mm/mempolicy: add set_mempolicy_home_node syscall

This syscall can be used to set a home node for the MPOL_BIND and
MPOL_PREFERRED_MANY memory policy.  Users should use this syscall after
setting up a memory policy for the specified range as shown below.

  mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp,
        new_nodes->size + 1, 0);
  sys_set_mempolicy_home_node((unsigned long)p, nr_pages * page_size,
				home_node, 0);

The syscall allows specifying a home node/preferred node from which
kernel will fulfill memory allocation requests first.

For address range with MPOL_BIND memory policy, if nodemask specifies
more than one node, page allocations will come from the node in the
nodemask with sufficient free memory that is closest to the home
node/preferred node.

For MPOL_PREFERRED_MANY if the nodemask specifies more than one node,
page allocation will come from the node in the nodemask with sufficient
free memory that is closest to the home node/preferred node.  If there
is not enough memory in all the nodes specified in the nodemask, the
allocation will be attempted from the closest numa node to the home node
in the system.

This helps applications to hint at a memory allocation preference node
and fallback to _only_ a set of nodes if the memory is not available on
the preferred node.  Fallback allocation is attempted from the node
which is nearest to the preferred node.

This helps applications to have control on memory allocation numa nodes
and avoids default fallback to slow memory NUMA nodes.  For example a
system with NUMA nodes 1,2 and 3 with DRAM memory and 10, 11 and 12 of
slow memory

 new_nodes = numa_bitmask_alloc(nr_nodes);

 numa_bitmask_setbit(new_nodes, 1);
 numa_bitmask_setbit(new_nodes, 2);
 numa_bitmask_setbit(new_nodes, 3);

 p = mmap(NULL, nr_pages * page_size, protflag, mapflag, -1, 0);
 mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp,  new_nodes->size + 1, 0);

 sys_set_mempolicy_home_node(p, nr_pages * page_size, 2, 0);

This will allocate from nodes closer to node 2 and will make sure the
kernel will only allocate from nodes 1, 2, and 3.  Memory will not be
allocated from slow memory nodes 10, 11, and 12.  This differs from
default MPOL_BIND behavior in that with default MPOL_BIND the allocation
will be attempted from node closer to the local node.  One of the
reasons to specify a home node is to allow allocations from cpu less
NUMA node and its nearby NUMA nodes.

With MPOL_PREFERRED_MANY on the other hand will first try to allocate
from the closest node to node 2 from the node list 1, 2 and 3.  If those
nodes don't have enough memory, kernel will allocate from slow memory
node 10, 11 and 12 which ever is closer to node 2.

Link: https://lkml.kernel.org/r/20211202123810.267175-3-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Ben Widawsky <ben.widawsky@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 79 insertions, 0 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index de70f119984a..fc6cae7926f3 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -296,6 +296,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	atomic_set(&policy->refcnt, 1);
 	policy->mode = mode;
 	policy->flags = flags;
+	policy->home_node = NUMA_NO_NODE;
 
 	return policy;
 }
@@ -1478,6 +1479,77 @@ static long kernel_mbind(unsigned long start, unsigned long len,
 	return do_mbind(start, len, lmode, mode_flags, &nodes, flags);
 }
 
+SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len,
+		unsigned long, home_node, unsigned long, flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	struct mempolicy *new;
+	unsigned long vmstart;
+	unsigned long vmend;
+	unsigned long end;
+	int err = -ENOENT;
+
+	start = untagged_addr(start);
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+	/*
+	 * flags is used for future extension if any.
+	 */
+	if (flags != 0)
+		return -EINVAL;
+
+	/*
+	 * Check home_node is online to avoid accessing uninitialized
+	 * NODE_DATA.
+	 */
+	if (home_node >= MAX_NUMNODES || !node_online(home_node))
+		return -EINVAL;
+
+	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
+	end = start + len;
+
+	if (end < start)
+		return -EINVAL;
+	if (end == start)
+		return 0;
+	mmap_write_lock(mm);
+	vma = find_vma(mm, start);
+	for (; vma && vma->vm_start < end;  vma = vma->vm_next) {
+
+		vmstart = max(start, vma->vm_start);
+		vmend   = min(end, vma->vm_end);
+		new = mpol_dup(vma_policy(vma));
+		if (IS_ERR(new)) {
+			err = PTR_ERR(new);
+			break;
+		}
+		/*
+		 * Only update home node if there is an existing vma policy
+		 */
+		if (!new)
+			continue;
+
+		/*
+		 * If any vma in the range got policy other than MPOL_BIND
+		 * or MPOL_PREFERRED_MANY we return error. We don't reset
+		 * the home node for vmas we already updated before.
+		 */
+		if (new->mode != MPOL_BIND && new->mode != MPOL_PREFERRED_MANY) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+
+		new->home_node = home_node;
+		err = mbind_range(mm, vmstart, vmend, new);
+		mpol_put(new);
+		if (err)
+			break;
+	}
+	mmap_write_unlock(mm);
+	return err;
+}
+
 SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
 		unsigned long, mode, const unsigned long __user *, nmask,
 		unsigned long, maxnode, unsigned int, flags)
@@ -1802,6 +1874,11 @@ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd)
 		WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE));
 	}
 
+	if ((policy->mode == MPOL_BIND ||
+	     policy->mode == MPOL_PREFERRED_MANY) &&
+	    policy->home_node != NUMA_NO_NODE)
+		return policy->home_node;
+
 	return nd;
 }
 
@@ -2344,6 +2421,8 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 		return false;
 	if (a->flags != b->flags)
 		return false;
+	if (a->home_node != b->home_node)
+		return false;
 	if (mpol_store_user_nodemask(a))
 		if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask))
 			return false;