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>

3 files changed, 11 insertions, 113 deletions

diff --git a/drivers/fpga/dfl-afu-dma-region.c b/drivers/fpga/dfl-afu-dma-region.c
index dcd80b088c7b..62f924489db5 100644
--- a/drivers/fpga/dfl-afu-dma-region.c
+++ b/drivers/fpga/dfl-afu-dma-region.c
@@ -12,6 +12,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/sched/signal.h>
 #include <linux/uaccess.h>
+#include <linux/mm.h>
 
 #include "dfl-afu.h"
 
@@ -32,52 +33,6 @@ void afu_dma_region_init(struct dfl_feature_platform_data *pdata)
 }
 
 /**
- * afu_dma_adjust_locked_vm - adjust locked memory
- * @dev: port device
- * @npages: number of pages
- * @incr: increase or decrease locked memory
- *
- * Increase or decrease the locked memory size with npages input.
- *
- * Return 0 on success.
- * Return -ENOMEM if locked memory size is over the limit and no CAP_IPC_LOCK.
- */
-static int afu_dma_adjust_locked_vm(struct device *dev, long npages, bool incr)
-{
-	unsigned long locked, lock_limit;
-	int ret = 0;
-
-	/* the task is exiting. */
-	if (!current->mm)
-		return 0;
-
-	down_write(&current->mm->mmap_sem);
-
-	if (incr) {
-		locked = current->mm->locked_vm + npages;
-		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			ret = -ENOMEM;
-		else
-			current->mm->locked_vm += npages;
-	} else {
-		if (WARN_ON_ONCE(npages > current->mm->locked_vm))
-			npages = current->mm->locked_vm;
-		current->mm->locked_vm -= npages;
-	}
-
-	dev_dbg(dev, "[%d] RLIMIT_MEMLOCK %c%ld %ld/%ld%s\n", current->pid,
-		incr ? '+' : '-', npages << PAGE_SHIFT,
-		current->mm->locked_vm << PAGE_SHIFT, rlimit(RLIMIT_MEMLOCK),
-		ret ? "- exceeded" : "");
-
-	up_write(&current->mm->mmap_sem);
-
-	return ret;
-}
-
-/**
  * afu_dma_pin_pages - pin pages of given dma memory region
  * @pdata: feature device platform data
  * @region: dma memory region to be pinned
@@ -92,7 +47,7 @@ static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
 	struct device *dev = &pdata->dev->dev;
 	int ret, pinned;
 
-	ret = afu_dma_adjust_locked_vm(dev, npages, true);
+	ret = account_locked_vm(current->mm, npages, true);
 	if (ret)
 		return ret;
 
@@ -121,7 +76,7 @@ put_pages:
 free_pages:
 	kfree(region->pages);
 unlock_vm:
-	afu_dma_adjust_locked_vm(dev, npages, false);
+	account_locked_vm(current->mm, npages, false);
 	return ret;
 }
 
@@ -141,7 +96,7 @@ static void afu_dma_unpin_pages(struct dfl_feature_platform_data *pdata,
 
 	put_all_pages(region->pages, npages);
 	kfree(region->pages);
-	afu_dma_adjust_locked_vm(dev, npages, false);
+	account_locked_vm(current->mm, npages, false);
 
 	dev_dbg(dev, "%ld pages unpinned\n", npages);
 }
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);
 	}