From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id BCFC7AD23 for ; Thu, 16 Jan 2025 05:31:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1737005515; cv=none; b=syeIgrRzxFuDSI1Fpq74pQcbMEYv2ZbYwIpQARKaPi0EE+ADNNWhPpEk+mVinnRhKtBiHlkar3jr71NudU9Gl8WXXERmm9lAD4Io9WAwsBIU9nBpYRPZyVICv0POyo5lazjue4a6fjRtsJmfM38xBiqEW2kA194AdB4T7gPLHgg= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1737005515; c=relaxed/simple; bh=O0airM1kroKCNqQRrQeo5+DYz48D200E79cWzHTm2qU=; h=Message-ID:Date:MIME-Version:Cc:Subject:To:References:From: In-Reply-To:Content-Type; b=gWklMxuTM9bn4eyEOX7woE/b/l5//vw4fPDNa6UlEy4N/S11O6RIFYVOi519wpoZR43Qo00cfn0+yulIyL6AXgv70s8Ny8VZNsXcy41SJM6k+UYeGNlnLqB5ce2zZoCZNLAcL3aM5jb2BCTk2S57PfdSxv4p2RfPn9vOdjAR/28= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=SfcR9nMa; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="SfcR9nMa" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 7694DC4CED6; Thu, 16 Jan 2025 05:31:54 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1737005515; bh=O0airM1kroKCNqQRrQeo5+DYz48D200E79cWzHTm2qU=; h=Date:Cc:Subject:To:References:From:In-Reply-To:From; b=SfcR9nMa7BCTZ3nj8DN9PABvAnhjcTHI1uKr/O7buZ6vd+gSMzgUQiJJP4UNXDsFG LociY3XH1uWHnd4lGDWEfBgq+wOdIFHM1Cyv4H0yGMdUTYG4wIsWmJ8OegbgsW+cTM 8Poy8gbpo7NAf95XwmEv67qSjSESLzO9ElOS48PpvXZKdl+uiCVKS1KkgMIPEMa3OT 4bdN4AhoPzlBWO24aSJuZ89xVVpzRHxqS+HnyQ8wWy2v5+7jKepGSG1TisNOTfJu6K ismQ2gWrguc3kO1d0gJDBAVzl3wJVF2KmzgCCCTCZGtvK2msjE8TS1CrrMfg+XylQw YyBvXWc4fHQUg== Message-ID: <328860a6-05d6-4b99-bac8-8eb73cac76be@kernel.org> Date: Thu, 16 Jan 2025 13:31:51 +0800 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Cc: chao@kernel.org Subject: Re: [f2fs-dev] [PATCH 1/2] f2fs: register inodes which is able to donate pages To: Jaegeuk Kim , linux-kernel@vger.kernel.org, linux-f2fs-devel@lists.sourceforge.net References: <20250116044245.1995715-1-jaegeuk@kernel.org> <20250116044245.1995715-2-jaegeuk@kernel.org> Content-Language: en-US From: Chao Yu In-Reply-To: <20250116044245.1995715-2-jaegeuk@kernel.org> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit On 1/16/25 12:42, Jaegeuk Kim via Linux-f2fs-devel wrote: > This patch introduces an inode list to keep the page cache ranges that users > can donate pages together. > > #define F2FS_IOC_DONATE_RANGE _IOW(F2FS_IOCTL_MAGIC, 27, \ > struct f2fs_donate_range) > struct f2fs_donate_range { > __u64 start; > __u64 len; > }; > > e.g., ioctl(F2FS_IOC_DONATE_RANGE, &range); > > Signed-off-by: Jaegeuk Kim > --- > fs/f2fs/debug.c | 3 ++ > fs/f2fs/f2fs.h | 12 +++++++- > fs/f2fs/file.c | 65 +++++++++++++++++++++++++++++++++++++++ > fs/f2fs/inode.c | 14 +++++++++ > fs/f2fs/super.c | 1 + > include/uapi/linux/f2fs.h | 7 +++++ > 6 files changed, 101 insertions(+), 1 deletion(-) > > diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c > index 468828288a4a..16c2dfb4f595 100644 > --- a/fs/f2fs/debug.c > +++ b/fs/f2fs/debug.c > @@ -164,6 +164,7 @@ static void update_general_status(struct f2fs_sb_info *sbi) > si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA); > si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE]; > si->ndirty_files = sbi->ndirty_inode[FILE_INODE]; > + si->ndonate_files = sbi->donate_files; > si->nquota_files = sbi->nquota_files; > si->ndirty_all = sbi->ndirty_inode[DIRTY_META]; > si->aw_cnt = atomic_read(&sbi->atomic_files); > @@ -501,6 +502,8 @@ static int stat_show(struct seq_file *s, void *v) > si->compr_inode, si->compr_blocks); > seq_printf(s, " - Swapfile Inode: %u\n", > si->swapfile_inode); > + seq_printf(s, " - Donate Inode: %u\n", > + si->ndonate_files); > seq_printf(s, " - Orphan/Append/Update Inode: %u, %u, %u\n", > si->orphans, si->append, si->update); > seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n", > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h > index 4bfe162eefd3..951fbc3f94c7 100644 > --- a/fs/f2fs/f2fs.h > +++ b/fs/f2fs/f2fs.h > @@ -850,6 +850,11 @@ struct f2fs_inode_info { > #endif > struct list_head dirty_list; /* dirty list for dirs and files */ > struct list_head gdirty_list; /* linked in global dirty list */ > + > + /* linked in global inode list for cache donation */ > + struct list_head gdonate_list; > + loff_t donate_start, donate_end; /* inclusive */ > + > struct task_struct *atomic_write_task; /* store atomic write task */ > struct extent_tree *extent_tree[NR_EXTENT_CACHES]; > /* cached extent_tree entry */ > @@ -1274,6 +1279,7 @@ enum inode_type { > DIR_INODE, /* for dirty dir inode */ > FILE_INODE, /* for dirty regular/symlink inode */ > DIRTY_META, /* for all dirtied inode metadata */ > + DONATE_INODE, /* for all inode to donate pages */ > NR_INODE_TYPE, > }; > > @@ -1629,6 +1635,9 @@ struct f2fs_sb_info { > unsigned int warm_data_age_threshold; > unsigned int last_age_weight; > > + /* control donate caches */ > + unsigned int donate_files; > + > /* basic filesystem units */ > unsigned int log_sectors_per_block; /* log2 sectors per block */ > unsigned int log_blocksize; /* log2 block size */ > @@ -3984,7 +3993,8 @@ struct f2fs_stat_info { > unsigned long long allocated_data_blocks; > int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta; > int ndirty_data, ndirty_qdata; > - unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all; > + unsigned int ndirty_dirs, ndirty_files, ndirty_all; > + unsigned int nquota_files, ndonate_files; > int nats, dirty_nats, sits, dirty_sits; > int free_nids, avail_nids, alloc_nids; > int total_count, utilization; > diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c > index 81764b10840b..ff475bdc2832 100644 > --- a/fs/f2fs/file.c > +++ b/fs/f2fs/file.c > @@ -2429,6 +2429,68 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) > return ret; > } > > +static int f2fs_ioc_donate_range(struct file *filp, unsigned long arg) > +{ > + struct inode *inode = file_inode(filp); > + struct mnt_idmap *idmap = file_mnt_idmap(filp); > + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); > + struct f2fs_donate_range range; > + u64 max_pages = F2FS_BLK_TO_BYTES(max_file_blocks(inode)) >> PAGE_SHIFT; > + bool partial = range.start & PAGE_MASK; > + int ret; > + > + if (copy_from_user(&range, (struct f2fs_donate_range __user *)arg, > + sizeof(range))) > + return -EFAULT; > + > + if (!inode_owner_or_capable(idmap, inode)) > + return -EACCES; > + > + if (!S_ISREG(inode->i_mode)) > + return -EINVAL; > + > + range.start >>= PAGE_SHIFT; > + range.len = DIV_ROUND_UP(range.len, PAGE_SIZE) + partial ? 1: 0; e.g. range.start = 2048 range.len = 6144 original range is [2048, 8192] after calculation, the range becomes [0, 12288]? How about this? u64 max_size = F2FS_BLK_TO_BYTES(max_file_blocks(inode)); u64 start, end; if (range.start >= max_size || range.len > max_size || (range.start + range.len) > max_pages) start = range.start >> PAGE_SHIFT; end = DIV_ROUND_UP(range.start + range.len, PAGE_SIZE); ... /* let's remove the range, if len = 0 */ if (start == end) ... F2FS_I(inode)->donate_start = start; F2FS_I(inode)->donate_end = end; Thanks, > + > + if (range.start >= max_pages || range.len > max_pages || > + (range.start + range.len) > max_pages) > + return -EINVAL; > + > + ret = mnt_want_write_file(filp); > + if (ret) > + return ret; > + > + inode_lock(inode); > + > + if (f2fs_is_atomic_file(inode)) > + goto out; > + > + spin_lock(&sbi->inode_lock[DONATE_INODE]); > + /* let's remove the range, if len = 0 */ > + if (!range.len) { > + if (!list_empty(&F2FS_I(inode)->gdonate_list)) { > + list_del_init(&F2FS_I(inode)->gdonate_list); > + sbi->donate_files--; > + } > + } else { > + if (list_empty(&F2FS_I(inode)->gdonate_list)) { > + list_add_tail(&F2FS_I(inode)->gdonate_list, > + &sbi->inode_list[DONATE_INODE]); > + sbi->donate_files++; > + } else { > + list_move_tail(&F2FS_I(inode)->gdonate_list, > + &sbi->inode_list[DONATE_INODE]); > + } > + F2FS_I(inode)->donate_start = range.start; > + F2FS_I(inode)->donate_end = range.start + range.len - 1; > + } > + spin_unlock(&sbi->inode_lock[DONATE_INODE]); > +out: > + inode_unlock(inode); > + mnt_drop_write_file(filp); > + return ret; > +} > + > static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) > { > struct inode *inode = file_inode(filp); > @@ -4458,6 +4520,8 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) > return -EOPNOTSUPP; > case F2FS_IOC_SHUTDOWN: > return f2fs_ioc_shutdown(filp, arg); > + case F2FS_IOC_DONATE_RANGE: > + return f2fs_ioc_donate_range(filp, arg); > case FITRIM: > return f2fs_ioc_fitrim(filp, arg); > case FS_IOC_SET_ENCRYPTION_POLICY: > @@ -5209,6 +5273,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) > case F2FS_IOC_RELEASE_VOLATILE_WRITE: > case F2FS_IOC_ABORT_ATOMIC_WRITE: > case F2FS_IOC_SHUTDOWN: > + case F2FS_IOC_DONATE_RANGE: > case FITRIM: > case FS_IOC_SET_ENCRYPTION_POLICY: > case FS_IOC_GET_ENCRYPTION_PWSALT: > diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c > index 7de33da8b3ea..f9fc58f313f2 100644 > --- a/fs/f2fs/inode.c > +++ b/fs/f2fs/inode.c > @@ -804,6 +804,19 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) > return 0; > } > > +static void f2fs_remove_donate_inode(struct inode *inode) > +{ > + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); > + > + if (list_empty(&F2FS_I(inode)->gdonate_list)) > + return; > + > + spin_lock(&sbi->inode_lock[DONATE_INODE]); > + list_del_init(&F2FS_I(inode)->gdonate_list); > + sbi->donate_files--; > + spin_unlock(&sbi->inode_lock[DONATE_INODE]); > +} > + > /* > * Called at the last iput() if i_nlink is zero > */ > @@ -838,6 +851,7 @@ void f2fs_evict_inode(struct inode *inode) > > f2fs_bug_on(sbi, get_dirty_pages(inode)); > f2fs_remove_dirty_inode(inode); > + f2fs_remove_donate_inode(inode); > > if (!IS_DEVICE_ALIASING(inode)) > f2fs_destroy_extent_tree(inode); > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c > index fc7d463dee15..ef639a6d82e5 100644 > --- a/fs/f2fs/super.c > +++ b/fs/f2fs/super.c > @@ -1441,6 +1441,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) > spin_lock_init(&fi->i_size_lock); > INIT_LIST_HEAD(&fi->dirty_list); > INIT_LIST_HEAD(&fi->gdirty_list); > + INIT_LIST_HEAD(&fi->gdonate_list); > init_f2fs_rwsem(&fi->i_gc_rwsem[READ]); > init_f2fs_rwsem(&fi->i_gc_rwsem[WRITE]); > init_f2fs_rwsem(&fi->i_xattr_sem); > diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h > index f7aaf8d23e20..cd38a7c166e6 100644 > --- a/include/uapi/linux/f2fs.h > +++ b/include/uapi/linux/f2fs.h > @@ -44,6 +44,8 @@ > #define F2FS_IOC_COMPRESS_FILE _IO(F2FS_IOCTL_MAGIC, 24) > #define F2FS_IOC_START_ATOMIC_REPLACE _IO(F2FS_IOCTL_MAGIC, 25) > #define F2FS_IOC_GET_DEV_ALIAS_FILE _IOR(F2FS_IOCTL_MAGIC, 26, __u32) > +#define F2FS_IOC_DONATE_RANGE _IOW(F2FS_IOCTL_MAGIC, 27, \ > + struct f2fs_donate_range) > > /* > * should be same as XFS_IOC_GOINGDOWN. > @@ -97,4 +99,9 @@ struct f2fs_comp_option { > __u8 log_cluster_size; > }; > > +struct f2fs_donate_range { > + __u64 start; > + __u64 len; > +}; > + > #endif /* _UAPI_LINUX_F2FS_H */