Merge tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of work all over, Intel improving DG2 support, amdkfd CRIU
  support, msm new hw support, and faster fbdev support.

  dma-buf:
   - rename dma-buf-map to iosys-map

  core:
   - move buddy allocator to core
   - add pci/platform init macros
   - improve EDID parser deep color handling
   - EDID timing type 7 support
   - add GPD Win Max quirk
   - add yes/no helpers to string_helpers
   - flatten syncobj chains
   - add nomodeset support to lots of drivers
   - improve fb-helper clipping support
   - add default property value interface

  fbdev:
   - improve fbdev ops speed

  ttm:
   - add a backpointer from ttm bo->ttm resource

  dp:
   - move displayport headers
   - add a dp helper module

  bridge:
   - anx7625 atomic support, HDCP support

  panel:
   - split out panel-lvds and lvds bindings
   - find panels in OF subnodes

  privacy:
   - add chromeos privacy screen support

  fb:
   - hot unplug fw fb on forced removal

  simpledrm:
   - request region instead of marking ioresource busy
   - add panel oreintation property

  udmabuf:
   - fix oops with 0 pages

  amdgpu:
   - power management code cleanup
   - Enable freesync video mode by default
   - RAS code cleanup
   - Improve VRAM access for debug using SDMA
   - SR-IOV rework special register access and fixes
   - profiling power state request ioctl
   - expose IP discovery via sysfs
   - Cyan skillfish updates
   - GC 10.3.7, SDMA 5.2.7, DCN 3.1.6 updates
   - expose benchmark tests via debugfs
   - add module param to disable XGMI for testing
   - GPU reset debugfs register dumping support

  amdkfd:
   - CRIU support
   - SDMA queue fixes

  radeon:
   - UVD suspend fix
   - iMac backlight fix

  i915:
   - minimal parallel submission for execlists
   - DG2-G12 subplatform added
   - DG2 programming workarounds
   - DG2 accelerated migration support
   - flat CCS and CCS engine support for XeHP
   - initial small BAR support
   - drop fake LMEM support
   - ADL-N PCH support
   - bigjoiner updates
   - introduce VMA resources and async unbinding
   - register definitions cleanups
   - multi-FBC refactoring
   - DG1 OPROM over SPI support
   - ADL-N platform enabling
   - opregion mailbox #5 support
   - DP MST ESI improvements
   - drm device based logging
   - async flip optimisation for DG2
   - CPU arch abstraction fixes
   - improve GuC ADS init to work on aarch64
   - tweak TTM LRU priority hint
   - GuC 69.0.3 support
   - remove short term execbuf pins

  nouveau:
   - higher DP/eDP bitrates
   - backlight fixes

  msm:
   - dpu + dp support for sc8180x
   - dp support for sm8350
   - dpu + dsi support for qcm2290
   - 10nm dsi phy tuning support
   - bridge support for dp encoder
   - gpu support for additional 7c3 SKUs

  ingenic:
   - HDMI support for JZ4780
   - aux channel EDID support

  ast:
   - AST2600 support
   - add wide screen support
   - create DP/DVI connectors

  omapdrm:
   - fix implicit dma_buf fencing

  vc4:
   - add CSC + full range support
   - better display firmware handoff

  panfrost:
   - add initial dual-core GPU support

  stm:
   - new revision support
   - fb handover support

  mediatek:
   - transfer display binding document to yaml format.
   - add mt8195 display device binding.
   - allow commands to be sent during video mode.
   - add wait_for_event for crtc disable by cmdq.

  tegra:
   - YUV format support

  rcar-du:
   - LVDS support for M3-W+ (R8A77961)

  exynos:
   - BGR pixel format for FIMD device"

* tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm: (1529 commits)
  drm/i915/display: Do not re-enable PSR after it was marked as not reliable
  drm/i915/display: Fix HPD short pulse handling for eDP
  drm/amdgpu: Use drm_mode_copy()
  drm/radeon: Use drm_mode_copy()
  drm/amdgpu: Use ternary operator in `vcn_v1_0_start()`
  drm/amdgpu: Remove pointless on stack mode copies
  drm/amd/pm: fix indenting in __smu_cmn_reg_print_error()
  drm/amdgpu/dc: fix typos in comments
  drm/amdgpu: fix typos in comments
  drm/amd/pm: fix typos in comments
  drm/amdgpu: Add stolen reserved memory for MI25 SRIOV.
  drm/amdgpu: Merge get_reserved_allocation to get_vbios_allocations.
  drm/amdkfd: evict svm bo worker handle error
  drm/amdgpu/vcn: fix vcn ring test failure in igt reload test
  drm/amdgpu: only allow secure submission on rings which support that
  drm/amdgpu: fixed the warnings reported by kernel test robot
  drm/amd/display: 3.2.177
  drm/amd/display: [FW Promotion] Release 0.0.108.0
  drm/amd/display: Add save/restore PANEL_PWRSEQ_REF_DIV2
  drm/amd/display: Wait for hubp read line for Pollock
  ...

5 files changed, 170 insertions, 79 deletions

diff --git a/drivers/video/fbdev/core/cfbimgblt.c b/drivers/video/fbdev/core/cfbimgblt.c
index a2bb276a8b24..7361cfabdd85 100644
--- a/drivers/video/fbdev/core/cfbimgblt.c
+++ b/drivers/video/fbdev/core/cfbimgblt.c
@@ -16,15 +16,15 @@
  *  must be laid out exactly in the same format as the framebuffer. Yes I know
  *  their are cards with hardware that coverts images of various depths to the
  *  framebuffer depth. But not every card has this. All images must be rounded
- *  up to the nearest byte. For example a bitmap 12 bits wide must be two 
- *  bytes width. 
+ *  up to the nearest byte. For example a bitmap 12 bits wide must be two
+ *  bytes width.
  *
- *  Tony: 
- *  Incorporate mask tables similar to fbcon-cfb*.c in 2.4 API.  This speeds 
+ *  Tony:
+ *  Incorporate mask tables similar to fbcon-cfb*.c in 2.4 API.  This speeds
  *  up the code significantly.
- *  
+ *
  *  Code for depths not multiples of BITS_PER_LONG is still kludgy, which is
- *  still processed a bit at a time.   
+ *  still processed a bit at a time.
  *
  *  Also need to add code to deal with cards endians that are different than
  *  the native cpu endians. I also need to deal with MSB position in the word.
@@ -72,8 +72,8 @@ static const u32 cfb_tab32[] = {
 #define FB_WRITEL fb_writel
 #define FB_READL  fb_readl
 
-static inline void color_imageblit(const struct fb_image *image, 
-				   struct fb_info *p, u8 __iomem *dst1, 
+static inline void color_imageblit(const struct fb_image *image,
+				   struct fb_info *p, u8 __iomem *dst1,
 				   u32 start_index,
 				   u32 pitch_index)
 {
@@ -92,7 +92,7 @@ static inline void color_imageblit(const struct fb_image *image,
 		dst = (u32 __iomem *) dst1;
 		shift = 0;
 		val = 0;
-		
+
 		if (start_index) {
 			u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
 						start_index, bswapmask);
@@ -109,8 +109,8 @@ static inline void color_imageblit(const struct fb_image *image,
 			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
 			if (shift >= null_bits) {
 				FB_WRITEL(val, dst++);
-	
-				val = (shift == null_bits) ? 0 : 
+
+				val = (shift == null_bits) ? 0 :
 					FB_SHIFT_LOW(p, color, 32 - shift);
 			}
 			shift += bpp;
@@ -134,9 +134,9 @@ static inline void color_imageblit(const struct fb_image *image,
 	}
 }
 
-static inline void slow_imageblit(const struct fb_image *image, struct fb_info *p, 
+static inline void slow_imageblit(const struct fb_image *image, struct fb_info *p,
 				  u8 __iomem *dst1, u32 fgcolor,
-				  u32 bgcolor, 
+				  u32 bgcolor,
 				  u32 start_index,
 				  u32 pitch_index)
 {
@@ -172,7 +172,7 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 			l--;
 			color = (*s & (1 << l)) ? fgcolor : bgcolor;
 			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
-			
+
 			/* Did the bitshift spill bits to the next long? */
 			if (shift >= null_bits) {
 				FB_WRITEL(val, dst++);
@@ -191,16 +191,16 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 
 			FB_WRITEL((FB_READL(dst) & end_mask) | val, dst);
 		}
-		
+
 		dst1 += pitch;
-		src += spitch;	
+		src += spitch;
 		if (pitch_index) {
 			dst2 += pitch;
 			dst1 = (u8 __iomem *)((long __force)dst2 & ~(sizeof(u32) - 1));
 			start_index += pitch_index;
 			start_index &= 32 - 1;
 		}
-		
+
 	}
 }
 
@@ -212,29 +212,35 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
  *           fix->line_legth is divisible by 4;
  *           beginning and end of a scanline is dword aligned
  */
-static inline void fast_imageblit(const struct fb_image *image, struct fb_info *p, 
-				  u8 __iomem *dst1, u32 fgcolor, 
-				  u32 bgcolor) 
+static inline void fast_imageblit(const struct fb_image *image, struct fb_info *p,
+				  u8 __iomem *dst1, u32 fgcolor,
+				  u32 bgcolor)
 {
 	u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
 	u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
-	u32 bit_mask, end_mask, eorx, shift;
+	u32 bit_mask, eorx;
 	const char *s = image->data, *src;
 	u32 __iomem *dst;
 	const u32 *tab = NULL;
+	size_t tablen;
+	u32 colortab[16];
 	int i, j, k;
 
 	switch (bpp) {
 	case 8:
 		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
+		tablen = 16;
 		break;
 	case 16:
 		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
+		tablen = 4;
 		break;
 	case 32:
-	default:
 		tab = cfb_tab32;
+		tablen = 2;
 		break;
+	default:
+		return;
 	}
 
 	for (i = ppw-1; i--; ) {
@@ -243,25 +249,52 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
 		fgx |= fgcolor;
 		bgx |= bgcolor;
 	}
-	
+
 	bit_mask = (1 << ppw) - 1;
 	eorx = fgx ^ bgx;
 	k = image->width/ppw;
 
+	for (i = 0; i < tablen; ++i)
+		colortab[i] = (tab[i] & eorx) ^ bgx;
+
 	for (i = image->height; i--; ) {
-		dst = (u32 __iomem *) dst1, shift = 8; src = s;
-		
-		for (j = k; j--; ) {
-			shift -= ppw;
-			end_mask = tab[(*src >> shift) & bit_mask];
-			FB_WRITEL((end_mask & eorx)^bgx, dst++);
-			if (!shift) { shift = 8; src++; }		
+		dst = (u32 __iomem *)dst1;
+		src = s;
+
+		switch (ppw) {
+		case 4: /* 8 bpp */
+			for (j = k; j; j -= 2, ++src) {
+				FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
+			}
+			break;
+		case 2: /* 16 bpp */
+			for (j = k; j; j -= 4, ++src) {
+				FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 2) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
+			}
+			break;
+		case 1: /* 32 bpp */
+			for (j = k; j; j -= 8, ++src) {
+				FB_WRITEL(colortab[(*src >> 7) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 5) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 3) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 2) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 1) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
+			}
+			break;
 		}
+
 		dst1 += p->fix.line_length;
 		s += spitch;
 	}
-}	
-	
+}
+
 void cfb_imageblit(struct fb_info *p, const struct fb_image *image)
 {
 	u32 fgcolor, bgcolor, start_index, bitstart, pitch_index = 0;
@@ -292,13 +325,13 @@ void cfb_imageblit(struct fb_info *p, const struct fb_image *image)
 		} else {
 			fgcolor = image->fg_color;
 			bgcolor = image->bg_color;
-		}	
-		
-		if (32 % bpp == 0 && !start_index && !pitch_index && 
+		}
+
+		if (32 % bpp == 0 && !start_index && !pitch_index &&
 		    ((width & (32/bpp-1)) == 0) &&
-		    bpp >= 8 && bpp <= 32) 			
+		    bpp >= 8 && bpp <= 32)
 			fast_imageblit(image, p, dst1, fgcolor, bgcolor);
-		else 
+		else
 			slow_imageblit(image, p, dst1, fgcolor, bgcolor,
 					start_index, pitch_index);
 	} else
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index d0b0b05e0dff..842c66b3e33d 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -59,6 +59,7 @@ static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf)
 		printk(KERN_ERR "no mapping available\n");
 
 	BUG_ON(!page->mapping);
+	INIT_LIST_HEAD(&page->lru);
 	page->index = vmf->pgoff;
 
 	vmf->page = page;
@@ -95,7 +96,7 @@ static vm_fault_t fb_deferred_io_mkwrite(struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	struct fb_info *info = vmf->vma->vm_private_data;
 	struct fb_deferred_io *fbdefio = info->fbdefio;
-	struct page *cur;
+	struct list_head *pos = &fbdefio->pagelist;
 
 	/* this is a callback we get when userspace first tries to
 	write to the page. we schedule a workqueue. that workqueue
@@ -122,21 +123,38 @@ static vm_fault_t fb_deferred_io_mkwrite(struct vm_fault *vmf)
 	 */
 	lock_page(page);
 
-	/* we loop through the pagelist before adding in order
-	to keep the pagelist sorted */
-	list_for_each_entry(cur, &fbdefio->pagelist, lru) {
-		/* this check is to catch the case where a new
-		process could start writing to the same page
-		through a new pte. this new access can cause the
-		mkwrite even when the original ps's pte is marked
-		writable */
-		if (unlikely(cur == page))
-			goto page_already_added;
-		else if (cur->index > page->index)
-			break;
+	/*
+	 * This check is to catch the case where a new process could start
+	 * writing to the same page through a new PTE. This new access
+	 * can cause a call to .page_mkwrite even if the original process'
+	 * PTE is marked writable.
+	 *
+	 * TODO: The lru field is owned by the page cache; hence the name.
+	 *       We dequeue in fb_deferred_io_work() after flushing the
+	 *       page's content into video memory. Instead of lru, fbdefio
+	 *       should have it's own field.
+	 */
+	if (!list_empty(&page->lru))
+		goto page_already_added;
+
+	if (unlikely(fbdefio->sort_pagelist)) {
+		/*
+		 * We loop through the pagelist before adding in order to
+		 * keep the pagelist sorted. This has significant overhead
+		 * of O(n^2) with n being the number of written pages. If
+		 * possible, drivers should try to work with unsorted page
+		 * lists instead.
+		 */
+		struct page *cur;
+
+		list_for_each_entry(cur, &fbdefio->pagelist, lru) {
+			if (cur->index > page->index)
+				break;
+		}
+		pos = &cur->lru;
 	}
 
-	list_add_tail(&page->lru, &cur->lru);
+	list_add_tail(&page->lru, pos);
 
 page_already_added:
 	mutex_unlock(&fbdefio->lock);
@@ -187,7 +205,7 @@ static void fb_deferred_io_work(struct work_struct *work)
 
 	/* clear the list */
 	list_for_each_safe(node, next, &fbdefio->pagelist) {
-		list_del(node);
+		list_del_init(node);
 	}
 	mutex_unlock(&fbdefio->lock);
 }
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 8df3ac991e5a..34d6bb1bf82e 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/linux_logo.h>
 #include <linux/proc_fs.h>
+#include <linux/platform_device.h>
 #include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/kmod.h>
@@ -1555,18 +1556,36 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a,
 	/* check all firmware fbs and kick off if the base addr overlaps */
 	for_each_registered_fb(i) {
 		struct apertures_struct *gen_aper;
+		struct device *device;
 
 		if (!(registered_fb[i]->flags & FBINFO_MISC_FIRMWARE))
 			continue;
 
 		gen_aper = registered_fb[i]->apertures;
+		device = registered_fb[i]->device;
 		if (fb_do_apertures_overlap(gen_aper, a) ||
 			(primary && gen_aper && gen_aper->count &&
 			 gen_aper->ranges[0].base == VGA_FB_PHYS)) {
 
 			printk(KERN_INFO "fb%d: switching to %s from %s\n",
 			       i, name, registered_fb[i]->fix.id);
-			do_unregister_framebuffer(registered_fb[i]);
+
+			/*
+			 * If we kick-out a firmware driver, we also want to remove
+			 * the underlying platform device, such as simple-framebuffer,
+			 * VESA, EFI, etc. A native driver will then be able to
+			 * allocate the memory range.
+			 *
+			 * If it's not a platform device, at least print a warning. A
+			 * fix would add code to remove the device from the system.
+			 */
+			if (dev_is_platform(device)) {
+				registered_fb[i]->forced_out = true;
+				platform_device_unregister(to_platform_device(device));
+			} else {
+				pr_warn("fb%d: cannot remove device\n", i);
+				do_unregister_framebuffer(registered_fb[i]);
+			}
 		}
 	}
 }
@@ -1896,9 +1915,13 @@ EXPORT_SYMBOL(register_framebuffer);
 void
 unregister_framebuffer(struct fb_info *fb_info)
 {
-	mutex_lock(&registration_lock);
+	bool forced_out = fb_info->forced_out;
+
+	if (!forced_out)
+		mutex_lock(&registration_lock);
 	do_unregister_framebuffer(fb_info);
-	mutex_unlock(&registration_lock);
+	if (!forced_out)
+		mutex_unlock(&registration_lock);
 }
 EXPORT_SYMBOL(unregister_framebuffer);
 
diff --git a/drivers/video/fbdev/core/sysfillrect.c b/drivers/video/fbdev/core/sysfillrect.c
index 33ee3d34f9d2..bcdcaeae6538 100644
--- a/drivers/video/fbdev/core/sysfillrect.c
+++ b/drivers/video/fbdev/core/sysfillrect.c
@@ -50,19 +50,9 @@ bitfill_aligned(struct fb_info *p, unsigned long *dst, int dst_idx,
 
 		/* Main chunk */
 		n /= bits;
-		while (n >= 8) {
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			n -= 8;
-		}
-		while (n--)
-			*dst++ = pat;
+		memset_l(dst, pat, n);
+		dst += n;
+
 		/* Trailing bits */
 		if (last)
 			*dst = comp(pat, *dst, last);
diff --git a/drivers/video/fbdev/core/sysimgblt.c b/drivers/video/fbdev/core/sysimgblt.c
index a4d05b1b17d7..722c327a381b 100644
--- a/drivers/video/fbdev/core/sysimgblt.c
+++ b/drivers/video/fbdev/core/sysimgblt.c
@@ -188,23 +188,29 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
 {
 	u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
 	u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
-	u32 bit_mask, end_mask, eorx, shift;
+	u32 bit_mask, eorx;
 	const char *s = image->data, *src;
 	u32 *dst;
-	const u32 *tab = NULL;
+	const u32 *tab;
+	size_t tablen;
+	u32 colortab[16];
 	int i, j, k;
 
 	switch (bpp) {
 	case 8:
 		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
+		tablen = 16;
 		break;
 	case 16:
 		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
+		tablen = 4;
 		break;
 	case 32:
-	default:
 		tab = cfb_tab32;
+		tablen = 2;
 		break;
+	default:
+		return;
 	}
 
 	for (i = ppw-1; i--; ) {
@@ -218,19 +224,40 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
 	eorx = fgx ^ bgx;
 	k = image->width/ppw;
 
+	for (i = 0; i < tablen; ++i)
+		colortab[i] = (tab[i] & eorx) ^ bgx;
+
 	for (i = image->height; i--; ) {
 		dst = dst1;
-		shift = 8;
 		src = s;
 
-		for (j = k; j--; ) {
-			shift -= ppw;
-			end_mask = tab[(*src >> shift) & bit_mask];
-			*dst++ = (end_mask & eorx) ^ bgx;
-			if (!shift) {
-				shift = 8;
-				src++;
+		switch (ppw) {
+		case 4: /* 8 bpp */
+			for (j = k; j; j -= 2, ++src) {
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
+			}
+			break;
+		case 2: /* 16 bpp */
+			for (j = k; j; j -= 4, ++src) {
+				*dst++ = colortab[(*src >> 6) & bit_mask];
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 2) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
+			}
+			break;
+		case 1: /* 32 bpp */
+			for (j = k; j; j -= 8, ++src) {
+				*dst++ = colortab[(*src >> 7) & bit_mask];
+				*dst++ = colortab[(*src >> 6) & bit_mask];
+				*dst++ = colortab[(*src >> 5) & bit_mask];
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 3) & bit_mask];
+				*dst++ = colortab[(*src >> 2) & bit_mask];
+				*dst++ = colortab[(*src >> 1) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
 			}
+			break;
 		}
 		dst1 += p->fix.line_length;
 		s += spitch;