| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAF8kJuNVFq_jWFM3h0fLaUu+kVwa7zWvD3A_AJ1PxR+0Yyw_Dw@mail.gmail.com>
Date: Sat, 27 Jan 2024 12:06:16 -0800
From: Chris Li <chrisl@...nel.org>
To: Barry Song <21cnbao@...il.com>
Cc: ryan.roberts@....com, akpm@...ux-foundation.org, david@...hat.com,
linux-mm@...ck.org, linux-kernel@...r.kernel.org, mhocko@...e.com,
shy828301@...il.com, wangkefeng.wang@...wei.com, willy@...radead.org,
xiang@...nel.org, ying.huang@...el.com, yuzhao@...gle.com, surenb@...gle.com,
steven.price@....com, Chuanhua Han <hanchuanhua@...o.com>,
Barry Song <v-songbaohua@...o.com>
Subject: Re: [PATCH RFC 4/6] mm: support large folios swapin as a whole
On Thu, Jan 18, 2024 at 3:12 AM Barry Song <21cnbao@...il.com> wrote:
>
> From: Chuanhua Han <hanchuanhua@...o.com>
>
> On an embedded system like Android, more than half of anon memory is actually
> in swap devices such as zRAM. For example, while an app is switched to back-
> ground, its most memory might be swapped-out.
>
> Now we have mTHP features, unfortunately, if we don't support large folios
> swap-in, once those large folios are swapped-out, we immediately lose the
> performance gain we can get through large folios and hardware optimization
> such as CONT-PTE.
>
> This patch brings up mTHP swap-in support. Right now, we limit mTHP swap-in
> to those contiguous swaps which were likely swapped out from mTHP as a whole.
>
> On the other hand, the current implementation only covers the SWAP_SYCHRONOUS
> case. It doesn't support swapin_readahead as large folios yet.
>
> Right now, we are re-faulting large folios which are still in swapcache as a
> whole, this can effectively decrease extra loops and early-exitings which we
> have increased in arch_swap_restore() while supporting MTE restore for folios
> rather than page.
>
> Signed-off-by: Chuanhua Han <hanchuanhua@...o.com>
> Co-developed-by: Barry Song <v-songbaohua@...o.com>
> Signed-off-by: Barry Song <v-songbaohua@...o.com>
> ---
> mm/memory.c | 108 +++++++++++++++++++++++++++++++++++++++++++++-------
> 1 file changed, 94 insertions(+), 14 deletions(-)
>
> diff --git a/mm/memory.c b/mm/memory.c
> index f61a48929ba7..928b3f542932 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -107,6 +107,8 @@ EXPORT_SYMBOL(mem_map);
> static vm_fault_t do_fault(struct vm_fault *vmf);
> static vm_fault_t do_anonymous_page(struct vm_fault *vmf);
> static bool vmf_pte_changed(struct vm_fault *vmf);
> +static struct folio *alloc_anon_folio(struct vm_fault *vmf,
> + bool (*pte_range_check)(pte_t *, int));
>
> /*
> * Return true if the original pte was a uffd-wp pte marker (so the pte was
> @@ -3784,6 +3786,34 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
> return VM_FAULT_SIGBUS;
> }
>
> +static bool pte_range_swap(pte_t *pte, int nr_pages)
> +{
> + int i;
> + swp_entry_t entry;
> + unsigned type;
> + pgoff_t start_offset;
> +
> + entry = pte_to_swp_entry(ptep_get_lockless(pte));
> + if (non_swap_entry(entry))
> + return false;
> + start_offset = swp_offset(entry);
> + if (start_offset % nr_pages)
> + return false;
> +
> + type = swp_type(entry);
> + for (i = 1; i < nr_pages; i++) {
> + entry = pte_to_swp_entry(ptep_get_lockless(pte + i));
> + if (non_swap_entry(entry))
> + return false;
> + if (swp_offset(entry) != start_offset + i)
> + return false;
> + if (swp_type(entry) != type)
> + return false;
> + }
> +
> + return true;
> +}
> +
> /*
> * We enter with non-exclusive mmap_lock (to exclude vma changes,
> * but allow concurrent faults), and pte mapped but not yet locked.
> @@ -3804,6 +3834,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> pte_t pte;
> vm_fault_t ret = 0;
> void *shadow = NULL;
> + int nr_pages = 1;
> + unsigned long start_address;
> + pte_t *start_pte;
>
> if (!pte_unmap_same(vmf))
> goto out;
> @@ -3868,13 +3901,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
> __swap_count(entry) == 1) {
> /* skip swapcache */
> - folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
> - vma, vmf->address, false);
> + folio = alloc_anon_folio(vmf, pte_range_swap);
> page = &folio->page;
> if (folio) {
> __folio_set_locked(folio);
> __folio_set_swapbacked(folio);
>
> + if (folio_test_large(folio)) {
> + unsigned long start_offset;
> +
> + nr_pages = folio_nr_pages(folio);
> + start_offset = swp_offset(entry) & ~(nr_pages - 1);
> + entry = swp_entry(swp_type(entry), start_offset);
> + }
> +
> if (mem_cgroup_swapin_charge_folio(folio,
> vma->vm_mm, GFP_KERNEL,
> entry)) {
> @@ -3980,6 +4020,39 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> */
> vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
> &vmf->ptl);
> +
> + start_address = vmf->address;
> + start_pte = vmf->pte;
> + if (folio_test_large(folio)) {
> + unsigned long nr = folio_nr_pages(folio);
> + unsigned long addr = ALIGN_DOWN(vmf->address, nr * PAGE_SIZE);
> + pte_t *pte_t = vmf->pte - (vmf->address - addr) / PAGE_SIZE;
I forgot about one comment here.
Please change the variable name other than "pte_t", it is a bit
strange to use the typedef name as variable name here.
Chris
> +
> + /*
> + * case 1: we are allocating large_folio, try to map it as a whole
> + * iff the swap entries are still entirely mapped;
> + * case 2: we hit a large folio in swapcache, and all swap entries
> + * are still entirely mapped, try to map a large folio as a whole.
> + * otherwise, map only the faulting page within the large folio
> + * which is swapcache
> + */
> + if (pte_range_swap(pte_t, nr)) {
> + start_address = addr;
> + start_pte = pte_t;
> + if (unlikely(folio == swapcache)) {
> + /*
> + * the below has been done before swap_read_folio()
> + * for case 1
> + */
> + nr_pages = nr;
> + entry = pte_to_swp_entry(ptep_get(start_pte));
> + page = &folio->page;
> + }
> + } else if (nr_pages > 1) { /* ptes have changed for case 1 */
> + goto out_nomap;
> + }
> + }
> +
> if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte)))
> goto out_nomap;
>
> @@ -4047,12 +4120,14 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> * We're already holding a reference on the page but haven't mapped it
> * yet.
> */
> - swap_free(entry);
> + swap_nr_free(entry, nr_pages);
> if (should_try_to_free_swap(folio, vma, vmf->flags))
> folio_free_swap(folio);
>
> - inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
> - dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
> + folio_ref_add(folio, nr_pages - 1);
> + add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
> + add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages);
> +
> pte = mk_pte(page, vma->vm_page_prot);
>
> /*
> @@ -4062,14 +4137,14 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> * exclusivity.
> */
> if (!folio_test_ksm(folio) &&
> - (exclusive || folio_ref_count(folio) == 1)) {
> + (exclusive || folio_ref_count(folio) == nr_pages)) {
> if (vmf->flags & FAULT_FLAG_WRITE) {
> pte = maybe_mkwrite(pte_mkdirty(pte), vma);
> vmf->flags &= ~FAULT_FLAG_WRITE;
> }
> rmap_flags |= RMAP_EXCLUSIVE;
> }
> - flush_icache_page(vma, page);
> + flush_icache_pages(vma, page, nr_pages);
> if (pte_swp_soft_dirty(vmf->orig_pte))
> pte = pte_mksoft_dirty(pte);
> if (pte_swp_uffd_wp(vmf->orig_pte))
> @@ -4081,14 +4156,15 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> folio_add_new_anon_rmap(folio, vma, vmf->address);
> folio_add_lru_vma(folio, vma);
> } else {
> - folio_add_anon_rmap_pte(folio, page, vma, vmf->address,
> + folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, start_address,
> rmap_flags);
> }
>
> VM_BUG_ON(!folio_test_anon(folio) ||
> (pte_write(pte) && !PageAnonExclusive(page)));
> - set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
> - arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
> + set_ptes(vma->vm_mm, start_address, start_pte, pte, nr_pages);
> +
> + arch_do_swap_page(vma->vm_mm, vma, start_address, pte, vmf->orig_pte);
>
> folio_unlock(folio);
> if (folio != swapcache && swapcache) {
> @@ -4105,6 +4181,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> }
>
> if (vmf->flags & FAULT_FLAG_WRITE) {
> + if (folio_test_large(folio) && nr_pages > 1)
> + vmf->orig_pte = ptep_get(vmf->pte);
> +
> ret |= do_wp_page(vmf);
> if (ret & VM_FAULT_ERROR)
> ret &= VM_FAULT_ERROR;
> @@ -4112,7 +4191,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> }
>
> /* No need to invalidate - it was non-present before */
> - update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
> + update_mmu_cache_range(vmf, vma, start_address, start_pte, nr_pages);
> unlock:
> if (vmf->pte)
> pte_unmap_unlock(vmf->pte, vmf->ptl);
> @@ -4148,7 +4227,8 @@ static bool pte_range_none(pte_t *pte, int nr_pages)
> return true;
> }
>
> -static struct folio *alloc_anon_folio(struct vm_fault *vmf)
> +static struct folio *alloc_anon_folio(struct vm_fault *vmf,
> + bool (*pte_range_check)(pte_t *, int))
> {
> #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> struct vm_area_struct *vma = vmf->vma;
> @@ -4190,7 +4270,7 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
> order = highest_order(orders);
> while (orders) {
> addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
> - if (pte_range_none(pte + pte_index(addr), 1 << order))
> + if (pte_range_check(pte + pte_index(addr), 1 << order))
> break;
> order = next_order(&orders, order);
> }
> @@ -4269,7 +4349,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
> if (unlikely(anon_vma_prepare(vma)))
> goto oom;
> /* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */
> - folio = alloc_anon_folio(vmf);
> + folio = alloc_anon_folio(vmf, pte_range_none);
> if (IS_ERR(folio))
> return 0;
> if (!folio)
> --
> 2.34.1
>
>
Powered by blists - more mailing lists