Merge ra.kernel.org:/pub/scm/linux/kernel/git/davem/net

Documentation/admin-guide/pm/intel_pstate.rst

@@ -410,7 +410,7 @@ argument is passed to the kernel in the command line.
 	That only is supported in some configurations, though (for example, if
 	the `HWP feature is enabled in the processor <Active Mode With HWP_>`_,
 	the operation mode of the driver cannot be changed), and if it is not
-	supported in the current configuration, writes to this attribute with
+	supported in the current configuration, writes to this attribute will
 	fail with an appropriate error.
 
 Interpretation of Policy Attributes

Documentation/networking/e100.rst

@@ -1,3 +1,4 @@
+==============================================================
 Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
 ==============================================================
 
@@ -86,83 +87,84 @@ Event Log Message Level:  The driver uses the message level flag to log events
 Additional Configurations
 =========================
 
-  Configuring the Driver on Different Distributions
-  -------------------------------------------------
+Configuring the Driver on Different Distributions
+-------------------------------------------------
 
-  Configuring a network driver to load properly when the system is started is
-  distribution dependent. Typically, the configuration process involves adding
-  an alias line to /etc/modprobe.d/*.conf as well as editing other system
-  startup scripts and/or configuration files.  Many popular Linux
-  distributions ship with tools to make these changes for you. To learn the
-  proper way to configure a network device for your system, refer to your
-  distribution documentation.  If during this process you are asked for the
-  driver or module name, the name for the Linux Base Driver for the Intel
-  PRO/100 Family of Adapters is e100.
+Configuring a network driver to load properly when the system is started
+is distribution dependent.  Typically, the configuration process involves
+adding an alias line to /etc/modprobe.d/*.conf as well as editing other
+system startup scripts and/or configuration files.  Many popular Linux
+distributions ship with tools to make these changes for you.  To learn
+the proper way to configure a network device for your system, refer to
+your distribution documentation.  If during this process you are asked
+for the driver or module name, the name for the Linux Base Driver for
+the Intel PRO/100 Family of Adapters is e100.
 
-  As an example, if you install the e100 driver for two PRO/100 adapters
-  (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/
+As an example, if you install the e100 driver for two PRO/100 adapters
+(eth0 and eth1), add the following to a configuration file in
+/etc/modprobe.d/::
 
        alias eth0 e100
        alias eth1 e100
 
-  Viewing Link Messages
-  ---------------------
-  In order to see link messages and other Intel driver information on your
-  console, you must set the dmesg level up to six. This can be done by
-  entering the following on the command line before loading the e100 driver::
-
-       dmesg -n 6
+Viewing Link Messages
+---------------------
 
-  If you wish to see all messages issued by the driver, including debug
-  messages, set the dmesg level to eight.
+In order to see link messages and other Intel driver information on your
+console, you must set the dmesg level up to six.  This can be done by
+entering the following on the command line before loading the e100
+driver::
 
-  NOTE: This setting is not saved across reboots.
+       dmesg -n 6
 
+If you wish to see all messages issued by the driver, including debug
+messages, set the dmesg level to eight.
 
-  ethtool
-  -------
+NOTE: This setting is not saved across reboots.
 
-  The driver utilizes the ethtool interface for driver configuration and
-  diagnostics, as well as displaying statistical information.  The ethtool
-  version 1.6 or later is required for this functionality.
+ethtool
+-------
 
-  The latest release of ethtool can be found from
-  https://www.kernel.org/pub/software/network/ethtool/
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information.  The ethtool
+version 1.6 or later is required for this functionality.
 
-  Enabling Wake on LAN* (WoL)
-  ---------------------------
-  WoL is provided through the ethtool* utility.  For instructions on enabling
-  WoL with ethtool, refer to the ethtool man page.
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
 
-  WoL will be enabled on the system during the next shut down or reboot. For
-  this driver version, in order to enable WoL, the e100 driver must be
-  loaded when shutting down or rebooting the system.
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is provided through the ethtool* utility.  For instructions on
+enabling WoL with ethtool, refer to the ethtool man page.  WoL will be
+enabled on the system during the next shut down or reboot.  For this
+driver version, in order to enable WoL, the e100 driver must be loaded
+when shutting down or rebooting the system.
 
-  NAPI
-  ----
+NAPI
+----
 
-  NAPI (Rx polling mode) is supported in the e100 driver.
+NAPI (Rx polling mode) is supported in the e100 driver.
 
-  See https://wiki.linuxfoundation.org/networking/napi for more information
-  on NAPI.
+See https://wiki.linuxfoundation.org/networking/napi for more
+information on NAPI.
 
-  Multiple Interfaces on Same Ethernet Broadcast Network
-  ------------------------------------------------------
+Multiple Interfaces on Same Ethernet Broadcast Network
+------------------------------------------------------
 
-  Due to the default ARP behavior on Linux, it is not possible to have
-  one system on two IP networks in the same Ethernet broadcast domain
-  (non-partitioned switch) behave as expected. All Ethernet interfaces
-  will respond to IP traffic for any IP address assigned to the system.
-  This results in unbalanced receive traffic.
+Due to the default ARP behavior on Linux, it is not possible to have one
+system on two IP networks in the same Ethernet broadcast domain
+(non-partitioned switch) behave as expected.  All Ethernet interfaces
+will respond to IP traffic for any IP address assigned to the system.
+This results in unbalanced receive traffic.
 
-  If you have multiple interfaces in a server, either turn on ARP
-  filtering by
+If you have multiple interfaces in a server, either turn on ARP
+filtering by
 
-  (1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-      (this only works if your kernel's version is higher than 2.4.5), or
+(1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+    (this only works if your kernel's version is higher than 2.4.5), or
 
-  (2) installing the interfaces in separate broadcast domains (either
-      in different switches or in a switch partitioned to VLANs).
+(2) installing the interfaces in separate broadcast domains (either
+    in different switches or in a switch partitioned to VLANs).
 
 
 Support

Documentation/networking/e1000.rst

@@ -1,3 +1,4 @@
+===========================================================
 Linux* Base Driver for Intel(R) Ethernet Network Connection
 ===========================================================
 
@@ -354,57 +355,58 @@ previously mentioned to force the adapter to the same speed and duplex.
 Additional Configurations
 =========================
 
-  Jumbo Frames
-  ------------
-  Jumbo Frames support is enabled by changing the MTU to a value larger than
-  the default of 1500.  Use the ifconfig command to increase the MTU size.
-  For example::
+Jumbo Frames
+------------
+Jumbo Frames support is enabled by changing the MTU to a value larger
+than the default of 1500.  Use the ifconfig command to increase the MTU
+size.  For example::
 
        ifconfig eth<x> mtu 9000 up
 
-  This setting is not saved across reboots.  It can be made permanent if
-  you add::
+This setting is not saved across reboots.  It can be made permanent if
+you add::
 
        MTU=9000
 
-   to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
-   applies to the Red Hat distributions; other distributions may store this
-   setting in a different location.
+to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
+applies to the Red Hat distributions; other distributions may store this
+setting in a different location.
+
+Notes: Degradation in throughput performance may be observed in some
+Jumbo frames environments.  If this is observed, increasing the
+application's socket buffer size and/or increasing the
+/proc/sys/net/ipv4/tcp_*mem entry values may help.  See the specific
+application manual and /usr/src/linux*/Documentation/
+networking/ip-sysctl.txt for more details.
 
-  Notes:
-  Degradation in throughput performance may be observed in some Jumbo frames
-  environments. If this is observed, increasing the application's socket buffer
-  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
-  See the specific application manual and /usr/src/linux*/Documentation/
-  networking/ip-sysctl.txt for more details.
+- The maximum MTU setting for Jumbo Frames is 16110.  This value
+  coincides with the maximum Jumbo Frames size of 16128.
 
-  - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
-    with the maximum Jumbo Frames size of 16128.
+- Using Jumbo frames at 10 or 100 Mbps is not supported and may result
+  in poor performance or loss of link.
 
-  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
-    poor performance or loss of link.
+- Adapters based on the Intel(R) 82542 and 82573V/E controller do not
+  support Jumbo Frames.  These correspond to the following product names:
+  Intel(R) PRO/1000 Gigabit Server Adapter Intel(R) PRO/1000 PM Network
+  Connection
 
-  - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
-    support Jumbo Frames. These correspond to the following product names:
-     Intel(R) PRO/1000 Gigabit Server Adapter
-     Intel(R) PRO/1000 PM Network Connection
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information.  The ethtool
+version 1.6 or later is required for this functionality.
 
-  ethtool
-  -------
-  The driver utilizes the ethtool interface for driver configuration and
-  diagnostics, as well as displaying statistical information.  The ethtool
-  version 1.6 or later is required for this functionality.
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
 
-  The latest release of ethtool can be found from
-  https://www.kernel.org/pub/software/network/ethtool/
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is configured through the ethtool* utility.
 
-  Enabling Wake on LAN* (WoL)
-  ---------------------------
-  WoL is configured through the ethtool* utility.
+WoL will be enabled on the system during the next shut down or reboot.
+For this driver version, in order to enable WoL, the e1000 driver must be
+loaded when shutting down or rebooting the system.
 
-  WoL will be enabled on the system during the next shut down or reboot.
-  For this driver version, in order to enable WoL, the e1000 driver must be
-  loaded when shutting down or rebooting the system.
 
 Support
 =======

Documentation/networking/strparser.txt

@@ -48,7 +48,7 @@ void strp_pause(struct strparser *strp)
      Temporarily pause a stream parser. Message parsing is suspended
      and no new messages are delivered to the upper layer.
 
-void strp_pause(struct strparser *strp)
+void strp_unpause(struct strparser *strp)
 
      Unpause a paused stream parser.
 

Documentation/trace/histogram.txt

@@ -1729,35 +1729,35 @@ If a variable isn't a key variable or prefixed with 'vals=', the
 associated event field will be saved in a variable but won't be summed
 as a value:
 
-  # echo 'hist:keys=next_pid:ts1=common_timestamp ... >> event/trigger
+  # echo 'hist:keys=next_pid:ts1=common_timestamp ...' >> event/trigger
 
 Multiple variables can be assigned at the same time.  The below would
 result in both ts0 and b being created as variables, with both
 common_timestamp and field1 additionally being summed as values:
 
-  # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ... >> \
+  # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ...' >> \
 	event/trigger
 
 Note that variable assignments can appear either preceding or
 following their use.  The command below behaves identically to the
 command above:
 
-  # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ... >> \
+  # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ...' >> \
 	event/trigger
 
 Any number of variables not bound to a 'vals=' prefix can also be
 assigned by simply separating them with colons.  Below is the same
 thing but without the values being summed in the histogram:
 
-  # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ... >> event/trigger
+  # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ...' >> event/trigger
 
 Variables set as above can be referenced and used in expressions on
 another event.
 
 For example, here's how a latency can be calculated:
 
-  # echo 'hist:keys=pid,prio:ts0=common_timestamp ... >> event1/trigger
-  # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ... >> event2/trigger
+  # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger
+  # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger
 
 In the first line above, the event's timetamp is saved into the
 variable ts0.  In the next line, ts0 is subtracted from the second
@@ -1766,7 +1766,7 @@ yet another variable, 'wakeup_lat'.  The hist trigger below in turn
 makes use of the wakeup_lat variable to compute a combined latency
 using the same key and variable from yet another event:
 
-  # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ... >> event3/trigger
+  # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ...' >> event3/trigger
 
 2.2.2 Synthetic Events
 ----------------------
@@ -1807,10 +1807,11 @@ the command that defined it with a '!':
 At this point, there isn't yet an actual 'wakeup_latency' event
 instantiated in the event subsytem - for this to happen, a 'hist
 trigger action' needs to be instantiated and bound to actual fields
-and variables defined on other events (see Section 6.3.3 below).
+and variables defined on other events (see Section 2.2.3 below on
+how that is done using hist trigger 'onmatch' action). Once that is
+done, the 'wakeup_latency' synthetic event instance is created.
 
-Once that is done, an event instance is created, and a histogram can
-be defined using it:
+A histogram can now be defined for the new synthetic event:
 
   # echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
         /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
@@ -1960,7 +1961,7 @@ hist trigger specification.
     back to that pid, the timestamp difference is calculated.  If the
     resulting latency, stored in wakeup_lat, exceeds the current
     maximum latency, the values specified in the save() fields are
-    recoreded:
+    recorded:
 
     # echo 'hist:keys=pid:ts0=common_timestamp.usecs \
             if comm=="cyclictest"' >> \

Documentation/virtual/kvm/api.txt

@@ -4610,7 +4610,7 @@ This capability indicates that kvm will implement the interfaces to handle
 reset, migration and nested KVM for branch prediction blocking. The stfle
 facility 82 should not be provided to the guest without this capability.
 
-8.14 KVM_CAP_HYPERV_TLBFLUSH
+8.18 KVM_CAP_HYPERV_TLBFLUSH
 
 Architectures: x86
 

MAINTAINERS

@@ -9882,6 +9882,7 @@ M:	Andrew Lunn <andrew@lunn.ch>
 M:	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 S:	Maintained
+F:	Documentation/devicetree/bindings/net/dsa/
 F:	net/dsa/
 F:	include/net/dsa.h
 F:	include/linux/dsa/
@@ -15574,6 +15575,7 @@ M:	x86@kernel.org
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
 S:	Maintained
+F:	Documentation/devicetree/bindings/x86/
 F:	Documentation/x86/
 F:	arch/x86/
 

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Merciless Moray
 
 # *DOCUMENTATION*

arch/alpha/Kconfig

@@ -555,11 +555,6 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
-config HAVE_DEC_LOCK
-	bool
-	depends on SMP
-	default y
-
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32

arch/alpha/lib/Makefile

@@ -35,8 +35,6 @@ lib-y =	__divqu.o __remqu.o __divlu.o __remlu.o \
 	callback_srm.o srm_puts.o srm_printk.o \
 	fls.o
 
-lib-$(CONFIG_SMP) += dec_and_lock.o
-
 # The division routines are built from single source, with different defines.
 AFLAGS___divqu.o = -DDIV
 AFLAGS___remqu.o =       -DREM

arch/alpha/lib/dec_and_lock.c

@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * arch/alpha/lib/dec_and_lock.c
- *
- * ll/sc version of atomic_dec_and_lock()
- * 
- */
-
-#include <linux/spinlock.h>
-#include <linux/atomic.h>
-#include <linux/export.h>
-
-  asm (".text					\n\
-	.global _atomic_dec_and_lock		\n\
-	.ent _atomic_dec_and_lock		\n\
-	.align	4				\n\
-_atomic_dec_and_lock:				\n\
-	.prologue 0				\n\
-1:	ldl_l	$1, 0($16)			\n\
-	subl	$1, 1, $1			\n\
-	beq	$1, 2f				\n\
-	stl_c	$1, 0($16)			\n\
-	beq	$1, 4f				\n\
-	mb					\n\
-	clr	$0				\n\
-	ret					\n\
-2:	br	$29, 3f				\n\
-3:	ldgp	$29, 0($29)			\n\
-	br	$atomic_dec_and_lock_1..ng	\n\
-	.subsection 2				\n\
-4:	br	1b				\n\
-	.previous				\n\
-	.end _atomic_dec_and_lock");
-
-static int __used atomic_dec_and_lock_1(atomic_t *atomic, spinlock_t *lock)
-{
-	/* Slow path */
-	spin_lock(lock);
-	if (atomic_dec_and_test(atomic))
-		return 1;
-	spin_unlock(lock);
-	return 0;
-}
-EXPORT_SYMBOL(_atomic_dec_and_lock);

arch/arm/kernel/signal.c

@@ -544,7 +544,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	 * Increment event counter and perform fixup for the pre-signal
 	 * frame.
 	 */
-	rseq_signal_deliver(regs);
+	rseq_signal_deliver(ksig, regs);
 
 	/*
 	 * Set up the stack frame
@@ -666,7 +666,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 			} else {
 				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
-				rseq_handle_notify_resume(regs);
+				rseq_handle_notify_resume(NULL, regs);
 			}
 		}
 		local_irq_disable();

arch/arm/xen/enlighten.c

@@ -59,6 +59,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
 static __read_mostly unsigned int xen_events_irq;
 
+uint32_t xen_start_flags;
+EXPORT_SYMBOL(xen_start_flags);
+
 int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       xen_pfn_t *gfn, int nr,
@@ -293,9 +296,7 @@ void __init xen_early_init(void)
 	xen_setup_features();
 
 	if (xen_feature(XENFEAT_dom0))
-		xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
-	else
-		xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
+		xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
 
 	if (!console_set_on_cmdline && !xen_initial_domain())
 		add_preferred_console("hvc", 0, NULL);

arch/arm64/crypto/aes-glue.c

@@ -223,8 +223,8 @@ static int ctr_encrypt(struct skcipher_request *req)
 		kernel_neon_begin();
 		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_enc, rounds, blocks, walk.iv);
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	if (walk.nbytes) {
 		u8 __aligned(8) tail[AES_BLOCK_SIZE];

arch/arm64/include/asm/kvm_host.h

@@ -306,6 +306,7 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_FP_ENABLED		(1 << 1) /* guest FP regs loaded */
 #define KVM_ARM64_FP_HOST		(1 << 2) /* host FP regs loaded */
 #define KVM_ARM64_HOST_SVE_IN_USE	(1 << 3) /* backup for host TIF_SVE */
+#define KVM_ARM64_HOST_SVE_ENABLED	(1 << 4) /* SVE enabled for EL0 */
 
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 

arch/arm64/include/asm/sysreg.h

@@ -728,6 +728,17 @@ asm(
 	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
 } while (0)
 
+/*
+ * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the
+ * set mask are set. Other bits are left as-is.
+ */
+#define sysreg_clear_set(sysreg, clear, set) do {			\
+	u64 __scs_val = read_sysreg(sysreg);				\
+	u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set);		\
+	if (__scs_new != __scs_val)					\
+		write_sysreg(__scs_new, sysreg);			\
+} while (0)
+
 static inline void config_sctlr_el1(u32 clear, u32 set)
 {
 	u32 val;

arch/arm64/kernel/cpufeature.c

@@ -937,7 +937,7 @@ static int __init parse_kpti(char *str)
 	__kpti_forced = enabled ? 1 : -1;
 	return 0;
 }
-__setup("kpti=", parse_kpti);
+early_param("kpti", parse_kpti);
 #endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #ifdef CONFIG_ARM64_HW_AFDBM

arch/arm64/kernel/smp.c

@@ -179,7 +179,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
  */
-asmlinkage void secondary_start_kernel(void)
+asmlinkage notrace void secondary_start_kernel(void)
 {
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;

arch/arm64/kvm/fpsimd.c

@@ -5,13 +5,14 @@
  * Copyright 2018 Arm Limited
  * Author: Dave Martin <Dave.Martin@arm.com>
  */
-#include <linux/bottom_half.h>
+#include <linux/irqflags.h>
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_host.h>
 #include <asm/kvm_mmu.h>
+#include <asm/sysreg.h>
 
 /*
  * Called on entry to KVM_RUN unless this vcpu previously ran at least
@@ -61,10 +62,16 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(!current->mm);
 
-	vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE);
+	vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+			      KVM_ARM64_HOST_SVE_IN_USE |
+			      KVM_ARM64_HOST_SVE_ENABLED);
 	vcpu->arch.flags |= KVM_ARM64_FP_HOST;
+
 	if (test_thread_flag(TIF_SVE))
 		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE;
+
+	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
+		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
 }
 
 /*
@@ -92,19 +99,30 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
  */
 void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 {
-	local_bh_disable();
+	unsigned long flags;
 
-	update_thread_flag(TIF_SVE,
-			   vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE);
+	local_irq_save(flags);
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
 		/* Clean guest FP state to memory and invalidate cpu view */
 		fpsimd_save();
 		fpsimd_flush_cpu_state();
-	} else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
-		/* Ensure user trap controls are correctly restored */
-		fpsimd_bind_task_to_cpu();
+	} else if (system_supports_sve()) {
+		/*
+		 * The FPSIMD/SVE state in the CPU has not been touched, and we
+		 * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been
+		 * reset to CPACR_EL1_DEFAULT by the Hyp code, disabling SVE
+		 * for EL0.  To avoid spurious traps, restore the trap state
+		 * seen by kvm_arch_vcpu_load_fp():
+		 */
+		if (vcpu->arch.flags & KVM_ARM64_HOST_SVE_ENABLED)
+			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
+		else
+			sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
 	}
 
-	local_bh_enable();
+	update_thread_flag(TIF_SVE,
+			   vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE);
+
+	local_irq_restore(flags);
 }

arch/arm64/mm/dma-mapping.c

@@ -583,13 +583,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 						    size >> PAGE_SHIFT);
 			return NULL;
 		}
-		if (!coherent)
-			__dma_flush_area(page_to_virt(page), iosize);
-
 		addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
 						   prot,
 						   __builtin_return_address(0));
-		if (!addr) {
+		if (addr) {
+			memset(addr, 0, size);
+			if (!coherent)
+				__dma_flush_area(page_to_virt(page), iosize);
+		} else {
 			iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
 			dma_release_from_contiguous(dev, page,
 						    size >> PAGE_SHIFT);

arch/arm64/mm/proc.S

@@ -217,8 +217,9 @@ ENDPROC(idmap_cpu_replace_ttbr1)
 
 	.macro __idmap_kpti_put_pgtable_ent_ng, type
 	orr	\type, \type, #PTE_NG		// Same bit for blocks and pages
-	str	\type, [cur_\()\type\()p]	// Update the entry and ensure it
-	dc	civac, cur_\()\type\()p		// is visible to all CPUs.
+	str	\type, [cur_\()\type\()p]	// Update the entry and ensure
+	dmb	sy				// that it is visible to all
+	dc	civac, cur_\()\type\()p		// CPUs.
 	.endm
 
 /*

arch/mips/Kconfig

@@ -65,6 +65,7 @@ config MIPS
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP

arch/mips/ath79/mach-pb44.c

@@ -34,7 +34,7 @@
 #define PB44_KEYS_DEBOUNCE_INTERVAL	(3 * PB44_KEYS_POLL_INTERVAL)
 
 static struct gpiod_lookup_table pb44_i2c_gpiod_table = {
-	.dev_id = "i2c-gpio",
+	.dev_id = "i2c-gpio.0",
 	.table = {
 		GPIO_LOOKUP_IDX("ath79-gpio", PB44_GPIO_I2C_SDA,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),

arch/mips/bcm47xx/setup.c

@@ -212,6 +212,12 @@ static int __init bcm47xx_cpu_fixes(void)
 		 */
 		if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706)
 			cpu_wait = NULL;
+
+		/*
+		 * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail"
+		 * Enable ExternalSync for sync instruction to take effect
+		 */
+		set_c0_config7(MIPS_CONF7_ES);
 		break;
 #endif
 	}

arch/mips/include/asm/io.h

@@ -414,6 +414,8 @@ static inline type pfx##in##bwlq##p(unsigned long port)			\
 	__val = *__addr;						\
 	slow;								\
 									\
+	/* prevent prefetching of coherent DMA data prematurely */	\
+	rmb();								\
 	return pfx##ioswab##bwlq(__addr, __val);			\
 }
 

arch/mips/include/asm/mipsregs.h

@@ -681,6 +681,8 @@
 #define MIPS_CONF7_WII		(_ULCAST_(1) << 31)
 
 #define MIPS_CONF7_RPS		(_ULCAST_(1) << 2)
+/* ExternalSync */
+#define MIPS_CONF7_ES		(_ULCAST_(1) << 8)
 
 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
@@ -2765,6 +2767,7 @@ __BUILD_SET_C0(status)
 __BUILD_SET_C0(cause)
 __BUILD_SET_C0(config)
 __BUILD_SET_C0(config5)
+__BUILD_SET_C0(config7)
 __BUILD_SET_C0(intcontrol)
 __BUILD_SET_C0(intctl)
 __BUILD_SET_C0(srsmap)

arch/mips/include/uapi/asm/unistd.h

@@ -388,17 +388,19 @@
 #define __NR_pkey_alloc			(__NR_Linux + 364)
 #define __NR_pkey_free			(__NR_Linux + 365)
 #define __NR_statx			(__NR_Linux + 366)
+#define __NR_rseq			(__NR_Linux + 367)
+#define __NR_io_pgetevents		(__NR_Linux + 368)
 
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		366
+#define __NR_Linux_syscalls		368
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		366
+#define __NR_O32_Linux_syscalls		368
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -733,16 +735,18 @@
 #define __NR_pkey_alloc			(__NR_Linux + 324)
 #define __NR_pkey_free			(__NR_Linux + 325)
 #define __NR_statx			(__NR_Linux + 326)
+#define __NR_rseq			(__NR_Linux + 327)
+#define __NR_io_pgetevents		(__NR_Linux + 328)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		326
+#define __NR_Linux_syscalls		328
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		326
+#define __NR_64_Linux_syscalls		328
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1081,15 +1085,17 @@
 #define __NR_pkey_alloc			(__NR_Linux + 328)
 #define __NR_pkey_free			(__NR_Linux + 329)
 #define __NR_statx			(__NR_Linux + 330)
+#define __NR_rseq			(__NR_Linux + 331)
+#define __NR_io_pgetevents		(__NR_Linux + 332)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		330
+#define __NR_Linux_syscalls		332
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		330
+#define __NR_N32_Linux_syscalls		332
 
 #endif /* _UAPI_ASM_UNISTD_H */

arch/mips/kernel/entry.S

@@ -79,6 +79,10 @@ FEXPORT(ret_from_fork)
 	jal	schedule_tail		# a0 = struct task_struct *prev
 
 FEXPORT(syscall_exit)
+#ifdef CONFIG_DEBUG_RSEQ
+	move	a0, sp
+	jal	rseq_syscall
+#endif
 	local_irq_disable		# make sure need_resched and
 					# signals dont change between
 					# sampling and return
@@ -141,6 +145,10 @@ work_notifysig:				# deal with pending signals and
 	j	resume_userspace_check
 
 FEXPORT(syscall_exit_partial)
+#ifdef CONFIG_DEBUG_RSEQ
+	move	a0, sp
+	jal	rseq_syscall
+#endif
 	local_irq_disable		# make sure need_resched doesn't
 					# change between and return
 	LONG_L	a2, TI_FLAGS($28)	# current->work

arch/mips/kernel/mcount.S

@@ -119,10 +119,20 @@ NESTED(_mcount, PT_SIZE, ra)
 EXPORT_SYMBOL(_mcount)
 	PTR_LA	t1, ftrace_stub
 	PTR_L	t2, ftrace_trace_function /* Prepare t2 for (1) */
-	bne	t1, t2, static_trace
+	beq	t1, t2, fgraph_trace
 	 nop
 
+	MCOUNT_SAVE_REGS
+
+	move	a0, ra		/* arg1: self return address */
+	jalr	t2		/* (1) call *ftrace_trace_function */
+	 move	a1, AT		/* arg2: parent's return address */
+
+	MCOUNT_RESTORE_REGS
+
+fgraph_trace:
 #ifdef	CONFIG_FUNCTION_GRAPH_TRACER
+	PTR_LA	t1, ftrace_stub
 	PTR_L	t3, ftrace_graph_return
 	bne	t1, t3, ftrace_graph_caller
 	 nop
@@ -131,24 +141,11 @@ EXPORT_SYMBOL(_mcount)
 	bne	t1, t3, ftrace_graph_caller
 	 nop
 #endif
-	b	ftrace_stub
-#ifdef CONFIG_32BIT
-	 addiu sp, sp, 8
-#else
-	 nop
-#endif
 
-static_trace:
-	MCOUNT_SAVE_REGS
-
-	move	a0, ra		/* arg1: self return address */
-	jalr	t2		/* (1) call *ftrace_trace_function */
-	 move	a1, AT		/* arg2: parent's return address */
-
-	MCOUNT_RESTORE_REGS
 #ifdef CONFIG_32BIT
 	addiu sp, sp, 8
 #endif
+
 	.globl ftrace_stub
 ftrace_stub:
 	RETURN_BACK

arch/mips/kernel/scall32-o32.S

@@ -590,3 +590,5 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
 	PTR	sys_statx
+	PTR	sys_rseq
+	PTR	sys_io_pgetevents

arch/mips/kernel/scall64-64.S

@@ -439,4 +439,6 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 5325 */
 	PTR	sys_statx
+	PTR	sys_rseq
+	PTR	sys_io_pgetevents
 	.size	sys_call_table,.-sys_call_table

arch/mips/kernel/scall64-n32.S

@@ -434,4 +434,6 @@ EXPORT(sysn32_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free
 	PTR	sys_statx			/* 6330 */
+	PTR	sys_rseq
+	PTR	compat_sys_io_pgetevents
 	.size	sysn32_call_table,.-sysn32_call_table

arch/mips/kernel/scall64-o32.S

@@ -583,4 +583,6 @@ EXPORT(sys32_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
 	PTR	sys_statx
+	PTR	sys_rseq
+	PTR	compat_sys_io_pgetevents
 	.size	sys32_call_table,.-sys32_call_table

arch/mips/kernel/signal.c

@@ -801,6 +801,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		regs->regs[0] = 0;		/* Don't deal with this again.	*/
 	}
 
+	rseq_signal_deliver(regs);
+
 	if (sig_uses_siginfo(&ksig->ka, abi))
 		ret = abi->setup_rt_frame(vdso + abi->vdso->off_rt_sigreturn,
 					  ksig, regs, oldset);
@@ -868,6 +870,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
+		rseq_handle_notify_resume(regs);
 	}
 
 	user_enter();

arch/powerpc/Makefile

@@ -244,6 +244,7 @@ cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
 cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
+cpu-as-$(CONFIG_PPC_E500MC)	+= $(call as-option,-Wa$(comma)-me500mc)
 
 KBUILD_AFLAGS += $(cpu-as-y)
 KBUILD_CFLAGS += $(cpu-as-y)

arch/powerpc/include/asm/book3s/32/pgalloc.h

@@ -108,6 +108,7 @@ static inline void pgtable_free(void *table, unsigned index_size)
 }
 
 #define check_pgt_cache()	do { } while (0)
+#define get_hugepd_cache_index(x)  (x)
 
 #ifdef CONFIG_SMP
 static inline void pgtable_free_tlb(struct mmu_gather *tlb,

arch/powerpc/include/asm/book3s/64/pgtable-4k.h

@@ -49,6 +49,27 @@ static inline int hugepd_ok(hugepd_t hpd)
 }
 #define is_hugepd(hpd)		(hugepd_ok(hpd))
 
+/*
+ * 16M and 16G huge page directory tables are allocated from slab cache
+ *
+ */
+#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24)
+#define H_16G_CACHE_INDEX                                                      \
+	(PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34)
+
+static inline int get_hugepd_cache_index(int index)
+{
+	switch (index) {
+	case H_16M_CACHE_INDEX:
+		return HTLB_16M_INDEX;
+	case H_16G_CACHE_INDEX:
+		return HTLB_16G_INDEX;
+	default:
+		BUG();
+	}
+	/* should not reach */
+}
+
 #else /* !CONFIG_HUGETLB_PAGE */
 static inline int pmd_huge(pmd_t pmd) { return 0; }
 static inline int pud_huge(pud_t pud) { return 0; }

arch/powerpc/include/asm/book3s/64/pgtable-64k.h

@@ -45,8 +45,17 @@ static inline int hugepd_ok(hugepd_t hpd)
 {
 	return 0;
 }
+
 #define is_hugepd(pdep)			0
 
+/*
+ * This should never get called
+ */
+static inline int get_hugepd_cache_index(int index)
+{
+	BUG();
+}
+
 #else /* !CONFIG_HUGETLB_PAGE */
 static inline int pmd_huge(pmd_t pmd) { return 0; }
 static inline int pud_huge(pud_t pud) { return 0; }

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -287,6 +287,11 @@ enum pgtable_index {
 	PMD_INDEX,
 	PUD_INDEX,
 	PGD_INDEX,
+	/*
+	 * Below are used with 4k page size and hugetlb
+	 */
+	HTLB_16M_INDEX,
+	HTLB_16G_INDEX,
 };
 
 extern unsigned long __vmalloc_start;

arch/powerpc/include/asm/nmi.h

@@ -8,7 +8,7 @@ extern void arch_touch_nmi_watchdog(void);
 static inline void arch_touch_nmi_watchdog(void) {}
 #endif
 
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_STACKTRACE)
+#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE)
 extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
 					   bool exclude_self);
 #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace

arch/powerpc/include/asm/nohash/32/pgalloc.h

@@ -109,6 +109,7 @@ static inline void pgtable_free(void *table, unsigned index_size)
 }
 
 #define check_pgt_cache()	do { } while (0)
+#define get_hugepd_cache_index(x)	(x)
 
 #ifdef CONFIG_SMP
 static inline void pgtable_free_tlb(struct mmu_gather *tlb,

arch/powerpc/include/asm/nohash/64/pgalloc.h

@@ -141,6 +141,7 @@ static inline void pgtable_free(void *table, int shift)
 	}
 }
 
+#define get_hugepd_cache_index(x)	(x)
 #ifdef CONFIG_SMP
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 {

arch/powerpc/kernel/dt_cpu_ftrs.c

@@ -711,7 +711,8 @@ static __init void cpufeatures_cpu_quirks(void)
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
-	} else /* DD2.1 and up have DD2_1 */
+	} else if ((version & 0xffff0000) == 0x004e0000)
+		/* DD2.1 and up have DD2_1 */
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
 
 	if ((version & 0xffff0000) == 0x004e0000) {

arch/powerpc/kernel/setup-common.c

@@ -700,12 +700,19 @@ EXPORT_SYMBOL(check_legacy_ioport);
 static int ppc_panic_event(struct notifier_block *this,
                              unsigned long event, void *ptr)
 {
+	/*
+	 * panic does a local_irq_disable, but we really
+	 * want interrupts to be hard disabled.
+	 */
+	hard_irq_disable();
+
 	/*
 	 * If firmware-assisted dump has been registered then trigger
 	 * firmware-assisted dump and let firmware handle everything else.
 	 */
 	crash_fadump(NULL, ptr);
-	ppc_md.panic(ptr);  /* May not return */
+	if (ppc_md.panic)
+		ppc_md.panic(ptr);  /* May not return */
 	return NOTIFY_DONE;
 }
 
@@ -716,7 +723,8 @@ static struct notifier_block ppc_panic_block = {
 
 void __init setup_panic(void)
 {
-	if (!ppc_md.panic)
+	/* PPC64 always does a hard irq disable in its panic handler */
+	if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic)
 		return;
 	atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
 }

arch/powerpc/kernel/setup_64.c

@@ -387,6 +387,14 @@ void early_setup_secondary(void)
 
 #endif /* CONFIG_SMP */
 
+void panic_smp_self_stop(void)
+{
+	hard_irq_disable();
+	spin_begin();
+	while (1)
+		spin_cpu_relax();
+}
+
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
 static bool use_spinloop(void)
 {

arch/powerpc/kernel/signal.c

@@ -134,7 +134,7 @@ static void do_signal(struct task_struct *tsk)
 	/* Re-enable the breakpoints for the signal stack */
 	thread_change_pc(tsk, tsk->thread.regs);
 
-	rseq_signal_deliver(tsk->thread.regs);
+	rseq_signal_deliver(&ksig, tsk->thread.regs);
 
 	if (is32) {
         	if (ksig.ka.sa.sa_flags & SA_SIGINFO)
@@ -170,7 +170,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
-		rseq_handle_notify_resume(regs);
+		rseq_handle_notify_resume(NULL, regs);
 	}
 
 	user_enter();

arch/powerpc/kernel/smp.c

@@ -600,9 +600,6 @@ static void nmi_stop_this_cpu(struct pt_regs *regs)
 	nmi_ipi_busy_count--;
 	nmi_ipi_unlock();
 
-	/* Remove this CPU */
-	set_cpu_online(smp_processor_id(), false);
-
 	spin_begin();
 	while (1)
 		spin_cpu_relax();
@@ -617,9 +614,6 @@ void smp_send_stop(void)
 
 static void stop_this_cpu(void *dummy)
 {
-	/* Remove this CPU */
-	set_cpu_online(smp_processor_id(), false);
-
 	hard_irq_disable();
 	spin_begin();
 	while (1)

arch/powerpc/kernel/stacktrace.c

@@ -196,7 +196,7 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk,
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable);
 #endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
 
-#ifdef CONFIG_PPC_BOOK3S_64
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
 static void handle_backtrace_ipi(struct pt_regs *regs)
 {
 	nmi_cpu_backtrace(regs);
@@ -242,4 +242,4 @@ void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
 {
 	nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi);
 }
-#endif /* CONFIG_PPC64 */
+#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */

arch/powerpc/mm/hugetlbpage.c

@@ -337,7 +337,8 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
 	else
-		pgtable_free_tlb(tlb, hugepte, pdshift - shift);
+		pgtable_free_tlb(tlb, hugepte,
+				 get_hugepd_cache_index(pdshift - shift));
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,

arch/powerpc/mm/pgtable-book3s64.c

@@ -409,6 +409,18 @@ static inline void pgtable_free(void *table, int index)
 	case PUD_INDEX:
 		kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table);
 		break;
+#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
+		/* 16M hugepd directory at pud level */
+	case HTLB_16M_INDEX:
+		BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
+		kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
+		break;
+		/* 16G hugepd directory at the pgd level */
+	case HTLB_16G_INDEX:
+		BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
+		kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
+		break;
+#endif
 		/* We don't free pgd table via RCU callback */
 	default:
 		BUG();

arch/powerpc/mm/tlb-radix.c

@@ -689,22 +689,17 @@ EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
 static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
 static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
 
-void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
-		     unsigned long end)
+static inline void __radix__flush_tlb_range(struct mm_struct *mm,
+					unsigned long start, unsigned long end,
+					bool flush_all_sizes)
 
 {
-	struct mm_struct *mm = vma->vm_mm;
 	unsigned long pid;
 	unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
 	unsigned long page_size = 1UL << page_shift;
 	unsigned long nr_pages = (end - start) >> page_shift;
 	bool local, full;
 
-#ifdef CONFIG_HUGETLB_PAGE
-	if (is_vm_hugetlb_page(vma))
-		return radix__flush_hugetlb_tlb_range(vma, start, end);
-#endif
-
 	pid = mm->context.id;
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		return;
@@ -738,37 +733,64 @@ is_local:
 				_tlbie_pid(pid, RIC_FLUSH_TLB);
 		}
 	} else {
-		bool hflush = false;
+		bool hflush = flush_all_sizes;
+		bool gflush = flush_all_sizes;
 		unsigned long hstart, hend;
+		unsigned long gstart, gend;
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT;
-		hend = end >> HPAGE_PMD_SHIFT;
-		if (hstart < hend) {
-			hstart <<= HPAGE_PMD_SHIFT;
-			hend <<= HPAGE_PMD_SHIFT;
+		if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
 			hflush = true;
+
+		if (hflush) {
+			hstart = (start + PMD_SIZE - 1) & PMD_MASK;
+			hend = end & PMD_MASK;
+			if (hstart == hend)
+				hflush = false;
+		}
+
+		if (gflush) {
+			gstart = (start + PUD_SIZE - 1) & PUD_MASK;
+			gend = end & PUD_MASK;
+			if (gstart == gend)
+				gflush = false;
 		}
-#endif
 
 		asm volatile("ptesync": : :"memory");
 		if (local) {
 			__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
 			if (hflush)
 				__tlbiel_va_range(hstart, hend, pid,
-						HPAGE_PMD_SIZE, MMU_PAGE_2M);
+						PMD_SIZE, MMU_PAGE_2M);
+			if (gflush)
+				__tlbiel_va_range(gstart, gend, pid,
+						PUD_SIZE, MMU_PAGE_1G);
 			asm volatile("ptesync": : :"memory");
 		} else {
 			__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
 			if (hflush)
 				__tlbie_va_range(hstart, hend, pid,
-						HPAGE_PMD_SIZE, MMU_PAGE_2M);
+						PMD_SIZE, MMU_PAGE_2M);
+			if (gflush)
+				__tlbie_va_range(gstart, gend, pid,
+						PUD_SIZE, MMU_PAGE_1G);
 			fixup_tlbie();
 			asm volatile("eieio; tlbsync; ptesync": : :"memory");
 		}
 	}
 	preempt_enable();
 }
+
+void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end)
+
+{
+#ifdef CONFIG_HUGETLB_PAGE
+	if (is_vm_hugetlb_page(vma))
+		return radix__flush_hugetlb_tlb_range(vma, start, end);
+#endif
+
+	__radix__flush_tlb_range(vma->vm_mm, start, end, false);
+}
 EXPORT_SYMBOL(radix__flush_tlb_range);
 
 static int radix_get_mmu_psize(int page_size)
@@ -837,6 +859,8 @@ void radix__tlb_flush(struct mmu_gather *tlb)
 	int psize = 0;
 	struct mm_struct *mm = tlb->mm;
 	int page_size = tlb->page_size;
+	unsigned long start = tlb->start;
+	unsigned long end = tlb->end;
 
 	/*
 	 * if page size is not something we understand, do a full mm flush
@@ -847,15 +871,45 @@ void radix__tlb_flush(struct mmu_gather *tlb)
 	 */
 	if (tlb->fullmm) {
 		__flush_all_mm(mm, true);
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+	} else if (mm_tlb_flush_nested(mm)) {
+		/*
+		 * If there is a concurrent invalidation that is clearing ptes,
+		 * then it's possible this invalidation will miss one of those
+		 * cleared ptes and miss flushing the TLB. If this invalidate
+		 * returns before the other one flushes TLBs, that can result
+		 * in it returning while there are still valid TLBs inside the
+		 * range to be invalidated.
+		 *
+		 * See mm/memory.c:tlb_finish_mmu() for more details.
+		 *
+		 * The solution to this is ensure the entire range is always
+		 * flushed here. The problem for powerpc is that the flushes
+		 * are page size specific, so this "forced flush" would not
+		 * do the right thing if there are a mix of page sizes in
+		 * the range to be invalidated. So use __flush_tlb_range
+		 * which invalidates all possible page sizes in the range.
+		 *
+		 * PWC flush probably is not be required because the core code
+		 * shouldn't free page tables in this path, but accounting
+		 * for the possibility makes us a bit more robust.
+		 *
+		 * need_flush_all is an uncommon case because page table
+		 * teardown should be done with exclusive locks held (but
+		 * after locks are dropped another invalidate could come
+		 * in), it could be optimized further if necessary.
+		 */
+		if (!tlb->need_flush_all)
+			__radix__flush_tlb_range(mm, start, end, true);
+		else
+			radix__flush_all_mm(mm);
+#endif
 	} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
 		if (!tlb->need_flush_all)
 			radix__flush_tlb_mm(mm);
 		else
 			radix__flush_all_mm(mm);
 	} else {
-		unsigned long start = tlb->start;
-		unsigned long end = tlb->end;
-
 		if (!tlb->need_flush_all)
 			radix__flush_tlb_range_psize(mm, start, end, psize);
 		else
@@ -1043,6 +1097,8 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 		for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
 			if (sib == cpu)
 				continue;
+			if (!cpu_possible(sib))
+				continue;
 			if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
 				flush = true;
 		}

arch/x86/Makefile

@@ -258,11 +258,6 @@ archscripts: scripts_basic
 archheaders:
 	$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
 
-archprepare:
-ifeq ($(CONFIG_KEXEC_FILE),y)
-	$(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c
-endif
-
 ###
 # Kernel objects
 
@@ -327,7 +322,6 @@ archclean:
 	$(Q)rm -rf $(objtree)/arch/x86_64
 	$(Q)$(MAKE) $(clean)=$(boot)
 	$(Q)$(MAKE) $(clean)=arch/x86/tools
-	$(Q)$(MAKE) $(clean)=arch/x86/purgatory
 
 define archhelp
   echo  '* bzImage      - Compressed kernel image (arch/x86/boot/bzImage)'

arch/x86/boot/compressed/eboot.c

@@ -118,7 +118,7 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 	void *romimage;
 
 	status = efi_call_proto(efi_pci_io_protocol, attributes, pci,
-				EfiPciIoAttributeOperationGet, 0, 0,
+				EfiPciIoAttributeOperationGet, 0ULL,
 				&attributes);
 	if (status != EFI_SUCCESS)
 		return status;

arch/x86/entry/common.c

@@ -164,7 +164,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		if (cached_flags & _TIF_NOTIFY_RESUME) {
 			clear_thread_flag(TIF_NOTIFY_RESUME);
 			tracehook_notify_resume(regs);
-			rseq_handle_notify_resume(regs);
+			rseq_handle_notify_resume(NULL, regs);
 		}
 
 		if (cached_flags & _TIF_USER_RETURN_NOTIFY)

arch/x86/include/asm/barrier.h

@@ -38,7 +38,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 {
 	unsigned long mask;
 
-	asm ("cmp %1,%2; sbb %0,%0;"
+	asm volatile ("cmp %1,%2; sbb %0,%0;"
 			:"=r" (mask)
 			:"g"(size),"r" (index)
 			:"cc");

arch/x86/include/asm/vmx.h

@@ -114,6 +114,7 @@
 #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 #define VMX_MISC_ACTIVITY_HLT			0x00000040
+#define VMX_MISC_ZERO_LEN_INS			0x40000000
 
 /* VMFUNC functions */
 #define VMX_VMFUNC_EPTP_SWITCHING               0x00000001
@@ -351,11 +352,13 @@ enum vmcs_field {
 #define VECTORING_INFO_VALID_MASK       	INTR_INFO_VALID_MASK
 
 #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
+#define INTR_TYPE_RESERVED              (1 << 8) /* reserved */
 #define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
 #define INTR_TYPE_HARD_EXCEPTION	(3 << 8) /* processor exception */
 #define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
 #define INTR_TYPE_PRIV_SW_EXCEPTION	(5 << 8) /* ICE breakpoint - undocumented */
 #define INTR_TYPE_SOFT_EXCEPTION	(6 << 8) /* software exception */
+#define INTR_TYPE_OTHER_EVENT           (7 << 8) /* other event */
 
 /* GUEST_INTERRUPTIBILITY_INFO flags. */
 #define GUEST_INTR_STATE_STI		0x00000001

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/reboot.h>
+#include <linux/memory.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -392,6 +393,51 @@ extern int uv_hub_info_version(void)
 }
 EXPORT_SYMBOL(uv_hub_info_version);
 
+/* Default UV memory block size is 2GB */
+static unsigned long mem_block_size = (2UL << 30);
+
+/* Kernel parameter to specify UV mem block size */
+static int parse_mem_block_size(char *ptr)
+{
+	unsigned long size = memparse(ptr, NULL);
+
+	/* Size will be rounded down by set_block_size() below */
+	mem_block_size = size;
+	return 0;
+}
+early_param("uv_memblksize", parse_mem_block_size);
+
+static __init int adj_blksize(u32 lgre)
+{
+	unsigned long base = (unsigned long)lgre << UV_GAM_RANGE_SHFT;
+	unsigned long size;
+
+	for (size = mem_block_size; size > MIN_MEMORY_BLOCK_SIZE; size >>= 1)
+		if (IS_ALIGNED(base, size))
+			break;
+
+	if (size >= mem_block_size)
+		return 0;
+
+	mem_block_size = size;
+	return 1;
+}
+
+static __init void set_block_size(void)
+{
+	unsigned int order = ffs(mem_block_size);
+
+	if (order) {
+		/* adjust for ffs return of 1..64 */
+		set_memory_block_size_order(order - 1);
+		pr_info("UV: mem_block_size set to 0x%lx\n", mem_block_size);
+	} else {
+		/* bad or zero value, default to 1UL << 31 (2GB) */
+		pr_err("UV: mem_block_size error with 0x%lx\n", mem_block_size);
+		set_memory_block_size_order(31);
+	}
+}
+
 /* Build GAM range lookup table: */
 static __init void build_uv_gr_table(void)
 {
@@ -1180,23 +1226,30 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
 					<< UV_GAM_RANGE_SHFT);
 		int order = 0;
 		char suffix[] = " KMGTPE";
+		int flag = ' ';
 
 		while (size > 9999 && order < sizeof(suffix)) {
 			size /= 1024;
 			order++;
 		}
 
+		/* adjust max block size to current range start */
+		if (gre->type == 1 || gre->type == 2)
+			if (adj_blksize(lgre))
+				flag = '*';
+
 		if (!index) {
 			pr_info("UV: GAM Range Table...\n");
-			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
+			pr_info("UV:  # %20s %14s %6s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
 		}
-		pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d   %04x  %02x %02x\n",
+		pr_info("UV: %2d: 0x%014lx-0x%014lx%c %5lu%c %3d   %04x  %02x %02x\n",
 			index++,
 			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
 			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
-			size, suffix[order],
+			flag, size, suffix[order],
 			gre->type, gre->nasid, gre->sockid, gre->pnode);
 
+		/* update to next range start */
 		lgre = gre->limit;
 		if (sock_min > gre->sockid)
 			sock_min = gre->sockid;
@@ -1427,6 +1480,7 @@ static void __init uv_system_init_hub(void)
 
 	build_socket_tables();
 	build_uv_gr_table();
+	set_block_size();
 	uv_init_hub_info(&hub_info);
 	uv_possible_blades = num_possible_nodes();
 	if (!_node_to_pnode)

arch/x86/kernel/cpu/bugs.c

@@ -27,6 +27,7 @@
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/intel-family.h>
+#include <asm/hypervisor.h>
 
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
@@ -664,6 +665,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		if (boot_cpu_has(X86_FEATURE_PTI))
 			return sprintf(buf, "Mitigation: PTI\n");
 
+		if (hypervisor_is_type(X86_HYPER_XEN_PV))
+			return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n");
+
 		break;
 
 	case X86_BUG_SPECTRE_V1:

arch/x86/kernel/cpu/cacheinfo.c

@@ -671,7 +671,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
 			num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
 
 		if (num_sharing_cache) {
-			int bits = get_count_order(num_sharing_cache) - 1;
+			int bits = get_count_order(num_sharing_cache);
 
 			per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
 		}

arch/x86/kernel/cpu/common.c

@@ -1,3 +1,6 @@
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
 #include <linux/bootmem.h>
 #include <linux/linkage.h>
 #include <linux/bitops.h>

arch/x86/kernel/cpu/mcheck/mce-severity.c

@@ -160,6 +160,11 @@ static struct severity {
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
 		USER
 		),
+	MCESEV(
+		PANIC, "Data load in unrecoverable area of kernel",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+		KERNEL
+		),
 #endif
 	MCESEV(
 		PANIC, "Action required: unknown MCACOD",

arch/x86/kernel/cpu/mcheck/mce.c

@@ -772,23 +772,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
 static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			  struct pt_regs *regs)
 {
-	int i, ret = 0;
 	char *tmp;
+	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		m->status = mce_rdmsrl(msr_ops.status(i));
-		if (m->status & MCI_STATUS_VAL) {
-			__set_bit(i, validp);
-			if (quirk_no_way_out)
-				quirk_no_way_out(i, m, regs);
-		}
+		if (!(m->status & MCI_STATUS_VAL))
+			continue;
+
+		__set_bit(i, validp);
+		if (quirk_no_way_out)
+			quirk_no_way_out(i, m, regs);
 
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			mce_read_aux(m, i);
 			*msg = tmp;
-			ret = 1;
+			return 1;
 		}
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -1205,13 +1207,18 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		lmce = m.mcgstatus & MCG_STATUS_LMCES;
 
 	/*
+	 * Local machine check may already know that we have to panic.
+	 * Broadcast machine check begins rendezvous in mce_start()
 	 * Go through all banks in exclusion of the other CPUs. This way we
 	 * don't report duplicated events on shared banks because the first one
-	 * to see it will clear it. If this is a Local MCE, then no need to
-	 * perform rendezvous.
+	 * to see it will clear it.
 	 */
-	if (!lmce)
+	if (lmce) {
+		if (no_way_out)
+			mce_panic("Fatal local machine check", &m, msg);
+	} else {
 		order = mce_start(&no_way_out);
+	}
 
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);
@@ -1287,12 +1294,17 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 			no_way_out = worst >= MCE_PANIC_SEVERITY;
 	} else {
 		/*
-		 * Local MCE skipped calling mce_reign()
-		 * If we found a fatal error, we need to panic here.
+		 * If there was a fatal machine check we should have
+		 * already called mce_panic earlier in this function.
+		 * Since we re-read the banks, we might have found
+		 * something new. Check again to see if we found a
+		 * fatal error. We call "mce_severity()" again to
+		 * make sure we have the right "msg".
 		 */
-		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
-			mce_panic("Machine check from unknown source",
-				NULL, NULL);
+		if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) {
+			mce_severity(&m, cfg->tolerant, &msg, true);
+			mce_panic("Local fatal machine check!", &m, msg);
+		}
 	}
 
 	/*

arch/x86/kernel/cpu/microcode/intel.c

@@ -190,8 +190,11 @@ static void save_microcode_patch(void *data, unsigned int size)
 			p = memdup_patch(data, size);
 			if (!p)
 				pr_err("Error allocating buffer %p\n", data);
-			else
+			else {
 				list_replace(&iter->plist, &p->plist);
+				kfree(iter->data);
+				kfree(iter);
+			}
 		}
 	}
 

arch/x86/kernel/head64.c

@@ -44,7 +44,7 @@ static unsigned int __initdata next_early_pgt;
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
 #ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled __initdata;
+unsigned int __pgtable_l5_enabled __ro_after_init;
 unsigned int pgdir_shift __ro_after_init = 39;
 EXPORT_SYMBOL(pgdir_shift);
 unsigned int ptrs_per_p4d __ro_after_init = 1;

arch/x86/kernel/quirks.c

@@ -645,12 +645,19 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
 /* Skylake */
 static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
 {
-	u32 capid0;
+	u32 capid0, capid5;
 
 	pci_read_config_dword(pdev, 0x84, &capid0);
+	pci_read_config_dword(pdev, 0x98, &capid5);
 
-	if ((capid0 & 0xc0) == 0xc0)
+	/*
+	 * CAPID0{7:6} indicate whether this is an advanced RAS SKU
+	 * CAPID5{8:5} indicate that various NVDIMM usage modes are
+	 * enabled, so memory machine check recovery is also enabled.
+	 */
+	if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0))
 		static_branch_inc(&mcsafe_key);
+
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap);

arch/x86/kernel/signal.c

@@ -692,7 +692,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 	 * Increment event counter and perform fixup for the pre-signal
 	 * frame.
 	 */
-	rseq_signal_deliver(regs);
+	rseq_signal_deliver(ksig, regs);
 
 	/* Set up the stack frame */
 	if (is_ia32_frame(ksig)) {

arch/x86/kernel/traps.c

@@ -835,16 +835,18 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
 
-	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
-		return;
 	cond_local_irq_enable(regs);
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs, trapnr)) {
-			task->thread.error_code = error_code;
-			task->thread.trap_nr = trapnr;
+		if (fixup_exception(regs, trapnr))
+			return;
+
+		task->thread.error_code = error_code;
+		task->thread.trap_nr = trapnr;
+
+		if (notify_die(DIE_TRAP, str, regs, error_code,
+					trapnr, SIGFPE) != NOTIFY_STOP)
 			die(str, regs, error_code);
-		}
 		return;
 	}
 

arch/x86/kernel/uprobes.c

@@ -293,7 +293,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 	insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
 	/* has the side-effect of processing the entire instruction */
 	insn_get_length(insn);
-	if (WARN_ON_ONCE(!insn_complete(insn)))
+	if (!insn_complete(insn))
 		return -ENOEXEC;
 
 	if (is_prefix_bad(insn))

arch/x86/kvm/vmx.c

@@ -1705,6 +1705,17 @@ static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu)
 		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
 }
 
+static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS;
+}
+
+static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.procbased_ctls_high &
+			CPU_BASED_MONITOR_TRAP_FLAG;
+}
+
 static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
 {
 	return vmcs12->cpu_based_vm_exec_control & bit;
@@ -11620,6 +11631,62 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	    !nested_cr3_valid(vcpu, vmcs12->host_cr3))
 		return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
 
+	/*
+	 * From the Intel SDM, volume 3:
+	 * Fields relevant to VM-entry event injection must be set properly.
+	 * These fields are the VM-entry interruption-information field, the
+	 * VM-entry exception error code, and the VM-entry instruction length.
+	 */
+	if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
+		u32 intr_info = vmcs12->vm_entry_intr_info_field;
+		u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
+		u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
+		bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
+		bool should_have_error_code;
+		bool urg = nested_cpu_has2(vmcs12,
+					   SECONDARY_EXEC_UNRESTRICTED_GUEST);
+		bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;
+
+		/* VM-entry interruption-info field: interruption type */
+		if (intr_type == INTR_TYPE_RESERVED ||
+		    (intr_type == INTR_TYPE_OTHER_EVENT &&
+		     !nested_cpu_supports_monitor_trap_flag(vcpu)))
+			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+		/* VM-entry interruption-info field: vector */
+		if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
+		    (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
+		    (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
+			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+		/* VM-entry interruption-info field: deliver error code */
+		should_have_error_code =
+			intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
+			x86_exception_has_error_code(vector);
+		if (has_error_code != should_have_error_code)
+			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+		/* VM-entry exception error code */
+		if (has_error_code &&
+		    vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))
+			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+		/* VM-entry interruption-info field: reserved bits */
+		if (intr_info & INTR_INFO_RESVD_BITS_MASK)
+			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+		/* VM-entry instruction length */
+		switch (intr_type) {
+		case INTR_TYPE_SOFT_EXCEPTION:
+		case INTR_TYPE_SOFT_INTR:
+		case INTR_TYPE_PRIV_SW_EXCEPTION:
+			if ((vmcs12->vm_entry_instruction_len > 15) ||
+			    (vmcs12->vm_entry_instruction_len == 0 &&
+			     !nested_cpu_has_zero_length_injection(vcpu)))
+				return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+		}
+	}
+
 	return 0;
 }
 

arch/x86/kvm/x86.h

@@ -110,6 +110,15 @@ static inline bool is_la57_mode(struct kvm_vcpu *vcpu)
 #endif
 }
 
+static inline bool x86_exception_has_error_code(unsigned int vector)
+{
+	static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
+			BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) |
+			BIT(PF_VECTOR) | BIT(AC_VECTOR);
+
+	return (1U << vector) & exception_has_error_code;
+}
+
 static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;

arch/x86/mm/init_64.c

@@ -1350,16 +1350,28 @@ int kern_addr_valid(unsigned long addr)
 /* Amount of ram needed to start using large blocks */
 #define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)
 
+/* Adjustable memory block size */
+static unsigned long set_memory_block_size;
+int __init set_memory_block_size_order(unsigned int order)
+{
+	unsigned long size = 1UL << order;
+
+	if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE)
+		return -EINVAL;
+
+	set_memory_block_size = size;
+	return 0;
+}
+
 static unsigned long probe_memory_block_size(void)
 {
 	unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
 	unsigned long bz;
 
-	/* If this is UV system, always set 2G block size */
-	if (is_uv_system()) {
-		bz = MAX_BLOCK_SIZE;
+	/* If memory block size has been set, then use it */
+	bz = set_memory_block_size;
+	if (bz)
 		goto done;
-	}
 
 	/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
 	if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {

arch/x86/xen/enlighten.c

@@ -64,6 +64,13 @@ struct shared_info xen_dummy_shared_info;
 __read_mostly int xen_have_vector_callback;
 EXPORT_SYMBOL_GPL(xen_have_vector_callback);
 
+/*
+ * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
+ * before clearing the bss.
+ */
+uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
+EXPORT_SYMBOL(xen_start_flags);
+
 /*
  * Point at some empty memory to start with. We map the real shared_info
  * page as soon as fixmap is up and running.

arch/x86/xen/enlighten_pv.c

@@ -1203,6 +1203,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		return;
 
 	xen_domain_type = XEN_PV_DOMAIN;
+	xen_start_flags = xen_start_info->flags;
 
 	xen_setup_features();
 

arch/x86/xen/enlighten_pvh.c

@@ -97,6 +97,7 @@ void __init xen_prepare_pvh(void)
 	}
 
 	xen_pvh = 1;
+	xen_start_flags = pvh_start_info.flags;
 
 	msr = cpuid_ebx(xen_cpuid_base() + 2);
 	pfn = __pa(hypercall_page);

arch/x86/xen/smp_pv.c

@@ -32,6 +32,7 @@
 #include <xen/interface/vcpu.h>
 #include <xen/interface/xenpmu.h>
 
+#include <asm/spec-ctrl.h>
 #include <asm/xen/interface.h>
 #include <asm/xen/hypercall.h>
 
@@ -70,6 +71,8 @@ static void cpu_bringup(void)
 	cpu_data(cpu).x86_max_cores = 1;
 	set_cpu_sibling_map(cpu);
 
+	speculative_store_bypass_ht_init();
+
 	xen_setup_cpu_clockevents();
 
 	notify_cpu_starting(cpu);
@@ -250,6 +253,8 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 	}
 	set_cpu_sibling_map(0);
 
+	speculative_store_bypass_ht_init();
+
 	xen_pmu_init(0);
 
 	if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0))

block/bio.c

@@ -1807,9 +1807,6 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
-	if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
-		bio->bi_next = NULL;
-
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that

block/blk-core.c

@@ -273,10 +273,6 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	/*
-	 * XXX this code looks suspicious - it's not consistent with advancing
-	 * req->bio in caller
-	 */
 	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
 		bio_endio(bio);
 }
@@ -3081,10 +3077,8 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		struct bio *bio = req->bio;
 		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_iter.bi_size) {
+		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
-			bio->bi_next = NULL;
-		}
 
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);

block/blk-mq-debugfs.c

@@ -356,7 +356,7 @@ static const char *const blk_mq_rq_state_name_array[] = {
 
 static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
 {
-	if (WARN_ON_ONCE((unsigned int)rq_state >
+	if (WARN_ON_ONCE((unsigned int)rq_state >=
 			 ARRAY_SIZE(blk_mq_rq_state_name_array)))
 		return "(?)";
 	return blk_mq_rq_state_name_array[rq_state];

block/blk-mq.c

@@ -781,7 +781,6 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
 	}
 
-	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_add_timer(req);
 }
 

block/blk-softirq.c

@@ -144,6 +144,7 @@ do_local:
 
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(__blk_complete_request);
 
 /**
  * blk_complete_request - end I/O on a request

block/blk-timeout.c

@@ -210,6 +210,7 @@ void blk_add_timer(struct request *req)
 	if (!req->timeout)
 		req->timeout = q->rq_timeout;
 
+	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_rq_set_deadline(req, jiffies + req->timeout);
 
 	/*

block/sed-opal.c

@@ -877,7 +877,7 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 		return 0;
 	}
 
-	if (n > resp->num) {
+	if (n >= resp->num) {
 		pr_debug("Response has %d tokens. Can't access %d\n",
 			 resp->num, n);
 		return 0;
@@ -916,7 +916,7 @@ static u64 response_get_u64(const struct parsed_resp *resp, int n)
 		return 0;
 	}
 
-	if (n > resp->num) {
+	if (n >= resp->num) {
 		pr_debug("Response has %d tokens. Can't access %d\n",
 			 resp->num, n);
 		return 0;

crypto/morus640.c

@@ -274,8 +274,9 @@ static void crypto_morus640_decrypt_chunk(struct morus640_state *state, u8 *dst,
 		union morus640_block_in tail;
 
 		memcpy(tail.bytes, src, size);
+		memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);
 
-		crypto_morus640_load_a(&m, src);
+		crypto_morus640_load_a(&m, tail.bytes);
 		crypto_morus640_core(state, &m);
 		crypto_morus640_store_a(tail.bytes, &m);
 		memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);

crypto/sha3_generic.c

@@ -152,7 +152,7 @@ static SHA3_INLINE void keccakf_round(u64 st[25])
 	st[24] ^= bc[ 4];
 }
 
-static void __optimize("O3") keccakf(u64 st[25])
+static void keccakf(u64 st[25])
 {
 	int round;
 

drivers/acpi/acpi_lpss.c

@@ -22,6 +22,7 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/pwm.h>
+#include <linux/suspend.h>
 #include <linux/delay.h>
 
 #include "internal.h"
@@ -946,9 +947,10 @@ static void lpss_iosf_exit_d3_state(void)
 	mutex_unlock(&lpss_iosf_mutex);
 }
 
-static int acpi_lpss_suspend(struct device *dev, bool wakeup)
+static int acpi_lpss_suspend(struct device *dev, bool runtime)
 {
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	bool wakeup = runtime || device_may_wakeup(dev);
 	int ret;
 
 	if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
@@ -961,13 +963,14 @@ static int acpi_lpss_suspend(struct device *dev, bool wakeup)
 	 * wrong status for devices being about to be powered off. See
 	 * lpss_iosf_enter_d3_state() for further information.
 	 */
-	if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+	if ((runtime || !pm_suspend_via_firmware()) &&
+	    lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
 		lpss_iosf_enter_d3_state();
 
 	return ret;
 }
 
-static int acpi_lpss_resume(struct device *dev)
+static int acpi_lpss_resume(struct device *dev, bool runtime)
 {
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
 	int ret;
@@ -976,7 +979,8 @@ static int acpi_lpss_resume(struct device *dev)
 	 * This call is kept first to be in symmetry with
 	 * acpi_lpss_runtime_suspend() one.
 	 */
-	if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+	if ((runtime || !pm_resume_via_firmware()) &&
+	    lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
 		lpss_iosf_exit_d3_state();
 
 	ret = acpi_dev_resume(dev);
@@ -1000,12 +1004,12 @@ static int acpi_lpss_suspend_late(struct device *dev)
 		return 0;
 
 	ret = pm_generic_suspend_late(dev);
-	return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
+	return ret ? ret : acpi_lpss_suspend(dev, false);
 }
 
 static int acpi_lpss_resume_early(struct device *dev)
 {
-	int ret = acpi_lpss_resume(dev);
+	int ret = acpi_lpss_resume(dev, false);
 
 	return ret ? ret : pm_generic_resume_early(dev);
 }
@@ -1020,7 +1024,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev)
 
 static int acpi_lpss_runtime_resume(struct device *dev)
 {
-	int ret = acpi_lpss_resume(dev);
+	int ret = acpi_lpss_resume(dev, true);
 
 	return ret ? ret : pm_generic_runtime_resume(dev);
 }

drivers/acpi/ec.c

@@ -2037,6 +2037,17 @@ static inline void acpi_ec_query_exit(void)
 	}
 }
 
+static const struct dmi_system_id acpi_ec_no_wakeup[] = {
+	{
+		.ident = "Thinkpad X1 Carbon 6th",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "20KGS3JF01"),
+		},
+	},
+	{ },
+};
+
 int __init acpi_ec_init(void)
 {
 	int result;
@@ -2047,6 +2058,15 @@ int __init acpi_ec_init(void)
 	if (result)
 		return result;
 
+	/*
+	 * Disable EC wakeup on following systems to prevent periodic
+	 * wakeup from EC GPE.
+	 */
+	if (dmi_check_system(acpi_ec_no_wakeup)) {
+		ec_no_wakeup = true;
+		pr_debug("Disabling EC wakeup on suspend-to-idle\n");
+	}
+
 	/* Drivers must be started after acpi_ec_query_init() */
 	dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver);
 	/*

drivers/base/core.c

@@ -236,6 +236,13 @@ struct device_link *device_link_add(struct device *consumer,
 			link->rpm_active = true;
 		}
 		pm_runtime_new_link(consumer);
+		/*
+		 * If the link is being added by the consumer driver at probe
+		 * time, balance the decrementation of the supplier's runtime PM
+		 * usage counter after consumer probe in driver_probe_device().
+		 */
+		if (consumer->links.status == DL_DEV_PROBING)
+			pm_runtime_get_noresume(supplier);
 	}
 	get_device(supplier);
 	link->supplier = supplier;
@@ -255,12 +262,12 @@ struct device_link *device_link_add(struct device *consumer,
 			switch (consumer->links.status) {
 			case DL_DEV_PROBING:
 				/*
-				 * Balance the decrementation of the supplier's
-				 * runtime PM usage counter after consumer probe
-				 * in driver_probe_device().
+				 * Some callers expect the link creation during
+				 * consumer driver probe to resume the supplier
+				 * even without DL_FLAG_RPM_ACTIVE.
 				 */
 				if (flags & DL_FLAG_PM_RUNTIME)
-					pm_runtime_get_sync(supplier);
+					pm_runtime_resume(supplier);
 
 				link->status = DL_STATE_CONSUMER_PROBE;
 				break;

drivers/block/nbd.c

@@ -76,6 +76,7 @@ struct link_dead_args {
 #define NBD_HAS_CONFIG_REF		4
 #define NBD_BOUND			5
 #define NBD_DESTROY_ON_DISCONNECT	6
+#define NBD_DISCONNECT_ON_CLOSE 	7
 
 struct nbd_config {
 	u32 flags;
@@ -138,6 +139,7 @@ static void nbd_config_put(struct nbd_device *nbd);
 static void nbd_connect_reply(struct genl_info *info, int index);
 static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
 static void nbd_dead_link_work(struct work_struct *work);
+static void nbd_disconnect_and_put(struct nbd_device *nbd);
 
 static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 {
@@ -1305,6 +1307,12 @@ out:
 static void nbd_release(struct gendisk *disk, fmode_t mode)
 {
 	struct nbd_device *nbd = disk->private_data;
+	struct block_device *bdev = bdget_disk(disk, 0);
+
+	if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
+			bdev->bd_openers == 0)
+		nbd_disconnect_and_put(nbd);
+
 	nbd_config_put(nbd);
 	nbd_put(nbd);
 }
@@ -1705,6 +1713,10 @@ again:
 				&config->runtime_flags);
 			put_dev = true;
 		}
+		if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+			set_bit(NBD_DISCONNECT_ON_CLOSE,
+				&config->runtime_flags);
+		}
 	}
 
 	if (info->attrs[NBD_ATTR_SOCKETS]) {
@@ -1749,6 +1761,17 @@ out:
 	return ret;
 }
 
+static void nbd_disconnect_and_put(struct nbd_device *nbd)
+{
+	mutex_lock(&nbd->config_lock);
+	nbd_disconnect(nbd);
+	nbd_clear_sock(nbd);
+	mutex_unlock(&nbd->config_lock);
+	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+			       &nbd->config->runtime_flags))
+		nbd_config_put(nbd);
+}
+
 static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nbd_device *nbd;
@@ -1781,13 +1804,7 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 		nbd_put(nbd);
 		return 0;
 	}
-	mutex_lock(&nbd->config_lock);
-	nbd_disconnect(nbd);
-	nbd_clear_sock(nbd);
-	mutex_unlock(&nbd->config_lock);
-	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
-			       &nbd->config->runtime_flags))
-		nbd_config_put(nbd);
+	nbd_disconnect_and_put(nbd);
 	nbd_config_put(nbd);
 	nbd_put(nbd);
 	return 0;
@@ -1798,7 +1815,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	struct nbd_device *nbd = NULL;
 	struct nbd_config *config;
 	int index;
-	int ret = -EINVAL;
+	int ret = 0;
 	bool put_dev = false;
 
 	if (!netlink_capable(skb, CAP_SYS_ADMIN))
@@ -1838,6 +1855,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	    !nbd->task_recv) {
 		dev_err(nbd_to_dev(nbd),
 			"not configured, cannot reconfigure\n");
+		ret = -EINVAL;
 		goto out;
 	}
 
@@ -1862,6 +1880,14 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 					       &config->runtime_flags))
 				refcount_inc(&nbd->refs);
 		}
+
+		if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+			set_bit(NBD_DISCONNECT_ON_CLOSE,
+					&config->runtime_flags);
+		} else {
+			clear_bit(NBD_DISCONNECT_ON_CLOSE,
+					&config->runtime_flags);
+		}
 	}
 
 	if (info->attrs[NBD_ATTR_SOCKETS]) {

drivers/block/null_blk.c

@@ -1365,7 +1365,7 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
 static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
 {
 	pr_info("null: rq %p timed out\n", rq);
-	blk_mq_complete_request(rq);
+	__blk_complete_request(rq);
 	return BLK_EH_DONE;
 }
 

drivers/char/hw_random/core.c

@@ -516,11 +516,18 @@ EXPORT_SYMBOL_GPL(hwrng_register);
 
 void hwrng_unregister(struct hwrng *rng)
 {
+	int err;
+
 	mutex_lock(&rng_mutex);
 
 	list_del(&rng->list);
-	if (current_rng == rng)
-		enable_best_rng();
+	if (current_rng == rng) {
+		err = enable_best_rng();
+		if (err) {
+			drop_current_rng();
+			cur_rng_set_by_user = 0;
+		}
+	}
 
 	if (list_empty(&rng_list)) {
 		mutex_unlock(&rng_mutex);

drivers/clocksource/timer-stm32.c

@@ -304,8 +304,10 @@ static int __init stm32_timer_init(struct device_node *node)
 
 	to->private_data = kzalloc(sizeof(struct stm32_timer_private),
 				   GFP_KERNEL);
-	if (!to->private_data)
+	if (!to->private_data) {
+		ret = -ENOMEM;
 		goto deinit;
+	}
 
 	rstc = of_reset_control_get(node, NULL);
 	if (!IS_ERR(rstc)) {

drivers/cpufreq/intel_pstate.c

@@ -294,6 +294,7 @@ struct pstate_funcs {
 static struct pstate_funcs pstate_funcs __read_mostly;
 
 static int hwp_active __read_mostly;
+static int hwp_mode_bdw __read_mostly;
 static bool per_cpu_limits __read_mostly;
 static bool hwp_boost __read_mostly;
 
@@ -1413,7 +1414,15 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
 	cpu->pstate.scaling = pstate_funcs.get_scaling();
 	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
-	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+
+	if (hwp_active && !hwp_mode_bdw) {
+		unsigned int phy_max, current_max;
+
+		intel_pstate_get_hwp_max(cpu->cpu, &phy_max, &current_max);
+		cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling;
+	} else {
+		cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+	}
 
 	if (pstate_funcs.get_aperf_mperf_shift)
 		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
@@ -2467,28 +2476,36 @@ static inline bool intel_pstate_has_acpi_ppc(void) { return false; }
 static inline void intel_pstate_request_control_from_smm(void) {}
 #endif /* CONFIG_ACPI */
 
+#define INTEL_PSTATE_HWP_BROADWELL	0x01
+
+#define ICPU_HWP(model, hwp_mode) \
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_HWP, hwp_mode }
+
 static const struct x86_cpu_id hwp_support_ids[] __initconst = {
-	{ X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP },
+	ICPU_HWP(INTEL_FAM6_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL),
+	ICPU_HWP(INTEL_FAM6_BROADWELL_XEON_D, INTEL_PSTATE_HWP_BROADWELL),
+	ICPU_HWP(X86_MODEL_ANY, 0),
 	{}
 };
 
 static int __init intel_pstate_init(void)
 {
+	const struct x86_cpu_id *id;
 	int rc;
 
 	if (no_load)
 		return -ENODEV;
 
-	if (x86_match_cpu(hwp_support_ids)) {
+	id = x86_match_cpu(hwp_support_ids);
+	if (id) {
 		copy_cpu_funcs(&core_funcs);
 		if (!no_hwp) {
 			hwp_active++;
+			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
 			goto hwp_cpu_matched;
 		}
 	} else {
-		const struct x86_cpu_id *id;
-
 		id = x86_match_cpu(intel_pstate_cpu_ids);
 		if (!id)
 			return -ENODEV;

drivers/cpufreq/qcom-cpufreq-kryo.c

@@ -42,6 +42,8 @@ enum _msm8996_version {
 	NUM_OF_MSM8996_VERSIONS,
 };
 
+struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
+
 static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
 {
 	size_t len;
@@ -74,7 +76,6 @@ static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
 static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 {
 	struct opp_table *opp_tables[NR_CPUS] = {0};
-	struct platform_device *cpufreq_dt_pdev;
 	enum _msm8996_version msm8996_version;
 	struct nvmem_cell *speedbin_nvmem;
 	struct device_node *np;
@@ -115,6 +116,8 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 
 	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
 	nvmem_cell_put(speedbin_nvmem);
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
 
 	switch (msm8996_version) {
 	case MSM8996_V3:
@@ -127,6 +130,7 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 		BUG();
 		break;
 	}
+	kfree(speedbin);
 
 	for_each_possible_cpu(cpu) {
 		cpu_dev = get_cpu_device(cpu);
@@ -162,8 +166,15 @@ free_opp:
 	return ret;
 }
 
+static int qcom_cpufreq_kryo_remove(struct platform_device *pdev)
+{
+	platform_device_unregister(cpufreq_dt_pdev);
+	return 0;
+}
+
 static struct platform_driver qcom_cpufreq_kryo_driver = {
 	.probe = qcom_cpufreq_kryo_probe,
+	.remove = qcom_cpufreq_kryo_remove,
 	.driver = {
 		.name = "qcom-cpufreq-kryo",
 	},
@@ -198,8 +209,9 @@ static int __init qcom_cpufreq_kryo_init(void)
 	if (unlikely(ret < 0))
 		return ret;
 
-	ret = PTR_ERR_OR_ZERO(platform_device_register_simple(
-		"qcom-cpufreq-kryo", -1, NULL, 0));
+	kryo_cpufreq_pdev = platform_device_register_simple(
+		"qcom-cpufreq-kryo", -1, NULL, 0);
+	ret = PTR_ERR_OR_ZERO(kryo_cpufreq_pdev);
 	if (0 == ret)
 		return 0;
 
@@ -208,5 +220,12 @@ static int __init qcom_cpufreq_kryo_init(void)
 }
 module_init(qcom_cpufreq_kryo_init);
 
+static void __init qcom_cpufreq_kryo_exit(void)
+{
+	platform_device_unregister(kryo_cpufreq_pdev);
+	platform_driver_unregister(&qcom_cpufreq_kryo_driver);
+}
+module_exit(qcom_cpufreq_kryo_exit);
+
 MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
 MODULE_LICENSE("GPL v2");

drivers/crypto/chelsio/chtls/chtls_io.c

@@ -1548,15 +1548,14 @@ skip_copy:
 			tp->urg_data = 0;
 
 		if ((avail + offset) >= skb->len) {
-			if (likely(skb))
-				chtls_free_skb(sk, skb);
-			buffers_freed++;
 			if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) {
 				tp->copied_seq += skb->len;
 				hws->rcvpld = skb->hdr_len;
 			} else {
 				tp->copied_seq += hws->rcvpld;
 			}
+			chtls_free_skb(sk, skb);
+			buffers_freed++;
 			hws->copied_seq = 0;
 			if (copied >= target &&
 			    !skb_peek(&sk->sk_receive_queue))

drivers/firmware/efi/libstub/tpm.c

@@ -64,7 +64,7 @@ static void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg)
 	efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID;
 	efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID;
 	efi_status_t status;
-	efi_physical_addr_t log_location, log_last_entry;
+	efi_physical_addr_t log_location = 0, log_last_entry = 0;
 	struct linux_efi_tpm_eventlog *log_tbl = NULL;
 	unsigned long first_entry_addr, last_entry_addr;
 	size_t log_size, last_entry_size;

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

@@ -2158,10 +2158,18 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	switch (asic_type) {
 #if defined(CONFIG_DRM_AMD_DC)
 	case CHIP_BONAIRE:
-	case CHIP_HAWAII:
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
+		/*
+		 * We have systems in the wild with these ASICs that require
+		 * LVDS and VGA support which is not supported with DC.
+		 *
+		 * Fallback to the non-DC driver here by default so as not to
+		 * cause regressions.
+		 */
+		return amdgpu_dc > 0;
+	case CHIP_HAWAII:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
 	case CHIP_POLARIS10:

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

@@ -762,8 +762,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
 		adev->vram_pin_size += amdgpu_bo_size(bo);
-		if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
-			adev->invisible_pin_size += amdgpu_bo_size(bo);
+		adev->invisible_pin_size += amdgpu_vram_mgr_bo_invisible_size(bo);
 	} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
 		adev->gart_pin_size += amdgpu_bo_size(bo);
 	}
@@ -790,25 +789,22 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 	bo->pin_count--;
 	if (bo->pin_count)
 		return 0;
-	for (i = 0; i < bo->placement.num_placement; i++) {
-		bo->placements[i].lpfn = 0;
-		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
-	}
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
-	if (unlikely(r)) {
-		dev_err(adev->dev, "%p validate failed for unpin\n", bo);
-		goto error;
-	}
 
 	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
 		adev->vram_pin_size -= amdgpu_bo_size(bo);
-		if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
-			adev->invisible_pin_size -= amdgpu_bo_size(bo);
+		adev->invisible_pin_size -= amdgpu_vram_mgr_bo_invisible_size(bo);
 	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
 		adev->gart_pin_size -= amdgpu_bo_size(bo);
 	}
 
-error:
+	for (i = 0; i < bo->placement.num_placement; i++) {
+		bo->placements[i].lpfn = 0;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
+	}
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+	if (unlikely(r))
+		dev_err(adev->dev, "%p validate failed for unpin\n", bo);
+
 	return r;
 }
 

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

@@ -73,6 +73,7 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem);
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
 int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
 
+u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo);
 uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
 uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
 

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

@@ -130,7 +130,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	unsigned version_major, version_minor, family_id;
 	int i, j, r;
 
-	INIT_DELAYED_WORK(&adev->uvd.inst->idle_work, amdgpu_uvd_idle_work_handler);
+	INIT_DELAYED_WORK(&adev->uvd.idle_work, amdgpu_uvd_idle_work_handler);
 
 	switch (adev->asic_type) {
 #ifdef CONFIG_DRM_AMDGPU_CIK
@@ -314,12 +314,12 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	void *ptr;
 	int i, j;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
 		if (adev->uvd.inst[j].vcpu_bo == NULL)
 			continue;
 
-		cancel_delayed_work_sync(&adev->uvd.inst[j].idle_work);
-
 		/* only valid for physical mode */
 		if (adev->asic_type < CHIP_POLARIS10) {
 			for (i = 0; i < adev->uvd.max_handles; ++i)
@@ -1145,7 +1145,7 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
-		container_of(work, struct amdgpu_device, uvd.inst->idle_work.work);
+		container_of(work, struct amdgpu_device, uvd.idle_work.work);
 	unsigned fences = 0, i, j;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
@@ -1167,7 +1167,7 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 							       AMD_CG_STATE_GATE);
 		}
 	} else {
-		schedule_delayed_work(&adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
+		schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
 	}
 }
 
@@ -1179,7 +1179,7 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 	if (amdgpu_sriov_vf(adev))
 		return;
 
-	set_clocks = !cancel_delayed_work_sync(&adev->uvd.inst->idle_work);
+	set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work);
 	if (set_clocks) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, true);
@@ -1196,7 +1196,7 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring)
 {
 	if (!amdgpu_sriov_vf(ring->adev))
-		schedule_delayed_work(&ring->adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
+		schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
 }
 
 /**

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

@@ -44,7 +44,6 @@ struct amdgpu_uvd_inst {
 	void			*saved_bo;
 	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
 	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
-	struct delayed_work	idle_work;
 	struct amdgpu_ring	ring;
 	struct amdgpu_ring	ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
@@ -62,6 +61,7 @@ struct amdgpu_uvd {
 	bool			address_64_bit;
 	bool			use_ctx_buf;
 	struct amdgpu_uvd_inst		inst[AMDGPU_MAX_UVD_INSTANCES];
+	struct delayed_work	idle_work;
 };
 
 int amdgpu_uvd_sw_init(struct amdgpu_device *adev);