
+ struct vm_area_struct **vmas, int *nonblocking,
+ struct vaddr_pin *vaddr_pin)
{
long ret = 0, i = 0;
struct vm_area_struct *vma = NULL;
@@ -797,6 +794,8 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+ ctx.vaddr_pin = vaddr_pin;
+
/*
* If FOLL_FORCE is set then do not force a full fault as the hinting
* fault information is unrelated to the reference behaviour of a task
@@ -1025,7 +1024,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
lock_dropped = false;
for (;;) {
ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
- vmas, locked);
+ vmas, locked, vaddr_pin);
if (!locked)
/* VM_FAULT_RETRY couldn't trigger, bypass */
return ret;
@@ -1068,7 +1067,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
lock_dropped = true;
down_read(&mm->mmap_sem);
ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
- pages, NULL, NULL);
+ pages, NULL, NULL, vaddr_pin);
if (ret != 1) {
BUG_ON(ret > 1);
if (!pages_done)
@@ -1226,7 +1225,7 @@ long populate_vma_page_range(struct vm_area_struct *vma,
* not result in a stack expansion that recurses back here.
*/
return __get_user_pages(current, mm, start, nr_pages, gup_flags,
- NULL, NULL, nonblocking);
+ NULL, NULL, nonblocking, NULL);
}
/*
@@ -1311,7 +1310,7 @@ struct page *get_dump_page(unsigned long addr)
if (__get_user_pages(current, current->mm, addr, 1,
FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
- NULL) < 1)
+ NULL, NULL) < 1)
return NULL;
flush_cache_page(vma, addr, page_to_pfn(page));
return page;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index bc1a07a55be1..7e09f2f17ed8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -916,8 +916,9 @@ static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
}
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
+ pmd_t *pmd, int flags, struct follow_page_context *ctx)
{
+ struct dev_pagemap **pgmap = &ctx->pgmap;
unsigned long pfn = pmd_pfn(*pmd);
struct mm_struct *mm = vma->vm_mm;
struct page *page;
@@ -1068,8 +1069,9 @@ static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
}
struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud, int flags, struct dev_pagemap **pgmap)
+ pud_t *pud, int flags, struct follow_page_context *ctx)
{
+ struct dev_pagemap **pgmap = &ctx->pgmap;
unsigned long pfn = pud_pfn(*pud);
struct mm_struct *mm = vma->vm_mm;
struct page *page;
diff --git a/mm/internal.h b/mm/internal.h
index 0d5f720c75ab..46ada5279856 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -12,6 +12,34 @@
#include <linux/pagemap.h>
#include <linux/tracepoint-defs.h>
+struct follow_page_context {
+ struct dev_pagemap *pgmap;
+ unsigned int page_mask;
+ struct vaddr_pin *vaddr_pin;
+};
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t *pmd, int flags, struct follow_page_context *ctx);
+struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
+ pud_t *pud, int flags, struct follow_page_context *ctx);
+#else
+static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
+ unsigned long addr, pmd_t *pmd, int flags,
+ struct follow_page_context *ctx)
+{
+ return NULL;
+}
+
+static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pud, int flags,
+ struct follow_page_context *ctx)
+{
+ return NULL;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+
/*
* The set of flags that only affect watermark checking and reclaim
* behaviour. This is used by the MM to obey the caller constraints
--
2.20.1
next prev parent reply other threads:[~2019-08-09 22:59 UTC|newest]
Thread overview: 110+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-09 22:58 [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ;-) ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 01/19] fs/locks: Export F_LAYOUT lease to user space ira.weiny
2019-08-09 23:52 ` Dave Chinner
2019-08-12 17:36 ` Ira Weiny
2019-08-14 8:05 ` Dave Chinner
2019-08-14 11:21 ` Jeff Layton
2019-08-14 11:38 ` Dave Chinner
2019-08-09 22:58 ` [RFC PATCH v2 02/19] fs/locks: Add Exclusive flag to user Layout lease ira.weiny
2019-08-14 14:15 ` Jeff Layton
2019-08-14 21:56 ` Dave Chinner
2019-08-26 10:41 ` Jeff Layton
2019-08-29 23:34 ` Ira Weiny
2019-09-04 12:52 ` Jeff Layton
2019-09-04 23:12 ` John Hubbard
2019-08-09 22:58 ` [RFC PATCH v2 03/19] mm/gup: Pass flags down to __gup_device_huge* calls ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 04/19] mm/gup: Ensure F_LAYOUT lease is held prior to GUP'ing pages ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 05/19] fs/ext4: Teach ext4 to break layout leases ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 06/19] fs/ext4: Teach dax_layout_busy_page() to operate on a sub-range ira.weiny
2019-08-23 15:18 ` Vivek Goyal
2019-08-29 18:52 ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 07/19] fs/xfs: Teach xfs to use new dax_layout_busy_page() ira.weiny
2019-08-09 23:30 ` Dave Chinner
2019-08-12 18:05 ` Ira Weiny
2019-08-14 8:04 ` Dave Chinner
2019-08-09 22:58 ` [RFC PATCH v2 08/19] fs/xfs: Fail truncate if page lease can't be broken ira.weiny
2019-08-09 23:22 ` Dave Chinner
2019-08-12 18:08 ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 09/19] mm/gup: Introduce vaddr_pin structure ira.weiny
2019-08-10 0:06 ` John Hubbard
2019-08-09 22:58 ` [RFC PATCH v2 10/19] mm/gup: Pass a NULL vaddr_pin through GUP fast ira.weiny
2019-08-10 0:06 ` John Hubbard
2019-08-09 22:58 ` ira.weiny [this message]
2019-08-10 0:18 ` [RFC PATCH v2 11/19] mm/gup: Pass follow_page_context further down the call stack John Hubbard
2019-08-12 19:01 ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 12/19] mm/gup: Prep put_user_pages() to take an vaddr_pin struct ira.weiny
2019-08-10 0:30 ` John Hubbard
2019-08-12 20:46 ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 13/19] {mm,file}: Add file_pins objects ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 14/19] fs/locks: Associate file pins while performing GUP ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 15/19] mm/gup: Introduce vaddr_pin_pages() ira.weiny
2019-08-10 0:09 ` John Hubbard
2019-08-12 21:00 ` Ira Weiny
2019-08-12 21:20 ` John Hubbard
2019-08-11 23:07 ` John Hubbard
2019-08-12 21:01 ` Ira Weiny
2019-08-12 12:28 ` Jason Gunthorpe
2019-08-12 21:48 ` Ira Weiny
2019-08-13 11:47 ` Jason Gunthorpe
2019-08-13 17:46 ` Ira Weiny
2019-08-13 17:56 ` John Hubbard
2019-08-09 22:58 ` [RFC PATCH v2 16/19] RDMA/uverbs: Add back pointer to system file object ira.weiny
2019-08-12 13:00 ` Jason Gunthorpe
2019-08-12 17:28 ` Ira Weiny
2019-08-12 17:56 ` Jason Gunthorpe
2019-08-12 21:15 ` Ira Weiny
2019-08-13 11:48 ` Jason Gunthorpe
2019-08-13 17:41 ` Ira Weiny
2019-08-13 18:00 ` Jason Gunthorpe
2019-08-13 20:38 ` Ira Weiny
2019-08-14 12:23 ` Jason Gunthorpe
2019-08-14 17:50 ` Ira Weiny
2019-08-14 18:15 ` Jason Gunthorpe
2019-09-04 22:25 ` Ira Weiny
2019-09-11 8:19 ` Jason Gunthorpe
2019-08-09 22:58 ` [RFC PATCH v2 17/19] RDMA/umem: Convert to vaddr_[pin|unpin]* operations ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 18/19] {mm,procfs}: Add display file_pins proc ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 19/19] mm/gup: Remove FOLL_LONGTERM DAX exclusion ira.weiny
2019-08-14 10:17 ` [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ;-) Jan Kara
2019-08-14 18:08 ` Ira Weiny
2019-08-15 13:05 ` Jan Kara
2019-08-16 19:05 ` Ira Weiny
2019-08-16 23:20 ` [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ; -) Ira Weiny
2019-08-19 6:36 ` Jan Kara
2019-08-17 2:26 ` [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ;-) Dave Chinner
2019-08-19 6:34 ` Jan Kara
2019-08-19 9:24 ` Dave Chinner
2019-08-19 12:38 ` Jason Gunthorpe
2019-08-19 21:53 ` Ira Weiny
2019-08-20 1:12 ` Dave Chinner
2019-08-20 11:55 ` Jason Gunthorpe
2019-08-21 18:02 ` Ira Weiny
2019-08-21 18:13 ` Jason Gunthorpe
2019-08-21 18:22 ` John Hubbard
2019-08-21 18:57 ` Ira Weiny
2019-08-21 19:06 ` Ira Weiny
2019-08-21 19:48 ` Jason Gunthorpe
2019-08-21 20:44 ` Ira Weiny
2019-08-21 23:49 ` Jason Gunthorpe
2019-08-23 3:23 ` Dave Chinner
2019-08-23 12:04 ` Jason Gunthorpe
2019-08-24 0:11 ` Dave Chinner
2019-08-24 5:08 ` Ira Weiny
2019-08-26 5:55 ` Dave Chinner
2019-08-29 2:02 ` Ira Weiny
2019-08-29 3:27 ` John Hubbard
2019-08-29 16:16 ` Ira Weiny
2019-09-02 22:26 ` Dave Chinner
2019-09-04 16:54 ` Ira Weiny
2019-08-25 19:39 ` Jason Gunthorpe
2019-08-24 4:49 ` Ira Weiny
2019-08-25 19:40 ` Jason Gunthorpe
2019-08-23 0:59 ` Dave Chinner
2019-08-23 17:15 ` Ira Weiny
2019-08-24 0:18 ` Dave Chinner
2019-08-20 0:05 ` John Hubbard
2019-08-20 1:20 ` Dave Chinner
2019-08-20 3:09 ` John Hubbard
2019-08-20 3:36 ` Dave Chinner
2019-08-21 18:43 ` John Hubbard
2019-08-21 19:09 ` Ira Weiny
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=20190809225833.6657-12-ira.weiny@intel.com \
--to=ira.weiny@intel.com \
--cc=akpm@linux-foundation.org \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=jack@suse.cz \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvdimm@lists.01.org \
--cc=linux-rdma@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=mhocko@suse.com \
--cc=tytso@mit.edu \
--cc=willy@infradead.org \
/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).