From: Matthew Wilcox <willy@infradead.org>
To: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Cc: paulmck@linux.vnet.ibm.com, peterz@infradead.org,
akpm@linux-foundation.org, kirill@shutemov.name,
ak@linux.intel.com, mhocko@kernel.org, dave@stgolabs.net,
jack@suse.cz, benh@kernel.crashing.org, mpe@ellerman.id.au,
paulus@samba.org, Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
hpa@zytor.com, Will Deacon <will.deacon@arm.com>,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Alexei Starovoitov <alexei.starovoitov@gmail.com>,
kemi.wang@intel.com, sergey.senozhatsky.work@gmail.com,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
haren@linux.vnet.ibm.com, khandual@linux.vnet.ibm.com,
npiggin@gmail.com, bsingharora@gmail.com,
Tim Chen <tim.c.chen@linux.intel.com>,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org
Subject: Re: [PATCH v6 22/24] mm: Speculative page fault handler return VMA
Date: Fri, 12 Jan 2018 20:23:54 -0800 [thread overview]
Message-ID: <20180113042354.GA24241@bombadil.infradead.org> (raw)
In-Reply-To: <20180112190251.GC7590@bombadil.infradead.org>
On Fri, Jan 12, 2018 at 11:02:51AM -0800, Matthew Wilcox wrote:
> On Fri, Jan 12, 2018 at 06:26:06PM +0100, Laurent Dufour wrote:
> > @@ -1354,7 +1354,10 @@ extern int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
> > unsigned int flags);
> > #ifdef CONFIG_SPF
> > extern int handle_speculative_fault(struct mm_struct *mm,
> > + unsigned long address, unsigned int flags,
> > + struct vm_area_struct **vma);
>
> I think this shows that we need to create 'struct vm_fault' on the stack
> in the arch code and then pass it to handle_speculative_fault(), followed
> by handle_mm_fault(). That should be quite a nice cleanup actually.
> I know that's only 30+ architectures to change ;-)
Of course, we don't need to change them all. Try this:
Subject: [PATCH] Add vm_handle_fault
For the speculative fault handler, we want to create the struct vm_fault
on the stack in the arch code and pass it into the generic mm code.
To avoid changing 30+ architectures, leave handle_mm_fault with its
current function signature and move its guts into the new vm_handle_fault
function. Even this saves a nice 172 bytes on the random x86-64 .config
I happen to have around.
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
diff --git a/mm/memory.c b/mm/memory.c
index 5eb3d2524bdc..403934297a3d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3977,36 +3977,28 @@ static int handle_pte_fault(struct vm_fault *vmf)
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
-static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
- unsigned int flags)
+static int __handle_mm_fault(struct vm_fault *vmf)
{
- struct vm_fault vmf = {
- .vma = vma,
- .address = address & PAGE_MASK,
- .flags = flags,
- .pgoff = linear_page_index(vma, address),
- .gfp_mask = __get_fault_gfp_mask(vma),
- };
- unsigned int dirty = flags & FAULT_FLAG_WRITE;
- struct mm_struct *mm = vma->vm_mm;
+ unsigned int dirty = vmf->flags & FAULT_FLAG_WRITE;
+ struct mm_struct *mm = vmf->vma->vm_mm;
pgd_t *pgd;
p4d_t *p4d;
int ret;
- pgd = pgd_offset(mm, address);
- p4d = p4d_alloc(mm, pgd, address);
+ pgd = pgd_offset(mm, vmf->address);
+ p4d = p4d_alloc(mm, pgd, vmf->address);
if (!p4d)
return VM_FAULT_OOM;
- vmf.pud = pud_alloc(mm, p4d, address);
- if (!vmf.pud)
+ vmf->pud = pud_alloc(mm, p4d, vmf->address);
+ if (!vmf->pud)
return VM_FAULT_OOM;
- if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
- ret = create_huge_pud(&vmf);
+ if (pud_none(*vmf->pud) && transparent_hugepage_enabled(vmf->vma)) {
+ ret = create_huge_pud(vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- pud_t orig_pud = *vmf.pud;
+ pud_t orig_pud = *vmf->pud;
barrier();
if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
@@ -4014,50 +4006,51 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
/* NUMA case for anonymous PUDs would go here */
if (dirty && !pud_access_permitted(orig_pud, WRITE)) {
- ret = wp_huge_pud(&vmf, orig_pud);
+ ret = wp_huge_pud(vmf, orig_pud);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- huge_pud_set_accessed(&vmf, orig_pud);
+ huge_pud_set_accessed(vmf, orig_pud);
return 0;
}
}
}
- vmf.pmd = pmd_alloc(mm, vmf.pud, address);
- if (!vmf.pmd)
+ vmf->pmd = pmd_alloc(mm, vmf->pud, vmf->address);
+ if (!vmf->pmd)
return VM_FAULT_OOM;
- if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
- ret = create_huge_pmd(&vmf);
+ if (pmd_none(*vmf->pmd) && transparent_hugepage_enabled(vmf->vma)) {
+ ret = create_huge_pmd(vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- pmd_t orig_pmd = *vmf.pmd;
+ pmd_t orig_pmd = *vmf->pmd;
barrier();
if (unlikely(is_swap_pmd(orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
!is_pmd_migration_entry(orig_pmd));
if (is_pmd_migration_entry(orig_pmd))
- pmd_migration_entry_wait(mm, vmf.pmd);
+ pmd_migration_entry_wait(mm, vmf->pmd);
return 0;
}
if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
- if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
- return do_huge_pmd_numa_page(&vmf, orig_pmd);
+ if (pmd_protnone(orig_pmd) &&
+ vma_is_accessible(vmf->vma))
+ return do_huge_pmd_numa_page(vmf, orig_pmd);
if (dirty && !pmd_access_permitted(orig_pmd, WRITE)) {
- ret = wp_huge_pmd(&vmf, orig_pmd);
+ ret = wp_huge_pmd(vmf, orig_pmd);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- huge_pmd_set_accessed(&vmf, orig_pmd);
+ huge_pmd_set_accessed(vmf, orig_pmd);
return 0;
}
}
}
- return handle_pte_fault(&vmf);
+ return handle_pte_fault(vmf);
}
/*
@@ -4066,9 +4059,10 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
-int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
- unsigned int flags)
+int vm_handle_fault(struct vm_fault *vmf)
{
+ unsigned int flags = vmf->flags;
+ struct vm_area_struct *vma = vmf->vma;
int ret;
__set_current_state(TASK_RUNNING);
@@ -4092,9 +4086,9 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
mem_cgroup_oom_enable();
if (unlikely(is_vm_hugetlb_page(vma)))
- ret = hugetlb_fault(vma->vm_mm, vma, address, flags);
+ ret = hugetlb_fault(vma->vm_mm, vma, vmf->address, flags);
else
- ret = __handle_mm_fault(vma, address, flags);
+ ret = __handle_mm_fault(vmf);
if (flags & FAULT_FLAG_USER) {
mem_cgroup_oom_disable();
@@ -4110,6 +4104,26 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
return ret;
}
+
+/*
+ * By the time we get here, we already hold the mm semaphore
+ *
+ * The mmap_sem may have been released depending on flags and our
+ * return value. See filemap_fault() and __lock_page_or_retry().
+ */
+int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
+ unsigned int flags)
+{
+ struct vm_fault vmf = {
+ .vma = vma,
+ .address = address & PAGE_MASK,
+ .flags = flags,
+ .pgoff = linear_page_index(vma, address),
+ .gfp_mask = __get_fault_gfp_mask(vma),
+ };
+
+ return vm_handle_fault(&vmf);
+}
EXPORT_SYMBOL_GPL(handle_mm_fault);
#ifndef __PAGETABLE_P4D_FOLDED
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2018-01-13 4:24 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-12 17:25 [PATCH v6 00/24] Speculative page faults Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 01/24] x86/mm: Define CONFIG_SPF Laurent Dufour
2018-01-12 18:57 ` Thomas Gleixner
2018-01-15 17:37 ` Laurent Dufour
2018-01-15 17:49 ` Thomas Gleixner
2018-01-15 18:37 ` Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 02/24] powerpc/mm: " Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 03/24] mm: Dont assume page-table invariance during faults Laurent Dufour
2018-01-17 3:04 ` Andi Kleen
2018-01-17 8:57 ` Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 04/24] mm: Prepare for FAULT_FLAG_SPECULATIVE Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 05/24] mm: Introduce pte_spinlock " Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 06/24] mm: VMA sequence count Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 07/24] mm: Protect VMA modifications using " Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 08/24] mm: protect mremap() against SPF hanlder Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 09/24] mm: Protect SPF handler against anon_vma changes Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 10/24] mm: Cache some VMA fields in the vm_fault structure Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 11/24] mm/migrate: Pass vm_fault pointer to migrate_misplaced_page() Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 12/24] mm: Introduce __lru_cache_add_active_or_unevictable Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 13/24] mm: Introduce __maybe_mkwrite() Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 14/24] mm: Introduce __vm_normal_page() Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 15/24] mm: Introduce __page_add_new_anon_rmap() Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 16/24] mm: Protect mm_rb tree with a rwlock Laurent Dufour
2018-01-12 18:48 ` Matthew Wilcox
2018-01-15 17:42 ` Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 17/24] mm: Provide speculative fault infrastructure Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 18/24] mm: Try spin lock in speculative path Laurent Dufour
2018-01-12 18:18 ` Matthew Wilcox
2018-01-16 13:24 ` Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 19/24] mm: Adding speculative page fault failure trace events Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 20/24] perf: Add a speculative page fault sw event Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 21/24] perf tools: Add support for the SPF perf event Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 22/24] mm: Speculative page fault handler return VMA Laurent Dufour
2018-01-12 19:02 ` Matthew Wilcox
2018-01-13 4:23 ` Matthew Wilcox [this message]
2018-01-16 14:47 ` Laurent Dufour
2018-01-16 14:58 ` Matthew Wilcox
2018-01-12 17:26 ` [PATCH v6 23/24] x86/mm: Add speculative pagefault handling Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 24/24] powerpc/mm: Add speculative page fault Laurent Dufour
2018-01-16 15:11 ` [PATCH v6 00/24] Speculative page faults Kirill A. Shutemov
2018-01-17 15:15 ` Laurent Dufour
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=20180113042354.GA24241@bombadil.infradead.org \
--to=willy@infradead.org \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=alexei.starovoitov@gmail.com \
--cc=benh@kernel.crashing.org \
--cc=bsingharora@gmail.com \
--cc=dave@stgolabs.net \
--cc=haren@linux.vnet.ibm.com \
--cc=hpa@zytor.com \
--cc=jack@suse.cz \
--cc=kemi.wang@intel.com \
--cc=khandual@linux.vnet.ibm.com \
--cc=kirill@shutemov.name \
--cc=ldufour@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mhocko@kernel.org \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=sergey.senozhatsky.work@gmail.com \
--cc=sergey.senozhatsky@gmail.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=will.deacon@arm.com \
--cc=x86@kernel.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).