From fa290cda102c096f5ca394277d65d3dbd689930b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 10 Apr 2018 16:36:28 -0700 Subject: radix tree: use GFP_ZONEMASK bits of gfp_t for flags Patch series "XArray", v9. (First part thereof). This patchset is, I believe, appropriate for merging for 4.17. It contains the XArray implementation, to eventually replace the radix tree, and converts the page cache to use it. This conversion keeps the radix tree and XArray data structures in sync at all times. That allows us to convert the page cache one function at a time and should allow for easier bisection. Other than renaming some elements of the structures, the data structures are fundamentally unchanged; a radix tree walk and an XArray walk will touch the same number of cachelines. I have changes planned to the XArray data structure, but those will happen in future patches. Improvements the XArray has over the radix tree: - The radix tree provides operations like other trees do; 'insert' and 'delete'. But what most users really want is an automatically resizing array, and so it makes more sense to give users an API that is like an array -- 'load' and 'store'. We still have an 'insert' operation for users that really want that semantic. - The XArray considers locking as part of its API. This simplifies a lot of users who formerly had to manage their own locking just for the radix tree. It also improves code generation as we can now tell RCU that we're holding a lock and it doesn't need to generate as much fencing code. The other advantage is that tree nodes can be moved (not yet implemented). - GFP flags are now parameters to calls which may need to allocate memory. The radix tree forced users to decide what the allocation flags would be at creation time. It's much clearer to specify them at allocation time. - Memory is not preloaded; we don't tie up dozens of pages on the off chance that the slab allocator fails. Instead, we drop the lock, allocate a new node and retry the operation. We have to convert all the radix tree, IDA and IDR preload users before we can realise this benefit, but I have not yet found a user which cannot be converted. - The XArray provides a cmpxchg operation. The radix tree forces users to roll their own (and at least four have). - Iterators take a 'max' parameter. That simplifies many users and will reduce the amount of iteration done. - Iteration can proceed backwards. We only have one user for this, but since it's called as part of the pagefault readahead algorithm, that seemed worth mentioning. - RCU-protected pointers are not exposed as part of the API. There are some fun bugs where the page cache forgets to use rcu_dereference() in the current codebase. - Value entries gain an extra bit compared to radix tree exceptional entries. That gives us the extra bit we need to put huge page swap entries in the page cache. - Some iterators now take a 'filter' argument instead of having separate iterators for tagged/untagged iterations. The page cache is improved by this: - Shorter, easier to read code - More efficient iterations - Reduction in size of struct address_space - Fewer walks from the top of the data structure; the XArray API encourages staying at the leaf node and conducting operations there. This patch (of 8): None of these bits may be used for slab allocations, so we can use them as radix tree flags as long as we mask them off before passing them to the slab allocator. Move the IDR flag from the high bits to the GFP_ZONEMASK bits. Link: http://lkml.kernel.org/r/20180313132639.17387-3-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Jeff Layton Cc: Darrick J. Wong Cc: Dave Chinner Cc: Ryusuke Konishi Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 3 ++- include/linux/radix-tree.h | 7 ++++--- lib/radix-tree.c | 3 ++- tools/testing/radix-tree/linux/gfp.h | 1 + 4 files changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/idr.h b/include/linux/idr.h index 7d6a6313f0ab..913c335054f0 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -29,7 +29,8 @@ struct idr { #define IDR_FREE 0 /* Set the IDR flag and the IDR_FREE tag */ -#define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT)) +#define IDR_RT_MARKER (ROOT_IS_IDR | (__force gfp_t) \ + (1 << (ROOT_TAG_SHIFT + IDR_FREE))) #define IDR_INIT_BASE(base) { \ .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER), \ diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index fc55ff31eca7..6c4e2e716dac 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -104,9 +104,10 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* The top bits of gfp_mask are used to store the root tags and the IDR flag */ -#define ROOT_IS_IDR ((__force gfp_t)(1 << __GFP_BITS_SHIFT)) -#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT + 1) +/* The IDR tag is stored in the low bits of the GFP flags */ +#define ROOT_IS_IDR ((__force gfp_t)4) +/* The top bits of gfp_mask are used to store the root tags */ +#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) struct radix_tree_root { gfp_t gfp_mask; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 8e00138d593f..da9e10c827df 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -146,7 +146,7 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent, static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { - return root->gfp_mask & __GFP_BITS_MASK; + return root->gfp_mask & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, @@ -2285,6 +2285,7 @@ void __init radix_tree_init(void) int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); + BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index e3201ccf54c3..32159c08a52e 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -19,6 +19,7 @@ #define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM) +#define GFP_ZONEMASK 0x0fu #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) -- cgit v1.2.3-59-g8ed1b