Re: [PATCH v4 3/3] fs/ufs: Replace kmap() with kmap_local_page()

[Ira Weiny]

On Wed, Dec 21, 2022 at 06:28:02PM +0100, Fabio M. De Francesco wrote:
> kmap() is being deprecated in favor of kmap_local_page().
> 
> There are two main problems with kmap(): (1) It comes with an overhead as
> the mapping space is restricted and protected by a global lock for
> synchronization and (2) it also requires global TLB invalidation when the
> kmap’s pool wraps and it might block when the mapping space is fully
> utilized until a slot becomes available.
> 
> With kmap_local_page() the mappings are per thread, CPU local, can take
> page faults, and can be called from any context (including interrupts).
> It is faster than kmap() in kernels with HIGHMEM enabled. Furthermore,
> the tasks can be preempted and, when they are scheduled to run again, the
> kernel virtual addresses are restored and still valid.
> 
> Since its use in fs/ufs is safe everywhere, it should be preferred.
> 
> Therefore, replace kmap() with kmap_local_page() in fs/ufs. kunmap_local()
> requires the mapping address, so return that address from ufs_get_page()
> to be used in ufs_put_page().

I don't see the calls to kunmap() in ufs_rename converted here?

Did I miss them?

I think those calls need to be changed to ufs_put_page() calls in a precursor
patch to this one unless I'm missing something.

> 
> Suggested-by: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
> Suggested-by: Ira Weiny <ira.weiny@xxxxxxxxx>
> Signed-off-by: Fabio M. De Francesco <fmdefrancesco@xxxxxxxxx>
> ---
>  fs/ufs/dir.c | 75 ++++++++++++++++++++++++++++++++--------------------
>  1 file changed, 46 insertions(+), 29 deletions(-)
> 
> diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
> index 9fa86614d2d1..ed3568da29a8 100644
> --- a/fs/ufs/dir.c
> +++ b/fs/ufs/dir.c
> @@ -61,9 +61,9 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
>  	return err;
>  }
>  
> -static inline void ufs_put_page(struct page *page)
> +static inline void ufs_put_page(struct page *page, void *page_addr)
>  {
> -	kunmap(page);
> +	kunmap_local((void *)((unsigned long)page_addr & PAGE_MASK));

Any address in the page can be passed to kunmap_local() as this mask is done
internally.

>  	put_page(page);
>  }
>  
> @@ -76,7 +76,7 @@ ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr)
>  	de = ufs_find_entry(dir, qstr, &page);
>  	if (de) {
>  		res = fs32_to_cpu(dir->i_sb, de->d_ino);
> -		ufs_put_page(page);
> +		ufs_put_page(page, de);
>  	}
>  	return res;
>  }
> @@ -99,18 +99,17 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
>  	ufs_set_de_type(dir->i_sb, de, inode->i_mode);
>  
>  	err = ufs_commit_chunk(page, pos, len);
> -	ufs_put_page(page);
> +	ufs_put_page(page, de);
>  	if (update_times)
>  		dir->i_mtime = dir->i_ctime = current_time(dir);
>  	mark_inode_dirty(dir);
>  }
>  
>  
> -static bool ufs_check_page(struct page *page)
> +static bool ufs_check_page(struct page *page, char *kaddr)
>  {
>  	struct inode *dir = page->mapping->host;
>  	struct super_block *sb = dir->i_sb;
> -	char *kaddr = page_address(page);
>  	unsigned offs, rec_len;
>  	unsigned limit = PAGE_SIZE;
>  	const unsigned chunk_mask = UFS_SB(sb)->s_uspi->s_dirblksize - 1;
> @@ -185,23 +184,32 @@ static bool ufs_check_page(struct page *page)
>  	return false;
>  }
>  
> +/*
> + * Calls to ufs_get_page()/ufs_put_page() must be nested according to the
> + * rules documented in kmap_local_page()/kunmap_local().
> + *
> + * NOTE: ufs_find_entry() and ufs_dotdot() act as calls to ufs_get_page()
> + * and must be treated accordingly for nesting purposes.
> + */
>  static void *ufs_get_page(struct inode *dir, unsigned long n, struct page **p)
>  {
> +	char *kaddr;
> +
>  	struct address_space *mapping = dir->i_mapping;
>  	struct page *page = read_mapping_page(mapping, n, NULL);
>  	if (!IS_ERR(page)) {
> -		kmap(page);
> +		kaddr = kmap_local_page(page);
>  		if (unlikely(!PageChecked(page))) {
> -			if (!ufs_check_page(page))
> +			if (!ufs_check_page(page, kaddr))
>  				goto fail;
>  		}
>  		*p = page;
> -		return page_address(page);
> +		return kaddr;
>  	}
>  	return ERR_CAST(page);
>  
>  fail:
> -	ufs_put_page(page);
> +	ufs_put_page(page, kaddr);
>  	return ERR_PTR(-EIO);
>  }
>  
> @@ -227,6 +235,13 @@ ufs_next_entry(struct super_block *sb, struct ufs_dir_entry *p)
>  					fs16_to_cpu(sb, p->d_reclen));
>  }
>  
> +/*
> + * Calls to ufs_get_page()/ufs_put_page() must be nested according to the
> + * rules documented in kmap_local_page()/kunmap_local().
> + *
> + * ufs_dotdot() acts as a call to ufs_get_page() and must be treated
> + * accordingly for nesting purposes.
> + */
>  struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct page **p)
>  {
>  	struct ufs_dir_entry *de = ufs_get_page(dir, 0, p);
> @@ -238,12 +253,15 @@ struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct page **p)
>  }
>  
>  /*
> - *	ufs_find_entry()
> + * Finds an entry in the specified directory with the wanted name. It returns a
> + * pointer to the directory's entry. The page in which the entry was found is
> + * in the res_page out parameter. The page is returned mapped and unlocked.
> + * The entry is guaranteed to be valid.
>   *
> - * finds an entry in the specified directory with the wanted name. It
> - * returns the page in which the entry was found, and the entry itself
> - * (as a parameter - res_dir). Page is returned mapped and unlocked.
> - * Entry is guaranteed to be valid.

I don't follow why this comment needed changing for this patch.  It probably
warrants it's own patch.

> + * On Success ufs_put_page() should be called on *res_page.
> + *
> + * ufs_find_entry() acts as a call to ufs_get_page() and must be treated
> + * accordingly for nesting purposes.
>   */
>  struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr,
>  				     struct page **res_page)
> @@ -282,7 +300,7 @@ struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr,
>  					goto found;
>  				de = ufs_next_entry(sb, de);
>  			}
> -			ufs_put_page(page);
> +			ufs_put_page(page, kaddr);
>  		}
>  		if (++n >= npages)
>  			n = 0;
> @@ -360,7 +378,7 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode)
>  			de = (struct ufs_dir_entry *) ((char *) de + rec_len);
>  		}
>  		unlock_page(page);
> -		ufs_put_page(page);
> +		ufs_put_page(page, kaddr);
>  	}
>  	BUG();
>  	return -EINVAL;
> @@ -390,7 +408,7 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode)
>  	mark_inode_dirty(dir);
>  	/* OFFSET_CACHE */
>  out_put:
> -	ufs_put_page(page);
> +	ufs_put_page(page, kaddr);
>  	return err;
>  out_unlock:
>  	unlock_page(page);
> @@ -468,13 +486,13 @@ ufs_readdir(struct file *file, struct dir_context *ctx)
>  					       ufs_get_de_namlen(sb, de),
>  					       fs32_to_cpu(sb, de->d_ino),
>  					       d_type)) {
> -					ufs_put_page(page);
> +					ufs_put_page(page, kaddr);
>  					return 0;
>  				}
>  			}
>  			ctx->pos += fs16_to_cpu(sb, de->d_reclen);
>  		}
> -		ufs_put_page(page);
> +		ufs_put_page(page, kaddr);
>  	}
>  	return 0;
>  }
> @@ -485,10 +503,10 @@ ufs_readdir(struct file *file, struct dir_context *ctx)
>   * previous entry.
>   */
>  int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
> -		     struct page * page)
> +		     struct page *page)
>  {
>  	struct super_block *sb = inode->i_sb;
> -	char *kaddr = page_address(page);
> +	char *kaddr = (char *)((unsigned long)dir & PAGE_MASK);

I feel like this deserves a comment to clarify that dir points somewhere in the
page we need the base address of.

>  	unsigned int from = offset_in_page(dir) & ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1);
>  	unsigned int to = offset_in_page(dir) + fs16_to_cpu(sb, dir->d_reclen);
>  	loff_t pos;
> @@ -527,7 +545,7 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
>  	inode->i_ctime = inode->i_mtime = current_time(inode);
>  	mark_inode_dirty(inode);
>  out:
> -	ufs_put_page(page);
> +	ufs_put_page(page, kaddr);
>  	UFSD("EXIT\n");
>  	return err;
>  }
> @@ -551,8 +569,7 @@ int ufs_make_empty(struct inode * inode, struct inode *dir)
>  		goto fail;
>  	}
>  
> -	kmap(page);
> -	base = (char*)page_address(page);
> +	base = kmap_local_page(page);

NIT: I'd make this conversion a separate patch.

Ira

>  	memset(base, 0, PAGE_SIZE);
>  
>  	de = (struct ufs_dir_entry *) base;
> @@ -569,7 +586,7 @@ int ufs_make_empty(struct inode * inode, struct inode *dir)
>  	de->d_reclen = cpu_to_fs16(sb, chunk_size - UFS_DIR_REC_LEN(1));
>  	ufs_set_de_namlen(sb, de, 2);
>  	strcpy (de->d_name, "..");
> -	kunmap(page);
> +	kunmap_local(base);
>  
>  	err = ufs_commit_chunk(page, 0, chunk_size);
>  fail:
> @@ -585,9 +602,9 @@ int ufs_empty_dir(struct inode * inode)
>  	struct super_block *sb = inode->i_sb;
>  	struct page *page = NULL;
>  	unsigned long i, npages = dir_pages(inode);
> +	char *kaddr;
>  
>  	for (i = 0; i < npages; i++) {
> -		char *kaddr;
>  		struct ufs_dir_entry *de;
>  
>  		kaddr = ufs_get_page(inode, i, &page);
> @@ -620,12 +637,12 @@ int ufs_empty_dir(struct inode * inode)
>  			}
>  			de = ufs_next_entry(sb, de);
>  		}
> -		ufs_put_page(page);
> +		ufs_put_page(page, kaddr);
>  	}
>  	return 1;
>  
>  not_empty:
> -	ufs_put_page(page);
> +	ufs_put_page(page, kaddr);
>  	return 0;
>  }
>  
> -- 
> 2.39.0
>