mm/hmm/mirror: mirror process address space on device with HMM helpers

This is a heterogeneous memory management (HMM) process address space
mirroring.  In a nutshell this provide an API to mirror process address
space on a device.  This boils down to keeping CPU and device page table
synchronize (we assume that both device and CPU are cache coherent like
PCIe device can be).

This patch provide a simple API for device driver to achieve address space
mirroring thus avoiding each device driver to grow its own CPU page table
walker and its own CPU page table synchronization mechanism.

This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more
hardware in the future.

[jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"]
  Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com
Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com>
Signed-off-by: Sherry Cheung <SCheung@nvidia.com>
Signed-off-by: Subhash Gutti <sgutti@nvidia.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 150 insertions, 15 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 037fa26..254db99 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -705,6 +705,18 @@ config ARCH_HAS_HMM
 config HMM
 	bool
 
+config HMM_MIRROR
+	bool "HMM mirror CPU page table into a device page table"
+	depends on ARCH_HAS_HMM
+	select MMU_NOTIFIER
+	select HMM
+	help
+	  Select HMM_MIRROR if you want to mirror range of the CPU page table of a
+	  process into a device page table. Here, mirror means "keep synchronized".
+	  Prerequisites: the device must provide the ability to write-protect its
+	  page tables (at PAGE_SIZE granularity), and must be able to recover from
+	  the resulting potential page faults.
+
 config FRAME_VECTOR
 	bool
 
diff --git a/mm/hmm.c b/mm/hmm.c
index de032ff..d37daf9 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -21,16 +21,27 @@
 #include <linux/hmm.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/mmu_notifier.h>
 
 
 #ifdef CONFIG_HMM
+static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
+
 /*
  * struct hmm - HMM per mm struct
  *
  * @mm: mm struct this HMM struct is bound to
+ * @sequence: we track updates to the CPU page table with a sequence number
+ * @mirrors: list of mirrors for this mm
+ * @mmu_notifier: mmu notifier to track updates to CPU page table
+ * @mirrors_sem: read/write semaphore protecting the mirrors list
  */
 struct hmm {
 	struct mm_struct	*mm;
+	atomic_t		sequence;
+	struct list_head	mirrors;
+	struct mmu_notifier	mmu_notifier;
+	struct rw_semaphore	mirrors_sem;
 };
 
 /*
@@ -43,27 +54,48 @@ struct hmm {
  */
 static struct hmm *hmm_register(struct mm_struct *mm)
 {
-	if (!mm->hmm) {
-		struct hmm *hmm = NULL;
-
-		hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
-		if (!hmm)
-			return NULL;
-		hmm->mm = mm;
-
-		spin_lock(&mm->page_table_lock);
-		if (!mm->hmm)
-			mm->hmm = hmm;
-		else
-			kfree(hmm);
-		spin_unlock(&mm->page_table_lock);
-	}
+	struct hmm *hmm = READ_ONCE(mm->hmm);
+	bool cleanup = false;
 
 	/*
 	 * The hmm struct can only be freed once the mm_struct goes away,
 	 * hence we should always have pre-allocated an new hmm struct
 	 * above.
 	 */
+	if (hmm)
+		return hmm;
+
+	hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
+	if (!hmm)
+		return NULL;
+	INIT_LIST_HEAD(&hmm->mirrors);
+	init_rwsem(&hmm->mirrors_sem);
+	atomic_set(&hmm->sequence, 0);
+	hmm->mmu_notifier.ops = NULL;
+	hmm->mm = mm;
+
+	/*
+	 * We should only get here if hold the mmap_sem in write mode ie on
+	 * registration of first mirror through hmm_mirror_register()
+	 */
+	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
+	if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) {
+		kfree(hmm);
+		return NULL;
+	}
+
+	spin_lock(&mm->page_table_lock);
+	if (!mm->hmm)
+		mm->hmm = hmm;
+	else
+		cleanup = true;
+	spin_unlock(&mm->page_table_lock);
+
+	if (cleanup) {
+		mmu_notifier_unregister(&hmm->mmu_notifier, mm);
+		kfree(hmm);
+	}
+
 	return mm->hmm;
 }
 
@@ -72,3 +104,94 @@ void hmm_mm_destroy(struct mm_struct *mm)
 	kfree(mm->hmm);
 }
 #endif /* CONFIG_HMM */
+
+#if IS_ENABLED(CONFIG_HMM_MIRROR)
+static void hmm_invalidate_range(struct hmm *hmm,
+				 enum hmm_update_type action,
+				 unsigned long start,
+				 unsigned long end)
+{
+	struct hmm_mirror *mirror;
+
+	down_read(&hmm->mirrors_sem);
+	list_for_each_entry(mirror, &hmm->mirrors, list)
+		mirror->ops->sync_cpu_device_pagetables(mirror, action,
+							start, end);
+	up_read(&hmm->mirrors_sem);
+}
+
+static void hmm_invalidate_range_start(struct mmu_notifier *mn,
+				       struct mm_struct *mm,
+				       unsigned long start,
+				       unsigned long end)
+{
+	struct hmm *hmm = mm->hmm;
+
+	VM_BUG_ON(!hmm);
+
+	atomic_inc(&hmm->sequence);
+}
+
+static void hmm_invalidate_range_end(struct mmu_notifier *mn,
+				     struct mm_struct *mm,
+				     unsigned long start,
+				     unsigned long end)
+{
+	struct hmm *hmm = mm->hmm;
+
+	VM_BUG_ON(!hmm);
+
+	hmm_invalidate_range(mm->hmm, HMM_UPDATE_INVALIDATE, start, end);
+}
+
+static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
+	.invalidate_range_start	= hmm_invalidate_range_start,
+	.invalidate_range_end	= hmm_invalidate_range_end,
+};
+
+/*
+ * hmm_mirror_register() - register a mirror against an mm
+ *
+ * @mirror: new mirror struct to register
+ * @mm: mm to register against
+ *
+ * To start mirroring a process address space, the device driver must register
+ * an HMM mirror struct.
+ *
+ * THE mm->mmap_sem MUST BE HELD IN WRITE MODE !
+ */
+int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
+{
+	/* Sanity check */
+	if (!mm || !mirror || !mirror->ops)
+		return -EINVAL;
+
+	mirror->hmm = hmm_register(mm);
+	if (!mirror->hmm)
+		return -ENOMEM;
+
+	down_write(&mirror->hmm->mirrors_sem);
+	list_add(&mirror->list, &mirror->hmm->mirrors);
+	up_write(&mirror->hmm->mirrors_sem);
+
+	return 0;
+}
+EXPORT_SYMBOL(hmm_mirror_register);
+
+/*
+ * hmm_mirror_unregister() - unregister a mirror
+ *
+ * @mirror: new mirror struct to register
+ *
+ * Stop mirroring a process address space, and cleanup.
+ */
+void hmm_mirror_unregister(struct hmm_mirror *mirror)
+{
+	struct hmm *hmm = mirror->hmm;
+
+	down_write(&hmm->mirrors_sem);
+	list_del(&mirror->list);
+	up_write(&hmm->mirrors_sem);
+}
+EXPORT_SYMBOL(hmm_mirror_unregister);
+#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */