Merge drm/drm-next into drm-misc-next

drm-misc-next hasn't been updated in a while and I need a post -rc2
state to merge some vc4 patches.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

30 files changed, 472 insertions, 385 deletions

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index e93375c710b9..cc7338f9e0d1 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -1023,16 +1023,7 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 	port &= IO_SPACE_LIMIT;
 	return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port;
 }
-#define __pci_ioport_unmap __pci_ioport_unmap
-static inline void __pci_ioport_unmap(void __iomem *p)
-{
-	uintptr_t start = (uintptr_t) PCI_IOBASE;
-	uintptr_t addr = (uintptr_t) p;
-
-	if (addr >= start && addr < start + IO_SPACE_LIMIT)
-		return;
-	iounmap(p);
-}
+#define ARCH_HAS_GENERIC_IOPORT_MAP
 #endif
 
 #ifndef ioport_unmap
@@ -1048,21 +1039,10 @@ extern void ioport_unmap(void __iomem *p);
 #endif /* CONFIG_HAS_IOPORT_MAP */
 
 #ifndef CONFIG_GENERIC_IOMAP
-struct pci_dev;
-extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
-
-#ifndef __pci_ioport_unmap
-static inline void __pci_ioport_unmap(void __iomem *p) {}
-#endif
-
 #ifndef pci_iounmap
-#define pci_iounmap pci_iounmap
-static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
-{
-	__pci_ioport_unmap(p);
-}
+#define ARCH_WANTS_GENERIC_PCI_IOUNMAP
+#endif
 #endif
-#endif /* CONFIG_GENERIC_IOMAP */
 
 #ifndef xlate_dev_mem_ptr
 #define xlate_dev_mem_ptr xlate_dev_mem_ptr
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index 9b3eb6d86200..08237ae8b840 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size)
 }
 #endif
 
-#ifdef CONFIG_PCI
-/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
-struct pci_dev;
-extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
-#elif defined(CONFIG_GENERIC_IOMAP)
-struct pci_dev;
-static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
-{ }
-#endif
-
 #include <asm-generic/pci_iomap.h>
 
 #endif
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index c1ab6a6e72b5..d3eae6cdbacb 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -197,10 +197,12 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number)
 	return hv_vp_index[cpu_number];
 }
 
-static inline int cpumask_to_vpset(struct hv_vpset *vpset,
-				    const struct cpumask *cpus)
+static inline int __cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus,
+				    bool exclude_self)
 {
 	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+	int this_cpu = smp_processor_id();
 
 	/* valid_bank_mask can represent up to 64 banks */
 	if (hv_max_vp_index / 64 >= 64)
@@ -218,6 +220,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	 * Some banks may end up being empty but this is acceptable.
 	 */
 	for_each_cpu(cpu, cpus) {
+		if (exclude_self && cpu == this_cpu)
+			continue;
 		vcpu = hv_cpu_number_to_vp_number(cpu);
 		if (vcpu == VP_INVAL)
 			return -1;
@@ -232,6 +236,19 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	return nr_bank;
 }
 
+static inline int cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus)
+{
+	return __cpumask_to_vpset(vpset, cpus, false);
+}
+
+static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset,
+				    const struct cpumask *cpus)
+{
+	WARN_ON_ONCE(preemptible());
+	return __cpumask_to_vpset(vpset, cpus, true);
+}
+
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);
diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
index df636c6d8e6c..5a2f9bf53384 100644
--- a/include/asm-generic/pci_iomap.h
+++ b/include/asm-generic/pci_iomap.h
@@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
 extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
 					unsigned long offset,
 					unsigned long maxlen);
+extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
 /* Create a virtual mapping cookie for a port on a given PCI device.
  * Do not call this directly, it exists to make it easier for architectures
  * to override */
@@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
 {
 	return NULL;
 }
+static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
+{ }
 #endif
 
 #endif /* __ASM_GENERIC_PCI_IOMAP_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index aa50bf2959fe..f2984af2b85b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -116,11 +116,7 @@
  * GCC 4.5 and later have a 32 bytes section alignment for structures.
  * Except GCC 4.9, that feels the need to align on 64 bytes.
  */
-#if __GNUC__ == 4 && __GNUC_MINOR__ == 9
-#define STRUCT_ALIGNMENT 64
-#else
 #define STRUCT_ALIGNMENT 32
-#endif
 #define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT)
 
 /*
diff --git a/include/drm/amd_asic_type.h b/include/drm/amd_asic_type.h
index 0f66a0d9f06d..90b69270f2fa 100644
--- a/include/drm/amd_asic_type.h
+++ b/include/drm/amd_asic_type.h
@@ -62,6 +62,7 @@ enum amd_asic_type {
 	CHIP_DIMGREY_CAVEFISH,	/* 33 */
 	CHIP_BEIGE_GOBY,	/* 34 */
 	CHIP_YELLOW_CARP,	/* 35 */
+	CHIP_IP_DISCOVERY,	/* 36 */
 	CHIP_LAST,
 };
 
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index b83ba0285f29..b501d0badaea 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -616,6 +616,18 @@ struct drm_display_info {
 	 * @monitor_range: Frequency range supported by monitor range descriptor
 	 */
 	struct drm_monitor_range_info monitor_range;
+
+	/**
+	 * @mso_stream_count: eDP Multi-SST Operation (MSO) stream count from
+	 * the DisplayID VESA vendor block. 0 for conventional Single-Stream
+	 * Transport (SST), or 2 or 4 MSO streams.
+	 */
+	u8 mso_stream_count;
+
+	/**
+	 * @mso_pixel_overlap: eDP MSO segment pixel overlap, 0-8 pixels.
+	 */
+	u8 mso_pixel_overlap;
 };
 
 int drm_display_info_set_bus_formats(struct drm_display_info *info,
diff --git a/include/drm/drm_displayid.h b/include/drm/drm_displayid.h
index ec64d141f578..7ffbd9f7bfc7 100644
--- a/include/drm/drm_displayid.h
+++ b/include/drm/drm_displayid.h
@@ -23,38 +23,71 @@
 #define DRM_DISPLAYID_H
 
 #include <linux/types.h>
+#include <linux/bits.h>
 
 struct edid;
 
-#define DATA_BLOCK_PRODUCT_ID 0x00
-#define DATA_BLOCK_DISPLAY_PARAMETERS 0x01
-#define DATA_BLOCK_COLOR_CHARACTERISTICS 0x02
-#define DATA_BLOCK_TYPE_1_DETAILED_TIMING 0x03
-#define DATA_BLOCK_TYPE_2_DETAILED_TIMING 0x04
-#define DATA_BLOCK_TYPE_3_SHORT_TIMING 0x05
-#define DATA_BLOCK_TYPE_4_DMT_TIMING 0x06
-#define DATA_BLOCK_VESA_TIMING 0x07
-#define DATA_BLOCK_CEA_TIMING 0x08
-#define DATA_BLOCK_VIDEO_TIMING_RANGE 0x09
-#define DATA_BLOCK_PRODUCT_SERIAL_NUMBER 0x0a
-#define DATA_BLOCK_GP_ASCII_STRING 0x0b
-#define DATA_BLOCK_DISPLAY_DEVICE_DATA 0x0c
-#define DATA_BLOCK_INTERFACE_POWER_SEQUENCING 0x0d
-#define DATA_BLOCK_TRANSFER_CHARACTERISTICS 0x0e
-#define DATA_BLOCK_DISPLAY_INTERFACE 0x0f
-#define DATA_BLOCK_STEREO_DISPLAY_INTERFACE 0x10
-#define DATA_BLOCK_TILED_DISPLAY 0x12
-#define DATA_BLOCK_CTA 0x81
-
-#define DATA_BLOCK_VENDOR_SPECIFIC 0x7f
-
-#define PRODUCT_TYPE_EXTENSION 0
-#define PRODUCT_TYPE_TEST 1
-#define PRODUCT_TYPE_PANEL 2
-#define PRODUCT_TYPE_MONITOR 3
-#define PRODUCT_TYPE_TV 4
-#define PRODUCT_TYPE_REPEATER 5
-#define PRODUCT_TYPE_DIRECT_DRIVE 6
+#define VESA_IEEE_OUI				0x3a0292
+
+/* DisplayID Structure versions */
+#define DISPLAY_ID_STRUCTURE_VER_12		0x12
+#define DISPLAY_ID_STRUCTURE_VER_20		0x20
+
+/* DisplayID Structure v1r2 Data Blocks */
+#define DATA_BLOCK_PRODUCT_ID			0x00
+#define DATA_BLOCK_DISPLAY_PARAMETERS		0x01
+#define DATA_BLOCK_COLOR_CHARACTERISTICS	0x02
+#define DATA_BLOCK_TYPE_1_DETAILED_TIMING	0x03
+#define DATA_BLOCK_TYPE_2_DETAILED_TIMING	0x04
+#define DATA_BLOCK_TYPE_3_SHORT_TIMING		0x05
+#define DATA_BLOCK_TYPE_4_DMT_TIMING		0x06
+#define DATA_BLOCK_VESA_TIMING			0x07
+#define DATA_BLOCK_CEA_TIMING			0x08
+#define DATA_BLOCK_VIDEO_TIMING_RANGE		0x09
+#define DATA_BLOCK_PRODUCT_SERIAL_NUMBER	0x0a
+#define DATA_BLOCK_GP_ASCII_STRING		0x0b
+#define DATA_BLOCK_DISPLAY_DEVICE_DATA		0x0c
+#define DATA_BLOCK_INTERFACE_POWER_SEQUENCING	0x0d
+#define DATA_BLOCK_TRANSFER_CHARACTERISTICS	0x0e
+#define DATA_BLOCK_DISPLAY_INTERFACE		0x0f
+#define DATA_BLOCK_STEREO_DISPLAY_INTERFACE	0x10
+#define DATA_BLOCK_TILED_DISPLAY		0x12
+#define DATA_BLOCK_VENDOR_SPECIFIC		0x7f
+#define DATA_BLOCK_CTA				0x81
+
+/* DisplayID Structure v2r0 Data Blocks */
+#define DATA_BLOCK_2_PRODUCT_ID			0x20
+#define DATA_BLOCK_2_DISPLAY_PARAMETERS		0x21
+#define DATA_BLOCK_2_TYPE_7_DETAILED_TIMING	0x22
+#define DATA_BLOCK_2_TYPE_8_ENUMERATED_TIMING	0x23
+#define DATA_BLOCK_2_TYPE_9_FORMULA_TIMING	0x24
+#define DATA_BLOCK_2_DYNAMIC_VIDEO_TIMING	0x25
+#define DATA_BLOCK_2_DISPLAY_INTERFACE_FEATURES	0x26
+#define DATA_BLOCK_2_STEREO_DISPLAY_INTERFACE	0x27
+#define DATA_BLOCK_2_TILED_DISPLAY_TOPOLOGY	0x28
+#define DATA_BLOCK_2_CONTAINER_ID		0x29
+#define DATA_BLOCK_2_VENDOR_SPECIFIC		0x7e
+#define DATA_BLOCK_2_CTA_DISPLAY_ID		0x81
+
+/* DisplayID Structure v1r2 Product Type */
+#define PRODUCT_TYPE_EXTENSION			0
+#define PRODUCT_TYPE_TEST			1
+#define PRODUCT_TYPE_PANEL			2
+#define PRODUCT_TYPE_MONITOR			3
+#define PRODUCT_TYPE_TV				4
+#define PRODUCT_TYPE_REPEATER			5
+#define PRODUCT_TYPE_DIRECT_DRIVE		6
+
+/* DisplayID Structure v2r0 Display Product Primary Use Case (~Product Type) */
+#define PRIMARY_USE_EXTENSION			0
+#define PRIMARY_USE_TEST			1
+#define PRIMARY_USE_GENERIC			2
+#define PRIMARY_USE_TV				3
+#define PRIMARY_USE_DESKTOP_PRODUCTIVITY	4
+#define PRIMARY_USE_DESKTOP_GAMING		5
+#define PRIMARY_USE_PRESENTATION		6
+#define PRIMARY_USE_HEAD_MOUNTED_VR		7
+#define PRIMARY_USE_HEAD_MOUNTED_AR		8
 
 struct displayid_header {
 	u8 rev;
@@ -96,6 +129,16 @@ struct displayid_detailed_timing_block {
 	struct displayid_detailed_timings_1 timings[];
 };
 
+#define DISPLAYID_VESA_MSO_OVERLAP	GENMASK(3, 0)
+#define DISPLAYID_VESA_MSO_MODE		GENMASK(6, 5)
+
+struct displayid_vesa_vendor_specific_block {
+	struct displayid_block base;
+	u8 oui[3];
+	u8 data_structure_type;
+	u8 mso;
+} __packed;
+
 /* DisplayID iteration */
 struct displayid_iter {
 	const struct edid *edid;
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index b653c5da7065..afdf7f4183f9 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1346,6 +1346,10 @@ struct drm_panel;
 #define DP_MAX_LANE_COUNT_PHY_REPEATER			    0xf0004 /* 1.4a */
 #define DP_Repeater_FEC_CAPABILITY			    0xf0004 /* 1.4 */
 #define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT		    0xf0005 /* 1.4a */
+#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER	    0xf0006 /* 2.0 */
+# define DP_PHY_REPEATER_128B132B_SUPPORTED		    (1 << 0)
+/* See DP_128B132B_SUPPORTED_LINK_RATES for values */
+#define DP_PHY_REPEATER_128B132B_RATES			    0xf0007 /* 2.0 */
 
 enum drm_dp_phy {
 	DP_PHY_DPRX,
@@ -1522,6 +1526,8 @@ u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE],
 				     int lane);
 u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE],
 					  int lane);
+u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE],
+				   int lane);
 u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE],
 					 unsigned int lane);
 
diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h
index 55c3b123581b..c1e2a43d2d1e 100644
--- a/include/drm/i915_component.h
+++ b/include/drm/i915_component.h
@@ -29,6 +29,7 @@
 enum i915_component_type {
 	I915_COMPONENT_AUDIO = 1,
 	I915_COMPONENT_HDCP,
+	I915_COMPONENT_PXP
 };
 
 /* MAX_PORT is the number of port
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index eee18fa53b54..c00ac54692d7 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -632,18 +632,16 @@
 	INTEL_VGA_DEVICE(0x4905, info), \
 	INTEL_VGA_DEVICE(0x4906, info), \
 	INTEL_VGA_DEVICE(0x4907, info), \
-	INTEL_VGA_DEVICE(0x4908, info)
+	INTEL_VGA_DEVICE(0x4908, info), \
+	INTEL_VGA_DEVICE(0x4909, info)
 
 /* ADL-S */
 #define INTEL_ADLS_IDS(info) \
 	INTEL_VGA_DEVICE(0x4680, info), \
-	INTEL_VGA_DEVICE(0x4681, info), \
 	INTEL_VGA_DEVICE(0x4682, info), \
-	INTEL_VGA_DEVICE(0x4683, info), \
 	INTEL_VGA_DEVICE(0x4688, info), \
-	INTEL_VGA_DEVICE(0x4689, info), \
+	INTEL_VGA_DEVICE(0x468A, info), \
 	INTEL_VGA_DEVICE(0x4690, info), \
-	INTEL_VGA_DEVICE(0x4691, info), \
 	INTEL_VGA_DEVICE(0x4692, info), \
 	INTEL_VGA_DEVICE(0x4693, info)
 
diff --git a/include/drm/i915_pxp_tee_interface.h b/include/drm/i915_pxp_tee_interface.h
new file mode 100644
index 000000000000..af593ec64469
--- /dev/null
+++ b/include/drm/i915_pxp_tee_interface.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef _I915_PXP_TEE_INTERFACE_H_
+#define _I915_PXP_TEE_INTERFACE_H_
+
+#include <linux/mutex.h>
+#include <linux/device.h>
+
+/**
+ * struct i915_pxp_component_ops - ops for PXP services.
+ * @owner: Module providing the ops
+ * @send: sends data to PXP
+ * @receive: receives data from PXP
+ */
+struct i915_pxp_component_ops {
+	/**
+	 * @owner: owner of the module provding the ops
+	 */
+	struct module *owner;
+
+	int (*send)(struct device *dev, const void *message, size_t size);
+	int (*recv)(struct device *dev, void *buffer, size_t size);
+};
+
+/**
+ * struct i915_pxp_component - Used for communication between i915 and TEE
+ * drivers for the PXP services
+ * @tee_dev: device that provide the PXP service from TEE Bus.
+ * @pxp_ops: Ops implemented by TEE driver, used by i915 driver.
+ */
+struct i915_pxp_component {
+	struct device *tee_dev;
+	const struct i915_pxp_component_ops *ops;
+
+	/* To protect the above members. */
+	struct mutex mutex;
+};
+
+#endif /* _I915_TEE_PXP_INTERFACE_H_ */
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 68d6069572aa..5f087575194b 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -322,7 +322,7 @@ int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem);
  */
 void ttm_bo_tt_destroy(struct ttm_buffer_object *bo);
 
-void ttm_move_memcpy(struct ttm_buffer_object *bo,
+void ttm_move_memcpy(bool clear,
 		     u32 num_pages,
 		     struct ttm_kmap_iter *dst_iter,
 		     struct ttm_kmap_iter *src_iter);
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index e1c705fdfa7c..db2e147e069f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
  * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains
  * per-socket cgroup information except for memcg association.
  *
- * On legacy hierarchies, net_prio and net_cls controllers directly set
- * attributes on each sock which can then be tested by the network layer.
- * On the default hierarchy, each sock is associated with the cgroup it was
- * created in and the networking layer can match the cgroup directly.
- *
- * To avoid carrying all three cgroup related fields separately in sock,
- * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.
- * On boot, sock_cgroup_data records the cgroup that the sock was created
- * in so that cgroup2 matches can be made; however, once either net_prio or
- * net_cls starts being used, the area is overridden to carry prioidx and/or
- * classid.  The two modes are distinguished by whether the lowest bit is
- * set.  Clear bit indicates cgroup pointer while set bit prioidx and
- * classid.
- *
- * While userland may start using net_prio or net_cls at any time, once
- * either is used, cgroup2 matching no longer works.  There is no reason to
- * mix the two and this is in line with how legacy and v2 compatibility is
- * handled.  On mode switch, cgroup references which are already being
- * pointed to by socks may be leaked.  While this can be remedied by adding
- * synchronization around sock_cgroup_data, given that the number of leaked
- * cgroups is bound and highly unlikely to be high, this seems to be the
- * better trade-off.
+ * On legacy hierarchies, net_prio and net_cls controllers directly
+ * set attributes on each sock which can then be tested by the network
+ * layer. On the default hierarchy, each sock is associated with the
+ * cgroup it was created in and the networking layer can match the
+ * cgroup directly.
  */
 struct sock_cgroup_data {
-	union {
-#ifdef __LITTLE_ENDIAN
-		struct {
-			u8	is_data : 1;
-			u8	no_refcnt : 1;
-			u8	unused : 6;
-			u8	padding;
-			u16	prioidx;
-			u32	classid;
-		} __packed;
-#else
-		struct {
-			u32	classid;
-			u16	prioidx;
-			u8	padding;
-			u8	unused : 6;
-			u8	no_refcnt : 1;
-			u8	is_data : 1;
-		} __packed;
+	struct cgroup	*cgroup; /* v2 */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	u32		classid; /* v1 */
+#endif
+#ifdef CONFIG_CGROUP_NET_PRIO
+	u16		prioidx; /* v1 */
 #endif
-		u64		val;
-	};
 };
 
-/*
- * There's a theoretical window where the following accessors race with
- * updaters and return part of the previous pointer as the prioidx or
- * classid.  Such races are short-lived and the result isn't critical.
- */
 static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 1 which is always the ID of the root cgroup */
-	return (skcd->is_data & 1) ? skcd->prioidx : 1;
+#ifdef CONFIG_CGROUP_NET_PRIO
+	return READ_ONCE(skcd->prioidx);
+#else
+	return 1;
+#endif
 }
 
 static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 0 which is the unconfigured default classid */
-	return (skcd->is_data & 1) ? skcd->classid : 0;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	return READ_ONCE(skcd->classid);
+#else
+	return 0;
+#endif
 }
 
-/*
- * If invoked concurrently, the updaters may clobber each other.  The
- * caller is responsible for synchronization.
- */
 static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 					   u16 prioidx)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_prioidx(&skcd_buf) == prioidx)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.prioidx = prioidx;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_PRIO
+	WRITE_ONCE(skcd->prioidx, prioidx);
+#endif
 }
 
 static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
 					   u32 classid)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_classid(&skcd_buf) == classid)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.classid = classid;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	WRITE_ONCE(skcd->classid, classid);
+#endif
 }
 
 #else	/* CONFIG_SOCK_CGROUP_DATA */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 7bf60454a313..75c151413fda 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
  */
 #ifdef CONFIG_SOCK_CGROUP_DATA
 
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-extern spinlock_t cgroup_sk_update_lock;
-#endif
-
-void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
 void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 {
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-	unsigned long v;
-
-	/*
-	 * @skcd->val is 64bit but the following is safe on 32bit too as we
-	 * just need the lower ulong to be written and read atomically.
-	 */
-	v = READ_ONCE(skcd->val);
-
-	if (v & 3)
-		return &cgrp_dfl_root.cgrp;
-
-	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
-#else
-	return (struct cgroup *)(unsigned long)skcd->val;
-#endif
+	return skcd->cgroup;
 }
 
 #else	/* CONFIG_CGROUP_DATA */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 49b0ac8b6fd3..3c4de9b6c6e3 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -62,19 +62,6 @@
 #define __no_sanitize_coverage
 #endif
 
-/*
- * Not all versions of clang implement the type-generic versions
- * of the builtin overflow checkers. Fortunately, clang implements
- * __has_builtin allowing us to avoid awkward version
- * checks. Unfortunately, we don't know which version of gcc clang
- * pretends to be, so the macro may or may not be defined.
- */
-#if __has_builtin(__builtin_mul_overflow) && \
-    __has_builtin(__builtin_add_overflow) && \
-    __has_builtin(__builtin_sub_overflow)
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 21c36b69eb06..bd2b881c6b63 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -95,10 +95,8 @@
 
 #if GCC_VERSION >= 70000
 #define KASAN_ABI_VERSION 5
-#elif GCC_VERSION >= 50000
+#else
 #define KASAN_ABI_VERSION 4
-#elif GCC_VERSION >= 40902
-#define KASAN_ABI_VERSION 3
 #endif
 
 #if __has_attribute(__no_sanitize_address__)
@@ -125,10 +123,6 @@
 #define __no_sanitize_coverage
 #endif
 
-#if GCC_VERSION >= 50100
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 /*
  * Turn individual warnings and errors on and off locally, depending
  * on version.
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index b67261a1e3e9..3d5af56337bd 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
     (typeof(ptr)) (__ptr + (off)); })
 #endif
 
+#define absolute_pointer(val)	RELOC_HIDE((void *)(val), 0)
+
 #ifndef OPTIMIZER_HIDE_VAR
 /* Make the optimizer believe the variable can be manipulated arbitrarily. */
 #define OPTIMIZER_HIDE_VAR(var)						\
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 8f2106e9e5c1..e6ec63403965 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -21,29 +21,6 @@
  */
 
 /*
- * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17.
- * In the meantime, to support gcc < 5, we implement __has_attribute
- * by hand.
- */
-#ifndef __has_attribute
-# define __has_attribute(x) __GCC4_has_attribute_##x
-# define __GCC4_has_attribute___assume_aligned__      1
-# define __GCC4_has_attribute___copy__                0
-# define __GCC4_has_attribute___designated_init__     0
-# define __GCC4_has_attribute___error__               1
-# define __GCC4_has_attribute___externally_visible__  1
-# define __GCC4_has_attribute___no_caller_saved_registers__ 0
-# define __GCC4_has_attribute___noclone__             1
-# define __GCC4_has_attribute___no_profile_instrument_function__ 0
-# define __GCC4_has_attribute___nonstring__           0
-# define __GCC4_has_attribute___no_sanitize_address__ 1
-# define __GCC4_has_attribute___no_sanitize_undefined__ 1
-# define __GCC4_has_attribute___no_sanitize_coverage__ 0
-# define __GCC4_has_attribute___fallthrough__         0
-# define __GCC4_has_attribute___warning__             1
-#endif
-
-/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute
  */
 #define __alias(symbol)                 __attribute__((__alias__(#symbol)))
@@ -77,7 +54,6 @@
  * compiler should see some alignment anyway, when the return value is
  * massaged by 'flags = ptr & 3; ptr &= ~3;').
  *
- * Optional: only supported since gcc >= 4.9
  * Optional: not supported by icc
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index 45f1d4812a37..dbd235ab447f 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -380,7 +380,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj,
  */
 static inline bool __must_check dma_resv_trylock(struct dma_resv *obj)
 {
-	return ww_mutex_trylock(&obj->lock);
+	return ww_mutex_trylock(&obj->lock, NULL);
 }
 
 /**
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b066024c62e3..34de69b3b8ba 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
 
 void memblock_free_all(void);
+void memblock_free_ptr(void *ptr, size_t size);
 void reset_node_managed_pages(pg_data_t *pgdat);
 void reset_all_zones_managed_pages(void);
 
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index b179f1e3541a..96e113e23d04 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm)
 	up_read(&mm->mmap_lock);
 }
 
-static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
-{
-	if (mmap_read_trylock(mm)) {
-		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
-		return true;
-	}
-	return false;
-}
-
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
 	__mmap_lock_trace_released(mm, false);
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 0f12345c21fb..4669632bd72b 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -6,12 +6,9 @@
 #include <linux/limits.h>
 
 /*
- * In the fallback code below, we need to compute the minimum and
- * maximum values representable in a given type. These macros may also
- * be useful elsewhere, so we provide them outside the
- * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
- *
- * It would seem more obvious to do something like
+ * We need to compute the minimum and maximum values representable in a given
+ * type. These macros may also be useful elsewhere. It would seem more obvious
+ * to do something like:
  *
  * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
  * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
@@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	return unlikely(overflow);
 }
 
-#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
  * a, b and *d having the same type (similar to the min() and max()
@@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	__builtin_mul_overflow(__a, __b, __d);	\
 }))
 
-#else
-
-
-/* Checking for unsigned overflow is relatively easy without causing UB. */
-#define __unsigned_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a + __b;			\
-	*__d < __a;				\
-})
-#define __unsigned_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a - __b;			\
-	__a < __b;				\
-})
-/*
- * If one of a or b is a compile-time constant, this avoids a division.
- */
-#define __unsigned_mul_overflow(a, b, d) ({		\
-	typeof(a) __a = (a);				\
-	typeof(b) __b = (b);				\
-	typeof(d) __d = (d);				\
-	(void) (&__a == &__b);				\
-	(void) (&__a == __d);				\
-	*__d = __a * __b;				\
-	__builtin_constant_p(__b) ?			\
-	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
-	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
-})
-
-/*
- * For signed types, detecting overflow is much harder, especially if
- * we want to avoid UB. But the interface of these macros is such that
- * we must provide a result in *d, and in fact we must produce the
- * result promised by gcc's builtins, which is simply the possibly
- * wrapped-around value. Fortunately, we can just formally do the
- * operations in the widest relevant unsigned type (u64) and then
- * truncate the result - gcc is smart enough to generate the same code
- * with and without the (u64) casts.
- */
-
-/*
- * Adding two signed integers can overflow only if they have the same
- * sign, and overflow has happened iff the result has the opposite
- * sign.
- */
-#define __signed_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a + (u64)__b;		\
-	(((~(__a ^ __b)) & (*__d ^ __a))	\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Subtraction is similar, except that overflow can now happen only
- * when the signs are opposite. In this case, overflow has happened if
- * the result has the opposite sign of a.
- */
-#define __signed_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a - (u64)__b;		\
-	((((__a ^ __b)) & (*__d ^ __a))		\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Signed multiplication is rather hard. gcc always follows C99, so
- * division is truncated towards 0. This means that we can write the
- * overflow check like this:
- *
- * (a > 0 && (b > MAX/a || b < MIN/a)) ||
- * (a < -1 && (b > MIN/a || b < MAX/a) ||
- * (a == -1 && b == MIN)
- *
- * The redundant casts of -1 are to silence an annoying -Wtype-limits
- * (included in -Wextra) warning: When the type is u8 or u16, the
- * __b_c_e in check_mul_overflow obviously selects
- * __unsigned_mul_overflow, but unfortunately gcc still parses this
- * code and warns about the limited range of __b.
- */
-
-#define __signed_mul_overflow(a, b, d) ({				\
-	typeof(a) __a = (a);						\
-	typeof(b) __b = (b);						\
-	typeof(d) __d = (d);						\
-	typeof(a) __tmax = type_max(typeof(a));				\
-	typeof(a) __tmin = type_min(typeof(a));				\
-	(void) (&__a == &__b);						\
-	(void) (&__a == __d);						\
-	*__d = (u64)__a * (u64)__b;					\
-	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
-	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
-	(__b == (typeof(__b))-1 && __a == __tmin);			\
-})
-
-
-#define check_add_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d)))
-
-#define check_sub_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d)))
-
-#define check_mul_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d)))
-
-#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
-
 /** check_shl_overflow() - Calculate a left-shifted value and check overflow
  *
  * @a: Value to be shifted
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e12b524426b0..39039ce8ac4c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1471,6 +1471,7 @@ struct task_struct {
 					mce_whole_page : 1,
 					__mce_reserved : 62;
 	struct callback_head		mce_kill_me;
+	int				mce_count;
 #endif
 
 #ifdef CONFIG_KRETPROBES
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6bdb0db3e825..841e2f0f5240 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk,
 	WRITE_ONCE(newsk->prev, prev);
 	WRITE_ONCE(next->prev, newsk);
 	WRITE_ONCE(prev->next, newsk);
-	list->qlen++;
+	WRITE_ONCE(list->qlen, list->qlen + 1);
 }
 
 static inline void __skb_queue_splice(const struct sk_buff_head *list,
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 5265024e8b90..207101a9c5c3 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -27,6 +27,12 @@ enum iter_type {
 	ITER_DISCARD,
 };
 
+struct iov_iter_state {
+	size_t iov_offset;
+	size_t count;
+	unsigned long nr_segs;
+};
+
 struct iov_iter {
 	u8 iter_type;
 	bool data_source;
@@ -47,7 +53,6 @@ struct iov_iter {
 		};
 		loff_t xarray_start;
 	};
-	size_t truncated;
 };
 
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
@@ -55,6 +60,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 	return i->iter_type;
 }
 
+static inline void iov_iter_save_state(struct iov_iter *iter,
+				       struct iov_iter_state *state)
+{
+	state->iov_offset = iter->iov_offset;
+	state->count = iter->count;
+	state->nr_segs = iter->nr_segs;
+}
+
 static inline bool iter_is_iovec(const struct iov_iter *i)
 {
 	return iov_iter_type(i) == ITER_IOVEC;
@@ -233,6 +246,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
+void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state);
 
 const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
 
@@ -255,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
 	 * conversion in assignement is by definition greater than all
 	 * values of size_t, including old i->count.
 	 */
-	if (i->count > count) {
-		i->truncated += i->count - count;
+	if (i->count > count)
 		i->count = count;
-	}
 }
 
 /*
@@ -267,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
  */
 static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
-	i->truncated -= count - i->count;
 	i->count = count;
 }
 
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 29db736af86d..bb763085479a 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -28,12 +28,10 @@
 #ifndef CONFIG_PREEMPT_RT
 #define WW_MUTEX_BASE			mutex
 #define ww_mutex_base_init(l,n,k)	__mutex_init(l,n,k)
-#define ww_mutex_base_trylock(l)	mutex_trylock(l)
 #define ww_mutex_base_is_locked(b)	mutex_is_locked((b))
 #else
 #define WW_MUTEX_BASE			rt_mutex
 #define ww_mutex_base_init(l,n,k)	__rt_mutex_init(l,n,k)
-#define ww_mutex_base_trylock(l)	rt_mutex_trylock(l)
 #define ww_mutex_base_is_locked(b)	rt_mutex_base_is_locked(&(b)->rtmutex)
 #endif
 
@@ -339,17 +337,8 @@ ww_mutex_lock_slow_interruptible(struct ww_mutex *lock,
 
 extern void ww_mutex_unlock(struct ww_mutex *lock);
 
-/**
- * ww_mutex_trylock - tries to acquire the w/w mutex without acquire context
- * @lock: mutex to lock
- *
- * Trylocks a mutex without acquire context, so no deadlock detection is
- * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise.
- */
-static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock)
-{
-	return ww_mutex_base_trylock(&lock->base);
-}
+extern int __must_check ww_mutex_trylock(struct ww_mutex *lock,
+					 struct ww_acquire_ctx *ctx);
 
 /***
  * ww_mutex_destroy - mark a w/w mutex unusable
diff --git a/include/net/dsa.h b/include/net/dsa.h
index f9a17145255a..258867eff230 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -447,6 +447,11 @@ static inline bool dsa_port_is_user(struct dsa_port *dp)
 	return dp->type == DSA_PORT_TYPE_USER;
 }
 
+static inline bool dsa_port_is_unused(struct dsa_port *dp)
+{
+	return dp->type == DSA_PORT_TYPE_UNUSED;
+}
+
 static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
 {
 	return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index bde5860b3686..914ebd9290e5 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching {
 #define I915_TILING_NONE	0
 #define I915_TILING_X		1
 #define I915_TILING_Y		2
+/*
+ * Do not add new tiling types here.  The I915_TILING_* values are for
+ * de-tiling fence registers that no longer exist on modern platforms.  Although
+ * the hardware may support new types of tiling in general (e.g., Tile4), we
+ * do not need to add them to the uapi that is specific to now-defunct ioctls.
+ */
 #define I915_TILING_LAST	I915_TILING_Y
 
 #define I915_BIT_6_SWIZZLE_NONE		0
@@ -1824,6 +1830,7 @@ struct drm_i915_gem_context_param {
  * Extensions:
  *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ *   i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
 
@@ -1846,6 +1853,55 @@ struct drm_i915_gem_context_param {
  * attempted to use it, never re-use this context param number.
  */
 #define I915_CONTEXT_PARAM_RINGSIZE	0xc
+
+/*
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT:
+ *
+ * Mark that the context makes use of protected content, which will result
+ * in the context being invalidated when the protected content session is.
+ * Given that the protected content session is killed on suspend, the device
+ * is kept awake for the lifetime of a protected context, so the user should
+ * make sure to dispose of them once done.
+ * This flag can only be set at context creation time and, when set to true,
+ * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE
+ * to false. This flag can't be set to true in conjunction with setting the
+ * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_i915_gem_context_create_ext_setparam p_protected = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_PROTECTED_CONTENT,
+ *			.value = 1,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext_setparam p_norecover = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *			.next_extension = to_user_pointer(&p_protected),
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_RECOVERABLE,
+ *			.value = 0,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext create = {
+ *		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ *		.extensions = to_user_pointer(&p_norecover);
+ *	};
+ *
+ *	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * In addition to the normal failure cases, setting this flag during context
+ * creation can result in the following errors:
+ *
+ * -ENODEV: feature not available
+ * -EPERM: trying to mark a recoverable or not bannable context as protected
+ */
+#define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -2050,6 +2106,135 @@ struct i915_context_engines_bond {
 } __attribute__((packed)) name__
 
 /**
+ * struct i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915 to
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior are described below. Lastly, the default is to not allow BBs to be
+ * preempted mid-batch. Rather insert coordinated preemption points on all
+ * hardware contexts between each set of BBs. Flags could be added in the future
+ * to change both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ *	Examples syntax:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *
+ *	Example 1 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=1,
+ *		     engines=CS[0],CS[1])
+ *
+ *	Results in the following valid placement:
+ *	CS[0], CS[1]
+ *
+ *	Example 2 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ *	Results in the following valid placements:
+ *	CS[0], CS[1]
+ *	CS[2], CS[3]
+ *
+ *	This can be thought of as two virtual engines, each containing two
+ *	engines thereby making a 2D array. However, there are bonds tying the
+ *	entries together and placing restrictions on how they can be scheduled.
+ *	Specifically, the scheduler can choose only vertical columns from the 2D
+ *	array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
+ *	scheduler wants to submit to CS[0], it must also choose CS[1] and vice
+ *	versa. Same for CS[2] requires also using CS[3].
+ *	VE[0] = CS[0], CS[2]
+ *	VE[1] = CS[1], CS[3]
+ *
+ *	Example 3 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ *	Results in the following valid and invalid placements:
+ *	CS[0], CS[1]
+ *	CS[1], CS[3] - Not logically contiguous, return -EINVAL
+ */
+struct i915_context_engines_parallel_submit {
+	/**
+	 * @base: base user extension.
+	 */
+	struct i915_user_extension base;
+
+	/**
+	 * @engine_index: slot for parallel engine
+	 */
+	__u16 engine_index;
+
+	/**
+	 * @width: number of contexts per parallel engine or in other words the
+	 * number of batches in each submission
+	 */
+	__u16 width;
+
+	/**
+	 * @num_siblings: number of siblings per context or in other words the
+	 * number of possible placements for each submission
+	 */
+	__u16 num_siblings;
+
+	/**
+	 * @mbz16: reserved for future use; must be zero
+	 */
+	__u16 mbz16;
+
+	/**
+	 * @flags: all undefined flags must be zero, currently not defined flags
+	 */
+	__u64 flags;
+
+	/**
+	 * @mbz64: reserved for future use; must be zero
+	 */
+	__u64 mbz64[3];
+
+	/**
+	 * @engines: 2-d array of engine instances to configure parallel engine
+	 *
+	 * length = width (i) * num_siblings (j)
+	 * index = j + i * num_siblings
+	 */
+	struct i915_engine_class_instance engines[0];
+
+} __packed;
+
+#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 width; \
+	__u16 num_siblings; \
+	__u16 mbz16; \
+	__u64 flags; \
+	__u64 mbz64[3]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
  * DOC: Context Engine Map uAPI
  *
  * Context engine map is a new way of addressing engines when submitting batch-
@@ -2108,6 +2293,7 @@ struct i915_context_param_engines {
 	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
 #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
 #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
 	struct i915_engine_class_instance engines[0];
 } __attribute__((packed));
 
@@ -2726,14 +2912,20 @@ struct drm_i915_engine_info {
 
 	/** @flags: Engine flags. */
 	__u64 flags;
+#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE		(1 << 0)
 
 	/** @capabilities: Capabilities of this engine. */
 	__u64 capabilities;
 #define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
 #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
 
+	/** @logical_instance: Logical instance of engine */
+	__u16 logical_instance;
+
 	/** @rsvd1: Reserved fields. */
-	__u64 rsvd1[4];
+	__u16 rsvd1[3];
+	/** @rsvd2: Reserved fields. */
+	__u64 rsvd2[3];
 };
 
 /**
@@ -2979,8 +3171,12 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
 	 * struct drm_i915_gem_create_ext_memory_regions.
+	 *
+	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
+	 * struct drm_i915_gem_create_ext_protected_content.
 	 */
 #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
+#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
 	__u64 extensions;
 };
 
@@ -3038,6 +3234,50 @@ struct drm_i915_gem_create_ext_memory_regions {
 	__u64 regions;
 };
 
+/**
+ * struct drm_i915_gem_create_ext_protected_content - The
+ * I915_OBJECT_PARAM_PROTECTED_CONTENT extension.
+ *
+ * If this extension is provided, buffer contents are expected to be protected
+ * by PXP encryption and require decryption for scan out and processing. This
+ * is only possible on platforms that have PXP enabled, on all other scenarios
+ * using this extension will cause the ioctl to fail and return -ENODEV. The
+ * flags parameter is reserved for future expansion and must currently be set
+ * to zero.
+ *
+ * The buffer contents are considered invalid after a PXP session teardown.
+ *
+ * The encryption is guaranteed to be processed correctly only if the object
+ * is submitted with a context created using the
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks
+ * at submission time on the validity of the objects involved.
+ *
+ * Below is an example on how to create a protected object:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_protected_content protected_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT },
+ *              .flags = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&protected_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_protected_content {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/** @flags: reserved for future usage, currently MBZ */
+	__u32 flags;
+};
+
+/* ID of the protected content session managed by i915 when PXP is active */
+#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 59ef35154e3d..b270a07b285e 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -317,13 +317,19 @@ enum {
 	IORING_REGISTER_IOWQ_AFF		= 17,
 	IORING_UNREGISTER_IOWQ_AFF		= 18,
 
-	/* set/get max number of workers */
+	/* set/get max number of io-wq workers */
 	IORING_REGISTER_IOWQ_MAX_WORKERS	= 19,
 
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
 
+/* io-wq worker categories */
+enum {
+	IO_WQ_BOUND,
+	IO_WQ_UNBOUND,
+};
+
 /* deprecated, see struct io_uring_rsrc_update */
 struct io_uring_files_update {
 	__u32 offset;