mm: add account_locked_vm utility function
locked_vm accounting is done roughly the same way in five places, so
unify them in a helper.
Include the helper's caller in the debug print to distinguish between
callsites.
Error codes stay the same, so user-visible behavior does too. The one
exception is that the -EPERM case in tce_account_locked_vm is removed
because Alexey has never seen it triggered.
[daniel.m.jordan@oracle.com: v3]
Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com
[sfr@canb.auug.org.au: fix mm/util.c]
Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com
Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Cc: Alan Tull <atull@kernel.org>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Moritz Fischer <mdf@kernel.org>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Steve Sistare <steven.sistare@oracle.com>
Cc: Wu Hao <hao.wu@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/util.c b/mm/util.c
index 68575a3..e6351a8 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -7,6 +7,7 @@
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/security.h>
#include <linux/swap.h>
@@ -300,6 +301,80 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
}
#endif
+/**
+ * __account_locked_vm - account locked pages to an mm's locked_vm
+ * @mm: mm to account against
+ * @pages: number of pages to account
+ * @inc: %true if @pages should be considered positive, %false if not
+ * @task: task used to check RLIMIT_MEMLOCK
+ * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
+ *
+ * Assumes @task and @mm are valid (i.e. at least one reference on each), and
+ * that mmap_sem is held as writer.
+ *
+ * Return:
+ * * 0 on success
+ * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
+ */
+int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
+ struct task_struct *task, bool bypass_rlim)
+{
+ unsigned long locked_vm, limit;
+ int ret = 0;
+
+ lockdep_assert_held_write(&mm->mmap_sem);
+
+ locked_vm = mm->locked_vm;
+ if (inc) {
+ if (!bypass_rlim) {
+ limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ if (locked_vm + pages > limit)
+ ret = -ENOMEM;
+ }
+ if (!ret)
+ mm->locked_vm = locked_vm + pages;
+ } else {
+ WARN_ON_ONCE(pages > locked_vm);
+ mm->locked_vm = locked_vm - pages;
+ }
+
+ pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid,
+ (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT,
+ locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK),
+ ret ? " - exceeded" : "");
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__account_locked_vm);
+
+/**
+ * account_locked_vm - account locked pages to an mm's locked_vm
+ * @mm: mm to account against, may be NULL
+ * @pages: number of pages to account
+ * @inc: %true if @pages should be considered positive, %false if not
+ *
+ * Assumes a non-NULL @mm is valid (i.e. at least one reference on it).
+ *
+ * Return:
+ * * 0 on success, or if mm is NULL
+ * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
+ */
+int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc)
+{
+ int ret;
+
+ if (pages == 0 || !mm)
+ return 0;
+
+ down_write(&mm->mmap_sem);
+ ret = __account_locked_vm(mm, pages, inc, current,
+ capable(CAP_IPC_LOCK));
+ up_write(&mm->mmap_sem);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(account_locked_vm);
+
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long pgoff)