Merge branch 'linux-5.10' of git://github.com/skeggsb/linux into drm-fixes

Fixes an endian regression on older GPUs, a refcount overflow,
a migration fix and 3 display fixes.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Ben Skeggs <skeggsb@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CACAvsv6MOjtgzKchpis1XrZYmu7-6CaxnHVzJKOXPH62_em7tw@mail.gmail.com

drivers/gpu/drm/nouveau/dispnv50/core.h

@@ -44,6 +44,7 @@ int core507d_new_(const struct nv50_core_func *, struct nouveau_drm *, s32,
 		  struct nv50_core **);
 int core507d_init(struct nv50_core *);
 void core507d_ntfy_init(struct nouveau_bo *, u32);
+int core507d_read_caps(struct nv50_disp *disp);
 int core507d_caps_init(struct nouveau_drm *, struct nv50_disp *);
 int core507d_ntfy_wait_done(struct nouveau_bo *, u32, struct nvif_device *);
 int core507d_update(struct nv50_core *, u32 *, bool);
@@ -55,6 +56,7 @@ extern const struct nv50_outp_func pior507d;
 int core827d_new(struct nouveau_drm *, s32, struct nv50_core **);
 
 int core907d_new(struct nouveau_drm *, s32, struct nv50_core **);
+int core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp);
 extern const struct nv50_outp_func dac907d;
 extern const struct nv50_outp_func sor907d;
 

drivers/gpu/drm/nouveau/dispnv50/core507d.c

@@ -78,18 +78,55 @@ core507d_ntfy_init(struct nouveau_bo *bo, u32 offset)
 }
 
 int
-core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+core507d_read_caps(struct nv50_disp *disp)
 {
 	struct nvif_push *push = disp->core->chan.push;
 	int ret;
 
-	if ((ret = PUSH_WAIT(push, 2)))
+	ret = PUSH_WAIT(push, 6);
+	if (ret)
 		return ret;
 
+	PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL,
+		  NVDEF(NV507D, SET_NOTIFIER_CONTROL, MODE, WRITE) |
+		  NVVAL(NV507D, SET_NOTIFIER_CONTROL, OFFSET, NV50_DISP_CORE_NTFY >> 2) |
+		  NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, ENABLE));
+
 	PUSH_MTHD(push, NV507D, GET_CAPABILITIES, 0x00000000);
+
+	PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL,
+		  NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE));
+
 	return PUSH_KICK(push);
 }
 
+int
+core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+{
+	struct nv50_core *core = disp->core;
+	struct nouveau_bo *bo = disp->sync;
+	s64 time;
+	int ret;
+
+	NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1,
+				     NVDEF(NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, FALSE));
+
+	ret = core507d_read_caps(disp);
+	if (ret < 0)
+		return ret;
+
+	time = nvif_msec(core->chan.base.device, 2000ULL,
+			 if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY,
+				       NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, ==, TRUE))
+				 break;
+			 usleep_range(1, 2);
+			 );
+	if (time < 0)
+		NV_ERROR(drm, "core caps notifier timeout\n");
+
+	return 0;
+}
+
 int
 core507d_init(struct nv50_core *core)
 {

drivers/gpu/drm/nouveau/dispnv50/core907d.c

@@ -22,11 +22,45 @@
 #include "core.h"
 #include "head.h"
 
+#include <nvif/push507c.h>
+#include <nvif/timer.h>
+
+#include <nvhw/class/cl907d.h>
+
+#include "nouveau_bo.h"
+
+int
+core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+{
+	struct nv50_core *core = disp->core;
+	struct nouveau_bo *bo = disp->sync;
+	s64 time;
+	int ret;
+
+	NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV907D_CORE_NOTIFIER_3, CAPABILITIES_4,
+				     NVDEF(NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, FALSE));
+
+	ret = core507d_read_caps(disp);
+	if (ret < 0)
+		return ret;
+
+	time = nvif_msec(core->chan.base.device, 2000ULL,
+			 if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY,
+				       NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, ==, TRUE))
+				 break;
+			 usleep_range(1, 2);
+			 );
+	if (time < 0)
+		NV_ERROR(drm, "core caps notifier timeout\n");
+
+	return 0;
+}
+
 static const struct nv50_core_func
 core907d = {
 	.init = core507d_init,
 	.ntfy_init = core507d_ntfy_init,
-	.caps_init = core507d_caps_init,
+	.caps_init = core907d_caps_init,
 	.ntfy_wait_done = core507d_ntfy_wait_done,
 	.update = core507d_update,
 	.head = &head907d,

drivers/gpu/drm/nouveau/dispnv50/core917d.c

@@ -26,7 +26,7 @@ static const struct nv50_core_func
 core917d = {
 	.init = core507d_init,
 	.ntfy_init = core507d_ntfy_init,
-	.caps_init = core507d_caps_init,
+	.caps_init = core907d_caps_init,
 	.ntfy_wait_done = core507d_ntfy_wait_done,
 	.update = core507d_update,
 	.head = &head917d,

drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h

@@ -32,7 +32,10 @@
 #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_DONE_TRUE                               0x00000001
 #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_R0                                      15:1
 #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_TIMESTAMP                               29:16
-
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1                                       0x00000001
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE                                  0:0
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_FALSE                            0x00000000
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_TRUE                             0x00000001
 
 // class methods
 #define NV507D_UPDATE                                                           (0x00000080)

drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h

@@ -24,6 +24,10 @@
 #ifndef _cl907d_h_
 #define _cl907d_h_
 
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4                                       0x00000004
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE                                  0:0
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_FALSE                            0x00000000
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_TRUE                             0x00000001
 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20                             0x00000014
 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18               0:0
 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18_FALSE         0x00000000

drivers/gpu/drm/nouveau/nouveau_connector.c

@@ -1023,29 +1023,6 @@ get_tmds_link_bandwidth(struct drm_connector *connector)
 		return 112000 * duallink_scale;
 }
 
-enum drm_mode_status
-nouveau_conn_mode_clock_valid(const struct drm_display_mode *mode,
-			      const unsigned min_clock,
-			      const unsigned max_clock,
-			      unsigned int *clock_out)
-{
-	unsigned int clock = mode->clock;
-
-	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) ==
-	    DRM_MODE_FLAG_3D_FRAME_PACKING)
-		clock *= 2;
-
-	if (clock < min_clock)
-		return MODE_CLOCK_LOW;
-	if (clock > max_clock)
-		return MODE_CLOCK_HIGH;
-
-	if (clock_out)
-		*clock_out = clock;
-
-	return MODE_OK;
-}
-
 static enum drm_mode_status
 nouveau_connector_mode_valid(struct drm_connector *connector,
 			     struct drm_display_mode *mode)
@@ -1053,7 +1030,7 @@ nouveau_connector_mode_valid(struct drm_connector *connector,
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder;
 	struct drm_encoder *encoder = to_drm_encoder(nv_encoder);
-	unsigned min_clock = 25000, max_clock = min_clock;
+	unsigned int min_clock = 25000, max_clock = min_clock, clock = mode->clock;
 
 	switch (nv_encoder->dcb->type) {
 	case DCB_OUTPUT_LVDS:
@@ -1082,8 +1059,15 @@ nouveau_connector_mode_valid(struct drm_connector *connector,
 		return MODE_BAD;
 	}
 
-	return nouveau_conn_mode_clock_valid(mode, min_clock, max_clock,
-					     NULL);
+	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+		clock *= 2;
+
+	if (clock < min_clock)
+		return MODE_CLOCK_LOW;
+	if (clock > max_clock)
+		return MODE_CLOCK_HIGH;
+
+	return MODE_OK;
 }
 
 static struct drm_encoder *

drivers/gpu/drm/nouveau/nouveau_dp.c

@@ -231,23 +231,30 @@ nv50_dp_mode_valid(struct drm_connector *connector,
 		   const struct drm_display_mode *mode,
 		   unsigned *out_clock)
 {
-	const unsigned min_clock = 25000;
-	unsigned max_clock, ds_clock, clock;
-	enum drm_mode_status ret;
+	const unsigned int min_clock = 25000;
+	unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock;
+	const u8 bpp = connector->display_info.bpc * 3;
 
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace)
 		return MODE_NO_INTERLACE;
 
-	max_clock = outp->dp.link_nr * outp->dp.link_bw;
-	ds_clock = drm_dp_downstream_max_dotclock(outp->dp.dpcd,
-						  outp->dp.downstream_ports);
-	if (ds_clock)
-		max_clock = min(max_clock, ds_clock);
+	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+		clock *= 2;
+
+	max_rate = outp->dp.link_nr * outp->dp.link_bw;
+	mode_rate = DIV_ROUND_UP(clock * bpp, 8);
+	if (mode_rate > max_rate)
+		return MODE_CLOCK_HIGH;
+
+	ds_max_dotclock = drm_dp_downstream_max_dotclock(outp->dp.dpcd, outp->dp.downstream_ports);
+	if (ds_max_dotclock && clock > ds_max_dotclock)
+		return MODE_CLOCK_HIGH;
+
+	if (clock < min_clock)
+		return MODE_CLOCK_LOW;
 
-	clock = mode->clock * (connector->display_info.bpc * 3) / 10;
-	ret = nouveau_conn_mode_clock_valid(mode, min_clock, max_clock,
-					    &clock);
 	if (out_clock)
 		*out_clock = clock;
-	return ret;
+
+	return MODE_OK;
 }

drivers/gpu/drm/nouveau/nouveau_gem.c

@@ -190,7 +190,8 @@ nouveau_gem_new(struct nouveau_cli *cli, u64 size, int align, uint32_t domain,
 	 * to the caller, instead of a normal nouveau_bo ttm reference. */
 	ret = drm_gem_object_init(drm->dev, &nvbo->bo.base, size);
 	if (ret) {
-		nouveau_bo_ref(NULL, &nvbo);
+		drm_gem_object_release(&nvbo->bo.base);
+		kfree(nvbo);
 		return ret;
 	}
 

drivers/gpu/drm/nouveau/nouveau_svm.c

@@ -105,11 +105,11 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct drm_nouveau_svm_bind *args = data;
 	unsigned target, cmd, priority;
-	unsigned long addr, end, size;
+	unsigned long addr, end;
 	struct mm_struct *mm;
 
 	args->va_start &= PAGE_MASK;
-	args->va_end &= PAGE_MASK;
+	args->va_end = ALIGN(args->va_end, PAGE_SIZE);
 
 	/* Sanity check arguments */
 	if (args->reserved0 || args->reserved1)
@@ -118,8 +118,6 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 		return -EINVAL;
 	if (args->va_start >= args->va_end)
 		return -EINVAL;
-	if (!args->npages)
-		return -EINVAL;
 
 	cmd = args->header >> NOUVEAU_SVM_BIND_COMMAND_SHIFT;
 	cmd &= NOUVEAU_SVM_BIND_COMMAND_MASK;
@@ -151,12 +149,6 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 	if (args->stride)
 		return -EINVAL;
 
-	size = ((unsigned long)args->npages) << PAGE_SHIFT;
-	if ((args->va_start + size) <= args->va_start)
-		return -EINVAL;
-	if ((args->va_start + size) > args->va_end)
-		return -EINVAL;
-
 	/*
 	 * Ok we are ask to do something sane, for now we only support migrate
 	 * commands but we will add things like memory policy (what to do on
@@ -171,7 +163,7 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	for (addr = args->va_start, end = args->va_start + size; addr < end;) {
+	for (addr = args->va_start, end = args->va_end; addr < end;) {
 		struct vm_area_struct *vma;
 		unsigned long next;
 

drivers/gpu/drm/nouveau/nvkm/engine/device/base.c

@@ -2924,17 +2924,34 @@ nvkm_device_del(struct nvkm_device **pdevice)
 	}
 }
 
+/* returns true if the GPU is in the CPU native byte order */
 static inline bool
 nvkm_device_endianness(struct nvkm_device *device)
 {
-	u32 boot1 = nvkm_rd32(device, 0x000004) & 0x01000001;
 #ifdef __BIG_ENDIAN
-	if (!boot1)
-		return false;
+	const bool big_endian = true;
 #else
-	if (boot1)
-		return false;
+	const bool big_endian = false;
 #endif
+
+	/* Read NV_PMC_BOOT_1, and assume non-functional endian switch if it
+	 * doesn't contain the expected values.
+	 */
+	u32 pmc_boot_1 = nvkm_rd32(device, 0x000004);
+	if (pmc_boot_1 && pmc_boot_1 != 0x01000001)
+		return !big_endian; /* Assume GPU is LE in this case. */
+
+	/* 0 means LE and 0x01000001 means BE GPU. Condition is true when
+	 * GPU/CPU endianness don't match.
+	 */
+	if (big_endian == !pmc_boot_1) {
+		nvkm_wr32(device, 0x000004, 0x01000001);
+		nvkm_rd32(device, 0x000000);
+		if (nvkm_rd32(device, 0x000004) != (big_endian ? 0x01000001 : 0x00000000))
+			return !big_endian; /* Assume GPU is LE on any unexpected read-back. */
+	}
+
+	/* CPU/GPU endianness should (hopefully) match. */
 	return true;
 }
 
@@ -2986,16 +3003,12 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 	/* identify the chipset, and determine classes of subdev/engines */
 	if (detect) {
 		/* switch mmio to cpu's native endianness */
-		if (!nvkm_device_endianness(device)) {
-			nvkm_wr32(device, 0x000004, 0x01000001);
-			nvkm_rd32(device, 0x000000);
 		if (!nvkm_device_endianness(device)) {
 			nvdev_error(device,
-					    "GPU not supported on big-endian\n");
+				    "Couldn't switch GPU to CPUs endianess\n");
 			ret = -ENOSYS;
 			goto done;
 		}
-		}
 
 		boot0 = nvkm_rd32(device, 0x000000);