[RFC PATCH v2 09/25] driver core: Add per-device pisa_* sysfs attributes for PISA optin

[Luigi Rizzo]

Because of the performance and security implications, the use of PISA
features is opt-in and configurable per device with a fine granularity.

Add boolean attributes to struct device exposed under
/sys/devices/*/*/pisa_*:
  - pisa_coherent:     enable PISA for coherent allocations
  - pisa_rx_bufs:      enable PISA for RX buffers / page_pool
  - pisa_tx_bufs:      enable PISA for TX socket page frags
  - pisa_tx_skb_heads: enable PISA slab cache for small TX skb heads

Signed-off-by: Luigi Rizzo <lrizzo@xxxxxxxxxx>
---
 drivers/base/core.c        | 64 ++++++++++++++++++++++++++++++++++++
 drivers/iommu/pisa-alloc.c | 24 ++++++++++++++
 drivers/iommu/pisa-kunit.c | 67 ++++++++++++++++++++++++++++++++++++++
 drivers/iommu/pisa-priv.h  |  1 -
 include/linux/device.h     | 12 +++++++
 include/linux/pisa.h       | 19 +++++++++++
 6 files changed, 186 insertions(+), 1 deletion(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index cbe05197d4a0b..97cd2d03ff77c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -25,6 +25,7 @@
 #include <linux/notifier.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pisa.h>
 #include <linux/pm_runtime.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
@@ -2907,6 +2908,54 @@ static ssize_t removable_show(struct device *dev, const struct device_attribute
 }
 static const DEVICE_ATTR_RO(removable);
 
+/* Per-device configuration to selectively enable PISA */
+static ssize_t pisa_attr_store(const char *buf, size_t count, bool *field)
+{
+	bool val;
+	int ret = kstrtobool(buf, &val);
+
+	if (ret < 0)
+		return ret;
+	if (val) {
+		ret = pisa_meta_init();
+		if (ret < 0)
+			return ret;
+	}
+	WRITE_ONCE(*field, val);
+	return count;
+}
+
+#define PISA_BOOL_ATTR(name)						\
+static ssize_t name##_show(struct device *dev,				\
+			   struct device_attribute *attr, char *buf)	\
+{									\
+	return sysfs_emit(buf, "%u\n", READ_ONCE(dev->name));		\
+}									\
+static ssize_t name##_store(struct device *dev,				\
+			    struct device_attribute *attr,		\
+			    const char *buf, size_t count)		\
+{									\
+	return pisa_attr_store(buf, count, &dev->name);			\
+}									\
+static DEVICE_ATTR_RW(name)
+
+PISA_BOOL_ATTR(pisa_coherent);
+PISA_BOOL_ATTR(pisa_rx_bufs);
+PISA_BOOL_ATTR(pisa_tx_bufs);
+PISA_BOOL_ATTR(pisa_tx_skb_heads);
+
+static struct attribute *dev_attr_pisa[] = {
+	&dev_attr_pisa_coherent.attr,
+	&dev_attr_pisa_rx_bufs.attr,
+	&dev_attr_pisa_tx_bufs.attr,
+	&dev_attr_pisa_tx_skb_heads.attr,
+	NULL,
+};
+
+static const struct attribute_group dev_attr_pisa_group = {
+	.attrs = dev_attr_pisa,
+};
+
 int device_add_groups(struct device *dev,
 		      const struct attribute_group *const *groups)
 {
@@ -3014,8 +3063,20 @@ static int device_add_attrs(struct device *dev)
 			goto err_remove_dev_removable;
 	}
 
+	if (IS_ENABLED(CONFIG_PISA) && dev->dma_mask) {
+		error = device_add_group(dev, &dev_attr_pisa_group);
+		if (error)
+			goto err_remove_dev_physical_location;
+	}
+
 	return 0;
 
+ err_remove_dev_physical_location:
+	if (dev->physical_location) {
+		device_remove_group(dev, &dev_attr_physical_location_group);
+		kfree(dev->physical_location);
+		dev->physical_location = NULL;
+	}
  err_remove_dev_removable:
 	device_remove_file(dev, &dev_attr_removable);
  err_remove_dev_waiting_for_supplier:
@@ -3039,6 +3100,9 @@ static void device_remove_attrs(struct device *dev)
 	const struct class *class = dev->class;
 	const struct device_type *type = dev->type;
 
+	if (IS_ENABLED(CONFIG_PISA) && dev->dma_mask)
+		device_remove_group(dev, &dev_attr_pisa_group);
+
 	if (dev->physical_location) {
 		device_remove_group(dev, &dev_attr_physical_location_group);
 		kfree(dev->physical_location);
diff --git a/drivers/iommu/pisa-alloc.c b/drivers/iommu/pisa-alloc.c
index f98142882519c..b0d968aa9181c 100644
--- a/drivers/iommu/pisa-alloc.c
+++ b/drivers/iommu/pisa-alloc.c
@@ -9,6 +9,7 @@
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/cache.h>
+#include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/pisa.h>
 #include <linux/export.h>
@@ -392,6 +393,29 @@ unsigned long pisa_alloc_pages_bulk(gfp_t gfp, unsigned int order, int preferred
 	return pisa_alloc_bulk(pa, gfp & ~__GFP_PISA_RW, nr_pages, page_array, frozen);
 }
 
+/**
+ * pisa_has_free_blocks_rx - Check if @dev has free PISA RX blocks of @order on @nid
+ * @dev: Device to check
+ * @order: Block order
+ * @nid: Target NUMA node (or NUMA_NO_NODE)
+ *
+ * Return: true if @dev->pisa_rx_bufs is enabled and the per-node allocator
+ * has a free block available.
+ */
+bool pisa_has_free_blocks_rx(const struct device *dev, unsigned int order, int nid)
+{
+	struct pisa_alloc *pa;
+
+	if (!dev || !READ_ONCE(dev->pisa_rx_bufs))
+		return false;
+	pa = pisa_node_pa(nid, order, false);
+	return pa &&
+	       (!list_empty_careful(&pa->partial) ||
+		!list_empty_careful(&pa->partial_dirty) ||
+		!list_empty_careful(&pa->idle));
+}
+EXPORT_SYMBOL(pisa_has_free_blocks_rx);
+
 /*
  * Split a non-compound page of @old_order into 1 << (@old_order - @new_order)
  * pages of @new_order (compound if @new_order > 0), all frozen at refcount 0.
diff --git a/drivers/iommu/pisa-kunit.c b/drivers/iommu/pisa-kunit.c
index e16268d55f3de..ab64657ad5c58 100644
--- a/drivers/iommu/pisa-kunit.c
+++ b/drivers/iommu/pisa-kunit.c
@@ -5,6 +5,8 @@
 #include <kunit/test.h>
 #include <linux/gfp.h>
 #include <linux/pisa.h>
+#include <linux/kernfs.h>
+#include <linux/sysfs.h>
 #include <linux/iommu.h>
 #include <linux/iova.h>
 #include <linux/mm.h>
@@ -350,6 +352,70 @@ static void test_map_and_domain_lifecycle(struct kunit *test)
 }
 #endif /* CONFIG_IOMMU_DMA */
 
+static void kunit_check_pisa_attr(struct kunit *test, struct device *dev,
+				  const char *name, bool *field)
+{
+	const struct sysfs_ops *ops = dev->kobj.ktype->sysfs_ops;
+	struct kernfs_node *kn;
+	char *buf;
+
+	buf = (char *)__get_free_page(GFP_KERNEL);
+	KUNIT_EXPECT_NOT_NULL(test, buf);
+	if (!buf)
+		return;
+	kn = kernfs_find_and_get(dev->kobj.sd, name);
+	KUNIT_EXPECT_NOT_NULL(test, kn);
+	if (!kn)
+		goto out_free;
+
+	KUNIT_EXPECT_EQ(test, ops->show(&dev->kobj, kn->priv, buf), 2);
+	KUNIT_EXPECT_STREQ(test, buf, "0\n");
+	KUNIT_EXPECT_FALSE(test, READ_ONCE(*field));
+
+	KUNIT_EXPECT_EQ(test, ops->store(&dev->kobj, kn->priv, "1\n", 2), 2);
+	KUNIT_EXPECT_TRUE(test, READ_ONCE(*field));
+	KUNIT_EXPECT_EQ(test, ops->show(&dev->kobj, kn->priv, buf), 2);
+	KUNIT_EXPECT_STREQ(test, buf, "1\n");
+
+	KUNIT_EXPECT_LT(test, ops->store(&dev->kobj, kn->priv, "bad", 3), 0);
+	KUNIT_EXPECT_TRUE(test, READ_ONCE(*field));
+
+	KUNIT_EXPECT_EQ(test, ops->store(&dev->kobj, kn->priv, "0\n", 2), 2);
+	KUNIT_EXPECT_FALSE(test, READ_ONCE(*field));
+
+	kernfs_put(kn);
+out_free:
+	free_page((unsigned long)buf);
+}
+
+static void kunit_attr_dev_release(struct device *dev)
+{
+	kfree(dev);
+}
+
+static void test_dev_pisa_attrs(struct kunit *test)
+{
+	struct device *dev;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, dev);
+	dev->init_name = "pisa_attr_kunit";
+	dev->release = kunit_attr_dev_release;
+	dev->coherent_dma_mask = DMA_BIT_MASK(64);
+	dev->dma_mask = &dev->coherent_dma_mask;
+
+	if (device_register(dev)) {
+		put_device(dev);
+		KUNIT_FAIL(test, "device_register failed");
+		return;
+	}
+	kunit_check_pisa_attr(test, dev, "pisa_coherent", &dev->pisa_coherent);
+	kunit_check_pisa_attr(test, dev, "pisa_rx_bufs", &dev->pisa_rx_bufs);
+	kunit_check_pisa_attr(test, dev, "pisa_tx_bufs", &dev->pisa_tx_bufs);
+	kunit_check_pisa_attr(test, dev, "pisa_tx_skb_heads", &dev->pisa_tx_skb_heads);
+	device_unregister(dev);
+}
+
 static void test_reservoir_and_scrubber(struct kunit *test)
 {
 	KUNIT_ASSERT_EQ(test, pisa_meta_init(), 0);
@@ -365,6 +431,7 @@ static struct kunit_case pisa_meta_test_cases[] = {
 	KUNIT_CASE(test_window_helpers),
 	KUNIT_CASE(test_map_and_domain_lifecycle),
 #endif
+	KUNIT_CASE(test_dev_pisa_attrs),
 	KUNIT_CASE(test_reservoir_and_scrubber),
 	{}
 };
diff --git a/drivers/iommu/pisa-priv.h b/drivers/iommu/pisa-priv.h
index 8d83ec09c19a9..e5ca95d2654cd 100644
--- a/drivers/iommu/pisa-priv.h
+++ b/drivers/iommu/pisa-priv.h
@@ -133,7 +133,6 @@ struct pisa_alloc {
 	unsigned int		num_idle_pages;
 	unsigned int		max_idle_pages;
 	unsigned long		idle_jiffies;
-
 	/* Cold. */
 	int			nid;
 	struct list_head	node;
diff --git a/include/linux/device.h b/include/linux/device.h
index 429e39f647cf9..b3c11e32116ca 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -695,6 +695,13 @@ enum struct_device_flags {
  * @removable:  Whether the device can be removed from the system. This
  *              should be set by the subsystem / bus driver that discovered
  *              the device.
+ * @pisa_coherent: Back coherent dma_alloc_attrs() with PISA
+ *		(sysfs pisa_coherent).
+ * @pisa_rx_bufs: Use PISA allocators for RX buffers (sysfs pisa_rx_bufs).
+ * @pisa_tx_bufs: Use PISA allocators for socket TX page fragments
+ *		(sysfs pisa_tx_bufs).
+ * @pisa_tx_skb_heads: Use PISA slab cache for small TX skb heads
+ *		(sysfs pisa_tx_skb_heads).
  * @flags:	DEV_FLAG_XXX flags. Use atomic bitfield operations to modify.
  *
  * At the lowest level, every device in a Linux system is represented by an
@@ -799,6 +806,11 @@ struct device {
 
 	enum device_removable	removable;
 
+	bool			pisa_coherent;
+	bool			pisa_rx_bufs;
+	bool			pisa_tx_bufs;
+	bool			pisa_tx_skb_heads;
+
 	DECLARE_BITMAP(flags, DEV_FLAG_COUNT);
 };
 
diff --git a/include/linux/pisa.h b/include/linux/pisa.h
index c64689b81befe..92482fce943e9 100644
--- a/include/linux/pisa.h
+++ b/include/linux/pisa.h
@@ -7,6 +7,7 @@
 #include <linux/bitops.h>
 #include <linux/dma-mapping.h>
 #include <linux/jump_label.h>
+#include <linux/device.h>
 #include <linux/mm.h>
 #include <linux/numa.h>
 #include <linux/rcupdate.h>
@@ -82,6 +83,13 @@ unsigned long pisa_alloc_pages_bulk(gfp_t gfp, unsigned int order,
 				    int nr_pages, struct page **page_array,
 				    bool frozen);
 
+bool pisa_has_free_blocks_rx(const struct device *dev, unsigned int order, int nid);
+
+static inline gfp_t pisa_rx_gfp(const struct device *dev)
+{
+	return dev && READ_ONCE(dev->pisa_rx_bufs) ? __GFP_PISA_RW : 0;
+}
+
 #else /* !CONFIG_PISA */
 
 static inline int pisa_meta_init(void)
@@ -109,6 +117,17 @@ pisa_alloc_pages_bulk(gfp_t gfp, unsigned int order, int preferred_nid,
 	return 0;
 }
 
+static inline gfp_t pisa_rx_gfp(const struct device *dev)
+{
+	return 0;
+}
+
+static inline bool pisa_has_free_blocks_rx(const struct device *dev,
+					   unsigned int order, int nid)
+{
+	return false;
+}
+
 #endif /* CONFIG_PISA */
 
 static inline struct page *
-- 
2.56.0.542.g3ef89b7020-goog