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.comSigned-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>

arch/powerpc/kvm/book3s_64_vio.c

@@ -19,6 +19,7 @@
 #include <linux/anon_inodes.h>
 #include <linux/iommu.h>
 #include <linux/file.h>
+#include <linux/mm.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -45,43 +46,6 @@ static unsigned long kvmppc_stt_pages(unsigned long tce_pages)
 	return tce_pages + ALIGN(stt_bytes, PAGE_SIZE) / PAGE_SIZE;
 }
 
-static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
-{
-	long ret = 0;
-
-	if (!current || !current->mm)
-		return ret; /* process exited */
-
-	down_write(&current->mm->mmap_sem);
-
-	if (inc) {
-		unsigned long locked, lock_limit;
-
-		locked = current->mm->locked_vm + stt_pages;
-		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			ret = -ENOMEM;
-		else
-			current->mm->locked_vm += stt_pages;
-	} else {
-		if (WARN_ON_ONCE(stt_pages > current->mm->locked_vm))
-			stt_pages = current->mm->locked_vm;
-
-		current->mm->locked_vm -= stt_pages;
-	}
-
-	pr_debug("[%d] RLIMIT_MEMLOCK KVM %c%ld %ld/%ld%s\n", current->pid,
-			inc ? '+' : '-',
-			stt_pages << PAGE_SHIFT,
-			current->mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK),
-			ret ? " - exceeded" : "");
-
-	up_write(&current->mm->mmap_sem);
-
-	return ret;
-}
-
 static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
 {
 	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
@@ -291,7 +255,7 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 
 	kvm_put_kvm(stt->kvm);
 
-	kvmppc_account_memlimit(
+	account_locked_vm(current->mm,
 		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
 	call_rcu(&stt->rcu, release_spapr_tce_table);
 
@@ -316,7 +280,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		return -EINVAL;
 
 	npages = kvmppc_tce_pages(size);
-	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
+	ret = account_locked_vm(current->mm, kvmppc_stt_pages(npages), true);
 	if (ret)
 		return ret;
 
@@ -362,7 +326,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 
 	kfree(stt);
  fail_acct:
-	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
+	account_locked_vm(current->mm, kvmppc_stt_pages(npages), false);
 	return ret;
 }
 

arch/powerpc/mm/book3s64/iommu_api.c

@@ -14,6 +14,7 @@
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <linux/sizes.h>
+#include <linux/mm.h>
 #include <asm/mmu_context.h>
 #include <asm/pte-walk.h>
 #include <linux/mm_inline.h>
@@ -46,40 +47,6 @@ struct mm_iommu_table_group_mem_t {
 	u64 dev_hpa;		/* Device memory base address */
 };
 
-static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
-		unsigned long npages, bool incr)
-{
-	long ret = 0, locked, lock_limit;
-
-	if (!npages)
-		return 0;
-
-	down_write(&mm->mmap_sem);
-
-	if (incr) {
-		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;
-	} else {
-		if (WARN_ON_ONCE(npages > mm->locked_vm))
-			npages = mm->locked_vm;
-		mm->locked_vm -= npages;
-	}
-
-	pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
-			current ? current->pid : 0,
-			incr ? '+' : '-',
-			npages << PAGE_SHIFT,
-			mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK));
-	up_write(&mm->mmap_sem);
-
-	return ret;
-}
-
 bool mm_iommu_preregistered(struct mm_struct *mm)
 {
 	return !list_empty(&mm->context.iommu_group_mem_list);
@@ -96,7 +63,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	unsigned long entry, chunk;
 
 	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
-		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
+		ret = account_locked_vm(mm, entries, true);
 		if (ret)
 			return ret;
 
@@ -211,7 +178,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	kfree(mem);
 
 unlock_exit:
-	mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+	account_locked_vm(mm, locked_entries, false);
 
 	return ret;
 }
@@ -311,7 +278,7 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
 
-	mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+	account_locked_vm(mm, unlock_entries, false);
 
 	return ret;
 }

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"
 
@@ -31,52 +32,6 @@ void afu_dma_region_init(struct dfl_feature_platform_data *pdata)
 	afu->dma_regions = RB_ROOT;
 }
 
-/**
- * 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
@@ -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 @@ static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
 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);
 }

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,

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);
 	}
 

include/linux/mm.h

@@ -1543,6 +1543,10 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
 
+int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
+int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
+			struct task_struct *task, bool bypass_rlim);
+
 /* Container for pinned pfns / pages */
 struct frame_vector {
 	unsigned int nr_allocated;	/* Number of frames we have space for */

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)