| 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: <761F148B-555B-4C51-8A1E-F17ABA85D014@nvidia.com>
Date: Tue, 03 Jan 2023 13:40:00 -0500
From: Zi Yan <ziy@...dia.com>
To: Huang Ying <ying.huang@...el.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, Yang Shi <shy828301@...il.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>,
Oscar Salvador <osalvador@...e.de>,
Matthew Wilcox <willy@...radead.org>,
Bharata B Rao <bharata@....com>,
Alistair Popple <apopple@...dia.com>,
haoxin <xhao@...ux.alibaba.com>
Subject: Re: [PATCH 3/8] migrate_pages: restrict number of pages to migrate in
batch
On 26 Dec 2022, at 19:28, Huang Ying wrote:
> This is a preparation patch to batch the folio unmapping and moving
> for non-hugetlb folios.
>
> If we had batched the folio unmapping, all folios to be migrated would
> be unmapped before copying the contents and flags of the folios. If
> the folios that were passed to migrate_pages() were too many in unit
> of pages, the execution of the processes would be stopped for too long
> time, thus too long latency. For example, migrate_pages() syscall
> will call migrate_pages() with all folios of a process. To avoid this
> possible issue, in this patch, we restrict the number of pages to be
> migrated to be no more than HPAGE_PMD_NR. That is, the influence is
> at the same level of THP migration.
>
> Signed-off-by: "Huang, Ying" <ying.huang@...el.com>
> Cc: Zi Yan <ziy@...dia.com>
> Cc: Yang Shi <shy828301@...il.com>
> Cc: Baolin Wang <baolin.wang@...ux.alibaba.com>
> Cc: Oscar Salvador <osalvador@...e.de>
> Cc: Matthew Wilcox <willy@...radead.org>
> Cc: Bharata B Rao <bharata@....com>
> Cc: Alistair Popple <apopple@...dia.com>
> Cc: haoxin <xhao@...ux.alibaba.com>
> ---
> mm/migrate.c | 173 +++++++++++++++++++++++++++++++--------------------
> 1 file changed, 106 insertions(+), 67 deletions(-)
>
> diff --git a/mm/migrate.c b/mm/migrate.c
> index bdbe73fe2eb7..97ea0737ab2b 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -1485,40 +1485,15 @@ static int migrate_hugetlbs(struct list_head *from, new_page_t get_new_page,
> return rc;
> }
>
> -/*
> - * migrate_pages - migrate the folios specified in a list, to the free folios
> - * supplied as the target for the page migration
> - *
> - * @from: The list of folios to be migrated.
> - * @get_new_page: The function used to allocate free folios to be used
> - * as the target of the folio migration.
> - * @put_new_page: The function used to free target folios if migration
> - * fails, or NULL if no special handling is necessary.
> - * @private: Private data to be passed on to get_new_page()
> - * @mode: The migration mode that specifies the constraints for
> - * folio migration, if any.
> - * @reason: The reason for folio migration.
> - * @ret_succeeded: Set to the number of folios migrated successfully if
> - * the caller passes a non-NULL pointer.
> - *
> - * The function returns after 10 attempts or if no folios are movable any more
> - * because the list has become empty or no retryable folios exist any more.
> - * It is caller's responsibility to call putback_movable_pages() to return folios
> - * to the LRU or free list only if ret != 0.
> - *
> - * Returns the number of {normal folio, large folio, hugetlb} that were not
> - * migrated, or an error code. The number of large folio splits will be
> - * considered as the number of non-migrated large folio, no matter how many
> - * split folios of the large folio are migrated successfully.
> - */
> -int migrate_pages(struct list_head *from, new_page_t get_new_page,
> +static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page,
> free_page_t put_new_page, unsigned long private,
> - enum migrate_mode mode, int reason, unsigned int *ret_succeeded)
> + enum migrate_mode mode, int reason, struct list_head *ret_folios,
> + struct migrate_pages_stats *stats)
> {
> int retry = 1;
> int large_retry = 1;
> int thp_retry = 1;
> - int nr_failed;
> + int nr_failed = 0;
> int nr_retry_pages = 0;
> int nr_large_failed = 0;
> int pass = 0;
> @@ -1526,20 +1501,9 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> bool is_thp = false;
> struct folio *folio, *folio2;
> int rc, nr_pages;
> - LIST_HEAD(ret_folios);
> LIST_HEAD(split_folios);
> bool nosplit = (reason == MR_NUMA_MISPLACED);
> bool no_split_folio_counting = false;
> - struct migrate_pages_stats stats;
> -
> - trace_mm_migrate_pages_start(mode, reason);
> -
> - memset(&stats, 0, sizeof(stats));
> - rc = migrate_hugetlbs(from, get_new_page, put_new_page, private, mode, reason,
> - &stats, &ret_folios);
> - if (rc < 0)
> - goto out;
> - nr_failed = rc;
>
> split_folio_migration:
> for (pass = 0; pass < 10 && (retry || large_retry); pass++) {
> @@ -1549,11 +1513,6 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> nr_retry_pages = 0;
>
> list_for_each_entry_safe(folio, folio2, from, lru) {
> - if (folio_test_hugetlb(folio)) {
> - list_move_tail(&folio->lru, &ret_folios);
> - continue;
> - }
> -
> /*
> * Large folio statistics is based on the source large
> * folio. Capture required information that might get
> @@ -1567,15 +1526,14 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>
> rc = unmap_and_move(get_new_page, put_new_page,
> private, folio, pass > 2, mode,
> - reason, &ret_folios);
> + reason, ret_folios);
> /*
> * The rules are:
> * Success: folio will be freed
> * -EAGAIN: stay on the from list
> * -ENOMEM: stay on the from list
> * -ENOSYS: stay on the from list
> - * Other errno: put on ret_folios list then splice to
> - * from list
> + * Other errno: put on ret_folios list
> */
> switch(rc) {
> /*
> @@ -1592,17 +1550,17 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> /* Large folio migration is unsupported */
> if (is_large) {
> nr_large_failed++;
> - stats.nr_thp_failed += is_thp;
> + stats->nr_thp_failed += is_thp;
> if (!try_split_folio(folio, &split_folios)) {
> - stats.nr_thp_split += is_thp;
> + stats->nr_thp_split += is_thp;
> break;
> }
> } else if (!no_split_folio_counting) {
> nr_failed++;
> }
>
> - stats.nr_failed_pages += nr_pages;
> - list_move_tail(&folio->lru, &ret_folios);
> + stats->nr_failed_pages += nr_pages;
> + list_move_tail(&folio->lru, ret_folios);
> break;
> case -ENOMEM:
> /*
> @@ -1611,13 +1569,13 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> */
> if (is_large) {
> nr_large_failed++;
> - stats.nr_thp_failed += is_thp;
> + stats->nr_thp_failed += is_thp;
> /* Large folio NUMA faulting doesn't split to retry. */
> if (!nosplit) {
> int ret = try_split_folio(folio, &split_folios);
>
> if (!ret) {
> - stats.nr_thp_split += is_thp;
> + stats->nr_thp_split += is_thp;
> break;
> } else if (reason == MR_LONGTERM_PIN &&
> ret == -EAGAIN) {
> @@ -1635,17 +1593,17 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> nr_failed++;
> }
>
> - stats.nr_failed_pages += nr_pages + nr_retry_pages;
> + stats->nr_failed_pages += nr_pages + nr_retry_pages;
> /*
> * There might be some split folios of fail-to-migrate large
> - * folios left in split_folios list. Move them back to migration
> + * folios left in split_folios list. Move them to ret_folios
> * list so that they could be put back to the right list by
> * the caller otherwise the folio refcnt will be leaked.
> */
> - list_splice_init(&split_folios, from);
> + list_splice_init(&split_folios, ret_folios);
> /* nr_failed isn't updated for not used */
> nr_large_failed += large_retry;
> - stats.nr_thp_failed += thp_retry;
> + stats->nr_thp_failed += thp_retry;
> goto out;
> case -EAGAIN:
> if (is_large) {
> @@ -1657,8 +1615,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> nr_retry_pages += nr_pages;
> break;
> case MIGRATEPAGE_SUCCESS:
> - stats.nr_succeeded += nr_pages;
> - stats.nr_thp_succeeded += is_thp;
> + stats->nr_succeeded += nr_pages;
> + stats->nr_thp_succeeded += is_thp;
> break;
> default:
> /*
> @@ -1669,20 +1627,20 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> */
> if (is_large) {
> nr_large_failed++;
> - stats.nr_thp_failed += is_thp;
> + stats->nr_thp_failed += is_thp;
> } else if (!no_split_folio_counting) {
> nr_failed++;
> }
>
> - stats.nr_failed_pages += nr_pages;
> + stats->nr_failed_pages += nr_pages;
> break;
> }
> }
> }
> nr_failed += retry;
> nr_large_failed += large_retry;
> - stats.nr_thp_failed += thp_retry;
> - stats.nr_failed_pages += nr_retry_pages;
> + stats->nr_thp_failed += thp_retry;
> + stats->nr_failed_pages += nr_retry_pages;
> /*
> * Try to migrate split folios of fail-to-migrate large folios, no
> * nr_failed counting in this round, since all split folios of a
> @@ -1693,7 +1651,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> * Move non-migrated folios (after 10 retries) to ret_folios
> * to avoid migrating them again.
> */
> - list_splice_init(from, &ret_folios);
> + list_splice_init(from, ret_folios);
> list_splice_init(&split_folios, from);
> no_split_folio_counting = true;
> retry = 1;
> @@ -1701,6 +1659,87 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> }
>
> rc = nr_failed + nr_large_failed;
> +out:
> + return rc;
> +}
> +
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +#define NR_MAX_BATCHED_MIGRATION HPAGE_PMD_NR
> +#else
> +#define NR_MAX_BATCHED_MIGRATION 512
> +#endif
> +
> +/*
> + * migrate_pages - migrate the folios specified in a list, to the free folios
> + * supplied as the target for the page migration
> + *
> + * @from: The list of folios to be migrated.
> + * @get_new_page: The function used to allocate free folios to be used
> + * as the target of the folio migration.
> + * @put_new_page: The function used to free target folios if migration
> + * fails, or NULL if no special handling is necessary.
> + * @private: Private data to be passed on to get_new_page()
> + * @mode: The migration mode that specifies the constraints for
> + * folio migration, if any.
> + * @reason: The reason for folio migration.
> + * @ret_succeeded: Set to the number of folios migrated successfully if
> + * the caller passes a non-NULL pointer.
> + *
> + * The function returns after 10 attempts or if no folios are movable any more
> + * because the list has become empty or no retryable folios exist any more.
> + * It is caller's responsibility to call putback_movable_pages() to return folios
> + * to the LRU or free list only if ret != 0.
> + *
> + * Returns the number of {normal folio, large folio, hugetlb} that were not
> + * migrated, or an error code. The number of large folio splits will be
> + * considered as the number of non-migrated large folio, no matter how many
> + * split folios of the large folio are migrated successfully.
> + */
> +int migrate_pages(struct list_head *from, new_page_t get_new_page,
> + free_page_t put_new_page, unsigned long private,
> + enum migrate_mode mode, int reason, unsigned int *ret_succeeded)
> +{
> + int rc, rc_gether;
rc_gether -> rc_gather?
> + int nr_pages;
> + struct folio *folio, *folio2;
> + LIST_HEAD(folios);
> + LIST_HEAD(ret_folios);
> + struct migrate_pages_stats stats;
> +
> + trace_mm_migrate_pages_start(mode, reason);
> +
> + memset(&stats, 0, sizeof(stats));
> +
> + rc_gether = migrate_hugetlbs(from, get_new_page, put_new_page, private,
> + mode, reason, &stats, &ret_folios);
> + if (rc_gether < 0)
> + goto out;
> +again:
> + nr_pages = 0;
> + list_for_each_entry_safe(folio, folio2, from, lru) {
> + if (folio_test_hugetlb(folio)) {
> + list_move_tail(&folio->lru, &ret_folios);
> + continue;
> + }
> +
> + nr_pages += folio_nr_pages(folio);
> + if (nr_pages > NR_MAX_BATCHED_MIGRATION)
> + break;
> + }
> + if (nr_pages > NR_MAX_BATCHED_MIGRATION)
> + list_cut_before(&folios, from, &folio->lru);
> + else
> + list_splice_init(from, &folios);
> + rc = migrate_pages_batch(&folios, get_new_page, put_new_page, private,
> + mode, reason, &ret_folios, &stats);
> + list_splice_tail_init(&folios, &ret_folios);
> + if (rc < 0) {
> + rc_gether = rc;
> + goto out;
> + }
> + rc_gether += rc;
> + if (!list_empty(from))
> + goto again;
> out:
> /*
> * Put the permanent failure folio back to migration list, they
> @@ -1713,7 +1752,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> * are migrated successfully.
> */
> if (list_empty(from))
> - rc = 0;
> + rc_gether = 0;
>
> count_vm_events(PGMIGRATE_SUCCESS, stats.nr_succeeded);
> count_vm_events(PGMIGRATE_FAIL, stats.nr_failed_pages);
> @@ -1727,7 +1766,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> if (ret_succeeded)
> *ret_succeeded = stats.nr_succeeded;
>
> - return rc;
> + return rc_gether;
> }
>
> struct page *alloc_migration_target(struct page *page, unsigned long private)
> --
> 2.35.1
--
Best Regards,
Yan, Zi
Download attachment "signature.asc" of type "application/pgp-signature" (855 bytes)
Powered by blists - more mailing lists