summaryrefslogtreecommitdiff
path: root/mm/hugetlb_vmemmap.c
diff options
context:
space:
mode:
authorMuchun Song <songmuchun@bytedance.com>2022-05-13 16:48:56 -0700
committerAndrew Morton <akpm@linux-foundation.org>2022-05-13 16:48:56 -0700
commit78f39084b41d287aedb2ea55f2c1895cfa11d61a (patch)
treec62a4a812871d03a691e9867dd6810fc37ea2dd2 /mm/hugetlb_vmemmap.c
parent9c54c522bb76cbef480722bd44059e2ba8304bd2 (diff)
mm: hugetlb_vmemmap: add hugetlb_optimize_vmemmap sysctl
We must add hugetlb_free_vmemmap=on (or "off") to the boot cmdline and reboot the server to enable or disable the feature of optimizing vmemmap pages associated with HugeTLB pages. However, rebooting usually takes a long time. So add a sysctl to enable or disable the feature at runtime without rebooting. Why we need this? There are 3 use cases. 1) The feature of minimizing overhead of struct page associated with each HugeTLB is disabled by default without passing "hugetlb_free_vmemmap=on" to the boot cmdline. When we (ByteDance) deliver the servers to the users who want to enable this feature, they have to configure the grub (change boot cmdline) and reboot the servers, whereas rebooting usually takes a long time (we have thousands of servers). It's a very bad experience for the users. So we need a approach to enable this feature after rebooting. This is a use case in our practical environment. 2) Some use cases are that HugeTLB pages are allocated 'on the fly' instead of being pulled from the HugeTLB pool, those workloads would be affected with this feature enabled. Those workloads could be identified by the characteristics of they never explicitly allocating huge pages with 'nr_hugepages' but only set 'nr_overcommit_hugepages' and then let the pages be allocated from the buddy allocator at fault time. We can confirm it is a real use case from the commit 099730d67417. For those workloads, the page fault time could be ~2x slower than before. We suspect those users want to disable this feature if the system has enabled this before and they don't think the memory savings benefit is enough to make up for the performance drop. 3) If the workload which wants vmemmap pages to be optimized and the workload which wants to set 'nr_overcommit_hugepages' and does not want the extera overhead at fault time when the overcommitted pages be allocated from the buddy allocator are deployed in the same server. The user could enable this feature and set 'nr_hugepages' and 'nr_overcommit_hugepages', then disable the feature. In this case, the overcommited HugeTLB pages will not encounter the extra overhead at fault time. Link: https://lkml.kernel.org/r/20220512041142.39501-5-songmuchun@bytedance.com Signed-off-by: Muchun Song <songmuchun@bytedance.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Iurii Zaikin <yzaikin@google.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: David Hildenbrand <david@redhat.com> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/hugetlb_vmemmap.c')
-rw-r--r--mm/hugetlb_vmemmap.c93
1 files changed, 84 insertions, 9 deletions
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index cc4ec752ec16..fcd9f7872064 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -10,6 +10,7 @@
*/
#define pr_fmt(fmt) "HugeTLB: " fmt
+#include <linux/memory_hotplug.h>
#include "hugetlb_vmemmap.h"
/*
@@ -22,21 +23,40 @@
#define RESERVE_VMEMMAP_NR 1U
#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+enum vmemmap_optimize_mode {
+ VMEMMAP_OPTIMIZE_OFF,
+ VMEMMAP_OPTIMIZE_ON,
+};
+
DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
hugetlb_optimize_vmemmap_key);
EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);
+static enum vmemmap_optimize_mode vmemmap_optimize_mode =
+ IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON);
+
+static void vmemmap_optimize_mode_switch(enum vmemmap_optimize_mode to)
+{
+ if (vmemmap_optimize_mode == to)
+ return;
+
+ if (to == VMEMMAP_OPTIMIZE_OFF)
+ static_branch_dec(&hugetlb_optimize_vmemmap_key);
+ else
+ static_branch_inc(&hugetlb_optimize_vmemmap_key);
+ WRITE_ONCE(vmemmap_optimize_mode, to);
+}
+
static int __init hugetlb_vmemmap_early_param(char *buf)
{
bool enable;
+ enum vmemmap_optimize_mode mode;
if (kstrtobool(buf, &enable))
return -EINVAL;
- if (enable)
- static_branch_enable(&hugetlb_optimize_vmemmap_key);
- else
- static_branch_disable(&hugetlb_optimize_vmemmap_key);
+ mode = enable ? VMEMMAP_OPTIMIZE_ON : VMEMMAP_OPTIMIZE_OFF;
+ vmemmap_optimize_mode_switch(mode);
return 0;
}
@@ -69,8 +89,10 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
*/
ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse,
GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE);
- if (!ret)
+ if (!ret) {
ClearHPageVmemmapOptimized(head);
+ static_branch_dec(&hugetlb_optimize_vmemmap_key);
+ }
return ret;
}
@@ -84,6 +106,11 @@ void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
if (!vmemmap_pages)
return;
+ if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF)
+ return;
+
+ static_branch_inc(&hugetlb_optimize_vmemmap_key);
+
vmemmap_addr += RESERVE_VMEMMAP_SIZE;
vmemmap_end = vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
vmemmap_reuse = vmemmap_addr - PAGE_SIZE;
@@ -93,7 +120,9 @@ void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
* to the page which @vmemmap_reuse is mapped to, then free the pages
* which the range [@vmemmap_addr, @vmemmap_end] is mapped to.
*/
- if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse))
+ if (vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse))
+ static_branch_dec(&hugetlb_optimize_vmemmap_key);
+ else
SetHPageVmemmapOptimized(head);
}
@@ -110,9 +139,6 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
BUILD_BUG_ON(__NR_USED_SUBPAGE >=
RESERVE_VMEMMAP_SIZE / sizeof(struct page));
- if (!hugetlb_optimize_vmemmap_enabled())
- return;
-
if (!is_power_of_2(sizeof(struct page))) {
pr_warn_once("cannot optimize vmemmap pages because \"struct page\" crosses page boundaries\n");
static_branch_disable(&hugetlb_optimize_vmemmap_key);
@@ -134,3 +160,52 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
pr_info("can optimize %d vmemmap pages for %s\n",
h->optimize_vmemmap_pages, h->name);
}
+
+#ifdef CONFIG_PROC_SYSCTL
+static int hugetlb_optimize_vmemmap_handler(struct ctl_table *table, int write,
+ void *buffer, size_t *length,
+ loff_t *ppos)
+{
+ int ret;
+ enum vmemmap_optimize_mode mode;
+ static DEFINE_MUTEX(sysctl_mutex);
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ mutex_lock(&sysctl_mutex);
+ mode = vmemmap_optimize_mode;
+ table->data = &mode;
+ ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
+ if (write && !ret)
+ vmemmap_optimize_mode_switch(mode);
+ mutex_unlock(&sysctl_mutex);
+
+ return ret;
+}
+
+static struct ctl_table hugetlb_vmemmap_sysctls[] = {
+ {
+ .procname = "hugetlb_optimize_vmemmap",
+ .maxlen = sizeof(enum vmemmap_optimize_mode),
+ .mode = 0644,
+ .proc_handler = hugetlb_optimize_vmemmap_handler,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ { }
+};
+
+static __init int hugetlb_vmemmap_sysctls_init(void)
+{
+ /*
+ * If "memory_hotplug.memmap_on_memory" is enabled or "struct page"
+ * crosses page boundaries, the vmemmap pages cannot be optimized.
+ */
+ if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page)))
+ register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
+
+ return 0;
+}
+late_initcall(hugetlb_vmemmap_sysctls_init);
+#endif /* CONFIG_PROC_SYSCTL */