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

Lots of overlapping changes and parallel additions, stuff
like that.

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

.mailmap

@@ -108,6 +108,10 @@ Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
 Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
+Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com>
+Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com>
+Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com>
+Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
 Jean Tourrilhes <jt@hpl.hp.com>
 <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -486,6 +486,8 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/l1tf
 		/sys/devices/system/cpu/vulnerabilities/mds
+		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
+		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities

Documentation/admin-guide/hw-vuln/index.rst

@@ -12,3 +12,5 @@ are configurable at compile, boot or run time.
    spectre
    l1tf
    mds
+   tsx_async_abort
+   multihit.rst

Documentation/admin-guide/hw-vuln/multihit.rst

@@ -0,0 +1,163 @@
+iTLB multihit
+=============
+
+iTLB multihit is an erratum where some processors may incur a machine check
+error, possibly resulting in an unrecoverable CPU lockup, when an
+instruction fetch hits multiple entries in the instruction TLB. This can
+occur when the page size is changed along with either the physical address
+or cache type. A malicious guest running on a virtualized system can
+exploit this erratum to perform a denial of service attack.
+
+
+Affected processors
+-------------------
+
+Variations of this erratum are present on most Intel Core and Xeon processor
+models. The erratum is not present on:
+
+   - non-Intel processors
+
+   - Some Atoms (Airmont, Bonnell, Goldmont, GoldmontPlus, Saltwell, Silvermont)
+
+   - Intel processors that have the PSCHANGE_MC_NO bit set in the
+     IA32_ARCH_CAPABILITIES MSR.
+
+
+Related CVEs
+------------
+
+The following CVE entry is related to this issue:
+
+   ==============  =================================================
+   CVE-2018-12207  Machine Check Error Avoidance on Page Size Change
+   ==============  =================================================
+
+
+Problem
+-------
+
+Privileged software, including OS and virtual machine managers (VMM), are in
+charge of memory management. A key component in memory management is the control
+of the page tables. Modern processors use virtual memory, a technique that creates
+the illusion of a very large memory for processors. This virtual space is split
+into pages of a given size. Page tables translate virtual addresses to physical
+addresses.
+
+To reduce latency when performing a virtual to physical address translation,
+processors include a structure, called TLB, that caches recent translations.
+There are separate TLBs for instruction (iTLB) and data (dTLB).
+
+Under this errata, instructions are fetched from a linear address translated
+using a 4 KB translation cached in the iTLB. Privileged software modifies the
+paging structure so that the same linear address using large page size (2 MB, 4
+MB, 1 GB) with a different physical address or memory type.  After the page
+structure modification but before the software invalidates any iTLB entries for
+the linear address, a code fetch that happens on the same linear address may
+cause a machine-check error which can result in a system hang or shutdown.
+
+
+Attack scenarios
+----------------
+
+Attacks against the iTLB multihit erratum can be mounted from malicious
+guests in a virtualized system.
+
+
+iTLB multihit system information
+--------------------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current iTLB
+multihit status of the system:whether the system is vulnerable and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/itlb_multihit
+
+The possible values in this file are:
+
+.. list-table::
+
+     * - Not affected
+       - The processor is not vulnerable.
+     * - KVM: Mitigation: Split huge pages
+       - Software changes mitigate this issue.
+     * - KVM: Vulnerable
+       - The processor is vulnerable, but no mitigation enabled
+
+
+Enumeration of the erratum
+--------------------------------
+
+A new bit has been allocated in the IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) msr
+and will be set on CPU's which are mitigated against this issue.
+
+   =======================================   ===========   ===============================
+   IA32_ARCH_CAPABILITIES MSR                Not present   Possibly vulnerable,check model
+   IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO]    '0'           Likely vulnerable,check model
+   IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO]    '1'           Not vulnerable
+   =======================================   ===========   ===============================
+
+
+Mitigation mechanism
+-------------------------
+
+This erratum can be mitigated by restricting the use of large page sizes to
+non-executable pages.  This forces all iTLB entries to be 4K, and removes
+the possibility of multiple hits.
+
+In order to mitigate the vulnerability, KVM initially marks all huge pages
+as non-executable. If the guest attempts to execute in one of those pages,
+the page is broken down into 4K pages, which are then marked executable.
+
+If EPT is disabled or not available on the host, KVM is in control of TLB
+flushes and the problematic situation cannot happen.  However, the shadow
+EPT paging mechanism used by nested virtualization is vulnerable, because
+the nested guest can trigger multiple iTLB hits by modifying its own
+(non-nested) page tables.  For simplicity, KVM will make large pages
+non-executable in all shadow paging modes.
+
+Mitigation control on the kernel command line and KVM - module parameter
+------------------------------------------------------------------------
+
+The KVM hypervisor mitigation mechanism for marking huge pages as
+non-executable can be controlled with a module parameter "nx_huge_pages=".
+The kernel command line allows to control the iTLB multihit mitigations at
+boot time with the option "kvm.nx_huge_pages=".
+
+The valid arguments for these options are:
+
+  ==========  ================================================================
+  force       Mitigation is enabled. In this case, the mitigation implements
+              non-executable huge pages in Linux kernel KVM module. All huge
+              pages in the EPT are marked as non-executable.
+              If a guest attempts to execute in one of those pages, the page is
+              broken down into 4K pages, which are then marked executable.
+
+  off	      Mitigation is disabled.
+
+  auto        Enable mitigation only if the platform is affected and the kernel
+              was not booted with the "mitigations=off" command line parameter.
+	      This is the default option.
+  ==========  ================================================================
+
+
+Mitigation selection guide
+--------------------------
+
+1. No virtualization in use
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The system is protected by the kernel unconditionally and no further
+   action is required.
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   If the guest comes from a trusted source, you may assume that the guest will
+   not attempt to maliciously exploit these errata and no further action is
+   required.
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+   If the guest comes from an untrusted source, the guest host kernel will need
+   to apply iTLB multihit mitigation via the kernel command line or kvm
+   module parameter.

Documentation/admin-guide/hw-vuln/tsx_async_abort.rst

@@ -0,0 +1,276 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+TAA - TSX Asynchronous Abort
+======================================
+
+TAA is a hardware vulnerability that allows unprivileged speculative access to
+data which is available in various CPU internal buffers by using asynchronous
+aborts within an Intel TSX transactional region.
+
+Affected processors
+-------------------
+
+This vulnerability only affects Intel processors that support Intel
+Transactional Synchronization Extensions (TSX) when the TAA_NO bit (bit 8)
+is 0 in the IA32_ARCH_CAPABILITIES MSR.  On processors where the MDS_NO bit
+(bit 5) is 0 in the IA32_ARCH_CAPABILITIES MSR, the existing MDS mitigations
+also mitigate against TAA.
+
+Whether a processor is affected or not can be read out from the TAA
+vulnerability file in sysfs. See :ref:`tsx_async_abort_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entry is related to this TAA issue:
+
+   ==============  =====  ===================================================
+   CVE-2019-11135  TAA    TSX Asynchronous Abort (TAA) condition on some
+                          microprocessors utilizing speculative execution may
+                          allow an authenticated user to potentially enable
+                          information disclosure via a side channel with
+                          local access.
+   ==============  =====  ===================================================
+
+Problem
+-------
+
+When performing store, load or L1 refill operations, processors write
+data into temporary microarchitectural structures (buffers). The data in
+those buffers can be forwarded to load operations as an optimization.
+
+Intel TSX is an extension to the x86 instruction set architecture that adds
+hardware transactional memory support to improve performance of multi-threaded
+software. TSX lets the processor expose and exploit concurrency hidden in an
+application due to dynamically avoiding unnecessary synchronization.
+
+TSX supports atomic memory transactions that are either committed (success) or
+aborted. During an abort, operations that happened within the transactional region
+are rolled back. An asynchronous abort takes place, among other options, when a
+different thread accesses a cache line that is also used within the transactional
+region when that access might lead to a data race.
+
+Immediately after an uncompleted asynchronous abort, certain speculatively
+executed loads may read data from those internal buffers and pass it to dependent
+operations. This can be then used to infer the value via a cache side channel
+attack.
+
+Because the buffers are potentially shared between Hyper-Threads cross
+Hyper-Thread attacks are possible.
+
+The victim of a malicious actor does not need to make use of TSX. Only the
+attacker needs to begin a TSX transaction and raise an asynchronous abort
+which in turn potenitally leaks data stored in the buffers.
+
+More detailed technical information is available in the TAA specific x86
+architecture section: :ref:`Documentation/x86/tsx_async_abort.rst <tsx_async_abort>`.
+
+
+Attack scenarios
+----------------
+
+Attacks against the TAA vulnerability can be implemented from unprivileged
+applications running on hosts or guests.
+
+As for MDS, the attacker has no control over the memory addresses that can
+be leaked. Only the victim is responsible for bringing data to the CPU. As
+a result, the malicious actor has to sample as much data as possible and
+then postprocess it to try to infer any useful information from it.
+
+A potential attacker only has read access to the data. Also, there is no direct
+privilege escalation by using this technique.
+
+
+.. _tsx_async_abort_sys_info:
+
+TAA system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current TAA status
+of mitigated systems. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
+
+The possible values in this file are:
+
+.. list-table::
+
+   * - 'Vulnerable'
+     - The CPU is affected by this vulnerability and the microcode and kernel mitigation are not applied.
+   * - 'Vulnerable: Clear CPU buffers attempted, no microcode'
+     - The system tries to clear the buffers but the microcode might not support the operation.
+   * - 'Mitigation: Clear CPU buffers'
+     - The microcode has been updated to clear the buffers. TSX is still enabled.
+   * - 'Mitigation: TSX disabled'
+     - TSX is disabled.
+   * - 'Not affected'
+     - The CPU is not affected by this issue.
+
+.. _ucode_needed:
+
+Best effort mitigation mode
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If the processor is vulnerable, but the availability of the microcode-based
+mitigation mechanism is not advertised via CPUID the kernel selects a best
+effort mitigation mode.  This mode invokes the mitigation instructions
+without a guarantee that they clear the CPU buffers.
+
+This is done to address virtualization scenarios where the host has the
+microcode update applied, but the hypervisor is not yet updated to expose the
+CPUID to the guest. If the host has updated microcode the protection takes
+effect; otherwise a few CPU cycles are wasted pointlessly.
+
+The state in the tsx_async_abort sysfs file reflects this situation
+accordingly.
+
+
+Mitigation mechanism
+--------------------
+
+The kernel detects the affected CPUs and the presence of the microcode which is
+required. If a CPU is affected and the microcode is available, then the kernel
+enables the mitigation by default.
+
+
+The mitigation can be controlled at boot time via a kernel command line option.
+See :ref:`taa_mitigation_control_command_line`.
+
+.. _virt_mechanism:
+
+Virtualization mitigation
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Affected systems where the host has TAA microcode and TAA is mitigated by
+having disabled TSX previously, are not vulnerable regardless of the status
+of the VMs.
+
+In all other cases, if the host either does not have the TAA microcode or
+the kernel is not mitigated, the system might be vulnerable.
+
+
+.. _taa_mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the TAA mitigations at boot time with
+the option "tsx_async_abort=". The valid arguments for this option are:
+
+  ============  =============================================================
+  off		This option disables the TAA mitigation on affected platforms.
+                If the system has TSX enabled (see next parameter) and the CPU
+                is affected, the system is vulnerable.
+
+  full	        TAA mitigation is enabled. If TSX is enabled, on an affected
+                system it will clear CPU buffers on ring transitions. On
+                systems which are MDS-affected and deploy MDS mitigation,
+                TAA is also mitigated. Specifying this option on those
+                systems will have no effect.
+
+  full,nosmt    The same as tsx_async_abort=full, with SMT disabled on
+                vulnerable CPUs that have TSX enabled. This is the complete
+                mitigation. When TSX is disabled, SMT is not disabled because
+                CPU is not vulnerable to cross-thread TAA attacks.
+  ============  =============================================================
+
+Not specifying this option is equivalent to "tsx_async_abort=full".
+
+The kernel command line also allows to control the TSX feature using the
+parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used
+to control the TSX feature and the enumeration of the TSX feature bits (RTM
+and HLE) in CPUID.
+
+The valid options are:
+
+  ============  =============================================================
+  off		Disables TSX on the system.
+
+                Note that this option takes effect only on newer CPUs which are
+                not vulnerable to MDS, i.e., have MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1
+                and which get the new IA32_TSX_CTRL MSR through a microcode
+                update. This new MSR allows for the reliable deactivation of
+                the TSX functionality.
+
+  on		Enables TSX.
+
+                Although there are mitigations for all known security
+                vulnerabilities, TSX has been known to be an accelerator for
+                several previous speculation-related CVEs, and so there may be
+                unknown security risks associated with leaving it enabled.
+
+  auto		Disables TSX if X86_BUG_TAA is present, otherwise enables TSX
+                on the system.
+  ============  =============================================================
+
+Not specifying this option is equivalent to "tsx=off".
+
+The following combinations of the "tsx_async_abort" and "tsx" are possible. For
+affected platforms tsx=auto is equivalent to tsx=off and the result will be:
+
+  =========  ==========================   =========================================
+  tsx=on     tsx_async_abort=full         The system will use VERW to clear CPU
+                                          buffers. Cross-thread attacks are still
+					  possible on SMT machines.
+  tsx=on     tsx_async_abort=full,nosmt   As above, cross-thread attacks on SMT
+                                          mitigated.
+  tsx=on     tsx_async_abort=off          The system is vulnerable.
+  tsx=off    tsx_async_abort=full         TSX might be disabled if microcode
+                                          provides a TSX control MSR. If so,
+					  system is not vulnerable.
+  tsx=off    tsx_async_abort=full,nosmt   Ditto
+  tsx=off    tsx_async_abort=off          ditto
+  =========  ==========================   =========================================
+
+
+For unaffected platforms "tsx=on" and "tsx_async_abort=full" does not clear CPU
+buffers.  For platforms without TSX control (MSR_IA32_ARCH_CAPABILITIES.MDS_NO=0)
+"tsx" command line argument has no effect.
+
+For the affected platforms below table indicates the mitigation status for the
+combinations of CPUID bit MD_CLEAR and IA32_ARCH_CAPABILITIES MSR bits MDS_NO
+and TSX_CTRL_MSR.
+
+  =======  =========  =============  ========================================
+  MDS_NO   MD_CLEAR   TSX_CTRL_MSR   Status
+  =======  =========  =============  ========================================
+    0          0            0        Vulnerable (needs microcode)
+    0          1            0        MDS and TAA mitigated via VERW
+    1          1            0        MDS fixed, TAA vulnerable if TSX enabled
+                                     because MD_CLEAR has no meaning and
+                                     VERW is not guaranteed to clear buffers
+    1          X            1        MDS fixed, TAA can be mitigated by
+                                     VERW or TSX_CTRL_MSR
+  =======  =========  =============  ========================================
+
+Mitigation selection guide
+--------------------------
+
+1. Trusted userspace and guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If all user space applications are from a trusted source and do not execute
+untrusted code which is supplied externally, then the mitigation can be
+disabled. The same applies to virtualized environments with trusted guests.
+
+
+2. Untrusted userspace and guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If there are untrusted applications or guests on the system, enabling TSX
+might allow a malicious actor to leak data from the host or from other
+processes running on the same physical core.
+
+If the microcode is available and the TSX is disabled on the host, attacks
+are prevented in a virtualized environment as well, even if the VMs do not
+explicitly enable the mitigation.
+
+
+.. _taa_default_mitigations:
+
+Default mitigations
+-------------------
+
+The kernel's default action for vulnerable processors is:
+
+  - Deploy TSX disable mitigation (tsx_async_abort=full tsx=off).

Documentation/admin-guide/kernel-parameters.txt

@@ -2055,6 +2055,25 @@
 			KVM MMU at runtime.
 			Default is 0 (off)
 
+	kvm.nx_huge_pages=
+			[KVM] Controls the software workaround for the
+			X86_BUG_ITLB_MULTIHIT bug.
+			force	: Always deploy workaround.
+			off	: Never deploy workaround.
+			auto    : Deploy workaround based on the presence of
+				  X86_BUG_ITLB_MULTIHIT.
+
+			Default is 'auto'.
+
+			If the software workaround is enabled for the host,
+			guests do need not to enable it for nested guests.
+
+	kvm.nx_huge_pages_recovery_ratio=
+			[KVM] Controls how many 4KiB pages are periodically zapped
+			back to huge pages.  0 disables the recovery, otherwise if
+			the value is N KVM will zap 1/Nth of the 4KiB pages every
+			minute.  The default is 60.
+
 	kvm-amd.nested=	[KVM,AMD] Allow nested virtualization in KVM/SVM.
 			Default is 1 (enabled)
 
@@ -2636,6 +2655,13 @@
 					       ssbd=force-off [ARM64]
 					       l1tf=off [X86]
 					       mds=off [X86]
+					       tsx_async_abort=off [X86]
+					       kvm.nx_huge_pages=off [X86]
+
+				Exceptions:
+					       This does not have any effect on
+					       kvm.nx_huge_pages when
+					       kvm.nx_huge_pages=force.
 
 			auto (default)
 				Mitigate all CPU vulnerabilities, but leave SMT
@@ -2651,6 +2677,7 @@
 				be fully mitigated, even if it means losing SMT.
 				Equivalent to: l1tf=flush,nosmt [X86]
 					       mds=full,nosmt [X86]
+					       tsx_async_abort=full,nosmt [X86]
 
 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
@@ -4848,6 +4875,71 @@
 			interruptions from clocksource watchdog are not
 			acceptable).
 
+	tsx=		[X86] Control Transactional Synchronization
+			Extensions (TSX) feature in Intel processors that
+			support TSX control.
+
+			This parameter controls the TSX feature. The options are:
+
+			on	- Enable TSX on the system. Although there are
+				mitigations for all known security vulnerabilities,
+				TSX has been known to be an accelerator for
+				several previous speculation-related CVEs, and
+				so there may be unknown	security risks associated
+				with leaving it enabled.
+
+			off	- Disable TSX on the system. (Note that this
+				option takes effect only on newer CPUs which are
+				not vulnerable to MDS, i.e., have
+				MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
+				the new IA32_TSX_CTRL MSR through a microcode
+				update. This new MSR allows for the reliable
+				deactivation of the TSX functionality.)
+
+			auto	- Disable TSX if X86_BUG_TAA is present,
+				  otherwise enable TSX on the system.
+
+			Not specifying this option is equivalent to tsx=off.
+
+			See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
+			for more details.
+
+	tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
+			Abort (TAA) vulnerability.
+
+			Similar to Micro-architectural Data Sampling (MDS)
+			certain CPUs that support Transactional
+			Synchronization Extensions (TSX) are vulnerable to an
+			exploit against CPU internal buffers which can forward
+			information to a disclosure gadget under certain
+			conditions.
+
+			In vulnerable processors, the speculatively forwarded
+			data can be used in a cache side channel attack, to
+			access data to which the attacker does not have direct
+			access.
+
+			This parameter controls the TAA mitigation.  The
+			options are:
+
+			full       - Enable TAA mitigation on vulnerable CPUs
+				     if TSX is enabled.
+
+			full,nosmt - Enable TAA mitigation and disable SMT on
+				     vulnerable CPUs. If TSX is disabled, SMT
+				     is not disabled because CPU is not
+				     vulnerable to cross-thread TAA attacks.
+			off        - Unconditionally disable TAA mitigation
+
+			Not specifying this option is equivalent to
+			tsx_async_abort=full.  On CPUs which are MDS affected
+			and deploy MDS mitigation, TAA mitigation is not
+			required and doesn't provide any additional
+			mitigation.
+
+			For details see:
+			Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
+
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
 			Format:

Documentation/x86/index.rst

@@ -27,6 +27,7 @@ x86-specific Documentation
    mds
    microcode
    resctrl_ui
+   tsx_async_abort
    usb-legacy-support
    i386/index
    x86_64/index

Documentation/x86/tsx_async_abort.rst

@@ -0,0 +1,117 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+TSX Async Abort (TAA) mitigation
+================================
+
+.. _tsx_async_abort:
+
+Overview
+--------
+
+TSX Async Abort (TAA) is a side channel attack on internal buffers in some
+Intel processors similar to Microachitectural Data Sampling (MDS).  In this
+case certain loads may speculatively pass invalid data to dependent operations
+when an asynchronous abort condition is pending in a Transactional
+Synchronization Extensions (TSX) transaction.  This includes loads with no
+fault or assist condition. Such loads may speculatively expose stale data from
+the same uarch data structures as in MDS, with same scope of exposure i.e.
+same-thread and cross-thread. This issue affects all current processors that
+support TSX.
+
+Mitigation strategy
+-------------------
+
+a) TSX disable - one of the mitigations is to disable TSX. A new MSR
+IA32_TSX_CTRL will be available in future and current processors after
+microcode update which can be used to disable TSX. In addition, it
+controls the enumeration of the TSX feature bits (RTM and HLE) in CPUID.
+
+b) Clear CPU buffers - similar to MDS, clearing the CPU buffers mitigates this
+vulnerability. More details on this approach can be found in
+:ref:`Documentation/admin-guide/hw-vuln/mds.rst <mds>`.
+
+Kernel internal mitigation modes
+--------------------------------
+
+ =============    ============================================================
+ off              Mitigation is disabled. Either the CPU is not affected or
+                  tsx_async_abort=off is supplied on the kernel command line.
+
+ tsx disabled     Mitigation is enabled. TSX feature is disabled by default at
+                  bootup on processors that support TSX control.
+
+ verw             Mitigation is enabled. CPU is affected and MD_CLEAR is
+                  advertised in CPUID.
+
+ ucode needed     Mitigation is enabled. CPU is affected and MD_CLEAR is not
+                  advertised in CPUID. That is mainly for virtualization
+                  scenarios where the host has the updated microcode but the
+                  hypervisor does not expose MD_CLEAR in CPUID. It's a best
+                  effort approach without guarantee.
+ =============    ============================================================
+
+If the CPU is affected and the "tsx_async_abort" kernel command line parameter is
+not provided then the kernel selects an appropriate mitigation depending on the
+status of RTM and MD_CLEAR CPUID bits.
+
+Below tables indicate the impact of tsx=on|off|auto cmdline options on state of
+TAA mitigation, VERW behavior and TSX feature for various combinations of
+MSR_IA32_ARCH_CAPABILITIES bits.
+
+1. "tsx=off"
+
+=========  =========  ============  ============  ==============  ===================  ======================
+MSR_IA32_ARCH_CAPABILITIES bits     Result with cmdline tsx=off
+----------------------------------  -------------------------------------------------------------------------
+TAA_NO     MDS_NO     TSX_CTRL_MSR  TSX state     VERW can clear  TAA mitigation       TAA mitigation
+                                    after bootup  CPU buffers     tsx_async_abort=off  tsx_async_abort=full
+=========  =========  ============  ============  ==============  ===================  ======================
+    0          0           0         HW default         Yes           Same as MDS           Same as MDS
+    0          0           1        Invalid case   Invalid case       Invalid case          Invalid case
+    0          1           0         HW default         No         Need ucode update     Need ucode update
+    0          1           1          Disabled          Yes           TSX disabled          TSX disabled
+    1          X           1          Disabled           X             None needed           None needed
+=========  =========  ============  ============  ==============  ===================  ======================
+
+2. "tsx=on"
+
+=========  =========  ============  ============  ==============  ===================  ======================
+MSR_IA32_ARCH_CAPABILITIES bits     Result with cmdline tsx=on
+----------------------------------  -------------------------------------------------------------------------
+TAA_NO     MDS_NO     TSX_CTRL_MSR  TSX state     VERW can clear  TAA mitigation       TAA mitigation
+                                    after bootup  CPU buffers     tsx_async_abort=off  tsx_async_abort=full
+=========  =========  ============  ============  ==============  ===================  ======================
+    0          0           0         HW default        Yes            Same as MDS          Same as MDS
+    0          0           1        Invalid case   Invalid case       Invalid case         Invalid case
+    0          1           0         HW default        No          Need ucode update     Need ucode update
+    0          1           1          Enabled          Yes               None              Same as MDS
+    1          X           1          Enabled          X              None needed          None needed
+=========  =========  ============  ============  ==============  ===================  ======================
+
+3. "tsx=auto"
+
+=========  =========  ============  ============  ==============  ===================  ======================
+MSR_IA32_ARCH_CAPABILITIES bits     Result with cmdline tsx=auto
+----------------------------------  -------------------------------------------------------------------------
+TAA_NO     MDS_NO     TSX_CTRL_MSR  TSX state     VERW can clear  TAA mitigation       TAA mitigation
+                                    after bootup  CPU buffers     tsx_async_abort=off  tsx_async_abort=full
+=========  =========  ============  ============  ==============  ===================  ======================
+    0          0           0         HW default    Yes                Same as MDS           Same as MDS
+    0          0           1        Invalid case  Invalid case        Invalid case          Invalid case
+    0          1           0         HW default    No              Need ucode update     Need ucode update
+    0          1           1          Disabled      Yes               TSX disabled          TSX disabled
+    1          X           1          Enabled       X                 None needed           None needed
+=========  =========  ============  ============  ==============  ===================  ======================
+
+In the tables, TSX_CTRL_MSR is a new bit in MSR_IA32_ARCH_CAPABILITIES that
+indicates whether MSR_IA32_TSX_CTRL is supported.
+
+There are two control bits in IA32_TSX_CTRL MSR:
+
+      Bit 0: When set it disables the Restricted Transactional Memory (RTM)
+             sub-feature of TSX (will force all transactions to abort on the
+             XBEGIN instruction).
+
+      Bit 1: When set it disables the enumeration of the RTM and HLE feature
+             (i.e. it will make CPUID(EAX=7).EBX{bit4} and
+             CPUID(EAX=7).EBX{bit11} read as 0).

MAINTAINERS

@@ -3268,7 +3268,6 @@ S:	Maintained
 F:	drivers/cpufreq/bmips-cpufreq.c
 
 BROADCOM BMIPS MIPS ARCHITECTURE
-M:	Kevin Cernekee <cernekee@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-mips@vger.kernel.org
@@ -3745,7 +3744,6 @@ F:	drivers/crypto/cavium/cpt/
 
 CAVIUM THUNDERX2 ARM64 SOC
 M:	Robert Richter <rrichter@cavium.com>
-M:	Jayachandran C <jnair@caviumnetworks.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm64/boot/dts/cavium/thunder2-99xx*

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -917,6 +917,9 @@ ifeq ($(CONFIG_RELR),y)
 LDFLAGS_vmlinux	+= --pack-dyn-relocs=relr
 endif
 
+# make the checker run with the right architecture
+CHECKFLAGS += --arch=$(ARCH)
+
 # insure the checker run with the right endianness
 CHECKFLAGS += $(if $(CONFIG_CPU_BIG_ENDIAN),-mbig-endian,-mlittle-endian)
 

arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi

@@ -328,6 +328,10 @@
 	pinctrl-0 = <&pinctrl_pwm3>;
 };
 
+&snvs_pwrkey {
+	status = "okay";
+};
+
 &ssi2 {
 	status = "okay";
 };

arch/arm/boot/dts/imx6qdl-sabreauto.dtsi

@@ -230,6 +230,8 @@
 			accelerometer@1c {
 				compatible = "fsl,mma8451";
 				reg = <0x1c>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_mma8451_int>;
 				interrupt-parent = <&gpio6>;
 				interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
 			};
@@ -628,6 +630,12 @@
 			>;
 		};
 
+		pinctrl_mma8451_int: mma8451intgrp {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_BCLK__GPIO6_IO31		0xb0b1
+			>;
+		};
+
 		pinctrl_pwm3: pwm1grp {
 			fsl,pins = <
 				MX6QDL_PAD_SD4_DAT1__PWM3_OUT		0x1b0b1

arch/arm/boot/dts/stm32mp157c-ev1.dts

@@ -183,14 +183,12 @@
 
 	ov5640: camera@3c {
 		compatible = "ovti,ov5640";
-		pinctrl-names = "default";
-		pinctrl-0 = <&ov5640_pins>;
 		reg = <0x3c>;
 		clocks = <&clk_ext_camera>;
 		clock-names = "xclk";
 		DOVDD-supply = <&v2v8>;
-		powerdown-gpios = <&stmfx_pinctrl 18 GPIO_ACTIVE_HIGH>;
+		powerdown-gpios = <&stmfx_pinctrl 18 (GPIO_ACTIVE_HIGH | GPIO_PUSH_PULL)>;
-		reset-gpios = <&stmfx_pinctrl 19 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&stmfx_pinctrl 19 (GPIO_ACTIVE_LOW | GPIO_PUSH_PULL)>;
 		rotation = <180>;
 		status = "okay";
 
@@ -223,15 +221,8 @@
 
 			joystick_pins: joystick {
 				pins = "gpio0", "gpio1", "gpio2", "gpio3", "gpio4";
-				drive-push-pull;
 				bias-pull-down;
 			};
-
-			ov5640_pins: camera {
-				pins = "agpio2", "agpio3"; /* stmfx pins 18 & 19 */
-				drive-push-pull;
-				output-low;
-			};
 		};
 	};
 };

arch/arm/boot/dts/stm32mp157c.dtsi

@@ -932,7 +932,7 @@
 			interrupt-names = "int0", "int1";
 			clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>;
 			clock-names = "hclk", "cclk";
-			bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>;
+			bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>;
 			status = "disabled";
 		};
 
@@ -945,7 +945,7 @@
 			interrupt-names = "int0", "int1";
 			clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>;
 			clock-names = "hclk", "cclk";
-			bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>;
+			bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>;
 			status = "disabled";
 		};
 

arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts

@@ -192,6 +192,7 @@
 	vqmmc-supply = <&reg_dldo1>;
 	non-removable;
 	wakeup-source;
+	keep-power-in-suspend;
 	status = "okay";
 
 	brcmf: wifi@1 {

arch/arm/mach-sunxi/mc_smp.c

@@ -481,14 +481,18 @@ static void sunxi_mc_smp_cpu_die(unsigned int l_cpu)
 static int sunxi_cpu_powerdown(unsigned int cpu, unsigned int cluster)
 {
 	u32 reg;
+	int gating_bit = cpu;
 
 	pr_debug("%s: cluster %u cpu %u\n", __func__, cluster, cpu);
 	if (cpu >= SUNXI_CPUS_PER_CLUSTER || cluster >= SUNXI_NR_CLUSTERS)
 		return -EINVAL;
 
+	if (is_a83t && cpu == 0)
+		gating_bit = 4;
+
 	/* gate processor power */
 	reg = readl(prcm_base + PRCM_PWROFF_GATING_REG(cluster));
-	reg |= PRCM_PWROFF_GATING_REG_CORE(cpu);
+	reg |= PRCM_PWROFF_GATING_REG_CORE(gating_bit);
 	writel(reg, prcm_base + PRCM_PWROFF_GATING_REG(cluster));
 	udelay(20);
 

arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts

@@ -127,7 +127,7 @@
 	status = "okay";
 
 	i2c-mux@77 {
-		compatible = "nxp,pca9847";
+		compatible = "nxp,pca9547";
 		reg = <0x77>;
 		#address-cells = <1>;
 		#size-cells = <0>;

arch/arm64/boot/dts/freescale/imx8mm.dtsi

@@ -394,7 +394,7 @@
 			};
 
 			sdma2: dma-controller@302c0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302c0000 0x10000>;
 				interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA2_ROOT>,
@@ -405,7 +405,7 @@
 			};
 
 			sdma3: dma-controller@302b0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302b0000 0x10000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA3_ROOT>,
@@ -737,7 +737,7 @@
 			};
 
 			sdma1: dma-controller@30bd0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>,

arch/arm64/boot/dts/freescale/imx8mn.dtsi

@@ -288,7 +288,7 @@
 			};
 
 			sdma3: dma-controller@302b0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302b0000 0x10000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA3_ROOT>,
@@ -299,7 +299,7 @@
 			};
 
 			sdma2: dma-controller@302c0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302c0000 0x10000>;
 				interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA2_ROOT>,
@@ -612,7 +612,7 @@
 			};
 
 			sdma1: dma-controller@30bd0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>,

arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi

@@ -88,7 +88,7 @@
 		regulator-name = "0V9_ARM";
 		regulator-min-microvolt = <900000>;
 		regulator-max-microvolt = <1000000>;
-		gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
+		gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>;
 		states = <1000000 0x1
 		           900000 0x0>;
 		regulator-always-on;

arch/arm64/include/asm/vdso/vsyscall.h

@@ -30,13 +30,6 @@ int __arm64_get_clock_mode(struct timekeeper *tk)
 }
 #define __arch_get_clock_mode __arm64_get_clock_mode
 
-static __always_inline
-int __arm64_use_vsyscall(struct vdso_data *vdata)
-{
-	return !vdata[CS_HRES_COARSE].clock_mode;
-}
-#define __arch_use_vsyscall __arm64_use_vsyscall
-
 static __always_inline
 void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk)
 {

arch/mips/include/asm/vdso/vsyscall.h

@@ -28,13 +28,6 @@ int __mips_get_clock_mode(struct timekeeper *tk)
 }
 #define __arch_get_clock_mode __mips_get_clock_mode
 
-static __always_inline
-int __mips_use_vsyscall(struct vdso_data *vdata)
-{
-	return (vdata[CS_HRES_COARSE].clock_mode != VDSO_CLOCK_NONE);
-}
-#define __arch_use_vsyscall __mips_use_vsyscall
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 

arch/mips/sgi-ip27/Kconfig

@@ -38,10 +38,3 @@ config REPLICATE_KTEXT
 	  Say Y here to enable replicating the kernel text across multiple
 	  nodes in a NUMA cluster.  This trades memory for speed.
 
-config REPLICATE_EXHANDLERS
-	bool "Exception handler replication support"
-	depends on SGI_IP27
-	help
-	  Say Y here to enable replicating the kernel exception handlers
-	  across multiple nodes in a NUMA cluster. This trades memory for
-	  speed.

arch/mips/sgi-ip27/ip27-init.c

@@ -69,23 +69,14 @@ static void per_hub_init(cnodeid_t cnode)
 
 	hub_rtc_init(cnode);
 
-#ifdef CONFIG_REPLICATE_EXHANDLERS
+	if (nasid) {
-	/*
+		/* copy exception handlers from first node to current node */
-	 * If this is not a headless node initialization,
+		memcpy((void *)NODE_OFFSET_TO_K0(nasid, 0),
-	 * copy over the caliased exception handlers.
+		       (void *)CKSEG0, 0x200);
-	 */
-	if (get_compact_nodeid() == cnode) {
-		extern char except_vec2_generic, except_vec3_generic;
-		extern void build_tlb_refill_handler(void);
-
-		memcpy((void *)(CKSEG0 + 0x100), &except_vec2_generic, 0x80);
-		memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x80);
-		build_tlb_refill_handler();
-		memcpy((void *)(CKSEG0 + 0x100), (void *) CKSEG0, 0x80);
-		memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x100);
 		__flush_cache_all();
+		/* switch to node local exception handlers */
+		REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K);
 	}
-#endif
 }
 
 void per_cpu_init(void)

arch/mips/sgi-ip27/ip27-memory.c

@@ -332,11 +332,7 @@ static void __init mlreset(void)
 		 * thinks it is a node 0 address.
 		 */
 		REMOTE_HUB_S(nasid, PI_REGION_PRESENT, (region_mask | 1));
-#ifdef CONFIG_REPLICATE_EXHANDLERS
-		REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K);
-#else
 		REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_0);
-#endif
 
 #ifdef LATER
 		/*

arch/sparc/vdso/Makefile

@@ -65,14 +65,14 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
 #
-CFLAGS_REMOVE_vdso-note.o = -pg
 CFLAGS_REMOVE_vclock_gettime.o = -pg
+CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg
 
 $(obj)/%.so: OBJCOPYFLAGS := -S
 $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
-CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
+CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds)
 VDSO_LDFLAGS_vdso32.lds = -m elf32_sparc -soname linux-gate.so.1
 
 #This makes sure the $(obj) subdirectory exists even though vdso32/

arch/x86/Kconfig

@@ -1940,6 +1940,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS
 
 	  If unsure, say y.
 
+choice
+	prompt "TSX enable mode"
+	depends on CPU_SUP_INTEL
+	default X86_INTEL_TSX_MODE_OFF
+	help
+	  Intel's TSX (Transactional Synchronization Extensions) feature
+	  allows to optimize locking protocols through lock elision which
+	  can lead to a noticeable performance boost.
+
+	  On the other hand it has been shown that TSX can be exploited
+	  to form side channel attacks (e.g. TAA) and chances are there
+	  will be more of those attacks discovered in the future.
+
+	  Therefore TSX is not enabled by default (aka tsx=off). An admin
+	  might override this decision by tsx=on the command line parameter.
+	  Even with TSX enabled, the kernel will attempt to enable the best
+	  possible TAA mitigation setting depending on the microcode available
+	  for the particular machine.
+
+	  This option allows to set the default tsx mode between tsx=on, =off
+	  and =auto. See Documentation/admin-guide/kernel-parameters.txt for more
+	  details.
+
+	  Say off if not sure, auto if TSX is in use but it should be used on safe
+	  platforms or on if TSX is in use and the security aspect of tsx is not
+	  relevant.
+
+config X86_INTEL_TSX_MODE_OFF
+	bool "off"
+	help
+	  TSX is disabled if possible - equals to tsx=off command line parameter.
+
+config X86_INTEL_TSX_MODE_ON
+	bool "on"
+	help
+	  TSX is always enabled on TSX capable HW - equals the tsx=on command
+	  line parameter.
+
+config X86_INTEL_TSX_MODE_AUTO
+	bool "auto"
+	help
+	  TSX is enabled on TSX capable HW that is believed to be safe against
+	  side channel attacks- equals the tsx=auto command line parameter.
+endchoice
+
 config EFI
 	bool "EFI runtime service support"
 	depends on ACPI

arch/x86/include/asm/cpufeatures.h

@@ -399,5 +399,7 @@
 #define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
 #define X86_BUG_MSBDS_ONLY		X86_BUG(20) /* CPU is only affected by the  MSDBS variant of BUG_MDS */
 #define X86_BUG_SWAPGS			X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
+#define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
+#define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

arch/x86/include/asm/kvm_host.h

@@ -312,9 +312,12 @@ struct kvm_rmap_head {
 struct kvm_mmu_page {
 	struct list_head link;
 	struct hlist_node hash_link;
+	struct list_head lpage_disallowed_link;
+
 	bool unsync;
 	u8 mmu_valid_gen;
 	bool mmio_cached;
+	bool lpage_disallowed; /* Can't be replaced by an equiv large page */
 
 	/*
 	 * The following two entries are used to key the shadow page in the
@@ -859,6 +862,7 @@ struct kvm_arch {
 	 */
 	struct list_head active_mmu_pages;
 	struct list_head zapped_obsolete_pages;
+	struct list_head lpage_disallowed_mmu_pages;
 	struct kvm_page_track_notifier_node mmu_sp_tracker;
 	struct kvm_page_track_notifier_head track_notifier_head;
 
@@ -933,6 +937,7 @@ struct kvm_arch {
 	bool exception_payload_enabled;
 
 	struct kvm_pmu_event_filter *pmu_event_filter;
+	struct task_struct *nx_lpage_recovery_thread;
 };
 
 struct kvm_vm_stat {
@@ -946,6 +951,7 @@ struct kvm_vm_stat {
 	ulong mmu_unsync;
 	ulong remote_tlb_flush;
 	ulong lpages;
+	ulong nx_lpage_splits;
 	ulong max_mmu_page_hash_collisions;
 };
 

arch/x86/include/asm/msr-index.h

@@ -93,6 +93,18 @@
 						  * Microarchitectural Data
 						  * Sampling (MDS) vulnerabilities.
 						  */
+#define ARCH_CAP_PSCHANGE_MC_NO		BIT(6)	 /*
+						  * The processor is not susceptible to a
+						  * machine check error due to modifying the
+						  * code page size along with either the
+						  * physical address or cache type
+						  * without TLB invalidation.
+						  */
+#define ARCH_CAP_TSX_CTRL_MSR		BIT(7)	/* MSR for TSX control is available. */
+#define ARCH_CAP_TAA_NO			BIT(8)	/*
+						 * Not susceptible to
+						 * TSX Async Abort (TAA) vulnerabilities.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@@ -103,6 +115,10 @@
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
+#define MSR_IA32_TSX_CTRL		0x00000122
+#define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
+#define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
+
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
 #define MSR_IA32_SYSENTER_EIP		0x00000176

arch/x86/include/asm/nospec-branch.h

@@ -314,7 +314,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 #include <asm/segment.h>
 
 /**
- * mds_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
  *
  * This uses the otherwise unused and obsolete VERW instruction in
  * combination with microcode which triggers a CPU buffer flush when the
@@ -337,7 +337,7 @@ static inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */

arch/x86/include/asm/processor.h

@@ -988,4 +988,11 @@ enum mds_mitigations {
 	MDS_MITIGATION_VMWERV,
 };
 
+enum taa_mitigations {
+	TAA_MITIGATION_OFF,
+	TAA_MITIGATION_UCODE_NEEDED,
+	TAA_MITIGATION_VERW,
+	TAA_MITIGATION_TSX_DISABLED,
+};
+
 #endif /* _ASM_X86_PROCESSOR_H */

arch/x86/kernel/apic/apic.c

@@ -1586,9 +1586,6 @@ static void setup_local_APIC(void)
 {
 	int cpu = smp_processor_id();
 	unsigned int value;
-#ifdef CONFIG_X86_32
-	int logical_apicid, ldr_apicid;
-#endif
 
 	if (disable_apic) {
 		disable_ioapic_support();
@@ -1626,16 +1623,21 @@ static void setup_local_APIC(void)
 	apic->init_apic_ldr();
 
 #ifdef CONFIG_X86_32
-	/*
+	if (apic->dest_logical) {
-	 * APIC LDR is initialized.  If logical_apicid mapping was
+		int logical_apicid, ldr_apicid;
-	 * initialized during get_smp_config(), make sure it matches the
+
-	 * actual value.
+		/*
-	 */
+		 * APIC LDR is initialized.  If logical_apicid mapping was
-	logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+		 * initialized during get_smp_config(), make sure it matches
-	ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+		 * the actual value.
-	WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid);
+		 */
-	/* always use the value from LDR */
+		logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
-	early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+		ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+		if (logical_apicid != BAD_APICID)
+			WARN_ON(logical_apicid != ldr_apicid);
+		/* Always use the value from LDR. */
+		early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+	}
 #endif
 
 	/*

arch/x86/kernel/cpu/Makefile

@@ -30,7 +30,7 @@ obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
 
 ifdef CONFIG_CPU_SUP_INTEL
-obj-y			+= intel.o intel_pconfig.o
+obj-y			+= intel.o intel_pconfig.o tsx.o
 obj-$(CONFIG_PM)	+= intel_epb.o
 endif
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o

arch/x86/kernel/cpu/bugs.c

@@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
+static void __init taa_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -105,6 +106,7 @@ void __init check_bugs(void)
 	ssb_select_mitigation();
 	l1tf_select_mitigation();
 	mds_select_mitigation();
+	taa_select_mitigation();
 
 	arch_smt_update();
 
@@ -268,6 +270,100 @@ static int __init mds_cmdline(char *str)
 }
 early_param("mds", mds_cmdline);
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"TAA: " fmt
+
+/* Default mitigation for TAA-affected CPUs */
+static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW;
+static bool taa_nosmt __ro_after_init;
+
+static const char * const taa_strings[] = {
+	[TAA_MITIGATION_OFF]		= "Vulnerable",
+	[TAA_MITIGATION_UCODE_NEEDED]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
+	[TAA_MITIGATION_VERW]		= "Mitigation: Clear CPU buffers",
+	[TAA_MITIGATION_TSX_DISABLED]	= "Mitigation: TSX disabled",
+};
+
+static void __init taa_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_TAA)) {
+		taa_mitigation = TAA_MITIGATION_OFF;
+		return;
+	}
+
+	/* TSX previously disabled by tsx=off */
+	if (!boot_cpu_has(X86_FEATURE_RTM)) {
+		taa_mitigation = TAA_MITIGATION_TSX_DISABLED;
+		goto out;
+	}
+
+	if (cpu_mitigations_off()) {
+		taa_mitigation = TAA_MITIGATION_OFF;
+		return;
+	}
+
+	/* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */
+	if (taa_mitigation == TAA_MITIGATION_OFF)
+		goto out;
+
+	if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
+		taa_mitigation = TAA_MITIGATION_VERW;
+	else
+		taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+
+	/*
+	 * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1.
+	 * A microcode update fixes this behavior to clear CPU buffers. It also
+	 * adds support for MSR_IA32_TSX_CTRL which is enumerated by the
+	 * ARCH_CAP_TSX_CTRL_MSR bit.
+	 *
+	 * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
+	 * update is required.
+	 */
+	ia32_cap = x86_read_arch_cap_msr();
+	if ( (ia32_cap & ARCH_CAP_MDS_NO) &&
+	    !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR))
+		taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+
+	/*
+	 * TSX is enabled, select alternate mitigation for TAA which is
+	 * the same as MDS. Enable MDS static branch to clear CPU buffers.
+	 *
+	 * For guests that can't determine whether the correct microcode is
+	 * present on host, enable the mitigation for UCODE_NEEDED as well.
+	 */
+	static_branch_enable(&mds_user_clear);
+
+	if (taa_nosmt || cpu_mitigations_auto_nosmt())
+		cpu_smt_disable(false);
+
+out:
+	pr_info("%s\n", taa_strings[taa_mitigation]);
+}
+
+static int __init tsx_async_abort_parse_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_TAA))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off")) {
+		taa_mitigation = TAA_MITIGATION_OFF;
+	} else if (!strcmp(str, "full")) {
+		taa_mitigation = TAA_MITIGATION_VERW;
+	} else if (!strcmp(str, "full,nosmt")) {
+		taa_mitigation = TAA_MITIGATION_VERW;
+		taa_nosmt = true;
+	}
+
+	return 0;
+}
+early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
+
 #undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
@@ -786,13 +882,10 @@ static void update_mds_branch_idle(void)
 }
 
 #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
 
 void cpu_bugs_smt_update(void)
 {
-	/* Enhanced IBRS implies STIBP. No update required. */
-	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
-		return;
-
 	mutex_lock(&spec_ctrl_mutex);
 
 	switch (spectre_v2_user) {
@@ -819,6 +912,17 @@ void cpu_bugs_smt_update(void)
 		break;
 	}
 
+	switch (taa_mitigation) {
+	case TAA_MITIGATION_VERW:
+	case TAA_MITIGATION_UCODE_NEEDED:
+		if (sched_smt_active())
+			pr_warn_once(TAA_MSG_SMT);
+		break;
+	case TAA_MITIGATION_TSX_DISABLED:
+	case TAA_MITIGATION_OFF:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -1149,6 +1253,9 @@ void x86_spec_ctrl_setup_ap(void)
 		x86_amd_ssb_disable();
 }
 
+bool itlb_multihit_kvm_mitigation;
+EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation);
+
 #undef pr_fmt
 #define pr_fmt(fmt)	"L1TF: " fmt
 
@@ -1304,11 +1411,24 @@ static ssize_t l1tf_show_state(char *buf)
 		       l1tf_vmx_states[l1tf_vmx_mitigation],
 		       sched_smt_active() ? "vulnerable" : "disabled");
 }
+
+static ssize_t itlb_multihit_show_state(char *buf)
+{
+	if (itlb_multihit_kvm_mitigation)
+		return sprintf(buf, "KVM: Mitigation: Split huge pages\n");
+	else
+		return sprintf(buf, "KVM: Vulnerable\n");
+}
 #else
 static ssize_t l1tf_show_state(char *buf)
 {
 	return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
 }
+
+static ssize_t itlb_multihit_show_state(char *buf)
+{
+	return sprintf(buf, "Processor vulnerable\n");
+}
 #endif
 
 static ssize_t mds_show_state(char *buf)
@@ -1328,6 +1448,21 @@ static ssize_t mds_show_state(char *buf)
 		       sched_smt_active() ? "vulnerable" : "disabled");
 }
 
+static ssize_t tsx_async_abort_show_state(char *buf)
+{
+	if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) ||
+	    (taa_mitigation == TAA_MITIGATION_OFF))
+		return sprintf(buf, "%s\n", taa_strings[taa_mitigation]);
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		return sprintf(buf, "%s; SMT Host state unknown\n",
+			       taa_strings[taa_mitigation]);
+	}
+
+	return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation],
+		       sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1398,6 +1533,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_MDS:
 		return mds_show_state(buf);
 
+	case X86_BUG_TAA:
+		return tsx_async_abort_show_state(buf);
+
+	case X86_BUG_ITLB_MULTIHIT:
+		return itlb_multihit_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1434,4 +1575,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
 }
+
+ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_TAA);
+}
+
+ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT);
+}
 #endif

arch/x86/kernel/cpu/common.c

@@ -1016,13 +1016,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define NO_SPECULATION	BIT(0)
+#define NO_SPECULATION		BIT(0)
-#define NO_MELTDOWN	BIT(1)
+#define NO_MELTDOWN		BIT(1)
-#define NO_SSB		BIT(2)
+#define NO_SSB			BIT(2)
-#define NO_L1TF		BIT(3)
+#define NO_L1TF			BIT(3)
-#define NO_MDS		BIT(4)
+#define NO_MDS			BIT(4)
-#define MSBDS_ONLY	BIT(5)
+#define MSBDS_ONLY		BIT(5)
-#define NO_SWAPGS	BIT(6)
+#define NO_SWAPGS		BIT(6)
+#define NO_ITLB_MULTIHIT	BIT(7)
 
 #define VULNWL(_vendor, _family, _model, _whitelist)	\
 	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -1043,27 +1044,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
 
 	/* Intel Family 6 */
-	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
 
-	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_SILVERMONT_D,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SILVERMONT_D,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
-	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	/*
 	 * Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1073,15 +1074,17 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	 * good enough for our purposes.
 	 */
 
+	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT),
+
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
 	{}
 };
 
@@ -1092,19 +1095,30 @@ static bool __init cpu_matches(unsigned long which)
 	return m && !!(m->driver_data & which);
 }
 
-static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
+u64 x86_read_arch_cap_msr(void)
 {
 	u64 ia32_cap = 0;
 
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+
+	return ia32_cap;
+}
+
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
+{
+	u64 ia32_cap = x86_read_arch_cap_msr();
+
+	/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
+	if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
+		setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
+
 	if (cpu_matches(NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
-	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
-
 	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
@@ -1121,6 +1135,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (!cpu_matches(NO_SWAPGS))
 		setup_force_cpu_bug(X86_BUG_SWAPGS);
 
+	/*
+	 * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when:
+	 *	- TSX is supported or
+	 *	- TSX_CTRL is present
+	 *
+	 * TSX_CTRL check is needed for cases when TSX could be disabled before
+	 * the kernel boot e.g. kexec.
+	 * TSX_CTRL check alone is not sufficient for cases when the microcode
+	 * update is not present or running as guest that don't get TSX_CTRL.
+	 */
+	if (!(ia32_cap & ARCH_CAP_TAA_NO) &&
+	    (cpu_has(c, X86_FEATURE_RTM) ||
+	     (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
+		setup_force_cpu_bug(X86_BUG_TAA);
+
 	if (cpu_matches(NO_MELTDOWN))
 		return;
 
@@ -1554,6 +1583,8 @@ void __init identify_boot_cpu(void)
 #endif
 	cpu_detect_tlb(&boot_cpu_data);
 	setup_cr_pinning();
+
+	tsx_init();
 }
 
 void identify_secondary_cpu(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/cpu.h

@@ -44,6 +44,22 @@ struct _tlb_table {
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
+#ifdef CONFIG_CPU_SUP_INTEL
+enum tsx_ctrl_states {
+	TSX_CTRL_ENABLE,
+	TSX_CTRL_DISABLE,
+	TSX_CTRL_NOT_SUPPORTED,
+};
+
+extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state;
+
+extern void __init tsx_init(void);
+extern void tsx_enable(void);
+extern void tsx_disable(void);
+#else
+static inline void tsx_init(void) { }
+#endif /* CONFIG_CPU_SUP_INTEL */
+
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
@@ -62,4 +78,6 @@ unsigned int aperfmperf_get_khz(int cpu);
 
 extern void x86_spec_ctrl_setup_ap(void);
 
+extern u64 x86_read_arch_cap_msr(void);
+
 #endif /* ARCH_X86_CPU_H */

arch/x86/kernel/cpu/intel.c

@@ -762,6 +762,11 @@ static void init_intel(struct cpuinfo_x86 *c)
 		detect_tme(c);
 
 	init_intel_misc_features(c);
+
+	if (tsx_ctrl_state == TSX_CTRL_ENABLE)
+		tsx_enable();
+	if (tsx_ctrl_state == TSX_CTRL_DISABLE)
+		tsx_disable();
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/cpu/resctrl/ctrlmondata.c

@@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto out;
+	}
 
 	md.priv = of->kn->priv;
 	resid = md.u.rid;

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 	}
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	rdt_last_cmd_clear();
 	if (!rdtgrp) {
 		ret = -ENOENT;
-		rdt_last_cmd_puts("Directory was removed\n");
 		goto unlock;
 	}
 
@@ -2648,10 +2646,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	int ret;
 
 	prdtgrp = rdtgroup_kn_lock_live(prgrp_kn);
-	rdt_last_cmd_clear();
 	if (!prdtgrp) {
 		ret = -ENODEV;
-		rdt_last_cmd_puts("Directory was removed\n");
 		goto out_unlock;
 	}
 

arch/x86/kernel/cpu/tsx.c

@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Transactional Synchronization Extensions (TSX) control.
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author:
+ *	Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
+ */
+
+#include <linux/cpufeature.h>
+
+#include <asm/cmdline.h>
+
+#include "cpu.h"
+
+enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED;
+
+void tsx_disable(void)
+{
+	u64 tsx;
+
+	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+
+	/* Force all transactions to immediately abort */
+	tsx |= TSX_CTRL_RTM_DISABLE;
+
+	/*
+	 * Ensure TSX support is not enumerated in CPUID.
+	 * This is visible to userspace and will ensure they
+	 * do not waste resources trying TSX transactions that
+	 * will always abort.
+	 */
+	tsx |= TSX_CTRL_CPUID_CLEAR;
+
+	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+}
+
+void tsx_enable(void)
+{
+	u64 tsx;
+
+	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+
+	/* Enable the RTM feature in the cpu */
+	tsx &= ~TSX_CTRL_RTM_DISABLE;
+
+	/*
+	 * Ensure TSX support is enumerated in CPUID.
+	 * This is visible to userspace and will ensure they
+	 * can enumerate and use the TSX feature.
+	 */
+	tsx &= ~TSX_CTRL_CPUID_CLEAR;
+
+	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+}
+
+static bool __init tsx_ctrl_is_supported(void)
+{
+	u64 ia32_cap = x86_read_arch_cap_msr();
+
+	/*
+	 * TSX is controlled via MSR_IA32_TSX_CTRL.  However, support for this
+	 * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES.
+	 *
+	 * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a
+	 * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES
+	 * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get
+	 * MSR_IA32_TSX_CTRL support even after a microcode update. Thus,
+	 * tsx= cmdline requests will do nothing on CPUs without
+	 * MSR_IA32_TSX_CTRL support.
+	 */
+	return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR);
+}
+
+static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
+{
+	if (boot_cpu_has_bug(X86_BUG_TAA))
+		return TSX_CTRL_DISABLE;
+
+	return TSX_CTRL_ENABLE;
+}
+
+void __init tsx_init(void)
+{
+	char arg[5] = {};
+	int ret;
+
+	if (!tsx_ctrl_is_supported())
+		return;
+
+	ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg));
+	if (ret >= 0) {
+		if (!strcmp(arg, "on")) {
+			tsx_ctrl_state = TSX_CTRL_ENABLE;
+		} else if (!strcmp(arg, "off")) {
+			tsx_ctrl_state = TSX_CTRL_DISABLE;
+		} else if (!strcmp(arg, "auto")) {
+			tsx_ctrl_state = x86_get_tsx_auto_mode();
+		} else {
+			tsx_ctrl_state = TSX_CTRL_DISABLE;
+			pr_err("tsx: invalid option, defaulting to off\n");
+		}
+	} else {
+		/* tsx= not provided */
+		if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO))
+			tsx_ctrl_state = x86_get_tsx_auto_mode();
+		else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF))
+			tsx_ctrl_state = TSX_CTRL_DISABLE;
+		else
+			tsx_ctrl_state = TSX_CTRL_ENABLE;
+	}
+
+	if (tsx_ctrl_state == TSX_CTRL_DISABLE) {
+		tsx_disable();
+
+		/*
+		 * tsx_disable() will change the state of the
+		 * RTM CPUID bit.  Clear it here since it is now
+		 * expected to be not set.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_RTM);
+	} else if (tsx_ctrl_state == TSX_CTRL_ENABLE) {
+
+		/*
+		 * HW defaults TSX to be enabled at bootup.
+		 * We may still need the TSX enable support
+		 * during init for special cases like
+		 * kexec after TSX is disabled.
+		 */
+		tsx_enable();
+
+		/*
+		 * tsx_enable() will change the state of the
+		 * RTM CPUID bit.  Force it here since it is now
+		 * expected to be set.
+		 */
+		setup_force_cpu_cap(X86_FEATURE_RTM);
+	}
+}

arch/x86/kernel/dumpstack_64.c

@@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
 	begin = (unsigned long)__this_cpu_read(cea_exception_stacks);
+	/*
+	 * Handle the case where stack trace is collected _before_
+	 * cea_exception_stacks had been initialized.
+	 */
+	if (!begin)
+		return false;
+
 	end = begin + sizeof(struct cea_exception_stacks);
 	/* Bail if @stack is outside the exception stack area. */
 	if (stk < begin || stk >= end)

arch/x86/kernel/early-quirks.c

@@ -710,6 +710,8 @@ static struct chipset early_qrk[] __initdata = {
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+	{ PCI_VENDOR_ID_INTEL, 0x3ec4,
+		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
 	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}

arch/x86/kernel/tsc.c

@@ -1505,6 +1505,9 @@ void __init tsc_init(void)
 		return;
 	}
 
+	if (tsc_clocksource_reliable || no_tsc_watchdog)
+		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
 }

arch/x86/kvm/mmu.c

@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/hash.h>
 #include <linux/kern_levels.h>
+#include <linux/kthread.h>
 
 #include <asm/page.h>
 #include <asm/pat.h>
@@ -47,6 +48,35 @@
 #include <asm/kvm_page_track.h>
 #include "trace.h"
 
+extern bool itlb_multihit_kvm_mitigation;
+
+static int __read_mostly nx_huge_pages = -1;
+#ifdef CONFIG_PREEMPT_RT
+/* Recovery can cause latency spikes, disable it for PREEMPT_RT.  */
+static uint __read_mostly nx_huge_pages_recovery_ratio = 0;
+#else
+static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
+#endif
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp);
+static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp);
+
+static struct kernel_param_ops nx_huge_pages_ops = {
+	.set = set_nx_huge_pages,
+	.get = param_get_bool,
+};
+
+static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = {
+	.set = set_nx_huge_pages_recovery_ratio,
+	.get = param_get_uint,
+};
+
+module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages, "bool");
+module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops,
+		&nx_huge_pages_recovery_ratio, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");
+
 /*
  * When setting this variable to true it enables Two-Dimensional-Paging
  * where the hardware walks 2 page tables:
@@ -352,6 +382,11 @@ static inline bool spte_ad_need_write_protect(u64 spte)
 	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
 }
 
+static bool is_nx_huge_page_enabled(void)
+{
+	return READ_ONCE(nx_huge_pages);
+}
+
 static inline u64 spte_shadow_accessed_mask(u64 spte)
 {
 	MMU_WARN_ON(is_mmio_spte(spte));
@@ -1190,6 +1225,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 }
 
+static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	if (sp->lpage_disallowed)
+		return;
+
+	++kvm->stat.nx_lpage_splits;
+	list_add_tail(&sp->lpage_disallowed_link,
+		      &kvm->arch.lpage_disallowed_mmu_pages);
+	sp->lpage_disallowed = true;
+}
+
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	struct kvm_memslots *slots;
@@ -1207,6 +1253,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
 
+static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	--kvm->stat.nx_lpage_splits;
+	sp->lpage_disallowed = false;
+	list_del(&sp->lpage_disallowed_link);
+}
+
 static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
 					  struct kvm_memory_slot *slot)
 {
@@ -2792,6 +2845,9 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 			kvm_reload_remote_mmus(kvm);
 	}
 
+	if (sp->lpage_disallowed)
+		unaccount_huge_nx_page(kvm, sp);
+
 	sp->role.invalid = 1;
 	return list_unstable;
 }
@@ -3013,6 +3069,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (!speculative)
 		spte |= spte_shadow_accessed_mask(spte);
 
+	if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) &&
+	    is_nx_huge_page_enabled()) {
+		pte_access &= ~ACC_EXEC_MASK;
+	}
+
 	if (pte_access & ACC_EXEC_MASK)
 		spte |= shadow_x_mask;
 	else
@@ -3233,9 +3294,32 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
+static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
+				       gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
+{
+	int level = *levelp;
+	u64 spte = *it.sptep;
+
+	if (it.level == level && level > PT_PAGE_TABLE_LEVEL &&
+	    is_nx_huge_page_enabled() &&
+	    is_shadow_present_pte(spte) &&
+	    !is_large_pte(spte)) {
+		/*
+		 * A small SPTE exists for this pfn, but FNAME(fetch)
+		 * and __direct_map would like to create a large PTE
+		 * instead: just force them to go down another level,
+		 * patching back for them into pfn the next 9 bits of
+		 * the address.
+		 */
+		u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1);
+		*pfnp |= gfn & page_mask;
+		(*levelp)--;
+	}
+}
+
 static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 			int map_writable, int level, kvm_pfn_t pfn,
-			bool prefault)
+			bool prefault, bool lpage_disallowed)
 {
 	struct kvm_shadow_walk_iterator it;
 	struct kvm_mmu_page *sp;
@@ -3248,6 +3332,12 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 
 	trace_kvm_mmu_spte_requested(gpa, level, pfn);
 	for_each_shadow_entry(vcpu, gpa, it) {
+		/*
+		 * We cannot overwrite existing page tables with an NX
+		 * large page, as the leaf could be executable.
+		 */
+		disallowed_hugepage_adjust(it, gfn, &pfn, &level);
+
 		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 		if (it.level == level)
 			break;
@@ -3258,6 +3348,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 					      it.level - 1, true, ACC_ALL);
 
 			link_shadow_page(vcpu, it.sptep, sp);
+			if (lpage_disallowed)
+				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
 
@@ -3306,7 +3398,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 * here.
 	 */
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
-	    level == PT_PAGE_TABLE_LEVEL &&
+	    !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompoundMap(pfn_to_page(pfn)) &&
 	    !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
 		unsigned long mask;
@@ -3550,11 +3642,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 {
 	int r;
 	int level;
-	bool force_pt_level = false;
+	bool force_pt_level;
 	kvm_pfn_t pfn;
 	unsigned long mmu_seq;
 	bool map_writable, write = error_code & PFERR_WRITE_MASK;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
 
+	force_pt_level = lpage_disallowed;
 	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
 		/*
@@ -3588,7 +3683,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault);
+	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+			 prefault, false);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
@@ -4174,6 +4270,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	unsigned long mmu_seq;
 	int write = error_code & PFERR_WRITE_MASK;
 	bool map_writable;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
 
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
@@ -4184,8 +4282,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	if (r)
 		return r;
 
-	force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn,
+	force_pt_level =
-							   PT_DIRECTORY_LEVEL);
+		lpage_disallowed ||
+		!check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL);
 	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
 		if (level > PT_DIRECTORY_LEVEL &&
@@ -4214,7 +4313,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault);
+	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
+			 prefault, lpage_disallowed);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
@@ -5914,9 +6014,9 @@ restart:
 		 * the guest, and the guest page table is using 4K page size
 		 * mapping if the indirect sp has level = 1.
 		 */
-		if (sp->role.direct &&
+		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
-			!kvm_is_reserved_pfn(pfn) &&
+		    !kvm_is_zone_device_pfn(pfn) &&
-			PageTransCompoundMap(pfn_to_page(pfn))) {
+		    PageTransCompoundMap(pfn_to_page(pfn))) {
 			pte_list_remove(rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
@@ -6155,10 +6255,59 @@ static void kvm_set_mmio_spte_mask(void)
 	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
 }
 
+static bool get_nx_auto_mode(void)
+{
+	/* Return true when CPU has the bug, and mitigations are ON */
+	return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off();
+}
+
+static void __set_nx_huge_pages(bool val)
+{
+	nx_huge_pages = itlb_multihit_kvm_mitigation = val;
+}
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
+{
+	bool old_val = nx_huge_pages;
+	bool new_val;
+
+	/* In "auto" mode deploy workaround only if CPU has the bug. */
+	if (sysfs_streq(val, "off"))
+		new_val = 0;
+	else if (sysfs_streq(val, "force"))
+		new_val = 1;
+	else if (sysfs_streq(val, "auto"))
+		new_val = get_nx_auto_mode();
+	else if (strtobool(val, &new_val) < 0)
+		return -EINVAL;
+
+	__set_nx_huge_pages(new_val);
+
+	if (new_val != old_val) {
+		struct kvm *kvm;
+
+		mutex_lock(&kvm_lock);
+
+		list_for_each_entry(kvm, &vm_list, vm_list) {
+			mutex_lock(&kvm->slots_lock);
+			kvm_mmu_zap_all_fast(kvm);
+			mutex_unlock(&kvm->slots_lock);
+
+			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+		}
+		mutex_unlock(&kvm_lock);
+	}
+
+	return 0;
+}
+
 int kvm_mmu_module_init(void)
 {
 	int ret = -ENOMEM;
 
+	if (nx_huge_pages == -1)
+		__set_nx_huge_pages(get_nx_auto_mode());
+
 	/*
 	 * MMU roles use union aliasing which is, generally speaking, an
 	 * undefined behavior. However, we supposedly know how compilers behave
@@ -6238,3 +6387,116 @@ void kvm_mmu_module_exit(void)
 	unregister_shrinker(&mmu_shrinker);
 	mmu_audit_disable();
 }
+
+static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp)
+{
+	unsigned int old_val;
+	int err;
+
+	old_val = nx_huge_pages_recovery_ratio;
+	err = param_set_uint(val, kp);
+	if (err)
+		return err;
+
+	if (READ_ONCE(nx_huge_pages) &&
+	    !old_val && nx_huge_pages_recovery_ratio) {
+		struct kvm *kvm;
+
+		mutex_lock(&kvm_lock);
+
+		list_for_each_entry(kvm, &vm_list, vm_list)
+			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+
+		mutex_unlock(&kvm_lock);
+	}
+
+	return err;
+}
+
+static void kvm_recover_nx_lpages(struct kvm *kvm)
+{
+	int rcu_idx;
+	struct kvm_mmu_page *sp;
+	unsigned int ratio;
+	LIST_HEAD(invalid_list);
+	ulong to_zap;
+
+	rcu_idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+	to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0;
+	while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) {
+		/*
+		 * We use a separate list instead of just using active_mmu_pages
+		 * because the number of lpage_disallowed pages is expected to
+		 * be relatively small compared to the total.
+		 */
+		sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+				      struct kvm_mmu_page,
+				      lpage_disallowed_link);
+		WARN_ON_ONCE(!sp->lpage_disallowed);
+		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+		WARN_ON_ONCE(sp->lpage_disallowed);
+
+		if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+			kvm_mmu_commit_zap_page(kvm, &invalid_list);
+			if (to_zap)
+				cond_resched_lock(&kvm->mmu_lock);
+		}
+	}
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, rcu_idx);
+}
+
+static long get_nx_lpage_recovery_timeout(u64 start_time)
+{
+	return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio)
+		? start_time + 60 * HZ - get_jiffies_64()
+		: MAX_SCHEDULE_TIMEOUT;
+}
+
+static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+{
+	u64 start_time;
+	long remaining_time;
+
+	while (true) {
+		start_time = get_jiffies_64();
+		remaining_time = get_nx_lpage_recovery_timeout(start_time);
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		while (!kthread_should_stop() && remaining_time > 0) {
+			schedule_timeout(remaining_time);
+			remaining_time = get_nx_lpage_recovery_timeout(start_time);
+			set_current_state(TASK_INTERRUPTIBLE);
+		}
+
+		set_current_state(TASK_RUNNING);
+
+		if (kthread_should_stop())
+			return 0;
+
+		kvm_recover_nx_lpages(kvm);
+	}
+}
+
+int kvm_mmu_post_init_vm(struct kvm *kvm)
+{
+	int err;
+
+	err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+					  "kvm-nx-lpage-recovery",
+					  &kvm->arch.nx_lpage_recovery_thread);
+	if (!err)
+		kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+
+	return err;
+}
+
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
+{
+	if (kvm->arch.nx_lpage_recovery_thread)
+		kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+}

arch/x86/kvm/mmu.h

@@ -210,4 +210,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
 int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+
+int kvm_mmu_post_init_vm(struct kvm *kvm);
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
+
 #endif

arch/x86/kvm/paging_tmpl.h

@@ -614,13 +614,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
-			 kvm_pfn_t pfn, bool map_writable, bool prefault)
+			 kvm_pfn_t pfn, bool map_writable, bool prefault,
+			 bool lpage_disallowed)
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
 	int top_level, ret;
-	gfn_t base_gfn;
+	gfn_t gfn, base_gfn;
 
 	direct_access = gw->pte_access;
 
@@ -665,13 +666,25 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	base_gfn = gw->gfn;
+	/*
+	 * FNAME(page_fault) might have clobbered the bottom bits of
+	 * gw->gfn, restore them from the virtual address.
+	 */
+	gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT);
+	base_gfn = gfn;
 
 	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
 
 	for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
 		clear_sp_write_flooding_count(it.sptep);
-		base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+
+		/*
+		 * We cannot overwrite existing page tables with an NX
+		 * large page, as the leaf could be executable.
+		 */
+		disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
+
+		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 		if (it.level == hlevel)
 			break;
 
@@ -683,6 +696,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
 					      it.level - 1, true, direct_access);
 			link_shadow_page(vcpu, it.sptep, sp);
+			if (lpage_disallowed)
+				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
 
@@ -759,9 +774,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int r;
 	kvm_pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
-	bool force_pt_level = false;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
+	bool force_pt_level = lpage_disallowed;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -851,7 +868,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	if (!force_pt_level)
 		transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
 	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
-			 level, pfn, map_writable, prefault);
+			 level, pfn, map_writable, prefault, lpage_disallowed);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock:

arch/x86/kvm/vmx/vmx.c

@@ -1268,6 +1268,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
 		return;
 
+	/*
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
+	 * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
+	 * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
+	 * correctly.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
+		goto after_clear_sn;
+	}
+
 	/* The full case.  */
 	do {
 		old.control = new.control = pi_desc->control;
@@ -1283,6 +1295,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	} while (cmpxchg64(&pi_desc->control, old.control,
 			   new.control) != old.control);
 
+after_clear_sn:
+
 	/*
 	 * Clear SN before reading the bitmap.  The VT-d firmware
 	 * writes the bitmap and reads SN atomically (5.2.3 in the
@@ -1291,7 +1305,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	 */
 	smp_mb__after_atomic();
 
-	if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS))
+	if (!pi_is_pir_empty(pi_desc))
 		pi_set_on(pi_desc);
 }
 
@@ -6137,7 +6151,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	if (pi_test_on(&vmx->pi_desc)) {
 		pi_clear_on(&vmx->pi_desc);
 		/*
-		 * IOMMU can write to PIR.ON, so the barrier matters even on UP.
+		 * IOMMU can write to PID.ON, so the barrier matters even on UP.
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
@@ -6167,7 +6181,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 
 static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
 {
-	return pi_test_on(vcpu_to_pi_desc(vcpu));
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	return pi_test_on(pi_desc) ||
+		(pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
 }
 
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)

arch/x86/kvm/vmx/vmx.h

@@ -355,6 +355,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
 	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
 }
 
+static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
+{
+	return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+}
+
 static inline void pi_set_sn(struct pi_desc *pi_desc)
 {
 	set_bit(POSTED_INTR_SN,
@@ -373,6 +378,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc)
 		(unsigned long *)&pi_desc->control);
 }
 
+static inline void pi_clear_sn(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_SN,
+		(unsigned long *)&pi_desc->control);
+}
+
 static inline int pi_test_on(struct pi_desc *pi_desc)
 {
 	return test_bit(POSTED_INTR_ON,

arch/x86/kvm/x86.c

@@ -213,6 +213,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
 	{ "largepages", VM_STAT(lpages, .mode = 0444) },
+	{ "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) },
 	{ "max_mmu_page_hash_collisions",
 		VM_STAT(max_mmu_page_hash_collisions) },
 	{ NULL }
@@ -1132,13 +1133,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
- * This list is modified at module load time to reflect the
+ * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
+ * extract the supported MSRs from the related const lists.
+ * msrs_to_save is selected from the msrs_to_save_all to reflect the
  * capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
  * may depend on host virtualization features rather than host cpu features.
  */
 
-static u32 msrs_to_save[] = {
+static const u32 msrs_to_save_all[] = {
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -1179,9 +1182,10 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
 };
 
+static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
 static unsigned num_msrs_to_save;
 
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs_all[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
@@ -1220,7 +1224,7 @@ static u32 emulated_msrs[] = {
 	 * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
 	 * We always support the "true" VMX control MSRs, even if the host
 	 * processor does not, so I am putting these registers here rather
-	 * than in msrs_to_save.
+	 * than in msrs_to_save_all.
 	 */
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
@@ -1239,13 +1243,14 @@ static u32 emulated_msrs[] = {
 	MSR_KVM_POLL_CONTROL,
 };
 
+static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
 static unsigned num_emulated_msrs;
 
 /*
  * List of msr numbers which are used to expose MSR-based features that
  * can be used by a hypervisor to validate requested CPU features.
  */
-static u32 msr_based_features[] = {
+static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
 	MSR_IA32_VMX_PINBASED_CTLS,
@@ -1270,6 +1275,7 @@ static u32 msr_based_features[] = {
 	MSR_IA32_ARCH_CAPABILITIES,
 };
 
+static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
 static u64 kvm_get_arch_capabilities(void)
@@ -1279,6 +1285,14 @@ static u64 kvm_get_arch_capabilities(void)
 	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
 
+	/*
+	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
+	 * the nested hypervisor runs with NX huge pages.  If it is not,
+	 * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+	 * L1 guests, so it need not worry about its own (L2) guests.
+	 */
+	data |= ARCH_CAP_PSCHANGE_MC_NO;
+
 	/*
 	 * If we're doing cache flushes (either "always" or "cond")
 	 * we will do one whenever the guest does a vmlaunch/vmresume.
@@ -1298,6 +1312,25 @@ static u64 kvm_get_arch_capabilities(void)
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
 		data |= ARCH_CAP_MDS_NO;
 
+	/*
+	 * On TAA affected systems, export MDS_NO=0 when:
+	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
+	 *	- Updated microcode is present. This is detected by
+	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
+	 *	  that VERW clears CPU buffers.
+	 *
+	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
+	 * mitigation and don't complain:
+	 *
+	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
+	 *
+	 * If TSX is disabled on the system, guests are also mitigated against
+	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
+	    (data & ARCH_CAP_TSX_CTRL_MSR))
+		data &= ~ARCH_CAP_MDS_NO;
+
 	return data;
 }
 
@@ -5090,22 +5123,26 @@ static void kvm_init_msr_list(void)
 {
 	struct x86_pmu_capability x86_pmu;
 	u32 dummy[2];
-	unsigned i, j;
+	unsigned i;
 
 	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
-			 "Please update the fixed PMCs in msrs_to_save[]");
+			 "Please update the fixed PMCs in msrs_to_saved_all[]");
 
 	perf_get_x86_pmu_capability(&x86_pmu);
 
-	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
+	num_msrs_to_save = 0;
-		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
+	num_emulated_msrs = 0;
+	num_msr_based_features = 0;
+
+	for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
+		if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 
 		/*
 		 * Even MSRs that are valid in the host may not be exposed
 		 * to the guests in some cases.
 		 */
-		switch (msrs_to_save[i]) {
+		switch (msrs_to_save_all[i]) {
 		case MSR_IA32_BNDCFGS:
 			if (!kvm_mpx_supported())
 				continue;
@@ -5133,17 +5170,17 @@ static void kvm_init_msr_list(void)
 			break;
 		case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
 			if (!kvm_x86_ops->pt_supported() ||
-				msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >=
+				msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
 		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
-			if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
 			break;
 		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
-			if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
 		}
@@ -5151,34 +5188,25 @@ static void kvm_init_msr_list(void)
 			break;
 		}
 
-		if (j < i)
+		msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
-			msrs_to_save[j] = msrs_to_save[i];
-		j++;
 	}
-	num_msrs_to_save = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
+	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
-		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i]))
 			continue;
 
-		if (j < i)
+		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
-			emulated_msrs[j] = emulated_msrs[i];
-		j++;
 	}
-	num_emulated_msrs = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+	for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
 		struct kvm_msr_entry msr;
 
-		msr.index = msr_based_features[i];
+		msr.index = msr_based_features_all[i];
 		if (kvm_get_msr_feature(&msr))
 			continue;
 
-		if (j < i)
+		msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
-			msr_based_features[j] = msr_based_features[i];
-		j++;
 	}
-	num_msr_based_features = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -9428,6 +9456,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+	INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
@@ -9456,6 +9485,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	return kvm_x86_ops->vm_init(kvm);
 }
 
+int kvm_arch_post_init_vm(struct kvm *kvm)
+{
+	return kvm_mmu_post_init_vm(kvm);
+}
+
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);
@@ -9557,6 +9591,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 }
 EXPORT_SYMBOL_GPL(x86_set_memory_region);
 
+void kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+	kvm_mmu_pre_destroy_vm(kvm);
+}
+
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	if (current->mm == kvm->mm) {

block/bfq-iosched.c

@@ -2713,6 +2713,28 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	}
 }
 
+
+static
+void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * To prevent bfqq's service guarantees from being violated,
+	 * bfqq may be left busy, i.e., queued for service, even if
+	 * empty (see comments in __bfq_bfqq_expire() for
+	 * details). But, if no process will send requests to bfqq any
+	 * longer, then there is no point in keeping bfqq queued for
+	 * service. In addition, keeping bfqq queued for service, but
+	 * with no process ref any longer, may have caused bfqq to be
+	 * freed when dequeued from service. But this is assumed to
+	 * never happen.
+	 */
+	if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) &&
+	    bfqq != bfqd->in_service_queue)
+		bfq_del_bfqq_busy(bfqd, bfqq, false);
+
+	bfq_put_queue(bfqq);
+}
+
 static void
 bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
@@ -2783,8 +2805,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	 */
 	new_bfqq->pid = -1;
 	bfqq->bic = NULL;
-	/* release process reference to bfqq */
+	bfq_release_process_ref(bfqd, bfqq);
-	bfq_put_queue(bfqq);
 }
 
 static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
@@ -4899,7 +4920,7 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 	bfq_put_cooperator(bfqq);
 
-	bfq_put_queue(bfqq); /* release process reference */
+	bfq_release_process_ref(bfqd, bfqq);
 }
 
 static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
@@ -5001,8 +5022,7 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
 
 	bfqq = bic_to_bfqq(bic, false);
 	if (bfqq) {
-		/* release process reference on this queue */
+		bfq_release_process_ref(bfqd, bfqq);
-		bfq_put_queue(bfqq);
 		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
 		bic_set_bfqq(bic, bfqq, false);
 	}
@@ -5963,7 +5983,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
 
 	bfq_put_cooperator(bfqq);
 
-	bfq_put_queue(bfqq);
+	bfq_release_process_ref(bfqq->bfqd, bfqq);
 	return NULL;
 }
 

block/bio.c

@@ -751,7 +751,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return false;
 
-	if (bio->bi_vcnt > 0) {
+	if (bio->bi_vcnt > 0 && !bio_full(bio, len)) {
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {

block/blk-iocost.c

@@ -1057,9 +1057,12 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 	atomic64_set(&iocg->active_period, cur_period);
 
 	/* already activated or breaking leaf-only constraint? */
-	for (i = iocg->level; i > 0; i--)
+	if (!list_empty(&iocg->active_list))
-		if (!list_empty(&iocg->active_list))
+		goto succeed_unlock;
+	for (i = iocg->level - 1; i > 0; i--)
+		if (!list_empty(&iocg->ancestors[i]->active_list))
 			goto fail_unlock;
+
 	if (iocg->child_active_sum)
 		goto fail_unlock;
 
@@ -1101,6 +1104,7 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 		ioc_start_period(ioc, now);
 	}
 
+succeed_unlock:
 	spin_unlock_irq(&ioc->lock);
 	return true;
 

drivers/base/cpu.c

@@ -554,12 +554,27 @@ ssize_t __weak cpu_show_mds(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_tsx_async_abort(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
+ssize_t __weak cpu_show_itlb_multihit(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
 static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
+static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
+static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -568,6 +583,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_spec_store_bypass.attr,
 	&dev_attr_l1tf.attr,
 	&dev_attr_mds.attr,
+	&dev_attr_tsx_async_abort.attr,
+	&dev_attr_itlb_multihit.attr,
 	NULL
 };
 

drivers/base/memory.c

@@ -872,3 +872,39 @@ int walk_memory_blocks(unsigned long start, unsigned long size,
 	}
 	return ret;
 }
+
+struct for_each_memory_block_cb_data {
+	walk_memory_blocks_func_t func;
+	void *arg;
+};
+
+static int for_each_memory_block_cb(struct device *dev, void *data)
+{
+	struct memory_block *mem = to_memory_block(dev);
+	struct for_each_memory_block_cb_data *cb_data = data;
+
+	return cb_data->func(mem, cb_data->arg);
+}
+
+/**
+ * for_each_memory_block - walk through all present memory blocks
+ *
+ * @arg: argument passed to func
+ * @func: callback for each memory block walked
+ *
+ * This function walks through all present memory blocks, calling func on
+ * each memory block.
+ *
+ * In case func() returns an error, walking is aborted and the error is
+ * returned.
+ */
+int for_each_memory_block(void *arg, walk_memory_blocks_func_t func)
+{
+	struct for_each_memory_block_cb_data cb_data = {
+		.func = func,
+		.arg = arg,
+	};
+
+	return bus_for_each_dev(&memory_subsys, NULL, &cb_data,
+				for_each_memory_block_cb);
+}

drivers/block/rbd.c

@@ -2087,7 +2087,7 @@ static int rbd_object_map_update_finish(struct rbd_obj_request *obj_req,
 	struct rbd_device *rbd_dev = obj_req->img_request->rbd_dev;
 	struct ceph_osd_data *osd_data;
 	u64 objno;
-	u8 state, new_state, current_state;
+	u8 state, new_state, uninitialized_var(current_state);
 	bool has_current_state;
 	void *p;
 

drivers/block/rsxx/core.c

@@ -1000,8 +1000,10 @@ static void rsxx_pci_remove(struct pci_dev *dev)
 
 	cancel_work_sync(&card->event_work);
 
+	destroy_workqueue(card->event_wq);
 	rsxx_destroy_dev(card);
 	rsxx_dma_destroy(card);
+	destroy_workqueue(card->creg_ctrl.creg_wq);
 
 	spin_lock_irqsave(&card->irq_lock, flags);
 	rsxx_disable_ier_and_isr(card, CR_INTR_ALL);

drivers/char/hw_random/core.c

@@ -13,7 +13,6 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/err.h>
-#include <linux/freezer.h>
 #include <linux/fs.h>
 #include <linux/hw_random.h>
 #include <linux/kernel.h>
@@ -422,9 +421,7 @@ static int hwrng_fillfn(void *unused)
 {
 	long rc;
 
-	set_freezable();
+	while (!kthread_should_stop()) {
-
-	while (!kthread_freezable_should_stop(NULL)) {
 		struct hwrng *rng;
 
 		rng = get_current_rng();

drivers/char/random.c

@@ -327,7 +327,6 @@
 #include <linux/percpu.h>
 #include <linux/cryptohash.h>
 #include <linux/fips.h>
-#include <linux/freezer.h>
 #include <linux/ptrace.h>
 #include <linux/workqueue.h>
 #include <linux/irq.h>
@@ -2500,8 +2499,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 	 * We'll be woken up again once below random_write_wakeup_thresh,
 	 * or when the calling thread is about to terminate.
 	 */
-	wait_event_freezable(random_write_wait,
+	wait_event_interruptible(random_write_wait, kthread_should_stop() ||
-			kthread_should_stop() ||
 			ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
 	mix_pool_bytes(poolp, buffer, count);
 	credit_entropy_bits(poolp, entropy);

drivers/clocksource/sh_mtu2.c

@@ -328,12 +328,13 @@ static int sh_mtu2_register(struct sh_mtu2_channel *ch, const char *name)
 	return 0;
 }
 
+static const unsigned int sh_mtu2_channel_offsets[] = {
+	0x300, 0x380, 0x000,
+};
+
 static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 				 struct sh_mtu2_device *mtu)
 {
-	static const unsigned int channel_offsets[] = {
-		0x300, 0x380, 0x000,
-	};
 	char name[6];
 	int irq;
 	int ret;
@@ -356,7 +357,7 @@ static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 		return ret;
 	}
 
-	ch->base = mtu->mapbase + channel_offsets[index];
+	ch->base = mtu->mapbase + sh_mtu2_channel_offsets[index];
 	ch->index = index;
 
 	return sh_mtu2_register(ch, dev_name(&mtu->pdev->dev));
@@ -408,7 +409,12 @@ static int sh_mtu2_setup(struct sh_mtu2_device *mtu,
 	}
 
 	/* Allocate and setup the channels. */
-	mtu->num_channels = 3;
+	ret = platform_irq_count(pdev);
+	if (ret < 0)
+		goto err_unmap;
+
+	mtu->num_channels = min_t(unsigned int, ret,
+				  ARRAY_SIZE(sh_mtu2_channel_offsets));
 
 	mtu->channels = kcalloc(mtu->num_channels, sizeof(*mtu->channels),
 				GFP_KERNEL);

drivers/clocksource/timer-mediatek.c

@@ -268,15 +268,12 @@ static int __init mtk_syst_init(struct device_node *node)
 
 	ret = timer_of_init(node, &to);
 	if (ret)
-		goto err;
+		return ret;
 
 	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
 					TIMER_SYNC_TICKS, 0xffffffff);
 
 	return 0;
-err:
-	timer_of_cleanup(&to);
-	return ret;
 }
 
 static int __init mtk_gpt_init(struct device_node *node)
@@ -293,7 +290,7 @@ static int __init mtk_gpt_init(struct device_node *node)
 
 	ret = timer_of_init(node, &to);
 	if (ret)
-		goto err;
+		return ret;
 
 	/* Configure clock source */
 	mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
@@ -311,9 +308,6 @@ static int __init mtk_gpt_init(struct device_node *node)
 	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
 
 	return 0;
-err:
-	timer_of_cleanup(&to);
-	return ret;
 }
 TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
 TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);

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

@@ -950,21 +950,7 @@ static void psp_print_fw_hdr(struct psp_context *psp,
 			     struct amdgpu_firmware_info *ucode)
 {
 	struct amdgpu_device *adev = psp->adev;
-	const struct sdma_firmware_header_v1_0 *sdma_hdr =
+	struct common_firmware_header *hdr;
-		(const struct sdma_firmware_header_v1_0 *)
-		adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
-	const struct gfx_firmware_header_v1_0 *ce_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
-	const struct gfx_firmware_header_v1_0 *pfp_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
-	const struct gfx_firmware_header_v1_0 *me_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
-	const struct gfx_firmware_header_v1_0 *mec_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
-	const struct rlc_firmware_header_v2_0 *rlc_hdr =
-		(const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
-	const struct smc_firmware_header_v1_0 *smc_hdr =
-		(const struct smc_firmware_header_v1_0 *)adev->pm.fw->data;
 
 	switch (ucode->ucode_id) {
 	case AMDGPU_UCODE_ID_SDMA0:
@@ -975,25 +961,33 @@ static void psp_print_fw_hdr(struct psp_context *psp,
 	case AMDGPU_UCODE_ID_SDMA5:
 	case AMDGPU_UCODE_ID_SDMA6:
 	case AMDGPU_UCODE_ID_SDMA7:
-		amdgpu_ucode_print_sdma_hdr(&sdma_hdr->header);
+		hdr = (struct common_firmware_header *)
+			adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
+		amdgpu_ucode_print_sdma_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_CE:
-		amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.ce_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_PFP:
-		amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.pfp_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_ME:
-		amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.me_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_MEC1:
-		amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.mec_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_RLC_G:
-		amdgpu_ucode_print_rlc_hdr(&rlc_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.rlc_fw->data;
+		amdgpu_ucode_print_rlc_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_SMC:
-		amdgpu_ucode_print_smc_hdr(&smc_hdr->header);
+		hdr = (struct common_firmware_header *)adev->pm.fw->data;
+		amdgpu_ucode_print_smc_hdr(hdr);
 		break;
 	default:
 		break;

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

@@ -4896,6 +4896,9 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume)
 
 	power_domains->initializing = true;
 
+	/* Must happen before power domain init on VLV/CHV */
+	intel_update_rawclk(i915);
+
 	if (INTEL_GEN(i915) >= 11) {
 		icl_display_core_init(i915, resume);
 	} else if (IS_CANNONLAKE(i915)) {

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -319,6 +319,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
 
+	kfree(ctx->jump_whitelist);
+
 	if (ctx->timeline)
 		intel_timeline_put(ctx->timeline);
 
@@ -441,6 +443,9 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
+	ctx->jump_whitelist = NULL;
+	ctx->jump_whitelist_cmds = 0;
+
 	return ctx;
 
 err_free:

drivers/gpu/drm/i915/gem/i915_gem_context_types.h

@@ -192,6 +192,13 @@ struct i915_gem_context {
 	 * per vm, which may be one per context or shared with the global GTT)
 	 */
 	struct radix_tree_root handles_vma;
+
+	/** jump_whitelist: Bit array for tracking cmds during cmdparsing
+	 *  Guarded by struct_mutex
+	 */
+	unsigned long *jump_whitelist;
+	/** jump_whitelist_cmds: No of cmd slots available */
+	u32 jump_whitelist_cmds;
 };
 
 #endif /* __I915_GEM_CONTEXT_TYPES_H__ */

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -296,7 +296,9 @@ static inline u64 gen8_noncanonical_addr(u64 address)
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 {
-	return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len;
+	return intel_engine_requires_cmd_parser(eb->engine) ||
+		(intel_engine_using_cmd_parser(eb->engine) &&
+		 eb->args->batch_len);
 }
 
 static int eb_create(struct i915_execbuffer *eb)
@@ -1955,40 +1957,94 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 	return 0;
 }
 
-static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master)
+static struct i915_vma *
+shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *dev_priv = eb->i915;
+	struct i915_vma * const vma = *eb->vma;
+	struct i915_address_space *vm;
+	u64 flags;
+
+	/*
+	 * PPGTT backed shadow buffers must be mapped RO, to prevent
+	 * post-scan tampering
+	 */
+	if (CMDPARSER_USES_GGTT(dev_priv)) {
+		flags = PIN_GLOBAL;
+		vm = &dev_priv->ggtt.vm;
+	} else if (vma->vm->has_read_only) {
+		flags = PIN_USER;
+		vm = vma->vm;
+		i915_gem_object_set_readonly(obj);
+	} else {
+		DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags);
+}
+
+static struct i915_vma *eb_parse(struct i915_execbuffer *eb)
 {
 	struct intel_engine_pool_node *pool;
 	struct i915_vma *vma;
+	u64 batch_start;
+	u64 shadow_batch_start;
 	int err;
 
 	pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len);
 	if (IS_ERR(pool))
 		return ERR_CAST(pool);
 
-	err = intel_engine_cmd_parser(eb->engine,
+	vma = shadow_batch_pin(eb, pool->obj);
+	if (IS_ERR(vma))
+		goto err;
+
+	batch_start = gen8_canonical_addr(eb->batch->node.start) +
+		      eb->batch_start_offset;
+
+	shadow_batch_start = gen8_canonical_addr(vma->node.start);
+
+	err = intel_engine_cmd_parser(eb->gem_context,
+				      eb->engine,
 				      eb->batch->obj,
-				      pool->obj,
+				      batch_start,
 				      eb->batch_start_offset,
 				      eb->batch_len,
-				      is_master);
+				      pool->obj,
+				      shadow_batch_start);
+
 	if (err) {
-		if (err == -EACCES) /* unhandled chained batch */
+		i915_vma_unpin(vma);
+
+		/*
+		 * Unsafe GGTT-backed buffers can still be submitted safely
+		 * as non-secure.
+		 * For PPGTT backing however, we have no choice but to forcibly
+		 * reject unsafe buffers
+		 */
+		if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES))
+			/* Execute original buffer non-secure */
 			vma = NULL;
 		else
 			vma = ERR_PTR(err);
 		goto err;
 	}
 
-	vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0);
-	if (IS_ERR(vma))
-		goto err;
-
 	eb->vma[eb->buffer_count] = i915_vma_get(vma);
 	eb->flags[eb->buffer_count] =
 		__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
 	vma->exec_flags = &eb->flags[eb->buffer_count];
 	eb->buffer_count++;
 
+	eb->batch_start_offset = 0;
+	eb->batch = vma;
+
+	if (CMDPARSER_USES_GGTT(eb->i915))
+		eb->batch_flags |= I915_DISPATCH_SECURE;
+
+	/* eb->batch_len unchanged */
+
 	vma->private = pool;
 	return vma;
 
@@ -2421,6 +2477,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_i915_gem_exec_object2 *exec,
 		       struct drm_syncobj **fences)
 {
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
 	struct dma_fence *exec_fence = NULL;
@@ -2432,7 +2489,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS &
 		     ~__EXEC_OBJECT_UNKNOWN_FLAGS);
 
-	eb.i915 = to_i915(dev);
+	eb.i915 = i915;
 	eb.file = file;
 	eb.args = args;
 	if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
@@ -2452,8 +2509,15 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
+		if (INTEL_GEN(i915) >= 11)
+			return -ENODEV;
+
+		/* Return -EPERM to trigger fallback code on old binaries. */
+		if (!HAS_SECURE_BATCHES(i915))
+			return -EPERM;
+
 		if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN))
-		    return -EPERM;
+			return -EPERM;
 
 		eb.batch_flags |= I915_DISPATCH_SECURE;
 	}
@@ -2530,34 +2594,19 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		goto err_vma;
 	}
 
+	if (eb.batch_len == 0)
+		eb.batch_len = eb.batch->size - eb.batch_start_offset;
+
 	if (eb_use_cmdparser(&eb)) {
 		struct i915_vma *vma;
 
-		vma = eb_parse(&eb, drm_is_current_master(file));
+		vma = eb_parse(&eb);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto err_vma;
 		}
-
-		if (vma) {
-			/*
-			 * Batch parsed and accepted:
-			 *
-			 * Set the DISPATCH_SECURE bit to remove the NON_SECURE
-			 * bit from MI_BATCH_BUFFER_START commands issued in
-			 * the dispatch_execbuffer implementations. We
-			 * specifically don't want that set on batches the
-			 * command parser has accepted.
-			 */
-			eb.batch_flags |= I915_DISPATCH_SECURE;
-			eb.batch_start_offset = 0;
-			eb.batch = vma;
-		}
 	}
 
-	if (eb.batch_len == 0)
-		eb.batch_len = eb.batch->size - eb.batch_start_offset;
-
 	/*
 	 * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
 	 * batch" bit. Hence we need to pin secure batches into the global gtt.

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

@@ -475,12 +475,13 @@ struct intel_engine_cs {
 
 	struct intel_engine_hangcheck hangcheck;
 
-#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0)
+#define I915_ENGINE_USING_CMD_PARSER BIT(0)
 #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_REQUIRES_CMD_PARSER BIT(7)
 	unsigned int flags;
 
 	/*
@@ -541,9 +542,15 @@ struct intel_engine_cs {
 };
 
 static inline bool
-intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine)
+intel_engine_using_cmd_parser(const struct intel_engine_cs *engine)
 {
-	return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER;
+	return engine->flags & I915_ENGINE_USING_CMD_PARSER;
+}
+
+static inline bool
+intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER;
 }
 
 static inline bool

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

@@ -38,6 +38,9 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 	GEM_BUG_ON(!gt->awake);
 
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
+
 	intel_enable_gt_powersave(i915);
 
 	i915_update_gfx_val(i915);
@@ -67,6 +70,11 @@ static int __gt_park(struct intel_wakeref *wf)
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_idle(i915);
 
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
+		i915_rc6_ctx_wa_check(i915);
+		intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
+	}
+
 	/* Everything switched off, flush any residual interrupt just in case */
 	intel_synchronize_irq(i915);
 

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

@@ -199,14 +199,6 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
 	MOCS_ENTRY(15, \
 		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \
 		   L3_3_WB), \
-	/* Bypass LLC - Uncached (EHL+) */ \
-	MOCS_ENTRY(16, \
-		   LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \
-		   L3_1_UC), \
-	/* Bypass LLC - L3 (Read-Only) (EHL+) */ \
-	MOCS_ENTRY(17, \
-		   LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \
-		   L3_3_WB), \
 	/* Self-Snoop - L3 + LLC */ \
 	MOCS_ENTRY(18, \
 		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \
@@ -270,7 +262,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = {
 		   L3_1_UC),
 	/* HW Special Case (Displayable) */
 	MOCS_ENTRY(61,
-		   LE_1_UC | LE_TC_1_LLC | LE_SCF(1),
+		   LE_1_UC | LE_TC_1_LLC,
 		   L3_3_WB),
 };
 

drivers/gpu/drm/i915/gvt/dmabuf.c

@@ -498,8 +498,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
 		goto out_free_gem;
 	}
 
-	i915_gem_object_put(obj);
-
 	ret = dma_buf_fd(dmabuf, DRM_CLOEXEC | DRM_RDWR);
 	if (ret < 0) {
 		gvt_vgpu_err("create dma-buf fd failed ret:%d\n", ret);
@@ -524,6 +522,8 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
 		    file_count(dmabuf->file),
 		    kref_read(&obj->base.refcount));
 
+	i915_gem_object_put(obj);
+
 	return dmabuf_fd;
 
 out_free_dmabuf:

drivers/gpu/drm/i915/i915_cmd_parser.c

@@ -53,13 +53,11 @@
  * granting userspace undue privileges. There are three categories of privilege.
  *
  * First, commands which are explicitly defined as privileged or which should
- * only be used by the kernel driver. The parser generally rejects such
+ * only be used by the kernel driver. The parser rejects such commands
- * commands, though it may allow some from the drm master process.
  *
  * Second, commands which access registers. To support correct/enhanced
  * userspace functionality, particularly certain OpenGL extensions, the parser
- * provides a whitelist of registers which userspace may safely access (for both
+ * provides a whitelist of registers which userspace may safely access
- * normal and drm master processes).
  *
  * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc).
  * The parser always rejects such commands.
@@ -84,9 +82,9 @@
  * in the per-engine command tables.
  *
  * Other command table entries map fairly directly to high level categories
- * mentioned above: rejected, master-only, register whitelist. The parser
+ * mentioned above: rejected, register whitelist. The parser implements a number
- * implements a number of checks, including the privileged memory checks, via a
+ * of checks, including the privileged memory checks, via a general bitmasking
- * general bitmasking mechanism.
+ * mechanism.
  */
 
 /*
@@ -104,8 +102,6 @@ struct drm_i915_cmd_descriptor {
 	 * CMD_DESC_REJECT: The command is never allowed
 	 * CMD_DESC_REGISTER: The command should be checked against the
 	 *                    register whitelist for the appropriate ring
-	 * CMD_DESC_MASTER: The command is allowed if the submitting process
-	 *                  is the DRM master
 	 */
 	u32 flags;
 #define CMD_DESC_FIXED    (1<<0)
@@ -113,7 +109,6 @@ struct drm_i915_cmd_descriptor {
 #define CMD_DESC_REJECT   (1<<2)
 #define CMD_DESC_REGISTER (1<<3)
 #define CMD_DESC_BITMASK  (1<<4)
-#define CMD_DESC_MASTER   (1<<5)
 
 	/*
 	 * The command's unique identification bits and the bitmask to get them.
@@ -194,7 +189,7 @@ struct drm_i915_cmd_table {
 #define CMD(op, opm, f, lm, fl, ...)				\
 	{							\
 		.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0),	\
-		.cmd = { (op), ~0u << (opm) },			\
+		.cmd = { (op & ~0u << (opm)), ~0u << (opm) },	\
 		.length = { (lm) },				\
 		__VA_ARGS__					\
 	}
@@ -209,14 +204,13 @@ struct drm_i915_cmd_table {
 #define R CMD_DESC_REJECT
 #define W CMD_DESC_REGISTER
 #define B CMD_DESC_BITMASK
-#define M CMD_DESC_MASTER
 
 /*            Command                          Mask   Fixed Len   Action
 	      ---------------------------------------------------------- */
-static const struct drm_i915_cmd_descriptor common_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
 	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
 	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      R  ),
-	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      M  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      R  ),
 	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
 	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
 	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
@@ -246,7 +240,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {
 	CMD(  MI_BATCH_BUFFER_START,            SMI,   !F,  0xFF,   S  ),
 };
 
-static const struct drm_i915_cmd_descriptor render_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = {
 	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_PREDICATE,                     SMI,    F,  1,      S  ),
@@ -313,7 +307,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  MI_URB_ATOMIC_ALLOC,              SMI,    F,  1,      S  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_RS_CONTEXT,                    SMI,    F,  1,      S  ),
-	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   W,
 	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
@@ -330,7 +324,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS,  S3D,   !F,  0x1FF,  S  ),
 };
 
-static const struct drm_i915_cmd_descriptor video_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = {
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
@@ -374,7 +368,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = {
 	CMD(  MFX_WAIT,                         SMFX,   F,  1,      S  ),
 };
 
-static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = {
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
@@ -412,7 +406,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
 	      }},						       ),
 };
 
-static const struct drm_i915_cmd_descriptor blt_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = {
 	CMD(  MI_DISPLAY_FLIP,                  SMI,   !F,  0xFF,   R  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  B,
 	      .bits = {{
@@ -446,10 +440,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = {
 };
 
 static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
-	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 };
 
+/*
+ * For Gen9 we can still rely on the h/w to enforce cmd security, and only
+ * need to re-enforce the register access checks. We therefore only need to
+ * teach the cmdparser how to find the end of each command, and identify
+ * register accesses. The table doesn't need to reject any commands, and so
+ * the only commands listed here are:
+ *   1) Those that touch registers
+ *   2) Those that do not have the default 8-bit length
+ *
+ * Note that the default MI length mask chosen for this table is 0xFF, not
+ * the 0x3F used on older devices. This is because the vast majority of MI
+ * cmds on Gen9 use a standard 8-bit Length field.
+ * All the Gen9 blitter instructions are standard 0xFF length mask, and
+ * none allow access to non-general registers, so in fact no BLT cmds are
+ * included in the table at all.
+ *
+ */
+static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = {
+	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
+	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      S  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      S  ),
+	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
+	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      S  ),
+	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_LOAD_REGISTER_IMM(1),          SMI,   !F,  0xFF,   W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 }    ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_STORE_REGISTER_MEM_GEN8,       SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_REGISTER_MEM_GEN8,        SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_LOAD_REGISTER_REG,             SMI,    !F,  0xFF,  W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
+
+	/*
+	 * We allow BB_START but apply further checks. We just sanitize the
+	 * basic fields here.
+	 */
+#define MI_BB_START_OPERAND_MASK   GENMASK(SMI-1, 0)
+#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1)
+	CMD(  MI_BATCH_BUFFER_START_GEN8,       SMI,    !F,  0xFF,  B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_BB_START_OPERAND_MASK,
+			.expected = MI_BB_START_OPERAND_EXPECT,
+	      }},						       ),
+};
+
 static const struct drm_i915_cmd_descriptor noop_desc =
 	CMD(MI_NOOP, SMI, F, 1, S);
 
@@ -463,40 +511,44 @@ static const struct drm_i915_cmd_descriptor noop_desc =
 #undef R
 #undef W
 #undef B
-#undef M
 
-static const struct drm_i915_cmd_table gen7_render_cmds[] = {
+static const struct drm_i915_cmd_table gen7_render_cmd_table[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
-	{ render_cmds, ARRAY_SIZE(render_cmds) },
+	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = {
+static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
-	{ render_cmds, ARRAY_SIZE(render_cmds) },
+	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
 	{ hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) },
 };
 
-static const struct drm_i915_cmd_table gen7_video_cmds[] = {
+static const struct drm_i915_cmd_table gen7_video_cmd_table[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
-	{ video_cmds, ARRAY_SIZE(video_cmds) },
+	{ gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_vebox_cmds[] = {
+static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
-	{ vecs_cmds, ARRAY_SIZE(vecs_cmds) },
+	{ gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) },
 };
 
-static const struct drm_i915_cmd_table gen7_blt_cmds[] = {
+static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
-	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = {
+static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
-	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
 	{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
 };
 
+static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = {
+	{ gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) },
+};
+
+
 /*
  * Register whitelists, sorted by increasing register offset.
  */
@@ -612,17 +664,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = {
 	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
 };
 
-static const struct drm_i915_reg_descriptor ivb_master_regs[] = {
+static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
-	REG32(FORCEWAKE_MT),
+	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
-	REG32(DERRMR),
+	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)),
+	REG32(BCS_SWCTRL),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)),
+	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)),
+	REG64_IDX(BCS_GPR, 0),
-};
+	REG64_IDX(BCS_GPR, 1),
-
+	REG64_IDX(BCS_GPR, 2),
-static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
+	REG64_IDX(BCS_GPR, 3),
-	REG32(FORCEWAKE_MT),
+	REG64_IDX(BCS_GPR, 4),
-	REG32(DERRMR),
+	REG64_IDX(BCS_GPR, 5),
+	REG64_IDX(BCS_GPR, 6),
+	REG64_IDX(BCS_GPR, 7),
+	REG64_IDX(BCS_GPR, 8),
+	REG64_IDX(BCS_GPR, 9),
+	REG64_IDX(BCS_GPR, 10),
+	REG64_IDX(BCS_GPR, 11),
+	REG64_IDX(BCS_GPR, 12),
+	REG64_IDX(BCS_GPR, 13),
+	REG64_IDX(BCS_GPR, 14),
+	REG64_IDX(BCS_GPR, 15),
 };
 
 #undef REG64
@@ -631,28 +693,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
 struct drm_i915_reg_table {
 	const struct drm_i915_reg_descriptor *regs;
 	int num_regs;
-	bool master;
 };
 
 static const struct drm_i915_reg_table ivb_render_reg_tables[] = {
-	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
+	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
-	{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
 };
 
 static const struct drm_i915_reg_table ivb_blt_reg_tables[] = {
-	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
+	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
-	{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
 };
 
 static const struct drm_i915_reg_table hsw_render_reg_tables[] = {
-	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
+	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
-	{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false },
+	{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs) },
-	{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
 };
 
 static const struct drm_i915_reg_table hsw_blt_reg_tables[] = {
-	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
+	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
-	{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
+};
+
+static const struct drm_i915_reg_table gen9_blt_reg_tables[] = {
+	{ gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) },
 };
 
 static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
@@ -710,6 +771,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	return 0;
 }
 
+static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
+{
+	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
+
+	if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
+		return 0xFF;
+
+	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	return 0;
+}
+
 static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
 				 const struct drm_i915_cmd_table *cmd_tables,
 				 int cmd_table_count)
@@ -867,18 +939,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 	int cmd_table_count;
 	int ret;
 
-	if (!IS_GEN(engine->i915, 7))
+	if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
+					  engine->class == COPY_ENGINE_CLASS))
 		return;
 
 	switch (engine->class) {
 	case RENDER_CLASS:
 		if (IS_HASWELL(engine->i915)) {
-			cmd_tables = hsw_render_ring_cmds;
+			cmd_tables = hsw_render_ring_cmd_table;
 			cmd_table_count =
-				ARRAY_SIZE(hsw_render_ring_cmds);
+				ARRAY_SIZE(hsw_render_ring_cmd_table);
 		} else {
-			cmd_tables = gen7_render_cmds;
+			cmd_tables = gen7_render_cmd_table;
-			cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
+			cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table);
 		}
 
 		if (IS_HASWELL(engine->i915)) {
@@ -888,36 +961,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 			engine->reg_tables = ivb_render_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables);
 		}
-
 		engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
 		break;
 	case VIDEO_DECODE_CLASS:
-		cmd_tables = gen7_video_cmds;
+		cmd_tables = gen7_video_cmd_table;
-		cmd_table_count = ARRAY_SIZE(gen7_video_cmds);
+		cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table);
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	case COPY_ENGINE_CLASS:
-		if (IS_HASWELL(engine->i915)) {
+		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
-			cmd_tables = hsw_blt_ring_cmds;
+		if (IS_GEN(engine->i915, 9)) {
-			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
+			cmd_tables = gen9_blt_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table);
+			engine->get_cmd_length_mask =
+				gen9_blt_get_cmd_length_mask;
+
+			/* BCS Engine unsafe without parser */
+			engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER;
+		} else if (IS_HASWELL(engine->i915)) {
+			cmd_tables = hsw_blt_ring_cmd_table;
+			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table);
 		} else {
-			cmd_tables = gen7_blt_cmds;
+			cmd_tables = gen7_blt_cmd_table;
-			cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
+			cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table);
 		}
 
-		if (IS_HASWELL(engine->i915)) {
+		if (IS_GEN(engine->i915, 9)) {
+			engine->reg_tables = gen9_blt_reg_tables;
+			engine->reg_table_count =
+				ARRAY_SIZE(gen9_blt_reg_tables);
+		} else if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
 		} else {
 			engine->reg_tables = ivb_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables);
 		}
-
-		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
 		break;
 	case VIDEO_ENHANCEMENT_CLASS:
-		cmd_tables = hsw_vebox_cmds;
+		cmd_tables = hsw_vebox_cmd_table;
-		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds);
+		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table);
 		/* VECS can use the same length_mask function as VCS */
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
@@ -943,7 +1026,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 		return;
 	}
 
-	engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER;
+	engine->flags |= I915_ENGINE_USING_CMD_PARSER;
 }
 
 /**
@@ -955,7 +1038,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
  */
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
 {
-	if (!intel_engine_needs_cmd_parser(engine))
+	if (!intel_engine_using_cmd_parser(engine))
 		return;
 
 	fini_hash_table(engine);
@@ -1029,22 +1112,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr)
 }
 
 static const struct drm_i915_reg_descriptor *
-find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr)
+find_reg(const struct intel_engine_cs *engine, u32 addr)
 {
 	const struct drm_i915_reg_table *table = engine->reg_tables;
+	const struct drm_i915_reg_descriptor *reg = NULL;
 	int count = engine->reg_table_count;
 
-	for (; count > 0; ++table, --count) {
+	for (; !reg && (count > 0); ++table, --count)
-		if (!table->master || is_master) {
+		reg = __find_reg(table->regs, table->num_regs, addr);
-			const struct drm_i915_reg_descriptor *reg;
 
-			reg = __find_reg(table->regs, table->num_regs, addr);
+	return reg;
-			if (reg != NULL)
-				return reg;
-		}
-	}
-
-	return NULL;
 }
 
 /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
@@ -1128,8 +1205,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 
 static bool check_cmd(const struct intel_engine_cs *engine,
 		      const struct drm_i915_cmd_descriptor *desc,
-		      const u32 *cmd, u32 length,
+		      const u32 *cmd, u32 length)
-		      const bool is_master)
 {
 	if (desc->flags & CMD_DESC_SKIP)
 		return true;
@@ -1139,12 +1215,6 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		return false;
 	}
 
-	if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
-		DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
-				 *cmd);
-		return false;
-	}
-
 	if (desc->flags & CMD_DESC_REGISTER) {
 		/*
 		 * Get the distance between individual register offset
@@ -1158,7 +1228,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		     offset += step) {
 			const u32 reg_addr = cmd[offset] & desc->reg.mask;
 			const struct drm_i915_reg_descriptor *reg =
-				find_reg(engine, is_master, reg_addr);
+				find_reg(engine, reg_addr);
 
 			if (!reg) {
 				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
@@ -1236,16 +1306,112 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 	return true;
 }
 
+static int check_bbstart(const struct i915_gem_context *ctx,
+			 u32 *cmd, u32 offset, u32 length,
+			 u32 batch_len,
+			 u64 batch_start,
+			 u64 shadow_batch_start)
+{
+	u64 jump_offset, jump_target;
+	u32 target_cmd_offset, target_cmd_index;
+
+	/* For igt compatibility on older platforms */
+	if (CMDPARSER_USES_GGTT(ctx->i915)) {
+		DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
+		return -EACCES;
+	}
+
+	if (length != 3) {
+		DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n",
+			  length);
+		return -EINVAL;
+	}
+
+	jump_target = *(u64*)(cmd+1);
+	jump_offset = jump_target - batch_start;
+
+	/*
+	 * Any underflow of jump_target is guaranteed to be outside the range
+	 * of a u32, so >= test catches both too large and too small
+	 */
+	if (jump_offset >= batch_len) {
+		DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
+			  jump_target);
+		return -EINVAL;
+	}
+
+	/*
+	 * This cannot overflow a u32 because we already checked jump_offset
+	 * is within the BB, and the batch_len is a u32
+	 */
+	target_cmd_offset = lower_32_bits(jump_offset);
+	target_cmd_index = target_cmd_offset / sizeof(u32);
+
+	*(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset;
+
+	if (target_cmd_index == offset)
+		return 0;
+
+	if (ctx->jump_whitelist_cmds <= target_cmd_index) {
+		DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
+		return -EINVAL;
+	} else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
+		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
+			  jump_target);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
+{
+	const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
+	const u32 exact_size = BITS_TO_LONGS(batch_cmds);
+	u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
+	unsigned long *next_whitelist;
+
+	if (CMDPARSER_USES_GGTT(ctx->i915))
+		return;
+
+	if (batch_cmds <= ctx->jump_whitelist_cmds) {
+		bitmap_zero(ctx->jump_whitelist, batch_cmds);
+		return;
+	}
+
+again:
+	next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
+	if (next_whitelist) {
+		kfree(ctx->jump_whitelist);
+		ctx->jump_whitelist = next_whitelist;
+		ctx->jump_whitelist_cmds =
+			next_size * BITS_PER_BYTE * sizeof(long);
+		return;
+	}
+
+	if (next_size > exact_size) {
+		next_size = exact_size;
+		goto again;
+	}
+
+	DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
+	bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
+
+	return;
+}
+
 #define LENGTH_BIAS 2
 
 /**
  * i915_parse_cmds() - parse a submitted batch buffer for privilege violations
+ * @ctx: the context in which the batch is to execute
  * @engine: the engine on which the batch is to execute
  * @batch_obj: the batch buffer in question
- * @shadow_batch_obj: copy of the batch buffer in question
+ * @batch_start: Canonical base address of batch
  * @batch_start_offset: byte offset in the batch at which execution starts
  * @batch_len: length of the commands in batch_obj
- * @is_master: is the submitting process the drm master?
+ * @shadow_batch_obj: copy of the batch buffer in question
+ * @shadow_batch_start: Canonical base address of shadow_batch_obj
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
@@ -1253,14 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine,
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+
+int intel_engine_cmd_parser(struct i915_gem_context *ctx,
+			    struct intel_engine_cs *engine,
 			    struct drm_i915_gem_object *batch_obj,
-			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 batch_start,
 			    u32 batch_start_offset,
 			    u32 batch_len,
-			    bool is_master)
+			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 shadow_batch_start)
 {
-	u32 *cmd, *batch_end;
+	u32 *cmd, *batch_end, offset = 0;
 	struct drm_i915_cmd_descriptor default_desc = noop_desc;
 	const struct drm_i915_cmd_descriptor *desc = &default_desc;
 	bool needs_clflush_after = false;
@@ -1274,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 		return PTR_ERR(cmd);
 	}
 
+	init_whitelist(ctx, batch_len);
+
 	/*
 	 * We use the batch length as size because the shadow object is as
 	 * large or larger and copy_batch() will write MI_NOPs to the extra
@@ -1283,31 +1454,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 	do {
 		u32 length;
 
-		if (*cmd == MI_BATCH_BUFFER_END) {
+		if (*cmd == MI_BATCH_BUFFER_END)
-			if (needs_clflush_after) {
-				void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
-				drm_clflush_virt_range(ptr,
-						       (void *)(cmd + 1) - ptr);
-			}
 			break;
-		}
 
 		desc = find_cmd(engine, *cmd, desc, &default_desc);
 		if (!desc) {
 			DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
 					 *cmd);
 			ret = -EINVAL;
-			break;
+			goto err;
-		}
-
-		/*
-		 * If the batch buffer contains a chained batch, return an
-		 * error that tells the caller to abort and dispatch the
-		 * workload as a non-secure batch.
-		 */
-		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
-			ret = -EACCES;
-			break;
 		}
 
 		if (desc->flags & CMD_DESC_FIXED)
@@ -1321,22 +1476,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 					 length,
 					 batch_end - cmd);
 			ret = -EINVAL;
+			goto err;
+		}
+
+		if (!check_cmd(engine, desc, cmd, length)) {
+			ret = -EACCES;
+			goto err;
+		}
+
+		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
+			ret = check_bbstart(ctx, cmd, offset, length,
+					    batch_len, batch_start,
+					    shadow_batch_start);
+
+			if (ret)
+				goto err;
 			break;
 		}
 
-		if (!check_cmd(engine, desc, cmd, length, is_master)) {
+		if (ctx->jump_whitelist_cmds > offset)
-			ret = -EACCES;
+			set_bit(offset, ctx->jump_whitelist);
-			break;
-		}
 
 		cmd += length;
+		offset += length;
 		if  (cmd >= batch_end) {
 			DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
 			ret = -EINVAL;
-			break;
+			goto err;
 		}
 	} while (1);
 
+	if (needs_clflush_after) {
+		void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
+
+		drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
+	}
+
+err:
 	i915_gem_object_unpin_map(shadow_batch_obj);
 	return ret;
 }
@@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 
 	/* If the command parser is not enabled, report 0 - unsupported */
 	for_each_uabi_engine(engine, dev_priv) {
-		if (intel_engine_needs_cmd_parser(engine)) {
+		if (intel_engine_using_cmd_parser(engine)) {
 			active = true;
 			break;
 		}
@@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 	 *    the parser enabled.
 	 * 9. Don't whitelist or handle oacontrol specially, as ownership
 	 *    for oacontrol state is moving to i915-perf.
+	 * 10. Support for Gen9 BCS Parsing
 	 */
-	return 9;
+	return 10;
 }

drivers/gpu/drm/i915/i915_drv.c

@@ -364,9 +364,6 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
 	if (ret)
 		goto cleanup_vga_client;
 
-	/* must happen before intel_power_domains_init_hw() on VLV/CHV */
-	intel_update_rawclk(dev_priv);
-
 	intel_power_domains_init_hw(dev_priv, false);
 
 	intel_csr_ucode_init(dev_priv);
@@ -1850,6 +1847,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 	i915_gem_suspend_late(dev_priv);
 
+	i915_rc6_ctx_wa_suspend(dev_priv);
+
 	intel_uncore_suspend(&dev_priv->uncore);
 
 	intel_power_domains_suspend(dev_priv,
@@ -2053,6 +2052,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
 
 	intel_power_domains_resume(dev_priv);
 
+	i915_rc6_ctx_wa_resume(dev_priv);
+
 	intel_gt_sanitize(&dev_priv->gt, true);
 
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);

drivers/gpu/drm/i915/i915_drv.h

@@ -593,6 +593,8 @@ struct intel_rps {
 
 struct intel_rc6 {
 	bool enabled;
+	bool ctx_corrupted;
+	intel_wakeref_t ctx_corrupted_wakeref;
 	u64 prev_hw_residency[4];
 	u64 cur_residency[4];
 };
@@ -2075,9 +2077,16 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define VEBOX_MASK(dev_priv) \
 	ENGINE_INSTANCES_MASK(dev_priv, VECS0, I915_MAX_VECS)
 
+/*
+ * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution
+ * All later gens can run the final buffer from the ppgtt
+ */
+#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7)
+
 #define HAS_LLC(dev_priv)	(INTEL_INFO(dev_priv)->has_llc)
 #define HAS_SNOOP(dev_priv)	(INTEL_INFO(dev_priv)->has_snoop)
 #define HAS_EDRAM(dev_priv)	((dev_priv)->edram_size_mb)
+#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6)
 #define HAS_WT(dev_priv)	((IS_HASWELL(dev_priv) || \
 				 IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv))
 
@@ -2110,10 +2119,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 /* Early gen2 have a totally busted CS tlb and require pinned batches. */
 #define HAS_BROKEN_CS_TLB(dev_priv)	(IS_I830(dev_priv) || IS_I845G(dev_priv))
 
+#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv)	\
+	(IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
+
 /* WaRsDisableCoarsePowerGating:skl,cnl */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
-	(IS_CANNONLAKE(dev_priv) || \
+	(IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
-	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
 
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
 #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
@@ -2284,6 +2295,14 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags);
 #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
 
+struct i915_vma * __must_check
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    const struct i915_ggtt_view *view,
+		    u64 size,
+		    u64 alignment,
+		    u64 flags);
+
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
 static inline int __must_check
@@ -2393,12 +2412,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+int intel_engine_cmd_parser(struct i915_gem_context *cxt,
+			    struct intel_engine_cs *engine,
 			    struct drm_i915_gem_object *batch_obj,
-			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 user_batch_start,
 			    u32 batch_start_offset,
 			    u32 batch_len,
-			    bool is_master);
+			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 shadow_batch_start);
 
 /* intel_device_info.c */
 static inline struct intel_device_info *

drivers/gpu/drm/i915/i915_gem.c

@@ -964,6 +964,20 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_address_space *vm = &dev_priv->ggtt.vm;
+
+	return i915_gem_object_pin(obj, vm, view, size, alignment,
+				   flags | PIN_GLOBAL);
+}
+
+struct i915_vma *
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    const struct i915_ggtt_view *view,
+		    u64 size,
+		    u64 alignment,
+		    u64 flags)
+{
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 	int ret;
 
@@ -1038,7 +1052,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			return ERR_PTR(ret);
 	}
 
-	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
+	ret = i915_vma_pin(vma, size, alignment, flags);
 	if (ret)
 		return ERR_PTR(ret);
 

drivers/gpu/drm/i915/i915_getparam.c

@@ -62,7 +62,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = !!(i915->caps.scheduler & I915_SCHEDULER_CAP_SEMAPHORES);
 		break;
 	case I915_PARAM_HAS_SECURE_BATCHES:
-		value = capable(CAP_SYS_ADMIN);
+		value = HAS_SECURE_BATCHES(i915) && capable(CAP_SYS_ADMIN);
 		break;
 	case I915_PARAM_CMD_PARSER_VERSION:
 		value = i915_cmd_parser_get_version(i915);

drivers/gpu/drm/i915/i915_reg.h

@@ -471,6 +471,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   ECOCHK_PPGTT_WT_HSW		(0x2 << 3)
 #define   ECOCHK_PPGTT_WB_HSW		(0x3 << 3)
 
+#define GEN8_RC6_CTX_INFO		_MMIO(0x8504)
+
 #define GAC_ECO_BITS			_MMIO(0x14090)
 #define   ECOBITS_SNB_BIT		(1 << 13)
 #define   ECOBITS_PPGTT_CACHE64B	(3 << 8)
@@ -555,6 +557,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  */
 #define BCS_SWCTRL _MMIO(0x22200)
 
+/* There are 16 GPR registers */
+#define BCS_GPR(n)	_MMIO(0x22600 + (n) * 8)
+#define BCS_GPR_UDW(n)	_MMIO(0x22600 + (n) * 8 + 4)
+
 #define GPGPU_THREADS_DISPATCHED        _MMIO(0x2290)
 #define GPGPU_THREADS_DISPATCHED_UDW	_MMIO(0x2290 + 4)
 #define HS_INVOCATION_COUNT             _MMIO(0x2300)
@@ -7211,6 +7217,10 @@ enum {
 #define TGL_DMC_DEBUG_DC5_COUNT	_MMIO(0x101084)
 #define TGL_DMC_DEBUG_DC6_COUNT	_MMIO(0x101088)
 
+/* Display Internal Timeout Register */
+#define RM_TIMEOUT		_MMIO(0x42060)
+#define  MMIO_TIMEOUT_US(us)	((us) << 0)
+
 /* interrupts */
 #define DE_MASTER_IRQ_CONTROL   (1 << 31)
 #define DE_SPRITEB_FLIP_DONE    (1 << 29)

drivers/gpu/drm/i915/intel_pm.c

@@ -126,6 +126,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
 	 */
 	I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
 		   PWM1_GATING_DIS | PWM2_GATING_DIS);
+
+	/*
+	 * Lower the display internal timeout.
+	 * This is needed to avoid any hard hangs when DSI port PLL
+	 * is off and a MMIO access is attempted by any privilege
+	 * application, using batch buffers or any other means.
+	 */
+	I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950));
 }
 
 static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -8544,6 +8552,100 @@ static void intel_init_emon(struct drm_i915_private *dev_priv)
 	dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
 }
 
+static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv)
+{
+	return !I915_READ(GEN8_RC6_CTX_INFO);
+}
+
+static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915)
+{
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return;
+
+	if (i915_rc6_ctx_corrupted(i915)) {
+		DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
+		i915->gt_pm.rc6.ctx_corrupted = true;
+		i915->gt_pm.rc6.ctx_corrupted_wakeref =
+			intel_runtime_pm_get(&i915->runtime_pm);
+	}
+}
+
+static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915)
+{
+	if (i915->gt_pm.rc6.ctx_corrupted) {
+		intel_runtime_pm_put(&i915->runtime_pm,
+				     i915->gt_pm.rc6.ctx_corrupted_wakeref);
+		i915->gt_pm.rc6.ctx_corrupted = false;
+	}
+}
+
+/**
+ * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to clean up the RC6 CTX WA before system suspend.
+ */
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915)
+{
+	if (i915->gt_pm.rc6.ctx_corrupted)
+		intel_runtime_pm_put(&i915->runtime_pm,
+				     i915->gt_pm.rc6.ctx_corrupted_wakeref);
+}
+
+/**
+ * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to re-init the RC6 CTX WA after system resume.
+ */
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915)
+{
+	if (!i915->gt_pm.rc6.ctx_corrupted)
+		return;
+
+	if (i915_rc6_ctx_corrupted(i915)) {
+		i915->gt_pm.rc6.ctx_corrupted_wakeref =
+			intel_runtime_pm_get(&i915->runtime_pm);
+		return;
+	}
+
+	DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
+	i915->gt_pm.rc6.ctx_corrupted = false;
+}
+
+static void intel_disable_rc6(struct drm_i915_private *dev_priv);
+
+/**
+ * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption
+ * @i915: i915 device
+ *
+ * Check if an RC6 CTX corruption has happened since the last check and if so
+ * disable RC6 and runtime power management.
+ *
+ * Return false if no context corruption has happened since the last call of
+ * this function, true otherwise.
+*/
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915)
+{
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return false;
+
+	if (i915->gt_pm.rc6.ctx_corrupted)
+		return false;
+
+	if (!i915_rc6_ctx_corrupted(i915))
+		return false;
+
+	DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
+
+	intel_disable_rc6(i915);
+	i915->gt_pm.rc6.ctx_corrupted = true;
+	i915->gt_pm.rc6.ctx_corrupted_wakeref =
+		intel_runtime_pm_get_noresume(&i915->runtime_pm);
+
+	return true;
+}
+
 void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -8557,6 +8659,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 		pm_runtime_get(&dev_priv->drm.pdev->dev);
 	}
 
+	i915_rc6_ctx_wa_init(dev_priv);
+
 	/* Initialize RPS limits (for userspace) */
 	if (IS_CHERRYVIEW(dev_priv))
 		cherryview_init_gt_powersave(dev_priv);
@@ -8595,6 +8699,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 	if (IS_VALLEYVIEW(dev_priv))
 		valleyview_cleanup_gt_powersave(dev_priv);
 
+	i915_rc6_ctx_wa_cleanup(dev_priv);
+
 	if (!HAS_RC6(dev_priv))
 		pm_runtime_put(&dev_priv->drm.pdev->dev);
 }
@@ -8623,7 +8729,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
 	i915->gt_pm.llc_pstate.enabled = false;
 }
 
-static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+static void __intel_disable_rc6(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
 
@@ -8642,6 +8748,15 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv)
 	dev_priv->gt_pm.rc6.enabled = false;
 }
 
+static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+{
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
+	mutex_lock(&rps->lock);
+	__intel_disable_rc6(dev_priv);
+	mutex_unlock(&rps->lock);
+}
+
 static void intel_disable_rps(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@@ -8667,7 +8782,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
-	intel_disable_rc6(dev_priv);
+	__intel_disable_rc6(dev_priv);
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
 		intel_disable_llc_pstate(dev_priv);
@@ -8694,6 +8809,9 @@ static void intel_enable_rc6(struct drm_i915_private *dev_priv)
 	if (dev_priv->gt_pm.rc6.enabled)
 		return;
 
+	if (dev_priv->gt_pm.rc6.ctx_corrupted)
+		return;
+
 	if (IS_CHERRYVIEW(dev_priv))
 		cherryview_enable_rc6(dev_priv);
 	else if (IS_VALLEYVIEW(dev_priv))

drivers/gpu/drm/i915/intel_pm.h

@@ -36,6 +36,9 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915);
 void gen6_rps_busy(struct drm_i915_private *dev_priv);
 void gen6_rps_idle(struct drm_i915_private *dev_priv);
 void gen6_rps_boost(struct i915_request *rq);

drivers/gpu/drm/sun4i/sun4i_tcon.c

@@ -488,7 +488,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
 
 	WARN_ON(!tcon->quirks->has_channel_0);
 
-	tcon->dclk_min_div = 6;
+	tcon->dclk_min_div = 1;
 	tcon->dclk_max_div = 127;
 	sun4i_tcon0_mode_set_common(tcon, mode);
 

drivers/hwtracing/intel_th/gth.c

@@ -626,6 +626,9 @@ static void intel_th_gth_switch(struct intel_th_device *thdev,
 	if (!count)
 		dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n");
 
+	/* De-assert the trigger */
+	iowrite32(0, gth->base + REG_CTS_CTL);
+
 	intel_th_gth_stop(gth, output, false);
 	intel_th_gth_start(gth, output);
 }

drivers/hwtracing/intel_th/msu.c

@@ -164,7 +164,7 @@ struct msc {
 };
 
 static LIST_HEAD(msu_buffer_list);
-static struct mutex msu_buffer_mutex;
+static DEFINE_MUTEX(msu_buffer_mutex);
 
 /**
  * struct msu_buffer_entry - internal MSU buffer bookkeeping
@@ -327,7 +327,7 @@ static size_t msc_win_total_sz(struct msc_window *win)
 		struct msc_block_desc *bdesc = sg_virt(sg);
 
 		if (msc_block_wrapped(bdesc))
-			return win->nr_blocks << PAGE_SHIFT;
+			return (size_t)win->nr_blocks << PAGE_SHIFT;
 
 		size += msc_total_sz(bdesc);
 		if (msc_block_last_written(bdesc))
@@ -1848,9 +1848,14 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf,
 		len = cp - buf;
 
 	mode = kstrndup(buf, len, GFP_KERNEL);
+	if (!mode)
+		return -ENOMEM;
+
 	i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode);
-	if (i >= 0)
+	if (i >= 0) {
+		kfree(mode);
 		goto found;
+	}
 
 	/* Buffer sinks only work with a usable IRQ */
 	if (!msc->do_irq) {

drivers/hwtracing/intel_th/pci.c

@@ -199,6 +199,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x02a6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Comet Lake PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x06a6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{
 		/* Ice Lake NNPI */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5),
@@ -209,6 +214,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Jasper Lake PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{ 0 },
 };
 

drivers/iio/adc/stm32-adc.c

@@ -1399,7 +1399,7 @@ static int stm32_adc_dma_start(struct iio_dev *indio_dev)
 	cookie = dmaengine_submit(desc);
 	ret = dma_submit_error(cookie);
 	if (ret) {
-		dmaengine_terminate_all(adc->dma_chan);
+		dmaengine_terminate_sync(adc->dma_chan);
 		return ret;
 	}
 
@@ -1477,7 +1477,7 @@ static void __stm32_adc_buffer_predisable(struct iio_dev *indio_dev)
 		stm32_adc_conv_irq_disable(adc);
 
 	if (adc->dma_chan)
-		dmaengine_terminate_all(adc->dma_chan);
+		dmaengine_terminate_sync(adc->dma_chan);
 
 	if (stm32_adc_set_trig(indio_dev, NULL))
 		dev_err(&indio_dev->dev, "Can't clear trigger\n");

drivers/iio/imu/adis16480.c

@@ -317,8 +317,11 @@ static int adis16480_set_freq(struct iio_dev *indio_dev, int val, int val2)
 	struct adis16480 *st = iio_priv(indio_dev);
 	unsigned int t, reg;
 
+	if (val < 0 || val2 < 0)
+		return -EINVAL;
+
 	t =  val * 1000 + val2 / 1000;
-	if (t <= 0)
+	if (t == 0)
 		return -EINVAL;
 
 	/*

drivers/iio/imu/inv_mpu6050/inv_mpu_core.c

@@ -114,54 +114,63 @@ static const struct inv_mpu6050_hw hw_info[] = {
 		.name = "MPU6050",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU6500_WHOAMI_VALUE,
 		.name = "MPU6500",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU6515_WHOAMI_VALUE,
 		.name = "MPU6515",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU6000_WHOAMI_VALUE,
 		.name = "MPU6000",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU9150_WHOAMI_VALUE,
 		.name = "MPU9150",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU9250_WHOAMI_VALUE,
 		.name = "MPU9250",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU9255_WHOAMI_VALUE,
 		.name = "MPU9255",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_ICM20608_WHOAMI_VALUE,
 		.name = "ICM20608",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_ICM20602_WHOAMI_VALUE,
 		.name = "ICM20602",
 		.reg = &reg_set_icm20602,
 		.config = &chip_config_6050,
+		.fifo_size = 1008,
 	},
 };
 

drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h

@@ -100,12 +100,14 @@ struct inv_mpu6050_chip_config {
  *  @name:      name of the chip.
  *  @reg:   register map of the chip.
  *  @config:    configuration of the chip.
+ *  @fifo_size:	size of the FIFO in bytes.
  */
 struct inv_mpu6050_hw {
 	u8 whoami;
 	u8 *name;
 	const struct inv_mpu6050_reg_map *reg;
 	const struct inv_mpu6050_chip_config *config;
+	size_t fifo_size;
 };
 
 /*

drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c

@@ -180,9 +180,6 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 			"failed to ack interrupt\n");
 		goto flush_fifo;
 	}
-	/* handle fifo overflow by reseting fifo */
-	if (int_status & INV_MPU6050_BIT_FIFO_OVERFLOW_INT)
-		goto flush_fifo;
 	if (!(int_status & INV_MPU6050_BIT_RAW_DATA_RDY_INT)) {
 		dev_warn(regmap_get_device(st->map),
 			"spurious interrupt with status 0x%x\n", int_status);
@@ -211,6 +208,18 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	if (result)
 		goto end_session;
 	fifo_count = get_unaligned_be16(&data[0]);
+
+	/*
+	 * Handle fifo overflow by resetting fifo.
+	 * Reset if there is only 3 data set free remaining to mitigate
+	 * possible delay between reading fifo count and fifo data.
+	 */
+	nb = 3 * bytes_per_datum;
+	if (fifo_count >= st->hw->fifo_size - nb) {
+		dev_warn(regmap_get_device(st->map), "fifo overflow reset\n");
+		goto flush_fifo;
+	}
+
 	/* compute and process all complete datum */
 	nb = fifo_count / bytes_per_datum;
 	inv_mpu6050_update_period(st, pf->timestamp, nb);

drivers/iio/proximity/srf04.c

@@ -110,7 +110,7 @@ static int srf04_read(struct srf04_data *data)
 	udelay(data->cfg->trigger_pulse_us);
 	gpiod_set_value(data->gpiod_trig, 0);
 
-	/* it cannot take more than 20 ms */
+	/* it should not take more than 20 ms until echo is rising */
 	ret = wait_for_completion_killable_timeout(&data->rising, HZ/50);
 	if (ret < 0) {
 		mutex_unlock(&data->lock);
@@ -120,7 +120,8 @@ static int srf04_read(struct srf04_data *data)
 		return -ETIMEDOUT;
 	}
 
-	ret = wait_for_completion_killable_timeout(&data->falling, HZ/50);
+	/* it cannot take more than 50 ms until echo is falling */
+	ret = wait_for_completion_killable_timeout(&data->falling, HZ/20);
 	if (ret < 0) {
 		mutex_unlock(&data->lock);
 		return ret;
@@ -135,19 +136,19 @@ static int srf04_read(struct srf04_data *data)
 
 	dt_ns = ktime_to_ns(ktime_dt);
 	/*
-	 * measuring more than 3 meters is beyond the capabilities of
+	 * measuring more than 6,45 meters is beyond the capabilities of
-	 * the sensor
+	 * the supported sensors
 	 * ==> filter out invalid results for not measuring echos of
 	 *     another us sensor
 	 *
 	 * formula:
-	 *         distance       3 m
+	 *         distance     6,45 * 2 m
-	 * time = ---------- = --------- = 9404389 ns
+	 * time = ---------- = ------------ = 40438871 ns
-	 *          speed       319 m/s
+	 *          speed         319 m/s
 	 *
 	 * using a minimum speed at -20 °C of 319 m/s
 	 */
-	if (dt_ns > 9404389)
+	if (dt_ns > 40438871)
 		return -EIO;
 
 	time_ns = dt_ns;
@@ -159,20 +160,20 @@ static int srf04_read(struct srf04_data *data)
 	 *   with Temp in °C
 	 *   and speed in m/s
 	 *
-	 * use 343 m/s as ultrasonic speed at 20 °C here in absence of the
+	 * use 343,5 m/s as ultrasonic speed at 20 °C here in absence of the
 	 * temperature
 	 *
 	 * therefore:
-	 *             time     343
+	 *             time     343,5     time * 106
-	 * distance = ------ * -----
+	 * distance = ------ * ------- = ------------
-	 *             10^6       2
+	 *             10^6         2         617176
 	 *   with time in ns
 	 *   and distance in mm (one way)
 	 *
-	 * because we limit to 3 meters the multiplication with 343 just
+	 * because we limit to 6,45 meters the multiplication with 106 just
 	 * fits into 32 bit
 	 */
-	distance_mm = time_ns * 343 / 2000000;
+	distance_mm = time_ns * 106 / 617176;
 
 	return distance_mm;
 }

drivers/infiniband/hw/hfi1/init.c

@@ -1489,7 +1489,6 @@ static int __init hfi1_mod_init(void)
 		goto bail_dev;
 	}
 
-	hfi1_compute_tid_rdma_flow_wt();
 	/*
 	 * These must be called before the driver is registered with
 	 * the PCI subsystem.

drivers/infiniband/hw/hfi1/pcie.c

@@ -319,7 +319,9 @@ int pcie_speeds(struct hfi1_devdata *dd)
 	/*
 	 * bus->max_bus_speed is set from the bridge's linkcap Max Link Speed
 	 */
-	if (parent && dd->pcidev->bus->max_bus_speed != PCIE_SPEED_8_0GT) {
+	if (parent &&
+	    (dd->pcidev->bus->max_bus_speed == PCIE_SPEED_2_5GT ||
+	     dd->pcidev->bus->max_bus_speed == PCIE_SPEED_5_0GT)) {
 		dd_dev_info(dd, "Parent PCIe bridge does not support Gen3\n");
 		dd->link_gen3_capable = 0;
 	}

drivers/infiniband/hw/hfi1/rc.c

@@ -2209,15 +2209,15 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 		if (qp->s_flags & RVT_S_WAIT_RNR)
 			goto bail_stop;
 		rdi = ib_to_rvt(qp->ibqp.device);
-		if (qp->s_rnr_retry == 0 &&
+		if (!(rdi->post_parms[wqe->wr.opcode].flags &
-		    !((rdi->post_parms[wqe->wr.opcode].flags &
+		       RVT_OPERATION_IGN_RNR_CNT)) {
-		      RVT_OPERATION_IGN_RNR_CNT) &&
+			if (qp->s_rnr_retry == 0) {
-		      qp->s_rnr_retry_cnt == 0)) {
+				status = IB_WC_RNR_RETRY_EXC_ERR;
-			status = IB_WC_RNR_RETRY_EXC_ERR;
+				goto class_b;
-			goto class_b;
+			}
+			if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0)
+				qp->s_rnr_retry--;
 		}
-		if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0)
-			qp->s_rnr_retry--;
 
 		/*
 		 * The last valid PSN is the previous PSN. For TID RDMA WRITE

drivers/infiniband/hw/hfi1/tid_rdma.c

@@ -107,8 +107,6 @@ static u32 mask_generation(u32 a)
  * C - Capcode
  */
 
-static u32 tid_rdma_flow_wt;
-
 static void tid_rdma_trigger_resume(struct work_struct *work);
 static void hfi1_kern_exp_rcv_free_flows(struct tid_rdma_request *req);
 static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req,
@@ -136,6 +134,26 @@ static void update_r_next_psn_fecn(struct hfi1_packet *packet,
 				   struct tid_rdma_flow *flow,
 				   bool fecn);
 
+static void validate_r_tid_ack(struct hfi1_qp_priv *priv)
+{
+	if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
+		priv->r_tid_ack = priv->r_tid_tail;
+}
+
+static void tid_rdma_schedule_ack(struct rvt_qp *qp)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	priv->s_flags |= RVT_S_ACK_PENDING;
+	hfi1_schedule_tid_send(qp);
+}
+
+static void tid_rdma_trigger_ack(struct rvt_qp *qp)
+{
+	validate_r_tid_ack(qp->priv);
+	tid_rdma_schedule_ack(qp);
+}
+
 static u64 tid_rdma_opfn_encode(struct tid_rdma_params *p)
 {
 	return
@@ -3005,10 +3023,7 @@ nak_psn:
 		qpriv->s_nak_state = IB_NAK_PSN_ERROR;
 		/* We are NAK'ing the next expected PSN */
 		qpriv->s_nak_psn = mask_psn(flow->flow_state.r_next_psn);
-		qpriv->s_flags |= RVT_S_ACK_PENDING;
+		tid_rdma_trigger_ack(qp);
-		if (qpriv->r_tid_ack == HFI1_QP_WQE_INVALID)
-			qpriv->r_tid_ack = qpriv->r_tid_tail;
-		hfi1_schedule_tid_send(qp);
 	}
 	goto unlock;
 }
@@ -3371,18 +3386,17 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	return sizeof(ohdr->u.tid_rdma.w_req) / sizeof(u32);
 }
 
-void hfi1_compute_tid_rdma_flow_wt(void)
+static u32 hfi1_compute_tid_rdma_flow_wt(struct rvt_qp *qp)
 {
 	/*
 	 * Heuristic for computing the RNR timeout when waiting on the flow
 	 * queue. Rather than a computationaly expensive exact estimate of when
 	 * a flow will be available, we assume that if a QP is at position N in
 	 * the flow queue it has to wait approximately (N + 1) * (number of
-	 * segments between two sync points), assuming PMTU of 4K. The rationale
+	 * segments between two sync points). The rationale for this is that
-	 * for this is that flows are released and recycled at each sync point.
+	 * flows are released and recycled at each sync point.
 	 */
-	tid_rdma_flow_wt = MAX_TID_FLOW_PSN * enum_to_mtu(OPA_MTU_4096) /
+	return (MAX_TID_FLOW_PSN * qp->pmtu) >> TID_RDMA_SEGMENT_SHIFT;
-		TID_RDMA_MAX_SEGMENT_SIZE;
 }
 
 static u32 position_in_queue(struct hfi1_qp_priv *qpriv,
@@ -3505,7 +3519,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 		if (qpriv->flow_state.index >= RXE_NUM_TID_FLOWS) {
 			ret = hfi1_kern_setup_hw_flow(qpriv->rcd, qp);
 			if (ret) {
-				to_seg = tid_rdma_flow_wt *
+				to_seg = hfi1_compute_tid_rdma_flow_wt(qp) *
 					position_in_queue(qpriv,
 							  &rcd->flow_queue);
 				break;
@@ -3526,7 +3540,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 		/*
 		 * If overtaking req->acked_tail, send an RNR NAK. Because the
 		 * QP is not queued in this case, and the issue can only be
-		 * caused due a delay in scheduling the second leg which we
+		 * caused by a delay in scheduling the second leg which we
 		 * cannot estimate, we use a rather arbitrary RNR timeout of
 		 * (MAX_FLOWS / 2) segments
 		 */
@@ -3534,8 +3548,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 				MAX_FLOWS)) {
 			ret = -EAGAIN;
 			to_seg = MAX_FLOWS >> 1;
-			qpriv->s_flags |= RVT_S_ACK_PENDING;
+			tid_rdma_trigger_ack(qp);
-			hfi1_schedule_tid_send(qp);
 			break;
 		}
 
@@ -4335,8 +4348,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet)
 	trace_hfi1_tid_req_rcv_write_data(qp, 0, e->opcode, e->psn, e->lpsn,
 					  req);
 	trace_hfi1_tid_write_rsp_rcv_data(qp);
-	if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
+	validate_r_tid_ack(priv);
-		priv->r_tid_ack = priv->r_tid_tail;
 
 	if (opcode == TID_OP(WRITE_DATA_LAST)) {
 		release_rdma_sge_mr(e);
@@ -4375,8 +4387,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet)
 	}
 
 done:
-	priv->s_flags |= RVT_S_ACK_PENDING;
+	tid_rdma_schedule_ack(qp);
-	hfi1_schedule_tid_send(qp);
 exit:
 	priv->r_next_psn_kdeth = flow->flow_state.r_next_psn;
 	if (fecn)
@@ -4388,10 +4399,7 @@ send_nak:
 	if (!priv->s_nak_state) {
 		priv->s_nak_state = IB_NAK_PSN_ERROR;
 		priv->s_nak_psn = flow->flow_state.r_next_psn;
-		priv->s_flags |= RVT_S_ACK_PENDING;
+		tid_rdma_trigger_ack(qp);
-		if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
-			priv->r_tid_ack = priv->r_tid_tail;
-		hfi1_schedule_tid_send(qp);
 	}
 	goto done;
 }
@@ -4939,8 +4947,7 @@ void hfi1_rc_rcv_tid_rdma_resync(struct hfi1_packet *packet)
 	qpriv->resync = true;
 	/* RESYNC request always gets a TID RDMA ACK. */
 	qpriv->s_nak_state = 0;
-	qpriv->s_flags |= RVT_S_ACK_PENDING;
+	tid_rdma_trigger_ack(qp);
-	hfi1_schedule_tid_send(qp);
 bail:
 	if (fecn)
 		qp->s_flags |= RVT_S_ECN;

drivers/infiniband/hw/hfi1/tid_rdma.h

@@ -17,6 +17,7 @@
 #define TID_RDMA_MIN_SEGMENT_SIZE       BIT(18)   /* 256 KiB (for now) */
 #define TID_RDMA_MAX_SEGMENT_SIZE       BIT(18)   /* 256 KiB (for now) */
 #define TID_RDMA_MAX_PAGES              (BIT(18) >> PAGE_SHIFT)
+#define TID_RDMA_SEGMENT_SHIFT		18
 
 /*
  * Bit definitions for priv->s_flags.
@@ -274,8 +275,6 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 				  struct ib_other_headers *ohdr,
 				  u32 *bth1, u32 *bth2, u32 *len);
 
-void hfi1_compute_tid_rdma_flow_wt(void);
-
 void hfi1_rc_rcv_tid_rdma_write_req(struct hfi1_packet *packet);
 
 u32 hfi1_build_tid_rdma_write_resp(struct rvt_qp *qp, struct rvt_ack_entry *e,

drivers/infiniband/hw/hns/hns_roce_hem.h

@@ -59,7 +59,7 @@ enum {
 
 #define HNS_ROCE_HEM_CHUNK_LEN	\
 	 ((256 - sizeof(struct list_head) - 2 * sizeof(int)) /	 \
-	 (sizeof(struct scatterlist)))
+	 (sizeof(struct scatterlist) + sizeof(void *)))
 
 #define check_whether_bt_num_3(type, hop_num) \
 	(type < HEM_TYPE_MTT && hop_num == 2)

drivers/infiniband/hw/hns/hns_roce_srq.c

@@ -376,7 +376,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq,
 	srq->max = roundup_pow_of_two(srq_init_attr->attr.max_wr + 1);
 	srq->max_gs = srq_init_attr->attr.max_sge;
 
-	srq_desc_size = max(16, 16 * srq->max_gs);
+	srq_desc_size = roundup_pow_of_two(max(16, 16 * srq->max_gs));
 
 	srq->wqe_shift = ilog2(srq_desc_size);
 

drivers/input/ff-memless.c

@@ -489,6 +489,15 @@ static void ml_ff_destroy(struct ff_device *ff)
 {
 	struct ml_device *ml = ff->private;
 
+	/*
+	 * Even though we stop all playing effects when tearing down
+	 * an input device (via input_device_flush() that calls into
+	 * input_ff_flush() that stops and erases all effects), we
+	 * do not actually stop the timer, and therefore we should
+	 * do it here.
+	 */
+	del_timer_sync(&ml->timer);
+
 	kfree(ml->private);
 }
 

drivers/input/mouse/synaptics.c

@@ -177,6 +177,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN0096", /* X280 */
 	"LEN0097", /* X280 -> ALPS trackpoint */
 	"LEN009b", /* T580 */
+	"LEN0402", /* X1 Extreme 2nd Generation */
 	"LEN200f", /* T450s */
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */

drivers/input/rmi4/rmi_f11.c

@@ -510,7 +510,6 @@ struct f11_data {
 	struct rmi_2d_sensor_platform_data sensor_pdata;
 	unsigned long *abs_mask;
 	unsigned long *rel_mask;
-	unsigned long *result_bits;
 };
 
 enum f11_finger_state {
@@ -1057,7 +1056,7 @@ static int rmi_f11_initialize(struct rmi_function *fn)
 	/*
 	** init instance data, fill in values and create any sysfs files
 	*/
-	f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 3,
+	f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 2,
 			GFP_KERNEL);
 	if (!f11)
 		return -ENOMEM;
@@ -1076,8 +1075,6 @@ static int rmi_f11_initialize(struct rmi_function *fn)
 			+ sizeof(struct f11_data));
 	f11->rel_mask = (unsigned long *)((char *)f11
 			+ sizeof(struct f11_data) + mask_size);
-	f11->result_bits = (unsigned long *)((char *)f11
-			+ sizeof(struct f11_data) + mask_size * 2);
 
 	set_bit(fn->irq_pos, f11->abs_mask);
 	set_bit(fn->irq_pos + 1, f11->rel_mask);
@@ -1284,8 +1281,8 @@ static irqreturn_t rmi_f11_attention(int irq, void *ctx)
 			valid_bytes = f11->sensor.attn_size;
 		memcpy(f11->sensor.data_pkt, drvdata->attn_data.data,
 			valid_bytes);
-		drvdata->attn_data.data += f11->sensor.attn_size;
+		drvdata->attn_data.data += valid_bytes;
-		drvdata->attn_data.size -= f11->sensor.attn_size;
+		drvdata->attn_data.size -= valid_bytes;
 	} else {
 		error = rmi_read_block(rmi_dev,
 				data_base_addr, f11->sensor.data_pkt,

drivers/input/rmi4/rmi_f12.c

@@ -55,6 +55,9 @@ struct f12_data {
 
 	const struct rmi_register_desc_item *data15;
 	u16 data15_offset;
+
+	unsigned long *abs_mask;
+	unsigned long *rel_mask;
 };
 
 static int rmi_f12_read_sensor_tuning(struct f12_data *f12)
@@ -209,8 +212,8 @@ static irqreturn_t rmi_f12_attention(int irq, void *ctx)
 			valid_bytes = sensor->attn_size;
 		memcpy(sensor->data_pkt, drvdata->attn_data.data,
 			valid_bytes);
-		drvdata->attn_data.data += sensor->attn_size;
+		drvdata->attn_data.data += valid_bytes;
-		drvdata->attn_data.size -= sensor->attn_size;
+		drvdata->attn_data.size -= valid_bytes;
 	} else {
 		retval = rmi_read_block(rmi_dev, f12->data_addr,
 					sensor->data_pkt, sensor->pkt_size);
@@ -291,9 +294,18 @@ static int rmi_f12_write_control_regs(struct rmi_function *fn)
 static int rmi_f12_config(struct rmi_function *fn)
 {
 	struct rmi_driver *drv = fn->rmi_dev->driver;
+	struct f12_data *f12 = dev_get_drvdata(&fn->dev);
+	struct rmi_2d_sensor *sensor;
 	int ret;
 
-	drv->set_irq_bits(fn->rmi_dev, fn->irq_mask);
+	sensor = &f12->sensor;
+
+	if (!sensor->report_abs)
+		drv->clear_irq_bits(fn->rmi_dev, f12->abs_mask);
+	else
+		drv->set_irq_bits(fn->rmi_dev, f12->abs_mask);
+
+	drv->clear_irq_bits(fn->rmi_dev, f12->rel_mask);
 
 	ret = rmi_f12_write_control_regs(fn);
 	if (ret)
@@ -315,9 +327,12 @@ static int rmi_f12_probe(struct rmi_function *fn)
 	struct rmi_device_platform_data *pdata = rmi_get_platform_data(rmi_dev);
 	struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
 	u16 data_offset = 0;
+	int mask_size;
 
 	rmi_dbg(RMI_DEBUG_FN, &fn->dev, "%s\n", __func__);
 
+	mask_size = BITS_TO_LONGS(drvdata->irq_count) * sizeof(unsigned long);
+
 	ret = rmi_read(fn->rmi_dev, query_addr, &buf);
 	if (ret < 0) {
 		dev_err(&fn->dev, "Failed to read general info register: %d\n",
@@ -332,10 +347,19 @@ static int rmi_f12_probe(struct rmi_function *fn)
 		return -ENODEV;
 	}
 
-	f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data), GFP_KERNEL);
+	f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data) + mask_size * 2,
+			GFP_KERNEL);
 	if (!f12)
 		return -ENOMEM;
 
+	f12->abs_mask = (unsigned long *)((char *)f12
+			+ sizeof(struct f12_data));
+	f12->rel_mask = (unsigned long *)((char *)f12
+			+ sizeof(struct f12_data) + mask_size);
+
+	set_bit(fn->irq_pos, f12->abs_mask);
+	set_bit(fn->irq_pos + 1, f12->rel_mask);
+
 	f12->has_dribble = !!(buf & BIT(3));
 
 	if (fn->dev.of_node) {

drivers/input/rmi4/rmi_f54.c

@@ -359,7 +359,7 @@ static const struct vb2_ops rmi_f54_queue_ops = {
 static const struct vb2_queue rmi_f54_queue = {
 	.type = V4L2_BUF_TYPE_VIDEO_CAPTURE,
 	.io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ,
-	.buf_struct_size = sizeof(struct vb2_buffer),
+	.buf_struct_size = sizeof(struct vb2_v4l2_buffer),
 	.ops = &rmi_f54_queue_ops,
 	.mem_ops = &vb2_vmalloc_memops,
 	.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC,
@@ -601,7 +601,7 @@ static int rmi_f54_config(struct rmi_function *fn)
 {
 	struct rmi_driver *drv = fn->rmi_dev->driver;
 
-	drv->set_irq_bits(fn->rmi_dev, fn->irq_mask);
+	drv->clear_irq_bits(fn->rmi_dev, fn->irq_mask);
 
 	return 0;
 }
@@ -730,6 +730,7 @@ static void rmi_f54_remove(struct rmi_function *fn)
 
 	video_unregister_device(&f54->vdev);
 	v4l2_device_unregister(&f54->v4l2);
+	destroy_workqueue(f54->workqueue);
 }
 
 struct rmi_function_handler rmi_f54_handler = {