Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Move the bpf verifier trace check into the new switch statement in
HEAD.

Resolve the overlapping changes in hinic, where bug fixes overlap
the addition of VF support.

Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/core-api/printk-formats.rst

@@ -112,6 +112,20 @@ used when printing stack backtraces. The specifier takes into
 consideration the effect of compiler optimisations which may occur
 when tail-calls are used and marked with the noreturn GCC attribute.
 
+Probed Pointers from BPF / tracing
+----------------------------------
+
+::
+
+	%pks	kernel string
+	%pus	user string
+
+The ``k`` and ``u`` specifiers are used for printing prior probed memory from
+either kernel memory (k) or user memory (u). The subsequent ``s`` specifier
+results in printing a string. For direct use in regular vsnprintf() the (k)
+and (u) annotation is ignored, however, when used out of BPF's bpf_trace_printk(),
+for example, it reads the memory it is pointing to without faulting.
+
 Kernel Pointers
 ---------------
 

Documentation/virt/kvm/index.rst

@@ -28,3 +28,5 @@ KVM
    arm/index
 
    devices/index
+
+   running-nested-guests

Documentation/virt/kvm/running-nested-guests.rst

@@ -0,0 +1,276 @@
+==============================
+Running nested guests with KVM
+==============================
+
+A nested guest is the ability to run a guest inside another guest (it
+can be KVM-based or a different hypervisor).  The straightforward
+example is a KVM guest that in turn runs on a KVM guest (the rest of
+this document is built on this example)::
+
+              .----------------.  .----------------.
+              |                |  |                |
+              |      L2        |  |      L2        |
+              | (Nested Guest) |  | (Nested Guest) |
+              |                |  |                |
+              |----------------'--'----------------|
+              |                                    |
+              |       L1 (Guest Hypervisor)        |
+              |          KVM (/dev/kvm)            |
+              |                                    |
+      .------------------------------------------------------.
+      |                 L0 (Host Hypervisor)                 |
+      |                    KVM (/dev/kvm)                    |
+      |------------------------------------------------------|
+      |        Hardware (with virtualization extensions)     |
+      '------------------------------------------------------'
+
+Terminology:
+
+- L0 – level-0; the bare metal host, running KVM
+
+- L1 – level-1 guest; a VM running on L0; also called the "guest
+  hypervisor", as it itself is capable of running KVM.
+
+- L2 – level-2 guest; a VM running on L1, this is the "nested guest"
+
+.. note:: The above diagram is modelled after the x86 architecture;
+          s390x, ppc64 and other architectures are likely to have
+          a different design for nesting.
+
+          For example, s390x always has an LPAR (LogicalPARtition)
+          hypervisor running on bare metal, adding another layer and
+          resulting in at least four levels in a nested setup — L0 (bare
+          metal, running the LPAR hypervisor), L1 (host hypervisor), L2
+          (guest hypervisor), L3 (nested guest).
+
+          This document will stick with the three-level terminology (L0,
+          L1, and L2) for all architectures; and will largely focus on
+          x86.
+
+
+Use Cases
+---------
+
+There are several scenarios where nested KVM can be useful, to name a
+few:
+
+- As a developer, you want to test your software on different operating
+  systems (OSes).  Instead of renting multiple VMs from a Cloud
+  Provider, using nested KVM lets you rent a large enough "guest
+  hypervisor" (level-1 guest).  This in turn allows you to create
+  multiple nested guests (level-2 guests), running different OSes, on
+  which you can develop and test your software.
+
+- Live migration of "guest hypervisors" and their nested guests, for
+  load balancing, disaster recovery, etc.
+
+- VM image creation tools (e.g. ``virt-install``,  etc) often run
+  their own VM, and users expect these to work inside a VM.
+
+- Some OSes use virtualization internally for security (e.g. to let
+  applications run safely in isolation).
+
+
+Enabling "nested" (x86)
+-----------------------
+
+From Linux kernel v4.19 onwards, the ``nested`` KVM parameter is enabled
+by default for Intel and AMD.  (Though your Linux distribution might
+override this default.)
+
+In case you are running a Linux kernel older than v4.19, to enable
+nesting, set the ``nested`` KVM module parameter to ``Y`` or ``1``.  To
+persist this setting across reboots, you can add it in a config file, as
+shown below:
+
+1. On the bare metal host (L0), list the kernel modules and ensure that
+   the KVM modules::
+
+    $ lsmod | grep -i kvm
+    kvm_intel             133627  0
+    kvm                   435079  1 kvm_intel
+
+2. Show information for ``kvm_intel`` module::
+
+    $ modinfo kvm_intel | grep -i nested
+    parm:           nested:bool
+
+3. For the nested KVM configuration to persist across reboots, place the
+   below in ``/etc/modprobed/kvm_intel.conf`` (create the file if it
+   doesn't exist)::
+
+    $ cat /etc/modprobe.d/kvm_intel.conf
+    options kvm-intel nested=y
+
+4. Unload and re-load the KVM Intel module::
+
+    $ sudo rmmod kvm-intel
+    $ sudo modprobe kvm-intel
+
+5. Verify if the ``nested`` parameter for KVM is enabled::
+
+    $ cat /sys/module/kvm_intel/parameters/nested
+    Y
+
+For AMD hosts, the process is the same as above, except that the module
+name is ``kvm-amd``.
+
+
+Additional nested-related kernel parameters (x86)
+-------------------------------------------------
+
+If your hardware is sufficiently advanced (Intel Haswell processor or
+higher, which has newer hardware virt extensions), the following
+additional features will also be enabled by default: "Shadow VMCS
+(Virtual Machine Control Structure)", APIC Virtualization on your bare
+metal host (L0).  Parameters for Intel hosts::
+
+    $ cat /sys/module/kvm_intel/parameters/enable_shadow_vmcs
+    Y
+
+    $ cat /sys/module/kvm_intel/parameters/enable_apicv
+    Y
+
+    $ cat /sys/module/kvm_intel/parameters/ept
+    Y
+
+.. note:: If you suspect your L2 (i.e. nested guest) is running slower,
+          ensure the above are enabled (particularly
+          ``enable_shadow_vmcs`` and ``ept``).
+
+
+Starting a nested guest (x86)
+-----------------------------
+
+Once your bare metal host (L0) is configured for nesting, you should be
+able to start an L1 guest with::
+
+    $ qemu-kvm -cpu host [...]
+
+The above will pass through the host CPU's capabilities as-is to the
+gues); or for better live migration compatibility, use a named CPU
+model supported by QEMU. e.g.::
+
+    $ qemu-kvm -cpu Haswell-noTSX-IBRS,vmx=on
+
+then the guest hypervisor will subsequently be capable of running a
+nested guest with accelerated KVM.
+
+
+Enabling "nested" (s390x)
+-------------------------
+
+1. On the host hypervisor (L0), enable the ``nested`` parameter on
+   s390x::
+
+    $ rmmod kvm
+    $ modprobe kvm nested=1
+
+.. note:: On s390x, the kernel parameter ``hpage`` is mutually exclusive
+          with the ``nested`` paramter — i.e. to be able to enable
+          ``nested``, the ``hpage`` parameter *must* be disabled.
+
+2. The guest hypervisor (L1) must be provided with the ``sie`` CPU
+   feature — with QEMU, this can be done by using "host passthrough"
+   (via the command-line ``-cpu host``).
+
+3. Now the KVM module can be loaded in the L1 (guest hypervisor)::
+
+    $ modprobe kvm
+
+
+Live migration with nested KVM
+------------------------------
+
+Migrating an L1 guest, with a  *live* nested guest in it, to another
+bare metal host, works as of Linux kernel 5.3 and QEMU 4.2.0 for
+Intel x86 systems, and even on older versions for s390x.
+
+On AMD systems, once an L1 guest has started an L2 guest, the L1 guest
+should no longer be migrated or saved (refer to QEMU documentation on
+"savevm"/"loadvm") until the L2 guest shuts down.  Attempting to migrate
+or save-and-load an L1 guest while an L2 guest is running will result in
+undefined behavior.  You might see a ``kernel BUG!`` entry in ``dmesg``, a
+kernel 'oops', or an outright kernel panic.  Such a migrated or loaded L1
+guest can no longer be considered stable or secure, and must be restarted.
+Migrating an L1 guest merely configured to support nesting, while not
+actually running L2 guests, is expected to function normally even on AMD
+systems but may fail once guests are started.
+
+Migrating an L2 guest is always expected to succeed, so all the following
+scenarios should work even on AMD systems:
+
+- Migrating a nested guest (L2) to another L1 guest on the *same* bare
+  metal host.
+
+- Migrating a nested guest (L2) to another L1 guest on a *different*
+  bare metal host.
+
+- Migrating a nested guest (L2) to a bare metal host.
+
+Reporting bugs from nested setups
+-----------------------------------
+
+Debugging "nested" problems can involve sifting through log files across
+L0, L1 and L2; this can result in tedious back-n-forth between the bug
+reporter and the bug fixer.
+
+- Mention that you are in a "nested" setup.  If you are running any kind
+  of "nesting" at all, say so.  Unfortunately, this needs to be called
+  out because when reporting bugs, people tend to forget to even
+  *mention* that they're using nested virtualization.
+
+- Ensure you are actually running KVM on KVM.  Sometimes people do not
+  have KVM enabled for their guest hypervisor (L1), which results in
+  them running with pure emulation or what QEMU calls it as "TCG", but
+  they think they're running nested KVM.  Thus confusing "nested Virt"
+  (which could also mean, QEMU on KVM) with "nested KVM" (KVM on KVM).
+
+Information to collect (generic)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The following is not an exhaustive list, but a very good starting point:
+
+  - Kernel, libvirt, and QEMU version from L0
+
+  - Kernel, libvirt and QEMU version from L1
+
+  - QEMU command-line of L1 -- when using libvirt, you'll find it here:
+    ``/var/log/libvirt/qemu/instance.log``
+
+  - QEMU command-line of L2 -- as above, when using libvirt, get the
+    complete libvirt-generated QEMU command-line
+
+  - ``cat /sys/cpuinfo`` from L0
+
+  - ``cat /sys/cpuinfo`` from L1
+
+  - ``lscpu`` from L0
+
+  - ``lscpu`` from L1
+
+  - Full ``dmesg`` output from L0
+
+  - Full ``dmesg`` output from L1
+
+x86-specific info to collect
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Both the below commands, ``x86info`` and ``dmidecode``, should be
+available on most Linux distributions with the same name:
+
+  - Output of: ``x86info -a`` from L0
+
+  - Output of: ``x86info -a`` from L1
+
+  - Output of: ``dmidecode`` from L0
+
+  - Output of: ``dmidecode`` from L1
+
+s390x-specific info to collect
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Along with the earlier mentioned generic details, the below is
+also recommended:
+
+  - ``/proc/sysinfo`` from L1; this will also include the info from L0

MAINTAINERS

@@ -3936,11 +3936,9 @@ F:	arch/powerpc/platforms/cell/
 CEPH COMMON CODE (LIBCEPH)
 M:	Ilya Dryomov <idryomov@gmail.com>
 M:	Jeff Layton <jlayton@kernel.org>
-M:	Sage Weil <sage@redhat.com>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 T:	git git://github.com/ceph/ceph-client.git
 F:	include/linux/ceph/
 F:	include/linux/crush/
@@ -3948,12 +3946,10 @@ F:	net/ceph/
 
 CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
 M:	Jeff Layton <jlayton@kernel.org>
-M:	Sage Weil <sage@redhat.com>
 M:	Ilya Dryomov <idryomov@gmail.com>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 T:	git git://github.com/ceph/ceph-client.git
 F:	Documentation/filesystems/ceph.rst
 F:	fs/ceph/
@@ -7119,9 +7115,10 @@ F:	include/uapi/asm-generic/
 
 GENERIC PHY FRAMEWORK
 M:	Kishon Vijay Abraham I <kishon@ti.com>
+M:	Vinod Koul <vkoul@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kishon/linux-phy.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git
 F:	Documentation/devicetree/bindings/phy/
 F:	drivers/phy/
 F:	include/linux/phy/
@@ -7746,11 +7743,6 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Orphan
 F:	drivers/platform/x86/tc1100-wmi.c
 
-HP100:	Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series
-M:	Jaroslav Kysela <perex@perex.cz>
-S:	Obsolete
-F:	drivers/staging/hp/hp100.*
-
 HPET:	High Precision Event Timers driver
 M:	Clemens Ladisch <clemens@ladisch.de>
 S:	Maintained
@@ -11718,8 +11710,9 @@ F:	net/core/drop_monitor.c
 
 NETWORKING DRIVERS
 M:	"David S. Miller" <davem@davemloft.net>
+M:	Jakub Kicinski <kuba@kernel.org>
 L:	netdev@vger.kernel.org
-S:	Odd Fixes
+S:	Maintained
 W:	http://www.linuxfoundation.org/en/Net
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
@@ -14102,12 +14095,10 @@ F:	drivers/media/radio/radio-tea5777.c
 
 RADOS BLOCK DEVICE (RBD)
 M:	Ilya Dryomov <idryomov@gmail.com>
-M:	Sage Weil <sage@redhat.com>
 R:	Dongsheng Yang <dongsheng.yang@easystack.cn>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 T:	git git://github.com/ceph/ceph-client.git
 F:	Documentation/ABI/testing/sysfs-bus-rbd
 F:	drivers/block/rbd.c
@@ -14644,6 +14635,7 @@ F:	drivers/iommu/s390-iommu.c
 
 S390 IUCV NETWORK LAYER
 M:	Julian Wiedmann <jwi@linux.ibm.com>
+M:	Karsten Graul <kgraul@linux.ibm.com>
 M:	Ursula Braun <ubraun@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
@@ -14654,6 +14646,7 @@ F:	net/iucv/
 
 S390 NETWORK DRIVERS
 M:	Julian Wiedmann <jwi@linux.ibm.com>
+M:	Karsten Graul <kgraul@linux.ibm.com>
 M:	Ursula Braun <ubraun@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -729,10 +729,6 @@ else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS += -Os
 endif
 
-ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED
-KBUILD_CFLAGS   += -Wno-maybe-uninitialized
-endif
-
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
 KBUILD_CFLAGS	+= $(call cc-option,-fno-allow-store-data-races)
@@ -881,6 +877,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 # disable stringop warnings in gcc 8+
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
+# We'll want to enable this eventually, but it's not going away for 5.7 at least
+KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
+
+# Another good warning that we'll want to enable eventually
+KBUILD_CFLAGS += $(call cc-disable-warning, restrict)
+
+# Enabled with W=2, disabled by default as noisy
+KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 

arch/arm/Kconfig

@@ -12,6 +12,7 @@ config ARM
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_SETUP_DMA_OPS

arch/arm/configs/keystone_defconfig

@@ -147,6 +147,7 @@ CONFIG_I2C_DAVINCI=y
 CONFIG_SPI=y
 CONFIG_SPI_DAVINCI=y
 CONFIG_SPI_SPIDEV=y
+CONFIG_PTP_1588_CLOCK=y
 CONFIG_PINCTRL_SINGLE=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y

arch/arm/configs/omap2plus_defconfig

@@ -274,6 +274,7 @@ CONFIG_SPI_TI_QSPI=m
 CONFIG_HSI=m
 CONFIG_OMAP_SSI=m
 CONFIG_SSI_PROTOCOL=m
+CONFIG_PTP_1588_CLOCK=y
 CONFIG_PINCTRL_SINGLE=y
 CONFIG_DEBUG_GPIO=y
 CONFIG_GPIO_SYSFS=y

arch/arm/include/asm/futex.h

@@ -165,7 +165,12 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 	preempt_enable();
 #endif
 
-	if (!ret)
+	/*
+	 * Store unconditionally. If ret != 0 the extra store is the least
+	 * of the worries but GCC cannot figure out that __futex_atomic_op()
+	 * is either setting ret to -EFAULT or storing the old value in
+	 * oldval which results in a uninitialized warning at the call site.
+	 */
 	*oval = oldval;
 
 	return ret;

arch/arm64/Kconfig

@@ -20,6 +20,7 @@ config ARM64
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SETUP_DMA_OPS

arch/arm64/kernel/machine_kexec.c

@@ -177,6 +177,7 @@ void machine_kexec(struct kimage *kimage)
 	 * the offline CPUs. Therefore, we must use the __* variant here.
 	 */
 	__flush_icache_range((uintptr_t)reboot_code_buffer,
+			     (uintptr_t)reboot_code_buffer +
 			     arm64_relocate_new_kernel_size);
 
 	/* Flush the kimage list and its buffers. */

arch/arm64/kvm/guest.c

@@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+
+	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
+		int i;
+
+		for (i = 0; i < 16; i++)
+			*vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i);
+	}
 out:
 	return err;
 }

arch/arm64/kvm/hyp/entry.S

@@ -18,6 +18,7 @@
 
 #define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
 #define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
 	.pushsection	.hyp.text, "ax"
@@ -47,6 +48,16 @@
 	ldp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
 .endm
 
+.macro save_sp_el0 ctxt, tmp
+	mrs	\tmp,	sp_el0
+	str	\tmp,	[\ctxt, #CPU_SP_EL0_OFFSET]
+.endm
+
+.macro restore_sp_el0 ctxt, tmp
+	ldr	\tmp,	  [\ctxt, #CPU_SP_EL0_OFFSET]
+	msr	sp_el0, \tmp
+.endm
+
 /*
  * u64 __guest_enter(struct kvm_vcpu *vcpu,
  *		     struct kvm_cpu_context *host_ctxt);
@@ -60,6 +71,9 @@ SYM_FUNC_START(__guest_enter)
 	// Store the host regs
 	save_callee_saved_regs x1
 
+	// Save the host's sp_el0
+	save_sp_el0	x1, x2
+
 	// Now the host state is stored if we have a pending RAS SError it must
 	// affect the host. If any asynchronous exception is pending we defer
 	// the guest entry. The DSB isn't necessary before v8.2 as any SError
@@ -83,6 +97,9 @@ alternative_else_nop_endif
 	// when this feature is enabled for kernel code.
 	ptrauth_switch_to_guest x29, x0, x1, x2
 
+	// Restore the guest's sp_el0
+	restore_sp_el0 x29, x0
+
 	// Restore guest regs x0-x17
 	ldp	x0, x1,   [x29, #CPU_XREG_OFFSET(0)]
 	ldp	x2, x3,   [x29, #CPU_XREG_OFFSET(2)]
@@ -130,6 +147,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// Store the guest regs x18-x29, lr
 	save_callee_saved_regs x1
 
+	// Store the guest's sp_el0
+	save_sp_el0	x1, x2
+
 	get_host_ctxt	x2, x3
 
 	// Macro ptrauth_switch_to_guest format:
@@ -139,6 +159,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// when this feature is enabled for kernel code.
 	ptrauth_switch_to_host x1, x2, x3, x4, x5
 
+	// Restore the hosts's sp_el0
+	restore_sp_el0 x2, x3
+
 	// Now restore the host regs
 	restore_callee_saved_regs x2
 

arch/arm64/kvm/hyp/hyp-entry.S

@@ -198,7 +198,6 @@ SYM_CODE_END(__hyp_panic)
 .macro invalid_vector	label, target = __hyp_panic
 	.align	2
 SYM_CODE_START(\label)
-\label:
 	b \target
 SYM_CODE_END(\label)
 .endm

arch/arm64/kvm/hyp/sysreg-sr.c

@@ -15,8 +15,9 @@
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate,
- * which are handled as part of the el2 return state) on every switch.
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
+ * pstate, which are handled as part of the el2 return state) on every
+ * switch (sp_el0 is being dealt with in the assembly code).
  * tpidr_el0 and tpidrro_el0 only need to be switched when going
  * to host userspace or a different VCPU.  EL1 registers only need to be
  * switched when potentially going to run a different VCPU.  The latter two
@@ -26,12 +27,6 @@
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
-
-	/*
-	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
-	 * therefore be saved/restored on every entry/exit to/from the guest.
-	 */
-	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
 }
 
 static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
@@ -99,12 +94,6 @@ NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
 static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
-
-	/*
-	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
-	 * therefore be saved/restored on every entry/exit to/from the guest.
-	 */
-	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
 }
 
 static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)

arch/arm64/mm/hugetlbpage.c

@@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		ptep = (pte_t *)pudp;
 	} else if (sz == (CONT_PTE_SIZE)) {
 		pmdp = pmd_alloc(mm, pudp, addr);
+		if (!pmdp)
+			return NULL;
 
 		WARN_ON(addr & (sz - 1));
 		/*

arch/powerpc/kvm/powerpc.c

@@ -521,6 +521,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_PPC_GUEST_DEBUG_SSTEP:

arch/riscv/Kconfig

@@ -54,7 +54,7 @@ config RISCV
 	select GENERIC_ARCH_TOPOLOGY if SMP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MMIOWB
-	select ARCH_HAS_DEBUG_VIRTUAL
+	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select HAVE_EBPF_JIT if MMU
 	select EDAC_SUPPORT
 	select ARCH_HAS_GIGANTIC_PAGE
@@ -136,6 +136,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
 config SYS_SUPPORTS_HUGETLBFS
+	depends on MMU
 	def_bool y
 
 config STACKTRACE_SUPPORT

arch/riscv/Kconfig.socs

@@ -12,10 +12,11 @@ config SOC_SIFIVE
 
 config SOC_VIRT
 	bool "QEMU Virt Machine"
+	select POWER_RESET
 	select POWER_RESET_SYSCON
 	select POWER_RESET_SYSCON_POWEROFF
 	select GOLDFISH
-       select RTC_DRV_GOLDFISH
+	select RTC_DRV_GOLDFISH if RTC_CLASS
 	select SIFIVE_PLIC
 	help
 	  This enables support for QEMU Virt Machine.

arch/riscv/include/asm/csr.h

@@ -51,13 +51,10 @@
 #define CAUSE_IRQ_FLAG		(_AC(1, UL) << (__riscv_xlen - 1))
 
 /* Interrupt causes (minus the high bit) */
-#define IRQ_U_SOFT		0
 #define IRQ_S_SOFT		1
 #define IRQ_M_SOFT		3
-#define IRQ_U_TIMER		4
 #define IRQ_S_TIMER		5
 #define IRQ_M_TIMER		7
-#define IRQ_U_EXT		8
 #define IRQ_S_EXT		9
 #define IRQ_M_EXT		11
 

arch/riscv/include/asm/hwcap.h

@@ -8,6 +8,7 @@
 #ifndef _ASM_RISCV_HWCAP_H
 #define _ASM_RISCV_HWCAP_H
 
+#include <linux/bits.h>
 #include <uapi/asm/hwcap.h>
 
 #ifndef __ASSEMBLY__
@@ -22,6 +23,27 @@ enum {
 };
 
 extern unsigned long elf_hwcap;
+
+#define RISCV_ISA_EXT_a		('a' - 'a')
+#define RISCV_ISA_EXT_c		('c' - 'a')
+#define RISCV_ISA_EXT_d		('d' - 'a')
+#define RISCV_ISA_EXT_f		('f' - 'a')
+#define RISCV_ISA_EXT_h		('h' - 'a')
+#define RISCV_ISA_EXT_i		('i' - 'a')
+#define RISCV_ISA_EXT_m		('m' - 'a')
+#define RISCV_ISA_EXT_s		('s' - 'a')
+#define RISCV_ISA_EXT_u		('u' - 'a')
+
+#define RISCV_ISA_EXT_MAX	64
+
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
+
+#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext)	\
+	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
 #endif
 
 #endif /* _ASM_RISCV_HWCAP_H */

arch/riscv/include/asm/mmio.h

@@ -16,6 +16,8 @@
 
 #ifndef CONFIG_MMU
 #define pgprot_noncached(x)	(x)
+#define pgprot_writecombine(x)	(x)
+#define pgprot_device(x)	(x)
 #endif /* CONFIG_MMU */
 
 /* Generic IO read/write.  These perform native-endian accesses. */

arch/riscv/include/asm/mmiowb.h

@@ -9,6 +9,7 @@
  */
 #define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
 
+#include <linux/smp.h>
 #include <asm-generic/mmiowb.h>
 
 #endif	/* _ASM_RISCV_MMIOWB_H */

arch/riscv/include/asm/perf_event.h

@@ -12,19 +12,14 @@
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
 
+#ifdef CONFIG_RISCV_BASE_PMU
 #define RISCV_BASE_COUNTERS	2
 
 /*
  * The RISCV_MAX_COUNTERS parameter should be specified.
  */
 
-#ifdef CONFIG_RISCV_BASE_PMU
 #define RISCV_MAX_COUNTERS	2
-#endif
-
-#ifndef RISCV_MAX_COUNTERS
-#error "Please provide a valid RISCV_MAX_COUNTERS for the PMU."
-#endif
 
 /*
  * These are the indexes of bits in counteren register *minus* 1,
@@ -82,6 +77,7 @@ struct riscv_pmu {
 	int		irq;
 };
 
+#endif
 #ifdef CONFIG_PERF_EVENTS
 #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
 #endif

arch/riscv/include/asm/pgtable.h

@@ -470,12 +470,15 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 
 #else /* CONFIG_MMU */
 
+#define PAGE_SHARED		__pgprot(0)
 #define PAGE_KERNEL		__pgprot(0)
 #define swapper_pg_dir		NULL
 #define VMALLOC_START		0
 
 #define TASK_SIZE 0xffffffffUL
 
+static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {}
+
 #endif /* !CONFIG_MMU */
 
 #define kern_addr_valid(addr)   (1) /* FIXME */

arch/riscv/include/asm/set_memory.h

@@ -22,14 +22,6 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; }
 static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
-#ifdef CONFIG_STRICT_KERNEL_RWX
-void set_kernel_text_ro(void);
-void set_kernel_text_rw(void);
-#else
-static inline void set_kernel_text_ro(void) { }
-static inline void set_kernel_text_rw(void) { }
-#endif
-
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
 

arch/riscv/kernel/Makefile

@@ -43,7 +43,7 @@ obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
-obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o
+obj-$(CONFIG_RISCV_BASE_PMU)	+= perf_event.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
 obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
 obj-$(CONFIG_RISCV_SBI)		+= sbi.o

arch/riscv/kernel/cpu_ops.c

@@ -15,8 +15,8 @@
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-void *__cpu_up_stack_pointer[NR_CPUS];
-void *__cpu_up_task_pointer[NR_CPUS];
+void *__cpu_up_stack_pointer[NR_CPUS] __section(.data);
+void *__cpu_up_task_pointer[NR_CPUS] __section(.data);
 
 extern const struct cpu_operations cpu_ops_sbi;
 extern const struct cpu_operations cpu_ops_spinwait;

arch/riscv/kernel/cpufeature.c

@@ -6,6 +6,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/bitmap.h>
 #include <linux/of.h>
 #include <asm/processor.h>
 #include <asm/hwcap.h>
@@ -13,15 +14,57 @@
 #include <asm/switch_to.h>
 
 unsigned long elf_hwcap __read_mostly;
+
+/* Host ISA bitmap */
+static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
+
 #ifdef CONFIG_FPU
 bool has_fpu __read_mostly;
 #endif
 
+/**
+ * riscv_isa_extension_base() - Get base extension word
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * Return: base extension word as unsigned long value
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap)
+{
+	if (!isa_bitmap)
+		return riscv_isa[0];
+	return isa_bitmap[0];
+}
+EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
+
+/**
+ * __riscv_isa_extension_available() - Check whether given extension
+ * is available or not
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * @bit: bit position of the desired extension
+ * Return: true or false
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+{
+	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
+
+	if (bit >= RISCV_ISA_EXT_MAX)
+		return false;
+
+	return test_bit(bit, bmap) ? true : false;
+}
+EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
+
 void riscv_fill_hwcap(void)
 {
 	struct device_node *node;
 	const char *isa;
-	size_t i;
+	char print_str[BITS_PER_LONG + 1];
+	size_t i, j, isa_len;
 	static unsigned long isa2hwcap[256] = {0};
 
 	isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
@@ -33,8 +76,11 @@ void riscv_fill_hwcap(void)
 
 	elf_hwcap = 0;
 
+	bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
+
 	for_each_of_cpu_node(node) {
 		unsigned long this_hwcap = 0;
+		unsigned long this_isa = 0;
 
 		if (riscv_of_processor_hartid(node) < 0)
 			continue;
@@ -44,8 +90,24 @@ void riscv_fill_hwcap(void)
 			continue;
 		}
 
-		for (i = 0; i < strlen(isa); ++i)
+		i = 0;
+		isa_len = strlen(isa);
+#if IS_ENABLED(CONFIG_32BIT)
+		if (!strncmp(isa, "rv32", 4))
+			i += 4;
+#elif IS_ENABLED(CONFIG_64BIT)
+		if (!strncmp(isa, "rv64", 4))
+			i += 4;
+#endif
+		for (; i < isa_len; ++i) {
 			this_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+			/*
+			 * TODO: X, Y and Z extension parsing for Host ISA
+			 * bitmap will be added in-future.
+			 */
+			if ('a' <= isa[i] && isa[i] < 'x')
+				this_isa |= (1UL << (isa[i] - 'a'));
+		}
 
 		/*
 		 * All "okay" hart should have same isa. Set HWCAP based on
@@ -56,6 +118,11 @@ void riscv_fill_hwcap(void)
 			elf_hwcap &= this_hwcap;
 		else
 			elf_hwcap = this_hwcap;
+
+		if (riscv_isa[0])
+			riscv_isa[0] &= this_isa;
+		else
+			riscv_isa[0] = this_isa;
 	}
 
 	/* We don't support systems with F but without D, so mask those out
@@ -65,7 +132,17 @@ void riscv_fill_hwcap(void)
 		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
 	}
 
-	pr_info("elf_hwcap is 0x%lx\n", elf_hwcap);
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+		if (riscv_isa[0] & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: ISA extensions %s\n", print_str);
+
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+		if (elf_hwcap & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: ELF capabilities %s\n", print_str);
 
 #ifdef CONFIG_FPU
 	if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D))

arch/riscv/kernel/perf_event.c

@@ -147,7 +147,7 @@ static int riscv_map_hw_event(u64 config)
 	return riscv_pmu->hw_events[config];
 }
 
-int riscv_map_cache_decode(u64 config, unsigned int *type,
+static int riscv_map_cache_decode(u64 config, unsigned int *type,
 			   unsigned int *op, unsigned int *result)
 {
 	return -ENOENT;
@@ -342,7 +342,7 @@ static void riscv_pmu_del(struct perf_event *event, int flags)
 
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
-irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
+static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
 {
 	return IRQ_NONE;
 }
@@ -361,7 +361,7 @@ static int reserve_pmc_hardware(void)
 	return err;
 }
 
-void release_pmc_hardware(void)
+static void release_pmc_hardware(void)
 {
 	mutex_lock(&pmc_reserve_mutex);
 	if (riscv_pmu->irq >= 0)
@@ -464,7 +464,7 @@ static const struct of_device_id riscv_pmu_of_ids[] = {
 	{ /* sentinel value */ }
 };
 
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
 {
 	struct device_node *node = of_find_node_by_type(NULL, "pmu");
 	const struct of_device_id *of_id;

arch/riscv/kernel/smp.c

@@ -10,6 +10,7 @@
 
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/module.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
@@ -63,6 +64,7 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out)
 	for_each_cpu(cpu, in)
 		cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
 }
+EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask);
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {

arch/riscv/kernel/stacktrace.c

@@ -65,7 +65,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 
 #else /* !CONFIG_FRAME_POINTER */
 
-static void notrace walk_stackframe(struct task_struct *task,
+void notrace walk_stackframe(struct task_struct *task,
 	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
 {
 	unsigned long sp, pc;

arch/riscv/kernel/vdso/Makefile

@@ -12,7 +12,7 @@ vdso-syms += getcpu
 vdso-syms += flush_icache
 
 # Files to link into the vdso
-obj-vdso = $(patsubst %, %.o, $(vdso-syms))
+obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 # Build rules
 targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o

arch/riscv/kernel/vdso/note.S

@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/elfnote.h>
+#include <linux/version.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END

arch/riscv/mm/init.c

@@ -150,7 +150,8 @@ void __init setup_bootmem(void)
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
 	set_max_mapnr(PFN_DOWN(mem_size));
-	max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_low_pfn = max_pfn;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
@@ -501,22 +502,6 @@ static inline void setup_vm_final(void)
 #endif /* CONFIG_MMU */
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
-void set_kernel_text_rw(void)
-{
-	unsigned long text_start = (unsigned long)_text;
-	unsigned long text_end = (unsigned long)_etext;
-
-	set_memory_rw(text_start, (text_end - text_start) >> PAGE_SHIFT);
-}
-
-void set_kernel_text_ro(void)
-{
-	unsigned long text_start = (unsigned long)_text;
-	unsigned long text_end = (unsigned long)_etext;
-
-	set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT);
-}
-
 void mark_rodata_ro(void)
 {
 	unsigned long text_start = (unsigned long)_text;

arch/s390/kvm/kvm-s390.c

@@ -545,6 +545,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_AIS:
 	case KVM_CAP_S390_AIS_MIGRATION:
 	case KVM_CAP_S390_VCPU_RESETS:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_S390_HPAGE_1M:

arch/s390/kvm/priv.c

@@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
 	 * available for the guest are AQIC and TAPQ with the t bit set
 	 * since we do not set IC.3 (FIII) we currently will only intercept
 	 * the AQIC function code.
+	 * Note: running nested under z/VM can result in intercepts for other
+	 * function codes, e.g. PQAP(QCI). We do not support this and bail out.
 	 */
 	reg0 = vcpu->run->s.regs.gprs[0];
 	fc = (reg0 >> 24) & 0xff;
-	if (WARN_ON_ONCE(fc != 0x03))
+	if (fc != 0x03)
 		return -EOPNOTSUPP;
 
 	/* PQAP instruction is allowed for guest kernel only */

arch/x86/Kconfig

@@ -68,6 +68,7 @@ config X86
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL

arch/x86/entry/calling.h

@@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with
 #define SIZEOF_PTREGS	21*8
 
 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
-	/*
-	 * Push registers and sanitize registers of values that a
-	 * speculation attack might otherwise want to exploit. The
-	 * lower registers are likely clobbered well before they
-	 * could be put to use in a speculative execution gadget.
-	 * Interleave XOR with PUSH for better uop scheduling:
-	 */
 	.if \save_ret
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
@@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq   %rsi		/* pt_regs->si */
 	.endif
 	pushq	\rdx		/* pt_regs->dx */
-	xorl	%edx, %edx	/* nospec   dx */
 	pushq   %rcx		/* pt_regs->cx */
-	xorl	%ecx, %ecx	/* nospec   cx */
 	pushq   \rax		/* pt_regs->ax */
 	pushq   %r8		/* pt_regs->r8 */
-	xorl	%r8d, %r8d	/* nospec   r8 */
 	pushq   %r9		/* pt_regs->r9 */
-	xorl	%r9d, %r9d	/* nospec   r9 */
 	pushq   %r10		/* pt_regs->r10 */
-	xorl	%r10d, %r10d	/* nospec   r10 */
 	pushq   %r11		/* pt_regs->r11 */
-	xorl	%r11d, %r11d	/* nospec   r11*/
 	pushq	%rbx		/* pt_regs->rbx */
-	xorl    %ebx, %ebx	/* nospec   rbx*/
 	pushq	%rbp		/* pt_regs->rbp */
-	xorl    %ebp, %ebp	/* nospec   rbp*/
 	pushq	%r12		/* pt_regs->r12 */
-	xorl	%r12d, %r12d	/* nospec   r12*/
 	pushq	%r13		/* pt_regs->r13 */
-	xorl	%r13d, %r13d	/* nospec   r13*/
 	pushq	%r14		/* pt_regs->r14 */
-	xorl	%r14d, %r14d	/* nospec   r14*/
 	pushq	%r15		/* pt_regs->r15 */
-	xorl	%r15d, %r15d	/* nospec   r15*/
 	UNWIND_HINT_REGS
+
 	.if \save_ret
 	pushq	%rsi		/* return address on top of stack */
 	.endif
+
+	/*
+	 * Sanitize registers of values that a speculation attack might
+	 * otherwise want to exploit. The lower registers are likely clobbered
+	 * well before they could be put to use in a speculative execution
+	 * gadget.
+	 */
+	xorl	%edx,  %edx	/* nospec dx  */
+	xorl	%ecx,  %ecx	/* nospec cx  */
+	xorl	%r8d,  %r8d	/* nospec r8  */
+	xorl	%r9d,  %r9d	/* nospec r9  */
+	xorl	%r10d, %r10d	/* nospec r10 */
+	xorl	%r11d, %r11d	/* nospec r11 */
+	xorl	%ebx,  %ebx	/* nospec rbx */
+	xorl	%ebp,  %ebp	/* nospec rbp */
+	xorl	%r12d, %r12d	/* nospec r12 */
+	xorl	%r13d, %r13d	/* nospec r13 */
+	xorl	%r14d, %r14d	/* nospec r14 */
+	xorl	%r15d, %r15d	/* nospec r15 */
+
 .endm
 
 .macro POP_REGS pop_rdi=1 skip_r11rcx=0

arch/x86/entry/entry_64.S

@@ -249,7 +249,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 */
 syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
-	UNWIND_HINT_EMPTY
 	POP_REGS pop_rdi=0 skip_r11rcx=1
 
 	/*
@@ -258,6 +257,7 @@ syscall_return_via_sysret:
 	 */
 	movq	%rsp, %rdi
 	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+	UNWIND_HINT_EMPTY
 
 	pushq	RSP-RDI(%rdi)	/* RSP */
 	pushq	(%rdi)		/* RDI */
@@ -279,8 +279,7 @@ SYM_CODE_END(entry_SYSCALL_64)
  * %rdi: prev task
  * %rsi: next task
  */
-SYM_CODE_START(__switch_to_asm)
-	UNWIND_HINT_FUNC
+SYM_FUNC_START(__switch_to_asm)
 	/*
 	 * Save callee-saved registers
 	 * This must match the order in inactive_task_frame
@@ -321,7 +320,7 @@ SYM_CODE_START(__switch_to_asm)
 	popq	%rbp
 
 	jmp	__switch_to
-SYM_CODE_END(__switch_to_asm)
+SYM_FUNC_END(__switch_to_asm)
 
 /*
  * A newly forked process directly context switches into this address.
@@ -512,7 +511,7 @@ SYM_CODE_END(spurious_entries_start)
  * +----------------------------------------------------+
  */
 SYM_CODE_START(interrupt_entry)
-	UNWIND_HINT_FUNC
+	UNWIND_HINT_IRET_REGS offset=16
 	ASM_CLAC
 	cld
 
@@ -544,9 +543,9 @@ SYM_CODE_START(interrupt_entry)
 	pushq	5*8(%rdi)		/* regs->eflags */
 	pushq	4*8(%rdi)		/* regs->cs */
 	pushq	3*8(%rdi)		/* regs->ip */
+	UNWIND_HINT_IRET_REGS
 	pushq	2*8(%rdi)		/* regs->orig_ax */
 	pushq	8(%rdi)			/* return address */
-	UNWIND_HINT_FUNC
 
 	movq	(%rdi), %rdi
 	jmp	2f
@@ -637,6 +636,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	 */
 	movq	%rsp, %rdi
 	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+	UNWIND_HINT_EMPTY
 
 	/* Copy the IRET frame to the trampoline stack. */
 	pushq	6*8(%rdi)	/* SS */
@@ -1739,7 +1739,7 @@ SYM_CODE_START(rewind_stack_do_exit)
 
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
 	leaq	-PTREGS_SIZE(%rax), %rsp
-	UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE
+	UNWIND_HINT_REGS
 
 	call	do_exit
 SYM_CODE_END(rewind_stack_do_exit)

arch/x86/include/asm/ftrace.h

@@ -56,16 +56,23 @@ struct dyn_arch_ftrace {
 
 #ifndef __ASSEMBLY__
 
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+extern void set_ftrace_ops_ro(void);
+#else
+static inline void set_ftrace_ops_ro(void) { }
+#endif
+
 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
 static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
 {
 	/*
 	 * Compare the symbol name with the system call name. Skip the
-	 * "__x64_sys", "__ia32_sys" or simple "sys" prefix.
+	 * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix.
 	 */
 	return !strcmp(sym + 3, name + 3) ||
 		(!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) ||
-		(!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3));
+		(!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) ||
+		(!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3));
 }
 
 #ifndef COMPILE_OFFSETS

arch/x86/include/asm/kvm_host.h

@@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
 {
 	/* We can only post Fixed and LowPrio IRQs */
-	return (irq->delivery_mode == dest_Fixed ||
-		irq->delivery_mode == dest_LowestPrio);
+	return (irq->delivery_mode == APIC_DM_FIXED ||
+		irq->delivery_mode == APIC_DM_LOWEST);
 }
 
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)

arch/x86/include/asm/unwind.h

@@ -19,7 +19,7 @@ struct unwind_state {
 #if defined(CONFIG_UNWINDER_ORC)
 	bool signal, full_regs;
 	unsigned long sp, bp, ip;
-	struct pt_regs *regs;
+	struct pt_regs *regs, *prev_regs;
 #elif defined(CONFIG_UNWINDER_FRAME_POINTER)
 	bool got_irq;
 	unsigned long *bp, *orig_sp, ip;

arch/x86/kernel/apic/apic.c

@@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 		 * According to Intel, MFENCE can do the serialization here.
 		 */
 		asm volatile("mfence" : : : "memory");
-
-		printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
 		return;
 	}
 
@@ -546,7 +544,7 @@ static struct clock_event_device lapic_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
-static u32 hsx_deadline_rev(void)
+static __init u32 hsx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x3a; /* EP */
@@ -556,7 +554,7 @@ static u32 hsx_deadline_rev(void)
 	return ~0U;
 }
 
-static u32 bdx_deadline_rev(void)
+static __init u32 bdx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x00000011;
@@ -568,7 +566,7 @@ static u32 bdx_deadline_rev(void)
 	return ~0U;
 }
 
-static u32 skx_deadline_rev(void)
+static __init u32 skx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x03: return 0x01000136;
@@ -581,7 +579,7 @@ static u32 skx_deadline_rev(void)
 	return ~0U;
 }
 
-static const struct x86_cpu_id deadline_match[] = {
+static const struct x86_cpu_id deadline_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X,		&hsx_deadline_rev),
 	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X,	0x0b000020),
 	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D,	&bdx_deadline_rev),
@@ -603,18 +601,19 @@ static const struct x86_cpu_id deadline_match[] = {
 	{},
 };
 
-static void apic_check_deadline_errata(void)
+static __init bool apic_validate_deadline_timer(void)
 {
 	const struct x86_cpu_id *m;
 	u32 rev;
 
-	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) ||
-	    boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return;
+	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return false;
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return true;
 
 	m = x86_match_cpu(deadline_match);
 	if (!m)
-		return;
+		return true;
 
 	/*
 	 * Function pointers will have the MSB set due to address layout,
@@ -626,11 +625,12 @@ static void apic_check_deadline_errata(void)
 		rev = (u32)m->driver_data;
 
 	if (boot_cpu_data.microcode >= rev)
-		return;
+		return true;
 
 	setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 	pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; "
 	       "please update microcode to version: 0x%x (or later)\n", rev);
+	return false;
 }
 
 /*
@@ -2092,7 +2092,8 @@ void __init init_apic_mappings(void)
 {
 	unsigned int new_apicid;
 
-	apic_check_deadline_errata();
+	if (apic_validate_deadline_timer())
+		pr_debug("TSC deadline timer available\n");
 
 	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();

arch/x86/kernel/dumpstack_64.c

@@ -183,6 +183,7 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	 */
 	if (visit_mask) {
 		if (*visit_mask & (1UL << info->type)) {
+			if (task == current)
 				printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
 			goto unknown;
 		}

arch/x86/kernel/ftrace.c

@@ -407,6 +407,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	set_vm_flush_reset_perms(trampoline);
 
+	if (likely(system_state != SYSTEM_BOOTING))
 		set_memory_ro((unsigned long)trampoline, npages);
 	set_memory_x((unsigned long)trampoline, npages);
 	return (unsigned long)trampoline;
@@ -415,6 +416,32 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	return 0;
 }
 
+void set_ftrace_ops_ro(void)
+{
+	struct ftrace_ops *ops;
+	unsigned long start_offset;
+	unsigned long end_offset;
+	unsigned long npages;
+	unsigned long size;
+
+	do_for_each_ftrace_op(ops, ftrace_ops_list) {
+		if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+			continue;
+
+		if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+			start_offset = (unsigned long)ftrace_regs_caller;
+			end_offset = (unsigned long)ftrace_regs_caller_end;
+		} else {
+			start_offset = (unsigned long)ftrace_caller;
+			end_offset = (unsigned long)ftrace_epilogue;
+		}
+		size = end_offset - start_offset;
+		size = size + RET_SIZE + sizeof(void *);
+		npages = DIV_ROUND_UP(size, PAGE_SIZE);
+		set_memory_ro((unsigned long)ops->trampoline, npages);
+	} while_for_each_ftrace_op(ops);
+}
+
 static unsigned long calc_trampoline_call_offset(bool save_regs)
 {
 	unsigned long start_offset;

arch/x86/kernel/unwind_frame.c

@@ -344,6 +344,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (IS_ENABLED(CONFIG_X86_32))
 		goto the_end;
 
+	if (state->task != current)
+		goto the_end;
+
 	if (state->regs) {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",

arch/x86/kernel/unwind_orc.c

@@ -8,19 +8,21 @@
 #include <asm/orc_lookup.h>
 
 #define orc_warn(fmt, ...) \
-	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
+	printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__)
+
+#define orc_warn_current(args...)					\
+({									\
+	if (state->task == current)					\
+		orc_warn(args);						\
+})
 
 extern int __start_orc_unwind_ip[];
 extern int __stop_orc_unwind_ip[];
 extern struct orc_entry __start_orc_unwind[];
 extern struct orc_entry __stop_orc_unwind[];
 
-static DEFINE_MUTEX(sort_mutex);
-int *cur_orc_ip_table = __start_orc_unwind_ip;
-struct orc_entry *cur_orc_table = __start_orc_unwind;
-
-unsigned int lookup_num_blocks;
-bool orc_init;
+static bool orc_init __ro_after_init;
+static unsigned int lookup_num_blocks __ro_after_init;
 
 static inline unsigned long orc_ip(const int *ip)
 {
@@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip)
 {
 	static struct orc_entry *orc;
 
-	if (!orc_init)
-		return NULL;
-
 	if (ip == 0)
 		return &null_orc_entry;
 
@@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip)
 
 #ifdef CONFIG_MODULES
 
+static DEFINE_MUTEX(sort_mutex);
+static int *cur_orc_ip_table = __start_orc_unwind_ip;
+static struct orc_entry *cur_orc_table = __start_orc_unwind;
+
 static void orc_sort_swap(void *_a, void *_b, int size)
 {
 	struct orc_entry *orc_a, *orc_b;
@@ -381,9 +384,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 	return true;
 }
 
+/*
+ * If state->regs is non-NULL, and points to a full pt_regs, just get the reg
+ * value from state->regs.
+ *
+ * Otherwise, if state->regs just points to IRET regs, and the previous frame
+ * had full regs, it's safe to get the value from the previous regs.  This can
+ * happen when early/late IRQ entry code gets interrupted by an NMI.
+ */
+static bool get_reg(struct unwind_state *state, unsigned int reg_off,
+		    unsigned long *val)
+{
+	unsigned int reg = reg_off/8;
+
+	if (!state->regs)
+		return false;
+
+	if (state->full_regs) {
+		*val = ((unsigned long *)state->regs)[reg];
+		return true;
+	}
+
+	if (state->prev_regs) {
+		*val = ((unsigned long *)state->prev_regs)[reg];
+		return true;
+	}
+
+	return false;
+}
+
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -445,43 +477,39 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_REG_R10:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R10 at ip %pB\n",
+		if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) {
+			orc_warn_current("missing R10 value at %pB\n",
 					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r10;
 		break;
 
 	case ORC_REG_R13:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R13 at ip %pB\n",
+		if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) {
+			orc_warn_current("missing R13 value at %pB\n",
 					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r13;
 		break;
 
 	case ORC_REG_DI:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DI at ip %pB\n",
+		if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) {
+			orc_warn_current("missing RDI value at %pB\n",
 					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->di;
 		break;
 
 	case ORC_REG_DX:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DX at ip %pB\n",
+		if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) {
+			orc_warn_current("missing DX value at %pB\n",
 					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->dx;
 		break;
 
 	default:
-		orc_warn("unknown SP base reg %d for ip %pB\n",
+		orc_warn("unknown SP base reg %d at %pB\n",
 			 orc->sp_reg, (void *)state->ip);
 		goto err;
 	}
@@ -504,44 +532,48 @@ bool unwind_next_frame(struct unwind_state *state)
 
 		state->sp = sp;
 		state->regs = NULL;
+		state->prev_regs = NULL;
 		state->signal = false;
 		break;
 
 	case ORC_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
-			orc_warn("can't dereference registers at %p for ip %pB\n",
-				 (void *)sp, (void *)orig_ip);
+			orc_warn_current("can't access registers at %pB\n",
+					 (void *)orig_ip);
 			goto err;
 		}
 
 		state->regs = (struct pt_regs *)sp;
+		state->prev_regs = NULL;
 		state->full_regs = true;
 		state->signal = true;
 		break;
 
 	case ORC_TYPE_REGS_IRET:
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
-			orc_warn("can't dereference iret registers at %p for ip %pB\n",
-				 (void *)sp, (void *)orig_ip);
+			orc_warn_current("can't access iret registers at %pB\n",
+					 (void *)orig_ip);
 			goto err;
 		}
 
+		if (state->full_regs)
+			state->prev_regs = state->regs;
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
 		state->full_regs = false;
 		state->signal = true;
 		break;
 
 	default:
-		orc_warn("unknown .orc_unwind entry type %d for ip %pB\n",
+		orc_warn("unknown .orc_unwind entry type %d at %pB\n",
 			 orc->type, (void *)orig_ip);
-		break;
+		goto err;
 	}
 
 	/* Find BP: */
 	switch (orc->bp_reg) {
 	case ORC_REG_UNDEFINED:
-		if (state->regs && state->full_regs)
-			state->bp = state->regs->bp;
+		if (get_reg(state, offsetof(struct pt_regs, bp), &tmp))
+			state->bp = tmp;
 		break;
 
 	case ORC_REG_PREV_SP:
@@ -564,7 +596,7 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (state->stack_info.type == prev_type &&
 	    on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) &&
 	    state->sp <= prev_sp) {
-		orc_warn("stack going in the wrong direction? ip=%pB\n",
+		orc_warn_current("stack going in the wrong direction? at %pB\n",
 				 (void *)orig_ip);
 		goto err;
 	}
@@ -585,6 +617,9 @@ EXPORT_SYMBOL_GPL(unwind_next_frame);
 void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		    struct pt_regs *regs, unsigned long *first_frame)
 {
+	if (!orc_init)
+		goto done;
+
 	memset(state, 0, sizeof(*state));
 	state->task = task;
 
@@ -651,7 +686,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	/* Otherwise, skip ahead to the user-specified starting frame: */
 	while (!unwind_done(state) &&
 	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
-			state->sp <= (unsigned long)first_frame))
+			state->sp < (unsigned long)first_frame))
 		unwind_next_frame(state);
 
 	return;

arch/x86/kvm/ioapic.c

@@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 	}
 
 	/*
-	 * AMD SVM AVIC accelerate EOI write and do not trap,
-	 * in-kernel IOAPIC will not be able to receive the EOI.
-	 * In this case, we do lazy update of the pending EOI when
-	 * trying to set IOAPIC irq.
+	 * AMD SVM AVIC accelerate EOI write iff the interrupt is edge
+	 * triggered, in which case the in-kernel IOAPIC will not be able
+	 * to receive the EOI.  In this case, we do a lazy update of the
+	 * pending EOI when trying to set IOAPIC irq.
 	 */
-	if (kvm_apicv_activated(ioapic->kvm))
+	if (edge && kvm_apicv_activated(ioapic->kvm))
 		ioapic_lazy_update_eoi(ioapic, irq);
 
 	/*

arch/x86/kvm/svm/sev.c

@@ -345,7 +345,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 		return NULL;
 
 	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
+	npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		goto err;

arch/x86/kvm/svm/svm.c

@@ -1752,6 +1752,8 @@ static int db_interception(struct vcpu_svm *svm)
 	if (svm->vcpu.guest_debug &
 	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6;
+		kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7;
 		kvm_run->debug.arch.pc =
 			svm->vmcb->save.cs.base + svm->vmcb->save.rip;
 		kvm_run->debug.arch.exception = DB_VECTOR;

arch/x86/kvm/vmx/nested.c

@@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	 */
 		break;
 	default:
-		BUG_ON(1);
+		BUG();
 		break;
 	}
 

arch/x86/kvm/vmx/vmenter.S

@@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit)
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 
+	/* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */
+	or $1, %_ASM_AX
+
 	pop %_ASM_AX
 .Lvmexit_skip_rsb:
 #endif

arch/x86/kvm/x86.c

@@ -926,19 +926,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 	__reserved_bits;				\
 })
 
-static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c)
-{
-	u64 reserved_bits = __cr4_reserved_bits(cpu_has, c);
-
-	if (kvm_cpu_cap_has(X86_FEATURE_LA57))
-		reserved_bits &= ~X86_CR4_LA57;
-
-	if (kvm_cpu_cap_has(X86_FEATURE_UMIP))
-		reserved_bits &= ~X86_CR4_UMIP;
-
-	return reserved_bits;
-}
-
 static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & cr4_reserved_bits)
@@ -3385,6 +3372,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_GET_MSR_FEATURES:
 	case KVM_CAP_MSR_PLATFORM_INFO:
 	case KVM_CAP_EXCEPTION_PAYLOAD:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -9675,7 +9663,9 @@ int kvm_arch_hardware_setup(void *opaque)
 	if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
 		supported_xss = 0;
 
-	cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data);
+#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f)
+	cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_);
+#undef __kvm_cpu_cap_has
 
 	if (kvm_has_tsc_control) {
 		/*
@@ -9707,7 +9697,8 @@ int kvm_arch_check_processor_compat(void *opaque)
 
 	WARN_ON(!irqs_disabled());
 
-	if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits)
+	if (__cr4_reserved_bits(cpu_has, c) !=
+	    __cr4_reserved_bits(cpu_has, &boot_cpu_data))
 		return -EIO;
 
 	return ops->check_processor_compatibility();

arch/x86/mm/init_64.c

@@ -54,6 +54,7 @@
 #include <asm/init.h>
 #include <asm/uv/uv.h>
 #include <asm/setup.h>
+#include <asm/ftrace.h>
 
 #include "mm_internal.h"
 
@@ -1291,6 +1292,8 @@ void mark_rodata_ro(void)
 	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
 	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
 
+	set_ftrace_ops_ro();
+
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
 	set_memory_rw(start, (end-start) >> PAGE_SHIFT);

arch/x86/mm/pat/set_memory.c

@@ -43,7 +43,8 @@ struct cpa_data {
 	unsigned long	pfn;
 	unsigned int	flags;
 	unsigned int	force_split		: 1,
-			force_static_prot	: 1;
+			force_static_prot	: 1,
+			force_flush_all		: 1;
 	struct page	**pages;
 };
 
@@ -355,10 +356,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		return;
 	}
 
-	if (cpa->numpages <= tlb_single_page_flush_ceiling)
-		on_each_cpu(__cpa_flush_tlb, cpa, 1);
-	else
+	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
 		flush_tlb_all();
+	else
+		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
 		return;
@@ -1598,6 +1599,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
+
 		ret = __change_page_attr_set_clr(&alias_cpa, 0);
 		if (ret)
 			return ret;
@@ -1618,6 +1621,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
 		/*
 		 * The high mapping range is imprecise, so ignore the
 		 * return value.

block/bfq-iosched.c

@@ -123,6 +123,7 @@
 #include <linux/ioprio.h>
 #include <linux/sbitmap.h>
 #include <linux/delay.h>
+#include <linux/backing-dev.h>
 
 #include "blk.h"
 #include "blk-mq.h"
@@ -4976,8 +4977,9 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
 	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
 	switch (ioprio_class) {
 	default:
-		dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
-			"bfq: bad prio class %d\n", ioprio_class);
+		pr_err("bdi %s: bfq: bad prio class %d\n",
+				bdi_dev_name(bfqq->bfqd->queue->backing_dev_info),
+				ioprio_class);
 		/* fall through */
 	case IOPRIO_CLASS_NONE:
 		/*

block/blk-cgroup.c

@@ -496,7 +496,7 @@ const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
 	/* some drivers (floppy) instantiate a queue w/o disk registered */
 	if (blkg->q->backing_dev_info->dev)
-		return dev_name(blkg->q->backing_dev_info->dev);
+		return bdi_dev_name(blkg->q->backing_dev_info);
 	return NULL;
 }
 

block/blk-iocost.c

@@ -466,7 +466,7 @@ struct ioc_gq {
 	 */
 	atomic64_t			vtime;
 	atomic64_t			done_vtime;
-	atomic64_t			abs_vdebt;
+	u64				abs_vdebt;
 	u64				last_vtime;
 
 	/*
@@ -1142,7 +1142,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now)
 	struct iocg_wake_ctx ctx = { .iocg = iocg };
 	u64 margin_ns = (u64)(ioc->period_us *
 			      WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC;
-	u64 abs_vdebt, vdebt, vshortage, expires, oexpires;
+	u64 vdebt, vshortage, expires, oexpires;
 	s64 vbudget;
 	u32 hw_inuse;
 
@@ -1152,18 +1152,15 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now)
 	vbudget = now->vnow - atomic64_read(&iocg->vtime);
 
 	/* pay off debt */
-	abs_vdebt = atomic64_read(&iocg->abs_vdebt);
-	vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse);
+	vdebt = abs_cost_to_cost(iocg->abs_vdebt, hw_inuse);
 	if (vdebt && vbudget > 0) {
 		u64 delta = min_t(u64, vbudget, vdebt);
 		u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse),
-				    abs_vdebt);
+				    iocg->abs_vdebt);
 
 		atomic64_add(delta, &iocg->vtime);
 		atomic64_add(delta, &iocg->done_vtime);
-		atomic64_sub(abs_delta, &iocg->abs_vdebt);
-		if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0))
-			atomic64_set(&iocg->abs_vdebt, 0);
+		iocg->abs_vdebt -= abs_delta;
 	}
 
 	/*
@@ -1219,12 +1216,18 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost)
 	u64 expires, oexpires;
 	u32 hw_inuse;
 
+	lockdep_assert_held(&iocg->waitq.lock);
+
 	/* debt-adjust vtime */
 	current_hweight(iocg, NULL, &hw_inuse);
-	vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse);
+	vtime += abs_cost_to_cost(iocg->abs_vdebt, hw_inuse);
 
-	/* clear or maintain depending on the overage */
-	if (time_before_eq64(vtime, now->vnow)) {
+	/*
+	 * Clear or maintain depending on the overage. Non-zero vdebt is what
+	 * guarantees that @iocg is online and future iocg_kick_delay() will
+	 * clear use_delay. Don't leave it on when there's no vdebt.
+	 */
+	if (!iocg->abs_vdebt || time_before_eq64(vtime, now->vnow)) {
 		blkcg_clear_delay(blkg);
 		return false;
 	}
@@ -1258,9 +1261,12 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer)
 {
 	struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer);
 	struct ioc_now now;
+	unsigned long flags;
 
+	spin_lock_irqsave(&iocg->waitq.lock, flags);
 	ioc_now(iocg->ioc, &now);
 	iocg_kick_delay(iocg, &now, 0);
+	spin_unlock_irqrestore(&iocg->waitq.lock, flags);
 
 	return HRTIMER_NORESTART;
 }
@@ -1368,14 +1374,13 @@ static void ioc_timer_fn(struct timer_list *timer)
 	 * should have woken up in the last period and expire idle iocgs.
 	 */
 	list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) {
-		if (!waitqueue_active(&iocg->waitq) &&
-		    !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg))
+		if (!waitqueue_active(&iocg->waitq) && iocg->abs_vdebt &&
+		    !iocg_is_idle(iocg))
 			continue;
 
 		spin_lock(&iocg->waitq.lock);
 
-		if (waitqueue_active(&iocg->waitq) ||
-		    atomic64_read(&iocg->abs_vdebt)) {
+		if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) {
 			/* might be oversleeping vtime / hweight changes, kick */
 			iocg_kick_waitq(iocg, &now);
 			iocg_kick_delay(iocg, &now, 0);
@@ -1718,28 +1723,49 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	 * tests are racy but the races aren't systemic - we only miss once
 	 * in a while which is fine.
 	 */
-	if (!waitqueue_active(&iocg->waitq) &&
-	    !atomic64_read(&iocg->abs_vdebt) &&
+	if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt &&
 	    time_before_eq64(vtime + cost, now.vnow)) {
 		iocg_commit_bio(iocg, bio, cost);
 		return;
 	}
 
 	/*
-	 * We're over budget.  If @bio has to be issued regardless,
-	 * remember the abs_cost instead of advancing vtime.
-	 * iocg_kick_waitq() will pay off the debt before waking more IOs.
+	 * We activated above but w/o any synchronization. Deactivation is
+	 * synchronized with waitq.lock and we won't get deactivated as long
+	 * as we're waiting or has debt, so we're good if we're activated
+	 * here. In the unlikely case that we aren't, just issue the IO.
+	 */
+	spin_lock_irq(&iocg->waitq.lock);
+
+	if (unlikely(list_empty(&iocg->active_list))) {
+		spin_unlock_irq(&iocg->waitq.lock);
+		iocg_commit_bio(iocg, bio, cost);
+		return;
+	}
+
+	/*
+	 * We're over budget. If @bio has to be issued regardless, remember
+	 * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay
+	 * off the debt before waking more IOs.
+	 *
 	 * This way, the debt is continuously paid off each period with the
-	 * actual budget available to the cgroup.  If we just wound vtime,
-	 * we would incorrectly use the current hw_inuse for the entire
-	 * amount which, for example, can lead to the cgroup staying
-	 * blocked for a long time even with substantially raised hw_inuse.
+	 * actual budget available to the cgroup. If we just wound vtime, we
+	 * would incorrectly use the current hw_inuse for the entire amount
+	 * which, for example, can lead to the cgroup staying blocked for a
+	 * long time even with substantially raised hw_inuse.
+	 *
+	 * An iocg with vdebt should stay online so that the timer can keep
+	 * deducting its vdebt and [de]activate use_delay mechanism
+	 * accordingly. We don't want to race against the timer trying to
+	 * clear them and leave @iocg inactive w/ dangling use_delay heavily
+	 * penalizing the cgroup and its descendants.
 	 */
 	if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) {
-		atomic64_add(abs_cost, &iocg->abs_vdebt);
+		iocg->abs_vdebt += abs_cost;
 		if (iocg_kick_delay(iocg, &now, cost))
 			blkcg_schedule_throttle(rqos->q,
 					(bio->bi_opf & REQ_SWAP) == REQ_SWAP);
+		spin_unlock_irq(&iocg->waitq.lock);
 		return;
 	}
 
@@ -1756,20 +1782,6 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	 * All waiters are on iocg->waitq and the wait states are
 	 * synchronized using waitq.lock.
 	 */
-	spin_lock_irq(&iocg->waitq.lock);
-
-	/*
-	 * We activated above but w/o any synchronization.  Deactivation is
-	 * synchronized with waitq.lock and we won't get deactivated as
-	 * long as we're waiting, so we're good if we're activated here.
-	 * In the unlikely case that we are deactivated, just issue the IO.
-	 */
-	if (unlikely(list_empty(&iocg->active_list))) {
-		spin_unlock_irq(&iocg->waitq.lock);
-		iocg_commit_bio(iocg, bio, cost);
-		return;
-	}
-
 	init_waitqueue_func_entry(&wait.wait, iocg_wake_fn);
 	wait.wait.private = current;
 	wait.bio = bio;
@@ -1801,6 +1813,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
 	struct ioc_now now;
 	u32 hw_inuse;
 	u64 abs_cost, cost;
+	unsigned long flags;
 
 	/* bypass if disabled or for root cgroup */
 	if (!ioc->enabled || !iocg->level)
@@ -1820,15 +1833,28 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
 		iocg->cursor = bio_end;
 
 	/*
-	 * Charge if there's enough vtime budget and the existing request
-	 * has cost assigned.  Otherwise, account it as debt.  See debt
-	 * handling in ioc_rqos_throttle() for details.
+	 * Charge if there's enough vtime budget and the existing request has
+	 * cost assigned.
 	 */
 	if (rq->bio && rq->bio->bi_iocost_cost &&
-	    time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow))
+	    time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) {
 		iocg_commit_bio(iocg, bio, cost);
-	else
-		atomic64_add(abs_cost, &iocg->abs_vdebt);
+		return;
+	}
+
+	/*
+	 * Otherwise, account it as debt if @iocg is online, which it should
+	 * be for the vast majority of cases. See debt handling in
+	 * ioc_rqos_throttle() for details.
+	 */
+	spin_lock_irqsave(&iocg->waitq.lock, flags);
+	if (likely(!list_empty(&iocg->active_list))) {
+		iocg->abs_vdebt += abs_cost;
+		iocg_kick_delay(iocg, &now, cost);
+	} else {
+		iocg_commit_bio(iocg, bio, cost);
+	}
+	spin_unlock_irqrestore(&iocg->waitq.lock, flags);
 }
 
 static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio)
@@ -1998,7 +2024,6 @@ static void ioc_pd_init(struct blkg_policy_data *pd)
 	iocg->ioc = ioc;
 	atomic64_set(&iocg->vtime, now.vnow);
 	atomic64_set(&iocg->done_vtime, now.vnow);
-	atomic64_set(&iocg->abs_vdebt, 0);
 	atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period));
 	INIT_LIST_HEAD(&iocg->active_list);
 	iocg->hweight_active = HWEIGHT_WHOLE;

crypto/lrw.c

@@ -287,7 +287,7 @@ static void exit_tfm(struct crypto_skcipher *tfm)
 	crypto_free_skcipher(ctx->child);
 }
 
-static void free(struct skcipher_instance *inst)
+static void free_inst(struct skcipher_instance *inst)
 {
 	crypto_drop_skcipher(skcipher_instance_ctx(inst));
 	kfree(inst);
@@ -400,12 +400,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.encrypt = encrypt;
 	inst->alg.decrypt = decrypt;
 
-	inst->free = free;
+	inst->free = free_inst;
 
 	err = skcipher_register_instance(tmpl, inst);
 	if (err) {
 err_free_inst:
-		free(inst);
+		free_inst(inst);
 	}
 	return err;
 }

crypto/xts.c

@@ -322,7 +322,7 @@ static void exit_tfm(struct crypto_skcipher *tfm)
 	crypto_free_cipher(ctx->tweak);
 }
 
-static void free(struct skcipher_instance *inst)
+static void free_inst(struct skcipher_instance *inst)
 {
 	crypto_drop_skcipher(skcipher_instance_ctx(inst));
 	kfree(inst);
@@ -434,12 +434,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.encrypt = encrypt;
 	inst->alg.decrypt = decrypt;
 
-	inst->free = free;
+	inst->free = free_inst;
 
 	err = skcipher_register_instance(tmpl, inst);
 	if (err) {
 err_free_inst:
-		free(inst);
+		free_inst(inst);
 	}
 	return err;
 }

drivers/acpi/ec.c

@@ -1994,23 +1994,31 @@ void acpi_ec_set_gpe_wake_mask(u8 action)
 		acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action);
 }
 
-bool acpi_ec_other_gpes_active(void)
-{
-	return acpi_any_gpe_status_set(first_ec ? first_ec->gpe : U32_MAX);
-}
-
 bool acpi_ec_dispatch_gpe(void)
 {
 	u32 ret;
 
 	if (!first_ec)
+		return acpi_any_gpe_status_set(U32_MAX);
+
+	/*
+	 * Report wakeup if the status bit is set for any enabled GPE other
+	 * than the EC one.
+	 */
+	if (acpi_any_gpe_status_set(first_ec->gpe))
+		return true;
+
+	if (ec_no_wakeup)
 		return false;
 
+	/*
+	 * Dispatch the EC GPE in-band, but do not report wakeup in any case
+	 * to allow the caller to process events properly after that.
+	 */
 	ret = acpi_dispatch_gpe(NULL, first_ec->gpe);
-	if (ret == ACPI_INTERRUPT_HANDLED) {
+	if (ret == ACPI_INTERRUPT_HANDLED)
 		pm_pr_dbg("EC GPE dispatched\n");
-		return true;
-	}
+
 	return false;
 }
 #endif /* CONFIG_PM_SLEEP */

drivers/acpi/internal.h

@@ -202,7 +202,6 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit);
 
 #ifdef CONFIG_PM_SLEEP
 void acpi_ec_flush_work(void);
-bool acpi_ec_other_gpes_active(void);
 bool acpi_ec_dispatch_gpe(void);
 #endif
 

drivers/acpi/sleep.c

@@ -1013,20 +1013,10 @@ static bool acpi_s2idle_wake(void)
 		if (acpi_check_wakeup_handlers())
 			return true;
 
-		/*
-		 * If the status bit is set for any enabled GPE other than the
-		 * EC one, the wakeup is regarded as a genuine one.
-		 */
-		if (acpi_ec_other_gpes_active())
+		/* Check non-EC GPE wakeups and dispatch the EC GPE. */
+		if (acpi_ec_dispatch_gpe())
 			return true;
 
-		/*
-		 * If the EC GPE status bit has not been set, the wakeup is
-		 * regarded as a spurious one.
-		 */
-		if (!acpi_ec_dispatch_gpe())
-			return false;
-
 		/*
 		 * Cancel the wakeup and process all pending events in case
 		 * there are any wakeup ones in there.

drivers/amba/bus.c

@@ -645,6 +645,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name)
 	dev->dev.release = amba_device_release;
 	dev->dev.bus = &amba_bustype;
 	dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
+	dev->dev.dma_parms = &dev->dma_parms;
 	dev->res.name = dev_name(&dev->dev);
 }
 

drivers/base/component.c

@@ -256,6 +256,7 @@ static int try_to_bring_up_master(struct master *master,
 	ret = master->ops->bind(master->dev);
 	if (ret < 0) {
 		devres_release_group(master->dev, NULL);
+		if (ret != -EPROBE_DEFER)
 			dev_info(master->dev, "master bind failed: %d\n", ret);
 		return ret;
 	}
@@ -611,6 +612,7 @@ static int component_bind(struct component *component, struct master *master,
 		devres_release_group(component->dev, NULL);
 		devres_release_group(master->dev, NULL);
 
+		if (ret != -EPROBE_DEFER)
 			dev_err(master->dev, "failed to bind %s (ops %ps): %d\n",
 				dev_name(component->dev), component->ops, ret);
 	}

drivers/base/core.c

@@ -2370,6 +2370,11 @@ u32 fw_devlink_get_flags(void)
 	return fw_devlink_flags;
 }
 
+static bool fw_devlink_is_permissive(void)
+{
+	return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY;
+}
+
 /**
  * device_add - add device to device hierarchy.
  * @dev: device.
@@ -2524,7 +2529,7 @@ int device_add(struct device *dev)
 	if (fw_devlink_flags && is_fwnode_dev &&
 	    fwnode_has_op(dev->fwnode, add_links)) {
 		fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev);
-		if (fw_ret == -ENODEV)
+		if (fw_ret == -ENODEV && !fw_devlink_is_permissive())
 			device_link_wait_for_mandatory_supplier(dev);
 		else if (fw_ret)
 			device_link_wait_for_optional_supplier(dev);

drivers/base/dd.c

@@ -224,17 +224,9 @@ static int deferred_devs_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(deferred_devs);
 
-#ifdef CONFIG_MODULES
-/*
- * In the case of modules, set the default probe timeout to
- * 30 seconds to give userland some time to load needed modules
- */
-int driver_deferred_probe_timeout = 30;
-#else
-/* In the case of !modules, no probe timeout needed */
-int driver_deferred_probe_timeout = -1;
-#endif
+int driver_deferred_probe_timeout;
 EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout);
+static DECLARE_WAIT_QUEUE_HEAD(probe_timeout_waitqueue);
 
 static int __init deferred_probe_timeout_setup(char *str)
 {
@@ -266,8 +258,8 @@ int driver_deferred_probe_check_state(struct device *dev)
 		return -ENODEV;
 	}
 
-	if (!driver_deferred_probe_timeout) {
-		dev_WARN(dev, "deferred probe timeout, ignoring dependency");
+	if (!driver_deferred_probe_timeout && initcalls_done) {
+		dev_warn(dev, "deferred probe timeout, ignoring dependency");
 		return -ETIMEDOUT;
 	}
 
@@ -284,6 +276,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work)
 
 	list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe)
 		dev_info(private->device, "deferred probe pending");
+	wake_up(&probe_timeout_waitqueue);
 }
 static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func);
 
@@ -658,6 +651,9 @@ int driver_probe_done(void)
  */
 void wait_for_device_probe(void)
 {
+	/* wait for probe timeout */
+	wait_event(probe_timeout_waitqueue, !driver_deferred_probe_timeout);
+
 	/* wait for the deferred probe workqueue to finish */
 	flush_work(&deferred_probe_work);
 

drivers/base/platform.c

@@ -380,6 +380,8 @@ struct platform_object {
  */
 static void setup_pdev_dma_masks(struct platform_device *pdev)
 {
+	pdev->dev.dma_parms = &pdev->dma_parms;
+
 	if (!pdev->dev.coherent_dma_mask)
 		pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	if (!pdev->dev.dma_mask) {

drivers/bus/mhi/core/init.c

@@ -812,10 +812,9 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 	if (!mhi_cntrl)
 		return -EINVAL;
 
-	if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put)
-		return -EINVAL;
-
-	if (!mhi_cntrl->status_cb || !mhi_cntrl->link_status)
+	if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put ||
+	    !mhi_cntrl->status_cb || !mhi_cntrl->read_reg ||
+	    !mhi_cntrl->write_reg)
 		return -EINVAL;
 
 	ret = parse_config(mhi_cntrl, config);

drivers/bus/mhi/core/internal.h

@@ -11,9 +11,6 @@
 
 extern struct bus_type mhi_bus_type;
 
-/* MHI MMIO register mapping */
-#define PCI_INVALID_READ(val) (val == U32_MAX)
-
 #define MHIREGLEN (0x0)
 #define MHIREGLEN_MHIREGLEN_MASK (0xFFFFFFFF)
 #define MHIREGLEN_MHIREGLEN_SHIFT (0)

drivers/bus/mhi/core/main.c

@@ -18,16 +18,7 @@
 int __must_check mhi_read_reg(struct mhi_controller *mhi_cntrl,
 			      void __iomem *base, u32 offset, u32 *out)
 {
-	u32 tmp = readl(base + offset);
-
-	/* If there is any unexpected value, query the link status */
-	if (PCI_INVALID_READ(tmp) &&
-	    mhi_cntrl->link_status(mhi_cntrl))
-		return -EIO;
-
-	*out = tmp;
-
-	return 0;
+	return mhi_cntrl->read_reg(mhi_cntrl, base + offset, out);
 }
 
 int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
@@ -49,7 +40,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base,
 		   u32 offset, u32 val)
 {
-	writel(val, base + offset);
+	mhi_cntrl->write_reg(mhi_cntrl, base + offset, val);
 }
 
 void mhi_write_reg_field(struct mhi_controller *mhi_cntrl, void __iomem *base,
@@ -294,7 +285,7 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl)
 		    !(mhi_chan->ee_mask & BIT(mhi_cntrl->ee)))
 			continue;
 		mhi_dev = mhi_alloc_device(mhi_cntrl);
-		if (!mhi_dev)
+		if (IS_ERR(mhi_dev))
 			return;
 
 		mhi_dev->dev_type = MHI_DEVICE_XFER;
@@ -336,7 +327,8 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl)
 
 		/* Channel name is same for both UL and DL */
 		mhi_dev->chan_name = mhi_chan->name;
-		dev_set_name(&mhi_dev->dev, "%04x_%s", mhi_chan->chan,
+		dev_set_name(&mhi_dev->dev, "%s_%s",
+			     dev_name(mhi_cntrl->cntrl_dev),
 			     mhi_dev->chan_name);
 
 		/* Init wakeup source if available */

drivers/bus/mhi/core/pm.c

@@ -902,7 +902,11 @@ int mhi_sync_power_up(struct mhi_controller *mhi_cntrl)
 			   MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state),
 			   msecs_to_jiffies(mhi_cntrl->timeout_ms));
 
-	return (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -EIO;
+	ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT;
+	if (ret)
+		mhi_power_down(mhi_cntrl, false);
+
+	return ret;
 }
 EXPORT_SYMBOL(mhi_sync_power_up);
 

drivers/firmware/efi/tpm.c

@@ -16,7 +16,7 @@
 int efi_tpm_final_log_size;
 EXPORT_SYMBOL(efi_tpm_final_log_size);
 
-static int tpm2_calc_event_log_size(void *data, int count, void *size_info)
+static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info)
 {
 	struct tcg_pcr_event2_head *header;
 	int event_size, size = 0;

drivers/gpio/gpio-pca953x.c

@@ -531,7 +531,7 @@ static int pca953x_gpio_set_config(struct gpio_chip *gc, unsigned int offset,
 {
 	struct pca953x_chip *chip = gpiochip_get_data(gc);
 
-	switch (config) {
+	switch (pinconf_to_config_param(config)) {
 	case PIN_CONFIG_BIAS_PULL_UP:
 	case PIN_CONFIG_BIAS_PULL_DOWN:
 		return pca953x_gpio_set_pull_up_down(chip, offset, config);

drivers/gpio/gpio-tegra.c

@@ -368,6 +368,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d)
 	struct tegra_gpio_info *tgi = bank->tgi;
 	unsigned int gpio = d->hwirq;
 
+	tegra_gpio_irq_mask(d);
 	gpiochip_unlock_as_irq(&tgi->gc, gpio);
 }
 

drivers/gpio/gpiolib.c

@@ -1158,8 +1158,19 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc,
 				  struct gpioline_info *info)
 {
 	struct gpio_chip *gc = desc->gdev->chip;
+	bool ok_for_pinctrl;
 	unsigned long flags;
 
+	/*
+	 * This function takes a mutex so we must check this before taking
+	 * the spinlock.
+	 *
+	 * FIXME: find a non-racy way to retrieve this information. Maybe a
+	 * lock common to both frameworks?
+	 */
+	ok_for_pinctrl =
+		pinctrl_gpio_can_use_line(gc->base + info->line_offset);
+
 	spin_lock_irqsave(&gpio_lock, flags);
 
 	if (desc->name) {
@@ -1186,7 +1197,7 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc,
 	    test_bit(FLAG_USED_AS_IRQ, &desc->flags) ||
 	    test_bit(FLAG_EXPORT, &desc->flags) ||
 	    test_bit(FLAG_SYSFS, &desc->flags) ||
-	    !pinctrl_gpio_can_use_line(gc->base + info->line_offset))
+	    !ok_for_pinctrl)
 		info->flags |= GPIOLINE_FLAG_KERNEL;
 	if (test_bit(FLAG_IS_OUT, &desc->flags))
 		info->flags |= GPIOLINE_FLAG_IS_OUT;
@@ -1227,6 +1238,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	void __user *ip = (void __user *)arg;
 	struct gpio_desc *desc;
 	__u32 offset;
+	int hwgpio;
 
 	/* We fail any subsequent ioctl():s when the chip is gone */
 	if (!gc)
@@ -1259,13 +1271,19 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (IS_ERR(desc))
 			return PTR_ERR(desc);
 
+		hwgpio = gpio_chip_hwgpio(desc);
+
+		if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL &&
+		    test_bit(hwgpio, priv->watched_lines))
+			return -EBUSY;
+
 		gpio_desc_to_lineinfo(desc, &lineinfo);
 
 		if (copy_to_user(ip, &lineinfo, sizeof(lineinfo)))
 			return -EFAULT;
 
 		if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL)
-			set_bit(gpio_chip_hwgpio(desc), priv->watched_lines);
+			set_bit(hwgpio, priv->watched_lines);
 
 		return 0;
 	} else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) {
@@ -1280,7 +1298,12 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (IS_ERR(desc))
 			return PTR_ERR(desc);
 
-		clear_bit(gpio_chip_hwgpio(desc), priv->watched_lines);
+		hwgpio = gpio_chip_hwgpio(desc);
+
+		if (!test_bit(hwgpio, priv->watched_lines))
+			return -EBUSY;
+
+		clear_bit(hwgpio, priv->watched_lines);
 		return 0;
 	}
 	return -EINVAL;
@@ -5289,8 +5312,9 @@ static int __init gpiolib_dev_init(void)
 	gpiolib_initialized = true;
 	gpiochip_setup_devs();
 
-	if (IS_ENABLED(CONFIG_OF_DYNAMIC))
+#if IS_ENABLED(CONFIG_OF_DYNAMIC) && IS_ENABLED(CONFIG_OF_GPIO)
 	WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier));
+#endif /* CONFIG_OF_DYNAMIC && CONFIG_OF_GPIO */
 
 	return ret;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -945,6 +945,7 @@ struct amdgpu_device {
 
 	/* s3/s4 mask */
 	bool                            in_suspend;
+	bool				in_hibernate;
 
 	/* record last mm index being written through WREG32*/
 	unsigned long last_mm_index;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -1343,7 +1343,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	}
 
 	/* Free the BO*/
-	amdgpu_bo_unref(&mem->bo);
+	drm_gem_object_put_unlocked(&mem->bo->tbo.base);
 	mutex_destroy(&mem->lock);
 	kfree(mem);
 
@@ -1688,7 +1688,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 		| KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE
 		| KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE;
 
-	(*mem)->bo = amdgpu_bo_ref(bo);
+	drm_gem_object_get(&bo->tbo.base);
+	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ?
 		AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3372,15 +3372,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		}
 	}
 
-	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
-	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
-
-	amdgpu_amdkfd_suspend(adev, !fbcon);
-
 	amdgpu_ras_suspend(adev);
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
 
+	amdgpu_amdkfd_suspend(adev, !fbcon);
+
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -1181,7 +1181,9 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	struct amdgpu_device *adev = drm_dev->dev_private;
 	int r;
 
+	adev->in_hibernate = true;
 	r = amdgpu_device_suspend(drm_dev, true);
+	adev->in_hibernate = false;
 	if (r)
 		return r;
 	return amdgpu_asic_reset(adev);

drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c

@@ -133,8 +133,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	u32 cpp;
 	u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 			       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS     |
-			       AMDGPU_GEM_CREATE_VRAM_CLEARED 	     |
-			       AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+			       AMDGPU_GEM_CREATE_VRAM_CLEARED;
 
 	info = drm_get_format_info(adev->ddev, mode_cmd);
 	cpp = info->cpp[0];

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -4273,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 		/* ===  CGCG /CGLS for GFX 3D Only === */
 		gfx_v10_0_update_3d_clock_gating(adev, enable);
 		/* ===  MGCG + MGLS === */
-		/* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */
+		gfx_v10_0_update_medium_grain_clock_gating(adev, enable);
 	}
 
 	if (adev->cg_flags &
@@ -4353,11 +4353,7 @@ static int gfx_v10_0_set_powergating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else
-			amdgpu_gfx_off_ctrl(adev, true);
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
@@ -4918,6 +4914,19 @@ static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
 							   ref, mask);
 }
 
+static void gfx_v10_0_ring_soft_recovery(struct amdgpu_ring *ring,
+					 unsigned vmid)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t value = 0;
+
+	value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03);
+	value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01);
+	value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1);
+	value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid);
+	WREG32_SOC15(GC, 0, mmSQ_CMD, value);
+}
+
 static void
 gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 				      uint32_t me, uint32_t pipe,
@@ -5309,6 +5318,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
+	.soft_recovery = gfx_v10_0_ring_soft_recovery,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -1236,6 +1236,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = {
 	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 },
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */
 	{ 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 },
+	/* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */
+	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 },
 	{ 0, 0, 0, 0, 0 },
 };
 
@@ -5025,10 +5027,9 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
-		if (!enable) {
+		if (!enable)
 			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		}
+
 		if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
 			gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true);
 			gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true);
@@ -5052,12 +5053,7 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 			amdgpu_gfx_off_ctrl(adev, true);
 		break;
 	case CHIP_VEGA12:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else {
-			amdgpu_gfx_off_ctrl(adev, true);
-		}
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -441,7 +441,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 
 /**
  * dm_crtc_high_irq() - Handles CRTC interrupt
- * @interrupt_params: ignored
+ * @interrupt_params: used for determining the CRTC instance
  *
  * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK
  * event handler.
@@ -455,70 +455,6 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	unsigned long flags;
 
 	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
-
-	if (acrtc) {
-		acrtc_state = to_dm_crtc_state(acrtc->base.state);
-
-		DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n",
-			      acrtc->crtc_id,
-			      amdgpu_dm_vrr_active(acrtc_state));
-
-		/* Core vblank handling at start of front-porch is only possible
-		 * in non-vrr mode, as only there vblank timestamping will give
-		 * valid results while done in front-porch. Otherwise defer it
-		 * to dm_vupdate_high_irq after end of front-porch.
-		 */
-		if (!amdgpu_dm_vrr_active(acrtc_state))
-			drm_crtc_handle_vblank(&acrtc->base);
-
-		/* Following stuff must happen at start of vblank, for crc
-		 * computation and below-the-range btr support in vrr mode.
-		 */
-		amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
-
-		if (acrtc_state->stream && adev->family >= AMDGPU_FAMILY_AI &&
-		    acrtc_state->vrr_params.supported &&
-		    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
-			spin_lock_irqsave(&adev->ddev->event_lock, flags);
-			mod_freesync_handle_v_update(
-				adev->dm.freesync_module,
-				acrtc_state->stream,
-				&acrtc_state->vrr_params);
-
-			dc_stream_adjust_vmin_vmax(
-				adev->dm.dc,
-				acrtc_state->stream,
-				&acrtc_state->vrr_params.adjust);
-			spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
-		}
-	}
-}
-
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-/**
- * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs
- * @interrupt params - interrupt parameters
- *
- * Notify DRM's vblank event handler at VSTARTUP
- *
- * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which:
- * * We are close enough to VUPDATE - the point of no return for hw
- * * We are in the fixed portion of variable front porch when vrr is enabled
- * * We are before VUPDATE, where double-buffered vrr registers are swapped
- *
- * It is therefore the correct place to signal vblank, send user flip events,
- * and update VRR.
- */
-static void dm_dcn_crtc_high_irq(void *interrupt_params)
-{
-	struct common_irq_params *irq_params = interrupt_params;
-	struct amdgpu_device *adev = irq_params->adev;
-	struct amdgpu_crtc *acrtc;
-	struct dm_crtc_state *acrtc_state;
-	unsigned long flags;
-
-	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
-
 	if (!acrtc)
 		return;
 
@@ -528,21 +464,34 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 			 amdgpu_dm_vrr_active(acrtc_state),
 			 acrtc_state->active_planes);
 
-	amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
+	/**
+	 * Core vblank handling at start of front-porch is only possible
+	 * in non-vrr mode, as only there vblank timestamping will give
+	 * valid results while done in front-porch. Otherwise defer it
+	 * to dm_vupdate_high_irq after end of front-porch.
+	 */
+	if (!amdgpu_dm_vrr_active(acrtc_state))
 		drm_crtc_handle_vblank(&acrtc->base);
 
+	/**
+	 * Following stuff must happen at start of vblank, for crc
+	 * computation and below-the-range btr support in vrr mode.
+	 */
+	amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
+
+	/* BTR updates need to happen before VUPDATE on Vega and above. */
+	if (adev->family < AMDGPU_FAMILY_AI)
+		return;
+
 	spin_lock_irqsave(&adev->ddev->event_lock, flags);
 
-	if (acrtc_state->vrr_params.supported &&
+	if (acrtc_state->stream && acrtc_state->vrr_params.supported &&
 	    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
-		mod_freesync_handle_v_update(
-		adev->dm.freesync_module,
+		mod_freesync_handle_v_update(adev->dm.freesync_module,
 					     acrtc_state->stream,
 					     &acrtc_state->vrr_params);
 
-		dc_stream_adjust_vmin_vmax(
-			adev->dm.dc,
-			acrtc_state->stream,
+		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream,
 					   &acrtc_state->vrr_params.adjust);
 	}
 
@@ -556,7 +505,8 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 	 * avoid race conditions between flip programming and completion,
 	 * which could cause too early flip completion events.
 	 */
-	if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED &&
+	if (adev->family >= AMDGPU_FAMILY_RV &&
+	    acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED &&
 	    acrtc_state->active_planes == 0) {
 		if (acrtc->event) {
 			drm_crtc_send_vblank_event(&acrtc->base, acrtc->event);
@@ -568,7 +518,6 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 }
-#endif
 
 static int dm_set_clockgating_state(void *handle,
 		  enum amd_clockgating_state state)
@@ -2008,17 +1957,22 @@ void amdgpu_dm_update_connector_after_detect(
 		dc_sink_retain(aconnector->dc_sink);
 		if (sink->dc_edid.length == 0) {
 			aconnector->edid = NULL;
-			drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux);
+			if (aconnector->dc_link->aux_mode) {
+				drm_dp_cec_unset_edid(
+					&aconnector->dm_dp_aux.aux);
+			}
 		} else {
 			aconnector->edid =
-				(struct edid *) sink->dc_edid.raw_edid;
-
+				(struct edid *)sink->dc_edid.raw_edid;
 
 			drm_connector_update_edid_property(connector,
 							   aconnector->edid);
+
+			if (aconnector->dc_link->aux_mode)
 				drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
 						    aconnector->edid);
 		}
+
 		amdgpu_dm_update_freesync_caps(connector, aconnector->edid);
 		update_connector_ext_caps(aconnector);
 	} else {
@@ -2440,8 +2394,36 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 		c_irq_params->adev = adev;
 		c_irq_params->irq_src = int_params.irq_source;
 
+		amdgpu_dm_irq_register_interrupt(
+			adev, &int_params, dm_crtc_high_irq, c_irq_params);
+	}
+
+	/* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to
+	 * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx
+	 * to trigger at end of each vblank, regardless of state of the lock,
+	 * matching DCE behaviour.
+	 */
+	for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT;
+	     i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1;
+	     i++) {
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq);
+
+		if (r) {
+			DRM_ERROR("Failed to add vupdate irq id!\n");
+			return r;
+		}
+
+		int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT;
+		int_params.irq_source =
+			dc_interrupt_to_irq_source(dc, i, 0);
+
+		c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1];
+
+		c_irq_params->adev = adev;
+		c_irq_params->irq_src = int_params.irq_source;
+
 		amdgpu_dm_irq_register_interrupt(adev, &int_params,
-				dm_dcn_crtc_high_irq, c_irq_params);
+				dm_vupdate_high_irq, c_irq_params);
 	}
 
 	/* Use GRPH_PFLIP interrupt */
@@ -4448,10 +4430,6 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	int rc;
 
-	/* Do not set vupdate for DCN hardware */
-	if (adev->family > AMDGPU_FAMILY_AI)
-		return 0;
-
 	irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst;
 
 	rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY;
@@ -7877,6 +7855,7 @@ static int dm_update_plane_state(struct dc *dc,
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state;
 	struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state;
+	struct amdgpu_crtc *new_acrtc;
 	bool needs_reset;
 	int ret = 0;
 
@@ -7886,10 +7865,31 @@ static int dm_update_plane_state(struct dc *dc,
 	dm_new_plane_state = to_dm_plane_state(new_plane_state);
 	dm_old_plane_state = to_dm_plane_state(old_plane_state);
 
-	/*TODO Implement atomic check for cursor plane */
-	if (plane->type == DRM_PLANE_TYPE_CURSOR)
+	/*TODO Implement better atomic check for cursor plane */
+	if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+		if (!enable || !new_plane_crtc ||
+			drm_atomic_plane_disabling(plane->state, new_plane_state))
 			return 0;
 
+		new_acrtc = to_amdgpu_crtc(new_plane_crtc);
+
+		if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) ||
+			(new_plane_state->crtc_h > new_acrtc->max_cursor_height)) {
+			DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n",
+							 new_plane_state->crtc_w, new_plane_state->crtc_h);
+			return -EINVAL;
+		}
+
+		if (new_plane_state->crtc_x <= -new_acrtc->max_cursor_width ||
+			new_plane_state->crtc_y <= -new_acrtc->max_cursor_height) {
+			DRM_DEBUG_ATOMIC("Bad cursor position %d, %d\n",
+							 new_plane_state->crtc_x, new_plane_state->crtc_y);
+			return -EINVAL;
+		}
+
+		return 0;
+	}
+
 	needs_reset = should_reset_plane(state, plane, old_plane_state,
 					 new_plane_state);
 

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c

@@ -398,15 +398,15 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
 	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
 
-	memset(display, 0, sizeof(*display));
-	memset(link, 0, sizeof(*link));
-
-	display->index = aconnector->base.index;
-
 	if (config->dpms_off) {
 		hdcp_remove_display(hdcp_work, link_index, aconnector);
 		return;
 	}
+
+	memset(display, 0, sizeof(*display));
+	memset(link, 0, sizeof(*link));
+
+	display->index = aconnector->base.index;
 	display->state = MOD_HDCP_DISPLAY_ACTIVE;
 
 	if (aconnector->dc_sink != NULL)

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

@@ -834,11 +834,10 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context)
 {
 	int i;
-	int count = 0;
-	struct pipe_ctx *pipe;
 	PERF_TRACE();
 	for (i = 0; i < MAX_PIPES; i++) {
-		pipe = &context->res_ctx.pipe_ctx[i];
+		int count = 0;
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (!pipe->plane_state)
 			continue;

drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c

@@ -3068,25 +3068,32 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
 	return out;
 }
 
-
-bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
-		bool fast_validate)
+/*
+ * This must be noinline to ensure anything that deals with FP registers
+ * is contained within this call; previously our compiling with hard-float
+ * would result in fp instructions being emitted outside of the boundaries
+ * of the DC_FP_START/END macros, which makes sense as the compiler has no
+ * idea about what is wrapped and what is not
+ *
+ * This is largely just a workaround to avoid breakage introduced with 5.6,
+ * ideally all fp-using code should be moved into its own file, only that
+ * should be compiled with hard-float, and all code exported from there
+ * should be strictly wrapped with DC_FP_START/END
+ */
+static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc,
+		struct dc_state *context, bool fast_validate)
 {
 	bool voltage_supported = false;
 	bool full_pstate_supported = false;
 	bool dummy_pstate_supported = false;
 	double p_state_latency_us;
 
-	DC_FP_START();
 	p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
 	context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
 		dc->debug.disable_dram_clock_change_vactive_support;
 
 	if (fast_validate) {
-		voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true);
-
-		DC_FP_END();
-		return voltage_supported;
+		return dcn20_validate_bandwidth_internal(dc, context, true);
 	}
 
 	// Best case, we support full UCLK switch latency
@@ -3115,7 +3122,15 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 
 restore_dml_state:
 	context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
+	return voltage_supported;
+}
 
+bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
+		bool fast_validate)
+{
+	bool voltage_supported = false;
+	DC_FP_START();
+	voltage_supported = dcn20_validate_bandwidth_fp(dc, context, fast_validate);
 	DC_FP_END();
 	return voltage_supported;
 }

drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c

@@ -1200,7 +1200,7 @@ static void dml_rq_dlg_get_dlg_params(
 	min_hratio_fact_l = 1.0;
 	min_hratio_fact_c = 1.0;
 
-	if (htaps_l <= 1)
+	if (hratio_l <= 1)
 		min_hratio_fact_l = 2.0;
 	else if (htaps_l <= 6) {
 		if ((hratio_l * 2.0) > 4.0)
@@ -1216,7 +1216,7 @@ static void dml_rq_dlg_get_dlg_params(
 
 	hscale_pixel_rate_l = min_hratio_fact_l * dppclk_freq_in_mhz;
 
-	if (htaps_c <= 1)
+	if (hratio_c <= 1)
 		min_hratio_fact_c = 2.0;
 	else if (htaps_c <= 6) {
 		if ((hratio_c * 2.0) > 4.0)
@@ -1522,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params(
 
 	disp_dlg_regs->refcyc_per_vm_group_vblank   = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
 	disp_dlg_regs->refcyc_per_vm_group_flip     = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
-	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
-	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
+	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10);
+	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10);
 
 	// Clamp to max for now
 	if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23))

drivers/gpu/drm/amd/display/dc/os_types.h

@@ -108,7 +108,7 @@
 #define ASSERT(expr) ASSERT_CRITICAL(expr)
 
 #else
-#define ASSERT(expr) WARN_ON(!(expr))
+#define ASSERT(expr) WARN_ON_ONCE(!(expr))
 #endif
 
 #define BREAK_TO_DEBUGGER() ASSERT(0)

drivers/gpu/drm/amd/powerplay/amd_powerplay.c

@@ -319,12 +319,12 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr  *hwmgr,
 		if (*level & profile_mode_mask) {
 			hwmgr->saved_dpm_level = hwmgr->dpm_level;
 			hwmgr->en_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-						AMD_IP_BLOCK_TYPE_GFX,
-						AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
+						AMD_IP_BLOCK_TYPE_GFX,
+						AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/

drivers/gpu/drm/amd/powerplay/amdgpu_smu.c

@@ -1476,7 +1476,7 @@ static int smu_disable_dpm(struct smu_context *smu)
 	bool use_baco = !smu->is_apu &&
 		((adev->in_gpu_reset &&
 		  (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) ||
-		 (adev->in_runpm && amdgpu_asic_supports_baco(adev)));
+		 ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev)));
 
 	ret = smu_get_smc_version(smu, NULL, &smu_version);
 	if (ret) {
@@ -1744,12 +1744,12 @@ static int smu_enable_umd_pstate(void *handle,
 		if (*level & profile_mode_mask) {
 			smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level;
 			smu_dpm_ctx->enable_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(smu->adev,
-							       AMD_IP_BLOCK_TYPE_GFX,
-							       AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(smu->adev,
 							       AMD_IP_BLOCK_TYPE_GFX,
 							       AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(smu->adev,
+							       AMD_IP_BLOCK_TYPE_GFX,
+							       AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/

drivers/gpu/drm/drm_hdcp.c

@@ -241,8 +241,12 @@ static int drm_hdcp_request_srm(struct drm_device *drm_dev,
 
 	ret = request_firmware_direct(&fw, (const char *)fw_name,
 				      drm_dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		*revoked_ksv_cnt = 0;
+		*revoked_ksv_list = NULL;
+		ret = 0;
 		goto exit;
+	}
 
 	if (fw->size && fw->data)
 		ret = drm_hdcp_srm_update(fw->data, fw->size, revoked_ksv_list,
@@ -287,6 +291,8 @@ int drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs,
 
 	ret = drm_hdcp_request_srm(drm_dev, &revoked_ksv_list,
 				   &revoked_ksv_cnt);
+	if (ret)
+		return ret;
 
 	/* revoked_ksv_cnt will be zero when above function failed */
 	for (i = 0; i < revoked_ksv_cnt; i++)

drivers/gpu/drm/i915/display/intel_fbc.c

@@ -485,8 +485,7 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
 	if (!ret)
 		goto err_llb;
 	else if (ret > 1) {
-		DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
-
+		DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
 	}
 
 	fbc->threshold = ret;

drivers/gpu/drm/i915/gem/i915_gem_domain.c

@@ -368,7 +368,6 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 
-	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
 	if (!atomic_read(&obj->bind_count))
 		return;
 
@@ -400,12 +399,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 void
 i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
 {
-	struct drm_i915_gem_object *obj = vma->obj;
-
-	assert_object_held(obj);
-
 	/* Bump the LRU to try and avoid premature eviction whilst flipping  */
-	i915_gem_object_bump_inactive_ggtt(obj);
+	i915_gem_object_bump_inactive_ggtt(vma->obj);
 
 	i915_vma_unpin(vma);
 }

drivers/gpu/drm/i915/gt/intel_context_types.h

@@ -69,7 +69,13 @@ struct intel_context {
 #define CONTEXT_NOPREEMPT		7
 
 	u32 *lrc_reg_state;
-	u64 lrc_desc;
+	union {
+		struct {
+			u32 lrca;
+			u32 ccid;
+		};
+		u64 desc;
+	} lrc;
 	u32 tag; /* cookie passed to HW to track this context on submission */
 
 	/* Time on GPU as tracked by the hw. */

drivers/gpu/drm/i915/gt/intel_engine.h

@@ -333,13 +333,4 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 	return intel_engine_has_preemption(engine);
 }
 
-static inline bool
-intel_engine_has_timeslices(const struct intel_engine_cs *engine)
-{
-	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
-		return false;
-
-	return intel_engine_has_semaphores(engine);
-}
-
 #endif /* _INTEL_RINGBUFFER_H_ */

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -1295,6 +1295,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
 		drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID));
+	if (HAS_EXECLISTS(dev_priv)) {
+		drm_printf(m, "\tEL_STAT_HI: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI));
+		drm_printf(m, "\tEL_STAT_LO: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO));
+	}
 	drm_printf(m, "\tRING_START: 0x%08x\n",
 		   ENGINE_READ(engine, RING_START));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -156,6 +156,20 @@ struct intel_engine_execlists {
 	 */
 	struct i915_priolist default_priolist;
 
+	/**
+	 * @ccid: identifier for contexts submitted to this engine
+	 */
+	u32 ccid;
+
+	/**
+	 * @yield: CCID at the time of the last semaphore-wait interrupt.
+	 *
+	 * Instead of leaving a semaphore busy-spinning on an engine, we would
+	 * like to switch to another ready context, i.e. yielding the semaphore
+	 * timeslice.
+	 */
+	u32 yield;
+
 	/**
 	 * @error_interrupt: CS Master EIR
 	 *
@@ -295,8 +309,7 @@ struct intel_engine_cs {
 	u32 context_size;
 	u32 mmio_base;
 
-	unsigned int context_tag;
-#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS)
+	unsigned long context_tag;
 
 	struct rb_node uabi_node;
 
@@ -483,10 +496,11 @@ struct intel_engine_cs {
 #define I915_ENGINE_SUPPORTS_STATS   BIT(1)
 #define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
-#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
-#define I915_ENGINE_IS_VIRTUAL       BIT(5)
-#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
-#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
+#define I915_ENGINE_HAS_TIMESLICES   BIT(4)
+#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5)
+#define I915_ENGINE_IS_VIRTUAL       BIT(6)
+#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8)
 	unsigned int flags;
 
 	/*
@@ -584,6 +598,15 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_HAS_SEMAPHORES;
 }
 
+static inline bool
+intel_engine_has_timeslices(const struct intel_engine_cs *engine)
+{
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return false;
+
+	return engine->flags & I915_ENGINE_HAS_TIMESLICES;
+}
+
 static inline bool
 intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine)
 {

drivers/gpu/drm/i915/gt/intel_gt_irq.c

@@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 		}
 	}
 
+	if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) {
+		WRITE_ONCE(engine->execlists.yield,
+			   ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI));
+		ENGINE_TRACE(engine, "semaphore yield: %08x\n",
+			     engine->execlists.yield);
+		if (del_timer(&engine->execlists.timer))
+			tasklet = true;
+	}
+
 	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
 		tasklet = true;
 
@@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	struct intel_uncore *uncore = gt->uncore;
 	const u32 dmask = irqs << 16 | irqs;
 	const u32 smask = irqs << 16;
@@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	const u32 gt_interrupts[] = {
 		irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT,
 		irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT,