Hi, Here are some drive-by review comments as I'm evaluating whether these patches can help me with what I'm trying to do at https://lore.kernel.org/linux-mm/20240215154059.2863126-1-ryan.roberts@xxxxxxx/... On 25/06/2024 12:44, Pankaj Raghav (Samsung) wrote: > From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx> > > We need filesystems to be able to communicate acceptable folio sizes > to the pagecache for a variety of uses (e.g. large block sizes). > Support a range of folio sizes between order-0 and order-31. > > Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> > Co-developed-by: Pankaj Raghav <p.raghav@xxxxxxxxxxx> > Signed-off-by: Pankaj Raghav <p.raghav@xxxxxxxxxxx> > Reviewed-by: Hannes Reinecke <hare@xxxxxxx> > Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx> > --- > include/linux/pagemap.h | 86 ++++++++++++++++++++++++++++++++++------- > mm/filemap.c | 6 +-- > mm/readahead.c | 4 +- > 3 files changed, 77 insertions(+), 19 deletions(-) > > diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h > index 4b71d581091f..0c51154cdb57 100644 > --- a/include/linux/pagemap.h > +++ b/include/linux/pagemap.h > @@ -204,14 +204,21 @@ enum mapping_flags { > AS_EXITING = 4, /* final truncate in progress */ > /* writeback related tags are not used */ > AS_NO_WRITEBACK_TAGS = 5, > - AS_LARGE_FOLIO_SUPPORT = 6, nit: this removed enum is still referenced in a comment further down the file. > - AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ > - AS_STABLE_WRITES, /* must wait for writeback before modifying > + AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ > + AS_STABLE_WRITES = 7, /* must wait for writeback before modifying > folio contents */ > - AS_UNMOVABLE, /* The mapping cannot be moved, ever */ > - AS_INACCESSIBLE, /* Do not attempt direct R/W access to the mapping */ > + AS_UNMOVABLE = 8, /* The mapping cannot be moved, ever */ > + AS_INACCESSIBLE = 9, /* Do not attempt direct R/W access to the mapping */ > + /* Bits 16-25 are used for FOLIO_ORDER */ > + AS_FOLIO_ORDER_BITS = 5, > + AS_FOLIO_ORDER_MIN = 16, > + AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, nit: These 3 new enums seem a bit odd. It might be clearer if you just reserve the bits for the fields here? AS_FOLIO_ORDER_BITS isn't actually a flags bit and the MAX value is currently the start of the max field, not the end. #define AS_FOLIO_ORDER_BITS 5 enum mapping_flags { ... AS_FOLIO_ORDERS_FIRST = 16, AS_FOLIO_ORDERS_LAST = AS_FOLIO_ORDERS_FIRST+(2*AS_FOLIO_ORDER_BITS)-1, ... }; #define AS_FOLIO_ORDER_MIN_MASK \ GENMASK(AS_FOLIO_ORDERS_FIRST + AS_FOLIO_ORDER_BITS - 1, \ AS_FOLIO_ORDERS_FIRST) #define AS_FOLIO_ORDER_MAX_MASK \ GENMASK(AS_FOLIO_ORDERS_LAST, \ AS_FOLIO_ORDERS_LAST - AS_FOLIO_ORDER_BITS + 1) > }; > > +#define AS_FOLIO_ORDER_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) > +#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_MASK << AS_FOLIO_ORDER_MIN) > +#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_MASK << AS_FOLIO_ORDER_MAX) > + > /** > * mapping_set_error - record a writeback error in the address_space > * @mapping: the mapping in which an error should be set > @@ -360,9 +367,49 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) > #define MAX_PAGECACHE_ORDER 8 > #endif > > +/* > + * mapping_set_folio_order_range() - Set the orders supported by a file. > + * @mapping: The address space of the file. > + * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). > + * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). > + * > + * The filesystem should call this function in its inode constructor to > + * indicate which base size (min) and maximum size (max) of folio the VFS > + * can use to cache the contents of the file. This should only be used > + * if the filesystem needs special handling of folio sizes (ie there is > + * something the core cannot know). > + * Do not tune it based on, eg, i_size. > + * > + * Context: This should not be called while the inode is active as it > + * is non-atomic. > + */ > +static inline void mapping_set_folio_order_range(struct address_space *mapping, > + unsigned int min, > + unsigned int max) > +{ > + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) > + return; > + > + if (min > MAX_PAGECACHE_ORDER) > + min = MAX_PAGECACHE_ORDER; > + if (max > MAX_PAGECACHE_ORDER) > + max = MAX_PAGECACHE_ORDER; > + if (max < min) > + max = min; It seems strange to silently clamp these? Presumably for the bs>ps usecase, whatever values are passed in are a hard requirement? So wouldn't want them to be silently reduced. (Especially given the recent change to reduce the size of MAX_PAGECACHE_ORDER to less then PMD size in some cases). > + > + mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | > + (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); > +} > + > +static inline void mapping_set_folio_min_order(struct address_space *mapping, > + unsigned int min) > +{ > + mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); > +} > + > /** > * mapping_set_large_folios() - Indicate the file supports large folios. > - * @mapping: The file. > + * @mapping: The address space of the file. > * > * The filesystem should call this function in its inode constructor to > * indicate that the VFS can use large folios to cache the contents of > @@ -373,7 +420,23 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) > */ > static inline void mapping_set_large_folios(struct address_space *mapping) > { > - __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); > + mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); > +} > + > +static inline > +unsigned int mapping_max_folio_order(const struct address_space *mapping) > +{ > + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) > + return 0; > + return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; > +} > + > +static inline > +unsigned int mapping_min_folio_order(const struct address_space *mapping) > +{ > + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) > + return 0; > + return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; > } > > /* > @@ -386,16 +449,13 @@ static inline bool mapping_large_folio_support(struct address_space *mapping) > VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, > "Anonymous mapping always supports large folio"); > > - return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && > - test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); > + return mapping_max_folio_order(mapping) > 0; > } > > /* Return the maximum folio size for this pagecache mapping, in bytes. */ > -static inline size_t mapping_max_folio_size(struct address_space *mapping) > +static inline size_t mapping_max_folio_size(const struct address_space *mapping) > { > - if (mapping_large_folio_support(mapping)) > - return PAGE_SIZE << MAX_PAGECACHE_ORDER; > - return PAGE_SIZE; > + return PAGE_SIZE << mapping_max_folio_order(mapping); > } > > static inline int filemap_nr_thps(struct address_space *mapping) > diff --git a/mm/filemap.c b/mm/filemap.c > index 0b8c732bb643..d617c9afca51 100644 > --- a/mm/filemap.c > +++ b/mm/filemap.c > @@ -1933,10 +1933,8 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, > if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) > fgp_flags |= FGP_LOCK; > > - if (!mapping_large_folio_support(mapping)) > - order = 0; > - if (order > MAX_PAGECACHE_ORDER) > - order = MAX_PAGECACHE_ORDER; > + if (order > mapping_max_folio_order(mapping)) > + order = mapping_max_folio_order(mapping); > /* If we're not aligned, allocate a smaller folio */ > if (index & ((1UL << order) - 1)) > order = __ffs(index); > diff --git a/mm/readahead.c b/mm/readahead.c > index c1b23989d9ca..66058ae02f2e 100644 > --- a/mm/readahead.c > +++ b/mm/readahead.c > @@ -503,9 +503,9 @@ void page_cache_ra_order(struct readahead_control *ractl, > > limit = min(limit, index + ra->size - 1); > > - if (new_order < MAX_PAGECACHE_ORDER) { > + if (new_order < mapping_max_folio_order(mapping)) { > new_order += 2; > - new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order); > + new_order = min(mapping_max_folio_order(mapping), new_order); > new_order = min_t(unsigned int, new_order, ilog2(ra->size)); I wonder if its possible that ra->size could ever be less than mapping_min_folio_order()? Do you need to handle that? Thanks, Ryan > } >
