diff mbox series

[v8,1/3] mm: add new api to enable ksm per process

Message ID 20230415225913.3206647-2-shr@devkernel.io (mailing list archive)
State New
Headers show
Series mm: process/cgroup ksm support | expand

Commit Message

Stefan Roesch April 15, 2023, 10:59 p.m. UTC
So far KSM can only be enabled by calling madvise for memory regions.  To
be able to use KSM for more workloads, KSM needs to have the ability to be
enabled / disabled at the process / cgroup level.

1. New options for prctl system command

   This patch series adds two new options to the prctl system call.
   The first one allows to enable KSM at the process level and the second
   one to query the setting.

   The setting will be inherited by child processes.

   With the above setting, KSM can be enabled for the seed process of a
   cgroup and all processes in the cgroup will inherit the setting.

2. Changes to KSM processing

   When KSM is enabled at the process level, the KSM code will iterate
   over all the VMA's and enable KSM for the eligible VMA's.

   When forking a process that has KSM enabled, the setting will be
   inherited by the new child process.

  1) Introduce new MMF_VM_MERGE_ANY flag

     This introduces the new flag MMF_VM_MERGE_ANY flag.  When this flag
     is set, kernel samepage merging (ksm) gets enabled for all vma's of a
     process.

  2) Setting VM_MERGEABLE on VMA creation

     When a VMA is created, if the MMF_VM_MERGE_ANY flag is set, the
     VM_MERGEABLE flag will be set for this VMA.

  3) support disabling of ksm for a process

     This adds the ability to disable ksm for a process if ksm has been
     enabled for the process with prctl.

  4) add new prctl option to get and set ksm for a process

     This adds two new options to the prctl system call
     - enable ksm for all vmas of a process (if the vmas support it).
     - query if ksm has been enabled for a process.

3. Disabling MMF_VM_MERGE_ANY for storage keys in s390

   In the s390 architecture when storage keys are used, the
   MMF_VM_MERGE_ANY will be disabled.

Signed-off-by: Stefan Roesch <shr@devkernel.io>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/s390/mm/gmap.c            |   7 +++
 include/linux/ksm.h            |  21 ++++++-
 include/linux/sched/coredump.h |   1 +
 include/uapi/linux/prctl.h     |   2 +
 kernel/sys.c                   |  27 +++++++++
 mm/ksm.c                       | 106 +++++++++++++++++++++++++++------
 mm/mmap.c                      |   3 +
 7 files changed, 148 insertions(+), 19 deletions(-)

Comments

David Hildenbrand April 17, 2023, 3 p.m. UTC | #1
> +static void __ksm_add_vma(struct vm_area_struct *vma)
> +{
> +	unsigned long vm_flags = vma->vm_flags;
> +
> +	if (vm_flags & VM_MERGEABLE)
> +		return;
> +
> +	if (vma_ksm_compatible(vma)) {
> +		vm_flags |= VM_MERGEABLE;
> +		vm_flags_reset(vma, vm_flags);
> +	}
> +}

We can do the following simplification on top:

diff --git a/mm/ksm.c b/mm/ksm.c
index 905c8edce5cf..26e7f585d65d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2511,15 +2511,11 @@ static int ksm_scan_thread(void *nothing)

  static void __ksm_add_vma(struct vm_area_struct *vma)
  {
-	unsigned long vm_flags = vma->vm_flags;
-
-	if (vm_flags & VM_MERGEABLE)
+	if (vma->vm_flags & VM_MERGEABLE)
  		return;

-	if (vma_ksm_compatible(vma)) {
-		vm_flags |= VM_MERGEABLE;
-		vm_flags_reset(vma, vm_flags);
-	}
+	if (vma_ksm_compatible(vma))
+		vm_flags_set(vma, VM_MERGEABLE);
  }

  /**
Stefan Roesch April 17, 2023, 4:36 p.m. UTC | #2
David Hildenbrand <david@redhat.com> writes:

>> +static void __ksm_add_vma(struct vm_area_struct *vma)
>> +{
>> +	unsigned long vm_flags = vma->vm_flags;
>> +
>> +	if (vm_flags & VM_MERGEABLE)
>> +		return;
>> +
>> +	if (vma_ksm_compatible(vma)) {
>> +		vm_flags |= VM_MERGEABLE;
>> +		vm_flags_reset(vma, vm_flags);
>> +	}
>> +}
>
> We can do the following simplification on top:
>
> diff --git a/mm/ksm.c b/mm/ksm.c
> index 905c8edce5cf..26e7f585d65d 100644
> --- a/mm/ksm.c
> +++ b/mm/ksm.c
> @@ -2511,15 +2511,11 @@ static int ksm_scan_thread(void *nothing)
>
>  static void __ksm_add_vma(struct vm_area_struct *vma)
>  {
> -	unsigned long vm_flags = vma->vm_flags;
> -
> -	if (vm_flags & VM_MERGEABLE)
> +	if (vma->vm_flags & VM_MERGEABLE)
>  		return;
>
> -	if (vma_ksm_compatible(vma)) {
> -		vm_flags |= VM_MERGEABLE;
> -		vm_flags_reset(vma, vm_flags);
> -	}
> +	if (vma_ksm_compatible(vma))
> +		vm_flags_set(vma, VM_MERGEABLE);
>  }
>
>  /**
> --
> 2.39.2
>
>

The next version has the above change.

> I have some patches based on your patch set (handling/testing unmerging whens
> setting PR_SET_MEMORY_MERGE=0. Will send out once you changes are queued.
diff mbox series

Patch

diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 5a716bdcba05..0949811761e6 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2591,6 +2591,13 @@  int gmap_mark_unmergeable(void)
 	int ret;
 	VMA_ITERATOR(vmi, mm, 0);
 
+	/*
+	 * Make sure to disable KSM (if enabled for the whole process or
+	 * individual VMAs). Note that nothing currently hinders user space
+	 * from re-enabling it.
+	 */
+	clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
+
 	for_each_vma(vmi, vma) {
 		/* Copy vm_flags to avoid partial modifications in ksm_madvise */
 		vm_flags = vma->vm_flags;
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 7e232ba59b86..fa996373653b 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -18,13 +18,26 @@ 
 #ifdef CONFIG_KSM
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags);
+
+void ksm_add_vma(struct vm_area_struct *vma);
+int ksm_enable_merge_any(struct mm_struct *mm);
+
 int __ksm_enter(struct mm_struct *mm);
 void __ksm_exit(struct mm_struct *mm);
 
 static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
-		return __ksm_enter(mm);
+	int ret;
+
+	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) {
+		ret = __ksm_enter(mm);
+		if (ret)
+			return ret;
+	}
+
+	if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags))
+		set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+
 	return 0;
 }
 
@@ -53,6 +66,10 @@  void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
 
 #else  /* !CONFIG_KSM */
 
+static inline void ksm_add_vma(struct vm_area_struct *vma)
+{
+}
+
 static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	return 0;
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 0e17ae7fbfd3..0ee96ea7a0e9 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -90,4 +90,5 @@  static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
 				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK)
 
+#define MMF_VM_MERGE_ANY	29
 #endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index b99c0be72577..f23d9a16507f 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -292,4 +292,6 @@  struct prctl_mm_map {
 
 #define PR_GET_AUXV			0x41555856
 
+#define PR_SET_MEMORY_MERGE		67
+#define PR_GET_MEMORY_MERGE		68
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 26c1399e0654..72cdb16e2636 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -15,6 +15,7 @@ 
 #include <linux/highuid.h>
 #include <linux/fs.h>
 #include <linux/kmod.h>
+#include <linux/ksm.h>
 #include <linux/perf_event.h>
 #include <linux/resource.h>
 #include <linux/kernel.h>
@@ -2687,6 +2688,32 @@  SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SET_VMA:
 		error = prctl_set_vma(arg2, arg3, arg4, arg5);
 		break;
+#ifdef CONFIG_KSM
+	case PR_SET_MEMORY_MERGE:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		if (mmap_write_lock_killable(me->mm))
+			return -EINTR;
+
+		if (arg2) {
+			error = ksm_enable_merge_any(me->mm);
+		} else {
+			/*
+			 * TODO: we might want disable KSM on all VMAs and
+			 * trigger unsharing to completely disable KSM.
+			 */
+			clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+			error = 0;
+		}
+		mmap_write_unlock(me->mm);
+		break;
+	case PR_GET_MEMORY_MERGE:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+		break;
+#endif
 	default:
 		error = -EINVAL;
 		break;
diff --git a/mm/ksm.c b/mm/ksm.c
index 290a3eb6d8de..1c81e4408af1 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -515,6 +515,28 @@  static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 	return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
 }
 
+static bool vma_ksm_compatible(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & (VM_SHARED  | VM_MAYSHARE   | VM_PFNMAP  |
+			     VM_IO      | VM_DONTEXPAND | VM_HUGETLB |
+			     VM_MIXEDMAP))
+		return false;		/* just ignore the advice */
+
+	if (vma_is_dax(vma))
+		return false;
+
+#ifdef VM_SAO
+	if (vma->vm_flags & VM_SAO)
+		return false;
+#endif
+#ifdef VM_SPARC_ADI
+	if (vma->vm_flags & VM_SPARC_ADI)
+		return false;
+#endif
+
+	return true;
+}
+
 static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
 		unsigned long addr)
 {
@@ -1026,6 +1048,7 @@  static int unmerge_and_remove_all_rmap_items(void)
 
 			mm_slot_free(mm_slot_cache, mm_slot);
 			clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+			clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 			mmdrop(mm);
 		} else
 			spin_unlock(&ksm_mmlist_lock);
@@ -2408,6 +2431,7 @@  static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 
 		mm_slot_free(mm_slot_cache, mm_slot);
 		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 		mmap_read_unlock(mm);
 		mmdrop(mm);
 	} else {
@@ -2485,6 +2509,68 @@  static int ksm_scan_thread(void *nothing)
 	return 0;
 }
 
+static void __ksm_add_vma(struct vm_area_struct *vma)
+{
+	unsigned long vm_flags = vma->vm_flags;
+
+	if (vm_flags & VM_MERGEABLE)
+		return;
+
+	if (vma_ksm_compatible(vma)) {
+		vm_flags |= VM_MERGEABLE;
+		vm_flags_reset(vma, vm_flags);
+	}
+}
+
+/**
+ * ksm_add_vma - Mark vma as mergeable if compatible
+ *
+ * @vma:  Pointer to vma
+ */
+void ksm_add_vma(struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+		__ksm_add_vma(vma);
+}
+
+static void ksm_add_vmas(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+
+	VMA_ITERATOR(vmi, mm, 0);
+	for_each_vma(vmi, vma)
+		__ksm_add_vma(vma);
+}
+
+/**
+ * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all
+ *                        compatible VMA's
+ *
+ * @mm:  Pointer to mm
+ *
+ * Returns 0 on success, otherwise error code
+ */
+int ksm_enable_merge_any(struct mm_struct *mm)
+{
+	int err;
+
+	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+		return 0;
+
+	if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+		err = __ksm_enter(mm);
+		if (err)
+			return err;
+	}
+
+	set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+	ksm_add_vmas(mm);
+
+	return 0;
+}
+
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags)
 {
@@ -2493,25 +2579,10 @@  int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 
 	switch (advice) {
 	case MADV_MERGEABLE:
-		/*
-		 * Be somewhat over-protective for now!
-		 */
-		if (*vm_flags & (VM_MERGEABLE | VM_SHARED  | VM_MAYSHARE   |
-				 VM_PFNMAP    | VM_IO      | VM_DONTEXPAND |
-				 VM_HUGETLB | VM_MIXEDMAP))
-			return 0;		/* just ignore the advice */
-
-		if (vma_is_dax(vma))
+		if (vma->vm_flags & VM_MERGEABLE)
 			return 0;
-
-#ifdef VM_SAO
-		if (*vm_flags & VM_SAO)
+		if (!vma_ksm_compatible(vma))
 			return 0;
-#endif
-#ifdef VM_SPARC_ADI
-		if (*vm_flags & VM_SPARC_ADI)
-			return 0;
-#endif
 
 		if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
 			err = __ksm_enter(mm);
@@ -2615,6 +2686,7 @@  void __ksm_exit(struct mm_struct *mm)
 
 	if (easy_to_free) {
 		mm_slot_free(mm_slot_cache, mm_slot);
+		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
 		mmdrop(mm);
 	} else if (mm_slot) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 51cd747884e3..10e573535380 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -46,6 +46,7 @@ 
 #include <linux/pkeys.h>
 #include <linux/oom.h>
 #include <linux/sched/mm.h>
+#include <linux/ksm.h>
 
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
@@ -2691,6 +2692,7 @@  unsigned long mmap_region(struct file *file, unsigned long addr,
 	if (file && vm_flags & VM_SHARED)
 		mapping_unmap_writable(file->f_mapping);
 	file = vma->vm_file;
+	ksm_add_vma(vma);
 expanded:
 	perf_event_mmap(vma);
 
@@ -2963,6 +2965,7 @@  static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		goto mas_store_fail;
 
 	mm->map_count++;
+	ksm_add_vma(vma);
 out:
 	perf_event_mmap(vma);
 	mm->total_vm += len >> PAGE_SHIFT;