mm: add a field to store names for private anonymous memory

Userspace processes often have multiple allocators that each do
anonymous mmaps to get memory.  When examining memory usage of
individual processes or systems as a whole, it is useful to be
able to break down the various heaps that were allocated by
each layer and examine their size, RSS, and physical memory
usage.

This patch adds a user pointer to the shared union in
vm_area_struct that points to a null terminated string inside
the user process containing a name for the vma.  vmas that
point to the same address will be merged, but vmas that
point to equivalent strings at different addresses will
not be merged.

Userspace can set the name for a region of memory by calling
prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name);
Setting the name to NULL clears it.

The names of named anonymous vmas are shown in /proc/pid/maps
as [anon:<name>] and in /proc/pid/smaps in a new "Name" field
that is only present for named vmas.  If the userspace pointer
is no longer valid all or part of the name will be replaced
with "<fault>".

The idea to store a userspace pointer to reduce the complexity
within mm (at the expense of the complexity of reading
/proc/pid/mem) came from Dave Hansen.  This results in no
runtime overhead in the mm subsystem other than comparing
the anon_name pointers when considering vma merging.  The pointer
is stored in a union with fieds that are only used on file-backed
mappings, so it does not increase memory usage.

Change-Id: I53b093d98dc24f41377824f34e076edced4a6f07

1 files changed, 146 insertions, 0 deletions

diff --git a/kernel/sys.c b/kernel/sys.c
index be53817..79b66c0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -40,6 +40,9 @@
 #include <linux/syscore_ops.h>
 #include <linux/version.h>
 #include <linux/ctype.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/mempolicy.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -1660,6 +1663,146 @@ SYSCALL_DEFINE1(umask, int, mask)
 	return mask;
 }
 
+
+static int prctl_update_vma_anon_name(struct vm_area_struct *vma,
+		struct vm_area_struct **prev,
+		unsigned long start, unsigned long end,
+		const char __user *name_addr)
+{
+	struct mm_struct * mm = vma->vm_mm;
+	int error = 0;
+	pgoff_t pgoff;
+
+	if (name_addr == vma_get_anon_name(vma)) {
+		*prev = vma;
+		goto out;
+	}
+
+	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+	*prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma,
+				vma->vm_file, pgoff, vma_policy(vma),
+				name_addr);
+	if (*prev) {
+		vma = *prev;
+		goto success;
+	}
+
+	*prev = vma;
+
+	if (start != vma->vm_start) {
+		error = split_vma(mm, vma, start, 1);
+		if (error)
+			goto out;
+	}
+
+	if (end != vma->vm_end) {
+		error = split_vma(mm, vma, end, 0);
+		if (error)
+			goto out;
+	}
+
+success:
+	if (!vma->vm_file)
+		vma->shared.anon_name = name_addr;
+
+out:
+	if (error == -ENOMEM)
+		error = -EAGAIN;
+	return error;
+}
+
+static int prctl_set_vma_anon_name(unsigned long start, unsigned long end,
+			unsigned long arg)
+{
+	unsigned long tmp;
+	struct vm_area_struct * vma, *prev;
+	int unmapped_error = 0;
+	int error = -EINVAL;
+
+	/*
+	 * If the interval [start,end) covers some unmapped address
+	 * ranges, just ignore them, but return -ENOMEM at the end.
+	 * - this matches the handling in madvise.
+	 */
+	vma = find_vma_prev(current->mm, start, &prev);
+	if (vma && start > vma->vm_start)
+		prev = vma;
+
+	for (;;) {
+		/* Still start < end. */
+		error = -ENOMEM;
+		if (!vma)
+			return error;
+
+		/* Here start < (end|vma->vm_end). */
+		if (start < vma->vm_start) {
+			unmapped_error = -ENOMEM;
+			start = vma->vm_start;
+			if (start >= end)
+				return error;
+		}
+
+		/* Here vma->vm_start <= start < (end|vma->vm_end) */
+		tmp = vma->vm_end;
+		if (end < tmp)
+			tmp = end;
+
+		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
+		error = prctl_update_vma_anon_name(vma, &prev, start, end,
+				(const char __user *)arg);
+		if (error)
+			return error;
+		start = tmp;
+		if (prev && start < prev->vm_end)
+			start = prev->vm_end;
+		error = unmapped_error;
+		if (start >= end)
+			return error;
+		if (prev)
+			vma = prev->vm_next;
+		else	/* madvise_remove dropped mmap_sem */
+			vma = find_vma(current->mm, start);
+	}
+}
+
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+		unsigned long len_in, unsigned long arg)
+{
+	struct mm_struct *mm = current->mm;
+	int error;
+	unsigned long len;
+	unsigned long end;
+
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+	len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+
+	/* Check to see whether len was rounded up from small -ve to zero */
+	if (len_in && !len)
+		return -EINVAL;
+
+	end = start + len;
+	if (end < start)
+		return -EINVAL;
+
+	if (end == start)
+		return 0;
+
+	down_write(&mm->mmap_sem);
+
+	switch (opt) {
+	case PR_SET_VMA_ANON_NAME:
+		error = prctl_set_vma_anon_name(start, end, arg);
+		break;
+	default:
+		error = -EINVAL;
+	}
+
+	up_write(&mm->mmap_sem);
+
+	return error;
+}
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -1808,6 +1951,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			else
 				error = PR_MCE_KILL_DEFAULT;
 			break;
+		case PR_SET_VMA:
+			error = prctl_set_vma(arg2, arg3, arg4, arg5);
+			break;
 		default:
 			error = -EINVAL;
 			break;