Merge tag 'v5.10.14' into 5.10

This is the 5.10.14 stable release

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 13
+SUBLEVEL = 14
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 

arch/arm/mm/Kconfig

@@ -743,6 +743,7 @@ config SWP_EMULATE
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on ARCH_SUPPORTS_BIG_ENDIAN
+	depends on !LD_IS_LLD
 	help
 	  Say Y if you plan on running a kernel in big-endian mode.
 	  Note that your board must be properly built and your board

arch/arm64/boot/dts/amlogic/meson-g12b.dtsi

@@ -135,3 +135,7 @@
 		};
 	};
 };
+
+&mali {
+	dma-coherent;
+};

arch/arm64/include/asm/memory.h

@@ -238,11 +238,11 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 
 
 /*
- * The linear kernel range starts at the bottom of the virtual address
- * space. Testing the top bit for the start of the region is a
- * sufficient check and avoids having to worry about the tag.
+ * Check whether an arbitrary address is within the linear map, which
+ * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the
+ * kernel's TTBR1 address range.
  */
-#define __is_lm_address(addr)	(!(((u64)addr) & BIT(vabits_actual - 1)))
+#define __is_lm_address(addr)	(((u64)(addr) ^ PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET))
 
 #define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
@@ -323,7 +323,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */
 
 #define virt_addr_valid(addr)	({					\
-	__typeof__(addr) __addr = addr;					\
+	__typeof__(addr) __addr = __tag_reset(addr);			\
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 

arch/arm64/mm/physaddr.c

@@ -9,7 +9,7 @@
 
 phys_addr_t __virt_to_phys(unsigned long x)
 {
-	WARN(!__is_lm_address(x),
+	WARN(!__is_lm_address(__tag_reset(x)),
 	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
 	      (void *)x,
 	      (void *)x);

arch/x86/include/asm/intel-family.h

@@ -97,6 +97,7 @@
 
 #define	INTEL_FAM6_LAKEFIELD		0x8A
 #define INTEL_FAM6_ALDERLAKE		0x97
+#define INTEL_FAM6_ALDERLAKE_L		0x9A
 
 /* "Small Core" Processors (Atom) */
 

arch/x86/include/asm/msr.h

@@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
  * think of extending them - you will be slapped with a stinking trout or a frozen
  * shark will reach you, wherever you are! You've been warned.
  */
-static inline unsigned long long notrace __rdmsr(unsigned int msr)
+static __always_inline unsigned long long __rdmsr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
@@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
+static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
 {
 	asm volatile("1: wrmsr\n"
 		     "2:\n"

arch/x86/kernel/setup.c

@@ -665,6 +665,17 @@ static void __init trim_platform_memory_ranges(void)
 
 static void __init trim_bios_range(void)
 {
+	/*
+	 * A special case is the first 4Kb of memory;
+	 * This is a BIOS owned area, not kernel ram, but generally
+	 * not listed as such in the E820 table.
+	 *
+	 * This typically reserves additional memory (64KiB by default)
+	 * since some BIOSes are known to corrupt low memory.  See the
+	 * Kconfig help text for X86_RESERVE_LOW.
+	 */
+	e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+
 	/*
 	 * special case: Some BIOSes report the PC BIOS
 	 * area (640Kb -> 1Mb) as RAM even though it is not.
@@ -722,15 +733,6 @@ early_param("reservelow", parse_reservelow);
 
 static void __init trim_low_memory_range(void)
 {
-	/*
-	 * A special case is the first 4Kb of memory;
-	 * This is a BIOS owned area, not kernel ram, but generally
-	 * not listed as such in the E820 table.
-	 *
-	 * This typically reserves additional memory (64KiB by default)
-	 * since some BIOSes are known to corrupt low memory.  See the
-	 * Kconfig help text for X86_RESERVE_LOW.
-	 */
 	memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE));
 }
 

drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c

@@ -239,6 +239,7 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 	struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
 	bool force_reset = false;
 	bool update_uclk = false;
+	bool p_state_change_support;
 
 	if (dc->work_arounds.skip_clock_update || !clk_mgr->smu_present)
 		return;
@@ -279,8 +280,9 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 		clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz;
 
 	clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support;
-	if (should_update_pstate_support(safe_to_lower, new_clocks->p_state_change_support, clk_mgr_base->clks.p_state_change_support)) {
-		clk_mgr_base->clks.p_state_change_support = new_clocks->p_state_change_support;
+	p_state_change_support = new_clocks->p_state_change_support || (display_count == 0);
+	if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.p_state_change_support)) {
+		clk_mgr_base->clks.p_state_change_support = p_state_change_support;
 
 		/* to disable P-State switching, set UCLK min = max */
 		if (!clk_mgr_base->clks.p_state_change_support)

drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c

@@ -2375,6 +2375,9 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting
 			initial_link_setting;
 	uint32_t link_bw;
 
+	if (req_bw > dc_link_bandwidth_kbps(link, &link->verified_link_cap))
+		return false;
+
 	/* search for the minimum link setting that:
 	 * 1. is supported according to the link training result
 	 * 2. could support the b/w requested by the timing
@@ -3020,14 +3023,14 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 		for (i = 0; i < MAX_PIPES; i++) {
 			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
-					pipe_ctx->stream->link == link)
+					pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe)
 				core_link_disable_stream(pipe_ctx);
 		}
 
 		for (i = 0; i < MAX_PIPES; i++) {
 			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
-					pipe_ctx->stream->link == link)
+					pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe)
 				core_link_enable_stream(link->dc->current_state, pipe_ctx);
 		}
 

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -646,8 +646,13 @@ static void power_on_plane(
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		hws->funcs.dpp_pg_control(hws, plane_id, true);
-		hws->funcs.hubp_pg_control(hws, plane_id, true);
+
+		if (hws->funcs.dpp_pg_control)
+			hws->funcs.dpp_pg_control(hws, plane_id, true);
+
+		if (hws->funcs.hubp_pg_control)
+			hws->funcs.hubp_pg_control(hws, plane_id, true);
+
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
 		DC_LOG_DEBUG(
@@ -1079,8 +1084,13 @@ void dcn10_plane_atomic_power_down(struct dc *dc,
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		hws->funcs.dpp_pg_control(hws, dpp->inst, false);
-		hws->funcs.hubp_pg_control(hws, hubp->inst, false);
+
+		if (hws->funcs.dpp_pg_control)
+			hws->funcs.dpp_pg_control(hws, dpp->inst, false);
+
+		if (hws->funcs.hubp_pg_control)
+			hws->funcs.hubp_pg_control(hws, hubp->inst, false);
+
 		dpp->funcs->dpp_reset(dpp);
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);

drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c

@@ -1069,8 +1069,13 @@ static void dcn20_power_on_plane(
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		dcn20_dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true);
-		dcn20_hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true);
+
+		if (hws->funcs.dpp_pg_control)
+			hws->funcs.dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true);
+
+		if (hws->funcs.hubp_pg_control)
+			hws->funcs.hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true);
+
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
 		DC_LOG_DEBUG(

drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c

@@ -295,7 +295,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = {
 	.num_banks = 8,
 	.num_chans = 4,
 	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 23.84,
+	.dram_clock_change_latency_us = 11.72,
 	.return_bus_width_bytes = 64,
 	.dispclk_dppclk_vco_speed_mhz = 3600,
 	.xfc_bus_transport_time_us = 4,

drivers/gpu/drm/panfrost/panfrost_device.h

@@ -88,6 +88,7 @@ struct panfrost_device {
 	/* pm_domains for devices with more than one. */
 	struct device *pm_domain_devs[MAX_PM_DOMAINS];
 	struct device_link *pm_domain_links[MAX_PM_DOMAINS];
+	bool coherent;
 
 	struct panfrost_features features;
 	const struct panfrost_compatible *comp;

drivers/gpu/drm/panfrost/panfrost_drv.c

@@ -587,6 +587,8 @@ static int panfrost_probe(struct platform_device *pdev)
 	if (!pfdev->comp)
 		return -ENODEV;
 
+	pfdev->coherent = device_get_dma_attr(&pdev->dev) == DEV_DMA_COHERENT;
+
 	/* Allocate and initialze the DRM device. */
 	ddev = drm_dev_alloc(&panfrost_drm_driver, &pdev->dev);
 	if (IS_ERR(ddev))

drivers/gpu/drm/panfrost/panfrost_gem.c

@@ -218,6 +218,7 @@ static const struct drm_gem_object_funcs panfrost_gem_funcs = {
  */
 struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t size)
 {
+	struct panfrost_device *pfdev = dev->dev_private;
 	struct panfrost_gem_object *obj;
 
 	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
@@ -227,6 +228,7 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t
 	INIT_LIST_HEAD(&obj->mappings.list);
 	mutex_init(&obj->mappings.lock);
 	obj->base.base.funcs = &panfrost_gem_funcs;
+	obj->base.map_cached = pfdev->coherent;
 
 	return &obj->base.base;
 }

drivers/gpu/drm/panfrost/panfrost_mmu.c

@@ -371,6 +371,7 @@ int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)
 		.pgsize_bitmap	= SZ_4K | SZ_2M,
 		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
 		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
+		.coherent_walk	= pfdev->coherent,
 		.tlb		= &mmu_tlb_ops,
 		.iommu_dev	= pfdev->dev,
 	};

drivers/i2c/busses/i2c-tegra.c

@@ -326,6 +326,8 @@ static void i2c_writel(struct tegra_i2c_dev *i2c_dev, u32 val, unsigned int reg)
 	/* read back register to make sure that register writes completed */
 	if (reg != I2C_TX_FIFO)
 		readl_relaxed(i2c_dev->base + tegra_i2c_reg_addr(i2c_dev, reg));
+	else if (i2c_dev->is_vi)
+		readl_relaxed(i2c_dev->base + tegra_i2c_reg_addr(i2c_dev, I2C_INT_STATUS));
 }
 
 static u32 i2c_readl(struct tegra_i2c_dev *i2c_dev, unsigned int reg)
@@ -339,6 +341,21 @@ static void i2c_writesl(struct tegra_i2c_dev *i2c_dev, void *data,
 	writesl(i2c_dev->base + tegra_i2c_reg_addr(i2c_dev, reg), data, len);
 }
 
+static void i2c_writesl_vi(struct tegra_i2c_dev *i2c_dev, void *data,
+			   unsigned int reg, unsigned int len)
+{
+	u32 *data32 = data;
+
+	/*
+	 * VI I2C controller has known hardware bug where writes get stuck
+	 * when immediate multiple writes happen to TX_FIFO register.
+	 * Recommended software work around is to read I2C register after
+	 * each write to TX_FIFO register to flush out the data.
+	 */
+	while (len--)
+		i2c_writel(i2c_dev, *data32++, reg);
+}
+
 static void i2c_readsl(struct tegra_i2c_dev *i2c_dev, void *data,
 		       unsigned int reg, unsigned int len)
 {
@@ -811,7 +828,10 @@ static int tegra_i2c_fill_tx_fifo(struct tegra_i2c_dev *i2c_dev)
 		i2c_dev->msg_buf_remaining = buf_remaining;
 		i2c_dev->msg_buf = buf + words_to_transfer * BYTES_PER_FIFO_WORD;
 
-		i2c_writesl(i2c_dev, buf, I2C_TX_FIFO, words_to_transfer);
+		if (i2c_dev->is_vi)
+			i2c_writesl_vi(i2c_dev, buf, I2C_TX_FIFO, words_to_transfer);
+		else
+			i2c_writesl(i2c_dev, buf, I2C_TX_FIFO, words_to_transfer);
 
 		buf += words_to_transfer * BYTES_PER_FIFO_WORD;
 	}

drivers/iommu/intel/iommu.c

@@ -3350,6 +3350,11 @@ static int __init init_dmars(void)
 
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
+
+		if (!intel_iommu_strict && cap_caching_mode(iommu->cap)) {
+			pr_warn("Disable batched IOTLB flush due to virtualization");
+			intel_iommu_strict = 1;
+		}
 		intel_svm_check(iommu);
 	}
 

drivers/iommu/io-pgtable-arm.c

@@ -417,7 +417,13 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
 
-	if (prot & IOMMU_CACHE)
+	/*
+	 * Also Mali has its own notions of shareability wherein its Inner
+	 * domain covers the cores within the GPU, and its Outer domain is
+	 * "outside the GPU" (i.e. either the Inner or System domain in CPU
+	 * terms, depending on coherency).
+	 */
+	if (prot & IOMMU_CACHE && data->iop.fmt != ARM_MALI_LPAE)
 		pte |= ARM_LPAE_PTE_SH_IS;
 	else
 		pte |= ARM_LPAE_PTE_SH_OS;
@@ -1021,6 +1027,9 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) |
 					  ARM_MALI_LPAE_TTBR_READ_INNER |
 					  ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	if (cfg->coherent_walk)
+		cfg->arm_mali_lpae_cfg.transtab |= ARM_MALI_LPAE_TTBR_SHARE_OUTER;
+
 	return &data->iop;
 
 out_free_data:

drivers/misc/habanalabs/common/device.c

@@ -1425,6 +1425,15 @@ void hl_device_fini(struct hl_device *hdev)
 		}
 	}
 
+	/* Disable PCI access from device F/W so it won't send us additional
+	 * interrupts. We disable MSI/MSI-X at the halt_engines function and we
+	 * can't have the F/W sending us interrupts after that. We need to
+	 * disable the access here because if the device is marked disable, the
+	 * message won't be send. Also, in case of heartbeat, the device CPU is
+	 * marked as disable so this message won't be sent
+	 */
+	hl_fw_send_pci_access_msg(hdev,	CPUCP_PACKET_DISABLE_PCI_ACCESS);
+
 	/* Mark device as disabled */
 	hdev->disabled = true;
 

drivers/misc/habanalabs/common/firmware_if.c

@@ -385,6 +385,10 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 	}
 	counters->rx_throughput = result;
 
+	memset(&pkt, 0, sizeof(pkt));
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_THROUGHPUT_GET <<
+			CPUCP_PKT_CTL_OPCODE_SHIFT);
+
 	/* Fetch PCI tx counter */
 	pkt.index = cpu_to_le32(cpucp_pcie_throughput_tx);
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
@@ -397,6 +401,7 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 	counters->tx_throughput = result;
 
 	/* Fetch PCI replay counter */
+	memset(&pkt, 0, sizeof(pkt));
 	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_REPLAY_CNT_GET <<
 			CPUCP_PKT_CTL_OPCODE_SHIFT);
 

drivers/misc/habanalabs/common/habanalabs_ioctl.c

@@ -133,6 +133,8 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
 
 	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
 					&hw_idle.busy_engines_mask_ext, NULL);
+	hw_idle.busy_engines_mask =
+			lower_32_bits(hw_idle.busy_engines_mask_ext);
 
 	return copy_to_user(out, &hw_idle,
 		min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;

drivers/misc/habanalabs/gaudi/gaudi.c

@@ -3119,7 +3119,8 @@ static int gaudi_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
 	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
 			VM_DONTCOPY | VM_NORESERVE;
 
-	rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size);
+	rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr,
+				(dma_addr - HOST_PHYS_BASE), size);
 	if (rc)
 		dev_err(hdev->dev, "dma_mmap_coherent error %d", rc);