[PATCH] fs/address_space: add alignment padding for i_map and i_mmap_rwsem to mitigate a false sharing.

[Zhu, Lipeng]

When running UnixBench/Shell Scripts, we observed high false sharing
for accessing i_mmap against i_mmap_rwsem.

UnixBench/Shell Scripts are typical load/execute command test scenarios,
the i_mmap will be accessed frequently to insert/remove vma_interval_tree.
Meanwhile, the i_mmap_rwsem is frequently loaded. Unfortunately, they are
in the same cacheline.

The patch places the i_mmap and i_mmap_rwsem in separate cache lines to avoid
this false sharing problem.

With this patch, on Intel Sapphire Rapids 2 sockets 112c/224t platform, based
on kernel v6.4-rc4, the 224 parallel score is improved ~2.5% for
UnixBench/Shell Scripts case. And perf c2c tool shows the false sharing is
resolved as expected, the symbol vma_interval_tree_remove disappeared in
cache line 0 after this change.

Baseline:
=================================================
      Shared Cache Line Distribution Pareto
=================================================
  -------------------------------------------------------------
      0    13642    19392     9012       63  0xff1ddd3f0c8a3b00
  -------------------------------------------------------------
    9.22%    7.37%    0.00%    0.00%    0x0     0       1  0xffffffffab344052       518       334       354     5490       160  [k] vma_interval_tree_remove    [kernel.kallsyms]  vma_interval_tree_remove+18      0  1
    0.71%    0.73%    0.00%    0.00%    0x8     0       1  0xffffffffabb9a21f       574       338       458     1991       160  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+655    0  1
    0.52%    0.71%    5.34%    6.35%    0x8     0       1  0xffffffffabb9a236      1080       597       390     4848       160  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+678    0  1
    0.56%    0.47%   26.39%    6.35%    0x8     0       1  0xffffffffabb9a5ec      1327      1037       587     8537       160  [k] down_write                  [kernel.kallsyms]  down_write+28                    0  1
    0.11%    0.08%   15.72%    1.59%    0x8     0       1  0xffffffffab17082b      1618      1077       735     7303       160  [k] up_write                    [kernel.kallsyms]  up_write+27                      0  1
    0.01%    0.02%    0.08%    0.00%    0x8     0       1  0xffffffffabb9a27d      1594       593       512       53        43  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+749    0  1
    0.00%    0.01%    0.00%    0.00%    0x8     0       1  0xffffffffabb9a0c4         0       323       518       97        74  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+308    0  1
   44.74%   49.78%    0.00%    0.00%   0x10     0       1  0xffffffffab170995       609       344       430    26841       160  [k] rwsem_spin_on_owner         [kernel.kallsyms]  rwsem_spin_on_owner+53           0  1
   26.62%   22.39%    0.00%    0.00%   0x10     0       1  0xffffffffab170965       514       347       437    13364       160  [k] rwsem_spin_on_owner         [kernel.kallsyms]  rwsem_spin_on_owner+5            0  1

With this change:
  -------------------------------------------------------------
      0    12726    18554     9039       49  0xff157a0f25b90c40
  -------------------------------------------------------------
    0.90%    0.72%    0.00%    0.00%    0x0     1       1  0xffffffffa5f9a21f       532       353       461     2200       160  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+655    0  1
    0.53%    0.70%    5.16%    6.12%    0x0     1       1  0xffffffffa5f9a236      1196       670       403     4774       160  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+678    0  1
    0.68%    0.51%   25.91%    6.12%    0x0     1       1  0xffffffffa5f9a5ec      1049       807       540     8552       160  [k] down_write                  [kernel.kallsyms]  down_write+28                    0  1
    0.09%    0.06%   16.50%    2.04%    0x0     1       1  0xffffffffa557082b      1693      1351       758     7317       160  [k] up_write                    [kernel.kallsyms]  up_write+27                      0  1
    0.01%    0.00%    0.00%    0.00%    0x0     1       1  0xffffffffa5f9a0c4       543         0       491       89        68  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+308    0  1
    0.00%    0.01%    0.02%    0.00%    0x0     1       1  0xffffffffa5f9a27d         0       597       742       45        40  [k] rwsem_down_write_slowpath   [kernel.kallsyms]  rwsem_down_write_slowpath+749    0  1
   49.29%   53.01%    0.00%    0.00%    0x8     1       1  0xffffffffa5570995       580       310       413    27106       160  [k] rwsem_spin_on_owner         [kernel.kallsyms]  rwsem_spin_on_owner+53           0  1
   28.60%   24.12%    0.00%    0.00%    0x8     1       1  0xffffffffa5570965       490       321       419    13244       160  [k] rwsem_spin_on_owner         [kernel.kallsyms]  rwsem_spin_on_owner+5            0  1

Reviewed-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Signed-off-by: Lipeng Zhu <lipeng.zhu@xxxxxxxxx>
---
 include/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index c85916e9f7db..d3dd8dcc9b8b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -434,7 +434,7 @@ struct address_space {
 	atomic_t		nr_thps;
 #endif
 	struct rb_root_cached	i_mmap;
-	struct rw_semaphore	i_mmap_rwsem;
+	struct rw_semaphore	i_mmap_rwsem ____cacheline_aligned_in_smp;
 	unsigned long		nrpages;
 	pgoff_t			writeback_index;
 	const struct address_space_operations *a_ops;
-- 
2.39.1