diff options
| author | Li Zhe <lizhe.67@bytedance.com> | 2026-08-31 19:16:34 +0800 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2026-10-06 17:39:17 -0700 |
| commit | 72dcfdc2ce47c84d248ab43490ec91a0d5098253 (patch) | |
| tree | e4f741978b03d45b64b9ed25dbec5cdb47d261d8 /include/linux/string.h | |
| parent | a5d43b7cd64235cc12d8563889f393894589f12f (diff) | |
| download | linux-next-72dcfdc2ce47c84d248ab43490ec91a0d5098253.tar.gz linux-next-72dcfdc2ce47c84d248ab43490ec91a0d5098253.zip | |
mm: add a template-based fast path for zone-device page init
memmap_init_zone_device() repeats nearly identical head-page
initialization for each PFN. Initialize the first real ZONE_DEVICE head
page through the existing path, copy that final state into a reusable
template, refresh the PFN-dependent fields in that template before each
copy, and copy it into the remaining destination pages.
Use the template path unconditionally. The page_ref_set tracepoint is
primarily a debugging aid, while this code is still initializing struct
pages before they are handed out. From the perspective of users of those
pages, the initialization-time refcount transitions are not part of the
observable page lifetime.
This means page_ref_set will no longer observe every initialization-time
refcount assignment for copied ZONE_DEVICE head pages. The impact is
controlled because the final initialized struct page state is unchanged,
and keeping a separate non-template path only for this local tracepoint
observability would add complexity to the common path.
This patch accelerates head-page initialization. The pfns_per_compound ==
1 case gets the full benefit here, compound tails are handled in the next
patch.
Tested in a VM with a 100 GB fsdax namespace device configured with
map=dev on Intel Ice Lake server. This test exercises the nd_pmem rebind
path (pfns_per_compound == 1).
Test procedure:
Rebind the nd_pmem driver 30 times and collect the memmap initialization
time from the pr_debug() output of memmap_init_zone_device().
Base(v7.3-rc1):
Average of rebinds for nd_pmem driver: 221.07 ms
With this patch and its prerequisites applied:
Average of rebinds for nd_pmem driver: 155.00 ms
This reduces the average memmap initialization time measured during
rebind from 221.07 ms to 155.00 ms, or about 29.9%.
[lizhe.67@bytedance.com: whitespace fix, per Mike]
Link: https://lore.kernel.org/20260903025806.70825-1-lizhe.67@bytedance.com
Link: https://lore.kernel.org/20260831111638.76012-4-lizhe.67@bytedance.com
Signed-off-by: Li Zhe <lizhe.67@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand (Arm) <david@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Diffstat (limited to 'include/linux/string.h')
0 files changed, 0 insertions, 0 deletions
