File 1005-drm-i915-Use-pagecache-write-to-prepopulate-shmemfs-.patch of Package drm.openSUSE_Leap_42.3_Update

From 4e6fdafa7ac395ad47a80a0e7b4fd1e11550f862 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 7 Mar 2017 12:03:38 +0000
Subject: [PATCH] drm/i915: Use pagecache write to prepopulate shmemfs from pwrite-ioctl
Git-commit: 4e6fdafa7ac395ad47a80a0e7b4fd1e11550f862
Patch-mainline: 4.11-rc3
References: bsc#1040463

Before we instantiate/pin the backing store for our use, we
can prepopulate the shmemfs filp efficiently using a write into the
pagecache. We avoid the penalty of instantiating all the pages, important
if the user is just writing to a few and never uses the object on the GPU,
and using a direct write into shmemfs allows it to avoid the cost of
retrieving a page (mostly the clear-before-use, but in theory we could
curtail swapin) before it is overwritten.

This can be extended later to provide additional specialisation for
other backends (other than shmemfs). For now it provides a defense
against very large write-only allocations from exhausting all of system
memory.

V2: Smelling fixes.

Fixes: fe115628d567 ("drm/i915: Implement pwrite without struct-mutex")
References: https://bugs.freedesktop.org/show_bug.cgi?id=99107
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v4.10+
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170307120338.7277-2-chris@chris-wilson.co.uk
(cherry picked from commit 7c55e2c5772dcf3cbacd0fa2bcfeefae416b73f7)

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 drivers/gpu/drm/i915/i915_drv.h |    2 +
 drivers/gpu/drm/i915/i915_gem.c |   79 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)

--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1460,6 +1460,12 @@ i915_gem_pwrite_ioctl(struct drm_device
 	if (ret)
 		goto err_rpm;
 
+	ret = -ENODEV;
+	if (obj->ops->pwrite)
+		ret = obj->ops->pwrite(obj, args);
+	if (ret != -ENODEV)
+		goto err_unlock;
+
 	ret = -EFAULT;
 	/* We can only do the GTT pwrite on untiled buffers, as otherwise
 	 * it would end up going through the fenced access, and we'll get
@@ -1488,6 +1494,8 @@ i915_gem_pwrite_ioctl(struct drm_device
 
 	return ret;
 
+err_unlock:
+	mutex_unlock(&dev->struct_mutex);
 err_rpm:
 	intel_runtime_pm_put(dev_priv);
 err:
@@ -2369,6 +2377,75 @@ i915_gem_object_get_pages(struct drm_i91
 	return 0;
 }
 
+static int
+i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
+			   const struct drm_i915_gem_pwrite *arg)
+{
+	struct address_space *mapping = obj->base.filp->f_mapping;
+	char __user *user_data = (char __user *)(uintptr_t)arg->data_ptr;
+	u64 remain, offset;
+	unsigned int pg;
+
+	/* Before we instantiate/pin the backing store for our use, we
+	 * can prepopulate the shmemfs filp efficiently using a write into
+	 * the pagecache. We avoid the penalty of instantiating all the
+	 * pages, important if the user is just writing to a few and never
+	 * uses the object on the GPU, and using a direct write into shmemfs
+	 * allows it to avoid the cost of retrieving a page (either swapin
+	 * or clearing-before-use) before it is overwritten.
+	 */
+	if (READ_ONCE(obj->pages))
+		return -ENODEV;
+
+	/* Before the pages are instantiated the object is treated as being
+	 * in the CPU domain. The pages will be clflushed as required before
+	 * use, and we can freely write into the pages directly. If userspace
+	 * races pwrite with any other operation; corruption will ensue -
+	 * that is userspace's prerogative!
+	 */
+
+	remain = arg->size;
+	offset = arg->offset;
+	pg = offset_in_page(offset);
+
+	do {
+		unsigned int len, unwritten;
+		struct page *page;
+		void *data, *vaddr;
+		int err;
+
+		len = PAGE_SIZE - pg;
+		if (len > remain)
+			len = remain;
+
+		err = pagecache_write_begin(obj->base.filp, mapping,
+					    offset, len, 0,
+					    &page, &data);
+		if (err < 0)
+			return err;
+
+		vaddr = kmap(page);
+		unwritten = copy_from_user(vaddr + pg, user_data, len);
+		kunmap(page);
+
+		err = pagecache_write_end(obj->base.filp, mapping,
+					  offset, len, len - unwritten,
+					  page, data);
+		if (err < 0)
+			return err;
+
+		if (unwritten)
+			return -EFAULT;
+
+		remain -= len;
+		user_data += len;
+		offset += len;
+		pg = 0;
+	} while (remain);
+
+	return 0;
+}
+
 /* The 'mapping' part of i915_gem_object_pin_map() below */
 static void *i915_gem_object_map(const struct drm_i915_gem_object *obj,
 				 enum i915_map_type type)
@@ -4099,6 +4176,8 @@ static const struct drm_i915_gem_object_
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = i915_gem_object_get_pages_gtt,
 	.put_pages = i915_gem_object_put_pages_gtt,
+
+	.pwrite = i915_gem_object_pwrite_gtt,
 };
 
 struct drm_i915_gem_object *i915_gem_object_create(struct drm_device *dev,
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2161,6 +2161,8 @@ struct drm_i915_gem_object_ops {
 	int (*get_pages)(struct drm_i915_gem_object *);
 	void (*put_pages)(struct drm_i915_gem_object *);
 
+	int (*pwrite)(struct drm_i915_gem_object *,
+		      const struct drm_i915_gem_pwrite *);
 	int (*dmabuf_export)(struct drm_i915_gem_object *);
 	void (*release)(struct drm_i915_gem_object *);
 };