diff --git a/.gitignore b/.gitignore
index 3ec73ea..20dce5c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -39,6 +39,7 @@
 *.o.*
 *.patch
 *.rmeta
+*.rpm
 *.rsi
 *.s
 *.so
diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst
index 93b2ae6..cfd37f3 100644
--- a/Documentation/maintainer/maintainer-entry-profile.rst
+++ b/Documentation/maintainer/maintainer-entry-profile.rst
@@ -104,3 +104,4 @@
    ../riscv/patch-acceptance
    ../driver-api/media/maintainer-entry-profile
    ../driver-api/vfio-pci-device-specific-driver-acceptance
+   ../nvme/feature-and-quirk-policy
diff --git a/Documentation/nvme/feature-and-quirk-policy.rst b/Documentation/nvme/feature-and-quirk-policy.rst
new file mode 100644
index 0000000..c01d836
--- /dev/null
+++ b/Documentation/nvme/feature-and-quirk-policy.rst
@@ -0,0 +1,77 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================
+Linux NVMe feature and and quirk policy
+=======================================
+
+This file explains the policy used to decide what is supported by the
+Linux NVMe driver and what is not.
+
+
+Introduction
+============
+
+NVM Express is an open collection of standards and information.
+
+The Linux NVMe host driver in drivers/nvme/host/ supports devices
+implementing the NVM Express (NVMe) family of specifications, which
+currently consists of a number of documents:
+
+ - the NVMe Base specification
+ - various Command Set specifications (e.g. NVM Command Set)
+ - various Transport specifications (e.g. PCIe, Fibre Channel, RDMA, TCP)
+ - the NVMe Management Interface specification
+
+See https://nvmexpress.org/developers/ for the NVMe specifications.
+
+
+Supported features
+==================
+
+NVMe is a large suite of specifications, and contains features that are only
+useful or suitable for specific use-cases. It is important to note that Linux
+does not aim to implement every feature in the specification.  Every additional
+feature implemented introduces more code, more maintenance and potentially more
+bugs.  Hence there is an inherent tradeoff between functionality and
+maintainability of the NVMe host driver.
+
+Any feature implemented in the Linux NVMe host driver must support the
+following requirements:
+
+  1. The feature is specified in a release version of an official NVMe
+     specification, or in a ratified Technical Proposal (TP) that is
+     available on NVMe website. Or if it is not directly related to the
+     on-wire protocol, does not contradict any of the NVMe specifications.
+  2. Does not conflict with the Linux architecture, nor the design of the
+     NVMe host driver.
+  3. Has a clear, indisputable value-proposition and a wide consensus across
+     the community.
+
+Vendor specific extensions are generally not supported in the NVMe host
+driver.
+
+It is strongly recommended to work with the Linux NVMe and block layer
+maintainers and get feedback on specification changes that are intended
+to be used by the Linux NVMe host driver in order to avoid conflict at a
+later stage.
+
+
+Quirks
+======
+
+Sometimes implementations of open standards fail to correctly implement parts
+of the standards.  Linux uses identifier-based quirks to work around such
+implementation bugs.  The intent of quirks is to deal with widely available
+hardware, usually consumer, which Linux users can't use without these quirks.
+Typically these implementations are not or only superficially tested with Linux
+by the hardware manufacturer.
+
+The Linux NVMe maintainers decide ad hoc whether to quirk implementations
+based on the impact of the problem to Linux users and how it impacts
+maintainability of the driver.  In general quirks are a last resort, if no
+firmware updates or other workarounds are available from the vendor.
+
+Quirks will not be added to the Linux kernel for hardware that isn't available
+on the mass market.  Hardware that fails qualification for enterprise Linux
+distributions, ChromeOS, Android or other consumers of the Linux kernel
+should be fixed before it is shipped instead of relying on Linux quirks.
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 0dd5d87..deb494f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5343,9 +5343,9 @@
   32 vCPUs in the shared_info page, KVM does not automatically do so
   and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used
   explicitly even when the vcpu_info for a given vCPU resides at the
-  "default" location in the shared_info page. This is because KVM is
-  not aware of the Xen CPU id which is used as the index into the
-  vcpu_info[] array, so cannot know the correct default location.
+  "default" location in the shared_info page. This is because KVM may
+  not be aware of the Xen CPU id which is used as the index into the
+  vcpu_info[] array, so may know the correct default location.
 
   Note that the shared info page may be constantly written to by KVM;
   it contains the event channel bitmap used to deliver interrupts to
@@ -5356,23 +5356,29 @@
   any vCPU has been running or any event channel interrupts can be
   routed to the guest.
 
+  Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared info
+  page.
+
 KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
   Sets the exception vector used to deliver Xen event channel upcalls.
   This is the HVM-wide vector injected directly by the hypervisor
   (not through the local APIC), typically configured by a guest via
-  HVM_PARAM_CALLBACK_IRQ.
+  HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest
+  SHUTDOWN_soft_reset) by setting it to zero.
 
 KVM_XEN_ATTR_TYPE_EVTCHN
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
   support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
   an outbound port number for interception of EVTCHNOP_send requests
-  from the guest. A given sending port number may be directed back
-  to a specified vCPU (by APIC ID) / port / priority on the guest,
-  or to trigger events on an eventfd. The vCPU and priority can be
-  changed by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call,
-  but other fields cannot change for a given sending port. A port
-  mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags
-  field.
+  from the guest. A given sending port number may be directed back to
+  a specified vCPU (by APIC ID) / port / priority on the guest, or to
+  trigger events on an eventfd. The vCPU and priority can be changed
+  by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other
+  fields cannot change for a given sending port. A port mapping is
+  removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing
+  KVM_XEN_EVTCHN_RESET in the flags field removes all interception of
+  outbound event channels. The values of the flags field are mutually
+  exclusive and cannot be combined as a bitmask.
 
 KVM_XEN_ATTR_TYPE_XEN_VERSION
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
@@ -5388,7 +5394,7 @@
   support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the
   XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read
   other vCPUs' vcpu_runstate_info. Xen guests enable this feature via
-  the VM_ASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist
+  the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist
   hypercall.
 
 4.127 KVM_XEN_HVM_GET_ATTR
@@ -5446,15 +5452,18 @@
   As with the shared_info page for the VM, the corresponding page may be
   dirtied at any time if event channel interrupt delivery is enabled, so
   userspace should always assume that the page is dirty without relying
-  on dirty logging.
+  on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable
+  the vcpu_info.
 
 KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO
   Sets the guest physical address of an additional pvclock structure
   for a given vCPU. This is typically used for guest vsyscall support.
+  Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure.
 
 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR
   Sets the guest physical address of the vcpu_runstate_info for a given
   vCPU. This is how a Xen guest tracks CPU state such as steal time.
+  Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area.
 
 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT
   Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of
@@ -5487,7 +5496,8 @@
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
   support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
   event channel port/priority for the VIRQ_TIMER of the vCPU, as well
-  as allowing a pending timer to be saved/restored.
+  as allowing a pending timer to be saved/restored. Setting the timer
+  port to zero disables kernel handling of the singleshot timer.
 
 KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
@@ -5495,7 +5505,8 @@
   per-vCPU local APIC upcall vector, configured by a Xen guest with
   the HVMOP_set_evtchn_upcall_vector hypercall. This is typically
   used by Windows guests, and is distinct from the HVM-wide upcall
-  vector configured with HVM_PARAM_CALLBACK_IRQ.
+  vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by
+  setting the vector to zero.
 
 
 4.129 KVM_XEN_VCPU_GET_ATTR
@@ -6577,11 +6588,6 @@
 primary storage for certain register types. Therefore, the kernel may use the
 values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
 
-::
-
-  };
-
-
 
 6. Capabilities that can be enabled on vCPUs
 ============================================
diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index 845a561..a3ca76f 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -16,17 +16,26 @@
 - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
   them together is quite rare.
 
-- Unlike kvm->slots_lock, kvm->slots_arch_lock is released before
-  synchronize_srcu(&kvm->srcu).  Therefore kvm->slots_arch_lock
-  can be taken inside a kvm->srcu read-side critical section,
-  while kvm->slots_lock cannot.
-
 - kvm->mn_active_invalidate_count ensures that pairs of
   invalidate_range_start() and invalidate_range_end() callbacks
   use the same memslots array.  kvm->slots_lock and kvm->slots_arch_lock
   are taken on the waiting side in install_new_memslots, so MMU notifiers
   must not take either kvm->slots_lock or kvm->slots_arch_lock.
 
+For SRCU:
+
+- ``synchronize_srcu(&kvm->srcu)`` is called _inside_
+  the kvm->slots_lock critical section, therefore kvm->slots_lock
+  cannot be taken inside a kvm->srcu read-side critical section.
+  Instead, kvm->slots_arch_lock is released before the call
+  to ``synchronize_srcu()`` and _can_ be taken inside a
+  kvm->srcu read-side critical section.
+
+- kvm->lock is taken inside kvm->srcu, therefore
+  ``synchronize_srcu(&kvm->srcu)`` cannot be called inside
+  a kvm->lock critical section.  If you cannot delay the
+  call until after kvm->lock is released, use ``call_srcu``.
+
 On x86:
 
 - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock
diff --git a/MAINTAINERS b/MAINTAINERS
index f61eb22..7f86d02 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11468,7 +11468,7 @@
 F:	arch/x86/kvm/kvm_onhyperv.*
 F:	arch/x86/kvm/svm/hyperv.*
 F:	arch/x86/kvm/svm/svm_onhyperv.*
-F:	arch/x86/kvm/vmx/evmcs.*
+F:	arch/x86/kvm/vmx/hyperv.*
 
 KVM X86 Xen (KVM/Xen)
 M:	David Woodhouse <dwmw2@infradead.org>
@@ -14916,6 +14916,7 @@
 S:	Supported
 W:	http://git.infradead.org/nvme.git
 T:	git://git.infradead.org/nvme.git
+F:	Documentation/nvme/
 F:	drivers/nvme/host/
 F:	drivers/nvme/common/
 F:	include/linux/nvme*
diff --git a/Makefile b/Makefile
index d4b6af8..a5133e4 100644
--- a/Makefile
+++ b/Makefile
@@ -297,7 +297,7 @@
 			headers_install modules_install kernelrelease image_name
 no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \
 			  image_name
-single-targets := %.a %.i %.rsi %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
+single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.rsi %.s %.symtypes %/
 
 config-build	:=
 mixed-build	:=
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 7d2c75e..ffea98f 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -119,7 +119,7 @@
 	return within_module_coretext(addr);
 }
 
-static __init_or_module bool skip_addr(void *dest)
+static bool skip_addr(void *dest)
 {
 	if (dest == error_entry)
 		return true;
@@ -181,7 +181,7 @@
 	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
 };
 
-static __init_or_module void *patch_dest(void *dest, bool direct)
+static void *patch_dest(void *dest, bool direct)
 {
 	unsigned int tsize = SKL_TMPL_SIZE;
 	u8 *pad = dest - tsize;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6629968..b36f3c3 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -37,6 +37,7 @@
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
@@ -281,12 +282,15 @@
 		if (ret < 0)
 			return 0;
 
+#ifdef CONFIG_KGDB
 		/*
-		 * Another debugging subsystem might insert this breakpoint.
-		 * In that case, we can't recover it.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
 			return 0;
+#endif
 		addr += insn.length;
 	}
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index e6b8c53..e57e07b 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -15,6 +15,7 @@
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/objtool.h>
 #include <linux/pgtable.h>
@@ -279,19 +280,6 @@
 	return ret;
 }
 
-static bool is_padding_int3(unsigned long addr, unsigned long eaddr)
-{
-	unsigned char ops;
-
-	for (; addr < eaddr; addr++) {
-		if (get_kernel_nofault(ops, (void *)addr) < 0 ||
-		    ops != INT3_INSN_OPCODE)
-			return false;
-	}
-
-	return true;
-}
-
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
@@ -334,15 +322,15 @@
 		ret = insn_decode_kernel(&insn, (void *)recovered_insn);
 		if (ret < 0)
 			return 0;
-
+#ifdef CONFIG_KGDB
 		/*
-		 * In the case of detecting unknown breakpoint, this could be
-		 * a padding INT3 between functions. Let's check that all the
-		 * rest of the bytes are also INT3.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
-			return is_padding_int3(addr, paddr - offset + size) ? 1 : 0;
-
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
+			return 0;
+#endif
 		/* Recover address */
 		insn.kaddr = (void *)addr;
 		insn.next_byte = (void *)(addr + insn.length);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 2c7f2a2..e829694 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1769,6 +1769,7 @@
 }
 
 struct kvm_hv_hcall {
+	/* Hypercall input data */
 	u64 param;
 	u64 ingpa;
 	u64 outgpa;
@@ -1779,12 +1780,21 @@
 	bool fast;
 	bool rep;
 	sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
+
+	/*
+	 * Current read offset when KVM reads hypercall input data gradually,
+	 * either offset in bytes from 'ingpa' for regular hypercalls or the
+	 * number of already consumed 'XMM halves' for 'fast' hypercalls.
+	 */
+	union {
+		gpa_t data_offset;
+		int consumed_xmm_halves;
+	};
 };
 
 
 static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc,
-			      u16 orig_cnt, u16 cnt_cap, u64 *data,
-			      int consumed_xmm_halves, gpa_t offset)
+			      u16 orig_cnt, u16 cnt_cap, u64 *data)
 {
 	/*
 	 * Preserve the original count when ignoring entries via a "cap", KVM
@@ -1799,11 +1809,11 @@
 		 * Each XMM holds two sparse banks, but do not count halves that
 		 * have already been consumed for hypercall parameters.
 		 */
-		if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves)
+		if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves)
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
 		for (i = 0; i < cnt; i++) {
-			j = i + consumed_xmm_halves;
+			j = i + hc->consumed_xmm_halves;
 			if (j % 2)
 				data[i] = sse128_hi(hc->xmm[j / 2]);
 			else
@@ -1812,27 +1822,24 @@
 		return 0;
 	}
 
-	return kvm_read_guest(kvm, hc->ingpa + offset, data,
+	return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data,
 			      cnt * sizeof(*data));
 }
 
 static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc,
-				 u64 *sparse_banks, int consumed_xmm_halves,
-				 gpa_t offset)
+				 u64 *sparse_banks)
 {
 	if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS)
 		return -EINVAL;
 
 	/* Cap var_cnt to ignore banks that cannot contain a legal VP index. */
 	return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS,
-				  sparse_banks, consumed_xmm_halves, offset);
+				  sparse_banks);
 }
 
-static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[],
-					int consumed_xmm_halves, gpa_t offset)
+static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[])
 {
-	return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt,
-				  entries, consumed_xmm_halves, offset);
+	return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries);
 }
 
 static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu,
@@ -1926,8 +1933,6 @@
 	struct kvm_vcpu *v;
 	unsigned long i;
 	bool all_cpus;
-	int consumed_xmm_halves = 0;
-	gpa_t data_offset;
 
 	/*
 	 * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS
@@ -1955,12 +1960,12 @@
 			flush.address_space = hc->ingpa;
 			flush.flags = hc->outgpa;
 			flush.processor_mask = sse128_lo(hc->xmm[0]);
-			consumed_xmm_halves = 1;
+			hc->consumed_xmm_halves = 1;
 		} else {
 			if (unlikely(kvm_read_guest(kvm, hc->ingpa,
 						    &flush, sizeof(flush))))
 				return HV_STATUS_INVALID_HYPERCALL_INPUT;
-			data_offset = sizeof(flush);
+			hc->data_offset = sizeof(flush);
 		}
 
 		trace_kvm_hv_flush_tlb(flush.processor_mask,
@@ -1985,12 +1990,12 @@
 			flush_ex.flags = hc->outgpa;
 			memcpy(&flush_ex.hv_vp_set,
 			       &hc->xmm[0], sizeof(hc->xmm[0]));
-			consumed_xmm_halves = 2;
+			hc->consumed_xmm_halves = 2;
 		} else {
 			if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex,
 						    sizeof(flush_ex))))
 				return HV_STATUS_INVALID_HYPERCALL_INPUT;
-			data_offset = sizeof(flush_ex);
+			hc->data_offset = sizeof(flush_ex);
 		}
 
 		trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask,
@@ -2009,8 +2014,7 @@
 			if (!hc->var_cnt)
 				goto ret_success;
 
-			if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks,
-						  consumed_xmm_halves, data_offset))
+			if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
 				return HV_STATUS_INVALID_HYPERCALL_INPUT;
 		}
 
@@ -2021,8 +2025,10 @@
 		 * consumed_xmm_halves to make sure TLB flush entries are read
 		 * from the correct offset.
 		 */
-		data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
-		consumed_xmm_halves += hc->var_cnt;
+		if (hc->fast)
+			hc->consumed_xmm_halves += hc->var_cnt;
+		else
+			hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
 	}
 
 	if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE ||
@@ -2030,8 +2036,7 @@
 	    hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) {
 		tlb_flush_entries = NULL;
 	} else {
-		if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries,
-						consumed_xmm_halves, data_offset))
+		if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries))
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 		tlb_flush_entries = __tlb_flush_entries;
 	}
@@ -2180,9 +2185,13 @@
 		if (!hc->var_cnt)
 			goto ret_success;
 
-		if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1,
-					  offsetof(struct hv_send_ipi_ex,
-						   vp_set.bank_contents)))
+		if (!hc->fast)
+			hc->data_offset = offsetof(struct hv_send_ipi_ex,
+						   vp_set.bank_contents);
+		else
+			hc->consumed_xmm_halves = 1;
+
+		if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 	}
 
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 0687162..3742d9a 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -426,8 +426,9 @@
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
 			if (irq.trig_mode &&
-			    kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
-						irq.dest_id, irq.dest_mode))
+			    (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
+						 irq.dest_id, irq.dest_mode) ||
+			     kvm_apic_pending_eoi(vcpu, irq.vector)))
 				__set_bit(irq.vector, ioapic_handled_vectors);
 		}
 	}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 28e3769..58c3242 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -188,11 +188,11 @@
 
 extern struct static_key_false_deferred apic_hw_disabled;
 
-static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
+static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic)
 {
 	if (static_branch_unlikely(&apic_hw_disabled.key))
 		return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
-	return MSR_IA32_APICBASE_ENABLE;
+	return true;
 }
 
 extern struct static_key_false_deferred apic_sw_disabled;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 1f03701..6f54dc9 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -363,7 +363,7 @@
  * A shadow-present leaf SPTE may be non-writable for 4 possible reasons:
  *
  *  1. To intercept writes for dirty logging. KVM write-protects huge pages
- *     so that they can be split be split down into the dirty logging
+ *     so that they can be split down into the dirty logging
  *     granularity (4KiB) whenever the guest writes to them. KVM also
  *     write-protects 4KiB pages so that writes can be recorded in the dirty log
  *     (e.g. if not using PML). SPTEs are write-protected for dirty logging
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 771210c..d6df38d 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1074,7 +1074,9 @@
 	int ret = RET_PF_FIXED;
 	bool wrprot = false;
 
-	WARN_ON(sp->role.level != fault->goal_level);
+	if (WARN_ON_ONCE(sp->role.level != fault->goal_level))
+		return RET_PF_RETRY;
+
 	if (unlikely(!fault->slot))
 		new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
 	else
@@ -1173,9 +1175,6 @@
 		if (fault->nx_huge_page_workaround_enabled)
 			disallowed_hugepage_adjust(fault, iter.old_spte, iter.level);
 
-		if (iter.level == fault->goal_level)
-			break;
-
 		/*
 		 * If SPTE has been frozen by another thread, just give up and
 		 * retry, avoiding unnecessary page table allocation and free.
@@ -1183,6 +1182,9 @@
 		if (is_removed_spte(iter.old_spte))
 			goto retry;
 
+		if (iter.level == fault->goal_level)
+			goto map_target_level;
+
 		/* Step down into the lower level page table if it exists. */
 		if (is_shadow_present_pte(iter.old_spte) &&
 		    !is_large_pte(iter.old_spte))
@@ -1203,8 +1205,8 @@
 			r = tdp_mmu_link_sp(kvm, &iter, sp, true);
 
 		/*
-		 * Also force the guest to retry the access if the upper level SPTEs
-		 * aren't in place.
+		 * Force the guest to retry if installing an upper level SPTE
+		 * failed, e.g. because a different task modified the SPTE.
 		 */
 		if (r) {
 			tdp_mmu_free_sp(sp);
@@ -1214,11 +1216,20 @@
 		if (fault->huge_page_disallowed &&
 		    fault->req_level >= iter.level) {
 			spin_lock(&kvm->arch.tdp_mmu_pages_lock);
-			track_possible_nx_huge_page(kvm, sp);
+			if (sp->nx_huge_page_disallowed)
+				track_possible_nx_huge_page(kvm, sp);
 			spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
 		}
 	}
 
+	/*
+	 * The walk aborted before reaching the target level, e.g. because the
+	 * iterator detected an upper level SPTE was frozen during traversal.
+	 */
+	WARN_ON_ONCE(iter.level == fault->goal_level);
+	goto retry;
+
+map_target_level:
 	ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter);
 
 retry:
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 684393c..eb59462 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -238,7 +238,8 @@
 		return false;
 
 	/* recalibrate sample period and check if it's accepted by perf core */
-	if (perf_event_period(pmc->perf_event,
+	if (is_sampling_event(pmc->perf_event) &&
+	    perf_event_period(pmc->perf_event,
 			      get_sample_period(pmc, pmc->counter)))
 		return false;
 
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 85ff3c0..cdb9100 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -140,7 +140,8 @@
 
 static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
 {
-	if (!pmc->perf_event || pmc->is_paused)
+	if (!pmc->perf_event || pmc->is_paused ||
+	    !is_sampling_event(pmc->perf_event))
 		return;
 
 	perf_event_period(pmc->perf_event,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b6f4411..d93c715 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5296,10 +5296,19 @@
 		if (vmptr == vmx->nested.current_vmptr)
 			nested_release_vmcs12(vcpu);
 
-		kvm_vcpu_write_guest(vcpu,
-				     vmptr + offsetof(struct vmcs12,
-						      launch_state),
-				     &zero, sizeof(zero));
+		/*
+		 * Silently ignore memory errors on VMCLEAR, Intel's pseudocode
+		 * for VMCLEAR includes a "ensure that data for VMCS referenced
+		 * by the operand is in memory" clause that guards writes to
+		 * memory, i.e. doing nothing for I/O is architecturally valid.
+		 *
+		 * FIXME: Suppress failures if and only if no memslot is found,
+		 * i.e. exit to userspace if __copy_to_user() fails.
+		 */
+		(void)kvm_vcpu_write_guest(vcpu,
+					   vmptr + offsetof(struct vmcs12,
+							    launch_state),
+					   &zero, sizeof(zero));
 	} else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) {
 		nested_release_evmcs(vcpu);
 	}
@@ -6873,7 +6882,8 @@
 		SECONDARY_EXEC_ENABLE_INVPCID |
 		SECONDARY_EXEC_RDSEED_EXITING |
 		SECONDARY_EXEC_XSAVES |
-		SECONDARY_EXEC_TSC_SCALING;
+		SECONDARY_EXEC_TSC_SCALING |
+		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
 
 	/*
 	 * We can emulate "VMCS shadowing," even if the hardware
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index fe5615f..fc9008d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4459,6 +4459,13 @@
 	 * controls for features that are/aren't exposed to the guest.
 	 */
 	if (nested) {
+		/*
+		 * All features that can be added or removed to VMX MSRs must
+		 * be supported in the first place for nested virtualization.
+		 */
+		if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control)))
+			enabled = false;
+
 		if (enabled)
 			vmx->nested.msrs.secondary_ctls_high |= control;
 		else
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 312aea1..da4bbd0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13132,6 +13132,9 @@
 			      struct x86_exception *e)
 {
 	if (r == X86EMUL_PROPAGATE_FAULT) {
+		if (KVM_BUG_ON(!e, vcpu->kvm))
+			return -EIO;
+
 		kvm_inject_emulated_page_fault(vcpu, e);
 		return 1;
 	}
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index d7af402..2e29bdc 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -41,7 +41,7 @@
 	int ret = 0;
 	int idx = srcu_read_lock(&kvm->srcu);
 
-	if (gfn == GPA_INVALID) {
+	if (gfn == KVM_XEN_INVALID_GFN) {
 		kvm_gpc_deactivate(gpc);
 		goto out;
 	}
@@ -659,7 +659,7 @@
 		if (kvm->arch.xen.shinfo_cache.active)
 			data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa);
 		else
-			data->u.shared_info.gfn = GPA_INVALID;
+			data->u.shared_info.gfn = KVM_XEN_INVALID_GFN;
 		r = 0;
 		break;
 
@@ -705,7 +705,7 @@
 		BUILD_BUG_ON(offsetof(struct vcpu_info, time) !=
 			     offsetof(struct compat_vcpu_info, time));
 
-		if (data->u.gpa == GPA_INVALID) {
+		if (data->u.gpa == KVM_XEN_INVALID_GPA) {
 			kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
 			r = 0;
 			break;
@@ -719,7 +719,7 @@
 		break;
 
 	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
-		if (data->u.gpa == GPA_INVALID) {
+		if (data->u.gpa == KVM_XEN_INVALID_GPA) {
 			kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache);
 			r = 0;
 			break;
@@ -739,7 +739,7 @@
 			r = -EOPNOTSUPP;
 			break;
 		}
-		if (data->u.gpa == GPA_INVALID) {
+		if (data->u.gpa == KVM_XEN_INVALID_GPA) {
 			r = 0;
 		deactivate_out:
 			kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache);
@@ -937,7 +937,7 @@
 		if (vcpu->arch.xen.vcpu_info_cache.active)
 			data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa;
 		else
-			data->u.gpa = GPA_INVALID;
+			data->u.gpa = KVM_XEN_INVALID_GPA;
 		r = 0;
 		break;
 
@@ -945,7 +945,7 @@
 		if (vcpu->arch.xen.vcpu_time_info_cache.active)
 			data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa;
 		else
-			data->u.gpa = GPA_INVALID;
+			data->u.gpa = KVM_XEN_INVALID_GPA;
 		r = 0;
 		break;
 
@@ -1069,6 +1069,7 @@
 		u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
 				  : kvm->arch.xen_hvm_config.blob_size_32;
 		u8 *page;
+		int ret;
 
 		if (page_num >= blob_size)
 			return 1;
@@ -1079,10 +1080,10 @@
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
-		if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) {
-			kfree(page);
+		ret = kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE);
+		kfree(page);
+		if (ret)
 			return 1;
-		}
 	}
 	return 0;
 }
@@ -1183,30 +1184,22 @@
 static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
 				 u64 param, u64 *r)
 {
-	int idx, i;
 	struct sched_poll sched_poll;
 	evtchn_port_t port, *ports;
-	gpa_t gpa;
+	struct x86_exception e;
+	int i;
 
 	if (!lapic_in_kernel(vcpu) ||
 	    !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND))
 		return false;
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-	if (!gpa) {
-		*r = -EFAULT;
-		return true;
-	}
-
 	if (IS_ENABLED(CONFIG_64BIT) && !longmode) {
 		struct compat_sched_poll sp32;
 
 		/* Sanity check that the compat struct definition is correct */
 		BUILD_BUG_ON(sizeof(sp32) != 16);
 
-		if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) {
+		if (kvm_read_guest_virt(vcpu, param, &sp32, sizeof(sp32), &e)) {
 			*r = -EFAULT;
 			return true;
 		}
@@ -1220,8 +1213,8 @@
 		sched_poll.nr_ports = sp32.nr_ports;
 		sched_poll.timeout = sp32.timeout;
 	} else {
-		if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll,
-					sizeof(sched_poll))) {
+		if (kvm_read_guest_virt(vcpu, param, &sched_poll,
+					sizeof(sched_poll), &e)) {
 			*r = -EFAULT;
 			return true;
 		}
@@ -1243,18 +1236,13 @@
 	} else
 		ports = &port;
 
-	for (i = 0; i < sched_poll.nr_ports; i++) {
-		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		gpa = kvm_mmu_gva_to_gpa_system(vcpu,
-						(gva_t)(sched_poll.ports + i),
-						NULL);
-		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports,
+				sched_poll.nr_ports * sizeof(*ports), &e)) {
+		*r = -EFAULT;
+		return true;
+	}
 
-		if (!gpa || kvm_vcpu_read_guest(vcpu, gpa,
-						&ports[i], sizeof(port))) {
-			*r = -EFAULT;
-			goto out;
-		}
+	for (i = 0; i < sched_poll.nr_ports; i++) {
 		if (ports[i] >= max_evtchn_port(vcpu->kvm)) {
 			*r = -EINVAL;
 			goto out;
@@ -1330,9 +1318,8 @@
 				  int vcpu_id, u64 param, u64 *r)
 {
 	struct vcpu_set_singleshot_timer oneshot;
+	struct x86_exception e;
 	s64 delta;
-	gpa_t gpa;
-	int idx;
 
 	if (!kvm_xen_timer_enabled(vcpu))
 		return false;
@@ -1343,9 +1330,6 @@
 			*r = -EINVAL;
 			return true;
 		}
-		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
-		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 		/*
 		 * The only difference for 32-bit compat is the 4 bytes of
@@ -1363,9 +1347,8 @@
 		BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) !=
 			     sizeof_field(struct vcpu_set_singleshot_timer, flags));
 
-		if (!gpa ||
-		    kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) :
-					sizeof(struct compat_vcpu_set_singleshot_timer))) {
+		if (kvm_read_guest_virt(vcpu, param, &oneshot, longmode ? sizeof(oneshot) :
+					sizeof(struct compat_vcpu_set_singleshot_timer), &e)) {
 			*r = -EFAULT;
 			return true;
 		}
@@ -1825,20 +1808,20 @@
 {
 	u32 port = data->u.evtchn.send_port;
 	struct evtchnfd *evtchnfd;
+	int ret;
 
-	if (!port || port >= max_evtchn_port(kvm))
-		return -EINVAL;
-
+	/* Protect writes to evtchnfd as well as the idr lookup.  */
 	mutex_lock(&kvm->lock);
 	evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
-	mutex_unlock(&kvm->lock);
 
+	ret = -ENOENT;
 	if (!evtchnfd)
-		return -ENOENT;
+		goto out_unlock;
 
 	/* For an UPDATE, nothing may change except the priority/vcpu */
+	ret = -EINVAL;
 	if (evtchnfd->type != data->u.evtchn.type)
-		return -EINVAL;
+		goto out_unlock;
 
 	/*
 	 * Port cannot change, and if it's zero that was an eventfd
@@ -1846,20 +1829,21 @@
 	 */
 	if (!evtchnfd->deliver.port.port ||
 	    evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port)
-		return -EINVAL;
+		goto out_unlock;
 
 	/* We only support 2 level event channels for now */
 	if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
-		return -EINVAL;
+		goto out_unlock;
 
-	mutex_lock(&kvm->lock);
 	evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
 	if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) {
 		evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu;
 		evtchnfd->deliver.port.vcpu_idx = -1;
 	}
+	ret = 0;
+out_unlock:
 	mutex_unlock(&kvm->lock);
-	return 0;
+	return ret;
 }
 
 /*
@@ -1871,12 +1855,9 @@
 {
 	u32 port = data->u.evtchn.send_port;
 	struct eventfd_ctx *eventfd = NULL;
-	struct evtchnfd *evtchnfd = NULL;
+	struct evtchnfd *evtchnfd;
 	int ret = -EINVAL;
 
-	if (!port || port >= max_evtchn_port(kvm))
-		return -EINVAL;
-
 	evtchnfd = kzalloc(sizeof(struct evtchnfd), GFP_KERNEL);
 	if (!evtchnfd)
 		return -ENOMEM;
@@ -1952,8 +1933,7 @@
 	if (!evtchnfd)
 		return -ENOENT;
 
-	if (kvm)
-		synchronize_srcu(&kvm->srcu);
+	synchronize_srcu(&kvm->srcu);
 	if (!evtchnfd->deliver.port.port)
 		eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
 	kfree(evtchnfd);
@@ -1962,18 +1942,42 @@
 
 static int kvm_xen_eventfd_reset(struct kvm *kvm)
 {
-	struct evtchnfd *evtchnfd;
+	struct evtchnfd *evtchnfd, **all_evtchnfds;
 	int i;
+	int n = 0;
 
 	mutex_lock(&kvm->lock);
+
+	/*
+	 * Because synchronize_srcu() cannot be called inside the
+	 * critical section, first collect all the evtchnfd objects
+	 * in an array as they are removed from evtchn_ports.
+	 */
+	idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i)
+		n++;
+
+	all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
+	if (!all_evtchnfds) {
+		mutex_unlock(&kvm->lock);
+		return -ENOMEM;
+	}
+
+	n = 0;
 	idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) {
+		all_evtchnfds[n++] = evtchnfd;
 		idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
-		synchronize_srcu(&kvm->srcu);
+	}
+	mutex_unlock(&kvm->lock);
+
+	synchronize_srcu(&kvm->srcu);
+
+	while (n--) {
+		evtchnfd = all_evtchnfds[n];
 		if (!evtchnfd->deliver.port.port)
 			eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
 		kfree(evtchnfd);
 	}
-	mutex_unlock(&kvm->lock);
+	kfree(all_evtchnfds);
 
 	return 0;
 }
@@ -2002,20 +2006,22 @@
 {
 	struct evtchnfd *evtchnfd;
 	struct evtchn_send send;
-	gpa_t gpa;
-	int idx;
+	struct x86_exception e;
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-
-	if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) {
+	/* Sanity check: this structure is the same for 32-bit and 64-bit */
+	BUILD_BUG_ON(sizeof(send) != 4);
+	if (kvm_read_guest_virt(vcpu, param, &send, sizeof(send), &e)) {
 		*r = -EFAULT;
 		return true;
 	}
 
-	/* The evtchn_ports idr is protected by vcpu->kvm->srcu */
+	/*
+	 * evtchnfd is protected by kvm->srcu; the idr lookup instead
+	 * is protected by RCU.
+	 */
+	rcu_read_lock();
 	evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port);
+	rcu_read_unlock();
 	if (!evtchnfd)
 		return false;
 
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 16f43bb..ccf2204 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5317,8 +5317,8 @@
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
-		bfq_exit_bfqq(bfqd, bfqq);
 		bic_set_bfqq(bic, NULL, is_sync);
+		bfq_exit_bfqq(bfqd, bfqq);
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	}
 }
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 30d8fd0..97b711e5 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -70,11 +70,7 @@
 static int only_lcd = -1;
 module_param(only_lcd, int, 0444);
 
-/*
- * Display probing is known to take up to 5 seconds, so delay the fallback
- * backlight registration by 5 seconds + 3 seconds for some extra margin.
- */
-static int register_backlight_delay = 8;
+static int register_backlight_delay;
 module_param(register_backlight_delay, int, 0444);
 MODULE_PARM_DESC(register_backlight_delay,
 	"Delay in seconds before doing fallback (non GPU driver triggered) "
@@ -2176,6 +2172,17 @@
 	return false;
 }
 
+/*
+ * At least one graphics driver has reported that no LCD is connected
+ * via the native interface. cancel the registration for fallback acpi_video0.
+ * If another driver still deems this necessary, it can explicitly register it.
+ */
+void acpi_video_report_nolcd(void)
+{
+	cancel_delayed_work(&video_bus_register_backlight_work);
+}
+EXPORT_SYMBOL(acpi_video_report_nolcd);
+
 int acpi_video_register(void)
 {
 	int ret = 0;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index f27914a..16dcd31 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -432,10 +432,24 @@
 			DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"),
 		},
 	},
+	{
+		.ident = "Asus ExpertBook B2502",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B2502CBA"),
+		},
+	},
 	{ }
 };
 
-static const struct dmi_system_id lenovo_82ra[] = {
+static const struct dmi_system_id lenovo_laptop[] = {
+	{
+		.ident = "LENOVO IdeaPad Flex 5 14ALC7",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "82R9"),
+		},
+	},
 	{
 		.ident = "LENOVO IdeaPad Flex 5 16ALC7",
 		.matches = {
@@ -446,6 +460,17 @@
 	{ }
 };
 
+static const struct dmi_system_id schenker_gm_rg[] = {
+	{
+		.ident = "XMG CORE 15 (M22)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"),
+			DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"),
+		},
+	},
+	{ }
+};
+
 struct irq_override_cmp {
 	const struct dmi_system_id *system;
 	unsigned char irq;
@@ -458,8 +483,9 @@
 static const struct irq_override_cmp override_table[] = {
 	{ medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
 	{ asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
-	{ lenovo_82ra, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
-	{ lenovo_82ra, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+	{ lenovo_laptop, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+	{ lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+	{ schenker_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true },
 };
 
 static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity,
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index a934bbc..1b78c74 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -34,6 +34,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_data/x86/nvidia-wmi-ec-backlight.h>
+#include <linux/pnp.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
 #include <acpi/video.h>
@@ -105,6 +106,26 @@
 }
 #endif
 
+static bool apple_gmux_backlight_present(void)
+{
+	struct acpi_device *adev;
+	struct device *dev;
+
+	adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1);
+	if (!adev)
+		return false;
+
+	dev = acpi_get_first_physical_node(adev);
+	if (!dev)
+		return false;
+
+	/*
+	 * drivers/platform/x86/apple-gmux.c only supports old style
+	 * Apple GMUX with an IO-resource.
+	 */
+	return pnp_get_resource(to_pnp_dev(dev), IORESOURCE_IO, 0) != NULL;
+}
+
 /* Force to use vendor driver when the ACPI device is known to be
  * buggy */
 static int video_detect_force_vendor(const struct dmi_system_id *d)
@@ -767,7 +788,7 @@
 	if (nvidia_wmi_ec_present)
 		return acpi_backlight_nvidia_wmi_ec;
 
-	if (apple_gmux_present())
+	if (apple_gmux_backlight_present())
 		return acpi_backlight_apple_gmux;
 
 	/* Use ACPI video if available, except when native should be preferred. */
diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c
index 5350c73..c7afce4 100644
--- a/drivers/acpi/x86/s2idle.c
+++ b/drivers/acpi/x86/s2idle.c
@@ -28,10 +28,6 @@
 module_param(sleep_no_lps0, bool, 0644);
 MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface");
 
-static bool prefer_microsoft_dsm_guid __read_mostly;
-module_param(prefer_microsoft_dsm_guid, bool, 0644);
-MODULE_PARM_DESC(prefer_microsoft_dsm_guid, "Prefer using Microsoft GUID in LPS0 device _DSM evaluation");
-
 static const struct acpi_device_id lps0_device_ids[] = {
 	{"PNP0D80", },
 	{"", },
@@ -369,27 +365,15 @@
 }
 
 struct amd_lps0_hid_device_data {
-	const unsigned int rev_id;
 	const bool check_off_by_one;
-	const bool prefer_amd_guid;
 };
 
 static const struct amd_lps0_hid_device_data amd_picasso = {
-	.rev_id = 0,
 	.check_off_by_one = true,
-	.prefer_amd_guid = false,
 };
 
 static const struct amd_lps0_hid_device_data amd_cezanne = {
-	.rev_id = 0,
 	.check_off_by_one = false,
-	.prefer_amd_guid = false,
-};
-
-static const struct amd_lps0_hid_device_data amd_rembrandt = {
-	.rev_id = 2,
-	.check_off_by_one = false,
-	.prefer_amd_guid = true,
 };
 
 static const struct acpi_device_id amd_hid_ids[] = {
@@ -397,69 +381,27 @@
 	{"AMD0005",	(kernel_ulong_t)&amd_picasso,	},
 	{"AMDI0005",	(kernel_ulong_t)&amd_picasso,	},
 	{"AMDI0006",	(kernel_ulong_t)&amd_cezanne,	},
-	{"AMDI0007",	(kernel_ulong_t)&amd_rembrandt,	},
 	{}
 };
 
-static int lps0_prefer_microsoft(const struct dmi_system_id *id)
+static int lps0_prefer_amd(const struct dmi_system_id *id)
 {
-	pr_debug("Preferring Microsoft GUID.\n");
-	prefer_microsoft_dsm_guid = true;
+	pr_debug("Using AMD GUID w/ _REV 2.\n");
+	rev_id = 2;
 	return 0;
 }
-
 static const struct dmi_system_id s2idle_dmi_table[] __initconst = {
 	{
 		/*
-		 * ASUS TUF Gaming A17 FA707RE
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=216101
+		 * AMD Rembrandt based HP EliteBook 835/845/865 G9
+		 * Contains specialized AML in AMD/_REV 2 path to avoid
+		 * triggering a bug in Qualcomm WLAN firmware. This may be
+		 * removed in the future if that firmware is fixed.
 		 */
-		.callback = lps0_prefer_microsoft,
+		.callback = lps0_prefer_amd,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS TUF Gaming A17"),
-		},
-	},
-	{
-		/* ASUS ROG Zephyrus G14 (2022) */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Zephyrus G14 GA402"),
-		},
-	},
-	{
-		/*
-		 * Lenovo Yoga Slim 7 Pro X 14ARH7
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=216473 : 82V2
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=216438 : 82TL
-		 */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "82"),
-		},
-	},
-	{
-		/*
-		 * ASUSTeK COMPUTER INC. ROG Flow X13 GV301RE_GV301RE
-		 * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
-		 */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X13 GV301"),
-		},
-	},
-	{
-		/*
-		 * ASUSTeK COMPUTER INC. ROG Flow X16 GV601RW_GV601RW
-		 * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
-		 */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X16 GV601"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_BOARD_NAME, "8990"),
 		},
 	},
 	{}
@@ -484,16 +426,14 @@
 		if (dev_id->id[0])
 			data = (const struct amd_lps0_hid_device_data *) dev_id->driver_data;
 		else
-			data = &amd_rembrandt;
-		rev_id = data->rev_id;
+			data = &amd_cezanne;
 		lps0_dsm_func_mask = validate_dsm(adev->handle,
 					ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid);
 		if (lps0_dsm_func_mask > 0x3 && data->check_off_by_one) {
 			lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1;
 			acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n",
 					  ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask);
-		} else if (lps0_dsm_func_mask_microsoft > 0 && data->prefer_amd_guid &&
-				!prefer_microsoft_dsm_guid) {
+		} else if (lps0_dsm_func_mask_microsoft > 0 && rev_id) {
 			lps0_dsm_func_mask_microsoft = -EINVAL;
 			acpi_handle_debug(adev->handle, "_DSM Using AMD method\n");
 		}
@@ -501,8 +441,7 @@
 		rev_id = 1;
 		lps0_dsm_func_mask = validate_dsm(adev->handle,
 					ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid);
-		if (!prefer_microsoft_dsm_guid)
-			lps0_dsm_func_mask_microsoft = -EINVAL;
+		lps0_dsm_func_mask_microsoft = -EINVAL;
 	}
 
 	if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 0cfd0ec..14a1c0d 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -83,6 +83,7 @@
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static void ahci_remove_one(struct pci_dev *dev);
 static void ahci_shutdown_one(struct pci_dev *dev);
+static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hpriv);
 static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 				 unsigned long deadline);
 static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
@@ -676,6 +677,25 @@
 	ahci_save_initial_config(&pdev->dev, hpriv);
 }
 
+static int ahci_pci_reset_controller(struct ata_host *host)
+{
+	struct pci_dev *pdev = to_pci_dev(host->dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	int rc;
+
+	rc = ahci_reset_controller(host);
+	if (rc)
+		return rc;
+
+	/*
+	 * If platform firmware failed to enable ports, try to enable
+	 * them here.
+	 */
+	ahci_intel_pcs_quirk(pdev, hpriv);
+
+	return 0;
+}
+
 static void ahci_pci_init_controller(struct ata_host *host)
 {
 	struct ahci_host_priv *hpriv = host->private_data;
@@ -870,7 +890,7 @@
 	struct ata_host *host = pci_get_drvdata(pdev);
 	int rc;
 
-	rc = ahci_reset_controller(host);
+	rc = ahci_pci_reset_controller(host);
 	if (rc)
 		return rc;
 	ahci_pci_init_controller(host);
@@ -906,7 +926,7 @@
 		ahci_mcp89_apple_enable(pdev);
 
 	if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) {
-		rc = ahci_reset_controller(host);
+		rc = ahci_pci_reset_controller(host);
 		if (rc)
 			return rc;
 
@@ -1784,12 +1804,6 @@
 	/* save initial config */
 	ahci_pci_save_initial_config(pdev, hpriv);
 
-	/*
-	 * If platform firmware failed to enable ports, try to enable
-	 * them here.
-	 */
-	ahci_intel_pcs_quirk(pdev, hpriv);
-
 	/* prepare host */
 	if (hpriv->cap & HOST_CAP_NCQ) {
 		pi.flags |= ATA_FLAG_NCQ;
@@ -1899,7 +1913,7 @@
 	if (rc)
 		return rc;
 
-	rc = ahci_reset_controller(host);
+	rc = ahci_pci_reset_controller(host);
 	if (rc)
 		return rc;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 50c783e..86bc23a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4361,6 +4361,10 @@
 		amdgpu_set_panel_orientation(&aconnector->base);
 	}
 
+	/* If we didn't find a panel, notify the acpi video detection */
+	if (dm->adev->flags & AMD_IS_APU && dm->num_of_edps == 0)
+		acpi_video_report_nolcd();
+
 	/* Software is initialized. Now we can register interrupt handlers. */
 	switch (adev->asic_type) {
 #if defined(CONFIG_DRM_AMD_DC_SI)
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
index fce69fa..2cbc129 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -41,9 +41,11 @@
 
 #include "i915_drv.h"
 #include "i915_reg.h"
+#include "intel_de.h"
 #include "intel_display_types.h"
 #include "intel_dsi.h"
 #include "intel_dsi_vbt.h"
+#include "intel_gmbus_regs.h"
 #include "vlv_dsi.h"
 #include "vlv_dsi_regs.h"
 #include "vlv_sideband.h"
@@ -377,6 +379,85 @@
 	drm_dbg_kms(&dev_priv->drm, "Skipping ICL GPIO element execution\n");
 }
 
+enum {
+	MIPI_RESET_1 = 0,
+	MIPI_AVDD_EN_1,
+	MIPI_BKLT_EN_1,
+	MIPI_AVEE_EN_1,
+	MIPI_VIO_EN_1,
+	MIPI_RESET_2,
+	MIPI_AVDD_EN_2,
+	MIPI_BKLT_EN_2,
+	MIPI_AVEE_EN_2,
+	MIPI_VIO_EN_2,
+};
+
+static void icl_native_gpio_set_value(struct drm_i915_private *dev_priv,
+				      int gpio, bool value)
+{
+	int index;
+
+	if (drm_WARN_ON(&dev_priv->drm, DISPLAY_VER(dev_priv) == 11 && gpio >= MIPI_RESET_2))
+		return;
+
+	switch (gpio) {
+	case MIPI_RESET_1:
+	case MIPI_RESET_2:
+		index = gpio == MIPI_RESET_1 ? HPD_PORT_A : HPD_PORT_B;
+
+		/*
+		 * Disable HPD to set the pin to output, and set output
+		 * value. The HPD pin should not be enabled for DSI anyway,
+		 * assuming the board design and VBT are sane, and the pin isn't
+		 * used by a non-DSI encoder.
+		 *
+		 * The locking protects against concurrent SHOTPLUG_CTL_DDI
+		 * modifications in irq setup and handling.
+		 */
+		spin_lock_irq(&dev_priv->irq_lock);
+		intel_de_rmw(dev_priv, SHOTPLUG_CTL_DDI,
+			     SHOTPLUG_CTL_DDI_HPD_ENABLE(index) |
+			     SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index),
+			     value ? SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index) : 0);
+		spin_unlock_irq(&dev_priv->irq_lock);
+		break;
+	case MIPI_AVDD_EN_1:
+	case MIPI_AVDD_EN_2:
+		index = gpio == MIPI_AVDD_EN_1 ? 0 : 1;
+
+		intel_de_rmw(dev_priv, PP_CONTROL(index), PANEL_POWER_ON,
+			     value ? PANEL_POWER_ON : 0);
+		break;
+	case MIPI_BKLT_EN_1:
+	case MIPI_BKLT_EN_2:
+		index = gpio == MIPI_BKLT_EN_1 ? 0 : 1;
+
+		intel_de_rmw(dev_priv, PP_CONTROL(index), EDP_BLC_ENABLE,
+			     value ? EDP_BLC_ENABLE : 0);
+		break;
+	case MIPI_AVEE_EN_1:
+	case MIPI_AVEE_EN_2:
+		index = gpio == MIPI_AVEE_EN_1 ? 1 : 2;
+
+		intel_de_rmw(dev_priv, GPIO(dev_priv, index),
+			     GPIO_CLOCK_VAL_OUT,
+			     GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_DIR_OUT |
+			     GPIO_CLOCK_VAL_MASK | (value ? GPIO_CLOCK_VAL_OUT : 0));
+		break;
+	case MIPI_VIO_EN_1:
+	case MIPI_VIO_EN_2:
+		index = gpio == MIPI_VIO_EN_1 ? 1 : 2;
+
+		intel_de_rmw(dev_priv, GPIO(dev_priv, index),
+			     GPIO_DATA_VAL_OUT,
+			     GPIO_DATA_DIR_MASK | GPIO_DATA_DIR_OUT |
+			     GPIO_DATA_VAL_MASK | (value ? GPIO_DATA_VAL_OUT : 0));
+		break;
+	default:
+		MISSING_CASE(gpio);
+	}
+}
+
 static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 {
 	struct drm_device *dev = intel_dsi->base.base.dev;
@@ -384,8 +465,7 @@
 	struct intel_connector *connector = intel_dsi->attached_connector;
 	u8 gpio_source, gpio_index = 0, gpio_number;
 	bool value;
-
-	drm_dbg_kms(&dev_priv->drm, "\n");
+	bool native = DISPLAY_VER(dev_priv) >= 11;
 
 	if (connector->panel.vbt.dsi.seq_version >= 3)
 		gpio_index = *data++;
@@ -398,10 +478,18 @@
 	else
 		gpio_source = 0;
 
+	if (connector->panel.vbt.dsi.seq_version >= 4 && *data & BIT(1))
+		native = false;
+
 	/* pull up/down */
 	value = *data++ & 1;
 
-	if (DISPLAY_VER(dev_priv) >= 11)
+	drm_dbg_kms(&dev_priv->drm, "GPIO index %u, number %u, source %u, native %s, set to %s\n",
+		    gpio_index, gpio_number, gpio_source, str_yes_no(native), str_on_off(value));
+
+	if (native)
+		icl_native_gpio_set_value(dev_priv, gpio_number, value);
+	else if (DISPLAY_VER(dev_priv) >= 11)
 		icl_exec_gpio(connector, gpio_source, gpio_index, value);
 	else if (IS_VALLEYVIEW(dev_priv))
 		vlv_exec_gpio(connector, gpio_source, gpio_number, value);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index da09767..f266b68 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -730,37 +730,74 @@
 	bool unpinned;
 
 	/*
-	 * Attempt to pin all of the buffers into the GTT.
-	 * This is done in 2 phases:
+	 * We have one more buffers that we couldn't bind, which could be due to
+	 * various reasons. To resolve this we have 4 passes, with every next
+	 * level turning the screws tighter:
 	 *
-	 * 1. Unbind all objects that do not match the GTT constraints for
-	 *    the execbuffer (fenceable, mappable, alignment etc).
-	 * 2. Bind new objects.
+	 * 0. Unbind all objects that do not match the GTT constraints for the
+	 * execbuffer (fenceable, mappable, alignment etc). Bind all new
+	 * objects.  This avoids unnecessary unbinding of later objects in order
+	 * to make room for the earlier objects *unless* we need to defragment.
 	 *
-	 * This avoid unnecessary unbinding of later objects in order to make
-	 * room for the earlier objects *unless* we need to defragment.
+	 * 1. Reorder the buffers, where objects with the most restrictive
+	 * placement requirements go first (ignoring fixed location buffers for
+	 * now).  For example, objects needing the mappable aperture (the first
+	 * 256M of GTT), should go first vs objects that can be placed just
+	 * about anywhere. Repeat the previous pass.
 	 *
-	 * Defragmenting is skipped if all objects are pinned at a fixed location.
+	 * 2. Consider buffers that are pinned at a fixed location. Also try to
+	 * evict the entire VM this time, leaving only objects that we were
+	 * unable to lock. Try again to bind the buffers. (still using the new
+	 * buffer order).
+	 *
+	 * 3. We likely have object lock contention for one or more stubborn
+	 * objects in the VM, for which we need to evict to make forward
+	 * progress (perhaps we are fighting the shrinker?). When evicting the
+	 * VM this time around, anything that we can't lock we now track using
+	 * the busy_bo, using the full lock (after dropping the vm->mutex to
+	 * prevent deadlocks), instead of trylock. We then continue to evict the
+	 * VM, this time with the stubborn object locked, which we can now
+	 * hopefully unbind (if still bound in the VM). Repeat until the VM is
+	 * evicted. Finally we should be able bind everything.
 	 */
-	for (pass = 0; pass <= 2; pass++) {
+	for (pass = 0; pass <= 3; pass++) {
 		int pin_flags = PIN_USER | PIN_VALIDATE;
 
 		if (pass == 0)
 			pin_flags |= PIN_NONBLOCK;
 
 		if (pass >= 1)
-			unpinned = eb_unbind(eb, pass == 2);
+			unpinned = eb_unbind(eb, pass >= 2);
 
 		if (pass == 2) {
 			err = mutex_lock_interruptible(&eb->context->vm->mutex);
 			if (!err) {
-				err = i915_gem_evict_vm(eb->context->vm, &eb->ww);
+				err = i915_gem_evict_vm(eb->context->vm, &eb->ww, NULL);
 				mutex_unlock(&eb->context->vm->mutex);
 			}
 			if (err)
 				return err;
 		}
 
+		if (pass == 3) {
+retry:
+			err = mutex_lock_interruptible(&eb->context->vm->mutex);
+			if (!err) {
+				struct drm_i915_gem_object *busy_bo = NULL;
+
+				err = i915_gem_evict_vm(eb->context->vm, &eb->ww, &busy_bo);
+				mutex_unlock(&eb->context->vm->mutex);
+				if (err && busy_bo) {
+					err = i915_gem_object_lock(busy_bo, &eb->ww);
+					i915_gem_object_put(busy_bo);
+					if (!err)
+						goto retry;
+				}
+			}
+			if (err)
+				return err;
+		}
+
 		list_for_each_entry(ev, &eb->unbound, bind_link) {
 			err = eb_reserve_vma(eb, ev, pin_flags);
 			if (err)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index c29efde..0ad44f3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -369,7 +369,7 @@
 		if (vma == ERR_PTR(-ENOSPC)) {
 			ret = mutex_lock_interruptible(&ggtt->vm.mutex);
 			if (!ret) {
-				ret = i915_gem_evict_vm(&ggtt->vm, &ww);
+				ret = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
 				mutex_unlock(&ggtt->vm.mutex);
 			}
 			if (ret)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 767e329..9c18b5f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -1109,9 +1109,15 @@
 			continue;
 
 		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+			u32 val = BIT(engine->instance);
+
+			if (engine->class == VIDEO_DECODE_CLASS ||
+			    engine->class == VIDEO_ENHANCEMENT_CLASS ||
+			    engine->class == COMPUTE_CLASS)
+				val = _MASKED_BIT_ENABLE(val);
 			intel_gt_mcr_multicast_write_fw(gt,
 							xehp_regs[engine->class],
-							BIT(engine->instance));
+							val);
 		} else {
 			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
 			if (!i915_mmio_reg_offset(rb.reg))
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 0c80ba5..2bcdd19 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -545,6 +545,32 @@
 	return 0;
 }
 
+static int try_firmware_load(struct intel_uc_fw *uc_fw, const struct firmware **fw)
+{
+	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
+	struct device *dev = gt->i915->drm.dev;
+	int err;
+
+	err = firmware_request_nowarn(fw, uc_fw->file_selected.path, dev);
+
+	if (err)
+		return err;
+
+	if ((*fw)->size > INTEL_UC_RSVD_GGTT_PER_FW) {
+		drm_err(&gt->i915->drm,
+			"%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n",
+			intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path,
+			(*fw)->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K);
+
+		/* try to find another blob to load */
+		release_firmware(*fw);
+		*fw = NULL;
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
 /**
  * intel_uc_fw_fetch - fetch uC firmware
  * @uc_fw: uC firmware
@@ -558,7 +584,6 @@
 	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uc_fw_file file_ideal;
-	struct device *dev = i915->drm.dev;
 	struct drm_i915_gem_object *obj;
 	const struct firmware *fw = NULL;
 	bool old_ver = false;
@@ -574,20 +599,9 @@
 	__force_fw_fetch_failures(uc_fw, -EINVAL);
 	__force_fw_fetch_failures(uc_fw, -ESTALE);
 
-	err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev);
+	err = try_firmware_load(uc_fw, &fw);
 	memcpy(&file_ideal, &uc_fw->file_wanted, sizeof(file_ideal));
 
-	if (!err && fw->size > INTEL_UC_RSVD_GGTT_PER_FW) {
-		drm_err(&i915->drm,
-			"%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n",
-			intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path,
-			fw->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K);
-
-		/* try to find another blob to load */
-		release_firmware(fw);
-		err = -ENOENT;
-	}
-
 	/* Any error is terminal if overriding. Don't bother searching for older versions */
 	if (err && intel_uc_fw_is_overridden(uc_fw))
 		goto fail;
@@ -608,7 +622,7 @@
 			break;
 		}
 
-		err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev);
+		err = try_firmware_load(uc_fw, &fw);
 	}
 
 	if (err)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index f025ee4..a4b4d9b 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -416,6 +416,11 @@
  * @vm: Address space to cleanse
  * @ww: An optional struct i915_gem_ww_ctx. If not NULL, i915_gem_evict_vm
  * will be able to evict vma's locked by the ww as well.
+ * @busy_bo: Optional pointer to struct drm_i915_gem_object. If not NULL, then
+ * in the event i915_gem_evict_vm() is unable to trylock an object for eviction,
+ * then @busy_bo will point to it. -EBUSY is also returned. The caller must drop
+ * the vm->mutex, before trying again to acquire the contended lock. The caller
+ * also owns a reference to the object.
  *
  * This function evicts all vmas from a vm.
  *
@@ -425,7 +430,8 @@
  * To clarify: This is for freeing up virtual address space, not for freeing
  * memory in e.g. the shrinker.
  */
-int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww)
+int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww,
+		      struct drm_i915_gem_object **busy_bo)
 {
 	int ret = 0;
 
@@ -457,15 +463,22 @@
 			 * the resv is shared among multiple objects, we still
 			 * need the object ref.
 			 */
-			if (dying_vma(vma) ||
+			if (!i915_gem_object_get_rcu(vma->obj) ||
 			    (ww && (dma_resv_locking_ctx(vma->obj->base.resv) == &ww->ctx))) {
 				__i915_vma_pin(vma);
 				list_add(&vma->evict_link, &locked_eviction_list);
 				continue;
 			}
 
-			if (!i915_gem_object_trylock(vma->obj, ww))
+			if (!i915_gem_object_trylock(vma->obj, ww)) {
+				if (busy_bo) {
+					*busy_bo = vma->obj; /* holds ref */
+					ret = -EBUSY;
+					break;
+				}
+				i915_gem_object_put(vma->obj);
 				continue;
+			}
 
 			__i915_vma_pin(vma);
 			list_add(&vma->evict_link, &eviction_list);
@@ -473,25 +486,29 @@
 		if (list_empty(&eviction_list) && list_empty(&locked_eviction_list))
 			break;
 
-		ret = 0;
 		/* Unbind locked objects first, before unlocking the eviction_list */
 		list_for_each_entry_safe(vma, vn, &locked_eviction_list, evict_link) {
 			__i915_vma_unpin(vma);
 
-			if (ret == 0)
+			if (ret == 0) {
 				ret = __i915_vma_unbind(vma);
-			if (ret != -EINTR) /* "Get me out of here!" */
-				ret = 0;
+				if (ret != -EINTR) /* "Get me out of here!" */
+					ret = 0;
+			}
+			if (!dying_vma(vma))
+				i915_gem_object_put(vma->obj);
 		}
 
 		list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) {
 			__i915_vma_unpin(vma);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = __i915_vma_unbind(vma);
-			if (ret != -EINTR) /* "Get me out of here!" */
-				ret = 0;
+				if (ret != -EINTR) /* "Get me out of here!" */
+					ret = 0;
+			}
 
 			i915_gem_object_unlock(vma->obj);
+			i915_gem_object_put(vma->obj);
 		}
 	} while (ret == 0);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.h b/drivers/gpu/drm/i915/i915_gem_evict.h
index e593c53..bf0ee0e 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.h
+++ b/drivers/gpu/drm/i915/i915_gem_evict.h
@@ -11,6 +11,7 @@
 struct drm_mm_node;
 struct i915_address_space;
 struct i915_gem_ww_ctx;
+struct drm_i915_gem_object;
 
 int __must_check i915_gem_evict_something(struct i915_address_space *vm,
 					  struct i915_gem_ww_ctx *ww,
@@ -23,6 +24,7 @@
 					 struct drm_mm_node *node,
 					 unsigned int flags);
 int i915_gem_evict_vm(struct i915_address_space *vm,
-		      struct i915_gem_ww_ctx *ww);
+		      struct i915_gem_ww_ctx *ww,
+		      struct drm_i915_gem_object **busy_bo);
 
 #endif /* __I915_GEM_EVICT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index edfe363..91c5339 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1974,7 +1974,10 @@
 	if (ddi_hotplug_trigger) {
 		u32 dig_hotplug_reg;
 
+		/* Locking due to DSI native GPIO sequences */
+		spin_lock(&dev_priv->irq_lock);
 		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI, 0, 0);
+		spin_unlock(&dev_priv->irq_lock);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   ddi_hotplug_trigger, dig_hotplug_reg,
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 6da9784..ccd1f86 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -1129,7 +1129,6 @@
 	{}
 };
 
-__maybe_unused
 static const struct intel_device_info mtl_info = {
 	XE_HP_FEATURES,
 	XE_LPDP_FEATURES,
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 8e1892d..9161768 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5988,6 +5988,7 @@
 
 #define SHOTPLUG_CTL_DDI				_MMIO(0xc4030)
 #define   SHOTPLUG_CTL_DDI_HPD_ENABLE(hpd_pin)			(0x8 << (_HPD_PIN_DDI(hpd_pin) * 4))
+#define   SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(hpd_pin)		(0x4 << (_HPD_PIN_DDI(hpd_pin) * 4))
 #define   SHOTPLUG_CTL_DDI_HPD_STATUS_MASK(hpd_pin)		(0x3 << (_HPD_PIN_DDI(hpd_pin) * 4))
 #define   SHOTPLUG_CTL_DDI_HPD_NO_DETECT(hpd_pin)		(0x0 << (_HPD_PIN_DDI(hpd_pin) * 4))
 #define   SHOTPLUG_CTL_DDI_HPD_SHORT_DETECT(hpd_pin)		(0x1 << (_HPD_PIN_DDI(hpd_pin) * 4))
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 703fee6..3a33be5 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1566,7 +1566,7 @@
 			 * locked objects when called from execbuf when pinning
 			 * is removed. This would probably regress badly.
 			 */
-			i915_gem_evict_vm(vm, NULL);
+			i915_gem_evict_vm(vm, NULL, NULL);
 			mutex_unlock(&vm->mutex);
 		}
 	} while (1);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 8c6517d..3706854 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -344,7 +344,7 @@
 
 	/* Everything is pinned, nothing should happen */
 	mutex_lock(&ggtt->vm.mutex);
-	err = i915_gem_evict_vm(&ggtt->vm, NULL);
+	err = i915_gem_evict_vm(&ggtt->vm, NULL, NULL);
 	mutex_unlock(&ggtt->vm.mutex);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
@@ -356,7 +356,7 @@
 
 	for_i915_gem_ww(&ww, err, false) {
 		mutex_lock(&ggtt->vm.mutex);
-		err = i915_gem_evict_vm(&ggtt->vm, &ww);
+		err = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
 		mutex_unlock(&ggtt->vm.mutex);
 	}
 
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index bb0abbe..4424f53 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -953,7 +953,7 @@
 		goto err_free_dhchap_secret;
 
 	if (!ctrl->opts->dhchap_secret && !ctrl->opts->dhchap_ctrl_secret)
-		return ret;
+		return 0;
 
 	ctrl->dhchap_ctxs = kvcalloc(ctrl_max_dhchaps(ctrl),
 				sizeof(*chap), GFP_KERNEL);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 95c488e..7be562a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1074,6 +1074,18 @@
 	return 0;
 }
 
+static u32 nvme_known_nvm_effects(u8 opcode)
+{
+	switch (opcode) {
+	case nvme_cmd_write:
+	case nvme_cmd_write_zeroes:
+	case nvme_cmd_write_uncor:
+		 return NVME_CMD_EFFECTS_LBCC;
+	default:
+		return 0;
+	}
+}
+
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 {
 	u32 effects = 0;
@@ -1081,16 +1093,24 @@
 	if (ns) {
 		if (ns->head->effects)
 			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
+		if (ns->head->ids.csi == NVME_CAP_CSS_NVM)
+			effects |= nvme_known_nvm_effects(opcode);
 		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
 			dev_warn_once(ctrl->device,
-				"IO command:%02x has unhandled effects:%08x\n",
+				"IO command:%02x has unusual effects:%08x\n",
 				opcode, effects);
-		return 0;
-	}
 
-	if (ctrl->effects)
-		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
-	effects |= nvme_known_admin_effects(opcode);
+		/*
+		 * NVME_CMD_EFFECTS_CSE_MASK causes a freeze all I/O queues,
+		 * which would deadlock when done on an I/O command.  Note that
+		 * We already warn about an unusual effect above.
+		 */
+		effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
+	} else {
+		if (ctrl->effects)
+			effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+		effects |= nvme_known_admin_effects(opcode);
+	}
 
 	return effects;
 }
@@ -4926,7 +4946,7 @@
 
 	memset(set, 0, sizeof(*set));
 	set->ops = ops;
-	set->queue_depth = ctrl->sqsize + 1;
+	set->queue_depth = min_t(unsigned, ctrl->sqsize, BLK_MQ_MAX_DEPTH - 1);
 	/*
 	 * Some Apple controllers requires tags to be unique across admin and
 	 * the (only) I/O queue, so reserve the first 32 tags of the I/O queue.
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 9ddda57..a863991 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -11,6 +11,8 @@
 static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 		fmode_t mode)
 {
+	u32 effects;
+
 	if (capable(CAP_SYS_ADMIN))
 		return true;
 
@@ -43,11 +45,29 @@
 	}
 
 	/*
-	 * Only allow I/O commands that transfer data to the controller if the
-	 * special file is open for writing, but always allow I/O commands that
-	 * transfer data from the controller.
+	 * Check if the controller provides a Commands Supported and Effects log
+	 * and marks this command as supported.  If not reject unprivileged
+	 * passthrough.
 	 */
-	if (nvme_is_write(c))
+	effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
+	if (!(effects & NVME_CMD_EFFECTS_CSUPP))
+		return false;
+
+	/*
+	 * Don't allow passthrough for command that have intrusive (or unknown)
+	 * effects.
+	 */
+	if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
+			NVME_CMD_EFFECTS_UUID_SEL |
+			NVME_CMD_EFFECTS_SCOPE_MASK))
+		return false;
+
+	/*
+	 * Only allow I/O commands that transfer data to the controller or that
+	 * change the logical block contents if the file descriptor is open for
+	 * writing.
+	 */
+	if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC))
 		return mode & FMODE_WRITE;
 	return true;
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 6bbb73e..424c8a4 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -893,7 +893,7 @@
 {
 	struct nvme_ns *ns = req->q->queuedata;
 
-	if (req->cmd_flags & REQ_NVME_MPATH)
+	if ((req->cmd_flags & REQ_NVME_MPATH) && req->bio)
 		trace_block_bio_complete(ns->head->disk->queue, req->bio);
 }
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index f0f8027..b13bacce 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -36,7 +36,7 @@
 #define SQ_SIZE(q)	((q)->q_depth << (q)->sqes)
 #define CQ_SIZE(q)	((q)->q_depth * sizeof(struct nvme_completion))
 
-#define SGES_PER_PAGE	(PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+#define SGES_PER_PAGE	(NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))
 
 /*
  * These can be higher, but we need to ensure that any command doesn't
@@ -144,9 +144,9 @@
 	mempool_t *iod_mempool;
 
 	/* shadow doorbell buffer support: */
-	u32 *dbbuf_dbs;
+	__le32 *dbbuf_dbs;
 	dma_addr_t dbbuf_dbs_dma_addr;
-	u32 *dbbuf_eis;
+	__le32 *dbbuf_eis;
 	dma_addr_t dbbuf_eis_dma_addr;
 
 	/* host memory buffer support: */
@@ -208,10 +208,10 @@
 #define NVMEQ_SQ_CMB		1
 #define NVMEQ_DELETE_ERROR	2
 #define NVMEQ_POLLED		3
-	u32 *dbbuf_sq_db;
-	u32 *dbbuf_cq_db;
-	u32 *dbbuf_sq_ei;
-	u32 *dbbuf_cq_ei;
+	__le32 *dbbuf_sq_db;
+	__le32 *dbbuf_cq_db;
+	__le32 *dbbuf_sq_ei;
+	__le32 *dbbuf_cq_ei;
 	struct completion delete_done;
 };
 
@@ -343,11 +343,11 @@
 }
 
 /* Update dbbuf and return true if an MMIO is required */
-static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
-					      volatile u32 *dbbuf_ei)
+static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
+					      volatile __le32 *dbbuf_ei)
 {
 	if (dbbuf_db) {
-		u16 old_value;
+		u16 old_value, event_idx;
 
 		/*
 		 * Ensure that the queue is written before updating
@@ -355,8 +355,8 @@
 		 */
 		wmb();
 
-		old_value = *dbbuf_db;
-		*dbbuf_db = value;
+		old_value = le32_to_cpu(*dbbuf_db);
+		*dbbuf_db = cpu_to_le32(value);
 
 		/*
 		 * Ensure that the doorbell is updated before reading the event
@@ -366,7 +366,8 @@
 		 */
 		mb();
 
-		if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+		event_idx = le32_to_cpu(*dbbuf_ei);
+		if (!nvme_dbbuf_need_event(event_idx, value, old_value))
 			return false;
 	}
 
@@ -380,9 +381,9 @@
  */
 static int nvme_pci_npages_prp(void)
 {
-	unsigned nprps = DIV_ROUND_UP(NVME_MAX_KB_SZ + NVME_CTRL_PAGE_SIZE,
-				      NVME_CTRL_PAGE_SIZE);
-	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+	unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
+	unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
+	return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8);
 }
 
 /*
@@ -392,7 +393,7 @@
 static int nvme_pci_npages_sgl(void)
 {
 	return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc),
-			PAGE_SIZE);
+			NVME_CTRL_PAGE_SIZE);
 }
 
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
@@ -708,7 +709,7 @@
 		sge->length = cpu_to_le32(entries * sizeof(*sge));
 		sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
 	} else {
-		sge->length = cpu_to_le32(PAGE_SIZE);
+		sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE);
 		sge->type = NVME_SGL_FMT_SEG_DESC << 4;
 	}
 }
@@ -2332,10 +2333,12 @@
 	if (dev->cmb_use_sqes) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
 				sizeof(struct nvme_command));
-		if (result > 0)
+		if (result > 0) {
 			dev->q_depth = result;
-		else
+			dev->ctrl.sqsize = result - 1;
+		} else {
 			dev->cmb_use_sqes = false;
+		}
 	}
 
 	do {
@@ -2536,7 +2539,6 @@
 
 	dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
-	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
 	dev->dbs = dev->bar + 4096;
 
@@ -2577,7 +2579,7 @@
 		dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n",
 			 dev->q_depth);
 	}
-
+	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 
 	nvme_map_cmb(dev);
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 53a004e..6a54ed6 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -164,26 +164,31 @@
 
 static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
 {
-	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_get_log_page] =
+	log->acs[nvme_admin_identify] =
+	log->acs[nvme_admin_abort_cmd] =
+	log->acs[nvme_admin_set_features] =
+	log->acs[nvme_admin_get_features] =
+	log->acs[nvme_admin_async_event] =
+	log->acs[nvme_admin_keep_alive] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
 
-	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_read] =
+	log->iocs[nvme_cmd_flush] =
+	log->iocs[nvme_cmd_dsm]	=
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+	log->iocs[nvme_cmd_write] =
+	log->iocs[nvme_cmd_write_zeroes] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
 }
 
 static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log)
 {
-	log->iocs[nvme_cmd_zone_append]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_zone_mgmt_send]	= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_zone_mgmt_recv]	= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_zone_append] =
+	log->iocs[nvme_cmd_zone_mgmt_send] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
+	log->iocs[nvme_cmd_zone_mgmt_recv] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
 }
 
 static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 79af514..adc0958 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -334,14 +334,13 @@
 	}
 
 	/*
-	 * If there are effects for the command we are about to execute, or
-	 * an end_req function we need to use nvme_execute_passthru_rq()
-	 * synchronously in a work item seeing the end_req function and
-	 * nvme_passthru_end() can't be called in the request done callback
-	 * which is typically in interrupt context.
+	 * If a command needs post-execution fixups, or there are any
+	 * non-trivial effects, make sure to execute the command synchronously
+	 * in a workqueue so that nvme_passthru_end gets called.
 	 */
 	effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode);
-	if (req->p.use_workqueue || effects) {
+	if (req->p.use_workqueue ||
+	    (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))) {
 		INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work);
 		req->p.rq = rq;
 		queue_work(nvmet_wq, &req->p.work);
diff --git a/include/acpi/video.h b/include/acpi/video.h
index a275c35..8ed9bec 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -53,6 +53,7 @@
 };
 
 #if IS_ENABLED(CONFIG_ACPI_VIDEO)
+extern void acpi_video_report_nolcd(void);
 extern int acpi_video_register(void);
 extern void acpi_video_unregister(void);
 extern void acpi_video_register_backlight(void);
@@ -69,6 +70,7 @@
 				 struct acpi_video_device_brightness **dev_br,
 				 int *pmax_level);
 #else
+static inline void acpi_video_report_nolcd(void) { return; };
 static inline int acpi_video_register(void) { return -ENODEV; }
 static inline void acpi_video_unregister(void) { return; }
 static inline void acpi_video_register_backlight(void) { return; }
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index a94219e..659bf3b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -891,7 +891,12 @@
 #define PRINTK_INDEX
 #endif
 
+/*
+ * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler.
+ * Otherwise, the type of .notes section would become PROGBITS instead of NOTES.
+ */
 #define NOTES								\
+	/DISCARD/ : { *(.note.GNU-stack) }				\
 	.notes : AT(ADDR(.notes) - LOAD_OFFSET) {			\
 		BOUNDED_SECTION_BY(.note.*, _notes)			\
 	} NOTES_HEADERS							\
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index d6be2a6..4fad4aa 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_NVME_H
 #define _LINUX_NVME_H
 
+#include <linux/bits.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
 
@@ -639,8 +640,9 @@
 	NVME_CMD_EFFECTS_NCC		= 1 << 2,
 	NVME_CMD_EFFECTS_NIC		= 1 << 3,
 	NVME_CMD_EFFECTS_CCC		= 1 << 4,
-	NVME_CMD_EFFECTS_CSE_MASK	= 3 << 16,
+	NVME_CMD_EFFECTS_CSE_MASK	= GENMASK(18, 16),
 	NVME_CMD_EFFECTS_UUID_SEL	= 1 << 19,
+	NVME_CMD_EFFECTS_SCOPE_MASK	= GENMASK(31, 20),
 };
 
 struct nvme_effects_log {
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 9d4c407..2780bce 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -10,7 +10,15 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
+/*
+ * this file is shared with liburing and that has to autodetect
+ * if linux/time_types.h is available or not, it can
+ * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+ * if linux/time_types.h is not available
+ */
+#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
 #include <linux/time_types.h>
+#endif
 
 #ifdef __cplusplus
 extern "C" {
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 20522d4..55155e2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1767,6 +1767,7 @@
 		__u8 runstate_update_flag;
 		struct {
 			__u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
 		} shared_info;
 		struct {
 			__u32 send_port;
@@ -1798,6 +1799,7 @@
 	} u;
 };
 
+
 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
 #define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
 #define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
@@ -1823,6 +1825,7 @@
 	__u16 pad[3];
 	union {
 		__u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
 		__u64 pad[8];
 		struct {
 			__u64 state;
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 2291a53..b4f5dfa 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -288,24 +288,23 @@
 
 		ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
 
+		mutex_unlock(&ctx->uring_lock);
 		if (ret != -EALREADY)
 			break;
 
-		mutex_unlock(&ctx->uring_lock);
 		ret = io_run_task_work_sig(ctx);
-		if (ret < 0) {
-			mutex_lock(&ctx->uring_lock);
+		if (ret < 0)
 			break;
-		}
 		ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS);
-		mutex_lock(&ctx->uring_lock);
 		if (!ret) {
 			ret = -ETIME;
 			break;
 		}
+		mutex_lock(&ctx->uring_lock);
 	} while (1);
 
 	finish_wait(&ctx->cq_wait, &wait);
+	mutex_lock(&ctx->uring_lock);
 
 	if (ret == -ENOENT || ret > 0)
 		ret = 0;
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ff2bbac..58ac13b 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -677,16 +677,20 @@
 	io_cq_unlock_post(ctx);
 }
 
+static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
+{
+	/* iopoll syncs against uring_lock, not completion_lock */
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		mutex_lock(&ctx->uring_lock);
+	__io_cqring_overflow_flush(ctx);
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		mutex_unlock(&ctx->uring_lock);
+}
+
 static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 {
-	if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
-		/* iopoll syncs against uring_lock, not completion_lock */
-		if (ctx->flags & IORING_SETUP_IOPOLL)
-			mutex_lock(&ctx->uring_lock);
-		__io_cqring_overflow_flush(ctx);
-		if (ctx->flags & IORING_SETUP_IOPOLL)
-			mutex_unlock(&ctx->uring_lock);
-	}
+	if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
+		io_cqring_do_overflow_flush(ctx);
 }
 
 void __io_put_task(struct task_struct *task, int nr)
@@ -2549,7 +2553,10 @@
 
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
-		io_cqring_overflow_flush(ctx);
+		if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
+			finish_wait(&ctx->cq_wait, &iowq.wq);
+			io_cqring_do_overflow_flush(ctx);
+		}
 		prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
 		ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
@@ -4013,8 +4020,6 @@
 		return -EEXIST;
 
 	if (ctx->restricted) {
-		if (opcode >= IORING_REGISTER_LAST)
-			return -EINVAL;
 		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
 		if (!test_bit(opcode, ctx->restrictions.register_op))
 			return -EACCES;
@@ -4170,6 +4175,9 @@
 	long ret = -EBADF;
 	struct fd f;
 
+	if (opcode >= IORING_REGISTER_LAST)
+		return -EINVAL;
+
 	f = fdget(fd);
 	if (!f.file)
 		return -EBADF;
diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c
index 086a22d..a807407 100644
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -286,19 +286,22 @@
 	}
 
 	futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL);
-	if (!futexv)
-		return -ENOMEM;
+	if (!futexv) {
+		ret = -ENOMEM;
+		goto destroy_timer;
+	}
 
 	ret = futex_parse_waitv(futexv, waiters, nr_futexes);
 	if (!ret)
 		ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL);
 
+	kfree(futexv);
+
+destroy_timer:
 	if (timeout) {
 		hrtimer_cancel(&to.timer);
 		destroy_hrtimer_on_stack(&to.timer);
 	}
-
-	kfree(futexv);
 	return ret;
 }
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 7779ee8..010cf4e 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -89,15 +89,31 @@
  * set this bit before looking at the lock.
  */
 
-static __always_inline void
-rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner)
+static __always_inline struct task_struct *
+rt_mutex_owner_encode(struct rt_mutex_base *lock, struct task_struct *owner)
 {
 	unsigned long val = (unsigned long)owner;
 
 	if (rt_mutex_has_waiters(lock))
 		val |= RT_MUTEX_HAS_WAITERS;
 
-	WRITE_ONCE(lock->owner, (struct task_struct *)val);
+	return (struct task_struct *)val;
+}
+
+static __always_inline void
+rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner)
+{
+	/*
+	 * lock->wait_lock is held but explicit acquire semantics are needed
+	 * for a new lock owner so WRITE_ONCE is insufficient.
+	 */
+	xchg_acquire(&lock->owner, rt_mutex_owner_encode(lock, owner));
+}
+
+static __always_inline void rt_mutex_clear_owner(struct rt_mutex_base *lock)
+{
+	/* lock->wait_lock is held so the unlock provides release semantics. */
+	WRITE_ONCE(lock->owner, rt_mutex_owner_encode(lock, NULL));
 }
 
 static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock)
@@ -106,7 +122,8 @@
 			((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
-static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock)
+static __always_inline void
+fixup_rt_mutex_waiters(struct rt_mutex_base *lock, bool acquire_lock)
 {
 	unsigned long owner, *p = (unsigned long *) &lock->owner;
 
@@ -172,8 +189,21 @@
 	 * still set.
 	 */
 	owner = READ_ONCE(*p);
-	if (owner & RT_MUTEX_HAS_WAITERS)
-		WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
+	if (owner & RT_MUTEX_HAS_WAITERS) {
+		/*
+		 * See rt_mutex_set_owner() and rt_mutex_clear_owner() on
+		 * why xchg_acquire() is used for updating owner for
+		 * locking and WRITE_ONCE() for unlocking.
+		 *
+		 * WRITE_ONCE() would work for the acquire case too, but
+		 * in case that the lock acquisition failed it might
+		 * force other lockers into the slow path unnecessarily.
+		 */
+		if (acquire_lock)
+			xchg_acquire(p, owner & ~RT_MUTEX_HAS_WAITERS);
+		else
+			WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
+	}
 }
 
 /*
@@ -208,6 +238,13 @@
 		owner = *p;
 	} while (cmpxchg_relaxed(p, owner,
 				 owner | RT_MUTEX_HAS_WAITERS) != owner);
+
+	/*
+	 * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE
+	 * operations in the event of contention. Ensure the successful
+	 * cmpxchg is visible.
+	 */
+	smp_mb__after_atomic();
 }
 
 /*
@@ -1243,7 +1280,7 @@
 	 * try_to_take_rt_mutex() sets the lock waiters bit
 	 * unconditionally. Clean this up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 
 	return ret;
 }
@@ -1604,7 +1641,7 @@
 	 * try_to_take_rt_mutex() sets the waiter bit
 	 * unconditionally. We might have to fix that up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 
 	trace_contention_end(lock, ret);
 
@@ -1719,7 +1756,7 @@
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally.
 	 * We might have to fix that up:
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 	debug_rt_mutex_free_waiter(&waiter);
 
 	trace_contention_end(lock, 0);
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index 9002209..cb9fdff 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -267,7 +267,7 @@
 void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
 {
 	debug_rt_mutex_proxy_unlock(lock);
-	rt_mutex_set_owner(lock, NULL);
+	rt_mutex_clear_owner(lock);
 }
 
 /**
@@ -382,7 +382,7 @@
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
@@ -438,7 +438,7 @@
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, false);
 
 	raw_spin_unlock_irq(&lock->wait_lock);
 
diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c
index f5f5116..cc32743 100644
--- a/lib/kunit/string-stream.c
+++ b/lib/kunit/string-stream.c
@@ -23,8 +23,10 @@
 		return ERR_PTR(-ENOMEM);
 
 	frag->fragment = kunit_kmalloc(test, len, gfp);
-	if (!frag->fragment)
+	if (!frag->fragment) {
+		kunit_kfree(test, frag);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	return frag;
 }
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 5eb5e82..0ee296c 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -55,6 +55,17 @@
 modpost-args += -n
 endif
 
+ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),)
+modpost-args += -w
+endif
+
+# Read out modules.order to pass in modpost.
+# Otherwise, allmodconfig would fail with "Argument list too long".
+ifdef KBUILD_MODULES
+modpost-args += -T $(MODORDER)
+modpost-deps += $(MODORDER)
+endif
+
 ifeq ($(KBUILD_EXTMOD),)
 
 # Generate the list of in-tree objects in vmlinux
@@ -113,17 +124,6 @@
 
 endif # ($(KBUILD_EXTMOD),)
 
-ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),)
-modpost-args += -w
-endif
-
-ifdef KBUILD_MODULES
-modpost-args += -T $(MODORDER)
-modpost-deps += $(MODORDER)
-endif
-
-# Read out modules.order to pass in modpost.
-# Otherwise, allmodconfig would fail with "Argument list too long".
 quiet_cmd_modpost = MODPOST $@
       cmd_modpost = \
 	$(if $(missing-input), \
diff --git a/scripts/Makefile.package b/scripts/Makefile.package
index 539e9f7..525a282 100644
--- a/scripts/Makefile.package
+++ b/scripts/Makefile.package
@@ -158,6 +158,7 @@
 PHONY += help
 help:
 	@echo '  rpm-pkg             - Build both source and binary RPM kernel packages'
+	@echo '  srcrpm-pkg          - Build only the source kernel RPM package'
 	@echo '  binrpm-pkg          - Build only the binary kernel RPM package'
 	@echo '  deb-pkg             - Build both source and binary deb kernel packages'
 	@echo '  bindeb-pkg          - Build only the binary kernel deb package'
diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c
index 2328f9a..f932aea 100644
--- a/scripts/basic/fixdep.c
+++ b/scripts/basic/fixdep.c
@@ -94,7 +94,6 @@
 #include <unistd.h>
 #include <fcntl.h>
 #include <string.h>
-#include <stdarg.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <ctype.h>
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index 9c54968..e67e0db 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -161,6 +161,12 @@
 "(especially with a larger number of unrolled categories) than the\n"
 "default mode.\n"
 "\n"
+
+"Search\n"
+"-------\n"
+"Pressing the forward-slash (/) anywhere brings up a search dialog box.\n"
+"\n"
+
 "Different color themes available\n"
 "--------------------------------\n"
 "It is possible to select different color themes using the variable\n"
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index dda00a9..adab28f 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -51,7 +51,8 @@
 	URL: https://www.kernel.org
 $S	Source: kernel-$__KERNELRELEASE.tar.gz
 	Provides: $PROVIDES
-$S	BuildRequires: bc binutils bison dwarves elfutils-libelf-devel flex
+$S	BuildRequires: bc binutils bison dwarves
+$S	BuildRequires: (elfutils-libelf-devel or libelf-devel) flex
 $S	BuildRequires: gcc make openssl openssl-devel perl python3 rsync
 
 	# $UTS_MACHINE as a fallback of _arch in case
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 8015e44..386dd9d9 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -167,6 +167,7 @@
 	struct hdmi_ops ops;
 
 	bool dyn_pin_out;
+	bool static_pcm_mapping;
 	/* hdmi interrupt trigger control flag for Nvidia codec */
 	bool hdmi_intr_trig_ctrl;
 	bool nv_dp_workaround; /* workaround DP audio infoframe for Nvidia */
@@ -1525,13 +1526,16 @@
 	 */
 	pcm_jack = pin_idx_to_pcm_jack(codec, per_pin);
 
-	if (eld->eld_valid) {
-		hdmi_attach_hda_pcm(spec, per_pin);
-		hdmi_pcm_setup_pin(spec, per_pin);
-	} else {
-		hdmi_pcm_reset_pin(spec, per_pin);
-		hdmi_detach_hda_pcm(spec, per_pin);
+	if (!spec->static_pcm_mapping) {
+		if (eld->eld_valid) {
+			hdmi_attach_hda_pcm(spec, per_pin);
+			hdmi_pcm_setup_pin(spec, per_pin);
+		} else {
+			hdmi_pcm_reset_pin(spec, per_pin);
+			hdmi_detach_hda_pcm(spec, per_pin);
+		}
 	}
+
 	/* if pcm_idx == -1, it means this is in monitor connection event
 	 * we can get the correct pcm_idx now.
 	 */
@@ -2281,8 +2285,8 @@
 	struct hdmi_spec *spec = codec->spec;
 	int idx, pcm_num;
 
-	/* limit the PCM devices to the codec converters */
-	pcm_num = spec->num_cvts;
+	/* limit the PCM devices to the codec converters or available PINs */
+	pcm_num = min(spec->num_cvts, spec->num_pins);
 	codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num);
 
 	for (idx = 0; idx < pcm_num; idx++) {
@@ -2379,6 +2383,11 @@
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
 		struct hdmi_eld *pin_eld = &per_pin->sink_eld;
 
+		if (spec->static_pcm_mapping) {
+			hdmi_attach_hda_pcm(spec, per_pin);
+			hdmi_pcm_setup_pin(spec, per_pin);
+		}
+
 		pin_eld->eld_valid = false;
 		hdmi_present_sense(per_pin, 0);
 	}
@@ -4419,6 +4428,8 @@
 
 	spec = codec->spec;
 
+	spec->static_pcm_mapping = true;
+
 	spec->ops.pin_get_eld = atihdmi_pin_get_eld;
 	spec->ops.pin_setup_infoframe = atihdmi_pin_setup_infoframe;
 	spec->ops.pin_hbr_setup = atihdmi_pin_hbr_setup;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e443d88..3794b52 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7175,6 +7175,7 @@
 	ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK,
 	ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN,
 	ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS,
+	ALC236_FIXUP_DELL_DUAL_CODECS,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -9130,6 +9131,12 @@
 		.chained = true,
 		.chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 	},
+	[ALC236_FIXUP_DELL_DUAL_CODECS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.func = alc1220_fixup_gb_dual_codecs,
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -9232,6 +9239,12 @@
 	SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
+	SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 59faa5a..b67617b 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -304,7 +304,8 @@
 		for (;;) {
 			done =
 				line6_midibuf_read(mb, line6->buffer_message,
-						LINE6_MIDI_MESSAGE_MAXLEN);
+						   LINE6_MIDI_MESSAGE_MAXLEN,
+						   LINE6_MIDIBUF_READ_RX);
 
 			if (done <= 0)
 				break;
diff --git a/sound/usb/line6/midi.c b/sound/usb/line6/midi.c
index ba0e2b7..0838632 100644
--- a/sound/usb/line6/midi.c
+++ b/sound/usb/line6/midi.c
@@ -44,7 +44,8 @@
 	int req, done;
 
 	for (;;) {
-		req = min(line6_midibuf_bytes_free(mb), line6->max_packet_size);
+		req = min3(line6_midibuf_bytes_free(mb), line6->max_packet_size,
+			   LINE6_FALLBACK_MAXPACKETSIZE);
 		done = snd_rawmidi_transmit_peek(substream, chunk, req);
 
 		if (done == 0)
@@ -56,7 +57,8 @@
 
 	for (;;) {
 		done = line6_midibuf_read(mb, chunk,
-					  LINE6_FALLBACK_MAXPACKETSIZE);
+					  LINE6_FALLBACK_MAXPACKETSIZE,
+					  LINE6_MIDIBUF_READ_TX);
 
 		if (done == 0)
 			break;
diff --git a/sound/usb/line6/midibuf.c b/sound/usb/line6/midibuf.c
index 6a70463..e7f830f 100644
--- a/sound/usb/line6/midibuf.c
+++ b/sound/usb/line6/midibuf.c
@@ -9,6 +9,7 @@
 
 #include "midibuf.h"
 
+
 static int midibuf_message_length(unsigned char code)
 {
 	int message_length;
@@ -20,12 +21,7 @@
 
 		message_length = length[(code >> 4) - 8];
 	} else {
-		/*
-		   Note that according to the MIDI specification 0xf2 is
-		   the "Song Position Pointer", but this is used by Line 6
-		   to send sysex messages to the host.
-		 */
-		static const int length[] = { -1, 2, -1, 2, -1, -1, 1, 1, 1, 1,
+		static const int length[] = { -1, 2, 2, 2, -1, -1, 1, 1, 1, -1,
 			1, 1, 1, -1, 1, 1
 		};
 		message_length = length[code & 0x0f];
@@ -125,7 +121,7 @@
 }
 
 int line6_midibuf_read(struct midi_buffer *this, unsigned char *data,
-		       int length)
+		       int length, int read_type)
 {
 	int bytes_used;
 	int length1, length2;
@@ -148,9 +144,22 @@
 
 	length1 = this->size - this->pos_read;
 
-	/* check MIDI command length */
 	command = this->buf[this->pos_read];
+	/*
+	   PODxt always has status byte lower nibble set to 0010,
+	   when it means to send 0000, so we correct if here so
+	   that control/program changes come on channel 1 and
+	   sysex message status byte is correct
+	 */
+	if (read_type == LINE6_MIDIBUF_READ_RX) {
+		if (command == 0xb2 || command == 0xc2 || command == 0xf2) {
+			unsigned char fixed = command & 0xf0;
+			this->buf[this->pos_read] = fixed;
+			command = fixed;
+		}
+	}
 
+	/* check MIDI command length */
 	if (command & 0x80) {
 		midi_length = midibuf_message_length(command);
 		this->command_prev = command;
diff --git a/sound/usb/line6/midibuf.h b/sound/usb/line6/midibuf.h
index 124a8f9..542e8d8 100644
--- a/sound/usb/line6/midibuf.h
+++ b/sound/usb/line6/midibuf.h
@@ -8,6 +8,9 @@
 #ifndef MIDIBUF_H
 #define MIDIBUF_H
 
+#define LINE6_MIDIBUF_READ_TX 0
+#define LINE6_MIDIBUF_READ_RX 1
+
 struct midi_buffer {
 	unsigned char *buf;
 	int size;
@@ -23,7 +26,7 @@
 extern int line6_midibuf_ignore(struct midi_buffer *mb, int length);
 extern int line6_midibuf_init(struct midi_buffer *mb, int size, int split);
 extern int line6_midibuf_read(struct midi_buffer *mb, unsigned char *data,
-			      int length);
+			      int length, int read_type);
 extern void line6_midibuf_reset(struct midi_buffer *mb);
 extern int line6_midibuf_write(struct midi_buffer *mb, unsigned char *data,
 			       int length);
diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c
index cd41aa7..d173971 100644
--- a/sound/usb/line6/pod.c
+++ b/sound/usb/line6/pod.c
@@ -159,8 +159,9 @@
 	.bytes_per_channel = 3 /* SNDRV_PCM_FMTBIT_S24_3LE */
 };
 
+
 static const char pod_version_header[] = {
-	0xf2, 0x7e, 0x7f, 0x06, 0x02
+	0xf0, 0x7e, 0x7f, 0x06, 0x02
 };
 
 static char *pod_alloc_sysex_buffer(struct usb_line6_pod *pod, int code,
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 6ce8c48..6d9381d 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,86 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
-/aarch64/aarch32_id_regs
-/aarch64/arch_timer
-/aarch64/debug-exceptions
-/aarch64/get-reg-list
-/aarch64/hypercalls
-/aarch64/page_fault_test
-/aarch64/psci_test
-/aarch64/vcpu_width_config
-/aarch64/vgic_init
-/aarch64/vgic_irq
-/s390x/memop
-/s390x/resets
-/s390x/sync_regs_test
-/s390x/tprot
-/x86_64/amx_test
-/x86_64/cpuid_test
-/x86_64/cr4_cpuid_sync_test
-/x86_64/debug_regs
-/x86_64/exit_on_emulation_failure_test
-/x86_64/fix_hypercall_test
-/x86_64/get_msr_index_features
-/x86_64/kvm_clock_test
-/x86_64/kvm_pv_test
-/x86_64/hyperv_clock
-/x86_64/hyperv_cpuid
-/x86_64/hyperv_evmcs
-/x86_64/hyperv_features
-/x86_64/hyperv_ipi
-/x86_64/hyperv_svm_test
-/x86_64/hyperv_tlb_flush
-/x86_64/max_vcpuid_cap_test
-/x86_64/mmio_warning_test
-/x86_64/monitor_mwait_test
-/x86_64/nested_exceptions_test
-/x86_64/nx_huge_pages_test
-/x86_64/platform_info_test
-/x86_64/pmu_event_filter_test
-/x86_64/set_boot_cpu_id
-/x86_64/set_sregs_test
-/x86_64/sev_migrate_tests
-/x86_64/smaller_maxphyaddr_emulation_test
-/x86_64/smm_test
-/x86_64/state_test
-/x86_64/svm_vmcall_test
-/x86_64/svm_int_ctl_test
-/x86_64/svm_nested_soft_inject_test
-/x86_64/svm_nested_shutdown_test
-/x86_64/sync_regs_test
-/x86_64/tsc_msrs_test
-/x86_64/tsc_scaling_sync
-/x86_64/ucna_injection_test
-/x86_64/userspace_io_test
-/x86_64/userspace_msr_exit_test
-/x86_64/vmx_apic_access_test
-/x86_64/vmx_close_while_nested_test
-/x86_64/vmx_dirty_log_test
-/x86_64/vmx_exception_with_invalid_guest_state
-/x86_64/vmx_invalid_nested_guest_state
-/x86_64/vmx_msrs_test
-/x86_64/vmx_preemption_timer_test
-/x86_64/vmx_set_nested_state_test
-/x86_64/vmx_tsc_adjust_test
-/x86_64/vmx_nested_tsc_scaling_test
-/x86_64/xapic_ipi_test
-/x86_64/xapic_state_test
-/x86_64/xen_shinfo_test
-/x86_64/xen_vmcall_test
-/x86_64/xss_msr_test
-/x86_64/vmx_pmu_caps_test
-/x86_64/triple_fault_event_test
-/access_tracking_perf_test
-/demand_paging_test
-/dirty_log_test
-/dirty_log_perf_test
-/hardware_disable_test
-/kvm_create_max_vcpus
-/kvm_page_table_test
-/max_guest_memory_test
-/memslot_modification_stress_test
-/memslot_perf_test
-/rseq_test
-/set_memory_region_test
-/steal_time
-/kvm_binary_stats_test
-/system_counter_offset_test
+*
+!/**/
+!*.c
+!*.h
+!*.S
+!*.sh
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 9476769..1750f91 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -7,35 +7,14 @@
 include $(top_srcdir)/scripts/subarch.include
 ARCH            ?= $(SUBARCH)
 
-# For cross-builds to work, UNAME_M has to map to ARCH and arch specific
-# directories and targets in this Makefile. "uname -m" doesn't map to
-# arch specific sub-directory names.
-#
-# UNAME_M variable to used to run the compiles pointing to the right arch
-# directories and build the right targets for these supported architectures.
-#
-# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable.
-# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable.
-#
-# x86_64 targets are named to include x86_64 as a suffix and directories
-# for includes are in x86_64 sub-directory. s390x and aarch64 follow the
-# same convention. "uname -m" doesn't result in the correct mapping for
-# s390x and aarch64.
-#
-# No change necessary for x86_64
-UNAME_M := $(shell uname -m)
-
-# Set UNAME_M for arm64 compile/install to work
-ifeq ($(ARCH),arm64)
-	UNAME_M := aarch64
-endif
-# Set UNAME_M s390x compile/install to work
-ifeq ($(ARCH),s390)
-	UNAME_M := s390x
-endif
-# Set UNAME_M riscv compile/install to work
-ifeq ($(ARCH),riscv)
-	UNAME_M := riscv
+ifeq ($(ARCH),x86)
+	ARCH_DIR := x86_64
+else ifeq ($(ARCH),arm64)
+	ARCH_DIR := aarch64
+else ifeq ($(ARCH),s390)
+	ARCH_DIR := s390x
+else
+	ARCH_DIR := $(ARCH)
 endif
 
 LIBKVM += lib/assert.c
@@ -196,10 +175,15 @@
 TEST_GEN_PROGS_riscv += set_memory_region_test
 TEST_GEN_PROGS_riscv += kvm_binary_stats_test
 
-TEST_PROGS += $(TEST_PROGS_$(UNAME_M))
-TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
-TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(UNAME_M))
-LIBKVM += $(LIBKVM_$(UNAME_M))
+TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR))
+LIBKVM += $(LIBKVM_$(ARCH_DIR))
+
+# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most
+# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`,
+# which causes the environment variable to override the makefile).
+include ../lib.mk
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
@@ -210,25 +194,23 @@
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
+	-Wno-gnu-variable-sized-type-not-at-end \
+	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
 	-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
-	-I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \
+	-I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \
 	$(KHDR_INCLUDES)
 
-no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
-        $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
+no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
+        $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
 
 # On s390, build the testcases KVM-enabled
-pgste-option = $(call try-run, echo 'int main() { return 0; }' | \
+pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \
 	$(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste)
 
 LDLIBS += -ldl
 LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
 
-# After inclusion, $(OUTPUT) is defined and
-# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
-include ../lib.mk
-
 LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 95d22cf..beb944f 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -117,7 +117,7 @@
 	GUEST_ASSERT(guest_check_lse());
 	asm volatile(".arch_extension lse\n"
 		     "casal %0, %1, [%2]\n"
-		     :: "r" (0), "r" (TEST_DATA), "r" (guest_test_memory));
+		     :: "r" (0ul), "r" (TEST_DATA), "r" (guest_test_memory));
 	val = READ_ONCE(*guest_test_memory);
 	GUEST_ASSERT_EQ(val, TEST_DATA);
 }
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index 562c16d..f212bd8 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -14,11 +14,13 @@
 
 void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
-	virt_pg_map(vm, mmio_gpa, mmio_gpa);
+	vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR);
+
+	virt_map(vm, mmio_gva, mmio_gpa, 1);
 
 	vm->ucall_mmio_addr = mmio_gpa;
 
-	write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa);
+	write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva);
 }
 
 void ucall_arch_do_ucall(vm_vaddr_t uc)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index c88c3ac..56d5ea9 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -186,6 +186,15 @@
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
 
+/*
+ * Initializes vm->vpages_valid to match the canonical VA space of the
+ * architecture.
+ *
+ * The default implementation is valid for architectures which split the
+ * range addressed by a single page table into a low and high region
+ * based on the MSB of the VA. On architectures with this behavior
+ * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1].
+ */
 __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
 {
 	sparsebit_set_num(vm->vpages_valid,
@@ -1416,10 +1425,10 @@
 
 	while (npages--) {
 		virt_pg_map(vm, vaddr, paddr);
+		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
+
 		vaddr += page_size;
 		paddr += page_size;
-
-		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index 0cc0971..2f0e2ea 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -4,6 +4,8 @@
 #include "linux/bitmap.h"
 #include "linux/atomic.h"
 
+#define GUEST_UCALL_FAILED -1
+
 struct ucall_header {
 	DECLARE_BITMAP(in_use, KVM_MAX_VCPUS);
 	struct ucall ucalls[KVM_MAX_VCPUS];
@@ -41,7 +43,8 @@
 	struct ucall *uc;
 	int i;
 
-	GUEST_ASSERT(ucall_pool);
+	if (!ucall_pool)
+		goto ucall_failed;
 
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (!test_and_set_bit(i, ucall_pool->in_use)) {
@@ -51,7 +54,13 @@
 		}
 	}
 
-	GUEST_ASSERT(0);
+ucall_failed:
+	/*
+	 * If the vCPU cannot grab a ucall structure, make a bare ucall with a
+	 * magic value to signal to get_ucall() that things went sideways.
+	 * GUEST_ASSERT() depends on ucall_alloc() and so cannot be used here.
+	 */
+	ucall_arch_do_ucall(GUEST_UCALL_FAILED);
 	return NULL;
 }
 
@@ -93,6 +102,9 @@
 
 	addr = ucall_arch_get_ucall(vcpu);
 	if (addr) {
+		TEST_ASSERT(addr != (void *)GUEST_UCALL_FAILED,
+			    "Guest failed to allocate ucall struct");
+
 		memcpy(uc, addr, sizeof(*uc));
 		vcpu_run_complete_io(vcpu);
 	} else {
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index c4d368d..acfa1d0 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1031,7 +1031,7 @@
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 {
 	if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) {
-		*pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
+		*pa_bits = kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
 		*va_bits = 32;
 	} else {
 		*pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR);
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index e698306..e6587e1 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -265,6 +265,9 @@
 	slots = data->nslots;
 	while (--slots > 1) {
 		pages_per_slot = mempages / slots;
+		if (!pages_per_slot)
+			continue;
+
 		rempages = mempages % pages_per_slot;
 		if (check_slot_pages(host_page_size, guest_page_size,
 				     pages_per_slot, rempages))
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
index 8b791ea..0cbb0e6 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
@@ -193,8 +193,9 @@
 	GUEST_SYNC(stage++);
 	/*
 	 * 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL.
-	 * Nothing to write anything to XMM regs.
 	 */
+	ipi_ex->vp_set.valid_bank_mask = 0;
+	hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2);
 	hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT,
 			 IPI_VECTOR, HV_GENERIC_SET_ALL);
 	nop_loop();
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
index e497ace..b34980d 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -41,8 +41,17 @@
 static void l2_guest_code_int(void)
 {
 	GUEST_ASSERT_1(int_fired == 1, int_fired);
-	vmmcall();
-	ud2();
+
+	/*
+         * Same as the vmmcall() function, but with a ud2 sneaked after the
+         * vmmcall.  The caller injects an exception with the return address
+         * increased by 2, so the "pop rbp" must be after the ud2 and we cannot
+	 * use vmmcall() directly.
+         */
+	__asm__ __volatile__("push %%rbp; vmmcall; ud2; pop %%rbp"
+                             : : "a"(0xdeadbeef), "c"(0xbeefdead)
+                             : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+                               "r10", "r11", "r12", "r13", "r14", "r15");
 
 	GUEST_ASSERT_1(bp_fired == 1, bp_fired);
 	hlt();
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 5943187..ff8ecdf 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -49,11 +49,6 @@
 	NUM_VMX_PAGES,
 };
 
-struct kvm_single_msr {
-	struct kvm_msrs header;
-	struct kvm_msr_entry entry;
-} __attribute__((packed));
-
 /* The virtual machine object. */
 static struct kvm_vm *vm;
 
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 721f6a6..dae510c 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -962,6 +962,12 @@
 	}
 
  done:
+	struct kvm_xen_hvm_attr evt_reset = {
+		.type = KVM_XEN_ATTR_TYPE_EVTCHN,
+		.u.evtchn.flags = KVM_XEN_EVTCHN_RESET,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
+
 	alarm(0);
 	clock_gettime(CLOCK_REALTIME, &max_ts);
 
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index a1ab150..180f1a0 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -14,14 +14,10 @@
 #define KVM_MMU_LOCK_INIT(kvm)		rwlock_init(&(kvm)->mmu_lock)
 #define KVM_MMU_LOCK(kvm)		write_lock(&(kvm)->mmu_lock)
 #define KVM_MMU_UNLOCK(kvm)		write_unlock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_LOCK(kvm)		read_lock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_UNLOCK(kvm)	read_unlock(&(kvm)->mmu_lock)
 #else
 #define KVM_MMU_LOCK_INIT(kvm)		spin_lock_init(&(kvm)->mmu_lock)
 #define KVM_MMU_LOCK(kvm)		spin_lock(&(kvm)->mmu_lock)
 #define KVM_MMU_UNLOCK(kvm)		spin_unlock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_LOCK(kvm)		spin_lock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_UNLOCK(kvm)	spin_unlock(&(kvm)->mmu_lock)
 #endif /* KVM_HAVE_MMU_RWLOCK */
 
 kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,