From: Logan Gunthorpe <logang@deltatee.com>
To: linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org,
linux-block@vger.kernel.org, linux-pci@vger.kernel.org,
linux-mm@kvack.org
Cc: "Christoph Hellwig" <hch@lst.de>,
"Greg Kroah-Hartman" <gregkh@linuxfoundation.org>,
"Dan Williams" <dan.j.williams@intel.com>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Christian König" <christian.koenig@amd.com>,
"John Hubbard" <jhubbard@nvidia.com>,
"Don Dutile" <ddutile@redhat.com>,
"Matthew Wilcox" <willy@infradead.org>,
"Daniel Vetter" <daniel.vetter@ffwll.ch>,
"Minturn Dave B" <dave.b.minturn@intel.com>,
"Jason Ekstrand" <jason@jlekstrand.net>,
"Dave Hansen" <dave.hansen@linux.intel.com>,
"Xiong Jianxin" <jianxin.xiong@intel.com>,
"Bjorn Helgaas" <helgaas@kernel.org>,
"Ira Weiny" <ira.weiny@intel.com>,
"Robin Murphy" <robin.murphy@arm.com>,
"Martin Oliveira" <martin.oliveira@eideticom.com>,
"Chaitanya Kulkarni" <ckulkarnilinux@gmail.com>,
"Ralph Campbell" <rcampbell@nvidia.com>,
"Stephen Bates" <sbates@raithlin.com>,
"Logan Gunthorpe" <logang@deltatee.com>
Subject: [PATCH v11 1/9] mm: allow multiple error returns in try_grab_page()
Date: Fri, 21 Oct 2022 11:41:08 -0600 [thread overview]
Message-ID: <20221021174116.7200-2-logang@deltatee.com> (raw)
In-Reply-To: <20221021174116.7200-1-logang@deltatee.com>
In order to add checks for P2PDMA memory into try_grab_page(), expand
the error return from a bool to an int/error code. Update all the
callsites handle change in usage.
Also remove the WARN_ON_ONCE() call at the callsites seeing there
already is a WARN_ON_ONCE() inside the function if it fails.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
---
include/linux/mm.h | 2 +-
mm/gup.c | 26 ++++++++++++++------------
mm/huge_memory.c | 19 +++++++++++++------
mm/hugetlb.c | 17 +++++++++--------
4 files changed, 37 insertions(+), 27 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8bbcccbc5565..62a91dc1272b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1129,7 +1129,7 @@ static inline void get_page(struct page *page)
folio_get(page_folio(page));
}
-bool __must_check try_grab_page(struct page *page, unsigned int flags);
+int __must_check try_grab_page(struct page *page, unsigned int flags);
static inline __must_check bool try_get_page(struct page *page)
{
diff --git a/mm/gup.c b/mm/gup.c
index fe195d47de74..e2f447446384 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -202,17 +202,19 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
* time. Cases: please see the try_grab_folio() documentation, with
* "refs=1".
*
- * Return: true for success, or if no action was required (if neither FOLL_PIN
- * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or
- * FOLL_PIN was set, but the page could not be grabbed.
+ * Return: 0 for success, or if no action was required (if neither FOLL_PIN
+ * nor FOLL_GET was set, nothing is done). A negative error code for failure:
+ *
+ * -ENOMEM FOLL_GET or FOLL_PIN was set, but the page could not
+ * be grabbed.
*/
-bool __must_check try_grab_page(struct page *page, unsigned int flags)
+int __must_check try_grab_page(struct page *page, unsigned int flags)
{
struct folio *folio = page_folio(page);
WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
if (WARN_ON_ONCE(folio_ref_count(folio) <= 0))
- return false;
+ return -ENOMEM;
if (flags & FOLL_GET)
folio_ref_inc(folio);
@@ -232,7 +234,7 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags)
node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1);
}
- return true;
+ return 0;
}
/**
@@ -624,8 +626,9 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
!PageAnonExclusive(page), page);
/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
- if (unlikely(!try_grab_page(page, flags))) {
- page = ERR_PTR(-ENOMEM);
+ ret = try_grab_page(page, flags);
+ if (unlikely(ret)) {
+ page = ERR_PTR(ret);
goto out;
}
/*
@@ -960,10 +963,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
goto unmap;
*page = pte_page(*pte);
}
- if (unlikely(!try_grab_page(*page, gup_flags))) {
- ret = -ENOMEM;
+ ret = try_grab_page(*page, gup_flags);
+ if (unlikely(ret))
goto unmap;
- }
out:
ret = 0;
unmap:
@@ -2536,7 +2538,7 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
}
SetPageReferenced(page);
pages[*nr] = page;
- if (unlikely(!try_grab_page(page, flags))) {
+ if (unlikely(try_grab_page(page, flags))) {
undo_dev_pagemap(nr, nr_start, flags, pages);
break;
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1cc4a5f4791e..52f2b2a2ffae 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1035,6 +1035,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn = pmd_pfn(*pmd);
struct mm_struct *mm = vma->vm_mm;
struct page *page;
+ int ret;
assert_spin_locked(pmd_lockptr(mm, pmd));
@@ -1066,8 +1067,9 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
if (!*pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
- if (!try_grab_page(page, flags))
- page = ERR_PTR(-ENOMEM);
+ ret = try_grab_page(page, flags);
+ if (ret)
+ page = ERR_PTR(ret);
return page;
}
@@ -1193,6 +1195,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn = pud_pfn(*pud);
struct mm_struct *mm = vma->vm_mm;
struct page *page;
+ int ret;
assert_spin_locked(pud_lockptr(mm, pud));
@@ -1226,8 +1229,10 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
if (!*pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
- if (!try_grab_page(page, flags))
- page = ERR_PTR(-ENOMEM);
+
+ ret = try_grab_page(page, flags);
+ if (ret)
+ page = ERR_PTR(ret);
return page;
}
@@ -1435,6 +1440,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
{
struct mm_struct *mm = vma->vm_mm;
struct page *page;
+ int ret;
assert_spin_locked(pmd_lockptr(mm, pmd));
@@ -1459,8 +1465,9 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
!PageAnonExclusive(page), page);
- if (!try_grab_page(page, flags))
- return ERR_PTR(-ENOMEM);
+ ret = try_grab_page(page, flags);
+ if (ret)
+ return ERR_PTR(ret);
if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b586cdd75930..e8d01a19ce46 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7224,14 +7224,15 @@ follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags
page = pte_page(pte) +
((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
/*
- * try_grab_page() should always succeed here, because: a) we
- * hold the pmd (ptl) lock, and b) we've just checked that the
- * huge pmd (head) page is present in the page tables. The ptl
- * prevents the head page and tail pages from being rearranged
- * in any way. So this page must be available at this point,
- * unless the page refcount overflowed:
+ * try_grab_page() should always be able to get the page here,
+ * because: a) we hold the pmd (ptl) lock, and b) we've just
+ * checked that the huge pmd (head) page is present in the
+ * page tables. The ptl prevents the head page and tail pages
+ * from being rearranged in any way. So this page must be
+ * available at this point, unless the page refcount
+ * overflowed:
*/
- if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
+ if (try_grab_page(page, flags)) {
page = NULL;
goto out;
}
@@ -7269,7 +7270,7 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
pte = huge_ptep_get((pte_t *)pud);
if (pte_present(pte)) {
page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
- if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
+ if (try_grab_page(page, flags)) {
page = NULL;
goto out;
}
--
2.30.2
next prev parent reply other threads:[~2022-10-21 17:42 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-21 17:41 [PATCH v11 0/9] Userspace P2PDMA with O_DIRECT NVMe devices Logan Gunthorpe
2022-10-21 17:41 ` Logan Gunthorpe [this message]
2022-10-24 15:00 ` [PATCH v11 1/9] mm: allow multiple error returns in try_grab_page() Christoph Hellwig
2022-10-24 16:37 ` Dan Williams
2022-10-25 1:06 ` Chaitanya Kulkarni
2022-10-21 17:41 ` [PATCH v11 2/9] mm: introduce FOLL_PCI_P2PDMA to gate getting PCI P2PDMA pages Logan Gunthorpe
2022-10-24 15:00 ` Christoph Hellwig
2022-10-25 1:09 ` Chaitanya Kulkarni
2022-10-21 17:41 ` [PATCH v11 3/9] iov_iter: introduce iov_iter_get_pages_[alloc_]flags() Logan Gunthorpe
2022-10-25 1:14 ` Chaitanya Kulkarni
2022-10-25 15:35 ` Logan Gunthorpe
2022-10-25 15:41 ` Christoph Hellwig
2022-10-27 7:11 ` Jay Fang
2022-10-27 14:22 ` Logan Gunthorpe
2022-10-21 17:41 ` [PATCH v11 4/9] block: add check when merging zone device pages Logan Gunthorpe
2022-10-25 1:16 ` Chaitanya Kulkarni
2022-10-21 17:41 ` [PATCH v11 5/9] lib/scatterlist: " Logan Gunthorpe
2022-10-25 1:19 ` Chaitanya Kulkarni
2022-10-21 17:41 ` [PATCH v11 6/9] block: set FOLL_PCI_P2PDMA in __bio_iov_iter_get_pages() Logan Gunthorpe
2022-10-25 1:23 ` Chaitanya Kulkarni
2022-10-25 15:37 ` Logan Gunthorpe
2022-10-25 1:25 ` Chaitanya Kulkarni
2022-10-21 17:41 ` [PATCH v11 7/9] block: set FOLL_PCI_P2PDMA in bio_map_user_iov() Logan Gunthorpe
2022-10-25 1:26 ` Chaitanya Kulkarni
2022-10-21 17:41 ` [PATCH v11 8/9] PCI/P2PDMA: Allow userspace VMA allocations through sysfs Logan Gunthorpe
2022-10-25 1:29 ` Chaitanya Kulkarni
2022-10-25 1:34 ` Chaitanya Kulkarni
2022-10-21 17:41 ` [PATCH v11 9/9] ABI: sysfs-bus-pci: add documentation for p2pmem allocate Logan Gunthorpe
2022-10-25 1:29 ` Chaitanya Kulkarni
2022-10-24 15:03 ` [PATCH v11 0/9] Userspace P2PDMA with O_DIRECT NVMe devices Christoph Hellwig
2022-10-24 19:15 ` John Hubbard
2022-11-08 6:56 ` Christoph Hellwig
2022-11-09 17:28 ` Logan Gunthorpe
2022-11-09 18:33 ` Jens Axboe
2022-11-09 18:44 ` Jens Axboe
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=20221021174116.7200-2-logang@deltatee.com \
--to=logang@deltatee.com \
--cc=christian.koenig@amd.com \
--cc=ckulkarnilinux@gmail.com \
--cc=dan.j.williams@intel.com \
--cc=daniel.vetter@ffwll.ch \
--cc=dave.b.minturn@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=ddutile@redhat.com \
--cc=gregkh@linuxfoundation.org \
--cc=hch@lst.de \
--cc=helgaas@kernel.org \
--cc=ira.weiny@intel.com \
--cc=jason@jlekstrand.net \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=jianxin.xiong@intel.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=martin.oliveira@eideticom.com \
--cc=rcampbell@nvidia.com \
--cc=robin.murphy@arm.com \
--cc=sbates@raithlin.com \
--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).