Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "VM:
   - z3fold fixes and enhancements by Henry Burns and Vitaly Wool

   - more accurate reclaimed slab caches calculations by Yafang Shao

   - fix MAP_UNINITIALIZED UAPI symbol to not depend on config, by
     Christoph Hellwig

   - !CONFIG_MMU fixes by Christoph Hellwig

   - new novmcoredd parameter to omit device dumps from vmcore, by
     Kairui Song

   - new test_meminit module for testing heap and pagealloc
     initialization, by Alexander Potapenko

   - ioremap improvements for huge mappings, by Anshuman Khandual

   - generalize kprobe page fault handling, by Anshuman Khandual

   - device-dax hotplug fixes and improvements, by Pavel Tatashin

   - enable synchronous DAX fault on powerpc, by Aneesh Kumar K.V

   - add pte_devmap() support for arm64, by Robin Murphy

   - unify locked_vm accounting with a helper, by Daniel Jordan

   - several misc fixes

  core/lib:
   - new typeof_member() macro including some users, by Alexey Dobriyan

   - make BIT() and GENMASK() available in asm, by Masahiro Yamada

   - changed LIST_POISON2 on x86_64 to 0xdead000000000122 for better
     code generation, by Alexey Dobriyan

   - rbtree code size optimizations, by Michel Lespinasse

   - convert struct pid count to refcount_t, by Joel Fernandes

  get_maintainer.pl:
   - add --no-moderated switch to skip moderated ML's, by Joe Perches

  misc:
   - ptrace PTRACE_GET_SYSCALL_INFO interface

   - coda updates

   - gdb scripts, various"

[ Using merge message suggestion from Vlastimil Babka, with some editing - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (100 commits)
  fs/select.c: use struct_size() in kmalloc()
  mm: add account_locked_vm utility function
  arm64: mm: implement pte_devmap support
  mm: introduce ARCH_HAS_PTE_DEVMAP
  mm: clean up is_device_*_page() definitions
  mm/mmap: move common defines to mman-common.h
  mm: move MAP_SYNC to asm-generic/mman-common.h
  device-dax: "Hotremove" persistent memory that is used like normal RAM
  mm/hotplug: make remove_memory() interface usable
  device-dax: fix memory and resource leak if hotplug fails
  include/linux/lz4.h: fix spelling and copy-paste errors in documentation
  ipc/mqueue.c: only perform resource calculation if user valid
  include/asm-generic/bug.h: fix "cut here" for WARN_ON for __WARN_TAINT architectures
  scripts/gdb: add helpers to find and list devices
  scripts/gdb: add lx-genpd-summary command
  drivers/pps/pps.c: clear offset flags in PPS_SETPARAMS ioctl
  kernel/pid.c: convert struct pid count to refcount_t
  drivers/rapidio/devices/rio_mport_cdev.c: NUL terminate some strings
  select: shift restore_saved_sigmask_unless() into poll_select_copy_remaining()
  select: change do_poll() to return -ERESTARTNOHAND rather than -EINTR
  ...

2 files changed, 7 insertions, 64 deletions

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 7048c9198c21..8ce9ad21129f 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -19,6 +19,7 @@
 #include <linux/vmalloc.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
+#include <linux/mm.h>
 
 #include <asm/iommu.h>
 #include <asm/tce.h>
@@ -31,51 +32,6 @@
 static void tce_iommu_detach_group(void *iommu_data,
 		struct iommu_group *iommu_group);
 
-static long try_increment_locked_vm(struct mm_struct *mm, long npages)
-{
-	long ret = 0, locked, lock_limit;
-
-	if (WARN_ON_ONCE(!mm))
-		return -EPERM;
-
-	if (!npages)
-		return 0;
-
-	down_write(&mm->mmap_sem);
-	locked = mm->locked_vm + npages;
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-		ret = -ENOMEM;
-	else
-		mm->locked_vm += npages;
-
-	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
-			npages << PAGE_SHIFT,
-			mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK),
-			ret ? " - exceeded" : "");
-
-	up_write(&mm->mmap_sem);
-
-	return ret;
-}
-
-static void decrement_locked_vm(struct mm_struct *mm, long npages)
-{
-	if (!mm || !npages)
-		return;
-
-	down_write(&mm->mmap_sem);
-	if (WARN_ON_ONCE(npages > mm->locked_vm))
-		npages = mm->locked_vm;
-	mm->locked_vm -= npages;
-	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
-			npages << PAGE_SHIFT,
-			mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK));
-	up_write(&mm->mmap_sem);
-}
-
 /*
  * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
  *
@@ -333,7 +289,7 @@ static int tce_iommu_enable(struct tce_container *container)
 		return ret;
 
 	locked = table_group->tce32_size >> PAGE_SHIFT;
-	ret = try_increment_locked_vm(container->mm, locked);
+	ret = account_locked_vm(container->mm, locked, true);
 	if (ret)
 		return ret;
 
@@ -352,7 +308,7 @@ static void tce_iommu_disable(struct tce_container *container)
 	container->enabled = false;
 
 	BUG_ON(!container->mm);
-	decrement_locked_vm(container->mm, container->locked_pages);
+	account_locked_vm(container->mm, container->locked_pages, false);
 }
 
 static void *tce_iommu_open(unsigned long arg)
@@ -656,7 +612,7 @@ static long tce_iommu_create_table(struct tce_container *container,
 	if (!table_size)
 		return -EINVAL;
 
-	ret = try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT);
+	ret = account_locked_vm(container->mm, table_size >> PAGE_SHIFT, true);
 	if (ret)
 		return ret;
 
@@ -675,7 +631,7 @@ static void tce_iommu_free_table(struct tce_container *container,
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
 	iommu_tce_table_put(tbl);
-	decrement_locked_vm(container->mm, pages);
+	account_locked_vm(container->mm, pages, false);
 }
 
 static long tce_iommu_create_window(struct tce_container *container,
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index add34adfadc7..054391f30fa8 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -272,21 +272,8 @@ static int vfio_lock_acct(struct vfio_dma *dma, long npage, bool async)
 
 	ret = down_write_killable(&mm->mmap_sem);
 	if (!ret) {
-		if (npage > 0) {
-			if (!dma->lock_cap) {
-				unsigned long limit;
-
-				limit = task_rlimit(dma->task,
-						RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
-				if (mm->locked_vm + npage > limit)
-					ret = -ENOMEM;
-			}
-		}
-
-		if (!ret)
-			mm->locked_vm += npage;
-
+		ret = __account_locked_vm(mm, abs(npage), npage > 0, dma->task,
+					  dma->lock_cap);
 		up_write(&mm->mmap_sem);
 	}