| Message ID | 20240928021620.8369-6-kanchana.p.sridhar@intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm: zswap swap-out of large folios | expand |
On Fri, Sep 27, 2024 at 7:16 PM Kanchana P Sridhar <kanchana.p.sridhar@intel.com> wrote: > > For zswap_store() to support large folios, we need to be able to do > a batch update of zswap_stored_pages upon successful store of all pages > in the folio. For this, we need to add folio_nr_pages(), which returns > a long, to zswap_stored_pages. Do we really need this? A lot of places in the kernel assign the result of folio_nr_pages() to an int (thp_nr_pages(), split_huge_pages_all(), etc). I don't think we need to worry about folio_nr_pages() exceeding INT_MAX for a while. > > Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> > --- > fs/proc/meminfo.c | 2 +- > include/linux/zswap.h | 2 +- > mm/zswap.c | 19 +++++++++++++------ > 3 files changed, 15 insertions(+), 8 deletions(-) > > diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c > index 245171d9164b..8ba9b1472390 100644 > --- a/fs/proc/meminfo.c > +++ b/fs/proc/meminfo.c > @@ -91,7 +91,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) > #ifdef CONFIG_ZSWAP > show_val_kb(m, "Zswap: ", zswap_total_pages()); > seq_printf(m, "Zswapped: %8lu kB\n", > - (unsigned long)atomic_read(&zswap_stored_pages) << > + (unsigned long)atomic_long_read(&zswap_stored_pages) << > (PAGE_SHIFT - 10)); > #endif > show_val_kb(m, "Dirty: ", > diff --git a/include/linux/zswap.h b/include/linux/zswap.h > index 9cd1beef0654..d961ead91bf1 100644 > --- a/include/linux/zswap.h > +++ b/include/linux/zswap.h > @@ -7,7 +7,7 @@ > > struct lruvec; > > -extern atomic_t zswap_stored_pages; > +extern atomic_long_t zswap_stored_pages; > > #ifdef CONFIG_ZSWAP > > diff --git a/mm/zswap.c b/mm/zswap.c > index 0f281e50a034..43e4e216db41 100644 > --- a/mm/zswap.c > +++ b/mm/zswap.c > @@ -43,7 +43,7 @@ > * statistics > **********************************/ > /* The number of compressed pages currently stored in zswap */ > -atomic_t zswap_stored_pages = ATOMIC_INIT(0); > +atomic_long_t zswap_stored_pages = ATOMIC_INIT(0); > > /* > * The statistics below are not protected from concurrent access for > @@ -802,7 +802,7 @@ static void zswap_entry_free(struct zswap_entry *entry) > obj_cgroup_put(entry->objcg); > } > zswap_entry_cache_free(entry); > - atomic_dec(&zswap_stored_pages); > + atomic_long_dec(&zswap_stored_pages); > } > > /********************************* > @@ -1232,7 +1232,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, > nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); > } else { > nr_backing = zswap_total_pages(); > - nr_stored = atomic_read(&zswap_stored_pages); > + nr_stored = atomic_long_read(&zswap_stored_pages); > } > > if (!nr_stored) > @@ -1501,7 +1501,7 @@ bool zswap_store(struct folio *folio) > } > > /* update stats */ > - atomic_inc(&zswap_stored_pages); > + atomic_long_inc(&zswap_stored_pages); > count_vm_event(ZSWPOUT); > > return true; > @@ -1650,6 +1650,13 @@ static int debugfs_get_total_size(void *data, u64 *val) > } > DEFINE_DEBUGFS_ATTRIBUTE(total_size_fops, debugfs_get_total_size, NULL, "%llu\n"); > > +static int debugfs_get_stored_pages(void *data, u64 *val) > +{ > + *val = atomic_long_read(&zswap_stored_pages); > + return 0; > +} > +DEFINE_DEBUGFS_ATTRIBUTE(stored_pages_fops, debugfs_get_stored_pages, NULL, "%llu\n"); > + > static int zswap_debugfs_init(void) > { > if (!debugfs_initialized()) > @@ -1673,8 +1680,8 @@ static int zswap_debugfs_init(void) > zswap_debugfs_root, &zswap_written_back_pages); > debugfs_create_file("pool_total_size", 0444, > zswap_debugfs_root, NULL, &total_size_fops); > - debugfs_create_atomic_t("stored_pages", 0444, > - zswap_debugfs_root, &zswap_stored_pages); > + debugfs_create_file("stored_pages", 0444, > + zswap_debugfs_root, NULL, &stored_pages_fops); > > return 0; > } > -- > 2.27.0 >
On Fri, Sep 27, 2024 at 07:57:49PM -0700, Yosry Ahmed wrote: > On Fri, Sep 27, 2024 at 7:16 PM Kanchana P Sridhar > <kanchana.p.sridhar@intel.com> wrote: > > > > For zswap_store() to support large folios, we need to be able to do > > a batch update of zswap_stored_pages upon successful store of all pages > > in the folio. For this, we need to add folio_nr_pages(), which returns > > a long, to zswap_stored_pages. > > Do we really need this? A lot of places in the kernel assign the > result of folio_nr_pages() to an int (thp_nr_pages(), > split_huge_pages_all(), etc). I don't think we need to worry about > folio_nr_pages() exceeding INT_MAX for a while. You'd be surprised. Let's assume we add support for PUD-sized pages (personally I think this is too large to make sense, but some people can't be told). On arm64, we can have a 64kB page size, so that's 13 bits per level for a total of 2^26 pages per PUD. That feels uncomfortable close to 2^32 to me. Anywhere you've found that's using an int to store folio_nr_pages() is somewhere we should probably switch to long. And this, btw, is why I've moved from using an int to store folio_size() to using size_t. A PMD is already 512MB (with a 64KB page size), and so a PUD will be 4TB. thp_nr_pages() is not a good example. I'll be happy when we kill it; we're actually almost there.
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 245171d9164b..8ba9b1472390 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -91,7 +91,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_ZSWAP show_val_kb(m, "Zswap: ", zswap_total_pages()); seq_printf(m, "Zswapped: %8lu kB\n", - (unsigned long)atomic_read(&zswap_stored_pages) << + (unsigned long)atomic_long_read(&zswap_stored_pages) << (PAGE_SHIFT - 10)); #endif show_val_kb(m, "Dirty: ", diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 9cd1beef0654..d961ead91bf1 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -7,7 +7,7 @@ struct lruvec; -extern atomic_t zswap_stored_pages; +extern atomic_long_t zswap_stored_pages; #ifdef CONFIG_ZSWAP diff --git a/mm/zswap.c b/mm/zswap.c index 0f281e50a034..43e4e216db41 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -43,7 +43,7 @@ * statistics **********************************/ /* The number of compressed pages currently stored in zswap */ -atomic_t zswap_stored_pages = ATOMIC_INIT(0); +atomic_long_t zswap_stored_pages = ATOMIC_INIT(0); /* * The statistics below are not protected from concurrent access for @@ -802,7 +802,7 @@ static void zswap_entry_free(struct zswap_entry *entry) obj_cgroup_put(entry->objcg); } zswap_entry_cache_free(entry); - atomic_dec(&zswap_stored_pages); + atomic_long_dec(&zswap_stored_pages); } /********************************* @@ -1232,7 +1232,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); } else { nr_backing = zswap_total_pages(); - nr_stored = atomic_read(&zswap_stored_pages); + nr_stored = atomic_long_read(&zswap_stored_pages); } if (!nr_stored) @@ -1501,7 +1501,7 @@ bool zswap_store(struct folio *folio) } /* update stats */ - atomic_inc(&zswap_stored_pages); + atomic_long_inc(&zswap_stored_pages); count_vm_event(ZSWPOUT); return true; @@ -1650,6 +1650,13 @@ static int debugfs_get_total_size(void *data, u64 *val) } DEFINE_DEBUGFS_ATTRIBUTE(total_size_fops, debugfs_get_total_size, NULL, "%llu\n"); +static int debugfs_get_stored_pages(void *data, u64 *val) +{ + *val = atomic_long_read(&zswap_stored_pages); + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(stored_pages_fops, debugfs_get_stored_pages, NULL, "%llu\n"); + static int zswap_debugfs_init(void) { if (!debugfs_initialized()) @@ -1673,8 +1680,8 @@ static int zswap_debugfs_init(void) zswap_debugfs_root, &zswap_written_back_pages); debugfs_create_file("pool_total_size", 0444, zswap_debugfs_root, NULL, &total_size_fops); - debugfs_create_atomic_t("stored_pages", 0444, - zswap_debugfs_root, &zswap_stored_pages); + debugfs_create_file("stored_pages", 0444, + zswap_debugfs_root, NULL, &stored_pages_fops); return 0; }
For zswap_store() to support large folios, we need to be able to do a batch update of zswap_stored_pages upon successful store of all pages in the folio. For this, we need to add folio_nr_pages(), which returns a long, to zswap_stored_pages. Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> --- fs/proc/meminfo.c | 2 +- include/linux/zswap.h | 2 +- mm/zswap.c | 19 +++++++++++++------ 3 files changed, 15 insertions(+), 8 deletions(-)