@@ -434,6 +434,7 @@ extern pgprot_t protection_map[16];
* @FAULT_FLAG_REMOTE: The fault is not for current task/mm.
* @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch.
* @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals.
+ * @FAULT_FLAG_PREFAULT: Fault was a prefault.
*
* About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
* whether we would allow page faults to retry by specifying these two
@@ -464,6 +465,7 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_REMOTE 0x80
#define FAULT_FLAG_INSTRUCTION 0x100
#define FAULT_FLAG_INTERRUPTIBLE 0x200
+#define FAULT_FLAG_PREFAULT 0x400
/*
* The default fault flags that should be used by most of the
@@ -501,7 +503,8 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags)
{ FAULT_FLAG_USER, "USER" }, \
{ FAULT_FLAG_REMOTE, "REMOTE" }, \
{ FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \
- { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }
+ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \
+ { FAULT_FLAG_PREFAULT, "PREFAULT" }
/*
* vm_fault is filled by the pagefault handler and passed to the vma's
@@ -3019,6 +3019,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
struct address_space *mapping = file->f_mapping;
pgoff_t last_pgoff = start_pgoff;
unsigned long address = vmf->address;
+ unsigned long flags = vmf->flags;
XA_STATE(xas, &mapping->i_pages, start_pgoff);
struct page *head, *page;
unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
@@ -3051,14 +3052,18 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
if (!pte_none(*vmf->pte))
goto unlock;
+ /* We're about to handle the fault */
+ if (vmf->address == address) {
+ vmf->flags &= ~FAULT_FLAG_PREFAULT;
+ ret = VM_FAULT_NOPAGE;
+ } else {
+ vmf->flags |= FAULT_FLAG_PREFAULT;
+ }
+
do_set_pte(vmf, page);
/* no need to invalidate: a not-present page won't be cached */
update_mmu_cache(vma, vmf->address, vmf->pte);
unlock_page(head);
-
- /* The fault is handled */
- if (vmf->address == address)
- ret = VM_FAULT_NOPAGE;
continue;
unlock:
unlock_page(head);
@@ -3067,6 +3072,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
rcu_read_unlock();
+ vmf->flags = flags;
vmf->address = address;
WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
return ret;
@@ -134,6 +134,18 @@ static inline bool arch_faults_on_old_pte(void)
}
#endif
+#ifndef arch_wants_old_prefaulted_pte
+static inline bool arch_wants_old_prefaulted_pte(void)
+{
+ /*
+ * Transitioning a PTE from 'old' to 'young' can be expensive on
+ * some architectures, even if it's performed in hardware. By
+ * default, "false" means prefaulted entries will be 'young'.
+ */
+ return false;
+}
+#endif
+
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
@@ -3725,11 +3737,17 @@ void do_set_pte(struct vm_fault *vmf, struct page *page)
{
struct vm_area_struct *vma = vmf->vma;
bool write = vmf->flags & FAULT_FLAG_WRITE;
+ bool prefault = vmf->flags & FAULT_FLAG_PREFAULT;
pte_t entry;
flush_icache_page(vma, page);
entry = mk_pte(page, vma->vm_page_prot);
- entry = pte_sw_mkyoung(entry);
+
+ if (prefault && arch_wants_old_prefaulted_pte())
+ entry = pte_mkold(entry);
+ else
+ entry = pte_sw_mkyoung(entry);
+
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
/* copy-on-write page */
Commit 5c0a85fad949 ("mm: make faultaround produce old ptes") changed the "faultaround" behaviour to initialise prefaulted PTEs as 'old', since this avoids vmscan wrongly assuming that they are hot, despite having never been explicitly accessed by userspace. The change has been shown to benefit numerous arm64 micro-architectures (with hardware access flag) running Android, where both application launch latency and direct reclaim time are significantly reduced (by 10%+ and ~80% respectively). Unfortunately, commit 315d09bf30c2 ("Revert "mm: make faultaround produce old ptes"") reverted the change due to it being identified as the cause of a ~6% regression in unixbench on x86. Experiments on a variety of recent arm64 micro-architectures indicate that unixbench is not affected by the original commit, which appears to yield a 0-1% performance improvement. Since one size does not fit all for the initial state of prefaulted PTEs, introduce arch_wants_old_prefaulted_pte(), which allows an architecture to opt-in to 'old' prefaulted PTEs at runtime based on whatever criteria it may have. Cc: Jan Kara <jack@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Reported-by: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Will Deacon <will@kernel.org> --- include/linux/mm.h | 5 ++++- mm/filemap.c | 14 ++++++++++---- mm/memory.c | 20 +++++++++++++++++++- 3 files changed, 33 insertions(+), 6 deletions(-)