#include <linux/dax.h>
#include <linux/oom.h>
#include <linux/numa.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
#include <trace/events/kmem.h>
* @pfn: source kernel pfn
* @pgprot: pgprot flags for the inserted page
*
- * This is exactly like vmf_insert_pfn(), except that it allows drivers to
+ * This is exactly like vmf_insert_pfn(), except that it allows drivers
* to override pgprot on a per-page basis.
*
* This only makes sense for IO mappings, and it makes no sense for
* @pfn: source kernel pfn
* @pgprot: pgprot flags for the inserted page
*
- * This is exactly like vmf_insert_mixed(), except that it allows drivers to
+ * This is exactly like vmf_insert_mixed(), except that it allows drivers
* to override pgprot on a per-page basis.
*
* Typically this function should be used by drivers to set caching- and
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = vmf->address;
- debug_dma_assert_idle(src);
-
if (likely(src)) {
copy_user_highpage(dst, src, addr, vma);
return true;
*/
ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
page_add_new_anon_rmap(new_page, vma, vmf->address, false);
- lru_cache_add_active_or_unevictable(new_page, vma);
+ lru_cache_add_inactive_or_unevictable(new_page, vma);
/*
* We call the notify macro here because, when using secondary
* mmu page tables (such as kvm shadow page tables), we want the
int locked;
int exclusive = 0;
vm_fault_t ret = 0;
+ void *shadow = NULL;
if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
goto out;
if (!page) {
struct swap_info_struct *si = swp_swap_info(entry);
- if (si->flags & SWP_SYNCHRONOUS_IO &&
- __swap_count(entry) == 1) {
+ if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
+ __swap_count(entry) == 1) {
/* skip swapcache */
page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
vmf->address);
goto out_page;
}
- /*
- * XXX: Move to lru_cache_add() when it
- * supports new vs putback
- */
- spin_lock_irq(&page_pgdat(page)->lru_lock);
- lru_note_cost_page(page);
- spin_unlock_irq(&page_pgdat(page)->lru_lock);
+ shadow = get_shadow_from_swap_cache(entry);
+ if (shadow)
+ workingset_refault(page, shadow);
lru_cache_add(page);
swap_readpage(page, true);
/* ksm created a completely new copy */
if (unlikely(page != swapcache && swapcache)) {
page_add_new_anon_rmap(page, vma, vmf->address, false);
- lru_cache_add_active_or_unevictable(page, vma);
+ lru_cache_add_inactive_or_unevictable(page, vma);
} else {
do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
- activate_page(page);
}
swap_free(entry);
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, vmf->address, false);
- lru_cache_add_active_or_unevictable(page, vma);
+ lru_cache_add_inactive_or_unevictable(page, vma);
setpte:
set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
if (write && !(vma->vm_flags & VM_SHARED)) {
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, vmf->address, false);
- lru_cache_add_active_or_unevictable(page, vma);
+ lru_cache_add_inactive_or_unevictable(page, vma);
} else {
inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
page_add_file_rmap(page, false);
vmf->flags & FAULT_FLAG_WRITE)) {
update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
} else {
+ /* Skip spurious TLB flush for retried page fault */
+ if (vmf->flags & FAULT_FLAG_TRIED)
+ goto unlock;
/*
* This is needed only for protection faults but the arch code
* is not yet telling us if this is a protection fault or not.
return handle_pte_fault(&vmf);
}
+/**
+ * mm_account_fault - Do page fault accountings
+ *
+ * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting
+ * of perf event counters, but we'll still do the per-task accounting to
+ * the task who triggered this page fault.
+ * @address: the faulted address.
+ * @flags: the fault flags.
+ * @ret: the fault retcode.
+ *
+ * This will take care of most of the page fault accountings. Meanwhile, it
+ * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter
+ * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
+ * still be in per-arch page fault handlers at the entry of page fault.
+ */
+static inline void mm_account_fault(struct pt_regs *regs,
+ unsigned long address, unsigned int flags,
+ vm_fault_t ret)
+{
+ bool major;
+
+ /*
+ * We don't do accounting for some specific faults:
+ *
+ * - Unsuccessful faults (e.g. when the address wasn't valid). That
+ * includes arch_vma_access_permitted() failing before reaching here.
+ * So this is not a "this many hardware page faults" counter. We
+ * should use the hw profiling for that.
+ *
+ * - Incomplete faults (VM_FAULT_RETRY). They will only be counted
+ * once they're completed.
+ */
+ if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY))
+ return;
+
+ /*
+ * We define the fault as a major fault when the final successful fault
+ * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't
+ * handle it immediately previously).
+ */
+ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);
+
+ if (major)
+ current->maj_flt++;
+ else
+ current->min_flt++;
+
+ /*
+ * If the fault is done for GUP, regs will be NULL. We only do the
+ * accounting for the per thread fault counters who triggered the
+ * fault, and we skip the perf event updates.
+ */
+ if (!regs)
+ return;
+
+ if (major)
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+ else
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+}
+
/*
* By the time we get here, we already hold the mm semaphore
*
* return value. See filemap_fault() and __lock_page_or_retry().
*/
vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
- unsigned int flags)
+ unsigned int flags, struct pt_regs *regs)
{
vm_fault_t ret;
mem_cgroup_oom_synchronize(false);
}
+ mm_account_fault(regs, address, flags, ret);
+
return ret;
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
void *maddr;
struct page *page = NULL;
- ret = get_user_pages_remote(tsk, mm, addr, 1,
+ ret = get_user_pages_remote(mm, addr, 1,
gup_flags, &page, &vma, NULL);
if (ret <= 0) {
#ifndef CONFIG_HAVE_IOREMAP_PROT
projects / linux-2.6-microblaze.git / blobdiff