This series is based on next-20220428.
This series amis to add hugetlb_optimize_vmemmap sysctl to enable or disable
the feature of optimizing vmemmap pages associated with HugeTLB pages.
v11:
- Collect Reviewed-by from Mike.
- Remove hugetlb_optimize_vmemmap_enabled() check from flush_free_hpage_work().
v10:
- Collect Reviewed-by from Mike.
- Remove hugetlb_optimize_vmemmap_enabled() check from
hugetlb_optimize_vmemmap_pages() (Mike).
- Add more explanation to Documentation/admin-guide/sysctl/vm.rst.
- Fix cannot disable the feature via hugetlb_optimize_vmemmap sysctl (Mike).
- Update patch 2's commit log (Mike).
v9:
- Go back to v3 since checking the size of struct page at config time is
very complex.
v8:
- Fix compilation (scripts/selinux/mdp/mdp.c) error when
CONFIG_SECURITY_SELINUX is selected.
v7:
- Fix circular dependency issue reported by kernel test robot.
- Introduce CONFIG_HUGETLB_PAGE_HAS_OPTIMIZE_VMEMMAP instead of
STRUCT_PAGE_SIZE_IS_POWER_OF_2.
- Add more comments into vm.rst to explain hugetlb_optimize_vmemmap (Andrew).
- Drop the patch "sysctl: allow to set extra1 to SYSCTL_ONE".
- Add a new patch "use kstrtobool for hugetlb_vmemmap param parsing".
- Reuse static_key's refcount to count the number of HugeTLB pages with
vmemmap pages optimized to simplify the lock scheme.
v6:
- Remove "make syncconfig" from Kbuild.
v5:
- Fix not working properly if one is workig off of a very clean build
reported by Luis Chamberlain.
- Add Suggested-by for Luis Chamberlain.
v4:
- Introduce STRUCT_PAGE_SIZE_IS_POWER_OF_2 inspired by Luis.
v3:
- Add pr_warn_once() (Mike).
- Handle the transition from enabling to disabling (Luis)
v2:
- Fix compilation when !CONFIG_MHP_MEMMAP_ON_MEMORY reported by kernel
test robot <[email protected]>.
- Move sysctl code from kernel/sysctl.c to mm/hugetlb_vmemmap.c.
Muchun Song (4):
mm: hugetlb_vmemmap: disable hugetlb_optimize_vmemmap when struct page
crosses page boundaries
mm: memory_hotplug: override memmap_on_memory when
hugetlb_free_vmemmap=on
mm: hugetlb_vmemmap: use kstrtobool for hugetlb_vmemmap param parsing
mm: hugetlb_vmemmap: add hugetlb_optimize_vmemmap sysctl
Documentation/admin-guide/kernel-parameters.txt | 6 +-
Documentation/admin-guide/sysctl/vm.rst | 39 +++++++++
include/linux/memory_hotplug.h | 9 ++
mm/hugetlb_vmemmap.c | 105 ++++++++++++++++++++----
mm/memory_hotplug.c | 27 ++++--
5 files changed, 162 insertions(+), 24 deletions(-)
--
2.11.0
Use kstrtobool rather than open coding "on" and "off" parsing in
mm/hugetlb_vmemmap.c, which is more powerful to handle all kinds
of parameters like 'Yy1Nn0' or [oO][NnFf] for "on" and "off".
Signed-off-by: Muchun Song <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]>
---
Documentation/admin-guide/kernel-parameters.txt | 6 +++---
mm/hugetlb_vmemmap.c | 10 +++++-----
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 308da668bbb1..43b8385073ad 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1703,10 +1703,10 @@
enabled.
Allows heavy hugetlb users to free up some more
memory (7 * PAGE_SIZE for each 2MB hugetlb page).
- Format: { on | off (default) }
+ Format: { [oO][Nn]/Y/y/1 | [oO][Ff]/N/n/0 (default) }
- on: enable the feature
- off: disable the feature
+ [oO][Nn]/Y/y/1: enable the feature
+ [oO][Ff]/N/n/0: disable the feature
Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y,
the default is on.
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 6254bb2d4ae5..cc4ec752ec16 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -28,15 +28,15 @@ EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);
static int __init hugetlb_vmemmap_early_param(char *buf)
{
- if (!buf)
+ bool enable;
+
+ if (kstrtobool(buf, &enable))
return -EINVAL;
- if (!strcmp(buf, "on"))
+ if (enable)
static_branch_enable(&hugetlb_optimize_vmemmap_key);
- else if (!strcmp(buf, "off"))
- static_branch_disable(&hugetlb_optimize_vmemmap_key);
else
- return -EINVAL;
+ static_branch_disable(&hugetlb_optimize_vmemmap_key);
return 0;
}
--
2.11.0
Optimizing HugeTLB vmemmap pages is not compatible with allocating memmap on
hot added memory. If "hugetlb_free_vmemmap=on" and
memory_hotplug.memmap_on_memory" are both passed on the kernel command line,
optimizing hugetlb pages takes precedence. However, the global variable
memmap_on_memory will still be set to 1, even though we will not try to
allocate memmap on hot added memory.
Also introduce mhp_memmap_on_memory() helper to move the definition of
"memmap_on_memory" to the scope of CONFIG_MHP_MEMMAP_ON_MEMORY. In the
next patch, mhp_memmap_on_memory() will also be exported to be used in
hugetlb_vmemmap.c.
Signed-off-by: Muchun Song <[email protected]>
Acked-by: Mike Kravetz <[email protected]>
---
mm/memory_hotplug.c | 32 ++++++++++++++++++++++++++------
1 file changed, 26 insertions(+), 6 deletions(-)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 111684878fd9..a6101ae402f9 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -42,14 +42,36 @@
#include "internal.h"
#include "shuffle.h"
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+static int memmap_on_memory_set(const char *val, const struct kernel_param *kp)
+{
+ if (hugetlb_optimize_vmemmap_enabled())
+ return 0;
+ return param_set_bool(val, kp);
+}
+
+static const struct kernel_param_ops memmap_on_memory_ops = {
+ .flags = KERNEL_PARAM_OPS_FL_NOARG,
+ .set = memmap_on_memory_set,
+ .get = param_get_bool,
+};
/*
* memory_hotplug.memmap_on_memory parameter
*/
static bool memmap_on_memory __ro_after_init;
-#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
-module_param(memmap_on_memory, bool, 0444);
+module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444);
MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
+
+static inline bool mhp_memmap_on_memory(void)
+{
+ return memmap_on_memory;
+}
+#else
+static inline bool mhp_memmap_on_memory(void)
+{
+ return false;
+}
#endif
enum {
@@ -1263,9 +1285,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size)
* altmap as an alternative source of memory, and we do not exactly
* populate a single PMD.
*/
- return memmap_on_memory &&
- !hugetlb_optimize_vmemmap_enabled() &&
- IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) &&
+ return mhp_memmap_on_memory() &&
size == memory_block_size_bytes() &&
IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
@@ -2083,7 +2103,7 @@ static int __ref try_remove_memory(u64 start, u64 size)
* We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
* the same granularity it was added - a single memory block.
*/
- if (memmap_on_memory) {
+ if (mhp_memmap_on_memory()) {
nr_vmemmap_pages = walk_memory_blocks(start, size, NULL,
get_nr_vmemmap_pages_cb);
if (nr_vmemmap_pages) {
--
2.11.0
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.
Signed-off-by: Muchun Song <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]>
---
Documentation/admin-guide/sysctl/vm.rst | 39 ++++++++++++++
include/linux/memory_hotplug.h | 9 ++++
mm/hugetlb_vmemmap.c | 93 +++++++++++++++++++++++++++++----
mm/memory_hotplug.c | 7 +--
4 files changed, 133 insertions(+), 15 deletions(-)
diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index 747e325ebcd0..5c9aa171a0d3 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -562,6 +562,45 @@ Change the minimum size of the hugepage pool.
See Documentation/admin-guide/mm/hugetlbpage.rst
+hugetlb_optimize_vmemmap
+========================
+
+This knob is not available when memory_hotplug.memmap_on_memory (kernel parameter)
+is configured or the size of 'struct page' (a structure defined in
+include/linux/mm_types.h) is not power of two (an unusual system config could
+result in this).
+
+Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap pages
+associated with each HugeTLB page.
+
+Once enabled, the vmemmap pages of subsequent allocation of HugeTLB pages from
+buddy allocator will be optimized (7 pages per 2MB HugeTLB page and 4095 pages
+per 1GB HugeTLB page), whereas already allocated HugeTLB pages will not be
+optimized. When those optimized HugeTLB pages are freed from the HugeTLB pool
+to the buddy allocator, the vmemmap pages representing that range needs to be
+remapped again and the vmemmap pages discarded earlier need to be rellocated
+again. If your use case is that HugeTLB pages are allocated 'on the fly' (e.g.
+never explicitly allocating HugeTLB pages with 'nr_hugepages' but only set
+'nr_overcommit_hugepages', those overcommitted HugeTLB pages are allocated 'on
+the fly') instead of being pulled from the HugeTLB pool, you should weigh the
+benefits of memory savings against the more overhead (~2x slower than before)
+of allocation or freeing HugeTLB pages between the HugeTLB pool and the buddy
+allocator. Another behavior to note is that if the system is under heavy memory
+pressure, it could prevent the user from freeing HugeTLB pages from the HugeTLB
+pool to the buddy allocator since the allocation of vmemmap pages could be
+failed, you have to retry later if your system encounter this situation.
+
+Once disabled, the vmemmap pages of subsequent allocation of HugeTLB pages from
+buddy allocator will not be optimized meaning the extra overhead at allocation
+time from buddy allocator disappears, whereas already optimized HugeTLB pages
+will not be affected. If you want to make sure there are no optimized HugeTLB
+pages, you can set "nr_hugepages" to 0 first and then disable this. Note that
+writing 0 to nr_hugepages will make any "in use" HugeTLB pages become surplus
+pages. So, those surplus pages are still optimized until they are no longer
+in use. You would need to wait for those surplus pages to be released before
+there are no optimized pages in the system.
+
+
nr_hugepages_mempolicy
======================
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 029fb7e26504..917112661b5c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -351,4 +351,13 @@ void arch_remove_linear_mapping(u64 start, u64 size);
extern bool mhp_supports_memmap_on_memory(unsigned long size);
#endif /* CONFIG_MEMORY_HOTPLUG */
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+bool mhp_memmap_on_memory(void);
+#else
+static inline bool mhp_memmap_on_memory(void)
+{
+ return false;
+}
+#endif
+
#endif /* __LINUX_MEMORY_HOTPLUG_H */
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 */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a6101ae402f9..c72070cdd055 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -63,15 +63,10 @@ static bool memmap_on_memory __ro_after_init;
module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444);
MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
-static inline bool mhp_memmap_on_memory(void)
+bool mhp_memmap_on_memory(void)
{
return memmap_on_memory;
}
-#else
-static inline bool mhp_memmap_on_memory(void)
-{
- return false;
-}
#endif
enum {
--
2.11.0