]> git.hungrycats.org Git - linux/commit
Revert "mm: limit filemap_fault readahead to VMA boundaries"
authorLorenzo Stoakes <ljs@kernel.org>
Fri, 19 Jun 2026 11:28:51 +0000 (12:28 +0100)
committerAndrew Morton <akpm@linux-foundation.org>
Sun, 21 Jun 2026 18:37:38 +0000 (11:37 -0700)
commit13a1e1a618858407fa12c391f664ea750651f6b2
treea37196f4677422ebfe2ab1a426a4a0583b14bfba
parent44238b122ae834ac52748e59809a139a2cb8409b
Revert "mm: limit filemap_fault readahead to VMA boundaries"

This reverts commit 7b32f64bc512b40b268776c5ac4d354b325b3197.

This patch caused a significant performance regression, so revert it, and
we can determine whether the approach is sensible or not moving forwards,
and if so how to avoid this.

There was a merge conflict with commit de97ae6222c1 ("mm/readahead: no
PG_readahead on EOF"), care was taken to ensure that the revert retained
the behaviour of this patch and cleanly reverts commit 7b32f64bc512 ("mm:
limit filemap_fault readahead to VMA boundaries") only.

Link: https://lore.kernel.org/20260619112852.104213-1-ljs@kernel.org
Fixes: 7b32f64bc512 ("mm: limit filemap_fault readahead to VMA boundaries")
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202606181547.617a6967-lkp@intel.com
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Kalesh Singh <kaleshsingh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
include/linux/pagemap.h
mm/filemap.c
mm/readahead.c