From a11024457d348672b26b3d4581ed19c793399b48 Mon Sep 17 00:00:00 2001
From: Felix Kuehling
Date: Tue, 6 Feb 2018 20:32:46 -0500
Subject: uapi: Fix type used in ioctl parameter structures

Use __u32 and __u64 instead of POSIX types that may not be defined
in user mode builds.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 include/uapi/linux/kfd_ioctl.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index f4cab5b3ba9a..111d73ba2d96 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -263,10 +263,10 @@ struct kfd_ioctl_get_tile_config_args {
 };
 
 struct kfd_ioctl_set_trap_handler_args {
-	uint64_t tba_addr;		/* to KFD */
-	uint64_t tma_addr;		/* to KFD */
-	uint32_t gpu_id;		/* to KFD */
-	uint32_t pad;
+	__u64 tba_addr;		/* to KFD */
+	__u64 tma_addr;		/* to KFD */
+	__u32 gpu_id;		/* to KFD */
+	__u32 pad;
 };
 
 #define AMDKFD_IOCTL_BASE 'K'
-- 
cgit v1.2.3


From e3890d05b34266f5981876c65a6a97fc0d0d0ccb Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi
Date: Wed, 7 Feb 2018 23:32:19 -0800
Subject: drm/i915/cnl: Sync PCI ID with Spec.

Add one missing PCI ID and sort them in a way
that gets easier to review and compare against spec's
table.

When trying to sync libdrm and mesa id list with kernel
and spec I noticed something was wrong and we were missing
a pci id. So to make our lives easier when checking against
spec let's simplify and sort like spec does.

BSpec: 13621

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: James Ausmus <james.ausmus@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180208073219.27860-1-rodrigo.vivi@intel.com
---
 include/drm/i915_pciids.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 9e1fe6634424..0b2ba46fa00b 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -416,18 +416,19 @@
 
 /* CNL */
 #define INTEL_CNL_IDS(info) \
-	INTEL_VGA_DEVICE(0x5A52, info), \
-	INTEL_VGA_DEVICE(0x5A5A, info), \
-	INTEL_VGA_DEVICE(0x5A42, info), \
-	INTEL_VGA_DEVICE(0x5A4A, info), \
 	INTEL_VGA_DEVICE(0x5A51, info), \
 	INTEL_VGA_DEVICE(0x5A59, info), \
 	INTEL_VGA_DEVICE(0x5A41, info), \
 	INTEL_VGA_DEVICE(0x5A49, info), \
-	INTEL_VGA_DEVICE(0x5A71, info), \
-	INTEL_VGA_DEVICE(0x5A79, info), \
+	INTEL_VGA_DEVICE(0x5A52, info), \
+	INTEL_VGA_DEVICE(0x5A5A, info), \
+	INTEL_VGA_DEVICE(0x5A42, info), \
+	INTEL_VGA_DEVICE(0x5A4A, info), \
+	INTEL_VGA_DEVICE(0x5A50, info), \
+	INTEL_VGA_DEVICE(0x5A40, info), \
 	INTEL_VGA_DEVICE(0x5A54, info), \
 	INTEL_VGA_DEVICE(0x5A5C, info), \
-	INTEL_VGA_DEVICE(0x5A44, info)
+	INTEL_VGA_DEVICE(0x5A44, info), \
+	INTEL_VGA_DEVICE(0x5A4C, info)
 
 #endif /* _I915_PCIIDS_H */
-- 
cgit v1.2.3


From 3b765c0b765d2cc03ef02276f1af2658a03b3ced Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan
Date: Fri, 2 Feb 2018 21:12:53 -0800
Subject: drm/vblank: Data type fixes for 64-bit vblank sequences.

drm_vblank_count() has an u32 type returning what is a 64-bit vblank count.
The effect of this is when drm_wait_vblank_ioctl() tries to widen the user
space requested vblank sequence using this clipped 32-bit count(when the
value is >= 2^32) as reference, the requested sequence remains a 32-bit
value and gets queued like that. However, the code that checks if the
requested sequence has passed compares this against the 64-bit vblank
count.

With drm_vblank_count() returning all bits of the vblank count, update
drm_crtc_accurate_vblank_count() so that drm_crtc_arm_vblank_event() queues
the correct sequence. Otherwise, this leads to prolonged waits for a vblank
sequence when the current count is >=2^32.

Finally, fix drm_wait_one_vblank() too.

v2: Commit message fix (Keith)
    Squash commits (Rodrigo)

Fixes: 570e86963a51 ("drm: Widen vblank count to 64-bits [v3]")
Cc: Keith Packard <keithp@keithp.com>
Cc: Michel Dänzer <michel@daenzer.net>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180203051302.9974-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/drm_vblank.c | 8 ++++----
 include/drm/drm_vblank.h     | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c
index 32d9bcf5be7f..f0d3ed5f2528 100644
--- a/drivers/gpu/drm/drm_vblank.c
+++ b/drivers/gpu/drm/drm_vblank.c
@@ -271,7 +271,7 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
 	store_vblank(dev, pipe, diff, t_vblank, cur_vblank);
 }
 
-static u32 drm_vblank_count(struct drm_device *dev, unsigned int pipe)
+static u64 drm_vblank_count(struct drm_device *dev, unsigned int pipe)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
 
@@ -292,11 +292,11 @@ static u32 drm_vblank_count(struct drm_device *dev, unsigned int pipe)
  * This is mostly useful for hardware that can obtain the scanout position, but
  * doesn't have a hardware frame counter.
  */
-u32 drm_crtc_accurate_vblank_count(struct drm_crtc *crtc)
+u64 drm_crtc_accurate_vblank_count(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	unsigned int pipe = drm_crtc_index(crtc);
-	u32 vblank;
+	u64 vblank;
 	unsigned long flags;
 
 	WARN_ONCE(drm_debug & DRM_UT_VBL && !dev->driver->get_vblank_timestamp,
@@ -1055,7 +1055,7 @@ void drm_wait_one_vblank(struct drm_device *dev, unsigned int pipe)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
 	int ret;
-	u32 last;
+	u64 last;
 
 	if (WARN_ON(pipe >= dev->num_crtcs))
 		return;
diff --git a/include/drm/drm_vblank.h b/include/drm/drm_vblank.h
index 848b463a0af5..a4c3b0a0a197 100644
--- a/include/drm/drm_vblank.h
+++ b/include/drm/drm_vblank.h
@@ -179,7 +179,7 @@ void drm_crtc_wait_one_vblank(struct drm_crtc *crtc);
 void drm_crtc_vblank_off(struct drm_crtc *crtc);
 void drm_crtc_vblank_reset(struct drm_crtc *crtc);
 void drm_crtc_vblank_on(struct drm_crtc *crtc);
-u32 drm_crtc_accurate_vblank_count(struct drm_crtc *crtc);
+u64 drm_crtc_accurate_vblank_count(struct drm_crtc *crtc);
 
 bool drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
 					   unsigned int pipe, int *max_error,
-- 
cgit v1.2.3


From f4c0468e4bd64b7cd00e2db309925728fc72bf8b Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan
Date: Fri, 2 Feb 2018 21:12:59 -0800
Subject: drm/atomic: Handle 64-bit return from drm_crtc_vblank_count()

570e86963a51 ("drm: Widen vblank count to 64-bits [v3]") changed the
return type for drm_crtc_vblank_count() to u64.

The flip ioctl receives a 32-bit target sequence from user space and is
compared against the current sequence from drm_crtc_vblank_count(). So,
typecast return from drm_crtc_vblank_count() explicitly to add clarity.

__drm_crtcs_state.last_vblank_count however only ever stores the value from
drm_crtc_vblank_count() and can be upgraded to u64.

Cc: Keith Packard <keithp@keithp.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180203051302.9974-7-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/drm_plane.c | 2 +-
 include/drm/drm_atomic.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 2c90519576a3..c3419ee09ff0 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -944,7 +944,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 		if (r)
 			return r;
 
-		current_vblank = drm_crtc_vblank_count(crtc);
+		current_vblank = (u32)drm_crtc_vblank_count(crtc);
 
 		switch (page_flip->flags & DRM_MODE_PAGE_FLIP_TARGET) {
 		case DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE:
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index 1c27526c499e..6649baa19b65 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -145,7 +145,7 @@ struct __drm_crtcs_state {
 	struct drm_crtc *ptr;
 	struct drm_crtc_state *state, *old_state, *new_state;
 	s32 __user *out_fence_ptr;
-	unsigned last_vblank_count;
+	u64 last_vblank_count;
 };
 
 struct __drm_connnectors_state {
-- 
cgit v1.2.3


From d0bb96b4be69feea97f16de5306c35e280658931 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan
Date: Fri, 2 Feb 2018 21:13:01 -0800
Subject: drm/vblank: Restoring vblank counts after device PM events.

The HW frame counter can get reset if device enters a low power state after
vblank interrupts were disabled. This messes up any following vblank count
update as a negative diff (huge unsigned diff) is calculated from the HW
frame counter change. We cannot ignore negative diffs altogther as there
could be legitimate wrap arounds. So, allow drivers to update vblank->count
with missed vblanks for the time interrupts were disabled. This is similar
to _crtc_vblank_on() except that vblanks interrupts are not enabled at the
end as this function is expected to be called from the driver
_enable_vblank() vfunc.

v2: drm_crtc_vblank_restore should take crtc as arg. (Chris)
    Add docs and sprinkle some asserts.

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Dänzer <michel@daenzer.net>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180203051302.9974-9-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/drm_vblank.c | 59 ++++++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_vblank.h     |  2 ++
 2 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c
index 913954765d9e..c781cb426bf1 100644
--- a/drivers/gpu/drm/drm_vblank.c
+++ b/drivers/gpu/drm/drm_vblank.c
@@ -1237,6 +1237,65 @@ void drm_crtc_vblank_on(struct drm_crtc *crtc)
 }
 EXPORT_SYMBOL(drm_crtc_vblank_on);
 
+/**
+ * drm_vblank_restore - estimated vblanks using timestamps and update it.
+ *
+ * Power manamement features can cause frame counter resets between vblank
+ * disable and enable. Drivers can then use this function in their
+ * &drm_crtc_funcs.enable_vblank implementation to estimate the vblanks since
+ * the last &drm_crtc_funcs.disable_vblank.
+ *
+ * This function is the legacy version of drm_crtc_vblank_restore().
+ */
+void drm_vblank_restore(struct drm_device *dev, unsigned int pipe)
+{
+	ktime_t t_vblank;
+	struct drm_vblank_crtc *vblank;
+	int framedur_ns;
+	u64 diff_ns;
+	u32 cur_vblank, diff = 1;
+	int count = DRM_TIMESTAMP_MAXRETRIES;
+
+	if (WARN_ON(pipe >= dev->num_crtcs))
+		return;
+
+	assert_spin_locked(&dev->vbl_lock);
+	assert_spin_locked(&dev->vblank_time_lock);
+
+	vblank = &dev->vblank[pipe];
+	WARN_ONCE((drm_debug & DRM_UT_VBL) && !vblank->framedur_ns,
+		  "Cannot compute missed vblanks without frame duration\n");
+	framedur_ns = vblank->framedur_ns;
+
+	do {
+		cur_vblank = __get_vblank_counter(dev, pipe);
+		drm_get_last_vbltimestamp(dev, pipe, &t_vblank, false);
+	} while (cur_vblank != __get_vblank_counter(dev, pipe) && --count > 0);
+
+	diff_ns = ktime_to_ns(ktime_sub(t_vblank, vblank->time));
+	if (framedur_ns)
+		diff = DIV_ROUND_CLOSEST_ULL(diff_ns, framedur_ns);
+
+
+	DRM_DEBUG_VBL("missed %d vblanks in %lld ns, frame duration=%d ns, hw_diff=%d\n",
+		      diff, diff_ns, framedur_ns, cur_vblank - vblank->last);
+	store_vblank(dev, pipe, diff, t_vblank, cur_vblank);
+}
+EXPORT_SYMBOL(drm_vblank_restore);
+
+/**
+ * drm_crtc_vblank_restore - estimate vblanks using timestamps and update it.
+ * Power manamement features can cause frame counter resets between vblank
+ * disable and enable. Drivers can then use this function in their
+ * &drm_crtc_funcs.enable_vblank implementation to estimate the vblanks since
+ * the last &drm_crtc_funcs.disable_vblank.
+ */
+void drm_crtc_vblank_restore(struct drm_crtc *crtc)
+{
+	drm_vblank_restore(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_vblank_restore);
+
 static void drm_legacy_vblank_pre_modeset(struct drm_device *dev,
 					  unsigned int pipe)
 {
diff --git a/include/drm/drm_vblank.h b/include/drm/drm_vblank.h
index a4c3b0a0a197..16d46e2a6854 100644
--- a/include/drm/drm_vblank.h
+++ b/include/drm/drm_vblank.h
@@ -180,6 +180,8 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc);
 void drm_crtc_vblank_reset(struct drm_crtc *crtc);
 void drm_crtc_vblank_on(struct drm_crtc *crtc);
 u64 drm_crtc_accurate_vblank_count(struct drm_crtc *crtc);
+void drm_vblank_restore(struct drm_device *dev, unsigned int pipe);
+void drm_crtc_vblank_restore(struct drm_crtc *crtc);
 
 bool drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
 					   unsigned int pipe, int *max_error,
-- 
cgit v1.2.3


From c0a51fd07b1dd50f31a413f0e7bb5e4499de2042 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Fri, 16 Feb 2018 13:43:38 +0100
Subject: drm: move read_domains and write_domain into i915

i915 is the only driver using those fields in the drm_gem_object
structure, so they only waste memory for all other drivers.

Move the fields into drm_i915_gem_object instead and patch the i915 code
with the following sed commands:

sed -i "s/obj->base.read_domains/obj->read_domains/g" drivers/gpu/drm/i915/*.c drivers/gpu/drm/i915/*/*.c
sed -i "s/obj->base.write_domain/obj->write_domain/g" drivers/gpu/drm/i915/*.c drivers/gpu/drm/i915/*/*.c

Change is only compile tested.

v2: move fields around as suggested by Chris.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180216124338.9087-1-christian.koenig@amd.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gvt/dmabuf.c                 |  4 +-
 drivers/gpu/drm/i915/i915_debugfs.c               |  4 +-
 drivers/gpu/drm/i915/i915_gem.c                   | 60 +++++++++++------------
 drivers/gpu/drm/i915/i915_gem_clflush.c           |  2 +-
 drivers/gpu/drm/i915/i915_gem_dmabuf.c            |  4 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c        | 10 ++--
 drivers/gpu/drm/i915/i915_gem_internal.c          |  4 +-
 drivers/gpu/drm/i915/i915_gem_object.h            | 15 ++++++
 drivers/gpu/drm/i915/i915_gem_stolen.c            |  2 +-
 drivers/gpu/drm/i915/i915_gem_userptr.c           |  4 +-
 drivers/gpu/drm/i915/i915_gpu_error.c             |  4 +-
 drivers/gpu/drm/i915/selftests/huge_gem_object.c  |  4 +-
 drivers/gpu/drm/i915/selftests/huge_pages.c       |  8 +--
 drivers/gpu/drm/i915/selftests/i915_gem_context.c |  4 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c     |  4 +-
 include/drm/drm_gem.h                             | 15 ------
 16 files changed, 74 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 2ab584f97dfb..de3e076dcb31 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -162,8 +162,8 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 		info->size << PAGE_SHIFT);
 	i915_gem_object_init(obj, &intel_vgpu_gem_ops);
 
-	obj->base.read_domains = I915_GEM_DOMAIN_GTT;
-	obj->base.write_domain = 0;
+	obj->read_domains = I915_GEM_DOMAIN_GTT;
+	obj->write_domain = 0;
 	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		unsigned int tiling_mode = 0;
 		unsigned int stride = 0;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3560eb567ca7..0cbe154e517d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -150,8 +150,8 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   get_global_flag(obj),
 		   get_pin_mapped_flag(obj),
 		   obj->base.size / 1024,
-		   obj->base.read_domains,
-		   obj->base.write_domain,
+		   obj->read_domains,
+		   obj->write_domain,
 		   i915_cache_level_str(dev_priv, obj->cache_level),
 		   obj->mm.dirty ? " dirty" : "",
 		   obj->mm.madv == I915_MADV_DONTNEED ? " purgeable" : "");
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fc68b35854df..f530cd247724 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -240,8 +240,8 @@ err_phys:
 
 static void __start_cpu_write(struct drm_i915_gem_object *obj)
 {
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	if (cpu_write_needs_clflush(obj))
 		obj->cache_dirty = true;
 }
@@ -257,7 +257,7 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
 		obj->mm.dirty = false;
 
 	if (needs_clflush &&
-	    (obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0 &&
+	    (obj->read_domains & I915_GEM_DOMAIN_CPU) == 0 &&
 	    !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
 		drm_clflush_sg(pages);
 
@@ -703,10 +703,10 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains)
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 
-	if (!(obj->base.write_domain & flush_domains))
+	if (!(obj->write_domain & flush_domains))
 		return;
 
-	switch (obj->base.write_domain) {
+	switch (obj->write_domain) {
 	case I915_GEM_DOMAIN_GTT:
 		i915_gem_flush_ggtt_writes(dev_priv);
 
@@ -731,7 +731,7 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains)
 		break;
 	}
 
-	obj->base.write_domain = 0;
+	obj->write_domain = 0;
 }
 
 static inline int
@@ -831,7 +831,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
 	 * anyway again before the next pread happens.
 	 */
 	if (!obj->cache_dirty &&
-	    !(obj->base.read_domains & I915_GEM_DOMAIN_CPU))
+	    !(obj->read_domains & I915_GEM_DOMAIN_CPU))
 		*needs_clflush = CLFLUSH_BEFORE;
 
 out:
@@ -890,7 +890,7 @@ int i915_gem_obj_prepare_shmem_write(struct drm_i915_gem_object *obj,
 		 * Same trick applies to invalidate partially written
 		 * cachelines read before writing.
 		 */
-		if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU))
+		if (!(obj->read_domains & I915_GEM_DOMAIN_CPU))
 			*needs_clflush |= CLFLUSH_BEFORE;
 	}
 
@@ -2391,8 +2391,8 @@ static int i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	 * wasn't in the GTT, there shouldn't be any way it could have been in
 	 * a GPU cache
 	 */
-	GEM_BUG_ON(obj->base.read_domains & I915_GEM_GPU_DOMAINS);
-	GEM_BUG_ON(obj->base.write_domain & I915_GEM_GPU_DOMAINS);
+	GEM_BUG_ON(obj->read_domains & I915_GEM_GPU_DOMAINS);
+	GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS);
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
 	if (st == NULL)
@@ -3703,7 +3703,7 @@ static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
 	flush_write_domain(obj, ~I915_GEM_DOMAIN_CPU);
 	if (obj->cache_dirty)
 		i915_gem_clflush_object(obj, I915_CLFLUSH_FORCE);
-	obj->base.write_domain = 0;
+	obj->write_domain = 0;
 }
 
 void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj)
@@ -3740,7 +3740,7 @@ i915_gem_object_set_to_wc_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
-	if (obj->base.write_domain == I915_GEM_DOMAIN_WC)
+	if (obj->write_domain == I915_GEM_DOMAIN_WC)
 		return 0;
 
 	/* Flush and acquire obj->pages so that we are coherent through
@@ -3761,17 +3761,17 @@ i915_gem_object_set_to_wc_domain(struct drm_i915_gem_object *obj, bool write)
 	 * coherent writes from the GPU, by effectively invalidating the
 	 * WC domain upon first access.
 	 */
-	if ((obj->base.read_domains & I915_GEM_DOMAIN_WC) == 0)
+	if ((obj->read_domains & I915_GEM_DOMAIN_WC) == 0)
 		mb();
 
 	/* It should now be out of any other write domains, and we can update
 	 * the domain values for our changes.
 	 */
-	GEM_BUG_ON((obj->base.write_domain & ~I915_GEM_DOMAIN_WC) != 0);
-	obj->base.read_domains |= I915_GEM_DOMAIN_WC;
+	GEM_BUG_ON((obj->write_domain & ~I915_GEM_DOMAIN_WC) != 0);
+	obj->read_domains |= I915_GEM_DOMAIN_WC;
 	if (write) {
-		obj->base.read_domains = I915_GEM_DOMAIN_WC;
-		obj->base.write_domain = I915_GEM_DOMAIN_WC;
+		obj->read_domains = I915_GEM_DOMAIN_WC;
+		obj->write_domain = I915_GEM_DOMAIN_WC;
 		obj->mm.dirty = true;
 	}
 
@@ -3803,7 +3803,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
-	if (obj->base.write_domain == I915_GEM_DOMAIN_GTT)
+	if (obj->write_domain == I915_GEM_DOMAIN_GTT)
 		return 0;
 
 	/* Flush and acquire obj->pages so that we are coherent through
@@ -3824,17 +3824,17 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	 * coherent writes from the GPU, by effectively invalidating the
 	 * GTT domain upon first access.
 	 */
-	if ((obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0)
+	if ((obj->read_domains & I915_GEM_DOMAIN_GTT) == 0)
 		mb();
 
 	/* It should now be out of any other write domains, and we can update
 	 * the domain values for our changes.
 	 */
-	GEM_BUG_ON((obj->base.write_domain & ~I915_GEM_DOMAIN_GTT) != 0);
-	obj->base.read_domains |= I915_GEM_DOMAIN_GTT;
+	GEM_BUG_ON((obj->write_domain & ~I915_GEM_DOMAIN_GTT) != 0);
+	obj->read_domains |= I915_GEM_DOMAIN_GTT;
 	if (write) {
-		obj->base.read_domains = I915_GEM_DOMAIN_GTT;
-		obj->base.write_domain = I915_GEM_DOMAIN_GTT;
+		obj->read_domains = I915_GEM_DOMAIN_GTT;
+		obj->write_domain = I915_GEM_DOMAIN_GTT;
 		obj->mm.dirty = true;
 	}
 
@@ -4146,7 +4146,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	/* It should now be out of any other write domains, and we can update
 	 * the domain values for our changes.
 	 */
-	obj->base.read_domains |= I915_GEM_DOMAIN_GTT;
+	obj->read_domains |= I915_GEM_DOMAIN_GTT;
 
 	return vma;
 
@@ -4199,15 +4199,15 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 	flush_write_domain(obj, ~I915_GEM_DOMAIN_CPU);
 
 	/* Flush the CPU cache if it's still invalid. */
-	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0) {
+	if ((obj->read_domains & I915_GEM_DOMAIN_CPU) == 0) {
 		i915_gem_clflush_object(obj, I915_CLFLUSH_SYNC);
-		obj->base.read_domains |= I915_GEM_DOMAIN_CPU;
+		obj->read_domains |= I915_GEM_DOMAIN_CPU;
 	}
 
 	/* It should now be out of any other write domains, and we can update
 	 * the domain values for our changes.
 	 */
-	GEM_BUG_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU);
+	GEM_BUG_ON(obj->write_domain & ~I915_GEM_DOMAIN_CPU);
 
 	/* If we're writing through the CPU, then the GPU read domains will
 	 * need to be invalidated at next use.
@@ -4643,8 +4643,8 @@ i915_gem_object_create(struct drm_i915_private *dev_priv, u64 size)
 
 	i915_gem_object_init(obj, &i915_gem_object_ops);
 
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
 
 	if (HAS_LLC(dev_priv))
 		/* On some devices, we can have the GPU use the LLC (the CPU
@@ -5702,7 +5702,7 @@ i915_gem_object_create_from_data(struct drm_i915_private *dev_priv,
 	if (IS_ERR(obj))
 		return obj;
 
-	GEM_BUG_ON(obj->base.write_domain != I915_GEM_DOMAIN_CPU);
+	GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU);
 
 	file = obj->base.filp;
 	offset = 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_clflush.c b/drivers/gpu/drm/i915/i915_gem_clflush.c
index b9b53ac14176..f5c570d35b2a 100644
--- a/drivers/gpu/drm/i915/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/i915_gem_clflush.c
@@ -177,7 +177,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	} else if (obj->mm.pages) {
 		__i915_do_clflush(obj);
 	} else {
-		GEM_BUG_ON(obj->base.write_domain != I915_GEM_DOMAIN_CPU);
+		GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU);
 	}
 
 	obj->cache_dirty = false;
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 864439a214c8..69a7aec49e84 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -330,8 +330,8 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 	 * write-combined buffer or a delay through the chipset for GTT
 	 * writes that do require us to treat GTT as a separate cache domain.)
 	 */
-	obj->base.read_domains = I915_GEM_DOMAIN_GTT;
-	obj->base.write_domain = 0;
+	obj->read_domains = I915_GEM_DOMAIN_GTT;
+	obj->write_domain = 0;
 
 	return &obj->base;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index ed6e9db51e67..51f3c32c64bf 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1073,7 +1073,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	u32 *cmd;
 	int err;
 
-	GEM_BUG_ON(vma->obj->base.write_domain & I915_GEM_DOMAIN_CPU);
+	GEM_BUG_ON(vma->obj->write_domain & I915_GEM_DOMAIN_CPU);
 
 	obj = i915_gem_batch_pool_get(&eb->engine->batch_pool, PAGE_SIZE);
 	if (IS_ERR(obj))
@@ -1861,16 +1861,16 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 	i915_gem_active_set(&vma->last_read[idx], req);
 	list_move_tail(&vma->vm_link, &vma->vm->active_list);
 
-	obj->base.write_domain = 0;
+	obj->write_domain = 0;
 	if (flags & EXEC_OBJECT_WRITE) {
-		obj->base.write_domain = I915_GEM_DOMAIN_RENDER;
+		obj->write_domain = I915_GEM_DOMAIN_RENDER;
 
 		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
 			i915_gem_active_set(&obj->frontbuffer_write, req);
 
-		obj->base.read_domains = 0;
+		obj->read_domains = 0;
 	}
-	obj->base.read_domains |= I915_GEM_GPU_DOMAINS;
+	obj->read_domains |= I915_GEM_GPU_DOMAINS;
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE)
 		i915_gem_active_set(&vma->last_fence, req);
diff --git a/drivers/gpu/drm/i915/i915_gem_internal.c b/drivers/gpu/drm/i915/i915_gem_internal.c
index 8301c06c952f..0d0144b2104c 100644
--- a/drivers/gpu/drm/i915/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/i915_gem_internal.c
@@ -201,8 +201,8 @@ i915_gem_object_create_internal(struct drm_i915_private *i915,
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
 	i915_gem_object_init(obj, &i915_gem_object_internal_ops);
 
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
 
 	cache_level = HAS_LLC(i915) ? I915_CACHE_LLC : I915_CACHE_NONE;
 	i915_gem_object_set_cache_coherency(obj, cache_level);
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 05e89e1c0a08..ca2b3b62569d 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -148,6 +148,21 @@ struct drm_i915_gem_object {
 #define I915_BO_CACHE_COHERENT_FOR_WRITE BIT(1)
 	unsigned int cache_dirty:1;
 
+	/**
+	 * @read_domains: Read memory domains.
+	 *
+	 * These monitor which caches contain read/write data related to the
+	 * object. When transitioning from one set of domains to another,
+	 * the driver is called to ensure that caches are suitably flushed and
+	 * invalidated.
+	 */
+	u16 read_domains;
+
+	/**
+	 * @write_domain: Corresponding unique write memory domain.
+	 */
+	u16 write_domain;
+
 	atomic_t frontbuffer_bits;
 	unsigned int frontbuffer_ggtt_origin; /* write once */
 	struct i915_gem_active frontbuffer_write;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index f18da9e2be8e..62aa67960bf4 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -516,7 +516,7 @@ _i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 	i915_gem_object_init(obj, &i915_gem_object_stolen_ops);
 
 	obj->stolen = stolen;
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
+	obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
 	cache_level = HAS_LLC(dev_priv) ? I915_CACHE_LLC : I915_CACHE_NONE;
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 1f9d24021cbb..d596a8302ca3 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -798,8 +798,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 
 	drm_gem_private_object_init(dev, &obj->base, args->user_size);
 	i915_gem_object_init(obj, &i915_gem_userptr_ops);
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
 
 	obj->userptr.ptr = args->user_ptr;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 161d9103a65e..65c0bef73ee5 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1021,8 +1021,8 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 	err->engine = __active_get_engine_id(&obj->frontbuffer_write);
 
 	err->gtt_offset = vma->node.start;
-	err->read_domains = obj->base.read_domains;
-	err->write_domain = obj->base.write_domain;
+	err->read_domains = obj->read_domains;
+	err->write_domain = obj->write_domain;
 	err->fence_reg = vma->fence ? vma->fence->id : -1;
 	err->tiling = i915_gem_object_get_tiling(obj);
 	err->dirty = obj->mm.dirty;
diff --git a/drivers/gpu/drm/i915/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/selftests/huge_gem_object.c
index a2632df39173..391f3d9ffdf1 100644
--- a/drivers/gpu/drm/i915/selftests/huge_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/huge_gem_object.c
@@ -129,8 +129,8 @@ huge_gem_object(struct drm_i915_private *i915,
 	drm_gem_private_object_init(&i915->drm, &obj->base, dma_size);
 	i915_gem_object_init(obj, &huge_ops);
 
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	cache_level = HAS_LLC(i915) ? I915_CACHE_LLC : I915_CACHE_NONE;
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 	obj->scratch = phys_size;
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 2ea69394f428..52b1bd17bf46 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -178,8 +178,8 @@ huge_pages_object(struct drm_i915_private *i915,
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
 	i915_gem_object_init(obj, &huge_page_ops);
 
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->cache_level = I915_CACHE_NONE;
 
 	obj->mm.page_mask = page_mask;
@@ -329,8 +329,8 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 	else
 		i915_gem_object_init(obj, &fake_ops);
 
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->cache_level = I915_CACHE_NONE;
 
 	return obj;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 56a803d11916..6da2a2f29c54 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -215,8 +215,8 @@ static int cpu_fill(struct drm_i915_gem_object *obj, u32 value)
 	}
 
 	i915_gem_obj_finish_shmem_access(obj);
-	obj->base.read_domains = I915_GEM_DOMAIN_GTT | I915_GEM_DOMAIN_CPU;
-	obj->base.write_domain = 0;
+	obj->read_domains = I915_GEM_DOMAIN_GTT | I915_GEM_DOMAIN_CPU;
+	obj->write_domain = 0;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 89b6ca9b14a7..f7dc926f4ef1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -113,8 +113,8 @@ fake_dma_object(struct drm_i915_private *i915, u64 size)
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
 	i915_gem_object_init(obj, &fake_ops);
 
-	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
-	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->cache_level = I915_CACHE_NONE;
 
 	/* Preallocate the "backing storage" */
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 9c55c2acaa2b..3583b98a1718 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -115,21 +115,6 @@ struct drm_gem_object {
 	 */
 	int name;
 
-	/**
-	 * @read_domains:
-	 *
-	 * Read memory domains. These monitor which caches contain read/write data
-	 * related to the object. When transitioning from one set of domains
-	 * to another, the driver is called to ensure that caches are suitably
-	 * flushed and invalidated.
-	 */
-	uint32_t read_domains;
-
-	/**
-	 * @write_domain: Corresponding unique write memory domain.
-	 */
-	uint32_t write_domain;
-
 	/**
 	 * @dma_buf:
 	 *
-- 
cgit v1.2.3


From 60bbade2a63de363a7acdb5e3b0f166a883fe3be Mon Sep 17 00:00:00 2001
From: Rex Zhu
Date: Wed, 17 Jan 2018 13:18:47 +0800
Subject: drm/amdgpu: Expose more GPU sensor queries

Add sub-queries for stable pstate shader/memory clock.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 18 ++++++++++++++++++
 include/uapi/drm/amdgpu_drm.h           |  4 ++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 9f189ab07cdd..b929986dd3d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -758,6 +758,24 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 				return -EINVAL;
 			}
 			break;
+		case AMDGPU_INFO_SENSOR_STABLE_PSTATE_GFX_SCLK:
+			/* get stable pstate sclk in Mhz */
+			if (amdgpu_dpm_read_sensor(adev,
+						   AMDGPU_PP_SENSOR_STABLE_PSTATE_SCLK,
+						   (void *)&ui32, &ui32_size)) {
+				return -EINVAL;
+			}
+			ui32 /= 100;
+			break;
+		case AMDGPU_INFO_SENSOR_STABLE_PSTATE_GFX_MCLK:
+			/* get stable pstate mclk in Mhz */
+			if (amdgpu_dpm_read_sensor(adev,
+						   AMDGPU_PP_SENSOR_STABLE_PSTATE_MCLK,
+						   (void *)&ui32, &ui32_size)) {
+				return -EINVAL;
+			}
+			ui32 /= 100;
+			break;
 		default:
 			DRM_DEBUG_KMS("Invalid request %d\n",
 				      info->sensor_info.type);
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 4d21191aaed0..1816bd8200d1 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -664,6 +664,10 @@ struct drm_amdgpu_cs_chunk_data {
 	#define AMDGPU_INFO_SENSOR_VDDNB		0x6
 	/* Subquery id: Query graphics voltage */
 	#define AMDGPU_INFO_SENSOR_VDDGFX		0x7
+	/* Subquery id: Query GPU stable pstate shader clock */
+	#define AMDGPU_INFO_SENSOR_STABLE_PSTATE_GFX_SCLK		0x8
+	/* Subquery id: Query GPU stable pstate memory clock */
+	#define AMDGPU_INFO_SENSOR_STABLE_PSTATE_GFX_MCLK		0x9
 /* Number of VRAM page faults on CPU access. */
 #define AMDGPU_INFO_NUM_VRAM_CPU_PAGE_FAULTS	0x1E
 #define AMDGPU_INFO_VRAM_LOST_COUNTER		0x1F
-- 
cgit v1.2.3


From cb5f1a52caf23414c65c6bc7eeefc281164ad092 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky
Date: Fri, 22 Dec 2017 08:12:40 -0500
Subject: drm/ttm: Allow page allocations w/o triggering OOM..

This to allow drivers to choose to avoid OOM invocation and handle
page allocation failures instead.

v2:
Remove extra new lines.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c             |  3 +++
 drivers/gpu/drm/ttm/ttm_page_alloc.c     |  6 ++++++
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c |  3 +++
 drivers/gpu/drm/ttm/ttm_tt.c             | 13 +++++++++++--
 include/drm/ttm/ttm_bo_driver.h          |  4 ++++
 5 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 2fef09a56d16..d33a6bb742a1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -235,6 +235,9 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 	if (bdev->need_dma32)
 		page_flags |= TTM_PAGE_FLAG_DMA32;
 
+	if (bdev->no_retry)
+		page_flags |= TTM_PAGE_FLAG_NO_RETRY;
+
 	switch (bo->type) {
 	case ttm_bo_type_device:
 		if (zero_alloc)
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 2b12c55a3bff..c84da14311ec 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -741,6 +741,9 @@ out:
 		if (ttm_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
 			gfp_flags |= __GFP_ZERO;
 
+		if (ttm_flags & TTM_PAGE_FLAG_NO_RETRY)
+			gfp_flags |= __GFP_RETRY_MAYFAIL;
+
 		/* ttm_alloc_new_pages doesn't reference pool so we can run
 		 * multiple requests in parallel.
 		 **/
@@ -893,6 +896,9 @@ static int ttm_get_pages(struct page **pages, unsigned npages, int flags,
 		if (flags & TTM_PAGE_FLAG_ZERO_ALLOC)
 			gfp_flags |= __GFP_ZERO;
 
+		if (flags & TTM_PAGE_FLAG_NO_RETRY)
+			gfp_flags |= __GFP_RETRY_MAYFAIL;
+
 		if (flags & TTM_PAGE_FLAG_DMA32)
 			gfp_flags |= GFP_DMA32;
 		else
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index a88051552ace..9e90d0ebc773 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -920,6 +920,9 @@ static gfp_t ttm_dma_pool_gfp_flags(struct ttm_dma_tt *ttm_dma, bool huge)
 		gfp_flags &= ~__GFP_COMP;
 	}
 
+	if (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY)
+		gfp_flags |= __GFP_RETRY_MAYFAIL;
+
 	return gfp_flags;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 5a046a3c543a..9e4d43d68e91 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -301,7 +301,11 @@ int ttm_tt_swapin(struct ttm_tt *ttm)
 	swap_space = swap_storage->f_mapping;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
-		from_page = shmem_read_mapping_page(swap_space, i);
+		gfp_t gfp_mask = mapping_gfp_mask(swap_space);
+
+		gfp_mask |= (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY ? __GFP_RETRY_MAYFAIL : 0);
+		from_page = shmem_read_mapping_page_gfp(swap_space, i, gfp_mask);
+
 		if (IS_ERR(from_page)) {
 			ret = PTR_ERR(from_page);
 			goto out_err;
@@ -350,10 +354,15 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage)
 	swap_space = swap_storage->f_mapping;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
+		gfp_t gfp_mask = mapping_gfp_mask(swap_space);
+
+		gfp_mask |= (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY ? __GFP_RETRY_MAYFAIL : 0);
+
 		from_page = ttm->pages[i];
 		if (unlikely(from_page == NULL))
 			continue;
-		to_page = shmem_read_mapping_page(swap_space, i);
+
+		to_page = shmem_read_mapping_page_gfp(swap_space, i, gfp_mask);
 		if (IS_ERR(to_page)) {
 			ret = PTR_ERR(to_page);
 			goto out_err;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 94064b126e8e..9b417eb2df20 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -86,6 +86,7 @@ struct ttm_backend_func {
 #define TTM_PAGE_FLAG_ZERO_ALLOC      (1 << 6)
 #define TTM_PAGE_FLAG_DMA32           (1 << 7)
 #define TTM_PAGE_FLAG_SG              (1 << 8)
+#define TTM_PAGE_FLAG_NO_RETRY	      (1 << 9)
 
 enum ttm_caching_state {
 	tt_uncached,
@@ -556,6 +557,7 @@ struct ttm_bo_global {
  * @dev_mapping: A pointer to the struct address_space representing the
  * device address space.
  * @wq: Work queue structure for the delayed delete workqueue.
+ * @no_retry: Don't retry allocation if it fails
  *
  */
 
@@ -592,6 +594,8 @@ struct ttm_bo_device {
 	struct delayed_work wq;
 
 	bool need_dma32;
+
+	bool no_retry;
 };
 
 /**
-- 
cgit v1.2.3


From 25893a14c938d54babb1bbee46dd9b622591c866 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Thu, 1 Feb 2018 14:39:29 +0100
Subject: drm/ttm: add ttm_tt_populate wrapper

Stop calling the driver callback directly.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo_util.c | 12 +++++-------
 drivers/gpu/drm/ttm/ttm_bo_vm.c   |  2 +-
 drivers/gpu/drm/ttm/ttm_tt.c      | 10 +++++++++-
 include/drm/ttm/ttm_bo_driver.h   |  9 +++++++++
 4 files changed, 24 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 33ffe286f3a5..38da6903cae9 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -375,8 +375,8 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	/*
 	 * TTM might be null for moves within the same region.
 	 */
-	if (ttm && ttm->state == tt_unpopulated) {
-		ret = ttm->bdev->driver->ttm_tt_populate(ttm, ctx);
+	if (ttm) {
+		ret = ttm_tt_populate(ttm, ctx);
 		if (ret)
 			goto out1;
 	}
@@ -557,11 +557,9 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 
 	BUG_ON(!ttm);
 
-	if (ttm->state == tt_unpopulated) {
-		ret = ttm->bdev->driver->ttm_tt_populate(ttm, &ctx);
-		if (ret)
-			return ret;
-	}
+	ret = ttm_tt_populate(ttm, &ctx);
+	if (ret)
+		return ret;
 
 	if (num_pages == 1 && (mem->placement & TTM_PL_FLAG_CACHED)) {
 		/*
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 716e724ac710..610d6714042a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -234,7 +234,7 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 						cvma.vm_page_prot);
 
 		/* Allocate all page at once, most common usage */
-		if (ttm->bdev->driver->ttm_tt_populate(ttm, &ctx)) {
+		if (ttm_tt_populate(ttm, &ctx)) {
 			ret = VM_FAULT_OOM;
 			goto out_io_unlock;
 		}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 95a77dab8cc9..39c44e301c72 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -276,7 +276,7 @@ int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem,
 	if (ttm->state == tt_bound)
 		return 0;
 
-	ret = ttm->bdev->driver->ttm_tt_populate(ttm, ctx);
+	ret = ttm_tt_populate(ttm, ctx);
 	if (ret)
 		return ret;
 
@@ -392,6 +392,14 @@ out_err:
 	return ret;
 }
 
+int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+{
+	if (ttm->state != tt_unpopulated)
+		return 0;
+
+	return ttm->bdev->driver->ttm_tt_populate(ttm, ctx);
+}
+
 static void ttm_tt_clear_mapping(struct ttm_tt *ttm)
 {
 	pgoff_t i;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 9b417eb2df20..2bac25a6cf90 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -700,6 +700,15 @@ int ttm_tt_swapin(struct ttm_tt *ttm);
 int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement);
 int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage);
 
+/**
+ * ttm_tt_populate - allocate pages for a ttm
+ *
+ * @ttm: Pointer to the ttm_tt structure
+ *
+ * Calls the driver method to allocate pages for a ttm
+ */
+int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
+
 /**
  * ttm_tt_unpopulate - free pages from a ttm
  *
-- 
cgit v1.2.3


From 6a8bd08d0465b2b8d214007c58598e2c15312296 Mon Sep 17 00:00:00 2001
From: Rob Clark
Date: Wed, 13 Dec 2017 15:12:57 -0500
Subject: drm/msm: add sudo flag to submit ioctl

This flags cause cmdstream to be executed from the ringbuffer (RB)
instead of IB1.  Normally not something you'd ever want to do, but
it is super useful for firmware debugging.

Hidden behind CAP_SYS_RAWIO and a default=n kconfig option which
depends on EXPERT (and has a suitably scary warning), to prevent
it from being used on accident.

Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/Kconfig           | 13 +++++++
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 65 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/msm_gem.h         |  1 +
 drivers/gpu/drm/msm/msm_gem_submit.c  |  9 +++++
 include/uapi/drm/msm_drm.h            |  2 ++
 5 files changed, 90 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 99d39b2aefa6..3065cb290aa8 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -28,6 +28,19 @@ config DRM_MSM_REGISTER_LOGGING
 	  that can be parsed by envytools demsm tool.  If enabled, register
 	  logging can be switched on via msm.reglog=y module param.
 
+config DRM_MSM_GPU_SUDO
+	bool "Enable SUDO flag on submits"
+	depends on DRM_MSM && EXPERT
+	default n
+	help
+	  Enable userspace that has CAP_SYS_RAWIO to submit GPU commands
+	  that are run from RB instead of IB1.  This essentially gives
+	  userspace kernel level access, but is useful for firmware
+	  debugging.
+
+	  Only use this if you are a driver developer.  This should *not*
+	  be enabled for production kernels.  If unsure, say N.
+
 config DRM_MSM_HDMI_HDCP
 	bool "Enable HDMI HDCP support in MSM DRM driver"
 	depends on DRM_MSM && QCOM_SCM
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 579c28c8c994..fa08b4897a56 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -140,6 +140,65 @@ static void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 		gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr);
 }
 
+static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit,
+	struct msm_file_private *ctx)
+{
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct msm_ringbuffer *ring = submit->ring;
+	struct msm_gem_object *obj;
+	uint32_t *ptr, dwords;
+	unsigned int i;
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		switch (submit->cmd[i].type) {
+		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
+			break;
+		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
+			if (priv->lastctx == ctx)
+				break;
+		case MSM_SUBMIT_CMD_BUF:
+			/* copy commands into RB: */
+			obj = submit->bos[submit->cmd[i].idx].obj;
+			dwords = submit->cmd[i].size;
+
+			ptr = msm_gem_get_vaddr(&obj->base);
+
+			/* _get_vaddr() shouldn't fail at this point,
+			 * since we've already mapped it once in
+			 * submit_reloc()
+			 */
+			if (WARN_ON(!ptr))
+				return;
+
+			for (i = 0; i < dwords; i++) {
+				/* normally the OUT_PKTn() would wait
+				 * for space for the packet.  But since
+				 * we just OUT_RING() the whole thing,
+				 * need to call adreno_wait_ring()
+				 * ourself:
+				 */
+				adreno_wait_ring(ring, 1);
+				OUT_RING(ring, ptr[i]);
+			}
+
+			msm_gem_put_vaddr(&obj->base);
+
+			break;
+		}
+	}
+
+	a5xx_flush(gpu, ring);
+	a5xx_preempt_trigger(gpu);
+
+	/* we might not necessarily have a cmd from userspace to
+	 * trigger an event to know that submit has completed, so
+	 * do this manually:
+	 */
+	a5xx_idle(gpu, ring);
+	ring->memptrs->fence = submit->seqno;
+	msm_gpu_retire(gpu);
+}
+
 static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	struct msm_file_private *ctx)
 {
@@ -149,6 +208,12 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
+	if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) {
+		priv->lastctx = NULL;
+		a5xx_submit_in_rb(gpu, submit, ctx);
+		return;
+	}
+
 	OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1);
 	OUT_RING(ring, 0x02);
 
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 9320e184b48d..c5d9bd3e47a8 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -146,6 +146,7 @@ struct msm_gem_submit {
 	struct msm_gpu_submitqueue *queue;
 	struct pid *pid;    /* submitting process */
 	bool valid;         /* true if no cmdstream patching needed */
+	bool in_rb;         /* "sudo" mode, copy cmds into RB */
 	struct msm_ringbuffer *ring;
 	unsigned int nr_cmds;
 	unsigned int nr_bos;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index b8dc8f96caf2..7bd83e0afa97 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -430,6 +430,12 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_FLAGS)
 		return -EINVAL;
 
+	if (args->flags & MSM_SUBMIT_SUDO) {
+		if (!IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) ||
+		    !capable(CAP_SYS_RAWIO))
+			return -EINVAL;
+	}
+
 	queue = msm_submitqueue_get(ctx, args->queueid);
 	if (!queue)
 		return -ENOENT;
@@ -471,6 +477,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
+	if (args->flags & MSM_SUBMIT_SUDO)
+		submit->in_rb = true;
+
 	ret = submit_lookup_objects(submit, args, file);
 	if (ret)
 		goto out;
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index bbbaffad772d..c06d0a5bdd80 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -201,10 +201,12 @@ struct drm_msm_gem_submit_bo {
 #define MSM_SUBMIT_NO_IMPLICIT   0x80000000 /* disable implicit sync */
 #define MSM_SUBMIT_FENCE_FD_IN   0x40000000 /* enable input fence_fd */
 #define MSM_SUBMIT_FENCE_FD_OUT  0x20000000 /* enable output fence_fd */
+#define MSM_SUBMIT_SUDO          0x10000000 /* run submitted cmds from RB */
 #define MSM_SUBMIT_FLAGS                ( \
 		MSM_SUBMIT_NO_IMPLICIT   | \
 		MSM_SUBMIT_FENCE_FD_IN   | \
 		MSM_SUBMIT_FENCE_FD_OUT  | \
+		MSM_SUBMIT_SUDO          | \
 		0)
 
 /* Each cmdstream submit consists of a table of buffers involved, and
-- 
cgit v1.2.3


From d55cb4fa2cf0105bfb16b60a2846737b91fdc173 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni
Date: Tue, 20 Feb 2018 17:37:52 +0200
Subject: drm/i915/icl: Add the ICL PCI IDs

This is the current PCI ID list in our documentation.

Let's leave the _gt#_ part out for now since our current documentation
is not 100% clear and we don't need this info now anyway.

v2: Use the new ICL_11 naming (Kelvin Gardiner).
v3: Latest IDs as per BSpec (Oscar).
v4: Make it compile (Paulo).
v5: Remove comments (Lucas).
v6: Multile rebases (Paulo).
v7: Rebase (Mika)

Reviewed-by: Anuj Phogat <anuj.phogat@intel.com> (v1)
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180220153755.13509-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_pci.c |  1 +
 include/drm/i915_pciids.h       | 12 ++++++++++++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 1eaabf28d7b7..26e8f5c13231 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -664,6 +664,7 @@ static const struct pci_device_id pciidlist[] = {
 	INTEL_CFL_U_GT2_IDS(&intel_coffeelake_gt2_info),
 	INTEL_CFL_U_GT3_IDS(&intel_coffeelake_gt3_info),
 	INTEL_CNL_IDS(&intel_cannonlake_info),
+	INTEL_ICL_11_IDS(&intel_icelake_11_info),
 	{0, 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, pciidlist);
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 0b2ba46fa00b..70f0c2535b87 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -431,4 +431,16 @@
 	INTEL_VGA_DEVICE(0x5A44, info), \
 	INTEL_VGA_DEVICE(0x5A4C, info)
 
+/* ICL */
+#define INTEL_ICL_11_IDS(info) \
+	INTEL_VGA_DEVICE(0x8A50, info), \
+	INTEL_VGA_DEVICE(0x8A51, info), \
+	INTEL_VGA_DEVICE(0x8A5C, info), \
+	INTEL_VGA_DEVICE(0x8A5D, info), \
+	INTEL_VGA_DEVICE(0x8A52, info), \
+	INTEL_VGA_DEVICE(0x8A5A, info), \
+	INTEL_VGA_DEVICE(0x8A5B, info), \
+	INTEL_VGA_DEVICE(0x8A71, info), \
+	INTEL_VGA_DEVICE(0x8A70, info)
+
 #endif /* _I915_PCIIDS_H */
-- 
cgit v1.2.3


From d330fca11500bebaf7f25b60b7b087bbe8ad0b7f Mon Sep 17 00:00:00 2001
From: Roger He
Date: Tue, 6 Feb 2018 11:22:57 +0800
Subject: drm/ttm: use bit flag to replace allow_reserved_eviction in
 ttm_operation_ctx

for saving memory and more bit flag can be used in future

Signed-off-by: Roger He <Hongbo.He@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c     | 4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4 ++--
 drivers/gpu/drm/ttm/ttm_bo.c               | 3 ++-
 include/drm/ttm/ttm_bo_api.h               | 7 +++++--
 4 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index eaa3cb0c3ad1..dc34b50e6b29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -346,8 +346,8 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 	struct ttm_operation_ctx ctx = {
 		.interruptible = true,
 		.no_wait_gpu = false,
-		.allow_reserved_eviction = false,
-		.resv = bo->tbo.resv
+		.resv = bo->tbo.resv,
+		.flags = 0
 	};
 	uint32_t domain;
 	int r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 969de54b62da..c2a4b7215c46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -341,8 +341,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	struct ttm_operation_ctx ctx = {
 		.interruptible = !kernel,
 		.no_wait_gpu = false,
-		.allow_reserved_eviction = true,
-		.resv = resv
+		.resv = resv,
+		.flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
 	};
 	struct amdgpu_bo *bo;
 	enum ttm_bo_type type;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index d90b1cf10b27..a907311afe1a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -730,7 +730,8 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo,
 	*locked = false;
 	if (bo->resv == ctx->resv) {
 		reservation_object_assert_held(bo->resv);
-		if (ctx->allow_reserved_eviction || !list_empty(&bo->ddestroy))
+		if (ctx->flags & TTM_OPT_FLAG_ALLOW_RES_EVICT
+		    || !list_empty(&bo->ddestroy))
 			ret = true;
 	} else {
 		*locked = reservation_object_trylock(bo->resv);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 2cd025c2abe7..872ff6c1d709 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -263,8 +263,8 @@ struct ttm_bo_kmap_obj {
  *
  * @interruptible: Sleep interruptible if sleeping.
  * @no_wait_gpu: Return immediately if the GPU is busy.
- * @allow_reserved_eviction: Allow eviction of reserved BOs.
  * @resv: Reservation object to allow reserved evictions with.
+ * @flags: Including the following flags
  *
  * Context for TTM operations like changing buffer placement or general memory
  * allocation.
@@ -272,11 +272,14 @@ struct ttm_bo_kmap_obj {
 struct ttm_operation_ctx {
 	bool interruptible;
 	bool no_wait_gpu;
-	bool allow_reserved_eviction;
 	struct reservation_object *resv;
 	uint64_t bytes_moved;
+	uint32_t flags;
 };
 
+/* Allow eviction of reserved BOs */
+#define TTM_OPT_FLAG_ALLOW_RES_EVICT	0x1
+
 /**
  * ttm_bo_reference - reference a struct ttm_buffer_object
  *
-- 
cgit v1.2.3


From aa7662b67bf6f56cd0d678da6732e26f1b4bf0ed Mon Sep 17 00:00:00 2001
From: Roger He
Date: Wed, 17 Jan 2018 15:07:23 +0800
Subject: drm/ttm: add bit flag TTM_OPT_FLAG_FORCE_ALLOC

set TTM_OPT_FLAG_FORCE_ALLOC when we are servicing for page
fault routine.

for ttm_mem_global_reserve if in page fault routine, allow the gtt
pages reservation always. because page fault routing already grabbed
system memory and the allowance of this exception is harmless.
Otherwise, it will trigger OOM killer.

will be used later.

v2: set the FORCE_ALLOC always
v3: minor refine

Signed-off-by: Roger He <Hongbo.He@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo_vm.c | 4 +++-
 include/drm/ttm/ttm_bo_api.h    | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 121f017ac7ca..8eba95b3c737 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -226,7 +226,9 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 	} else {
 		struct ttm_operation_ctx ctx = {
 			.interruptible = false,
-			.no_wait_gpu = false
+			.no_wait_gpu = false,
+			.flags = TTM_OPT_FLAG_FORCE_ALLOC
+
 		};
 
 		ttm = bo->ttm;
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 872ff6c1d709..21426395820c 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -278,7 +278,9 @@ struct ttm_operation_ctx {
 };
 
 /* Allow eviction of reserved BOs */
-#define TTM_OPT_FLAG_ALLOW_RES_EVICT	0x1
+#define TTM_OPT_FLAG_ALLOW_RES_EVICT		0x1
+/* when serving page fault or suspend, allow alloc anyway */
+#define TTM_OPT_FLAG_FORCE_ALLOC		0x2
 
 /**
  * ttm_bo_reference - reference a struct ttm_buffer_object
-- 
cgit v1.2.3


From 38392633627c60ca8a1e90106055c85b5215a494 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Wed, 21 Feb 2018 17:26:45 +0100
Subject: drm/ttm: drop bo->glob

The pointer is available as bo->bdev->glob as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/qxl/qxl_release.c      |  2 +-
 drivers/gpu/drm/ttm/ttm_bo.c           | 23 ++++++++++++-----------
 drivers/gpu/drm/ttm/ttm_bo_util.c      |  2 +-
 drivers/gpu/drm/ttm/ttm_execbuf_util.c |  6 +++---
 include/drm/ttm/ttm_bo_api.h           |  3 ++-
 include/drm/ttm/ttm_bo_driver.h        |  4 ++--
 6 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index b223c8d0a491..5d84a66fed36 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -458,7 +458,7 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 	trace_dma_fence_emit(&release->base);
 
 	driver = bdev->driver;
-	glob = bo->glob;
+	glob = bdev->glob;
 
 	spin_lock(&glob->lru_lock);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 2bde37291e3e..fe4aef6b1a7a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -149,7 +149,7 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	BUG_ON(!list_empty(&bo->lru));
 	BUG_ON(!list_empty(&bo->ddestroy));
 	ttm_tt_destroy(bo->ttm);
-	atomic_dec(&bo->glob->bo_count);
+	atomic_dec(&bo->bdev->glob->bo_count);
 	dma_fence_put(bo->moving);
 	reservation_object_fini(&bo->ttm_resv);
 	mutex_destroy(&bo->wu_mutex);
@@ -174,7 +174,7 @@ void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
 		if (bo->ttm && !(bo->ttm->page_flags &
 				 (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) {
 			list_add_tail(&bo->swap,
-				      &bo->glob->swap_lru[bo->priority]);
+				      &bdev->glob->swap_lru[bo->priority]);
 			kref_get(&bo->list_kref);
 		}
 	}
@@ -205,9 +205,11 @@ void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 
 void ttm_bo_del_sub_from_lru(struct ttm_buffer_object *bo)
 {
-	spin_lock(&bo->glob->lru_lock);
+	struct ttm_bo_global *glob = bo->bdev->glob;
+
+	spin_lock(&glob->lru_lock);
 	ttm_bo_del_from_lru(bo);
-	spin_unlock(&bo->glob->lru_lock);
+	spin_unlock(&glob->lru_lock);
 }
 EXPORT_SYMBOL(ttm_bo_del_sub_from_lru);
 
@@ -226,7 +228,7 @@ EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
 static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_global *glob = bo->glob;
+	struct ttm_bo_global *glob = bdev->glob;
 	int ret = 0;
 	uint32_t page_flags = 0;
 
@@ -429,7 +431,7 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo)
 static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_global *glob = bo->glob;
+	struct ttm_bo_global *glob = bdev->glob;
 	int ret;
 
 	ret = ttm_bo_individualize_resv(bo);
@@ -500,7 +502,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 			       bool interruptible, bool no_wait_gpu,
 			       bool unlock_resv)
 {
-	struct ttm_bo_global *glob = bo->glob;
+	struct ttm_bo_global *glob = bo->bdev->glob;
 	struct reservation_object *resv;
 	int ret;
 
@@ -1191,7 +1193,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	INIT_LIST_HEAD(&bo->io_reserve_lru);
 	mutex_init(&bo->wu_mutex);
 	bo->bdev = bdev;
-	bo->glob = bdev->glob;
 	bo->type = type;
 	bo->num_pages = num_pages;
 	bo->mem.size = num_pages << PAGE_SHIFT;
@@ -1213,7 +1214,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		bo->resv = &bo->ttm_resv;
 	}
 	reservation_object_init(&bo->ttm_resv);
-	atomic_inc(&bo->glob->bo_count);
+	atomic_inc(&bo->bdev->glob->bo_count);
 	drm_vma_node_reset(&bo->vma_node);
 	bo->priority = 0;
 
@@ -1246,9 +1247,9 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	}
 
 	if (resv && !(bo->mem.placement & TTM_PL_FLAG_NO_EVICT)) {
-		spin_lock(&bo->glob->lru_lock);
+		spin_lock(&bdev->glob->lru_lock);
 		ttm_bo_add_to_lru(bo);
-		spin_unlock(&bo->glob->lru_lock);
+		spin_unlock(&bdev->glob->lru_lock);
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 38da6903cae9..6d6a3f46143b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -470,7 +470,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	 * TODO: Explicit member copy would probably be better here.
 	 */
 
-	atomic_inc(&bo->glob->bo_count);
+	atomic_inc(&bo->bdev->glob->bo_count);
 	INIT_LIST_HEAD(&fbo->ddestroy);
 	INIT_LIST_HEAD(&fbo->lru);
 	INIT_LIST_HEAD(&fbo->swap);
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index fa44f7b15285..3dca206e85f7 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -62,7 +62,7 @@ void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
 		return;
 
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
-	glob = entry->bo->glob;
+	glob = entry->bo->bdev->glob;
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(entry, list, head) {
@@ -102,7 +102,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 		return 0;
 
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
-	glob = entry->bo->glob;
+	glob = entry->bo->bdev->glob;
 
 	if (ticket)
 		ww_acquire_init(ticket, &reservation_ww_class);
@@ -194,7 +194,7 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 	bo = list_first_entry(list, struct ttm_validate_buffer, head)->bo;
 	bdev = bo->bdev;
 	driver = bdev->driver;
-	glob = bo->glob;
+	glob = bo->bdev->glob;
 
 	spin_lock(&glob->lru_lock);
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 21426395820c..a9e0640849d8 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -41,6 +41,8 @@
 #include <linux/bitmap.h>
 #include <linux/reservation.h>
 
+struct ttm_bo_global;
+
 struct ttm_bo_device;
 
 struct drm_mm_node;
@@ -169,7 +171,6 @@ struct ttm_buffer_object {
 	 * Members constant at init.
 	 */
 
-	struct ttm_bo_global *glob;
 	struct ttm_bo_device *bdev;
 	enum ttm_bo_type type;
 	void (*destroy) (struct ttm_buffer_object *);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 2bac25a6cf90..738bb8d35c44 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -956,9 +956,9 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo,
 static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
 {
 	if (!(bo->mem.placement & TTM_PL_FLAG_NO_EVICT)) {
-		spin_lock(&bo->glob->lru_lock);
+		spin_lock(&bo->bdev->glob->lru_lock);
 		ttm_bo_add_to_lru(bo);
-		spin_unlock(&bo->glob->lru_lock);
+		spin_unlock(&bo->bdev->glob->lru_lock);
 	}
 	reservation_object_unlock(bo->resv);
 }
-- 
cgit v1.2.3


From 3231a7696e22538529e9ee3500f2116a40a22734 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Wed, 21 Feb 2018 19:02:06 +0100
Subject: drm/ttm: drop ttm->glob

The pointer is available as ttm->bdev->glob as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc.c     |  6 +++---
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 11 ++++++-----
 drivers/gpu/drm/ttm/ttm_tt.c             |  2 --
 include/drm/ttm/ttm_bo_driver.h          |  1 -
 4 files changed, 9 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 5edcd896cd53..2c28c4568c5f 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -1072,6 +1072,7 @@ void ttm_page_alloc_fini(void)
 static void
 ttm_pool_unpopulate_helper(struct ttm_tt *ttm, unsigned mem_count_update)
 {
+	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
 	unsigned i;
 
 	if (mem_count_update == 0)
@@ -1081,8 +1082,7 @@ ttm_pool_unpopulate_helper(struct ttm_tt *ttm, unsigned mem_count_update)
 		if (!ttm->pages[i])
 			continue;
 
-		ttm_mem_global_free_page(ttm->glob->mem_glob, ttm->pages[i],
-					 PAGE_SIZE);
+		ttm_mem_global_free_page(mem_glob, ttm->pages[i], PAGE_SIZE);
 	}
 
 put_pages:
@@ -1093,7 +1093,7 @@ put_pages:
 
 int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 {
-	struct ttm_mem_global *mem_glob = ttm->glob->mem_glob;
+	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
 	unsigned i;
 	int ret;
 
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index b122f6eee94c..3b4c97011b5c 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -929,7 +929,7 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev,
 			struct ttm_operation_ctx *ctx)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
-	struct ttm_mem_global *mem_glob = ttm->glob->mem_glob;
+	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
 	unsigned long num_pages = ttm->num_pages;
 	struct dma_pool *pool;
 	struct dma_page *d_page;
@@ -1031,6 +1031,7 @@ EXPORT_SYMBOL_GPL(ttm_dma_populate);
 void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
+	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
 	struct dma_pool *pool;
 	struct dma_page *d_page, *next;
 	enum pool_type type;
@@ -1051,8 +1052,8 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 
 			count++;
 			if (d_page->vaddr & VADDR_FLAG_UPDATED_COUNT) {
-				ttm_mem_global_free_page(ttm->glob->mem_glob,
-							 d_page->p, pool->size);
+				ttm_mem_global_free_page(mem_glob, d_page->p,
+							 pool->size);
 				d_page->vaddr &= ~VADDR_FLAG_UPDATED_COUNT;
 			}
 			ttm_dma_page_put(pool, d_page);
@@ -1080,8 +1081,8 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 		count++;
 
 		if (d_page->vaddr & VADDR_FLAG_UPDATED_COUNT) {
-			ttm_mem_global_free_page(ttm->glob->mem_glob,
-						 d_page->p, pool->size);
+			ttm_mem_global_free_page(mem_glob, d_page->p,
+						 pool->size);
 			d_page->vaddr &= ~VADDR_FLAG_UPDATED_COUNT;
 		}
 
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 65bf4eac184b..5d8f7f9b84b1 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -195,7 +195,6 @@ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
 		struct page *dummy_read_page)
 {
 	ttm->bdev = bdev;
-	ttm->glob = bdev->glob;
 	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
@@ -226,7 +225,6 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 
 	ttm->bdev = bdev;
-	ttm->glob = bdev->glob;
 	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 738bb8d35c44..0e4ae26da093 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -123,7 +123,6 @@ struct ttm_tt {
 	uint32_t page_flags;
 	unsigned long num_pages;
 	struct sg_table *sg; /* for SG objects via dma-buf */
-	struct ttm_bo_global *glob;
 	struct file *swap_storage;
 	enum ttm_caching_state caching_state;
 	enum {
-- 
cgit v1.2.3


From 231cdafc75434015f3925d6662a1821fcfef16b7 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Wed, 21 Feb 2018 20:34:13 +0100
Subject: drm/ttm: drop ttm->dummy_read_page

Only used by the AGP backend and there it can be easily accessed using
ttm->bdev->glob.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c     |  5 ++---
 drivers/gpu/drm/ast/ast_ttm.c               |  5 ++---
 drivers/gpu/drm/bochs/bochs_mm.c            |  5 ++---
 drivers/gpu/drm/cirrus/cirrus_ttm.c         |  5 ++---
 drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c |  5 ++---
 drivers/gpu/drm/mgag200/mgag200_ttm.c       |  5 ++---
 drivers/gpu/drm/nouveau/nouveau_bo.c        |  6 +++---
 drivers/gpu/drm/nouveau/nouveau_sgdma.c     |  5 ++---
 drivers/gpu/drm/nouveau/nouveau_ttm.h       |  3 +--
 drivers/gpu/drm/qxl/qxl_ttm.c               |  6 ++----
 drivers/gpu/drm/radeon/radeon_ttm.c         |  7 +++----
 drivers/gpu/drm/ttm/ttm_agp_backend.c       |  8 ++++----
 drivers/gpu/drm/ttm/ttm_bo.c                |  6 ++----
 drivers/gpu/drm/ttm/ttm_tt.c                |  8 ++------
 drivers/gpu/drm/virtio/virtgpu_ttm.c        |  6 ++----
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c      |  9 +++------
 drivers/staging/vboxvideo/vbox_ttm.c        |  5 ++---
 include/drm/ttm/ttm_bo_driver.h             | 17 ++++-------------
 18 files changed, 42 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index b372d8d650a5..e38e6db8f760 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -969,8 +969,7 @@ static struct ttm_backend_func amdgpu_backend_func = {
 };
 
 static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_bo_device *bdev,
-				    unsigned long size, uint32_t page_flags,
-				    struct page *dummy_read_page)
+				    unsigned long size, uint32_t page_flags)
 {
 	struct amdgpu_device *adev;
 	struct amdgpu_ttm_tt *gtt;
@@ -983,7 +982,7 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_bo_device *bdev,
 	}
 	gtt->ttm.ttm.func = &amdgpu_backend_func;
 	gtt->adev = adev;
-	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 68b9c5522eaa..77d2035dc7b7 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -200,8 +200,7 @@ static struct ttm_backend_func ast_tt_backend_func = {
 
 
 static struct ttm_tt *ast_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags,
-				 struct page *dummy_read_page)
+				 unsigned long size, uint32_t page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -209,7 +208,7 @@ static struct ttm_tt *ast_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &ast_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_tt_init(tt, bdev, size, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index 5525b6660340..96edf005bfea 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -178,8 +178,7 @@ static struct ttm_backend_func bochs_tt_backend_func = {
 
 static struct ttm_tt *bochs_ttm_tt_create(struct ttm_bo_device *bdev,
 					  unsigned long size,
-					  uint32_t page_flags,
-					  struct page *dummy_read_page)
+					  uint32_t page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -187,7 +186,7 @@ static struct ttm_tt *bochs_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &bochs_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_tt_init(tt, bdev, size, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 33798c76a64b..3413389c0fbe 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -200,8 +200,7 @@ static struct ttm_backend_func cirrus_tt_backend_func = {
 
 
 static struct ttm_tt *cirrus_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags,
-				 struct page *dummy_read_page)
+				 unsigned long size, uint32_t page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -209,7 +208,7 @@ static struct ttm_tt *cirrus_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &cirrus_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_tt_init(tt, bdev, size, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
index 0c93349fbacf..50e317a2a4ca 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
@@ -202,8 +202,7 @@ static struct ttm_backend_func hibmc_tt_backend_func = {
 
 static struct ttm_tt *hibmc_ttm_tt_create(struct ttm_bo_device *bdev,
 					  unsigned long size,
-					  u32 page_flags,
-					  struct page *dummy_read_page)
+					  u32 page_flags)
 {
 	struct ttm_tt *tt;
 	int ret;
@@ -214,7 +213,7 @@ static struct ttm_tt *hibmc_ttm_tt_create(struct ttm_bo_device *bdev,
 		return NULL;
 	}
 	tt->func = &hibmc_tt_backend_func;
-	ret = ttm_tt_init(tt, bdev, size, page_flags, dummy_read_page);
+	ret = ttm_tt_init(tt, bdev, size, page_flags);
 	if (ret) {
 		DRM_ERROR("failed to initialize ttm_tt: %d\n", ret);
 		kfree(tt);
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 26e5f14645c5..cd55ff5f0f0a 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -200,8 +200,7 @@ static struct ttm_backend_func mgag200_tt_backend_func = {
 
 
 static struct ttm_tt *mgag200_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags,
-				 struct page *dummy_read_page)
+				 unsigned long size, uint32_t page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -209,7 +208,7 @@ static struct ttm_tt *mgag200_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &mgag200_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_tt_init(tt, bdev, size, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 80fa68d54bd3..5c01ccfd3066 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -605,18 +605,18 @@ nouveau_bo_wr32(struct nouveau_bo *nvbo, unsigned index, u32 val)
 
 static struct ttm_tt *
 nouveau_ttm_tt_create(struct ttm_bo_device *bdev, unsigned long size,
-		      uint32_t page_flags, struct page *dummy_read)
+		      uint32_t page_flags)
 {
 #if IS_ENABLED(CONFIG_AGP)
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 
 	if (drm->agp.bridge) {
 		return ttm_agp_tt_create(bdev, drm->agp.bridge, size,
-					 page_flags, dummy_read);
+					 page_flags);
 	}
 #endif
 
-	return nouveau_sgdma_create_ttm(bdev, size, page_flags, dummy_read);
+	return nouveau_sgdma_create_ttm(bdev, size, page_flags);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index 11f6ca89769b..87b030437f4d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -83,8 +83,7 @@ static struct ttm_backend_func nv50_sgdma_backend = {
 
 struct ttm_tt *
 nouveau_sgdma_create_ttm(struct ttm_bo_device *bdev,
-			 unsigned long size, uint32_t page_flags,
-			 struct page *dummy_read_page)
+			 unsigned long size, uint32_t page_flags)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 	struct nouveau_sgdma_be *nvbe;
@@ -98,7 +97,7 @@ nouveau_sgdma_create_ttm(struct ttm_bo_device *bdev,
 	else
 		nvbe->ttm.ttm.func = &nv50_sgdma_backend;
 
-	if (ttm_dma_tt_init(&nvbe->ttm, bdev, size, page_flags, dummy_read_page))
+	if (ttm_dma_tt_init(&nvbe->ttm, bdev, size, page_flags))
 		/*
 		 * A failing ttm_dma_tt_init() will call ttm_tt_destroy()
 		 * and thus our nouveau_sgdma_destroy() hook, so we don't need
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.h b/drivers/gpu/drm/nouveau/nouveau_ttm.h
index 96082b696420..64e484ee5ef1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.h
@@ -13,8 +13,7 @@ extern const struct ttm_mem_type_manager_func nouveau_gart_manager;
 extern const struct ttm_mem_type_manager_func nv04_gart_manager;
 
 struct ttm_tt *nouveau_sgdma_create_ttm(struct ttm_bo_device *,
-					unsigned long size, u32 page_flags,
-					struct page *dummy_read_page);
+					unsigned long size, u32 page_flags);
 
 int  nouveau_ttm_init(struct nouveau_drm *drm);
 void nouveau_ttm_fini(struct nouveau_drm *drm);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 07d4f3fde6c1..2ad70eb96207 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -292,8 +292,7 @@ static struct ttm_backend_func qxl_backend_func = {
 };
 
 static struct ttm_tt *qxl_ttm_tt_create(struct ttm_bo_device *bdev,
-					unsigned long size, uint32_t page_flags,
-					struct page *dummy_read_page)
+					unsigned long size, uint32_t page_flags)
 {
 	struct qxl_device *qdev;
 	struct qxl_ttm_tt *gtt;
@@ -304,8 +303,7 @@ static struct ttm_tt *qxl_ttm_tt_create(struct ttm_bo_device *bdev,
 		return NULL;
 	gtt->ttm.ttm.func = &qxl_backend_func;
 	gtt->qdev = qdev;
-	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags,
-			    dummy_read_page)) {
+	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index c50620aadbd0..009f55a2bbf9 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -687,8 +687,7 @@ static struct ttm_backend_func radeon_backend_func = {
 };
 
 static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
-				    unsigned long size, uint32_t page_flags,
-				    struct page *dummy_read_page)
+				    unsigned long size, uint32_t page_flags)
 {
 	struct radeon_device *rdev;
 	struct radeon_ttm_tt *gtt;
@@ -697,7 +696,7 @@ static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
 		return ttm_agp_tt_create(bdev, rdev->ddev->agp->bridge,
-					 size, page_flags, dummy_read_page);
+					 size, page_flags);
 	}
 #endif
 
@@ -707,7 +706,7 @@ static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
 	}
 	gtt->ttm.ttm.func = &radeon_backend_func;
 	gtt->rdev = rdev;
-	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 3e795a099d06..f7c2aefbec7c 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -50,6 +50,7 @@ struct ttm_agp_backend {
 static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
+	struct page *dummy_read_page = ttm->bdev->glob->dummy_read_page;
 	struct drm_mm_node *node = bo_mem->mm_node;
 	struct agp_memory *mem;
 	int ret, cached = (bo_mem->placement & TTM_PL_FLAG_CACHED);
@@ -64,7 +65,7 @@ static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
 		struct page *page = ttm->pages[i];
 
 		if (!page)
-			page = ttm->dummy_read_page;
+			page = dummy_read_page;
 
 		mem->pages[mem->page_count++] = page;
 	}
@@ -111,8 +112,7 @@ static struct ttm_backend_func ttm_agp_func = {
 
 struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
 				 struct agp_bridge_data *bridge,
-				 unsigned long size, uint32_t page_flags,
-				 struct page *dummy_read_page)
+				 unsigned long size, uint32_t page_flags)
 {
 	struct ttm_agp_backend *agp_be;
 
@@ -124,7 +124,7 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
 	agp_be->bridge = bridge;
 	agp_be->ttm.func = &ttm_agp_func;
 
-	if (ttm_tt_init(&agp_be->ttm, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_tt_init(&agp_be->ttm, bdev, size, page_flags)) {
 		kfree(agp_be);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index fe4aef6b1a7a..55028745214b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -228,7 +228,6 @@ EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
 static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_global *glob = bdev->glob;
 	int ret = 0;
 	uint32_t page_flags = 0;
 
@@ -247,14 +246,13 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 			page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
 	case ttm_bo_type_kernel:
 		bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
-						      page_flags, glob->dummy_read_page);
+						      page_flags);
 		if (unlikely(bo->ttm == NULL))
 			ret = -ENOMEM;
 		break;
 	case ttm_bo_type_sg:
 		bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
-						      page_flags | TTM_PAGE_FLAG_SG,
-						      glob->dummy_read_page);
+						      page_flags | TTM_PAGE_FLAG_SG);
 		if (unlikely(bo->ttm == NULL)) {
 			ret = -ENOMEM;
 			break;
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 5d8f7f9b84b1..f93cd108b19d 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -191,14 +191,12 @@ void ttm_tt_destroy(struct ttm_tt *ttm)
 }
 
 int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags,
-		struct page *dummy_read_page)
+		unsigned long size, uint32_t page_flags)
 {
 	ttm->bdev = bdev;
 	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
-	ttm->dummy_read_page = dummy_read_page;
 	ttm->state = tt_unpopulated;
 	ttm->swap_storage = NULL;
 
@@ -219,8 +217,7 @@ void ttm_tt_fini(struct ttm_tt *ttm)
 EXPORT_SYMBOL(ttm_tt_fini);
 
 int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags,
-		struct page *dummy_read_page)
+		    unsigned long size, uint32_t page_flags)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 
@@ -228,7 +225,6 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
 	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
-	ttm->dummy_read_page = dummy_read_page;
 	ttm->state = tt_unpopulated;
 	ttm->swap_storage = NULL;
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_ttm.c b/drivers/gpu/drm/virtio/virtgpu_ttm.c
index 1cde060602aa..ee9839fbae66 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ttm.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ttm.c
@@ -326,8 +326,7 @@ static struct ttm_backend_func virtio_gpu_backend_func = {
 
 static struct ttm_tt *virtio_gpu_ttm_tt_create(struct ttm_bo_device *bdev,
 					       unsigned long size,
-					       uint32_t page_flags,
-					       struct page *dummy_read_page)
+					       uint32_t page_flags)
 {
 	struct virtio_gpu_device *vgdev;
 	struct virtio_gpu_ttm_tt *gtt;
@@ -338,8 +337,7 @@ static struct ttm_tt *virtio_gpu_ttm_tt_create(struct ttm_bo_device *bdev,
 		return NULL;
 	gtt->ttm.ttm.func = &virtio_gpu_backend_func;
 	gtt->vgdev = vgdev;
-	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags,
-			    dummy_read_page)) {
+	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index 22231bc9e845..fead3f2dbb46 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -694,8 +694,7 @@ static struct ttm_backend_func vmw_ttm_func = {
 };
 
 static struct ttm_tt *vmw_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags,
-				 struct page *dummy_read_page)
+				 unsigned long size, uint32_t page_flags)
 {
 	struct vmw_ttm_tt *vmw_be;
 	int ret;
@@ -709,11 +708,9 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_bo_device *bdev,
 	vmw_be->mob = NULL;
 
 	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
-		ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bdev, size, page_flags,
-				      dummy_read_page);
+		ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bdev, size, page_flags);
 	else
-		ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bdev, size, page_flags,
-				  dummy_read_page);
+		ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bdev, size, page_flags);
 	if (unlikely(ret != 0))
 		goto out_no_init;
 
diff --git a/drivers/staging/vboxvideo/vbox_ttm.c b/drivers/staging/vboxvideo/vbox_ttm.c
index c4b7a6b9abd5..d1a211b61718 100644
--- a/drivers/staging/vboxvideo/vbox_ttm.c
+++ b/drivers/staging/vboxvideo/vbox_ttm.c
@@ -195,8 +195,7 @@ static struct ttm_backend_func vbox_tt_backend_func = {
 
 static struct ttm_tt *vbox_ttm_tt_create(struct ttm_bo_device *bdev,
 					 unsigned long size,
-					 u32 page_flags,
-					 struct page *dummy_read_page)
+					 u32 page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -205,7 +204,7 @@ static struct ttm_tt *vbox_ttm_tt_create(struct ttm_bo_device *bdev,
 		return NULL;
 
 	tt->func = &vbox_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags, dummy_read_page)) {
+	if (ttm_tt_init(tt, bdev, size, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 0e4ae26da093..b338dd0ea038 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -100,7 +100,6 @@ enum ttm_caching_state {
  * @bdev: Pointer to a struct ttm_bo_device.
  * @func: Pointer to a struct ttm_backend_func that describes
  * the backend methods.
- * @dummy_read_page: Page to map where the ttm_tt page array contains a NULL
  * pointer.
  * @pages: Array of pages backing the data.
  * @num_pages: Number of pages in the page array.
@@ -118,7 +117,6 @@ enum ttm_caching_state {
 struct ttm_tt {
 	struct ttm_bo_device *bdev;
 	struct ttm_backend_func *func;
-	struct page *dummy_read_page;
 	struct page **pages;
 	uint32_t page_flags;
 	unsigned long num_pages;
@@ -331,7 +329,6 @@ struct ttm_bo_driver {
 	 * @bdev: pointer to a struct ttm_bo_device:
 	 * @size: Size of the data needed backing.
 	 * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
-	 * @dummy_read_page: See struct ttm_bo_device.
 	 *
 	 * Create a struct ttm_tt to back data with system memory pages.
 	 * No pages are actually allocated.
@@ -340,8 +337,7 @@ struct ttm_bo_driver {
 	 */
 	struct ttm_tt *(*ttm_tt_create)(struct ttm_bo_device *bdev,
 					unsigned long size,
-					uint32_t page_flags,
-					struct page *dummy_read_page);
+					uint32_t page_flags);
 
 	/**
 	 * ttm_tt_populate
@@ -621,7 +617,6 @@ ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask)
  * @bdev: pointer to a struct ttm_bo_device:
  * @size: Size of the data needed backing.
  * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
- * @dummy_read_page: See struct ttm_bo_device.
  *
  * Create a struct ttm_tt to back data with system memory pages.
  * No pages are actually allocated.
@@ -629,11 +624,9 @@ ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask)
  * NULL: Out of memory.
  */
 int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags,
-		struct page *dummy_read_page);
+		unsigned long size, uint32_t page_flags);
 int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		    unsigned long size, uint32_t page_flags,
-		    struct page *dummy_read_page);
+		    unsigned long size, uint32_t page_flags);
 
 /**
  * ttm_tt_fini
@@ -1080,7 +1073,6 @@ extern const struct ttm_mem_type_manager_func ttm_bo_manager_func;
  * @bridge: The agp bridge this device is sitting on.
  * @size: Size of the data needed backing.
  * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
- * @dummy_read_page: See struct ttm_bo_device.
  *
  *
  * Create a TTM backend that uses the indicated AGP bridge as an aperture
@@ -1089,8 +1081,7 @@ extern const struct ttm_mem_type_manager_func ttm_bo_manager_func;
  */
 struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
 				 struct agp_bridge_data *bridge,
-				 unsigned long size, uint32_t page_flags,
-				 struct page *dummy_read_page);
+				 unsigned long size, uint32_t page_flags);
 int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
 void ttm_agp_tt_unpopulate(struct ttm_tt *ttm);
 #endif
-- 
cgit v1.2.3


From 724daa4fd65d927e406f2cc0661c9a329876267b Mon Sep 17 00:00:00 2001
From: Christian König
Date: Thu, 22 Feb 2018 15:52:31 +0100
Subject: drm/ttm: drop persistent_swap_storage from ttm_bo_init and co

Never used as parameter, the only driver actually using this is nouveau
and there it is initialized after the BO is initialized.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c  |  4 ++--
 drivers/gpu/drm/ast/ast_ttm.c               |  2 +-
 drivers/gpu/drm/bochs/bochs_mm.c            |  2 +-
 drivers/gpu/drm/cirrus/cirrus_ttm.c         |  2 +-
 drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c |  2 +-
 drivers/gpu/drm/mgag200/mgag200_ttm.c       |  2 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c        |  2 +-
 drivers/gpu/drm/qxl/qxl_object.c            |  2 +-
 drivers/gpu/drm/radeon/radeon_object.c      |  4 ++--
 drivers/gpu/drm/ttm/ttm_bo.c                |  9 ++-------
 drivers/gpu/drm/virtio/virtgpu_object.c     |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c      |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_mob.c         |  5 ++---
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c    |  4 ++--
 drivers/staging/vboxvideo/vbox_ttm.c        |  2 +-
 include/drm/ttm/ttm_bo_api.h                | 16 +---------------
 16 files changed, 21 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index c2a4b7215c46..216799ccb545 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -418,8 +418,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	amdgpu_ttm_placement_from_domain(bo, domain);
 
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
-				 &bo->placement, page_align, &ctx, NULL,
-				 acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
+				 &bo->placement, page_align, &ctx, acc_size,
+				 sg, resv, &amdgpu_ttm_bo_destroy);
 	if (unlikely(r != 0))
 		return r;
 
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 77d2035dc7b7..211224f6bdd3 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -321,7 +321,7 @@ int ast_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&ast->ttm.bdev, &astbo->bo, size,
 			  ttm_bo_type_device, &astbo->placement,
-			  align >> PAGE_SHIFT, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, acc_size,
 			  NULL, NULL, ast_bo_ttm_destroy);
 	if (ret)
 		goto error;
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index 96edf005bfea..73722484e12b 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -368,7 +368,7 @@ static int bochs_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&bochs->ttm.bdev, &bochsbo->bo, size,
 			  ttm_bo_type_device, &bochsbo->placement,
-			  align >> PAGE_SHIFT, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, acc_size,
 			  NULL, NULL, bochs_bo_ttm_destroy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 3413389c0fbe..6cd0233b3bf8 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -328,7 +328,7 @@ int cirrus_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&cirrus->ttm.bdev, &cirrusbo->bo, size,
 			  ttm_bo_type_device, &cirrusbo->placement,
-			  align >> PAGE_SHIFT, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, acc_size,
 			  NULL, NULL, cirrus_bo_ttm_destroy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
index 50e317a2a4ca..8dfffdbb6b07 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
@@ -317,7 +317,7 @@ int hibmc_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&hibmc->bdev, &hibmcbo->bo, size,
 			  ttm_bo_type_device, &hibmcbo->placement,
-			  align >> PAGE_SHIFT, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, acc_size,
 			  NULL, NULL, hibmc_bo_ttm_destroy);
 	if (ret) {
 		hibmc_bo_unref(&hibmcbo);
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index cd55ff5f0f0a..69beb2046008 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -324,7 +324,7 @@ int mgag200_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&mdev->ttm.bdev, &mgabo->bo, size,
 			  ttm_bo_type_device, &mgabo->placement,
-			  align >> PAGE_SHIFT, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, acc_size,
 			  NULL, NULL, mgag200_bo_ttm_destroy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 5c01ccfd3066..49cc8dfcb141 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -298,7 +298,7 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
 
 	ret = ttm_bo_init(&drm->ttm.bdev, &nvbo->bo, size,
 			  type, &nvbo->placement,
-			  align >> PAGE_SHIFT, false, NULL, acc_size, sg,
+			  align >> PAGE_SHIFT, false, acc_size, sg,
 			  robj, nouveau_bo_del_ttm);
 	if (ret) {
 		/* ttm will call nouveau_bo_del_ttm if it fails.. */
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index f6b80fe47d1f..af62824ed4cc 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -109,7 +109,7 @@ int qxl_bo_create(struct qxl_device *qdev,
 	qxl_ttm_placement_from_domain(bo, domain, pinned);
 
 	r = ttm_bo_init(&qdev->mman.bdev, &bo->tbo, size, type,
-			&bo->placement, 0, !kernel, NULL, size,
+			&bo->placement, 0, !kernel, size,
 			NULL, NULL, &qxl_ttm_bo_destroy);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 64ab11d4ea58..38431f682ed0 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -255,8 +255,8 @@ int radeon_bo_create(struct radeon_device *rdev,
 	/* Kernel allocation are uninterruptible */
 	down_read(&rdev->pm.mclk_lock);
 	r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
-			&bo->placement, page_align, !kernel, NULL,
-			acc_size, sg, resv, &radeon_ttm_bo_destroy);
+			&bo->placement, page_align, !kernel, acc_size,
+			sg, resv, &radeon_ttm_bo_destroy);
 	up_read(&rdev->pm.mclk_lock);
 	if (unlikely(r != 0)) {
 		return r;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 55028745214b..4bfa109e2a66 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1149,7 +1149,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 			 struct ttm_placement *placement,
 			 uint32_t page_alignment,
 			 struct ttm_operation_ctx *ctx,
-			 struct file *persistent_swap_storage,
 			 size_t acc_size,
 			 struct sg_table *sg,
 			 struct reservation_object *resv,
@@ -1202,7 +1201,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	bo->mem.bus.io_reserved_count = 0;
 	bo->moving = NULL;
 	bo->mem.placement = (TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED);
-	bo->persistent_swap_storage = persistent_swap_storage;
 	bo->acc_size = acc_size;
 	bo->sg = sg;
 	if (resv) {
@@ -1261,7 +1259,6 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 		struct ttm_placement *placement,
 		uint32_t page_alignment,
 		bool interruptible,
-		struct file *persistent_swap_storage,
 		size_t acc_size,
 		struct sg_table *sg,
 		struct reservation_object *resv,
@@ -1271,8 +1268,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	int ret;
 
 	ret = ttm_bo_init_reserved(bdev, bo, size, type, placement,
-				   page_alignment, &ctx,
-				   persistent_swap_storage, acc_size,
+				   page_alignment, &ctx, acc_size,
 				   sg, resv, destroy);
 	if (ret)
 		return ret;
@@ -1318,7 +1314,6 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 			struct ttm_placement *placement,
 			uint32_t page_alignment,
 			bool interruptible,
-			struct file *persistent_swap_storage,
 			struct ttm_buffer_object **p_bo)
 {
 	struct ttm_buffer_object *bo;
@@ -1331,7 +1326,7 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 
 	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
 	ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment,
-			  interruptible, persistent_swap_storage, acc_size,
+			  interruptible, acc_size,
 			  NULL, NULL, NULL);
 	if (likely(ret == 0))
 		*p_bo = bo;
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 0b90cdb3d9fe..9f2f470efd9b 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -89,7 +89,7 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
 	virtio_gpu_init_ttm_placement(bo, pinned);
 
 	ret = ttm_bo_init(&vgdev->mman.bdev, &bo->tbo, size, type,
-			  &bo->placement, 0, !kernel, NULL, acc_size,
+			  &bo->placement, 0, !kernel, acc_size,
 			  NULL, NULL, &virtio_gpu_ttm_bo_destroy);
 	/* ttm_bo_init failure will call the destroy */
 	if (ret != 0)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
index c706ad30411b..f283324ce598 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
@@ -1245,7 +1245,7 @@ int vmw_cmdbuf_set_pool_size(struct vmw_cmdbuf_man *man,
 			return -ENOMEM;
 
 		ret = ttm_bo_create(&dev_priv->bdev, size, ttm_bo_type_device,
-				    &vmw_mob_ne_placement, 0, false, NULL,
+				    &vmw_mob_ne_placement, 0, false,
 				    &man->cmd_space);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index 736ca47e28ea..d07c585e3c1d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -260,8 +260,7 @@ static int vmw_otable_batch_setup(struct vmw_private *dev_priv,
 	ret = ttm_bo_create(&dev_priv->bdev, bo_size,
 			    ttm_bo_type_device,
 			    &vmw_sys_ne_placement,
-			    0, false, NULL,
-			    &batch->otable_bo);
+			    0, false, &batch->otable_bo);
 
 	if (unlikely(ret != 0))
 		goto out_no_bo;
@@ -444,7 +443,7 @@ static int vmw_mob_pt_populate(struct vmw_private *dev_priv,
 	ret = ttm_bo_create(&dev_priv->bdev, mob->num_pages * PAGE_SIZE,
 			    ttm_bo_type_device,
 			    &vmw_sys_ne_placement,
-			    0, false, NULL, &mob->pt_bo);
+			    0, false, &mob->pt_bo);
 	if (unlikely(ret != 0))
 		return ret;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 200904ff9a22..9e101450cc4d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -384,8 +384,8 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv,
 
 	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
 			  ttm_bo_type_device, placement,
-			  0, interruptible,
-			  NULL, acc_size, NULL, NULL, bo_free);
+			  0, interruptible, acc_size,
+			  NULL, NULL, bo_free);
 	return ret;
 }
 
diff --git a/drivers/staging/vboxvideo/vbox_ttm.c b/drivers/staging/vboxvideo/vbox_ttm.c
index d1a211b61718..2c7daa3d0f24 100644
--- a/drivers/staging/vboxvideo/vbox_ttm.c
+++ b/drivers/staging/vboxvideo/vbox_ttm.c
@@ -331,7 +331,7 @@ int vbox_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&vbox->ttm.bdev, &vboxbo->bo, size,
 			  ttm_bo_type_device, &vboxbo->placement,
-			  align >> PAGE_SHIFT, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, acc_size,
 			  NULL, NULL, vbox_bo_ttm_destroy);
 	if (ret)
 		goto err_free_vboxbo;
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index a9e0640849d8..8e2fb1ac4e0c 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -467,11 +467,6 @@ size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
  * @flags: Initial placement flags.
  * @page_alignment: Data alignment in pages.
  * @ctx: TTM operation context for memory allocation.
- * @persistent_swap_storage: Usually the swap storage is deleted for buffers
- * pinned in physical memory. If this behaviour is not desired, this member
- * holds a pointer to a persistent shmem object. Typically, this would
- * point to the shmem object backing a GEM object if TTM is used to back a
- * GEM user interface.
  * @acc_size: Accounted size for this object.
  * @resv: Pointer to a reservation_object, or NULL to let ttm allocate one.
  * @destroy: Destroy function. Use NULL for kfree().
@@ -504,7 +499,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 			 struct ttm_placement *placement,
 			 uint32_t page_alignment,
 			 struct ttm_operation_ctx *ctx,
-			 struct file *persistent_swap_storage,
 			 size_t acc_size,
 			 struct sg_table *sg,
 			 struct reservation_object *resv,
@@ -521,7 +515,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
  * @page_alignment: Data alignment in pages.
  * @interruptible: If needing to sleep to wait for GPU resources,
  * sleep interruptible.
- * @persistent_swap_storage: Usually the swap storage is deleted for buffers
  * pinned in physical memory. If this behaviour is not desired, this member
  * holds a pointer to a persistent shmem object. Typically, this would
  * point to the shmem object backing a GEM object if TTM is used to back a
@@ -551,8 +544,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 int ttm_bo_init(struct ttm_bo_device *bdev, struct ttm_buffer_object *bo,
 		unsigned long size, enum ttm_bo_type type,
 		struct ttm_placement *placement,
-		uint32_t page_alignment, bool interrubtible,
-		struct file *persistent_swap_storage, size_t acc_size,
+		uint32_t page_alignment, bool interrubtible, size_t acc_size,
 		struct sg_table *sg, struct reservation_object *resv,
 		void (*destroy) (struct ttm_buffer_object *));
 
@@ -566,11 +558,6 @@ int ttm_bo_init(struct ttm_bo_device *bdev, struct ttm_buffer_object *bo,
  * @page_alignment: Data alignment in pages.
  * @interruptible: If needing to sleep while waiting for GPU resources,
  * sleep interruptible.
- * @persistent_swap_storage: Usually the swap storage is deleted for buffers
- * pinned in physical memory. If this behaviour is not desired, this member
- * holds a pointer to a persistent shmem object. Typically, this would
- * point to the shmem object backing a GEM object if TTM is used to back a
- * GEM user interface.
  * @p_bo: On successful completion *p_bo points to the created object.
  *
  * This function allocates a ttm_buffer_object, and then calls ttm_bo_init
@@ -583,7 +570,6 @@ int ttm_bo_init(struct ttm_bo_device *bdev, struct ttm_buffer_object *bo,
 int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size,
 		  enum ttm_bo_type type, struct ttm_placement *placement,
 		  uint32_t page_alignment, bool interruptible,
-		  struct file *persistent_swap_storage,
 		  struct ttm_buffer_object **p_bo);
 
 /**
-- 
cgit v1.2.3


From ec3fe391bdb321b1629cfb0ddbb9fcc114b579bc Mon Sep 17 00:00:00 2001
From: Roger He
Date: Mon, 5 Feb 2018 17:57:07 +0800
Subject: drm/ttm: check if free mem space is under the lower limit

the free mem space and the lower limit both include two parts:
system memory and swap space.

For the OOM triggered by TTM, that is the case as below:
first swap space is full of swapped out pages and soon
system memory also is filled up with ttm pages. and then
any memory allocation request will run into OOM.

to cover two cases:
a. if no swap disk at all or free swap space is under swap mem
   limit but available system mem is bigger than sys mem limit,
   allow TTM allocation;

b. if the available system mem is less than sys mem limit but
   free swap space is bigger than swap mem limit, allow TTM
   allocation.

v2: merge two memory limit(swap and system) into one
v3: keep original behavior except ttm_opt_ctx->flags with
    TTM_OPT_FLAG_FORCE_ALLOC
v4: always set force_alloc as tx->flags & TTM_OPT_FLAG_FORCE_ALLOC
v5: add an attribute for lower_mem_limit
v6: set lower_mem_limit as 0 to keep original behavior

Signed-off-by: Roger He <Hongbo.He@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_memory.c         | 93 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/ttm/ttm_page_alloc.c     |  3 ++
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c |  3 ++
 include/drm/ttm/ttm_memory.h             |  5 ++
 4 files changed, 104 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index aa0c38136958..27856c55dc84 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -36,6 +36,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/swap.h>
 
 #define TTM_MEMORY_ALLOC_RETRIES 4
 
@@ -166,6 +167,54 @@ static struct kobj_type ttm_mem_zone_kobj_type = {
 	.default_attrs = ttm_mem_zone_attrs,
 };
 
+static struct attribute ttm_mem_global_lower_mem_limit = {
+	.name = "lower_mem_limit",
+	.mode = S_IRUGO | S_IWUSR
+};
+
+static ssize_t ttm_mem_global_show(struct kobject *kobj,
+				 struct attribute *attr,
+				 char *buffer)
+{
+	struct ttm_mem_global *glob =
+		container_of(kobj, struct ttm_mem_global, kobj);
+	uint64_t val = 0;
+
+	spin_lock(&glob->lock);
+	val = glob->lower_mem_limit;
+	spin_unlock(&glob->lock);
+	/* convert from number of pages to KB */
+	val <<= (PAGE_SHIFT - 10);
+	return snprintf(buffer, PAGE_SIZE, "%llu\n",
+			(unsigned long long) val);
+}
+
+static ssize_t ttm_mem_global_store(struct kobject *kobj,
+				  struct attribute *attr,
+				  const char *buffer,
+				  size_t size)
+{
+	int chars;
+	uint64_t val64;
+	unsigned long val;
+	struct ttm_mem_global *glob =
+		container_of(kobj, struct ttm_mem_global, kobj);
+
+	chars = sscanf(buffer, "%lu", &val);
+	if (chars == 0)
+		return size;
+
+	val64 = val;
+	/* convert from KB to number of pages */
+	val64 >>= (PAGE_SHIFT - 10);
+
+	spin_lock(&glob->lock);
+	glob->lower_mem_limit = val64;
+	spin_unlock(&glob->lock);
+
+	return size;
+}
+
 static void ttm_mem_global_kobj_release(struct kobject *kobj)
 {
 	struct ttm_mem_global *glob =
@@ -174,8 +223,20 @@ static void ttm_mem_global_kobj_release(struct kobject *kobj)
 	kfree(glob);
 }
 
+static struct attribute *ttm_mem_global_attrs[] = {
+	&ttm_mem_global_lower_mem_limit,
+	NULL
+};
+
+static const struct sysfs_ops ttm_mem_global_ops = {
+	.show = &ttm_mem_global_show,
+	.store = &ttm_mem_global_store,
+};
+
 static struct kobj_type ttm_mem_glob_kobj_type = {
 	.release = &ttm_mem_global_kobj_release,
+	.sysfs_ops = &ttm_mem_global_ops,
+	.default_attrs = ttm_mem_global_attrs,
 };
 
 static bool ttm_zones_above_swap_target(struct ttm_mem_global *glob,
@@ -375,6 +436,9 @@ int ttm_mem_global_init(struct ttm_mem_global *glob)
 
 	si_meminfo(&si);
 
+	/* set it as 0 by default to keep original behavior of OOM */
+	glob->lower_mem_limit = 0;
+
 	ret = ttm_mem_init_kernel_zone(glob, &si);
 	if (unlikely(ret != 0))
 		goto out_no_zone;
@@ -469,6 +533,35 @@ void ttm_mem_global_free(struct ttm_mem_global *glob,
 }
 EXPORT_SYMBOL(ttm_mem_global_free);
 
+/*
+ * check if the available mem is under lower memory limit
+ *
+ * a. if no swap disk at all or free swap space is under swap_mem_limit
+ * but available system mem is bigger than sys_mem_limit, allow TTM
+ * allocation;
+ *
+ * b. if the available system mem is less than sys_mem_limit but free
+ * swap disk is bigger than swap_mem_limit, allow TTM allocation.
+ */
+bool
+ttm_check_under_lowerlimit(struct ttm_mem_global *glob,
+			uint64_t num_pages,
+			struct ttm_operation_ctx *ctx)
+{
+	int64_t available;
+
+	if (ctx->flags & TTM_OPT_FLAG_FORCE_ALLOC)
+		return false;
+
+	available = get_nr_swap_pages() + si_mem_available();
+	available -= num_pages;
+	if (available < glob->lower_mem_limit)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(ttm_check_under_lowerlimit);
+
 static int ttm_mem_global_reserve(struct ttm_mem_global *glob,
 				  struct ttm_mem_zone *single_zone,
 				  uint64_t amount, bool reserve)
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 2c28c4568c5f..f0481b7b60c5 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -1100,6 +1100,9 @@ int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
+	if (ttm_check_under_lowerlimit(mem_glob, ttm->num_pages, ctx))
+		return -ENOMEM;
+
 	ret = ttm_get_pages(ttm->pages, ttm->num_pages, ttm->page_flags,
 			    ttm->caching_state);
 	if (unlikely(ret != 0)) {
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 3b4c97011b5c..8a25d1974385 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -940,6 +940,9 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev,
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
+	if (ttm_check_under_lowerlimit(mem_glob, num_pages, ctx))
+		return -ENOMEM;
+
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
 	i = 0;
 
diff --git a/include/drm/ttm/ttm_memory.h b/include/drm/ttm/ttm_memory.h
index 8936285b6543..737b5fed8003 100644
--- a/include/drm/ttm/ttm_memory.h
+++ b/include/drm/ttm/ttm_memory.h
@@ -49,6 +49,8 @@
  * @work: The workqueue callback for the shrink queue.
  * @lock: Lock to protect the @shrink - and the memory accounting members,
  * that is, essentially the whole structure with some exceptions.
+ * @lower_mem_limit: include lower limit of swap space and lower limit of
+ * system memory.
  * @zones: Array of pointers to accounting zones.
  * @num_zones: Number of populated entries in the @zones array.
  * @zone_kernel: Pointer to the kernel zone.
@@ -67,6 +69,7 @@ struct ttm_mem_global {
 	struct workqueue_struct *swap_queue;
 	struct work_struct work;
 	spinlock_t lock;
+	uint64_t lower_mem_limit;
 	struct ttm_mem_zone *zones[TTM_MEM_MAX_ZONES];
 	unsigned int num_zones;
 	struct ttm_mem_zone *zone_kernel;
@@ -90,4 +93,6 @@ extern void ttm_mem_global_free_page(struct ttm_mem_global *glob,
 				     struct page *page, uint64_t size);
 extern size_t ttm_round_pot(size_t size);
 extern uint64_t ttm_get_kernel_zone_memory_size(struct ttm_mem_global *glob);
+extern bool ttm_check_under_lowerlimit(struct ttm_mem_global *glob,
+			uint64_t num_pages, struct ttm_operation_ctx *ctx);
 #endif
-- 
cgit v1.2.3


From 97b7e1b8b55d5696093b4ebddb9dad63813bdcf2 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Thu, 22 Feb 2018 08:54:57 +0100
Subject: drm/ttm: move ttm_tt_create into ttm_tt.c v2

Rename ttm_bo_add_ttm to ttm_tt_create and move it into ttm_tt.c.

v2: separate the cleanup.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 50 ++---------------------------------------
 drivers/gpu/drm/ttm/ttm_tt.c    | 46 +++++++++++++++++++++++++++++++++++++
 include/drm/ttm/ttm_bo_driver.h | 11 +++++++++
 3 files changed, 59 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 4bfa109e2a66..ad142a92eb80 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -222,52 +222,6 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo)
 }
 EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
 
-/*
- * Call bo->mutex locked.
- */
-static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-	int ret = 0;
-	uint32_t page_flags = 0;
-
-	reservation_object_assert_held(bo->resv);
-	bo->ttm = NULL;
-
-	if (bdev->need_dma32)
-		page_flags |= TTM_PAGE_FLAG_DMA32;
-
-	if (bdev->no_retry)
-		page_flags |= TTM_PAGE_FLAG_NO_RETRY;
-
-	switch (bo->type) {
-	case ttm_bo_type_device:
-		if (zero_alloc)
-			page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
-	case ttm_bo_type_kernel:
-		bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
-						      page_flags);
-		if (unlikely(bo->ttm == NULL))
-			ret = -ENOMEM;
-		break;
-	case ttm_bo_type_sg:
-		bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
-						      page_flags | TTM_PAGE_FLAG_SG);
-		if (unlikely(bo->ttm == NULL)) {
-			ret = -ENOMEM;
-			break;
-		}
-		bo->ttm->sg = bo->sg;
-		break;
-	default:
-		pr_err("Illegal buffer object type\n");
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
 static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem, bool evict,
 				  struct ttm_operation_ctx *ctx)
@@ -295,7 +249,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	if (!(new_man->flags & TTM_MEMTYPE_FLAG_FIXED)) {
 		if (bo->ttm == NULL) {
 			bool zero = !(old_man->flags & TTM_MEMTYPE_FLAG_FIXED);
-			ret = ttm_bo_add_ttm(bo, zero);
+			ret = ttm_tt_create(bo, zero);
 			if (ret)
 				goto out_err;
 		}
@@ -1134,7 +1088,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	 * We might need to add a TTM.
 	 */
 	if (bo->mem.mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) {
-		ret = ttm_bo_add_ttm(bo, true);
+		ret = ttm_tt_create(bo, true);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index f93cd108b19d..917942d03047 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -47,6 +47,52 @@
 #include <asm/set_memory.h>
 #endif
 
+/**
+ * Allocates a ttm structure for the given BO.
+ */
+int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
+{
+	struct ttm_bo_device *bdev = bo->bdev;
+	int ret = 0;
+	uint32_t page_flags = 0;
+
+	reservation_object_assert_held(bo->resv);
+	bo->ttm = NULL;
+
+	if (bdev->need_dma32)
+		page_flags |= TTM_PAGE_FLAG_DMA32;
+
+	if (bdev->no_retry)
+		page_flags |= TTM_PAGE_FLAG_NO_RETRY;
+
+	switch (bo->type) {
+	case ttm_bo_type_device:
+		if (zero_alloc)
+			page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
+	case ttm_bo_type_kernel:
+		bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
+						      page_flags);
+		if (unlikely(bo->ttm == NULL))
+			ret = -ENOMEM;
+		break;
+	case ttm_bo_type_sg:
+		bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
+						      page_flags | TTM_PAGE_FLAG_SG);
+		if (unlikely(bo->ttm == NULL)) {
+			ret = -ENOMEM;
+			break;
+		}
+		bo->ttm->sg = bo->sg;
+		break;
+	default:
+		pr_err("Illegal buffer object type\n");
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 /**
  * Allocates storage for pointers to the pages that back the ttm.
  */
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index b338dd0ea038..4312b5326f0b 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -610,6 +610,17 @@ ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask)
 	return *old;
 }
 
+/**
+ * ttm_tt_create
+ *
+ * @bo: pointer to a struct ttm_buffer_object
+ * @zero_alloc: true if allocated pages needs to be zeroed
+ *
+ * Make sure we have a TTM structure allocated for the given BO.
+ * No pages are actually allocated.
+ */
+int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc);
+
 /**
  * ttm_tt_init
  *
-- 
cgit v1.2.3


From 39a751a4cb7e4798f0ce1169ec92de4a1aae39e3 Mon Sep 17 00:00:00 2001
From: Frank Rowand
Date: Mon, 12 Feb 2018 00:19:42 -0800
Subject: of: change overlay apply input data from unflattened to FDT

Move duplicating and unflattening of an overlay flattened devicetree
(FDT) into the overlay application code.  To accomplish this,
of_overlay_apply() is replaced by of_overlay_fdt_apply().

The copy of the FDT (aka "duplicate FDT") now belongs to devicetree
code, which is thus responsible for freeing the duplicate FDT.  The
caller of of_overlay_fdt_apply() remains responsible for freeing the
original FDT.

The unflattened devicetree now belongs to devicetree code, which is
thus responsible for freeing the unflattened devicetree.

These ownership changes prevent early freeing of the duplicated FDT
or the unflattened devicetree, which could result in use after free
errors.

of_overlay_fdt_apply() is a private function for the anticipated
overlay loader.

Update unittest.c to use of_overlay_fdt_apply() instead of
of_overlay_apply().

Move overlay fragments from artificial locations in
drivers/of/unittest-data/tests-overlay.dtsi into one devicetree
source file per overlay.  This led to changes in
drivers/of/unitest-data/Makefile and drivers/of/unitest.c.

  - Add overlay directives to the overlay devicetree source files so
    that dtc will compile them as true overlays into one FDT data
    chunk per overlay.

  - Set CFLAGS for drivers/of/unittest-data/testcases.dts so that
    symbols will be generated for overlay resolution of overlays
    that are no longer artificially contained in testcases.dts

  - Unflatten and apply each unittest overlay FDT using
    of_overlay_fdt_apply().

  - Enable the of_resolve_phandles() check for whether the unflattened
    overlay is detached.  This check was previously disabled because the
    overlays from tests-overlay.dtsi were not unflattened into detached
    trees.

  - Other changes to unittest.c infrastructure to manage multiple test
    FDTs built into the kernel image (access by name instead of
    arbitrary number).

  - of_unittest_overlay_high_level(): previously unused code to add
    properties from the overlay_base devicetree to the live tree
    was triggered by the restructuring of tests-overlay.dtsi and thus
    testcases.dts.  This exposed two bugs: (1) the need to dup a
    property before adding it, and (2) property 'name' is
    auto-generated in the unflatten code and thus will be a duplicate
    in the __symbols__ node - do not treat this duplicate as an error.

Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
 drivers/of/Kconfig                          |   1 +
 drivers/of/overlay.c                        | 112 ++++++++++-
 drivers/of/resolver.c                       |   6 -
 drivers/of/unittest-data/Makefile           |  28 ++-
 drivers/of/unittest-data/overlay_0.dts      |  14 ++
 drivers/of/unittest-data/overlay_1.dts      |  14 ++
 drivers/of/unittest-data/overlay_10.dts     |  34 ++++
 drivers/of/unittest-data/overlay_11.dts     |  34 ++++
 drivers/of/unittest-data/overlay_12.dts     |  14 ++
 drivers/of/unittest-data/overlay_13.dts     |  14 ++
 drivers/of/unittest-data/overlay_15.dts     |  35 ++++
 drivers/of/unittest-data/overlay_2.dts      |  14 ++
 drivers/of/unittest-data/overlay_3.dts      |  14 ++
 drivers/of/unittest-data/overlay_4.dts      |  23 +++
 drivers/of/unittest-data/overlay_5.dts      |  14 ++
 drivers/of/unittest-data/overlay_6.dts      |  15 ++
 drivers/of/unittest-data/overlay_7.dts      |  15 ++
 drivers/of/unittest-data/overlay_8.dts      |  15 ++
 drivers/of/unittest-data/overlay_9.dts      |  15 ++
 drivers/of/unittest-data/tests-overlay.dtsi | 213 --------------------
 drivers/of/unittest.c                       | 300 ++++++++++++++--------------
 include/linux/of.h                          |   6 +-
 22 files changed, 562 insertions(+), 388 deletions(-)
 create mode 100644 drivers/of/unittest-data/overlay_0.dts
 create mode 100644 drivers/of/unittest-data/overlay_1.dts
 create mode 100644 drivers/of/unittest-data/overlay_10.dts
 create mode 100644 drivers/of/unittest-data/overlay_11.dts
 create mode 100644 drivers/of/unittest-data/overlay_12.dts
 create mode 100644 drivers/of/unittest-data/overlay_13.dts
 create mode 100644 drivers/of/unittest-data/overlay_15.dts
 create mode 100644 drivers/of/unittest-data/overlay_2.dts
 create mode 100644 drivers/of/unittest-data/overlay_3.dts
 create mode 100644 drivers/of/unittest-data/overlay_4.dts
 create mode 100644 drivers/of/unittest-data/overlay_5.dts
 create mode 100644 drivers/of/unittest-data/overlay_6.dts
 create mode 100644 drivers/of/unittest-data/overlay_7.dts
 create mode 100644 drivers/of/unittest-data/overlay_8.dts
 create mode 100644 drivers/of/unittest-data/overlay_9.dts

(limited to 'include')

diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 783e0870bd22..ad3fcad4d75b 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -92,6 +92,7 @@ config OF_RESOLVE
 config OF_OVERLAY
 	bool "Device Tree overlays"
 	select OF_DYNAMIC
+	select OF_FLATTREE
 	select OF_RESOLVE
 	help
 	  Overlays are a method to dynamically modify part of the kernel's
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 3397d7642958..e3d7f69a8333 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -12,10 +12,12 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_fdt.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/libfdt.h>
 #include <linux/err.h>
 #include <linux/idr.h>
 
@@ -33,7 +35,9 @@ struct fragment {
 
 /**
  * struct overlay_changeset
+ * @id:			changeset identifier
  * @ovcs_list:		list on which we are located
+ * @fdt:		FDT that was unflattened to create @overlay_tree
  * @overlay_tree:	expanded device tree that contains the fragment nodes
  * @count:		count of fragment structures
  * @fragments:		fragment nodes in the overlay expanded device tree
@@ -43,6 +47,7 @@ struct fragment {
 struct overlay_changeset {
 	int id;
 	struct list_head ovcs_list;
+	const void *fdt;
 	struct device_node *overlay_tree;
 	int count;
 	struct fragment *fragments;
@@ -503,7 +508,8 @@ static struct device_node *find_target_node(struct device_node *info_node)
 
 /**
  * init_overlay_changeset() - initialize overlay changeset from overlay tree
- * @ovcs	Overlay changeset to build
+ * @ovcs:	Overlay changeset to build
+ * @fdt:	the FDT that was unflattened to create @tree
  * @tree:	Contains all the overlay fragments and overlay fixup nodes
  *
  * Initialize @ovcs.  Populate @ovcs->fragments with node information from
@@ -514,7 +520,7 @@ static struct device_node *find_target_node(struct device_node *info_node)
  * detected in @tree, or -ENOSPC if idr_alloc() error.
  */
 static int init_overlay_changeset(struct overlay_changeset *ovcs,
-		struct device_node *tree)
+		const void *fdt, struct device_node *tree)
 {
 	struct device_node *node, *overlay_node;
 	struct fragment *fragment;
@@ -535,6 +541,7 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 		pr_debug("%s() tree is not root\n", __func__);
 
 	ovcs->overlay_tree = tree;
+	ovcs->fdt = fdt;
 
 	INIT_LIST_HEAD(&ovcs->ovcs_list);
 
@@ -606,6 +613,7 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 	}
 
 	if (!cnt) {
+		pr_err("no fragments or symbols in overlay\n");
 		ret = -EINVAL;
 		goto err_free_fragments;
 	}
@@ -642,11 +650,24 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
 	}
 	kfree(ovcs->fragments);
 
+	/*
+	 * TODO
+	 *
+	 * would like to: kfree(ovcs->overlay_tree);
+	 * but can not since drivers may have pointers into this data
+	 *
+	 * would like to: kfree(ovcs->fdt);
+	 * but can not since drivers may have pointers into this data
+	 */
+
 	kfree(ovcs);
 }
 
-/**
+/*
+ * internal documentation
+ *
  * of_overlay_apply() - Create and apply an overlay changeset
+ * @fdt:	the FDT that was unflattened to create @tree
  * @tree:	Expanded overlay device tree
  * @ovcs_id:	Pointer to overlay changeset id
  *
@@ -685,21 +706,29 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
  * id is returned to *ovcs_id.
  */
 
-int of_overlay_apply(struct device_node *tree, int *ovcs_id)
+static int of_overlay_apply(const void *fdt, struct device_node *tree,
+		int *ovcs_id)
 {
 	struct overlay_changeset *ovcs;
 	int ret = 0, ret_revert, ret_tmp;
 
-	*ovcs_id = 0;
+	/*
+	 * As of this point, fdt and tree belong to the overlay changeset.
+	 * overlay changeset code is responsible for freeing them.
+	 */
 
 	if (devicetree_corrupt()) {
 		pr_err("devicetree state suspect, refuse to apply overlay\n");
+		kfree(fdt);
+		kfree(tree);
 		ret = -EBUSY;
 		goto out;
 	}
 
 	ovcs = kzalloc(sizeof(*ovcs), GFP_KERNEL);
 	if (!ovcs) {
+		kfree(fdt);
+		kfree(tree);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -709,12 +738,17 @@ int of_overlay_apply(struct device_node *tree, int *ovcs_id)
 
 	ret = of_resolve_phandles(tree);
 	if (ret)
-		goto err_free_overlay_changeset;
+		goto err_free_tree;
 
-	ret = init_overlay_changeset(ovcs, tree);
+	ret = init_overlay_changeset(ovcs, fdt, tree);
 	if (ret)
-		goto err_free_overlay_changeset;
+		goto err_free_tree;
 
+	/*
+	 * after overlay_notify(), ovcs->overlay_tree related pointers may have
+	 * leaked to drivers, so can not kfree() tree, aka ovcs->overlay_tree;
+	 * and can not free fdt, aka ovcs->fdt
+	 */
 	ret = overlay_notify(ovcs, OF_OVERLAY_PRE_APPLY);
 	if (ret) {
 		pr_err("overlay changeset pre-apply notify error %d\n", ret);
@@ -754,6 +788,10 @@ int of_overlay_apply(struct device_node *tree, int *ovcs_id)
 
 	goto out_unlock;
 
+err_free_tree:
+	kfree(fdt);
+	kfree(tree);
+
 err_free_overlay_changeset:
 	free_overlay_changeset(ovcs);
 
@@ -766,7 +804,63 @@ out:
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(of_overlay_apply);
+
+int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
+			 int *ovcs_id)
+{
+	const void *new_fdt;
+	int ret;
+	u32 size;
+	struct device_node *overlay_root;
+
+	*ovcs_id = 0;
+	ret = 0;
+
+	if (overlay_fdt_size < sizeof(struct fdt_header) ||
+	    fdt_check_header(overlay_fdt)) {
+		pr_err("Invalid overlay_fdt header\n");
+		return -EINVAL;
+	}
+
+	size = fdt_totalsize(overlay_fdt);
+	if (overlay_fdt_size < size)
+		return -EINVAL;
+
+	/*
+	 * Must create permanent copy of FDT because of_fdt_unflatten_tree()
+	 * will create pointers to the passed in FDT in the unflattened tree.
+	 */
+	new_fdt = kmemdup(overlay_fdt, size, GFP_KERNEL);
+	if (!new_fdt)
+		return -ENOMEM;
+
+	of_fdt_unflatten_tree(new_fdt, NULL, &overlay_root);
+	if (!overlay_root) {
+		pr_err("unable to unflatten overlay_fdt\n");
+		ret = -EINVAL;
+		goto out_free_new_fdt;
+	}
+
+	ret = of_overlay_apply(new_fdt, overlay_root, ovcs_id);
+	if (ret < 0) {
+		/*
+		 * new_fdt and overlay_root now belong to the overlay
+		 * changeset.
+		 * overlay changeset code is responsible for freeing them.
+		 */
+		goto out;
+	}
+
+	return 0;
+
+
+out_free_new_fdt:
+	kfree(new_fdt);
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_overlay_fdt_apply);
 
 /*
  * Find @np in @tree.
diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c
index 740d19bde601..b2f645187213 100644
--- a/drivers/of/resolver.c
+++ b/drivers/of/resolver.c
@@ -269,17 +269,11 @@ int of_resolve_phandles(struct device_node *overlay)
 		goto out;
 	}
 
-#if 0
-	Temporarily disable check so that old style overlay unittests
-	do not fail when of_resolve_phandles() is moved into
-	of_overlay_apply().
-
 	if (!of_node_check_flag(overlay, OF_DETACHED)) {
 		pr_err("overlay not detached\n");
 		err = -EINVAL;
 		goto out;
 	}
-#endif
 
 	phandle_delta = live_tree_max_phandle() + 1;
 	adjust_overlay_phandles(overlay, phandle_delta);
diff --git a/drivers/of/unittest-data/Makefile b/drivers/of/unittest-data/Makefile
index df697976740a..8fd0ea4b92b0 100644
--- a/drivers/of/unittest-data/Makefile
+++ b/drivers/of/unittest-data/Makefile
@@ -1,8 +1,22 @@
 # SPDX-License-Identifier: GPL-2.0
-DTC_FLAGS_testcases := -Wno-interrupts_property
 obj-y += testcases.dtb.o
 
 obj-$(CONFIG_OF_OVERLAY) += overlay.dtb.o \
+			    overlay_0.dtb.o \
+			    overlay_1.dtb.o \
+			    overlay_2.dtb.o \
+			    overlay_3.dtb.o \
+			    overlay_4.dtb.o \
+			    overlay_5.dtb.o \
+			    overlay_6.dtb.o \
+			    overlay_7.dtb.o \
+			    overlay_8.dtb.o \
+			    overlay_9.dtb.o \
+			    overlay_10.dtb.o \
+			    overlay_11.dtb.o \
+			    overlay_12.dtb.o \
+			    overlay_13.dtb.o \
+			    overlay_15.dtb.o \
 			    overlay_bad_phandle.dtb.o \
 			    overlay_bad_symbol.dtb.o \
 			    overlay_base.dtb.o
@@ -10,10 +24,14 @@ obj-$(CONFIG_OF_OVERLAY) += overlay.dtb.o \
 targets += $(foreach suffix, dtb dtb.S, $(patsubst %.dtb.o,%.$(suffix),$(obj-y)))
 
 # enable creation of __symbols__ node
-DTC_FLAGS_overlay := -@
-DTC_FLAGS_overlay_bad_phandle := -@
-DTC_FLAGS_overlay_bad_symbol := -@
-DTC_FLAGS_overlay_base := -@
+DTC_FLAGS_overlay += -@
+DTC_FLAGS_overlay_bad_phandle += -@
+DTC_FLAGS_overlay_bad_symbol += -@
+DTC_FLAGS_overlay_base += -@
+DTC_FLAGS_testcases += -@
+
+# suppress warnings about intentional errors
+DTC_FLAGS_testcases += -Wno-interrupts_property
 
 .PRECIOUS: \
 	$(obj)/%.dtb.S \
diff --git a/drivers/of/unittest-data/overlay_0.dts b/drivers/of/unittest-data/overlay_0.dts
new file mode 100644
index 000000000000..ac0f9e0fe65f
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_0.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_0 - enable using absolute target path */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/test-unittest0";
+		__overlay__ {
+			status = "okay";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_1.dts b/drivers/of/unittest-data/overlay_1.dts
new file mode 100644
index 000000000000..e92a626e2948
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_1.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_1 - disable using absolute target path */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/test-unittest1";
+		__overlay__ {
+			status = "disabled";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_10.dts b/drivers/of/unittest-data/overlay_10.dts
new file mode 100644
index 000000000000..445925a10cd3
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_10.dts
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_10 */
+	/* overlays 8, 9, 10, 11 application and removal in bad sequence */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus";
+		__overlay__ {
+
+			/* suppress DTC warning */
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			test-unittest10 {
+				compatible = "unittest";
+				status = "okay";
+				reg = <10>;
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				test-unittest101 {
+					compatible = "unittest";
+					status = "okay";
+					reg = <1>;
+				};
+
+			};
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_11.dts b/drivers/of/unittest-data/overlay_11.dts
new file mode 100644
index 000000000000..c1d14f34359e
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_11.dts
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_11 */
+	/* overlays 8, 9, 10, 11 application and removal in bad sequence */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus";
+		__overlay__ {
+
+			/* suppress DTC warning */
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			test-unittest11 {
+				compatible = "unittest";
+				status = "okay";
+				reg = <11>;
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				test-unittest111 {
+					compatible = "unittest";
+					status = "okay";
+					reg = <1>;
+				};
+
+			};
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_12.dts b/drivers/of/unittest-data/overlay_12.dts
new file mode 100644
index 000000000000..ca3441e2cbec
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_12.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_12 - enable using absolute target path (i2c) */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus/test-unittest12";
+		__overlay__ {
+			status = "okay";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_13.dts b/drivers/of/unittest-data/overlay_13.dts
new file mode 100644
index 000000000000..3c30dec63894
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_13.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_13 - disable using absolute target path (i2c) */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus/test-unittest13";
+		__overlay__ {
+			status = "disabled";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_15.dts b/drivers/of/unittest-data/overlay_15.dts
new file mode 100644
index 000000000000..44e44c62b739
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_15.dts
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_15 - mux overlay */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus";
+		__overlay__ {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			test-unittest15 {
+				reg = <11>;
+				compatible = "unittest-i2c-mux";
+				status = "okay";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				i2c@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+
+					test-mux-dev {
+						reg = <32>;
+						compatible = "unittest-i2c-dev";
+						status = "okay";
+					};
+				};
+			};
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_2.dts b/drivers/of/unittest-data/overlay_2.dts
new file mode 100644
index 000000000000..cf1e4245b7ce
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_2.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_2 -  enable using label */
+
+	fragment@0 {
+		target = <&unittest2>;
+		__overlay__ {
+			status = "okay";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_3.dts b/drivers/of/unittest-data/overlay_3.dts
new file mode 100644
index 000000000000..158dc44fc20a
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_3.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_3 - disable using label */
+
+	fragment@0 {
+		target = <&unittest3>;
+		__overlay__ {
+			status = "disabled";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_4.dts b/drivers/of/unittest-data/overlay_4.dts
new file mode 100644
index 000000000000..b4a2e6c6b016
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_4.dts
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_4 - test insertion of a full node */
+
+	fragment@0 {
+		target = <&unittestbus>;
+		__overlay__ {
+
+			/* suppress DTC warning */
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			test-unittest4 {
+				compatible = "unittest";
+				status = "okay";
+				reg = <4>;
+			};
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_5.dts b/drivers/of/unittest-data/overlay_5.dts
new file mode 100644
index 000000000000..02ad25c1f19c
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_5.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_5 - test overlay apply revert */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/test-unittest5";
+		__overlay__ {
+			status = "okay";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_6.dts b/drivers/of/unittest-data/overlay_6.dts
new file mode 100644
index 000000000000..a14e965f5497
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_6.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_6 */
+	/* overlays 6, 7 application and removal in sequence */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/test-unittest6";
+		__overlay__ {
+			status = "okay";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_7.dts b/drivers/of/unittest-data/overlay_7.dts
new file mode 100644
index 000000000000..4bd7e423209c
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_7.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_7 */
+	/* overlays 6, 7 application and removal in sequence */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/test-unittest7";
+		__overlay__ {
+			status = "okay";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_8.dts b/drivers/of/unittest-data/overlay_8.dts
new file mode 100644
index 000000000000..5b21c53945a9
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_8.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_8 */
+	/* overlays 8, 9, 10, 11 application and removal in bad sequence */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/test-unittest8";
+		__overlay__ {
+			status = "okay";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/overlay_9.dts b/drivers/of/unittest-data/overlay_9.dts
new file mode 100644
index 000000000000..20ff055a5349
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_9.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/ {
+	/* overlay_9 */
+	/* overlays 8, 9, 10, 11 application and removal in bad sequence */
+
+	fragment@0 {
+		target-path = "/testcase-data/overlay-node/test-bus/test-unittest8";
+		__overlay__ {
+			property-foo = "bar";
+		};
+	};
+};
diff --git a/drivers/of/unittest-data/tests-overlay.dtsi b/drivers/of/unittest-data/tests-overlay.dtsi
index 7b8001ab9f3a..fa2fb43bccac 100644
--- a/drivers/of/unittest-data/tests-overlay.dtsi
+++ b/drivers/of/unittest-data/tests-overlay.dtsi
@@ -113,218 +113,5 @@
 				};
 			};
 		};
-
-		/* test enable using absolute target path */
-		overlay0 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/test-unittest0";
-				__overlay__ {
-					status = "okay";
-				};
-			};
-		};
-
-		/* test disable using absolute target path */
-		overlay1 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/test-unittest1";
-				__overlay__ {
-					status = "disabled";
-				};
-			};
-		};
-
-		/* test enable using label */
-		overlay2 {
-			fragment@0 {
-				target = <&unittest2>;
-				__overlay__ {
-					status = "okay";
-				};
-			};
-		};
-
-		/* test disable using label */
-		overlay3 {
-			fragment@0 {
-				target = <&unittest3>;
-				__overlay__ {
-					status = "disabled";
-				};
-			};
-		};
-
-		/* test insertion of a full node */
-		overlay4 {
-			fragment@0 {
-				target = <&unittestbus>;
-				__overlay__ {
-
-					/* suppress DTC warning */
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					test-unittest4 {
-						compatible = "unittest";
-						status = "okay";
-						reg = <4>;
-					};
-				};
-			};
-		};
-
-		/* test overlay apply revert */
-		overlay5 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/test-unittest5";
-				__overlay__ {
-					status = "okay";
-				};
-			};
-		};
-
-		/* test overlays application and removal in sequence */
-		overlay6 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/test-unittest6";
-				__overlay__ {
-					status = "okay";
-				};
-			};
-		};
-		overlay7 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/test-unittest7";
-				__overlay__ {
-					status = "okay";
-				};
-			};
-		};
-
-		/* test overlays application and removal in bad sequence */
-		overlay8 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/test-unittest8";
-				__overlay__ {
-					status = "okay";
-				};
-			};
-		};
-		overlay9 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/test-unittest8";
-				__overlay__ {
-					property-foo = "bar";
-				};
-			};
-		};
-
-		overlay10 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus";
-				__overlay__ {
-
-					/* suppress DTC warning */
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					test-unittest10 {
-						compatible = "unittest";
-						status = "okay";
-						reg = <10>;
-
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						test-unittest101 {
-							compatible = "unittest";
-							status = "okay";
-							reg = <1>;
-						};
-
-					};
-				};
-			};
-		};
-
-		overlay11 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus";
-				__overlay__ {
-
-					/* suppress DTC warning */
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					test-unittest11 {
-						compatible = "unittest";
-						status = "okay";
-						reg = <11>;
-
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						test-unittest111 {
-							compatible = "unittest";
-							status = "okay";
-							reg = <1>;
-						};
-
-					};
-				};
-			};
-		};
-
-		/* test enable using absolute target path (i2c) */
-		overlay12 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus/test-unittest12";
-				__overlay__ {
-					status = "okay";
-				};
-			};
-		};
-
-		/* test disable using absolute target path (i2c) */
-		overlay13 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus/test-unittest13";
-				__overlay__ {
-					status = "disabled";
-				};
-			};
-		};
-
-		/* test mux overlay */
-		overlay15 {
-			fragment@0 {
-				target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus";
-				__overlay__ {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					test-unittest15 {
-						reg = <11>;
-						compatible = "unittest-i2c-mux";
-						status = "okay";
-
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						i2c@0 {
-							#address-cells = <1>;
-							#size-cells = <0>;
-							reg = <0>;
-
-							test-mux-dev {
-								reg = <32>;
-								compatible = "unittest-i2c-dev";
-								status = "okay";
-							};
-						};
-					};
-				};
-			};
-		};
-
 	};
 };
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 7a9abaae874d..a23b54780c7d 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -45,6 +45,8 @@ static struct unittest_results {
 	failed; \
 })
 
+static int __init overlay_data_apply(const char *overlay_name, int *overlay_id);
+
 static void __init of_unittest_find_node_by_name(void)
 {
 	struct device_node *np;
@@ -997,8 +999,7 @@ static int __init unittest_data_add(void)
 	}
 
 	/*
-	 * This lock normally encloses of_overlay_apply() as well as
-	 * of_resolve_phandles().
+	 * This lock normally encloses of_resolve_phandles()
 	 */
 	of_overlay_mutex_lock();
 
@@ -1191,12 +1192,12 @@ static int of_unittest_device_exists(int unittest_nr, enum overlay_type ovtype)
 	return 0;
 }
 
-static const char *overlay_path(int nr)
+static const char *overlay_name_from_nr(int nr)
 {
 	static char buf[256];
 
 	snprintf(buf, sizeof(buf) - 1,
-		"/testcase-data/overlay%d", nr);
+		"overlay_%d", nr);
 	buf[sizeof(buf) - 1] = '\0';
 
 	return buf;
@@ -1263,25 +1264,19 @@ static void of_unittest_destroy_tracked_overlays(void)
 	} while (defers > 0);
 }
 
-static int of_unittest_apply_overlay(int overlay_nr, int unittest_nr,
+static int __init of_unittest_apply_overlay(int overlay_nr, int unittest_nr,
 		int *overlay_id)
 {
 	struct device_node *np = NULL;
+	const char *overlay_name;
 	int ret;
 
-	np = of_find_node_by_path(overlay_path(overlay_nr));
-	if (np == NULL) {
-		unittest(0, "could not find overlay node @\"%s\"\n",
-				overlay_path(overlay_nr));
-		ret = -EINVAL;
-		goto out;
-	}
+	overlay_name = overlay_name_from_nr(overlay_nr);
 
-	*overlay_id = 0;
-	ret = of_overlay_apply(np, overlay_id);
-	if (ret < 0) {
-		unittest(0, "could not create overlay from \"%s\"\n",
-				overlay_path(overlay_nr));
+	ret = overlay_data_apply(overlay_name, overlay_id);
+	if (!ret) {
+		unittest(0, "could not apply overlay \"%s\"\n",
+				overlay_name);
 		goto out;
 	}
 	of_unittest_track_overlay(*overlay_id);
@@ -1295,15 +1290,16 @@ out:
 }
 
 /* apply an overlay while checking before and after states */
-static int of_unittest_apply_overlay_check(int overlay_nr, int unittest_nr,
-		int before, int after, enum overlay_type ovtype)
+static int __init of_unittest_apply_overlay_check(int overlay_nr,
+		int unittest_nr, int before, int after,
+		enum overlay_type ovtype)
 {
 	int ret, ovcs_id;
 
 	/* unittest device must not be in before state */
 	if (of_unittest_device_exists(unittest_nr, ovtype) != before) {
-		unittest(0, "overlay @\"%s\" with device @\"%s\" %s\n",
-				overlay_path(overlay_nr),
+		unittest(0, "%s with device @\"%s\" %s\n",
+				overlay_name_from_nr(overlay_nr),
 				unittest_path(unittest_nr, ovtype),
 				!before ? "enabled" : "disabled");
 		return -EINVAL;
@@ -1318,8 +1314,8 @@ static int of_unittest_apply_overlay_check(int overlay_nr, int unittest_nr,
 
 	/* unittest device must be to set to after state */
 	if (of_unittest_device_exists(unittest_nr, ovtype) != after) {
-		unittest(0, "overlay @\"%s\" failed to create @\"%s\" %s\n",
-				overlay_path(overlay_nr),
+		unittest(0, "%s failed to create @\"%s\" %s\n",
+				overlay_name_from_nr(overlay_nr),
 				unittest_path(unittest_nr, ovtype),
 				!after ? "enabled" : "disabled");
 		return -EINVAL;
@@ -1329,7 +1325,7 @@ static int of_unittest_apply_overlay_check(int overlay_nr, int unittest_nr,
 }
 
 /* apply an overlay and then revert it while checking before, after states */
-static int of_unittest_apply_revert_overlay_check(int overlay_nr,
+static int __init of_unittest_apply_revert_overlay_check(int overlay_nr,
 		int unittest_nr, int before, int after,
 		enum overlay_type ovtype)
 {
@@ -1337,8 +1333,8 @@ static int of_unittest_apply_revert_overlay_check(int overlay_nr,
 
 	/* unittest device must be in before state */
 	if (of_unittest_device_exists(unittest_nr, ovtype) != before) {
-		unittest(0, "overlay @\"%s\" with device @\"%s\" %s\n",
-				overlay_path(overlay_nr),
+		unittest(0, "%s with device @\"%s\" %s\n",
+				overlay_name_from_nr(overlay_nr),
 				unittest_path(unittest_nr, ovtype),
 				!before ? "enabled" : "disabled");
 		return -EINVAL;
@@ -1354,8 +1350,8 @@ static int of_unittest_apply_revert_overlay_check(int overlay_nr,
 
 	/* unittest device must be in after state */
 	if (of_unittest_device_exists(unittest_nr, ovtype) != after) {
-		unittest(0, "overlay @\"%s\" failed to create @\"%s\" %s\n",
-				overlay_path(overlay_nr),
+		unittest(0, "%s failed to create @\"%s\" %s\n",
+				overlay_name_from_nr(overlay_nr),
 				unittest_path(unittest_nr, ovtype),
 				!after ? "enabled" : "disabled");
 		return -EINVAL;
@@ -1363,16 +1359,16 @@ static int of_unittest_apply_revert_overlay_check(int overlay_nr,
 
 	ret = of_overlay_remove(&ovcs_id);
 	if (ret != 0) {
-		unittest(0, "overlay @\"%s\" failed to be destroyed @\"%s\"\n",
-				overlay_path(overlay_nr),
+		unittest(0, "%s failed to be destroyed @\"%s\"\n",
+				overlay_name_from_nr(overlay_nr),
 				unittest_path(unittest_nr, ovtype));
 		return ret;
 	}
 
 	/* unittest device must be again in before state */
 	if (of_unittest_device_exists(unittest_nr, PDEV_OVERLAY) != before) {
-		unittest(0, "overlay @\"%s\" with device @\"%s\" %s\n",
-				overlay_path(overlay_nr),
+		unittest(0, "%s with device @\"%s\" %s\n",
+				overlay_name_from_nr(overlay_nr),
 				unittest_path(unittest_nr, ovtype),
 				!before ? "enabled" : "disabled");
 		return -EINVAL;
@@ -1382,7 +1378,7 @@ static int of_unittest_apply_revert_overlay_check(int overlay_nr,
 }
 
 /* test activation of device */
-static void of_unittest_overlay_0(void)
+static void __init of_unittest_overlay_0(void)
 {
 	int ret;
 
@@ -1395,7 +1391,7 @@ static void of_unittest_overlay_0(void)
 }
 
 /* test deactivation of device */
-static void of_unittest_overlay_1(void)
+static void __init of_unittest_overlay_1(void)
 {
 	int ret;
 
@@ -1408,7 +1404,7 @@ static void of_unittest_overlay_1(void)
 }
 
 /* test activation of device */
-static void of_unittest_overlay_2(void)
+static void __init of_unittest_overlay_2(void)
 {
 	int ret;
 
@@ -1421,7 +1417,7 @@ static void of_unittest_overlay_2(void)
 }
 
 /* test deactivation of device */
-static void of_unittest_overlay_3(void)
+static void __init of_unittest_overlay_3(void)
 {
 	int ret;
 
@@ -1434,7 +1430,7 @@ static void of_unittest_overlay_3(void)
 }
 
 /* test activation of a full device node */
-static void of_unittest_overlay_4(void)
+static void __init of_unittest_overlay_4(void)
 {
 	int ret;
 
@@ -1447,7 +1443,7 @@ static void of_unittest_overlay_4(void)
 }
 
 /* test overlay apply/revert sequence */
-static void of_unittest_overlay_5(void)
+static void __init of_unittest_overlay_5(void)
 {
 	int ret;
 
@@ -1460,19 +1456,19 @@ static void of_unittest_overlay_5(void)
 }
 
 /* test overlay application in sequence */
-static void of_unittest_overlay_6(void)
+static void __init of_unittest_overlay_6(void)
 {
-	struct device_node *np;
 	int ret, i, ov_id[2], ovcs_id;
 	int overlay_nr = 6, unittest_nr = 6;
 	int before = 0, after = 1;
+	const char *overlay_name;
 
 	/* unittest device must be in before state */
 	for (i = 0; i < 2; i++) {
 		if (of_unittest_device_exists(unittest_nr + i, PDEV_OVERLAY)
 				!= before) {
-			unittest(0, "overlay @\"%s\" with device @\"%s\" %s\n",
-					overlay_path(overlay_nr + i),
+			unittest(0, "%s with device @\"%s\" %s\n",
+					overlay_name_from_nr(overlay_nr + i),
 					unittest_path(unittest_nr + i,
 						PDEV_OVERLAY),
 					!before ? "enabled" : "disabled");
@@ -1483,18 +1479,12 @@ static void of_unittest_overlay_6(void)
 	/* apply the overlays */
 	for (i = 0; i < 2; i++) {
 
-		np = of_find_node_by_path(overlay_path(overlay_nr + i));
-		if (np == NULL) {
-			unittest(0, "could not find overlay node @\"%s\"\n",
-					overlay_path(overlay_nr + i));
-			return;
-		}
+		overlay_name = overlay_name_from_nr(overlay_nr + i);
 
-		ovcs_id = 0;
-		ret = of_overlay_apply(np, &ovcs_id);
-		if (ret < 0)  {
-			unittest(0, "could not create overlay from \"%s\"\n",
-					overlay_path(overlay_nr + i));
+		ret = overlay_data_apply(overlay_name, &ovcs_id);
+		if (!ret)  {
+			unittest(0, "could not apply overlay \"%s\"\n",
+					overlay_name);
 			return;
 		}
 		ov_id[i] = ovcs_id;
@@ -1506,7 +1496,7 @@ static void of_unittest_overlay_6(void)
 		if (of_unittest_device_exists(unittest_nr + i, PDEV_OVERLAY)
 				!= after) {
 			unittest(0, "overlay @\"%s\" failed @\"%s\" %s\n",
-					overlay_path(overlay_nr + i),
+					overlay_name_from_nr(overlay_nr + i),
 					unittest_path(unittest_nr + i,
 						PDEV_OVERLAY),
 					!after ? "enabled" : "disabled");
@@ -1518,8 +1508,8 @@ static void of_unittest_overlay_6(void)
 		ovcs_id = ov_id[i];
 		ret = of_overlay_remove(&ovcs_id);
 		if (ret != 0) {
-			unittest(0, "overlay @\"%s\" failed destroy @\"%s\"\n",
-					overlay_path(overlay_nr + i),
+			unittest(0, "%s failed destroy @\"%s\"\n",
+					overlay_name_from_nr(overlay_nr + i),
 					unittest_path(unittest_nr + i,
 						PDEV_OVERLAY));
 			return;
@@ -1531,8 +1521,8 @@ static void of_unittest_overlay_6(void)
 		/* unittest device must be again in before state */
 		if (of_unittest_device_exists(unittest_nr + i, PDEV_OVERLAY)
 				!= before) {
-			unittest(0, "overlay @\"%s\" with device @\"%s\" %s\n",
-					overlay_path(overlay_nr + i),
+			unittest(0, "%s with device @\"%s\" %s\n",
+					overlay_name_from_nr(overlay_nr + i),
 					unittest_path(unittest_nr + i,
 						PDEV_OVERLAY),
 					!before ? "enabled" : "disabled");
@@ -1544,29 +1534,23 @@ static void of_unittest_overlay_6(void)
 }
 
 /* test overlay application in sequence */
-static void of_unittest_overlay_8(void)
+static void __init of_unittest_overlay_8(void)
 {
-	struct device_node *np;
 	int ret, i, ov_id[2], ovcs_id;
 	int overlay_nr = 8, unittest_nr = 8;
+	const char *overlay_name;
 
 	/* we don't care about device state in this test */
 
 	/* apply the overlays */
 	for (i = 0; i < 2; i++) {
 
-		np = of_find_node_by_path(overlay_path(overlay_nr + i));
-		if (np == NULL) {
-			unittest(0, "could not find overlay node @\"%s\"\n",
-					overlay_path(overlay_nr + i));
-			return;
-		}
+		overlay_name = overlay_name_from_nr(overlay_nr + i);
 
-		ovcs_id = 0;
-		ret = of_overlay_apply(np, &ovcs_id);
+		ret = overlay_data_apply(overlay_name, &ovcs_id);
 		if (ret < 0)  {
-			unittest(0, "could not create overlay from \"%s\"\n",
-					overlay_path(overlay_nr + i));
+			unittest(0, "could not apply overlay \"%s\"\n",
+					overlay_name);
 			return;
 		}
 		ov_id[i] = ovcs_id;
@@ -1577,8 +1561,8 @@ static void of_unittest_overlay_8(void)
 	ovcs_id = ov_id[0];
 	ret = of_overlay_remove(&ovcs_id);
 	if (ret == 0) {
-		unittest(0, "overlay @\"%s\" was destroyed @\"%s\"\n",
-				overlay_path(overlay_nr + 0),
+		unittest(0, "%s was destroyed @\"%s\"\n",
+				overlay_name_from_nr(overlay_nr + 0),
 				unittest_path(unittest_nr,
 					PDEV_OVERLAY));
 		return;
@@ -1589,8 +1573,8 @@ static void of_unittest_overlay_8(void)
 		ovcs_id = ov_id[i];
 		ret = of_overlay_remove(&ovcs_id);
 		if (ret != 0) {
-			unittest(0, "overlay @\"%s\" not destroyed @\"%s\"\n",
-					overlay_path(overlay_nr + i),
+			unittest(0, "%s not destroyed @\"%s\"\n",
+					overlay_name_from_nr(overlay_nr + i),
 					unittest_path(unittest_nr,
 						PDEV_OVERLAY));
 			return;
@@ -1602,7 +1586,7 @@ static void of_unittest_overlay_8(void)
 }
 
 /* test insertion of a bus with parent devices */
-static void of_unittest_overlay_10(void)
+static void __init of_unittest_overlay_10(void)
 {
 	int ret;
 	char *child_path;
@@ -1625,7 +1609,7 @@ static void of_unittest_overlay_10(void)
 }
 
 /* test insertion of a bus with parent devices (and revert) */
-static void of_unittest_overlay_11(void)
+static void __init of_unittest_overlay_11(void)
 {
 	int ret;
 
@@ -1891,7 +1875,7 @@ static void of_unittest_overlay_i2c_cleanup(void)
 	i2c_del_driver(&unittest_i2c_dev_driver);
 }
 
-static void of_unittest_overlay_i2c_12(void)
+static void __init of_unittest_overlay_i2c_12(void)
 {
 	int ret;
 
@@ -1904,7 +1888,7 @@ static void of_unittest_overlay_i2c_12(void)
 }
 
 /* test deactivation of device */
-static void of_unittest_overlay_i2c_13(void)
+static void __init of_unittest_overlay_i2c_13(void)
 {
 	int ret;
 
@@ -1921,7 +1905,7 @@ static void of_unittest_overlay_i2c_14(void)
 {
 }
 
-static void of_unittest_overlay_i2c_15(void)
+static void __init of_unittest_overlay_i2c_15(void)
 {
 	int ret;
 
@@ -2023,23 +2007,38 @@ static inline void __init of_unittest_overlay(void) { }
 	extern uint8_t __dtb_##name##_begin[]; \
 	extern uint8_t __dtb_##name##_end[]
 
-#define OVERLAY_INFO(name, expected) \
-{	.dtb_begin	 = __dtb_##name##_begin, \
-	.dtb_end	 = __dtb_##name##_end, \
-	.expected_result = expected, \
+#define OVERLAY_INFO(overlay_name, expected)             \
+{	.dtb_begin       = __dtb_##overlay_name##_begin, \
+	.dtb_end         = __dtb_##overlay_name##_end,   \
+	.expected_result = expected,                     \
+	.name            = #overlay_name,                \
 }
 
 struct overlay_info {
-	uint8_t		   *dtb_begin;
-	uint8_t		   *dtb_end;
-	void		   *data;
-	struct device_node *np_overlay;
-	int		   expected_result;
-	int		   overlay_id;
+	uint8_t		*dtb_begin;
+	uint8_t		*dtb_end;
+	int		expected_result;
+	int		overlay_id;
+	char		*name;
 };
 
 OVERLAY_INFO_EXTERN(overlay_base);
 OVERLAY_INFO_EXTERN(overlay);
+OVERLAY_INFO_EXTERN(overlay_0);
+OVERLAY_INFO_EXTERN(overlay_1);
+OVERLAY_INFO_EXTERN(overlay_2);
+OVERLAY_INFO_EXTERN(overlay_3);
+OVERLAY_INFO_EXTERN(overlay_4);
+OVERLAY_INFO_EXTERN(overlay_5);
+OVERLAY_INFO_EXTERN(overlay_6);
+OVERLAY_INFO_EXTERN(overlay_7);
+OVERLAY_INFO_EXTERN(overlay_8);
+OVERLAY_INFO_EXTERN(overlay_9);
+OVERLAY_INFO_EXTERN(overlay_10);
+OVERLAY_INFO_EXTERN(overlay_11);
+OVERLAY_INFO_EXTERN(overlay_12);
+OVERLAY_INFO_EXTERN(overlay_13);
+OVERLAY_INFO_EXTERN(overlay_15);
 OVERLAY_INFO_EXTERN(overlay_bad_phandle);
 OVERLAY_INFO_EXTERN(overlay_bad_symbol);
 
@@ -2047,6 +2046,21 @@ OVERLAY_INFO_EXTERN(overlay_bad_symbol);
 static struct overlay_info overlays[] = {
 	OVERLAY_INFO(overlay_base, -9999),
 	OVERLAY_INFO(overlay, 0),
+	OVERLAY_INFO(overlay_0, 0),
+	OVERLAY_INFO(overlay_1, 0),
+	OVERLAY_INFO(overlay_2, 0),
+	OVERLAY_INFO(overlay_3, 0),
+	OVERLAY_INFO(overlay_4, 0),
+	OVERLAY_INFO(overlay_5, 0),
+	OVERLAY_INFO(overlay_6, 0),
+	OVERLAY_INFO(overlay_7, 0),
+	OVERLAY_INFO(overlay_8, 0),
+	OVERLAY_INFO(overlay_9, 0),
+	OVERLAY_INFO(overlay_10, 0),
+	OVERLAY_INFO(overlay_11, 0),
+	OVERLAY_INFO(overlay_12, 0),
+	OVERLAY_INFO(overlay_13, 0),
+	OVERLAY_INFO(overlay_15, 0),
 	OVERLAY_INFO(overlay_bad_phandle, -EINVAL),
 	OVERLAY_INFO(overlay_bad_symbol, -EINVAL),
 	{}
@@ -2077,6 +2091,7 @@ void __init unittest_unflatten_overlay_base(void)
 {
 	struct overlay_info *info;
 	u32 data_size;
+	void *new_fdt;
 	u32 size;
 
 	info = &overlays[0];
@@ -2098,17 +2113,16 @@ void __init unittest_unflatten_overlay_base(void)
 		return;
 	}
 
-	info->data = dt_alloc_memory(size, roundup_pow_of_two(FDT_V17_SIZE));
-	if (!info->data) {
+	new_fdt = dt_alloc_memory(size, roundup_pow_of_two(FDT_V17_SIZE));
+	if (!new_fdt) {
 		pr_err("alloc for dtb 'overlay_base' failed");
 		return;
 	}
 
-	memcpy(info->data, info->dtb_begin, size);
+	memcpy(new_fdt, info->dtb_begin, size);
 
-	__unflatten_device_tree(info->data, NULL, &info->np_overlay,
+	__unflatten_device_tree(new_fdt, NULL, &overlay_base_root,
 				dt_alloc_memory, true);
-	overlay_base_root = info->np_overlay;
 }
 
 /*
@@ -2122,73 +2136,44 @@ void __init unittest_unflatten_overlay_base(void)
  *
  * Return 0 on unexpected error.
  */
-static int __init overlay_data_add(int onum)
+static int __init overlay_data_apply(const char *overlay_name, int *overlay_id)
 {
 	struct overlay_info *info;
+	int found = 0;
 	int k;
 	int ret;
 	u32 size;
-	u32 size_from_header;
 
-	for (k = 0, info = overlays; info; info++, k++) {
-		if (k == onum)
+	for (k = 0, info = overlays; info && info->name; info++, k++) {
+		if (!strcmp(overlay_name, info->name)) {
+			found = 1;
 			break;
+		}
 	}
-	if (onum > k)
+	if (!found) {
+		pr_err("no overlay data for %s\n", overlay_name);
 		return 0;
+	}
 
 	size = info->dtb_end - info->dtb_begin;
 	if (!size) {
-		pr_err("no overlay to attach, %d\n", onum);
+		pr_err("no overlay data for %s\n", overlay_name);
 		ret = 0;
 	}
 
-	size_from_header = fdt_totalsize(info->dtb_begin);
-	if (size_from_header != size) {
-		pr_err("overlay header totalsize != actual size, %d", onum);
-		return 0;
-	}
-
-	/*
-	 * Must create permanent copy of FDT because of_fdt_unflatten_tree()
-	 * will create pointers to the passed in FDT in the EDT.
-	 */
-	info->data = kmemdup(info->dtb_begin, size, GFP_KERNEL);
-	if (!info->data) {
-		pr_err("unable to allocate memory for data, %d\n", onum);
-		return 0;
-	}
-
-	of_fdt_unflatten_tree(info->data, NULL, &info->np_overlay);
-	if (!info->np_overlay) {
-		pr_err("unable to unflatten overlay, %d\n", onum);
-		ret = 0;
-		goto out_free_data;
-	}
-
-	info->overlay_id = 0;
-	ret = of_overlay_apply(info->np_overlay, &info->overlay_id);
-	if (ret < 0) {
-		pr_err("of_overlay_apply() (ret=%d), %d\n", ret, onum);
-		goto out_free_np_overlay;
-	}
-
-	pr_debug("__dtb_overlay_begin applied, overlay id %d\n", ret);
-
-	goto out;
-
-out_free_np_overlay:
-	/*
-	 * info->np_overlay is the unflattened device tree
-	 * It has not been spliced into the live tree.
-	 */
-
-	/* todo: function to free unflattened device tree */
+	ret = of_overlay_fdt_apply(info->dtb_begin, size, &info->overlay_id);
+	if (overlay_id)
+		*overlay_id = info->overlay_id;
+	if (ret < 0)
+		goto out;
 
-out_free_data:
-	kfree(info->data);
+	pr_debug("%s applied\n", overlay_name);
 
 out:
+	if (ret != info->expected_result)
+		pr_err("of_overlay_fdt_apply() expected %d, ret=%d, %s\n",
+		       info->expected_result, ret, overlay_name);
+
 	return (ret == info->expected_result);
 }
 
@@ -2290,18 +2275,29 @@ static __init void of_unittest_overlay_high_level(void)
 		__of_attach_node_sysfs(np);
 
 	if (of_symbols) {
+		struct property *new_prop;
 		for_each_property_of_node(overlay_base_symbols, prop) {
-			ret = __of_add_property(of_symbols, prop);
+
+			new_prop = __of_prop_dup(prop, GFP_KERNEL);
+			if (!new_prop) {
+				unittest(0, "__of_prop_dup() of '%s' from overlay_base node __symbols__",
+					 prop->name);
+				goto err_unlock;
+			}
+			ret = __of_add_property(of_symbols, new_prop);
 			if (ret) {
-				unittest(0,
-					 "duplicate property '%s' in overlay_base node __symbols__",
+				if (!strcmp(new_prop->name, "name")) {
+					/* auto-generated by unflatten */
+					ret = 0;
+					continue;
+				}
+				unittest(0, "duplicate property '%s' in overlay_base node __symbols__",
 					 prop->name);
 				goto err_unlock;
 			}
-			ret = __of_add_property_sysfs(of_symbols, prop);
+			ret = __of_add_property_sysfs(of_symbols, new_prop);
 			if (ret) {
-				unittest(0,
-					 "unable to add property '%s' in overlay_base node __symbols__ to sysfs",
+				unittest(0, "unable to add property '%s' in overlay_base node __symbols__ to sysfs",
 					 prop->name);
 				goto err_unlock;
 			}
@@ -2313,13 +2309,13 @@ static __init void of_unittest_overlay_high_level(void)
 
 	/* now do the normal overlay usage test */
 
-	unittest(overlay_data_add(1),
+	unittest(overlay_data_apply("overlay", NULL),
 		 "Adding overlay 'overlay' failed\n");
 
-	unittest(overlay_data_add(2),
+	unittest(overlay_data_apply("overlay_bad_phandle", NULL),
 		 "Adding overlay 'overlay_bad_phandle' failed\n");
 
-	unittest(overlay_data_add(3),
+	unittest(overlay_data_apply("overlay_bad_symbol", NULL),
 		 "Adding overlay 'overlay_bad_symbol' failed\n");
 
 	return;
diff --git a/include/linux/of.h b/include/linux/of.h
index da1ee95241c1..ebf22dd0860c 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1359,8 +1359,8 @@ struct of_overlay_notify_data {
 
 #ifdef CONFIG_OF_OVERLAY
 
-/* ID based overlays; the API for external users */
-int of_overlay_apply(struct device_node *tree, int *ovcs_id);
+int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
+			 int *ovcs_id);
 int of_overlay_remove(int *ovcs_id);
 int of_overlay_remove_all(void);
 
@@ -1369,7 +1369,7 @@ int of_overlay_notifier_unregister(struct notifier_block *nb);
 
 #else
 
-static inline int of_overlay_apply(struct device_node *tree, int *ovcs_id)
+static inline int of_overlay_fdt_apply(void *overlay_fdt, int *ovcs_id)
 {
 	return -ENOTSUPP;
 }
-- 
cgit v1.2.3


From a446ae2c6e6555048301f2339cfd97b8eed6d0b7 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin
Date: Tue, 6 Mar 2018 12:28:56 +0000
Subject: drm/i915: add query uAPI

There are a number of information that are readable from hardware
registers and that we would like to make accessible to userspace. One
particular example is the topology of the execution units (how are
execution units grouped in subslices and slices and also which ones
have been fused off for die recovery).

At the moment the GET_PARAM ioctl covers some basic needs, but
generally is only able to return a single value for each defined
parameter. This is a bit problematic with topology descriptions which
are array/maps of available units.

This change introduces a new ioctl that can deal with requests to fill
structures of potentially variable lengths. The user is expected fill
a query with length fields set at 0 on the first call, the kernel then
sets the length fields to the their expected values. A second call to
the kernel with length fields at their expected values will trigger a
copy of the data to the pointed memory locations.

The scope of this uAPI is only to provide information to userspace,
not to allow configuration of the device.

v2: Simplify dispatcher code iteration (Tvrtko)
    Tweak uapi drm_i915_query_item structure (Tvrtko)

v3: Rename pad fields into flags (Chris)
    Return error on flags field != 0 (Chris)
    Only copy length back to userspace in drm_i915_query_item (Chris)

v4: Use array of functions instead of switch (Chris)

v5: More comments in uapi (Tvrtko)
    Return query item errors in length field (All)

v6: Tweak uapi comments style to match the coding style (Lionel)

v7: Add i915_query.h (Joonas)

v8: (Lionel) Change the behavior of the item iterator to report
    invalid queries into the query item rather than stopping the
    iteration. This enables userspace applications to query newer
    items on older kernels and only have failure on the items that are
    not supported.

v9: Edit copyright headers (Joonas)

v10: Typos & comments in uapi (Joonas)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-6-lionel.g.landwerlin@intel.com
---
 drivers/gpu/drm/i915/Makefile     |  1 +
 drivers/gpu/drm/i915/i915_drv.c   |  2 ++
 drivers/gpu/drm/i915/i915_query.c | 50 +++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_query.h | 15 ++++++++++++
 include/uapi/drm/i915_drm.h       | 46 ++++++++++++++++++++++++++++++++---
 5 files changed, 111 insertions(+), 3 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/i915_query.c
 create mode 100644 drivers/gpu/drm/i915/i915_query.h

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 1bd9bc5b8c5c..4eee91a3a236 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -69,6 +69,7 @@ i915-y += i915_cmd_parser.o \
 	  i915_gem_timeline.o \
 	  i915_gem_userptr.o \
 	  i915_gemfs.o \
+	  i915_query.o \
 	  i915_request.o \
 	  i915_trace_points.o \
 	  i915_vma.o \
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c594ff5e57d0..d7c4de45644d 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -49,6 +49,7 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "i915_pmu.h"
+#include "i915_query.h"
 #include "i915_vgpu.h"
 #include "intel_drv.h"
 #include "intel_uc.h"
@@ -2832,6 +2833,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_PERF_OPEN, i915_perf_open_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_PERF_ADD_CONFIG, i915_perf_add_config_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_PERF_REMOVE_CONFIG, i915_perf_remove_config_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_QUERY, i915_query_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 
 static struct drm_driver driver = {
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
new file mode 100644
index 000000000000..5582e6c3234a
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -0,0 +1,50 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "i915_query.h"
+#include <uapi/drm/i915_drm.h>
+
+static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
+					struct drm_i915_query_item *query_item) = {
+};
+
+int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_query *args = data;
+	struct drm_i915_query_item __user *user_item_ptr =
+		u64_to_user_ptr(args->items_ptr);
+	u32 i;
+
+	if (args->flags != 0)
+		return -EINVAL;
+
+	for (i = 0; i < args->num_items; i++, user_item_ptr++) {
+		struct drm_i915_query_item item;
+		u64 func_idx;
+		int ret;
+
+		if (copy_from_user(&item, user_item_ptr, sizeof(item)))
+			return -EFAULT;
+
+		if (item.query_id == 0)
+			return -EINVAL;
+
+		func_idx = item.query_id - 1;
+
+		if (func_idx < ARRAY_SIZE(i915_query_funcs))
+			ret = i915_query_funcs[func_idx](dev_priv, &item);
+		else
+			ret = -EINVAL;
+
+		/* Only write the length back to userspace if they differ. */
+		if (ret != item.length && put_user(ret, &user_item_ptr->length))
+			return -EFAULT;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_query.h b/drivers/gpu/drm/i915/i915_query.h
new file mode 100644
index 000000000000..31dcef181f63
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_query.h
@@ -0,0 +1,15 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#ifndef _I915_QUERY_H_
+#define _I915_QUERY_H_
+
+struct drm_device;
+struct drm_file;
+
+int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+
+#endif
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 29fa48e4755d..eedd5a23a944 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -318,6 +318,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_PERF_OPEN		0x36
 #define DRM_I915_PERF_ADD_CONFIG	0x37
 #define DRM_I915_PERF_REMOVE_CONFIG	0x38
+#define DRM_I915_QUERY			0x39
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -375,6 +376,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
 #define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
 #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
+#define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -1606,15 +1608,53 @@ struct drm_i915_perf_oa_config {
 	__u32 n_flex_regs;
 
 	/*
-	 * These fields are pointers to tuples of u32 values (register
-	 * address, value). For example the expected length of the buffer
-	 * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 * These fields are pointers to tuples of u32 values (register address,
+	 * value). For example the expected length of the buffer pointed by
+	 * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
 	 */
 	__u64 mux_regs_ptr;
 	__u64 boolean_regs_ptr;
 	__u64 flex_regs_ptr;
 };
 
+struct drm_i915_query_item {
+	__u64 query_id;
+
+	/*
+	 * When set to zero by userspace, this is filled with the size of the
+	 * data to be written at the data_ptr pointer. The kernel sets this
+	 * value to a negative value to signal an error on a particular query
+	 * item.
+	 */
+	__s32 length;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Data will be written at the location pointed by data_ptr when the
+	 * value of length matches the length of the data to be written by the
+	 * kernel.
+	 */
+	__u64 data_ptr;
+};
+
+struct drm_i915_query {
+	__u32 num_items;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * This points to an array of num_items drm_i915_query_item structures.
+	 */
+	__u64 items_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif
-- 
cgit v1.2.3


From c822e059185585f79b2007b1d2cafacf4264e610 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin
Date: Tue, 6 Mar 2018 12:28:57 +0000
Subject: drm/i915: expose rcs topology through query uAPI

With the introduction of asymmetric slices in CNL, we cannot rely on
the previous SUBSLICE_MASK getparam to tell userspace what subslices
are available. Here we introduce a more detailed way of querying the
Gen's GPU topology that doesn't aggregate numbers.

This is essential for monitoring parts of the GPU with the OA unit,
because counters need to be normalized to the number of
EUs/subslices/slices. The current aggregated numbers like EU_TOTAL do
not gives us sufficient information.

The Mesa series making use of this API is :

    https://patchwork.freedesktop.org/series/38795/

As a bonus we can draw representations of the GPU :

    https://imgur.com/a/vuqpa

v2: Rename uapi struct s/_mask/_info/ (Tvrtko)
    Report max_slice/subslice/eus_per_subslice rather than strides (Tvrtko)
    Add uapi macros to read data from *_info structs (Tvrtko)

v3: Use !!(v & DRM_I915_BIT()) for uapi macros instead of custom shifts (Tvrtko)

v4: factorize query item writting (Tvrtko)
    tweak uapi struct/define names (Tvrtko)

v5: Replace ALIGN() macro (Chris)

v6: Updated uapi comments (Tvrtko)
    Moved flags != 0 checks into vfuncs (Tvrtko)

v7: Use access_ok() before copying anything, to avoid overflows (Chris)
    Switch BUG_ON() to GEM_WARN_ON() (Tvrtko)

v8: Tweak uapi comments style to match the coding style (Lionel)

v9: Fix error in comment about computation of enabled subslice (Tvrtko)

v10: Fix/update comments in uAPI (Sagar)

v11: Drop drm_i915_query_(slice|subslice|eu)_info in favor of a single
     drm_i915_query_topology_info (Joonas)

v12: Add subslice_stride/eu_stride in drm_i915_query_topology_info (Joonas)

v13: Fix comment in uAPI (Joonas)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-7-lionel.g.landwerlin@intel.com
---
 drivers/gpu/drm/i915/i915_query.c | 75 +++++++++++++++++++++++++++++++++++++++
 include/uapi/drm/i915_drm.h       | 62 ++++++++++++++++++++++++++++++++
 2 files changed, 137 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 5582e6c3234a..3ace929dd90f 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -8,8 +8,83 @@
 #include "i915_query.h"
 #include <uapi/drm/i915_drm.h>
 
+static int query_topology_info(struct drm_i915_private *dev_priv,
+			       struct drm_i915_query_item *query_item)
+{
+	const struct sseu_dev_info *sseu = &INTEL_INFO(dev_priv)->sseu;
+	struct drm_i915_query_topology_info topo;
+	u32 slice_length, subslice_length, eu_length, total_length;
+
+	if (query_item->flags != 0)
+		return -EINVAL;
+
+	if (sseu->max_slices == 0)
+		return -ENODEV;
+
+	BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
+
+	slice_length = sizeof(sseu->slice_mask);
+	subslice_length = sseu->max_slices *
+		DIV_ROUND_UP(sseu->max_subslices,
+			     sizeof(sseu->subslice_mask[0]) * BITS_PER_BYTE);
+	eu_length = sseu->max_slices * sseu->max_subslices *
+		DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE);
+
+	total_length = sizeof(topo) + slice_length + subslice_length + eu_length;
+
+	if (query_item->length == 0)
+		return total_length;
+
+	if (query_item->length < total_length)
+		return -EINVAL;
+
+	if (copy_from_user(&topo, u64_to_user_ptr(query_item->data_ptr),
+			   sizeof(topo)))
+		return -EFAULT;
+
+	if (topo.flags != 0)
+		return -EINVAL;
+
+	if (!access_ok(VERIFY_WRITE, u64_to_user_ptr(query_item->data_ptr),
+		       total_length))
+		return -EFAULT;
+
+	memset(&topo, 0, sizeof(topo));
+	topo.max_slices = sseu->max_slices;
+	topo.max_subslices = sseu->max_subslices;
+	topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
+
+	topo.subslice_offset = slice_length;
+	topo.subslice_stride = DIV_ROUND_UP(sseu->max_subslices, BITS_PER_BYTE);
+	topo.eu_offset = slice_length + subslice_length;
+	topo.eu_stride =
+		DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE);
+
+	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
+			   &topo, sizeof(topo)))
+		return -EFAULT;
+
+	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr + sizeof(topo)),
+			   &sseu->slice_mask, slice_length))
+		return -EFAULT;
+
+	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr +
+					   sizeof(topo) + slice_length),
+			   sseu->subslice_mask, subslice_length))
+		return -EFAULT;
+
+	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr +
+					   sizeof(topo) +
+					   slice_length + subslice_length),
+			   sseu->eu_mask, eu_length))
+		return -EFAULT;
+
+	return total_length;
+}
+
 static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
 					struct drm_i915_query_item *query_item) = {
+	query_topology_info,
 };
 
 int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index eedd5a23a944..7f5634ce8e88 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1619,6 +1619,7 @@ struct drm_i915_perf_oa_config {
 
 struct drm_i915_query_item {
 	__u64 query_id;
+#define DRM_I915_QUERY_TOPOLOGY_INFO    1
 
 	/*
 	 * When set to zero by userspace, this is filled with the size of the
@@ -1655,6 +1656,67 @@ struct drm_i915_query {
 	__u64 items_ptr;
 };
 
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO :
+ *
+ * data: contains the 3 pieces of information :
+ *
+ * - the slice mask with one bit per slice telling whether a slice is
+ *   available. The availability of slice X can be queried with the following
+ *   formula :
+ *
+ *           (data[X / 8] >> (X % 8)) & 1
+ *
+ * - the subslice mask for each slice with one bit per subslice telling
+ *   whether a subslice is available. The availability of subslice Y in slice
+ *   X can be queried with the following formula :
+ *
+ *           (data[subslice_offset +
+ *                 X * subslice_stride +
+ *                 Y / 8] >> (Y % 8)) & 1
+ *
+ * - the EU mask for each subslice in each slice with one bit per EU telling
+ *   whether an EU is available. The availability of EU Z in subslice Y in
+ *   slice X can be queried with the following formula :
+ *
+ *           (data[eu_offset +
+ *                 (X * max_subslices + Y) * eu_stride +
+ *                 Z / 8] >> (Z % 8)) & 1
+ */
+struct drm_i915_query_topology_info {
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u16 flags;
+
+	__u16 max_slices;
+	__u16 max_subslices;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Offset in data[] at which the subslice masks are stored.
+	 */
+	__u16 subslice_offset;
+
+	/*
+	 * Stride at which each of the subslice masks for each slice are
+	 * stored.
+	 */
+	__u16 subslice_stride;
+
+	/*
+	 * Offset in data[] at which the EU masks are stored.
+	 */
+	__u16 eu_offset;
+
+	/*
+	 * Stride at which each of the EU masks for each subslice are stored.
+	 */
+	__u16 eu_stride;
+
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
-- 
cgit v1.2.3


From 81f5ec025514865fb930d3a665a10a339b113da8 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Thu, 22 Feb 2018 09:23:44 +0100
Subject: drm/ttm: move ttm_tt defines into ttm_tt.h

Let's stop mangling everything in a single header and create one header
per object instead.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Acked-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_tt.c    |   6 -
 include/drm/ttm/ttm_bo_driver.h | 237 +---------------------------------
 include/drm/ttm/ttm_tt.h        | 272 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 273 insertions(+), 242 deletions(-)
 create mode 100644 include/drm/ttm/ttm_tt.h

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 0ee3b8f11605..8e0b525cda00 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -31,17 +31,11 @@
 #define pr_fmt(fmt) "[TTM] " fmt
 
 #include <linux/sched.h>
-#include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/shmem_fs.h>
 #include <linux/file.h>
-#include <linux/swap.h>
-#include <linux/slab.h>
-#include <linux/export.h>
 #include <drm/drm_cache.h>
-#include <drm/ttm/ttm_module.h>
 #include <drm/ttm/ttm_bo_driver.h>
-#include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_page_alloc.h>
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 4312b5326f0b..f8e2515b401f 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -42,111 +42,10 @@
 #include "ttm_memory.h"
 #include "ttm_module.h"
 #include "ttm_placement.h"
+#include "ttm_tt.h"
 
 #define TTM_MAX_BO_PRIORITY	4U
 
-struct ttm_backend_func {
-	/**
-	 * struct ttm_backend_func member bind
-	 *
-	 * @ttm: Pointer to a struct ttm_tt.
-	 * @bo_mem: Pointer to a struct ttm_mem_reg describing the
-	 * memory type and location for binding.
-	 *
-	 * Bind the backend pages into the aperture in the location
-	 * indicated by @bo_mem. This function should be able to handle
-	 * differences between aperture and system page sizes.
-	 */
-	int (*bind) (struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem);
-
-	/**
-	 * struct ttm_backend_func member unbind
-	 *
-	 * @ttm: Pointer to a struct ttm_tt.
-	 *
-	 * Unbind previously bound backend pages. This function should be
-	 * able to handle differences between aperture and system page sizes.
-	 */
-	int (*unbind) (struct ttm_tt *ttm);
-
-	/**
-	 * struct ttm_backend_func member destroy
-	 *
-	 * @ttm: Pointer to a struct ttm_tt.
-	 *
-	 * Destroy the backend. This will be call back from ttm_tt_destroy so
-	 * don't call ttm_tt_destroy from the callback or infinite loop.
-	 */
-	void (*destroy) (struct ttm_tt *ttm);
-};
-
-#define TTM_PAGE_FLAG_WRITE           (1 << 3)
-#define TTM_PAGE_FLAG_SWAPPED         (1 << 4)
-#define TTM_PAGE_FLAG_PERSISTENT_SWAP (1 << 5)
-#define TTM_PAGE_FLAG_ZERO_ALLOC      (1 << 6)
-#define TTM_PAGE_FLAG_DMA32           (1 << 7)
-#define TTM_PAGE_FLAG_SG              (1 << 8)
-#define TTM_PAGE_FLAG_NO_RETRY	      (1 << 9)
-
-enum ttm_caching_state {
-	tt_uncached,
-	tt_wc,
-	tt_cached
-};
-
-/**
- * struct ttm_tt
- *
- * @bdev: Pointer to a struct ttm_bo_device.
- * @func: Pointer to a struct ttm_backend_func that describes
- * the backend methods.
- * pointer.
- * @pages: Array of pages backing the data.
- * @num_pages: Number of pages in the page array.
- * @bdev: Pointer to the current struct ttm_bo_device.
- * @be: Pointer to the ttm backend.
- * @swap_storage: Pointer to shmem struct file for swap storage.
- * @caching_state: The current caching state of the pages.
- * @state: The current binding state of the pages.
- *
- * This is a structure holding the pages, caching- and aperture binding
- * status for a buffer object that isn't backed by fixed (VRAM / AGP)
- * memory.
- */
-
-struct ttm_tt {
-	struct ttm_bo_device *bdev;
-	struct ttm_backend_func *func;
-	struct page **pages;
-	uint32_t page_flags;
-	unsigned long num_pages;
-	struct sg_table *sg; /* for SG objects via dma-buf */
-	struct file *swap_storage;
-	enum ttm_caching_state caching_state;
-	enum {
-		tt_bound,
-		tt_unbound,
-		tt_unpopulated,
-	} state;
-};
-
-/**
- * struct ttm_dma_tt
- *
- * @ttm: Base ttm_tt struct.
- * @dma_address: The DMA (bus) addresses of the pages
- * @pages_list: used by some page allocation backend
- *
- * This is a structure holding the pages, caching- and aperture binding
- * status for a buffer object that isn't backed by fixed (VRAM / AGP)
- * memory.
- */
-struct ttm_dma_tt {
-	struct ttm_tt ttm;
-	dma_addr_t *dma_address;
-	struct list_head pages_list;
-};
-
 #define TTM_MEMTYPE_FLAG_FIXED         (1 << 0)	/* Fixed (on-card) PCI memory */
 #define TTM_MEMTYPE_FLAG_MAPPABLE      (1 << 1)	/* Memory mappable */
 #define TTM_MEMTYPE_FLAG_CMA           (1 << 3)	/* Can't map aperture */
@@ -610,117 +509,6 @@ ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask)
 	return *old;
 }
 
-/**
- * ttm_tt_create
- *
- * @bo: pointer to a struct ttm_buffer_object
- * @zero_alloc: true if allocated pages needs to be zeroed
- *
- * Make sure we have a TTM structure allocated for the given BO.
- * No pages are actually allocated.
- */
-int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc);
-
-/**
- * ttm_tt_init
- *
- * @ttm: The struct ttm_tt.
- * @bdev: pointer to a struct ttm_bo_device:
- * @size: Size of the data needed backing.
- * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
- *
- * Create a struct ttm_tt to back data with system memory pages.
- * No pages are actually allocated.
- * Returns:
- * NULL: Out of memory.
- */
-int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags);
-int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		    unsigned long size, uint32_t page_flags);
-
-/**
- * ttm_tt_fini
- *
- * @ttm: the ttm_tt structure.
- *
- * Free memory of ttm_tt structure
- */
-void ttm_tt_fini(struct ttm_tt *ttm);
-void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma);
-
-/**
- * ttm_ttm_bind:
- *
- * @ttm: The struct ttm_tt containing backing pages.
- * @bo_mem: The struct ttm_mem_reg identifying the binding location.
- *
- * Bind the pages of @ttm to an aperture location identified by @bo_mem
- */
-int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem,
-		struct ttm_operation_ctx *ctx);
-
-/**
- * ttm_ttm_destroy:
- *
- * @ttm: The struct ttm_tt.
- *
- * Unbind, unpopulate and destroy common struct ttm_tt.
- */
-void ttm_tt_destroy(struct ttm_tt *ttm);
-
-/**
- * ttm_ttm_unbind:
- *
- * @ttm: The struct ttm_tt.
- *
- * Unbind a struct ttm_tt.
- */
-void ttm_tt_unbind(struct ttm_tt *ttm);
-
-/**
- * ttm_tt_swapin:
- *
- * @ttm: The struct ttm_tt.
- *
- * Swap in a previously swap out ttm_tt.
- */
-int ttm_tt_swapin(struct ttm_tt *ttm);
-
-/**
- * ttm_tt_set_placement_caching:
- *
- * @ttm A struct ttm_tt the backing pages of which will change caching policy.
- * @placement: Flag indicating the desired caching policy.
- *
- * This function will change caching policy of any default kernel mappings of
- * the pages backing @ttm. If changing from cached to uncached or
- * write-combined,
- * all CPU caches will first be flushed to make sure the data of the pages
- * hit RAM. This function may be very costly as it involves global TLB
- * and cache flushes and potential page splitting / combining.
- */
-int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement);
-int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage);
-
-/**
- * ttm_tt_populate - allocate pages for a ttm
- *
- * @ttm: Pointer to the ttm_tt structure
- *
- * Calls the driver method to allocate pages for a ttm
- */
-int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
-
-/**
- * ttm_tt_unpopulate - free pages from a ttm
- *
- * @ttm: Pointer to the ttm_tt structure
- *
- * Calls the driver method to free all pages from a ttm
- */
-void ttm_tt_unpopulate(struct ttm_tt *ttm);
-
 /*
  * ttm_bo.c
  */
@@ -1074,27 +862,4 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
 
 extern const struct ttm_mem_type_manager_func ttm_bo_manager_func;
 
-#if IS_ENABLED(CONFIG_AGP)
-#include <linux/agp_backend.h>
-
-/**
- * ttm_agp_tt_create
- *
- * @bdev: Pointer to a struct ttm_bo_device.
- * @bridge: The agp bridge this device is sitting on.
- * @size: Size of the data needed backing.
- * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
- *
- *
- * Create a TTM backend that uses the indicated AGP bridge as an aperture
- * for TT memory. This function uses the linux agpgart interface to
- * bind and unbind memory backing a ttm_tt.
- */
-struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
-				 struct agp_bridge_data *bridge,
-				 unsigned long size, uint32_t page_flags);
-int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
-void ttm_agp_tt_unpopulate(struct ttm_tt *ttm);
-#endif
-
 #endif
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
new file mode 100644
index 000000000000..9c78556b488e
--- /dev/null
+++ b/include/drm/ttm/ttm_tt.h
@@ -0,0 +1,272 @@
+/**************************************************************************
+ *
+ * Copyright (c) 2006-2009 Vmware, Inc., Palo Alto, CA., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+#ifndef _TTM_TT_H_
+#define _TTM_TT_H_
+
+#include <linux/types.h>
+
+struct ttm_tt;
+struct ttm_mem_reg;
+struct ttm_buffer_object;
+struct ttm_operation_ctx;
+
+#define TTM_PAGE_FLAG_WRITE           (1 << 3)
+#define TTM_PAGE_FLAG_SWAPPED         (1 << 4)
+#define TTM_PAGE_FLAG_PERSISTENT_SWAP (1 << 5)
+#define TTM_PAGE_FLAG_ZERO_ALLOC      (1 << 6)
+#define TTM_PAGE_FLAG_DMA32           (1 << 7)
+#define TTM_PAGE_FLAG_SG              (1 << 8)
+#define TTM_PAGE_FLAG_NO_RETRY	      (1 << 9)
+
+enum ttm_caching_state {
+	tt_uncached,
+	tt_wc,
+	tt_cached
+};
+
+struct ttm_backend_func {
+	/**
+	 * struct ttm_backend_func member bind
+	 *
+	 * @ttm: Pointer to a struct ttm_tt.
+	 * @bo_mem: Pointer to a struct ttm_mem_reg describing the
+	 * memory type and location for binding.
+	 *
+	 * Bind the backend pages into the aperture in the location
+	 * indicated by @bo_mem. This function should be able to handle
+	 * differences between aperture and system page sizes.
+	 */
+	int (*bind) (struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem);
+
+	/**
+	 * struct ttm_backend_func member unbind
+	 *
+	 * @ttm: Pointer to a struct ttm_tt.
+	 *
+	 * Unbind previously bound backend pages. This function should be
+	 * able to handle differences between aperture and system page sizes.
+	 */
+	int (*unbind) (struct ttm_tt *ttm);
+
+	/**
+	 * struct ttm_backend_func member destroy
+	 *
+	 * @ttm: Pointer to a struct ttm_tt.
+	 *
+	 * Destroy the backend. This will be call back from ttm_tt_destroy so
+	 * don't call ttm_tt_destroy from the callback or infinite loop.
+	 */
+	void (*destroy) (struct ttm_tt *ttm);
+};
+
+/**
+ * struct ttm_tt
+ *
+ * @bdev: Pointer to a struct ttm_bo_device.
+ * @func: Pointer to a struct ttm_backend_func that describes
+ * the backend methods.
+ * pointer.
+ * @pages: Array of pages backing the data.
+ * @num_pages: Number of pages in the page array.
+ * @bdev: Pointer to the current struct ttm_bo_device.
+ * @be: Pointer to the ttm backend.
+ * @swap_storage: Pointer to shmem struct file for swap storage.
+ * @caching_state: The current caching state of the pages.
+ * @state: The current binding state of the pages.
+ *
+ * This is a structure holding the pages, caching- and aperture binding
+ * status for a buffer object that isn't backed by fixed (VRAM / AGP)
+ * memory.
+ */
+struct ttm_tt {
+	struct ttm_bo_device *bdev;
+	struct ttm_backend_func *func;
+	struct page **pages;
+	uint32_t page_flags;
+	unsigned long num_pages;
+	struct sg_table *sg; /* for SG objects via dma-buf */
+	struct file *swap_storage;
+	enum ttm_caching_state caching_state;
+	enum {
+		tt_bound,
+		tt_unbound,
+		tt_unpopulated,
+	} state;
+};
+
+/**
+ * struct ttm_dma_tt
+ *
+ * @ttm: Base ttm_tt struct.
+ * @dma_address: The DMA (bus) addresses of the pages
+ * @pages_list: used by some page allocation backend
+ *
+ * This is a structure holding the pages, caching- and aperture binding
+ * status for a buffer object that isn't backed by fixed (VRAM / AGP)
+ * memory.
+ */
+struct ttm_dma_tt {
+	struct ttm_tt ttm;
+	dma_addr_t *dma_address;
+	struct list_head pages_list;
+};
+
+/**
+ * ttm_tt_create
+ *
+ * @bo: pointer to a struct ttm_buffer_object
+ * @zero_alloc: true if allocated pages needs to be zeroed
+ *
+ * Make sure we have a TTM structure allocated for the given BO.
+ * No pages are actually allocated.
+ */
+int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc);
+
+/**
+ * ttm_tt_init
+ *
+ * @ttm: The struct ttm_tt.
+ * @bdev: pointer to a struct ttm_bo_device:
+ * @size: Size of the data needed backing.
+ * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
+ *
+ * Create a struct ttm_tt to back data with system memory pages.
+ * No pages are actually allocated.
+ * Returns:
+ * NULL: Out of memory.
+ */
+int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
+		unsigned long size, uint32_t page_flags);
+int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
+		    unsigned long size, uint32_t page_flags);
+
+/**
+ * ttm_tt_fini
+ *
+ * @ttm: the ttm_tt structure.
+ *
+ * Free memory of ttm_tt structure
+ */
+void ttm_tt_fini(struct ttm_tt *ttm);
+void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma);
+
+/**
+ * ttm_ttm_bind:
+ *
+ * @ttm: The struct ttm_tt containing backing pages.
+ * @bo_mem: The struct ttm_mem_reg identifying the binding location.
+ *
+ * Bind the pages of @ttm to an aperture location identified by @bo_mem
+ */
+int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem,
+		struct ttm_operation_ctx *ctx);
+
+/**
+ * ttm_ttm_destroy:
+ *
+ * @ttm: The struct ttm_tt.
+ *
+ * Unbind, unpopulate and destroy common struct ttm_tt.
+ */
+void ttm_tt_destroy(struct ttm_tt *ttm);
+
+/**
+ * ttm_ttm_unbind:
+ *
+ * @ttm: The struct ttm_tt.
+ *
+ * Unbind a struct ttm_tt.
+ */
+void ttm_tt_unbind(struct ttm_tt *ttm);
+
+/**
+ * ttm_tt_swapin:
+ *
+ * @ttm: The struct ttm_tt.
+ *
+ * Swap in a previously swap out ttm_tt.
+ */
+int ttm_tt_swapin(struct ttm_tt *ttm);
+
+/**
+ * ttm_tt_set_placement_caching:
+ *
+ * @ttm A struct ttm_tt the backing pages of which will change caching policy.
+ * @placement: Flag indicating the desired caching policy.
+ *
+ * This function will change caching policy of any default kernel mappings of
+ * the pages backing @ttm. If changing from cached to uncached or
+ * write-combined,
+ * all CPU caches will first be flushed to make sure the data of the pages
+ * hit RAM. This function may be very costly as it involves global TLB
+ * and cache flushes and potential page splitting / combining.
+ */
+int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement);
+int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage);
+
+/**
+ * ttm_tt_populate - allocate pages for a ttm
+ *
+ * @ttm: Pointer to the ttm_tt structure
+ *
+ * Calls the driver method to allocate pages for a ttm
+ */
+int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
+
+/**
+ * ttm_tt_unpopulate - free pages from a ttm
+ *
+ * @ttm: Pointer to the ttm_tt structure
+ *
+ * Calls the driver method to free all pages from a ttm
+ */
+void ttm_tt_unpopulate(struct ttm_tt *ttm);
+
+#if IS_ENABLED(CONFIG_AGP)
+#include <linux/agp_backend.h>
+
+/**
+ * ttm_agp_tt_create
+ *
+ * @bdev: Pointer to a struct ttm_bo_device.
+ * @bridge: The agp bridge this device is sitting on.
+ * @size: Size of the data needed backing.
+ * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
+ *
+ *
+ * Create a TTM backend that uses the indicated AGP bridge as an aperture
+ * for TT memory. This function uses the linux agpgart interface to
+ * bind and unbind memory backing a ttm_tt.
+ */
+struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
+				 struct agp_bridge_data *bridge,
+				 unsigned long size, uint32_t page_flags);
+int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
+void ttm_agp_tt_unpopulate(struct ttm_tt *ttm);
+#endif
+
+#endif
-- 
cgit v1.2.3


From 75a57669cbc881032c60615a31bfc6bfab4c813c Mon Sep 17 00:00:00 2001
From: Christian König
Date: Fri, 23 Feb 2018 15:12:00 +0100
Subject: drm/ttm: add ttm_sg_tt_init

This allows drivers to only allocate dma addresses, but not a page
array.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_tt.c | 54 ++++++++++++++++++++++++++++++++++++--------
 include/drm/ttm/ttm_tt.h     |  2 ++
 2 files changed, 47 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 8e0b525cda00..971133106ec2 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -108,6 +108,16 @@ static int ttm_dma_tt_alloc_page_directory(struct ttm_dma_tt *ttm)
 	return 0;
 }
 
+static int ttm_sg_tt_alloc_page_directory(struct ttm_dma_tt *ttm)
+{
+	ttm->dma_address = kvmalloc_array(ttm->ttm.num_pages,
+					  sizeof(*ttm->dma_address),
+					  GFP_KERNEL | __GFP_ZERO);
+	if (!ttm->dma_address)
+		return -ENOMEM;
+	return 0;
+}
+
 #ifdef CONFIG_X86
 static inline int ttm_tt_set_page_caching(struct page *p,
 					  enum ttm_caching_state c_old,
@@ -227,8 +237,8 @@ void ttm_tt_destroy(struct ttm_tt *ttm)
 	ttm->func->destroy(ttm);
 }
 
-int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags)
+void ttm_tt_init_fields(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
+			unsigned long size, uint32_t page_flags)
 {
 	ttm->bdev = bdev;
 	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -236,6 +246,12 @@ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
 	ttm->page_flags = page_flags;
 	ttm->state = tt_unpopulated;
 	ttm->swap_storage = NULL;
+}
+
+int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
+		unsigned long size, uint32_t page_flags)
+{
+	ttm_tt_init_fields(ttm, bdev, size, page_flags);
 
 	if (ttm_tt_alloc_page_directory(ttm)) {
 		ttm_tt_destroy(ttm);
@@ -258,12 +274,7 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 
-	ttm->bdev = bdev;
-	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	ttm->caching_state = tt_cached;
-	ttm->page_flags = page_flags;
-	ttm->state = tt_unpopulated;
-	ttm->swap_storage = NULL;
+	ttm_tt_init_fields(ttm, bdev, size, page_flags);
 
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
 	if (ttm_dma_tt_alloc_page_directory(ttm_dma)) {
@@ -275,11 +286,36 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_dma_tt_init);
 
+int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
+		   unsigned long size, uint32_t page_flags)
+{
+	struct ttm_tt *ttm = &ttm_dma->ttm;
+	int ret;
+
+	ttm_tt_init_fields(ttm, bdev, size, page_flags);
+
+	INIT_LIST_HEAD(&ttm_dma->pages_list);
+	if (page_flags & TTM_PAGE_FLAG_SG)
+		ret = ttm_sg_tt_alloc_page_directory(ttm_dma);
+	else
+		ret = ttm_dma_tt_alloc_page_directory(ttm_dma);
+	if (ret) {
+		ttm_tt_destroy(ttm);
+		pr_err("Failed allocating page table\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ttm_sg_tt_init);
+
 void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 
-	kvfree(ttm->pages);
+	if (ttm->pages)
+		kvfree(ttm->pages);
+	else
+		kvfree(ttm_dma->dma_address);
 	ttm->pages = NULL;
 	ttm_dma->dma_address = NULL;
 }
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 9c78556b488e..1cf316a4257c 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -163,6 +163,8 @@ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
 		unsigned long size, uint32_t page_flags);
 int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
 		    unsigned long size, uint32_t page_flags);
+int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
+		   unsigned long size, uint32_t page_flags);
 
 /**
  * ttm_tt_fini
-- 
cgit v1.2.3


From 1e09b05386f32efbebb798cf0341eca4b424c960 Mon Sep 17 00:00:00 2001
From: Hawking Zhang
Date: Thu, 8 Mar 2018 18:01:24 +0800
Subject: drm/amdgpu: query vram type from atombios

The vram type for dGPU is stored in umc_info while sys mem type
for APU is stored in integratedsysteminfo

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c | 95 +++++++++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h |  1 +
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c            |  4 +-
 include/uapi/drm/amdgpu_drm.h                    |  1 +
 4 files changed, 94 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index ff8efd0f8fd5..a0f48cb9b8f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -114,6 +114,9 @@ union igp_info {
 	struct atom_integrated_system_info_v1_11 v11;
 };
 
+union umc_info {
+	struct atom_umc_info_v3_1 v31;
+};
 /*
  * Return vram width from integrated system info table, if available,
  * or 0 if not.
@@ -143,6 +146,94 @@ int amdgpu_atomfirmware_get_vram_width(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int convert_atom_mem_type_to_vram_type (struct amdgpu_device *adev,
+					       int atom_mem_type)
+{
+	int vram_type;
+
+	if (adev->flags & AMD_IS_APU) {
+		switch (atom_mem_type) {
+		case Ddr2MemType:
+		case LpDdr2MemType:
+			vram_type = AMDGPU_VRAM_TYPE_DDR2;
+			break;
+		case Ddr3MemType:
+		case LpDdr3MemType:
+			vram_type = AMDGPU_VRAM_TYPE_DDR3;
+			break;
+		case Ddr4MemType:
+		case LpDdr4MemType:
+			vram_type = AMDGPU_VRAM_TYPE_DDR4;
+			break;
+		default:
+			vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
+			break;
+		}
+	} else {
+		switch (atom_mem_type) {
+		case ATOM_DGPU_VRAM_TYPE_GDDR5:
+			vram_type = AMDGPU_VRAM_TYPE_GDDR5;
+			break;
+		case ATOM_DGPU_VRAM_TYPE_HBM:
+			vram_type = AMDGPU_VRAM_TYPE_HBM;
+			break;
+		default:
+			vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
+			break;
+		}
+	}
+
+	return vram_type;
+}
+/*
+ * Return vram type from either integrated system info table
+ * or umc info table, if available, or 0 (TYPE_UNKNOWN) if not
+ */
+int amdgpu_atomfirmware_get_vram_type(struct amdgpu_device *adev)
+{
+	struct amdgpu_mode_info *mode_info = &adev->mode_info;
+	int index;
+	u16 data_offset, size;
+	union igp_info *igp_info;
+	union umc_info *umc_info;
+	u8 frev, crev;
+	u8 mem_type;
+
+	if (adev->flags & AMD_IS_APU)
+		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+						    integratedsysteminfo);
+	else
+		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+						    umc_info);
+	if (amdgpu_atom_parse_data_header(mode_info->atom_context,
+					  index, &size,
+					  &frev, &crev, &data_offset)) {
+		if (adev->flags & AMD_IS_APU) {
+			igp_info = (union igp_info *)
+				(mode_info->atom_context->bios + data_offset);
+			switch (crev) {
+			case 11:
+				mem_type = igp_info->v11.memorytype;
+				return convert_atom_mem_type_to_vram_type(adev, mem_type);
+			default:
+				return 0;
+			}
+		} else {
+			umc_info = (union umc_info *)
+				(mode_info->atom_context->bios + data_offset);
+			switch (crev) {
+			case 1:
+				mem_type = umc_info->v31.vram_type;
+				return convert_atom_mem_type_to_vram_type(adev, mem_type);
+			default:
+				return 0;
+			}
+		}
+	}
+
+	return 0;
+}
+
 union firmware_info {
 	struct atom_firmware_info_v3_1 v31;
 };
@@ -151,10 +242,6 @@ union smu_info {
 	struct atom_smu_info_v3_1 v31;
 };
 
-union umc_info {
-	struct atom_umc_info_v3_1 v31;
-};
-
 int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev)
 {
 	struct amdgpu_mode_info *mode_info = &adev->mode_info;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index 288b97e54347..7689c961c4ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -28,6 +28,7 @@ bool amdgpu_atomfirmware_gpu_supports_virtualization(struct amdgpu_device *adev)
 void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_vram_width(struct amdgpu_device *adev);
+int amdgpu_atomfirmware_get_vram_type(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 67cd1fe17649..ceab14f16795 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -836,9 +836,9 @@ static int gmc_v9_0_sw_init(void *handle)
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
+	adev->gmc.vram_type = amdgpu_atomfirmware_get_vram_type(adev);
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
-		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
 		if (adev->rev_id == 0x0 || adev->rev_id == 0x1) {
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
 		} else {
@@ -849,8 +849,6 @@ static int gmc_v9_0_sw_init(void *handle)
 		}
 		break;
 	case CHIP_VEGA10:
-		/* XXX Don't know how to get VRAM type yet. */
-		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
 		/*
 		 * To fulfill 4-level page support,
 		 * vm size is 256TB (48bit), maximum size of Vega10,
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 1816bd8200d1..528f6d041e90 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -806,6 +806,7 @@ struct drm_amdgpu_info_firmware {
 #define AMDGPU_VRAM_TYPE_GDDR5 5
 #define AMDGPU_VRAM_TYPE_HBM   6
 #define AMDGPU_VRAM_TYPE_DDR3  7
+#define AMDGPU_VRAM_TYPE_DDR4  8
 
 struct drm_amdgpu_info_device {
 	/** PCI Device ID */
-- 
cgit v1.2.3


From 5d95109815493e273a2ef9010df0939aa3cfe10f Mon Sep 17 00:00:00 2001
From: Christian König
Date: Tue, 20 Feb 2018 15:35:21 +0100
Subject: drm/ttm: add ttm_bo_pipeline_gutting

Allows us to gut a BO of it's backing store when the driver says that it
isn't needed any more.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c      | 15 ++++++++++++---
 drivers/gpu/drm/ttm/ttm_bo_util.c | 24 ++++++++++++++++++++++++
 include/drm/ttm/ttm_bo_driver.h   |  9 +++++++++
 3 files changed, 45 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ad142a92eb80..98e06f8bf23b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -622,14 +622,23 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 
 	reservation_object_assert_held(bo->resv);
 
+	placement.num_placement = 0;
+	placement.num_busy_placement = 0;
+	bdev->driver->evict_flags(bo, &placement);
+
+	if (!placement.num_placement && !placement.num_busy_placement) {
+		ret = ttm_bo_pipeline_gutting(bo);
+		if (ret)
+			return ret;
+
+		return ttm_tt_create(bo, false);
+	}
+
 	evict_mem = bo->mem;
 	evict_mem.mm_node = NULL;
 	evict_mem.bus.io_reserved_vm = false;
 	evict_mem.bus.io_reserved_count = 0;
 
-	placement.num_placement = 0;
-	placement.num_busy_placement = 0;
-	bdev->driver->evict_flags(bo, &placement);
 	ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx);
 	if (ret) {
 		if (ret != -ERESTARTSYS) {
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 6d6a3f46143b..1f730b3f18e5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -801,3 +801,27 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_pipeline_move);
+
+int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
+{
+	struct ttm_buffer_object *ghost;
+	int ret;
+
+	ret = ttm_buffer_object_transfer(bo, &ghost);
+	if (ret)
+		return ret;
+
+	ret = reservation_object_copy_fences(ghost->resv, bo->resv);
+	/* Last resort, wait for the BO to be idle when we are OOM */
+	if (ret)
+		ttm_bo_wait(bo, false, false);
+
+	memset(&bo->mem, 0, sizeof(bo->mem));
+	bo->mem.mem_type = TTM_PL_SYSTEM;
+	bo->ttm = NULL;
+
+	ttm_bo_unreserve(ghost);
+	ttm_bo_unref(&ghost);
+
+	return 0;
+}
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index f8e2515b401f..39cd6b086d3a 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -849,6 +849,15 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			 struct dma_fence *fence, bool evict,
 			 struct ttm_mem_reg *new_mem);
 
+/**
+ * ttm_bo_pipeline_gutting.
+ *
+ * @bo: A pointer to a struct ttm_buffer_object.
+ *
+ * Pipelined gutting a BO of it's backing store.
+ */
+int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo);
+
 /**
  * ttm_io_prot
  *
-- 
cgit v1.2.3


From dde5da2379319c08ceb2295467df6e60a3cf5da1 Mon Sep 17 00:00:00 2001
From: Christian König
Date: Thu, 22 Feb 2018 10:18:14 +0100
Subject: drm/ttm: add bo as parameter to the ttm_tt_create callback

Instead of calculating the size in bytes just to recalculate the number
of pages from it pass the BO directly to the function.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c     |  8 ++++----
 drivers/gpu/drm/ast/ast_ttm.c               |  6 +++---
 drivers/gpu/drm/bochs/bochs_mm.c            |  5 ++---
 drivers/gpu/drm/cirrus/cirrus_ttm.c         |  6 +++---
 drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c |  5 ++---
 drivers/gpu/drm/mgag200/mgag200_ttm.c       |  6 +++---
 drivers/gpu/drm/nouveau/nouveau_bo.c        | 10 ++++------
 drivers/gpu/drm/nouveau/nouveau_sgdma.c     |  7 +++----
 drivers/gpu/drm/nouveau/nouveau_ttm.h       |  4 ++--
 drivers/gpu/drm/qxl/qxl_ttm.c               |  8 ++++----
 drivers/gpu/drm/radeon/radeon_ttm.c         | 12 ++++++------
 drivers/gpu/drm/ttm/ttm_agp_backend.c       |  6 +++---
 drivers/gpu/drm/ttm/ttm_tt.c                | 29 ++++++++++++++---------------
 drivers/gpu/drm/virtio/virtgpu_ttm.c        |  7 +++----
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c      | 10 +++++-----
 drivers/staging/vboxvideo/vbox_ttm.c        |  5 ++---
 include/drm/ttm/ttm_bo_driver.h             |  6 ++----
 include/drm/ttm/ttm_tt.h                    | 22 ++++++++++------------
 18 files changed, 75 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 7187457b20fb..72e533493292 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -982,20 +982,20 @@ static struct ttm_backend_func amdgpu_backend_func = {
 	.destroy = &amdgpu_ttm_backend_destroy,
 };
 
-static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_bo_device *bdev,
-				    unsigned long size, uint32_t page_flags)
+static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
+					   uint32_t page_flags)
 {
 	struct amdgpu_device *adev;
 	struct amdgpu_ttm_tt *gtt;
 
-	adev = amdgpu_ttm_adev(bdev);
+	adev = amdgpu_ttm_adev(bo->bdev);
 
 	gtt = kzalloc(sizeof(struct amdgpu_ttm_tt), GFP_KERNEL);
 	if (gtt == NULL) {
 		return NULL;
 	}
 	gtt->ttm.ttm.func = &amdgpu_backend_func;
-	if (ttm_sg_tt_init(&gtt->ttm, bdev, size, page_flags)) {
+	if (ttm_sg_tt_init(&gtt->ttm, bo, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 211224f6bdd3..fe354ebf374d 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -199,8 +199,8 @@ static struct ttm_backend_func ast_tt_backend_func = {
 };
 
 
-static struct ttm_tt *ast_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags)
+static struct ttm_tt *ast_ttm_tt_create(struct ttm_buffer_object *bo,
+					uint32_t page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -208,7 +208,7 @@ static struct ttm_tt *ast_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &ast_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags)) {
+	if (ttm_tt_init(tt, bo, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index 18b95329f631..39cd08416773 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -176,8 +176,7 @@ static struct ttm_backend_func bochs_tt_backend_func = {
 	.destroy = &bochs_ttm_backend_destroy,
 };
 
-static struct ttm_tt *bochs_ttm_tt_create(struct ttm_bo_device *bdev,
-					  unsigned long size,
+static struct ttm_tt *bochs_ttm_tt_create(struct ttm_buffer_object *bo,
 					  uint32_t page_flags)
 {
 	struct ttm_tt *tt;
@@ -186,7 +185,7 @@ static struct ttm_tt *bochs_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &bochs_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags)) {
+	if (ttm_tt_init(tt, bo, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 6cd0233b3bf8..f21953243790 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -199,8 +199,8 @@ static struct ttm_backend_func cirrus_tt_backend_func = {
 };
 
 
-static struct ttm_tt *cirrus_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags)
+static struct ttm_tt *cirrus_ttm_tt_create(struct ttm_buffer_object *bo,
+					   uint32_t page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -208,7 +208,7 @@ static struct ttm_tt *cirrus_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &cirrus_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags)) {
+	if (ttm_tt_init(tt, bo, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
index 8dfffdbb6b07..4871025f7573 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
@@ -200,8 +200,7 @@ static struct ttm_backend_func hibmc_tt_backend_func = {
 	.destroy = &hibmc_ttm_backend_destroy,
 };
 
-static struct ttm_tt *hibmc_ttm_tt_create(struct ttm_bo_device *bdev,
-					  unsigned long size,
+static struct ttm_tt *hibmc_ttm_tt_create(struct ttm_buffer_object *bo,
 					  u32 page_flags)
 {
 	struct ttm_tt *tt;
@@ -213,7 +212,7 @@ static struct ttm_tt *hibmc_ttm_tt_create(struct ttm_bo_device *bdev,
 		return NULL;
 	}
 	tt->func = &hibmc_tt_backend_func;
-	ret = ttm_tt_init(tt, bdev, size, page_flags);
+	ret = ttm_tt_init(tt, bo, page_flags);
 	if (ret) {
 		DRM_ERROR("failed to initialize ttm_tt: %d\n", ret);
 		kfree(tt);
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 69beb2046008..05570f0de4d7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -199,8 +199,8 @@ static struct ttm_backend_func mgag200_tt_backend_func = {
 };
 
 
-static struct ttm_tt *mgag200_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags)
+static struct ttm_tt *mgag200_ttm_tt_create(struct ttm_buffer_object *bo,
+					    uint32_t page_flags)
 {
 	struct ttm_tt *tt;
 
@@ -208,7 +208,7 @@ static struct ttm_tt *mgag200_ttm_tt_create(struct ttm_bo_device *bdev,
 	if (tt == NULL)
 		return NULL;
 	tt->func = &mgag200_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags)) {
+	if (ttm_tt_init(tt, bo, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 49cc8dfcb141..6f402c4f2bdd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -604,19 +604,17 @@ nouveau_bo_wr32(struct nouveau_bo *nvbo, unsigned index, u32 val)
 }
 
 static struct ttm_tt *
-nouveau_ttm_tt_create(struct ttm_bo_device *bdev, unsigned long size,
-		      uint32_t page_flags)
+nouveau_ttm_tt_create(struct ttm_buffer_object *bo, uint32_t page_flags)
 {
 #if IS_ENABLED(CONFIG_AGP)
-	struct nouveau_drm *drm = nouveau_bdev(bdev);
+	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 
 	if (drm->agp.bridge) {
-		return ttm_agp_tt_create(bdev, drm->agp.bridge, size,
-					 page_flags);
+		return ttm_agp_tt_create(bo, drm->agp.bridge, page_flags);
 	}
 #endif
 
-	return nouveau_sgdma_create_ttm(bdev, size, page_flags);
+	return nouveau_sgdma_create_ttm(bo, page_flags);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index 87b030437f4d..8ebdc74cc0ad 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -82,10 +82,9 @@ static struct ttm_backend_func nv50_sgdma_backend = {
 };
 
 struct ttm_tt *
-nouveau_sgdma_create_ttm(struct ttm_bo_device *bdev,
-			 unsigned long size, uint32_t page_flags)
+nouveau_sgdma_create_ttm(struct ttm_buffer_object *bo, uint32_t page_flags)
 {
-	struct nouveau_drm *drm = nouveau_bdev(bdev);
+	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_sgdma_be *nvbe;
 
 	nvbe = kzalloc(sizeof(*nvbe), GFP_KERNEL);
@@ -97,7 +96,7 @@ nouveau_sgdma_create_ttm(struct ttm_bo_device *bdev,
 	else
 		nvbe->ttm.ttm.func = &nv50_sgdma_backend;
 
-	if (ttm_dma_tt_init(&nvbe->ttm, bdev, size, page_flags))
+	if (ttm_dma_tt_init(&nvbe->ttm, bo, page_flags))
 		/*
 		 * A failing ttm_dma_tt_init() will call ttm_tt_destroy()
 		 * and thus our nouveau_sgdma_destroy() hook, so we don't need
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.h b/drivers/gpu/drm/nouveau/nouveau_ttm.h
index 64e484ee5ef1..89929ad8c7cd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.h
@@ -12,8 +12,8 @@ extern const struct ttm_mem_type_manager_func nouveau_vram_manager;
 extern const struct ttm_mem_type_manager_func nouveau_gart_manager;
 extern const struct ttm_mem_type_manager_func nv04_gart_manager;
 
-struct ttm_tt *nouveau_sgdma_create_ttm(struct ttm_bo_device *,
-					unsigned long size, u32 page_flags);
+struct ttm_tt *nouveau_sgdma_create_ttm(struct ttm_buffer_object *bo,
+					u32 page_flags);
 
 int  nouveau_ttm_init(struct nouveau_drm *drm);
 void nouveau_ttm_fini(struct nouveau_drm *drm);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 2ad70eb96207..ee2340e31f06 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -291,19 +291,19 @@ static struct ttm_backend_func qxl_backend_func = {
 	.destroy = &qxl_ttm_backend_destroy,
 };
 
-static struct ttm_tt *qxl_ttm_tt_create(struct ttm_bo_device *bdev,
-					unsigned long size, uint32_t page_flags)
+static struct ttm_tt *qxl_ttm_tt_create(struct ttm_buffer_object *bo,
+					uint32_t page_flags)
 {
 	struct qxl_device *qdev;
 	struct qxl_ttm_tt *gtt;
 
-	qdev = qxl_get_qdev(bdev);
+	qdev = qxl_get_qdev(bo->bdev);
 	gtt = kzalloc(sizeof(struct qxl_ttm_tt), GFP_KERNEL);
 	if (gtt == NULL)
 		return NULL;
 	gtt->ttm.ttm.func = &qxl_backend_func;
 	gtt->qdev = qdev;
-	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags)) {
+	if (ttm_dma_tt_init(&gtt->ttm, bo, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 009f55a2bbf9..8689fcca051c 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -686,17 +686,17 @@ static struct ttm_backend_func radeon_backend_func = {
 	.destroy = &radeon_ttm_backend_destroy,
 };
 
-static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
-				    unsigned long size, uint32_t page_flags)
+static struct ttm_tt *radeon_ttm_tt_create(struct ttm_buffer_object *bo,
+					   uint32_t page_flags)
 {
 	struct radeon_device *rdev;
 	struct radeon_ttm_tt *gtt;
 
-	rdev = radeon_get_rdev(bdev);
+	rdev = radeon_get_rdev(bo->bdev);
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
-		return ttm_agp_tt_create(bdev, rdev->ddev->agp->bridge,
-					 size, page_flags);
+		return ttm_agp_tt_create(bo, rdev->ddev->agp->bridge,
+					 page_flags);
 	}
 #endif
 
@@ -706,7 +706,7 @@ static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
 	}
 	gtt->ttm.ttm.func = &radeon_backend_func;
 	gtt->rdev = rdev;
-	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags)) {
+	if (ttm_dma_tt_init(&gtt->ttm, bo, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index f7c2aefbec7c..7c2485fe88d8 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -110,9 +110,9 @@ static struct ttm_backend_func ttm_agp_func = {
 	.destroy = ttm_agp_destroy,
 };
 
-struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
+struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 				 struct agp_bridge_data *bridge,
-				 unsigned long size, uint32_t page_flags)
+				 uint32_t page_flags)
 {
 	struct ttm_agp_backend *agp_be;
 
@@ -124,7 +124,7 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
 	agp_be->bridge = bridge;
 	agp_be->ttm.func = &ttm_agp_func;
 
-	if (ttm_tt_init(&agp_be->ttm, bdev, size, page_flags)) {
+	if (ttm_tt_init(&agp_be->ttm, bo, page_flags)) {
 		kfree(agp_be);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 971133106ec2..65976238d24b 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -73,8 +73,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
 		return -EINVAL;
 	}
 
-	bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
-					      page_flags);
+	bo->ttm = bdev->driver->ttm_tt_create(bo, page_flags);
 	if (unlikely(bo->ttm == NULL))
 		return -ENOMEM;
 
@@ -237,21 +236,21 @@ void ttm_tt_destroy(struct ttm_tt *ttm)
 	ttm->func->destroy(ttm);
 }
 
-void ttm_tt_init_fields(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-			unsigned long size, uint32_t page_flags)
+void ttm_tt_init_fields(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
+			uint32_t page_flags)
 {
-	ttm->bdev = bdev;
-	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	ttm->bdev = bo->bdev;
+	ttm->num_pages = bo->num_pages;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
 	ttm->state = tt_unpopulated;
 	ttm->swap_storage = NULL;
 }
 
-int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags)
+int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
+		uint32_t page_flags)
 {
-	ttm_tt_init_fields(ttm, bdev, size, page_flags);
+	ttm_tt_init_fields(ttm, bo, page_flags);
 
 	if (ttm_tt_alloc_page_directory(ttm)) {
 		ttm_tt_destroy(ttm);
@@ -269,12 +268,12 @@ void ttm_tt_fini(struct ttm_tt *ttm)
 }
 EXPORT_SYMBOL(ttm_tt_fini);
 
-int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		    unsigned long size, uint32_t page_flags)
+int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
+		    uint32_t page_flags)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 
-	ttm_tt_init_fields(ttm, bdev, size, page_flags);
+	ttm_tt_init_fields(ttm, bo, page_flags);
 
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
 	if (ttm_dma_tt_alloc_page_directory(ttm_dma)) {
@@ -286,13 +285,13 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_dma_tt_init);
 
-int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		   unsigned long size, uint32_t page_flags)
+int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
+		   uint32_t page_flags)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 	int ret;
 
-	ttm_tt_init_fields(ttm, bdev, size, page_flags);
+	ttm_tt_init_fields(ttm, bo, page_flags);
 
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
 	if (page_flags & TTM_PAGE_FLAG_SG)
diff --git a/drivers/gpu/drm/virtio/virtgpu_ttm.c b/drivers/gpu/drm/virtio/virtgpu_ttm.c
index fd5d9450878e..11f8ae5b5332 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ttm.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ttm.c
@@ -322,20 +322,19 @@ static struct ttm_backend_func virtio_gpu_backend_func = {
 	.destroy = &virtio_gpu_ttm_backend_destroy,
 };
 
-static struct ttm_tt *virtio_gpu_ttm_tt_create(struct ttm_bo_device *bdev,
-					       unsigned long size,
+static struct ttm_tt *virtio_gpu_ttm_tt_create(struct ttm_buffer_object *bo,
 					       uint32_t page_flags)
 {
 	struct virtio_gpu_device *vgdev;
 	struct virtio_gpu_ttm_tt *gtt;
 
-	vgdev = virtio_gpu_get_vgdev(bdev);
+	vgdev = virtio_gpu_get_vgdev(bo->bdev);
 	gtt = kzalloc(sizeof(struct virtio_gpu_ttm_tt), GFP_KERNEL);
 	if (gtt == NULL)
 		return NULL;
 	gtt->ttm.ttm.func = &virtio_gpu_backend_func;
 	gtt->vgdev = vgdev;
-	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags)) {
+	if (ttm_dma_tt_init(&gtt->ttm, bo, page_flags)) {
 		kfree(gtt);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index fead3f2dbb46..7177eecb8c9f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -693,8 +693,8 @@ static struct ttm_backend_func vmw_ttm_func = {
 	.destroy = vmw_ttm_destroy,
 };
 
-static struct ttm_tt *vmw_ttm_tt_create(struct ttm_bo_device *bdev,
-				 unsigned long size, uint32_t page_flags)
+static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo,
+					uint32_t page_flags)
 {
 	struct vmw_ttm_tt *vmw_be;
 	int ret;
@@ -704,13 +704,13 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_bo_device *bdev,
 		return NULL;
 
 	vmw_be->dma_ttm.ttm.func = &vmw_ttm_func;
-	vmw_be->dev_priv = container_of(bdev, struct vmw_private, bdev);
+	vmw_be->dev_priv = container_of(bo->bdev, struct vmw_private, bdev);
 	vmw_be->mob = NULL;
 
 	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
-		ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bdev, size, page_flags);
+		ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bo, page_flags);
 	else
-		ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bdev, size, page_flags);
+		ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bo, page_flags);
 	if (unlikely(ret != 0))
 		goto out_no_init;
 
diff --git a/drivers/staging/vboxvideo/vbox_ttm.c b/drivers/staging/vboxvideo/vbox_ttm.c
index 2c7daa3d0f24..548edb7c494b 100644
--- a/drivers/staging/vboxvideo/vbox_ttm.c
+++ b/drivers/staging/vboxvideo/vbox_ttm.c
@@ -193,8 +193,7 @@ static struct ttm_backend_func vbox_tt_backend_func = {
 	.destroy = &vbox_ttm_backend_destroy,
 };
 
-static struct ttm_tt *vbox_ttm_tt_create(struct ttm_bo_device *bdev,
-					 unsigned long size,
+static struct ttm_tt *vbox_ttm_tt_create(struct ttm_buffer_object *bo,
 					 u32 page_flags)
 {
 	struct ttm_tt *tt;
@@ -204,7 +203,7 @@ static struct ttm_tt *vbox_ttm_tt_create(struct ttm_bo_device *bdev,
 		return NULL;
 
 	tt->func = &vbox_tt_backend_func;
-	if (ttm_tt_init(tt, bdev, size, page_flags)) {
+	if (ttm_tt_init(tt, bo, page_flags)) {
 		kfree(tt);
 		return NULL;
 	}
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 39cd6b086d3a..3234cc322e70 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -225,8 +225,7 @@ struct ttm_bo_driver {
 	/**
 	 * ttm_tt_create
 	 *
-	 * @bdev: pointer to a struct ttm_bo_device:
-	 * @size: Size of the data needed backing.
+	 * @bo: The buffer object to create the ttm for.
 	 * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
 	 *
 	 * Create a struct ttm_tt to back data with system memory pages.
@@ -234,8 +233,7 @@ struct ttm_bo_driver {
 	 * Returns:
 	 * NULL: Out of memory.
 	 */
-	struct ttm_tt *(*ttm_tt_create)(struct ttm_bo_device *bdev,
-					unsigned long size,
+	struct ttm_tt *(*ttm_tt_create)(struct ttm_buffer_object *bo,
 					uint32_t page_flags);
 
 	/**
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 1cf316a4257c..c0e928abf592 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -150,8 +150,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc);
  * ttm_tt_init
  *
  * @ttm: The struct ttm_tt.
- * @bdev: pointer to a struct ttm_bo_device:
- * @size: Size of the data needed backing.
+ * @bo: The buffer object we create the ttm for.
  * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
  *
  * Create a struct ttm_tt to back data with system memory pages.
@@ -159,12 +158,12 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc);
  * Returns:
  * NULL: Out of memory.
  */
-int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags);
-int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		    unsigned long size, uint32_t page_flags);
-int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		   unsigned long size, uint32_t page_flags);
+int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
+		uint32_t page_flags);
+int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
+		    uint32_t page_flags);
+int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
+		   uint32_t page_flags);
 
 /**
  * ttm_tt_fini
@@ -254,9 +253,8 @@ void ttm_tt_unpopulate(struct ttm_tt *ttm);
 /**
  * ttm_agp_tt_create
  *
- * @bdev: Pointer to a struct ttm_bo_device.
+ * @bo: Buffer object we allocate the ttm for.
  * @bridge: The agp bridge this device is sitting on.
- * @size: Size of the data needed backing.
  * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags.
  *
  *
@@ -264,9 +262,9 @@ void ttm_tt_unpopulate(struct ttm_tt *ttm);
  * for TT memory. This function uses the linux agpgart interface to
  * bind and unbind memory backing a ttm_tt.
  */
-struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
+struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 				 struct agp_bridge_data *bridge,
-				 unsigned long size, uint32_t page_flags);
+				 uint32_t page_flags);
 int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
 void ttm_agp_tt_unpopulate(struct ttm_tt *ttm);
 #endif
-- 
cgit v1.2.3