The patch titled
Subject: mm: override mTHP "enabled" defaults at kernel cmdline
has been added to the -mm mm-unstable branch. Its filename is
mm-override-mthp-enabled-defaults-at-kernel-cmdline.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-override-mthp-enabled-defaults-at-kernel-cmdline.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Ryan Roberts <ryan.roberts@xxxxxxx>
Subject: mm: override mTHP "enabled" defaults at kernel cmdline
Date: Wed, 14 Aug 2024 14:02:47 +1200
Add thp_anon= cmdline parameter to allow specifying the default enablement
of each supported anon THP size. The parameter accepts the following
format and can be provided multiple times to configure each size:
thp_anon=<size>,<size>[KMG]:<value>;<size>-<size>[KMG]:<value>
An example:
thp_anon=16K-64K:always;128K,512K:inherit;256K:madvise;1M-2M:never
See Documentation/admin-guide/mm/transhuge.rst for more details.
Configuring the defaults at boot time is useful to allow early user
space to take advantage of mTHP before its been configured through
sysfs.
Link: https://lkml.kernel.org/r/20240814020247.67297-1-21cnbao@xxxxxxxxx
Signed-off-by: Ryan Roberts <ryan.roberts@xxxxxxx>
Co-developed-by: Barry Song <v-songbaohua@xxxxxxxx>
Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
Cc: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Lance Yang <ioworker0@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/admin-guide/kernel-parameters.txt | 9 +
Documentation/admin-guide/mm/transhuge.rst | 35 ++++-
mm/huge_memory.c | 96 +++++++++++++-
3 files changed, 133 insertions(+), 7 deletions(-)
--- a/Documentation/admin-guide/kernel-parameters.txt~mm-override-mthp-enabled-defaults-at-kernel-cmdline
+++ a/Documentation/admin-guide/kernel-parameters.txt
@@ -6629,6 +6629,15 @@
<deci-seconds>: poll all this frequency
0: no polling (default)
+ thp_anon= [KNL]
+ Format: <size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state>
+ state is one of "always", "madvise", "never" or "inherit".
+ Can be used to control the default behavior of the
+ system with respect to anonymous transparent hugepages.
+ Can be used multiple times for multiple anon THP sizes.
+ See Documentation/admin-guide/mm/transhuge.rst for more
+ details.
+
threadirqs [KNL,EARLY]
Force threading of all interrupt handlers except those
marked explicitly IRQF_NO_THREAD.
--- a/Documentation/admin-guide/mm/transhuge.rst~mm-override-mthp-enabled-defaults-at-kernel-cmdline
+++ a/Documentation/admin-guide/mm/transhuge.rst
@@ -284,13 +284,36 @@ that THP is shared. Exceeding the number
A higher value may increase memory footprint for some workloads.
-Boot parameter
-==============
+Boot parameters
+===============
-You can change the sysfs boot time defaults of Transparent Hugepage
-Support by passing the parameter ``transparent_hugepage=always`` or
-``transparent_hugepage=madvise`` or ``transparent_hugepage=never``
-to the kernel command line.
+You can change the sysfs boot time default for the top-level "enabled"
+control by passing the parameter ``transparent_hugepage=always`` or
+``transparent_hugepage=madvise`` or ``transparent_hugepage=never`` to the
+kernel command line.
+
+Alternatively, each supported anonymous THP size can be controlled by
+passing ``thp_anon=<size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state>``,
+where ``<size>`` is the THP size and ``<state>`` is one of ``always``,
+``madvise``, ``never`` or ``inherit``.
+
+For example, the following will set 16K, 32K, 64K THP to ``always``,
+set 128K, 512K to ``inherit``, set 256K to ``madvise`` and 1M, 2M
+to ``never``::
+
+ thp_anon=16K-64K:always;128K,512K:inherit;256K:madvise;1M-2M:never
+
+``thp_anon=`` may be specified multiple times to configure all THP sizes as
+required. If ``thp_anon=`` is specified at least once, any anon THP sizes
+not explicitly configured on the command line are implicitly set to
+``never``.
+
+``transparent_hugepage`` setting only affects the global toggle. If
+``thp_anon`` is not specified, PMD_ORDER THP will default to ``inherit``.
+However, if a valid ``thp_anon`` setting is provided by the user, the
+PMD_ORDER THP policy will be overridden. If the policy for PMD_ORDER
+is not defined within a valid ``thp_anon``, its policy will default to
+``never``.
Hugepages in tmpfs/shmem
========================
--- a/mm/huge_memory.c~mm-override-mthp-enabled-defaults-at-kernel-cmdline
+++ a/mm/huge_memory.c
@@ -82,6 +82,7 @@ unsigned long huge_zero_pfn __read_mostl
unsigned long huge_anon_orders_always __read_mostly;
unsigned long huge_anon_orders_madvise __read_mostly;
unsigned long huge_anon_orders_inherit __read_mostly;
+static bool anon_orders_configured;
unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
unsigned long vm_flags,
@@ -756,7 +757,10 @@ static int __init hugepage_init_sysfs(st
* disable all other sizes. powerpc's PMD_ORDER isn't a compile-time
* constant so we have to do this here.
*/
- huge_anon_orders_inherit = BIT(PMD_ORDER);
+ if (!anon_orders_configured) {
+ huge_anon_orders_inherit = BIT(PMD_ORDER);
+ anon_orders_configured = true;
+ }
*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!*hugepage_kobj)) {
@@ -941,6 +945,96 @@ out:
}
__setup("transparent_hugepage=", setup_transparent_hugepage);
+static inline int get_order_from_str(const char *size_str)
+{
+ unsigned long size;
+ char *endptr;
+ int order;
+
+ size = memparse(size_str, &endptr);
+ order = fls(size >> PAGE_SHIFT) - 1;
+ if ((1 << order) & ~THP_ORDERS_ALL_ANON) {
+ pr_err("invalid size %s(order %d) in thp_anon boot parameter\n",
+ size_str, order);
+ return -EINVAL;
+ }
+
+ return order;
+}
+
+static char str_dup[PAGE_SIZE] __meminitdata;
+static int __init setup_thp_anon(char *str)
+{
+ char *token, *range, *policy, *subtoken;
+ unsigned long always, inherit, madvise;
+ char *start_size, *end_size;
+ int start, end;
+ char *p;
+
+ if (!str || strlen(str) + 1 > PAGE_SIZE)
+ goto err;
+ strcpy(str_dup, str);
+
+ always = huge_anon_orders_always;
+ madvise = huge_anon_orders_madvise;
+ inherit = huge_anon_orders_inherit;
+ p = str_dup;
+ while ((token = strsep(&p, ";")) != NULL) {
+ range = strsep(&token, ":");
+ policy = token;
+
+ if (!policy)
+ goto err;
+
+ while ((subtoken = strsep(&range, ",")) != NULL) {
+ if (strchr(subtoken, '-')) {
+ start_size = strsep(&subtoken, "-");
+ end_size = subtoken;
+
+ start = get_order_from_str(start_size);
+ end = get_order_from_str(end_size);
+ } else {
+ start = end = get_order_from_str(subtoken);
+ }
+
+ if (start < 0 || end < 0 || start > end)
+ goto err;
+
+ if (!strcmp(policy, "always")) {
+ bitmap_set(&always, start, end - start + 1);
+ bitmap_clear(&inherit, start, end - start + 1);
+ bitmap_clear(&madvise, start, end - start + 1);
+ } else if (!strcmp(policy, "madvise")) {
+ bitmap_set(&madvise, start, end - start + 1);
+ bitmap_clear(&inherit, start, end - start + 1);
+ bitmap_clear(&always, start, end - start + 1);
+ } else if (!strcmp(policy, "inherit")) {
+ bitmap_set(&inherit, start, end - start + 1);
+ bitmap_clear(&madvise, start, end - start + 1);
+ bitmap_clear(&always, start, end - start + 1);
+ } else if (!strcmp(policy, "never")) {
+ bitmap_clear(&inherit, start, end - start + 1);
+ bitmap_clear(&madvise, start, end - start + 1);
+ bitmap_clear(&always, start, end - start + 1);
+ } else {
+ pr_err("invalid policy %s in thp_anon boot parameter\n", policy);
+ goto err;
+ }
+ }
+ }
+
+ huge_anon_orders_always = always;
+ huge_anon_orders_madvise = madvise;
+ huge_anon_orders_inherit = inherit;
+ anon_orders_configured = true;
+ return 1;
+
+err:
+ pr_warn("thp_anon=%s: cannot parse, ignored\n", str);
+ return 0;
+}
+__setup("thp_anon=", setup_thp_anon);
+
pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
_
Patches currently in -mm which might be from ryan.roberts@xxxxxxx are
mm-cleanup-count_mthp_stat-definition.patch
mm-tidy-up-shmem-mthp-controls-and-stats.patch
mm-override-mthp-enabled-defaults-at-kernel-cmdline.patch
