From: Charan Teja Reddy <charante@xxxxxxxxxxxxxx> Currently fadvise(2) is supported only for the files that doesn't associated with noop_backing_dev_info thus for the files, like shmem, fadvise results into NOP. But then there is file_operations->fadvise() that lets the file systems to implement their own fadvise implementation. Use this support to implement some of the POSIX_FADV_XXX functionality for shmem files. This patch aims to implement POSIX_FADV_WILLNEED and POSIX_FADV_DONTNEED advices to shmem files which can be helpful for the drivers who may want to manage the shmem pages of the files that are created through shmem_file_setup[_with_mnt](). An example usecase may be like, driver can create the shmem file of the size equal to its requirements and map the pages for DMA and then pass the fd to user. The user who knows well about the usage of these pages can now decide when these pages are not required push them to swap through DONTNEED thus free up memory well in advance rather than relying on the reclaim and use WILLNEED when it decide that they are useful in the near future. IOW, it lets the clients to free up/read the memory when it wants to. Another usecase is that GEM objets which are currenlty allocated and managed through shmem files can use vfs_fadvise(DONT|WILLNEED) on shmem fd when the driver comes to know(like through some hints from user space) that GEM objects are not going to use/will need in the near future. Signed-off-by: Charan Teja Reddy <charante@xxxxxxxxxxxxxx> --- Changes in V2: -- Rearranged the code to not to sleep with rcu_lock while using xas_() functionality. -- Addressed the comments from Suren. changes in V1: -- Created the interface for fadvise(2) to work on shmem files. -- https://patchwork.kernel.org/project/linux-mm/patch/1633701982-22302-1-git-send-email-charante@xxxxxxxxxxxxxx/ mm/shmem.c | 167 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 167 insertions(+) diff --git a/mm/shmem.c b/mm/shmem.c index 70d9ce2..4c4685f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -38,6 +38,8 @@ #include <linux/hugetlb.h> #include <linux/frontswap.h> #include <linux/fs_parser.h> +#include <linux/mm_inline.h> +#include <linux/fadvise.h> #include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */ @@ -2792,6 +2794,170 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, return error; } +static void shmem_isolate_pages_range(struct address_space *mapping, loff_t start, + loff_t end, struct list_head *list) +{ + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; + + rcu_read_lock(); + xas_for_each(&xas, page, end) { + if (xas_retry(&xas, page)) + continue; + if (xa_is_value(page)) + continue; + if (!get_page_unless_zero(page)) + continue; + if (isolate_lru_page(page)) + continue; + + list_add(&page->lru, list); + inc_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); + put_page(page); + if (need_resched()) { + xas_pause(&xas); + cond_resched_rcu(); + } + } + rcu_read_unlock(); +} + +static int shmem_fadvise_dontneed(struct address_space *mapping, loff_t start, + loff_t end) +{ + int ret; + struct page *page; + LIST_HEAD(list); + + if (!shmem_mapping(mapping)) + return -EINVAL; + + if (!total_swap_pages) + return 0; + + lru_add_drain(); + shmem_isolate_pages_range(mapping, start, end, &list); + + while (!list_empty(&list)) { + page = lru_to_page(&list); + list_del(&page->lru); + lock_page(page); + if (clear_page_dirty_for_io(page)) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .nr_to_write = LONG_MAX, + .range_start = 0, + .range_end = LLONG_MAX, + .for_reclaim = 1, + }; + + SetPageReclaim(page); + ret = shmem_writepage(page, &wbc); + if (ret || PageWriteback(page)) { + if (ret) + unlock_page(page); + putback_lru_page(page); + dec_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); + continue; + } + } + + if (!PageWriteback(page)) + ClearPageReclaim(page); + + /* + * shmem_writepage() place the page in the swapcache. + * Delete the page from the swapcache and release the + * page. + */ + dec_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); + lock_page(page); + delete_from_swap_cache(page); + unlock_page(page); + put_page(page); + + } + + return 0; +} + +static int shmem_fadvise_willneed(struct address_space *mapping, + pgoff_t start, pgoff_t long end) +{ + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; + + rcu_read_lock(); + page = xas_find(&xas, end); + rcu_read_unlock(); + + while (page) { + if (xa_is_value(page)) { + page = shmem_read_mapping_page(mapping, xas.xa_index); + if (!IS_ERR(page)) + put_page(page); + } + + if (need_resched()) { + xas_pause(&xas); + cond_resched(); + } + + rcu_read_lock(); + page = xas_next_entry(&xas, end); + rcu_read_unlock(); + } + + return 0; +} + +static int shmem_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + loff_t endbyte; + pgoff_t start_index; + pgoff_t end_index; + struct address_space *mapping; + int ret = 0; + + mapping = file->f_mapping; + if (!mapping || len < 0) + return -EINVAL; + + endbyte = (u64)offset + (u64)len; + if (!len || endbyte < len) + endbyte = -1; + else + endbyte--; + + + start_index = offset >> PAGE_SHIFT; + end_index = endbyte >> PAGE_SHIFT; + switch (advice) { + case POSIX_FADV_DONTNEED: + ret = shmem_fadvise_dontneed(mapping, start_index, end_index); + break; + case POSIX_FADV_WILLNEED: + ret = shmem_fadvise_willneed(mapping, start_index, end_index); + break; + case POSIX_FADV_NORMAL: + case POSIX_FADV_RANDOM: + case POSIX_FADV_SEQUENTIAL: + case POSIX_FADV_NOREUSE: + /* + * No bad return value, but ignore advice. May have to + * implement in future. + */ + break; + default: + return -EINVAL; + } + + return ret; +} + static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) { struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); @@ -3799,6 +3965,7 @@ static const struct file_operations shmem_file_operations = { .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif + .fadvise = shmem_fadvise, }; static const struct inode_operations shmem_inode_operations = { -- QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation
