Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "The big highlight is support for the Scalable Vector Extension (SVE)
  which required extensive ABI work to ensure we don't break existing
  applications by blowing away their signal stack with the rather large
  new vector context (<= 2 kbit per vector register). There's further
  work to be done optimising things like exception return, but the ABI
  is solid now.

  Much of the line count comes from some new PMU drivers we have, but
  they're pretty self-contained and I suspect we'll have more of them in
  future.

  Plenty of acronym soup here:

   - initial support for the Scalable Vector Extension (SVE)

   - improved handling for SError interrupts (required to handle RAS
     events)

   - enable GCC support for 128-bit integer types

   - remove kernel text addresses from backtraces and register dumps

   - use of WFE to implement long delay()s

   - ACPI IORT updates from Lorenzo Pieralisi

   - perf PMU driver for the Statistical Profiling Extension (SPE)

   - perf PMU driver for Hisilicon's system PMUs

   - misc cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (97 commits)
  arm64: Make ARMV8_DEPRECATED depend on SYSCTL
  arm64: Implement __lshrti3 library function
  arm64: support __int128 on gcc 5+
  arm64/sve: Add documentation
  arm64/sve: Detect SVE and activate runtime support
  arm64/sve: KVM: Hide SVE from CPU features exposed to guests
  arm64/sve: KVM: Treat guest SVE use as undefined instruction execution
  arm64/sve: KVM: Prevent guests from using SVE
  arm64/sve: Add sysctl to set the default vector length for new processes
  arm64/sve: Add prctl controls for userspace vector length management
  arm64/sve: ptrace and ELF coredump support
  arm64/sve: Preserve SVE registers around EFI runtime service calls
  arm64/sve: Preserve SVE registers around kernel-mode NEON use
  arm64/sve: Probe SVE capabilities and usable vector lengths
  arm64: cpufeature: Move sys_caps_initialised declarations
  arm64/sve: Backend logic for setting the vector length
  arm64/sve: Signal handling support
  arm64/sve: Support vector length resetting for new processes
  arm64/sve: Core task context handling
  arm64/sve: Low-level CPU setup
  ...

Documentation/arm64/cpu-feature-registers.txt

@@ -110,10 +110,20 @@ infrastructure:
      x--------------------------------------------------x
      | Name                         |  bits   | visible |
      |--------------------------------------------------|
-     | RES0                         | [63-32] |    n    |
+     | RES0                         | [63-48] |    n    |
+     |--------------------------------------------------|
+     | DP                           | [47-44] |    y    |
+     |--------------------------------------------------|
+     | SM4                          | [43-40] |    y    |
+     |--------------------------------------------------|
+     | SM3                          | [39-36] |    y    |
+     |--------------------------------------------------|
+     | SHA3                         | [35-32] |    y    |
      |--------------------------------------------------|
      | RDM                          | [31-28] |    y    |
      |--------------------------------------------------|
+     | RES0                         | [27-24] |    n    |
+     |--------------------------------------------------|
      | ATOMICS                      | [23-20] |    y    |
      |--------------------------------------------------|
      | CRC32                        | [19-16] |    y    |
@@ -132,7 +142,11 @@ infrastructure:
      x--------------------------------------------------x
      | Name                         |  bits   | visible |
      |--------------------------------------------------|
-     | RES0                         | [63-28] |    n    |
+     | RES0                         | [63-36] |    n    |
+     |--------------------------------------------------|
+     | SVE                          | [35-32] |    y    |
+     |--------------------------------------------------|
+     | RES0                         | [31-28] |    n    |
      |--------------------------------------------------|
      | GIC                          | [27-24] |    n    |
      |--------------------------------------------------|

Documentation/arm64/elf_hwcaps.txt

@@ -0,0 +1,160 @@
+ARM64 ELF hwcaps
+================
+
+This document describes the usage and semantics of the arm64 ELF hwcaps.
+
+
+1. Introduction
+---------------
+
+Some hardware or software features are only available on some CPU
+implementations, and/or with certain kernel configurations, but have no
+architected discovery mechanism available to userspace code at EL0. The
+kernel exposes the presence of these features to userspace through a set
+of flags called hwcaps, exposed in the auxilliary vector.
+
+Userspace software can test for features by acquiring the AT_HWCAP entry
+of the auxilliary vector, and testing whether the relevant flags are
+set, e.g.
+
+bool floating_point_is_present(void)
+{
+	unsigned long hwcaps = getauxval(AT_HWCAP);
+	if (hwcaps & HWCAP_FP)
+		return true;
+
+	return false;
+}
+
+Where software relies on a feature described by a hwcap, it should check
+the relevant hwcap flag to verify that the feature is present before
+attempting to make use of the feature.
+
+Features cannot be probed reliably through other means. When a feature
+is not available, attempting to use it may result in unpredictable
+behaviour, and is not guaranteed to result in any reliable indication
+that the feature is unavailable, such as a SIGILL.
+
+
+2. Interpretation of hwcaps
+---------------------------
+
+The majority of hwcaps are intended to indicate the presence of features
+which are described by architected ID registers inaccessible to
+userspace code at EL0. These hwcaps are defined in terms of ID register
+fields, and should be interpreted with reference to the definition of
+these fields in the ARM Architecture Reference Manual (ARM ARM).
+
+Such hwcaps are described below in the form:
+
+    Functionality implied by idreg.field == val.
+
+Such hwcaps indicate the availability of functionality that the ARM ARM
+defines as being present when idreg.field has value val, but do not
+indicate that idreg.field is precisely equal to val, nor do they
+indicate the absence of functionality implied by other values of
+idreg.field.
+
+Other hwcaps may indicate the presence of features which cannot be
+described by ID registers alone. These may be described without
+reference to ID registers, and may refer to other documentation.
+
+
+3. The hwcaps exposed in AT_HWCAP
+---------------------------------
+
+HWCAP_FP
+
+    Functionality implied by ID_AA64PFR0_EL1.FP == 0b0000.
+
+HWCAP_ASIMD
+
+    Functionality implied by ID_AA64PFR0_EL1.AdvSIMD == 0b0000.
+
+HWCAP_EVTSTRM
+
+    The generic timer is configured to generate events at a frequency of
+    approximately 100KHz.
+
+HWCAP_AES
+
+    Functionality implied by ID_AA64ISAR1_EL1.AES == 0b0001.
+
+HWCAP_PMULL
+
+    Functionality implied by ID_AA64ISAR1_EL1.AES == 0b0010.
+
+HWCAP_SHA1
+
+    Functionality implied by ID_AA64ISAR0_EL1.SHA1 == 0b0001.
+
+HWCAP_SHA2
+
+    Functionality implied by ID_AA64ISAR0_EL1.SHA2 == 0b0001.
+
+HWCAP_CRC32
+
+    Functionality implied by ID_AA64ISAR0_EL1.CRC32 == 0b0001.
+
+HWCAP_ATOMICS
+
+    Functionality implied by ID_AA64ISAR0_EL1.Atomic == 0b0010.
+
+HWCAP_FPHP
+
+    Functionality implied by ID_AA64PFR0_EL1.FP == 0b0001.
+
+HWCAP_ASIMDHP
+
+    Functionality implied by ID_AA64PFR0_EL1.AdvSIMD == 0b0001.
+
+HWCAP_CPUID
+
+    EL0 access to certain ID registers is available, to the extent
+    described by Documentation/arm64/cpu-feature-registers.txt.
+
+    These ID registers may imply the availability of features.
+
+HWCAP_ASIMDRDM
+
+    Functionality implied by ID_AA64ISAR0_EL1.RDM == 0b0001.
+
+HWCAP_JSCVT
+
+    Functionality implied by ID_AA64ISAR1_EL1.JSCVT == 0b0001.
+
+HWCAP_FCMA
+
+    Functionality implied by ID_AA64ISAR1_EL1.FCMA == 0b0001.
+
+HWCAP_LRCPC
+
+    Functionality implied by ID_AA64ISAR1_EL1.LRCPC == 0b0001.
+
+HWCAP_DCPOP
+
+    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001.
+
+HWCAP_SHA3
+
+    Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001.
+
+HWCAP_SM3
+
+    Functionality implied by ID_AA64ISAR0_EL1.SM3 == 0b0001.
+
+HWCAP_SM4
+
+    Functionality implied by ID_AA64ISAR0_EL1.SM4 == 0b0001.
+
+HWCAP_ASIMDDP
+
+    Functionality implied by ID_AA64ISAR0_EL1.DP == 0b0001.
+
+HWCAP_SHA512
+
+    Functionality implied by ID_AA64ISAR0_EL1.SHA2 == 0b0002.
+
+HWCAP_SVE
+
+    Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.

Documentation/arm64/memory.txt

@@ -86,9 +86,9 @@ Translation table lookup with 64KB pages:
  +-------------------------------------------------> [63] TTBR0/1
 
 
-When using KVM, the hypervisor maps kernel pages in EL2, at a fixed
-offset from the kernel VA (top 24bits of the kernel VA set to zero):
+When using KVM without the Virtualization Host Extensions, the hypervisor
+maps kernel pages in EL2 at a fixed offset from the kernel VA. See the
+kern_hyp_va macro for more details.
 
-Start			End			Size		Use
------------------------------------------------------------------------
-0000004000000000	0000007fffffffff	 256GB		kernel objects mapped in HYP
+When using KVM with the Virtualization Host Extensions, no additional
+mappings are created, since the host kernel runs directly in EL2.

Documentation/arm64/sve.txt

@@ -0,0 +1,508 @@
+            Scalable Vector Extension support for AArch64 Linux
+            ===================================================
+
+Author: Dave Martin <Dave.Martin@arm.com>
+Date:   4 August 2017
+
+This document outlines briefly the interface provided to userspace by Linux in
+order to support use of the ARM Scalable Vector Extension (SVE).
+
+This is an outline of the most important features and issues only and not
+intended to be exhaustive.
+
+This document does not aim to describe the SVE architecture or programmer's
+model.  To aid understanding, a minimal description of relevant programmer's
+model features for SVE is included in Appendix A.
+
+
+1.  General
+-----------
+
+* SVE registers Z0..Z31, P0..P15 and FFR and the current vector length VL, are
+  tracked per-thread.
+
+* The presence of SVE is reported to userspace via HWCAP_SVE in the aux vector
+  AT_HWCAP entry.  Presence of this flag implies the presence of the SVE
+  instructions and registers, and the Linux-specific system interfaces
+  described in this document.  SVE is reported in /proc/cpuinfo as "sve".
+
+* Support for the execution of SVE instructions in userspace can also be
+  detected by reading the CPU ID register ID_AA64PFR0_EL1 using an MRS
+  instruction, and checking that the value of the SVE field is nonzero. [3]
+
+  It does not guarantee the presence of the system interfaces described in the
+  following sections: software that needs to verify that those interfaces are
+  present must check for HWCAP_SVE instead.
+
+* Debuggers should restrict themselves to interacting with the target via the
+  NT_ARM_SVE regset.  The recommended way of detecting support for this regset
+  is to connect to a target process first and then attempt a
+  ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov).
+
+
+2.  Vector length terminology
+-----------------------------
+
+The size of an SVE vector (Z) register is referred to as the "vector length".
+
+To avoid confusion about the units used to express vector length, the kernel
+adopts the following conventions:
+
+* Vector length (VL) = size of a Z-register in bytes
+
+* Vector quadwords (VQ) = size of a Z-register in units of 128 bits
+
+(So, VL = 16 * VQ.)
+
+The VQ convention is used where the underlying granularity is important, such
+as in data structure definitions.  In most other situations, the VL convention
+is used.  This is consistent with the meaning of the "VL" pseudo-register in
+the SVE instruction set architecture.
+
+
+3.  System call behaviour
+-------------------------
+
+* On syscall, V0..V31 are preserved (as without SVE).  Thus, bits [127:0] of
+  Z0..Z31 are preserved.  All other bits of Z0..Z31, and all of P0..P15 and FFR
+  become unspecified on return from a syscall.
+
+* The SVE registers are not used to pass arguments to or receive results from
+  any syscall.
+
+* In practice the affected registers/bits will be preserved or will be replaced
+  with zeros on return from a syscall, but userspace should not make
+  assumptions about this.  The kernel behaviour may vary on a case-by-case
+  basis.
+
+* All other SVE state of a thread, including the currently configured vector
+  length, the state of the PR_SVE_VL_INHERIT flag, and the deferred vector
+  length (if any), is preserved across all syscalls, subject to the specific
+  exceptions for execve() described in section 6.
+
+  In particular, on return from a fork() or clone(), the parent and new child
+  process or thread share identical SVE configuration, matching that of the
+  parent before the call.
+
+
+4.  Signal handling
+-------------------
+
+* A new signal frame record sve_context encodes the SVE registers on signal
+  delivery. [1]
+
+* This record is supplementary to fpsimd_context.  The FPSR and FPCR registers
+  are only present in fpsimd_context.  For convenience, the content of V0..V31
+  is duplicated between sve_context and fpsimd_context.
+
+* The signal frame record for SVE always contains basic metadata, in particular
+  the thread's vector length (in sve_context.vl).
+
+* The SVE registers may or may not be included in the record, depending on
+  whether the registers are live for the thread.  The registers are present if
+  and only if:
+  sve_context.head.size >= SVE_SIG_CONTEXT_SIZE(sve_vq_from_vl(sve_context.vl)).
+
+* If the registers are present, the remainder of the record has a vl-dependent
+  size and layout.  Macros SVE_SIG_* are defined [1] to facilitate access to
+  the members.
+
+* If the SVE context is too big to fit in sigcontext.__reserved[], then extra
+  space is allocated on the stack, an extra_context record is written in
+  __reserved[] referencing this space.  sve_context is then written in the
+  extra space.  Refer to [1] for further details about this mechanism.
+
+
+5.  Signal return
+-----------------
+
+When returning from a signal handler:
+
+* If there is no sve_context record in the signal frame, or if the record is
+  present but contains no register data as desribed in the previous section,
+  then the SVE registers/bits become non-live and take unspecified values.
+
+* If sve_context is present in the signal frame and contains full register
+  data, the SVE registers become live and are populated with the specified
+  data.  However, for backward compatibility reasons, bits [127:0] of Z0..Z31
+  are always restored from the corresponding members of fpsimd_context.vregs[]
+  and not from sve_context.  The remaining bits are restored from sve_context.
+
+* Inclusion of fpsimd_context in the signal frame remains mandatory,
+  irrespective of whether sve_context is present or not.
+
+* The vector length cannot be changed via signal return.  If sve_context.vl in
+  the signal frame does not match the current vector length, the signal return
+  attempt is treated as illegal, resulting in a forced SIGSEGV.
+
+
+6.  prctl extensions
+--------------------
+
+Some new prctl() calls are added to allow programs to manage the SVE vector
+length:
+
+prctl(PR_SVE_SET_VL, unsigned long arg)
+
+    Sets the vector length of the calling thread and related flags, where
+    arg == vl | flags.  Other threads of the calling process are unaffected.
+
+    vl is the desired vector length, where sve_vl_valid(vl) must be true.
+
+    flags:
+
+	PR_SVE_SET_VL_INHERIT
+
+	    Inherit the current vector length across execve().  Otherwise, the
+	    vector length is reset to the system default at execve().  (See
+	    Section 9.)
+
+	PR_SVE_SET_VL_ONEXEC
+
+	    Defer the requested vector length change until the next execve()
+	    performed by this thread.
+
+	    The effect is equivalent to implicit exceution of the following
+	    call immediately after the next execve() (if any) by the thread:
+
+		prctl(PR_SVE_SET_VL, arg & ~PR_SVE_SET_VL_ONEXEC)
+
+	    This allows launching of a new program with a different vector
+	    length, while avoiding runtime side effects in the caller.
+
+
+	    Without PR_SVE_SET_VL_ONEXEC, the requested change takes effect
+	    immediately.
+
+
+    Return value: a nonnegative on success, or a negative value on error:
+	EINVAL: SVE not supported, invalid vector length requested, or
+	    invalid flags.
+
+
+    On success:
+
+    * Either the calling thread's vector length or the deferred vector length
+      to be applied at the next execve() by the thread (dependent on whether
+      PR_SVE_SET_VL_ONEXEC is present in arg), is set to the largest value
+      supported by the system that is less than or equal to vl.  If vl ==
+      SVE_VL_MAX, the value set will be the largest value supported by the
+      system.
+
+    * Any previously outstanding deferred vector length change in the calling
+      thread is cancelled.
+
+    * The returned value describes the resulting configuration, encoded as for
+      PR_SVE_GET_VL.  The vector length reported in this value is the new
+      current vector length for this thread if PR_SVE_SET_VL_ONEXEC was not
+      present in arg; otherwise, the reported vector length is the deferred
+      vector length that will be applied at the next execve() by the calling
+      thread.
+
+    * Changing the vector length causes all of P0..P15, FFR and all bits of
+      Z0..V31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
+      unspecified.  Calling PR_SVE_SET_VL with vl equal to the thread's current
+      vector length, or calling PR_SVE_SET_VL with the PR_SVE_SET_VL_ONEXEC
+      flag, does not constitute a change to the vector length for this purpose.
+
+
+prctl(PR_SVE_GET_VL)
+
+    Gets the vector length of the calling thread.
+
+    The following flag may be OR-ed into the result:
+
+	PR_SVE_SET_VL_INHERIT
+
+	    Vector length will be inherited across execve().
+
+    There is no way to determine whether there is an outstanding deferred
+    vector length change (which would only normally be the case between a
+    fork() or vfork() and the corresponding execve() in typical use).
+
+    To extract the vector length from the result, and it with
+    PR_SVE_VL_LEN_MASK.
+
+    Return value: a nonnegative value on success, or a negative value on error:
+	EINVAL: SVE not supported.
+
+
+7.  ptrace extensions
+---------------------
+
+* A new regset NT_ARM_SVE is defined for use with PTRACE_GETREGSET and
+  PTRACE_SETREGSET.
+
+  Refer to [2] for definitions.
+
+The regset data starts with struct user_sve_header, containing:
+
+    size
+
+	Size of the complete regset, in bytes.
+	This depends on vl and possibly on other things in the future.
+
+	If a call to PTRACE_GETREGSET requests less data than the value of
+	size, the caller can allocate a larger buffer and retry in order to
+	read the complete regset.
+
+    max_size
+
+	Maximum size in bytes that the regset can grow to for the target
+	thread.  The regset won't grow bigger than this even if the target
+	thread changes its vector length etc.
+
+    vl
+
+	Target thread's current vector length, in bytes.
+
+    max_vl
+
+	Maximum possible vector length for the target thread.
+
+    flags
+
+	either
+
+	    SVE_PT_REGS_FPSIMD
+
+		SVE registers are not live (GETREGSET) or are to be made
+		non-live (SETREGSET).
+
+		The payload is of type struct user_fpsimd_state, with the same
+		meaning as for NT_PRFPREG, starting at offset
+		SVE_PT_FPSIMD_OFFSET from the start of user_sve_header.
+
+		Extra data might be appended in the future: the size of the
+		payload should be obtained using SVE_PT_FPSIMD_SIZE(vq, flags).
+
+		vq should be obtained using sve_vq_from_vl(vl).
+
+		or
+
+	    SVE_PT_REGS_SVE
+
+		SVE registers are live (GETREGSET) or are to be made live
+		(SETREGSET).
+
+		The payload contains the SVE register data, starting at offset
+		SVE_PT_SVE_OFFSET from the start of user_sve_header, and with
+		size SVE_PT_SVE_SIZE(vq, flags);
+
+	... OR-ed with zero or more of the following flags, which have the same
+	meaning and behaviour as the corresponding PR_SET_VL_* flags:
+
+	    SVE_PT_VL_INHERIT
+
+	    SVE_PT_VL_ONEXEC (SETREGSET only).
+
+* The effects of changing the vector length and/or flags are equivalent to
+  those documented for PR_SVE_SET_VL.
+
+  The caller must make a further GETREGSET call if it needs to know what VL is
+  actually set by SETREGSET, unless is it known in advance that the requested
+  VL is supported.
+
+* In the SVE_PT_REGS_SVE case, the size and layout of the payload depends on
+  the header fields.  The SVE_PT_SVE_*() macros are provided to facilitate
+  access to the members.
+
+* In either case, for SETREGSET it is permissible to omit the payload, in which
+  case only the vector length and flags are changed (along with any
+  consequences of those changes).
+
+* For SETREGSET, if an SVE_PT_REGS_SVE payload is present and the
+  requested VL is not supported, the effect will be the same as if the
+  payload were omitted, except that an EIO error is reported.  No
+  attempt is made to translate the payload data to the correct layout
+  for the vector length actually set.  The thread's FPSIMD state is
+  preserved, but the remaining bits of the SVE registers become
+  unspecified.  It is up to the caller to translate the payload layout
+  for the actual VL and retry.
+
+* The effect of writing a partial, incomplete payload is unspecified.
+
+
+8.  ELF coredump extensions
+---------------------------
+
+* A NT_ARM_SVE note will be added to each coredump for each thread of the
+  dumped process.  The contents will be equivalent to the data that would have
+  been read if a PTRACE_GETREGSET of NT_ARM_SVE were executed for each thread
+  when the coredump was generated.
+
+
+9.  System runtime configuration
+--------------------------------
+
+* To mitigate the ABI impact of expansion of the signal frame, a policy
+  mechanism is provided for administrators, distro maintainers and developers
+  to set the default vector length for userspace processes:
+
+/proc/sys/abi/sve_default_vector_length
+
+    Writing the text representation of an integer to this file sets the system
+    default vector length to the specified value, unless the value is greater
+    than the maximum vector length supported by the system in which case the
+    default vector length is set to that maximum.
+
+    The result can be determined by reopening the file and reading its
+    contents.
+
+    At boot, the default vector length is initially set to 64 or the maximum
+    supported vector length, whichever is smaller.  This determines the initial
+    vector length of the init process (PID 1).
+
+    Reading this file returns the current system default vector length.
+
+* At every execve() call, the new vector length of the new process is set to
+  the system default vector length, unless
+
+    * PR_SVE_SET_VL_INHERIT (or equivalently SVE_PT_VL_INHERIT) is set for the
+      calling thread, or
+
+    * a deferred vector length change is pending, established via the
+      PR_SVE_SET_VL_ONEXEC flag (or SVE_PT_VL_ONEXEC).
+
+* Modifying the system default vector length does not affect the vector length
+  of any existing process or thread that does not make an execve() call.
+
+
+Appendix A.  SVE programmer's model (informative)
+=================================================
+
+This section provides a minimal description of the additions made by SVE to the
+ARMv8-A programmer's model that are relevant to this document.
+
+Note: This section is for information only and not intended to be complete or
+to replace any architectural specification.
+
+A.1.  Registers
+---------------
+
+In A64 state, SVE adds the following:
+
+* 32 8VL-bit vector registers Z0..Z31
+  For each Zn, Zn bits [127:0] alias the ARMv8-A vector register Vn.
+
+  A register write using a Vn register name zeros all bits of the corresponding
+  Zn except for bits [127:0].
+
+* 16 VL-bit predicate registers P0..P15
+
+* 1 VL-bit special-purpose predicate register FFR (the "first-fault register")
+
+* a VL "pseudo-register" that determines the size of each vector register
+
+  The SVE instruction set architecture provides no way to write VL directly.
+  Instead, it can be modified only by EL1 and above, by writing appropriate
+  system registers.
+
+* The value of VL can be configured at runtime by EL1 and above:
+  16 <= VL <= VLmax, where VL must be a multiple of 16.
+
+* The maximum vector length is determined by the hardware:
+  16 <= VLmax <= 256.
+
+  (The SVE architecture specifies 256, but permits future architecture
+  revisions to raise this limit.)
+
+* FPSR and FPCR are retained from ARMv8-A, and interact with SVE floating-point
+  operations in a similar way to the way in which they interact with ARMv8
+  floating-point operations.
+
+         8VL-1                       128               0  bit index
+        +----          ////            -----------------+
+     Z0 |                               :       V0      |
+      :                                          :
+     Z7 |                               :       V7      |
+     Z8 |                               :     * V8      |
+      :                                       :  :
+    Z15 |                               :     *V15      |
+    Z16 |                               :      V16      |
+      :                                          :
+    Z31 |                               :      V31      |
+        +----          ////            -----------------+
+                                                 31    0
+         VL-1                  0                +-------+
+        +----       ////      --+          FPSR |       |
+     P0 |                       |               +-------+
+      : |                       |         *FPCR |       |
+    P15 |                       |               +-------+
+        +----       ////      --+
+    FFR |                       |               +-----+
+        +----       ////      --+            VL |     |
+                                                +-----+
+
+(*) callee-save:
+    This only applies to bits [63:0] of Z-/V-registers.
+    FPCR contains callee-save and caller-save bits.  See [4] for details.
+
+
+A.2.  Procedure call standard
+-----------------------------
+
+The ARMv8-A base procedure call standard is extended as follows with respect to
+the additional SVE register state:
+
+* All SVE register bits that are not shared with FP/SIMD are caller-save.
+
+* Z8 bits [63:0] .. Z15 bits [63:0] are callee-save.
+
+  This follows from the way these bits are mapped to V8..V15, which are caller-
+  save in the base procedure call standard.
+
+
+Appendix B.  ARMv8-A FP/SIMD programmer's model
+===============================================
+
+Note: This section is for information only and not intended to be complete or
+to replace any architectural specification.
+
+Refer to [4] for for more information.
+
+ARMv8-A defines the following floating-point / SIMD register state:
+
+* 32 128-bit vector registers V0..V31
+* 2 32-bit status/control registers FPSR, FPCR
+
+         127           0  bit index
+        +---------------+
+     V0 |               |
+      : :               :
+     V7 |               |
+   * V8 |               |
+   :  : :               :
+   *V15 |               |
+    V16 |               |
+      : :               :
+    V31 |               |
+        +---------------+
+
+                 31    0
+                +-------+
+           FPSR |       |
+                +-------+
+          *FPCR |       |
+                +-------+
+
+(*) callee-save:
+    This only applies to bits [63:0] of V-registers.
+    FPCR contains a mixture of callee-save and caller-save bits.
+
+
+References
+==========
+
+[1] arch/arm64/include/uapi/asm/sigcontext.h
+    AArch64 Linux signal ABI definitions
+
+[2] arch/arm64/include/uapi/asm/ptrace.h
+    AArch64 Linux ptrace ABI definitions
+
+[3] linux/Documentation/arm64/cpu-feature-registers.txt
+
+[4] ARM IHI0055C
+    http://infocenter.arm.com/help/topic/com.arm.doc.ihi0055c/IHI0055C_beta_aapcs64.pdf
+    http://infocenter.arm.com/help/topic/com.arm.doc.subset.swdev.abi/index.html
+    Procedure Call Standard for the ARM 64-bit Architecture (AArch64)

Documentation/devicetree/bindings/arm/spe-pmu.txt

@@ -0,0 +1,20 @@
+* ARMv8.2 Statistical Profiling Extension (SPE) Performance Monitor Units (PMU)
+
+ARMv8.2 introduces the optional Statistical Profiling Extension for collecting
+performance sample data using an in-memory trace buffer.
+
+** SPE Required properties:
+
+- compatible : should be one of:
+	       "arm,statistical-profiling-extension-v1"
+
+- interrupts : Exactly 1 PPI must be listed. For heterogeneous systems where
+               SPE is only supported on a subset of the CPUs, please consult
+	       the arm,gic-v3 binding for details on describing a PPI partition.
+
+** Example:
+
+spe-pmu {
+        compatible = "arm,statistical-profiling-extension-v1";
+        interrupts = <GIC_PPI 05 IRQ_TYPE_LEVEL_HIGH &part1>;
+};

Documentation/perf/hisi-pmu.txt

@@ -0,0 +1,53 @@
+HiSilicon SoC uncore Performance Monitoring Unit (PMU)
+======================================================
+The HiSilicon SoC chip includes various independent system device PMUs
+such as L3 cache (L3C), Hydra Home Agent (HHA) and DDRC. These PMUs are
+independent and have hardware logic to gather statistics and performance
+information.
+
+The HiSilicon SoC encapsulates multiple CPU and IO dies. Each CPU cluster
+(CCL) is made up of 4 cpu cores sharing one L3 cache; each CPU die is
+called Super CPU cluster (SCCL) and is made up of 6 CCLs. Each SCCL has
+two HHAs (0 - 1) and four DDRCs (0 - 3), respectively.
+
+HiSilicon SoC uncore PMU driver
+---------------------------------------
+Each device PMU has separate registers for event counting, control and
+interrupt, and the PMU driver shall register perf PMU drivers like L3C,
+HHA and DDRC etc. The available events and configuration options shall
+be described in the sysfs, see :
+/sys/devices/hisi_sccl{X}_<l3c{Y}/hha{Y}/ddrc{Y}>/, or
+/sys/bus/event_source/devices/hisi_sccl{X}_<l3c{Y}/hha{Y}/ddrc{Y}>.
+The "perf list" command shall list the available events from sysfs.
+
+Each L3C, HHA and DDRC is registered as a separate PMU with perf. The PMU
+name will appear in event listing as hisi_sccl<sccl-id>_module<index-id>.
+where "sccl-id" is the identifier of the SCCL and "index-id" is the index of
+module.
+e.g. hisi_sccl3_l3c0/rd_hit_cpipe is READ_HIT_CPIPE event of L3C index #0 in
+SCCL ID #3.
+e.g. hisi_sccl1_hha0/rx_operations is RX_OPERATIONS event of HHA index #0 in
+SCCL ID #1.
+
+The driver also provides a "cpumask" sysfs attribute, which shows the CPU core
+ID used to count the uncore PMU event.
+
+Example usage of perf:
+$# perf list
+hisi_sccl3_l3c0/rd_hit_cpipe/ [kernel PMU event]
+------------------------------------------
+hisi_sccl3_l3c0/wr_hit_cpipe/ [kernel PMU event]
+------------------------------------------
+hisi_sccl1_l3c0/rd_hit_cpipe/ [kernel PMU event]
+------------------------------------------
+hisi_sccl1_l3c0/wr_hit_cpipe/ [kernel PMU event]
+------------------------------------------
+
+$# perf stat -a -e hisi_sccl3_l3c0/rd_hit_cpipe/ sleep 5
+$# perf stat -a -e hisi_sccl3_l3c0/config=0x02/ sleep 5
+
+The current driver does not support sampling. So "perf record" is unsupported.
+Also attach to a task is unsupported as the events are all uncore.
+
+Note: Please contact the maintainer for a complete list of events supported for
+the PMU devices in the SoC and its information if needed.

MAINTAINERS

@@ -6259,6 +6259,13 @@ S:	Maintained
 F:	drivers/net/ethernet/hisilicon/
 F:	Documentation/devicetree/bindings/net/hisilicon*.txt
 
+HISILICON PMU DRIVER
+M:	Shaokun Zhang <zhangshaokun@hisilicon.com>
+W:	http://www.hisilicon.com
+S:	Supported
+F:	drivers/perf/hisilicon
+F:	Documentation/perf/hisi-pmu.txt
+
 HISILICON ROCE DRIVER
 M:	Lijun Ou <oulijun@huawei.com>
 M:	Wei Hu(Xavier) <xavier.huwei@huawei.com>

arch/arm/include/asm/arch_timer.h

@@ -107,6 +107,7 @@ static inline u32 arch_timer_get_cntkctl(void)
 static inline void arch_timer_set_cntkctl(u32 cntkctl)
 {
 	asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
+	isb();
 }
 
 #endif

arch/arm/include/asm/kvm_host.h

@@ -293,4 +293,7 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 
+/* All host FP/SIMD state is restored on guest exit, so nothing to save: */
+static inline void kvm_fpsimd_flush_cpu_state(void) {}
+
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm64/Kconfig

@@ -21,7 +21,7 @@ config ARM64
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK if !PREEMPT
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPT
 	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPT
@@ -115,7 +115,7 @@ config ARM64
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP if NUMA
-	select HAVE_NMI if ACPI_APEI_SEA
+	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -136,6 +136,7 @@ config ARM64
 	select PCI_ECAM if ACPI
 	select POWER_RESET
 	select POWER_SUPPLY
+	select REFCOUNT_FULL
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
@@ -842,6 +843,7 @@ config FORCE_MAX_ZONEORDER
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT
+	depends on SYSCTL
 	help
 	  Legacy software support may require certain instructions
 	  that have been deprecated or obsoleted in the architecture.
@@ -1011,6 +1013,17 @@ config ARM64_PMEM
 
 endmenu
 
+config ARM64_SVE
+	bool "ARM Scalable Vector Extension support"
+	default y
+	help
+	  The Scalable Vector Extension (SVE) is an extension to the AArch64
+	  execution state which complements and extends the SIMD functionality
+	  of the base architecture to support much larger vectors and to enable
+	  additional vectorisation opportunities.
+
+	  To enable use of this extension on CPUs that implement it, say Y.
+
 config ARM64_MODULE_CMODEL_LARGE
 	bool
 
@@ -1099,6 +1112,7 @@ config EFI_STUB
 config EFI
 	bool "UEFI runtime support"
 	depends on OF && !CPU_BIG_ENDIAN
+	depends on KERNEL_MODE_NEON
 	select LIBFDT
 	select UCS2_STRING
 	select EFI_PARAMS_FROM_FDT

arch/arm64/Makefile

@@ -14,8 +14,12 @@ LDFLAGS_vmlinux	:=-p --no-undefined -X
 CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 GZFLAGS		:=-9
 
-ifneq ($(CONFIG_RELOCATABLE),)
-LDFLAGS_vmlinux		+= -pie -shared -Bsymbolic
+ifeq ($(CONFIG_RELOCATABLE), y)
+# Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour
+# for relative relocs, since this leads to better Image compression
+# with the relocation offsets always being zero.
+LDFLAGS_vmlinux		+= -pie -shared -Bsymbolic \
+			$(call ld-option, --no-apply-dynamic-relocs)
 endif
 
 ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
@@ -53,6 +57,8 @@ KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst)
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)
 
+KBUILD_CFLAGS	+= $(call cc-ifversion, -ge, 0500, -DCONFIG_ARCH_SUPPORTS_INT128)
+
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__

arch/arm64/include/asm/arch_timer.h

@@ -144,6 +144,7 @@ static inline u32 arch_timer_get_cntkctl(void)
 static inline void arch_timer_set_cntkctl(u32 cntkctl)
 {
 	write_sysreg(cntkctl, cntkctl_el1);
+	isb();
 }
 
 static inline u64 arch_counter_get_cntpct(void)

arch/arm64/include/asm/asm-bug.h

@@ -22,10 +22,10 @@
 #define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
 #define __BUGVERBOSE_LOCATION(file, line)			\
 		.pushsection .rodata.str,"aMS",@progbits,1;	\
-	2:	.string file;					\
+	14472:	.string file;					\
 		.popsection;					\
 								\
-		.long 2b - 0b;					\
+		.long 14472b - 14470b;				\
 		.short line;
 #else
 #define _BUGVERBOSE_LOCATION(file, line)
@@ -36,11 +36,11 @@
 #define __BUG_ENTRY(flags) 				\
 		.pushsection __bug_table,"aw";		\
 		.align 2;				\
-	0:	.long 1f - 0b;				\
+	14470:	.long 14471f - 14470b;			\
 _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
 		.short flags; 				\
 		.popsection;				\
-	1:
+	14471:
 #else
 #define __BUG_ENTRY(flags)
 #endif

arch/arm64/include/asm/assembler.h

@@ -25,12 +25,41 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
+#include <asm/debug-monitors.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 
+	.macro save_and_disable_daif, flags
+	mrs	\flags, daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro disable_daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro enable_daif
+	msr	daifclr, #0xf
+	.endm
+
+	.macro	restore_daif, flags:req
+	msr	daif, \flags
+	.endm
+
+	/* Only on aarch64 pstate, PSR_D_BIT is different for aarch32 */
+	.macro	inherit_daif, pstate:req, tmp:req
+	and	\tmp, \pstate, #(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+	msr	daif, \tmp
+	.endm
+
+	/* IRQ is the lowest priority flag, unconditionally unmask the rest. */
+	.macro enable_da_f
+	msr	daifclr, #(8 | 4 | 1)
+	.endm
+
 /*
  * Enable and disable interrupts.
  */
@@ -51,13 +80,6 @@
 	msr	daif, \flags
 	.endm
 
-/*
- * Enable and disable debug exceptions.
- */
-	.macro	disable_dbg
-	msr	daifset, #8
-	.endm
-
 	.macro	enable_dbg
 	msr	daifclr, #8
 	.endm
@@ -65,30 +87,21 @@
 	.macro	disable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
 	mrs	\tmp, mdscr_el1
-	bic	\tmp, \tmp, #1
+	bic	\tmp, \tmp, #DBG_MDSCR_SS
 	msr	mdscr_el1, \tmp
 	isb	// Synchronise with enable_dbg
 9990:
 	.endm
 
+	/* call with daif masked */
 	.macro	enable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
-	disable_dbg
 	mrs	\tmp, mdscr_el1
-	orr	\tmp, \tmp, #1
+	orr	\tmp, \tmp, #DBG_MDSCR_SS
 	msr	mdscr_el1, \tmp
 9990:
 	.endm
 
-/*
- * Enable both debug exceptions and interrupts. This is likely to be
- * faster than two daifclr operations, since writes to this register
- * are self-synchronising.
- */
-	.macro	enable_dbg_and_irq
-	msr	daifclr, #(8 | 2)
-	.endm
-
 /*
  * SMP data memory barrier
  */

arch/arm64/include/asm/barrier.h

@@ -31,6 +31,8 @@
 #define dmb(opt)	asm volatile("dmb " #opt : : : "memory")
 #define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
+#define psb_csync()	asm volatile("hint #17" : : : "memory")
+
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)

arch/arm64/include/asm/cpu.h

@@ -41,6 +41,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64mmfr2;
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
+	u64		reg_id_aa64zfr0;
 
 	u32		reg_id_dfr0;
 	u32		reg_id_isar0;
@@ -59,6 +60,9 @@ struct cpuinfo_arm64 {
 	u32		reg_mvfr0;
 	u32		reg_mvfr1;
 	u32		reg_mvfr2;
+
+	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
+	u64		reg_zcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);

arch/arm64/include/asm/cpucaps.h

@@ -40,7 +40,8 @@
 #define ARM64_WORKAROUND_858921			19
 #define ARM64_WORKAROUND_CAVIUM_30115		20
 #define ARM64_HAS_DCPOP				21
+#define ARM64_SVE				22
 
-#define ARM64_NCAPS				22
+#define ARM64_NCAPS				23
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -10,7 +10,9 @@
 #define __ASM_CPUFEATURE_H
 
 #include <asm/cpucaps.h>
+#include <asm/fpsimd.h>
 #include <asm/hwcap.h>
+#include <asm/sigcontext.h>
 #include <asm/sysreg.h>
 
 /*
@@ -223,6 +225,13 @@ static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
 	return val == ID_AA64PFR0_EL0_32BIT_64BIT;
 }
 
+static inline bool id_aa64pfr0_sve(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_SVE_SHIFT);
+
+	return val > 0;
+}
+
 void __init setup_cpu_features(void);
 
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
@@ -262,6 +271,39 @@ static inline bool system_uses_ttbr0_pan(void)
 		!cpus_have_const_cap(ARM64_HAS_PAN);
 }
 
+static inline bool system_supports_sve(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SVE) &&
+		cpus_have_const_cap(ARM64_SVE);
+}
+
+/*
+ * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
+ * vector length.
+ *
+ * Use only if SVE is present.
+ * This function clobbers the SVE vector length.
+ */
+static inline u64 read_zcr_features(void)
+{
+	u64 zcr;
+	unsigned int vq_max;
+
+	/*
+	 * Set the maximum possible VL, and write zeroes to all other
+	 * bits to see if they stick.
+	 */
+	sve_kernel_enable(NULL);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
+
+	zcr = read_sysreg_s(SYS_ZCR_EL1);
+	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
+	vq_max = sve_vq_from_vl(sve_get_vl());
+	zcr |= vq_max - 1; /* set LEN field to maximum effective value */
+
+	return zcr;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif

arch/arm64/include/asm/daifflags.h

@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2017 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_DAIFFLAGS_H
+#define __ASM_DAIFFLAGS_H
+
+#include <linux/irqflags.h>
+
+#define DAIF_PROCCTX		0
+#define DAIF_PROCCTX_NOIRQ	PSR_I_BIT
+
+/* mask/save/unmask/restore all exceptions, including interrupts. */
+static inline void local_daif_mask(void)
+{
+	asm volatile(
+		"msr	daifset, #0xf		// local_daif_mask\n"
+		:
+		:
+		: "memory");
+	trace_hardirqs_off();
+}
+
+static inline unsigned long local_daif_save(void)
+{
+	unsigned long flags;
+
+	asm volatile(
+		"mrs	%0, daif		// local_daif_save\n"
+		: "=r" (flags)
+		:
+		: "memory");
+	local_daif_mask();
+
+	return flags;
+}
+
+static inline void local_daif_unmask(void)
+{
+	trace_hardirqs_on();
+	asm volatile(
+		"msr	daifclr, #0xf		// local_daif_unmask"
+		:
+		:
+		: "memory");
+}
+
+static inline void local_daif_restore(unsigned long flags)
+{
+	if (!arch_irqs_disabled_flags(flags))
+		trace_hardirqs_on();
+	asm volatile(
+		"msr	daif, %0		// local_daif_restore"
+		:
+		: "r" (flags)
+		: "memory");
+	if (arch_irqs_disabled_flags(flags))
+		trace_hardirqs_off();
+}
+
+#endif

arch/arm64/include/asm/elf.h

@@ -188,8 +188,8 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 
 #define compat_start_thread		compat_start_thread
 /*
- * Unlike the native SET_PERSONALITY macro, the compat version inherits
- * READ_IMPLIES_EXEC across a fork() since this is the behaviour on
+ * Unlike the native SET_PERSONALITY macro, the compat version maintains
+ * READ_IMPLIES_EXEC across an execve() since this is the behaviour on
  * arch/arm/.
  */
 #define COMPAT_SET_PERSONALITY(ex)					\

arch/arm64/include/asm/esr.h

@@ -43,7 +43,8 @@
 #define ESR_ELx_EC_HVC64	(0x16)
 #define ESR_ELx_EC_SMC64	(0x17)
 #define ESR_ELx_EC_SYS64	(0x18)
-/* Unallocated EC: 0x19 - 0x1E */
+#define ESR_ELx_EC_SVE		(0x19)
+/* Unallocated EC: 0x1A - 0x1E */
 #define ESR_ELx_EC_IMP_DEF	(0x1f)
 #define ESR_ELx_EC_IABT_LOW	(0x20)
 #define ESR_ELx_EC_IABT_CUR	(0x21)

arch/arm64/include/asm/fpsimd.h

@@ -17,9 +17,13 @@
 #define __ASM_FP_H
 
 #include <asm/ptrace.h>
+#include <asm/errno.h>
 
 #ifndef __ASSEMBLY__
 
+#include <linux/cache.h>
+#include <linux/stddef.h>
+
 /*
  * FP/SIMD storage area has:
  *  - FPSR and FPCR
@@ -35,13 +39,16 @@ struct fpsimd_state {
 			__uint128_t vregs[32];
 			u32 fpsr;
 			u32 fpcr;
+			/*
+			 * For ptrace compatibility, pad to next 128-bit
+			 * boundary here if extending this struct.
+			 */
 		};
 	};
 	/* the id of the last cpu to have restored this state */
 	unsigned int cpu;
 };
 
-
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /* Masks for extracting the FPSR and FPCR from the FPSCR */
 #define VFP_FPSCR_STAT_MASK	0xf800009f
@@ -61,11 +68,73 @@ extern void fpsimd_load_state(struct fpsimd_state *state);
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
+extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct fpsimd_state *state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void sve_flush_cpu_state(void);
+
+/* Maximum VL that SVE VL-agnostic software can transparently support */
+#define SVE_VL_ARCH_MAX 0x100
+
+extern void sve_save_state(void *state, u32 *pfpsr);
+extern void sve_load_state(void const *state, u32 const *pfpsr,
+			   unsigned long vq_minus_1);
+extern unsigned int sve_get_vl(void);
+extern int sve_kernel_enable(void *);
+
+extern int __ro_after_init sve_max_vl;
+
+#ifdef CONFIG_ARM64_SVE
+
+extern size_t sve_state_size(struct task_struct const *task);
+
+extern void sve_alloc(struct task_struct *task);
+extern void fpsimd_release_task(struct task_struct *task);
+extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void sve_sync_to_fpsimd(struct task_struct *task);
+extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
+
+extern int sve_set_vector_length(struct task_struct *task,
+				 unsigned long vl, unsigned long flags);
+
+extern int sve_set_current_vl(unsigned long arg);
+extern int sve_get_current_vl(void);
+
+/*
+ * Probing and setup functions.
+ * Calls to these functions must be serialised with one another.
+ */
+extern void __init sve_init_vq_map(void);
+extern void sve_update_vq_map(void);
+extern int sve_verify_vq_map(void);
+extern void __init sve_setup(void);
+
+#else /* ! CONFIG_ARM64_SVE */
+
+static inline void sve_alloc(struct task_struct *task) { }
+static inline void fpsimd_release_task(struct task_struct *task) { }
+static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
+static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
+
+static inline int sve_set_current_vl(unsigned long arg)
+{
+	return -EINVAL;
+}
+
+static inline int sve_get_current_vl(void)
+{
+	return -EINVAL;
+}
+
+static inline void sve_init_vq_map(void) { }
+static inline void sve_update_vq_map(void) { }
+static inline int sve_verify_vq_map(void) { return 0; }
+static inline void sve_setup(void) { }
+
+#endif /* ! CONFIG_ARM64_SVE */
 
 /* For use by EFI runtime services calls only */
 extern void __efi_fpsimd_begin(void);

arch/arm64/include/asm/fpsimdmacros.h

@@ -75,3 +75,151 @@
 	ldr	w\tmpnr, [\state, #16 * 2 + 4]
 	fpsimd_restore_fpcr x\tmpnr, \state
 .endm
+
+/* Sanity-check macros to help avoid encoding garbage instructions */
+
+.macro _check_general_reg nr
+	.if (\nr) < 0 || (\nr) > 30
+		.error "Bad register number \nr."
+	.endif
+.endm
+
+.macro _sve_check_zreg znr
+	.if (\znr) < 0 || (\znr) > 31
+		.error "Bad Scalable Vector Extension vector register number \znr."
+	.endif
+.endm
+
+.macro _sve_check_preg pnr
+	.if (\pnr) < 0 || (\pnr) > 15
+		.error "Bad Scalable Vector Extension predicate register number \pnr."
+	.endif
+.endm
+
+.macro _check_num n, min, max
+	.if (\n) < (\min) || (\n) > (\max)
+		.error "Number \n out of range [\min,\max]"
+	.endif
+.endm
+
+/* SVE instruction encodings for non-SVE-capable assemblers */
+
+/* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_str_v nz, nxbase, offset=0
+	_sve_check_zreg \nz
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe5804000			\
+		| (\nz)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* LDR (vector): LDR Z\nz, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_ldr_v nz, nxbase, offset=0
+	_sve_check_zreg \nz
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0x85804000			\
+		| (\nz)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* STR (predicate): STR P\np, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_str_p np, nxbase, offset=0
+	_sve_check_preg \np
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe5800000			\
+		| (\np)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* LDR (predicate): LDR P\np, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_ldr_p np, nxbase, offset=0
+	_sve_check_preg \np
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0x85800000			\
+		| (\np)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* RDVL X\nx, #\imm */
+.macro _sve_rdvl nx, imm
+	_check_general_reg \nx
+	_check_num (\imm), -0x20, 0x1f
+	.inst	0x04bf5000			\
+		| (\nx)				\
+		| (((\imm) & 0x3f) << 5)
+.endm
+
+/* RDFFR (unpredicated): RDFFR P\np.B */
+.macro _sve_rdffr np
+	_sve_check_preg \np
+	.inst	0x2519f000			\
+		| (\np)
+.endm
+
+/* WRFFR P\np.B */
+.macro _sve_wrffr np
+	_sve_check_preg \np
+	.inst	0x25289000			\
+		| ((\np) << 5)
+.endm
+
+.macro __for from:req, to:req
+	.if (\from) == (\to)
+		_for__body \from
+	.else
+		__for \from, (\from) + ((\to) - (\from)) / 2
+		__for (\from) + ((\to) - (\from)) / 2 + 1, \to
+	.endif
+.endm
+
+.macro _for var:req, from:req, to:req, insn:vararg
+	.macro _for__body \var:req
+		\insn
+	.endm
+
+	__for \from, \to
+
+	.purgem _for__body
+.endm
+
+.macro sve_save nxbase, xpfpsr, nxtmp
+ _for n, 0, 31,	_sve_str_v	\n, \nxbase, \n - 34
+ _for n, 0, 15,	_sve_str_p	\n, \nxbase, \n - 16
+		_sve_rdffr	0
+		_sve_str_p	0, \nxbase
+		_sve_ldr_p	0, \nxbase, -16
+
+		mrs		x\nxtmp, fpsr
+		str		w\nxtmp, [\xpfpsr]
+		mrs		x\nxtmp, fpcr
+		str		w\nxtmp, [\xpfpsr, #4]
+.endm
+
+.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp
+		mrs_s		x\nxtmp, SYS_ZCR_EL1
+		bic		x\nxtmp, x\nxtmp, ZCR_ELx_LEN_MASK
+		orr		x\nxtmp, x\nxtmp, \xvqminus1
+		msr_s		SYS_ZCR_EL1, x\nxtmp	// self-synchronising
+
+ _for n, 0, 31,	_sve_ldr_v	\n, \nxbase, \n - 34
+		_sve_ldr_p	0, \nxbase
+		_sve_wrffr	0
+ _for n, 0, 15,	_sve_ldr_p	\n, \nxbase, \n - 16
+
+		ldr		w\nxtmp, [\xpfpsr]
+		msr		fpsr, x\nxtmp
+		ldr		w\nxtmp, [\xpfpsr, #4]
+		msr		fpcr, x\nxtmp
+.endm

arch/arm64/include/asm/irqflags.h

@@ -20,6 +20,19 @@
 
 #include <asm/ptrace.h>
 
+/*
+ * Aarch64 has flags for masking: Debug, Asynchronous (serror), Interrupts and
+ * FIQ exceptions, in the 'daif' register. We mask and unmask them in 'dai'
+ * order:
+ * Masking debug exceptions causes all other exceptions to be masked too/
+ * Masking SError masks irq, but not debug exceptions. Masking irqs has no
+ * side effects for other flags. Keeping to this order makes it easier for
+ * entry.S to know which exceptions should be unmasked.
+ *
+ * FIQ is never expected, but we mask it when we disable debug exceptions, and
+ * unmask it at all other times.
+ */
+
 /*
  * CPU interrupt mask handling.
  */
@@ -53,12 +66,6 @@ static inline void arch_local_irq_disable(void)
 		: "memory");
 }
 
-#define local_fiq_enable()	asm("msr	daifclr, #1" : : : "memory")
-#define local_fiq_disable()	asm("msr	daifset, #1" : : : "memory")
-
-#define local_async_enable()	asm("msr	daifclr, #4" : : : "memory")
-#define local_async_disable()	asm("msr	daifset, #4" : : : "memory")
-
 /*
  * Save the current interrupt enable state.
  */
@@ -89,26 +96,5 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return flags & PSR_I_BIT;
 }
-
-/*
- * save and restore debug state
- */
-#define local_dbg_save(flags)						\
-	do {								\
-		typecheck(unsigned long, flags);			\
-		asm volatile(						\
-		"mrs    %0, daif		// local_dbg_save\n"	\
-		"msr    daifset, #8"					\
-		: "=r" (flags) : : "memory");				\
-	} while (0)
-
-#define local_dbg_restore(flags)					\
-	do {								\
-		typecheck(unsigned long, flags);			\
-		asm volatile(						\
-		"msr    daif, %0		// local_dbg_restore\n"	\
-		: : "r" (flags) : "memory");				\
-	} while (0)
-
 #endif
 #endif

arch/arm64/include/asm/kvm_arm.h

@@ -185,7 +185,9 @@
 #define CPTR_EL2_TCPAC	(1 << 31)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
-#define CPTR_EL2_DEFAULT	0x000033ff
+#define CPTR_EL2_TZ	(1 << 8)
+#define CPTR_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 */
+#define CPTR_EL2_DEFAULT	CPTR_EL2_RES1
 
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_TPMS		(1 << 14)
@@ -236,5 +238,6 @@
 
 #define CPACR_EL1_FPEN		(3 << 20)
 #define CPACR_EL1_TTA		(1 << 28)
+#define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN)
 
 #endif /* __ARM64_KVM_ARM_H__ */

arch/arm64/include/asm/kvm_host.h

@@ -25,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -384,4 +385,14 @@ static inline void __cpu_init_stage2(void)
 		  "PARange is %d bits, unsupported configuration!", parange);
 }
 
+/*
+ * All host FP/SIMD state is restored on guest exit, so nothing needs
+ * doing here except in the SVE case:
+*/
+static inline void kvm_fpsimd_flush_cpu_state(void)
+{
+	if (system_supports_sve())
+		sve_flush_cpu_state();
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/include/asm/memory.h

@@ -61,8 +61,6 @@
  * KIMAGE_VADDR - the virtual address of the start of the kernel image
  * VA_BITS - the maximum number of bits for virtual addresses.
  * VA_START - the first kernel virtual address.
- * TASK_SIZE - the maximum size of a user space task.
- * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
 #define VA_START		(UL(0xffffffffffffffff) - \
@@ -77,19 +75,6 @@
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
-#define TASK_SIZE_64		(UL(1) << VA_BITS)
-
-#ifdef CONFIG_COMPAT
-#define TASK_SIZE_32		UL(0x100000000)
-#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
-				TASK_SIZE_32 : TASK_SIZE_64)
-#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
-				TASK_SIZE_32 : TASK_SIZE_64)
-#else
-#define TASK_SIZE		TASK_SIZE_64
-#endif /* CONFIG_COMPAT */
-
-#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
 
 #define KERNEL_START      _text
 #define KERNEL_END        _end

arch/arm64/include/asm/pgtable.h

@@ -98,6 +98,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
+#define pte_valid_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 
 /*
  * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
@@ -107,6 +109,18 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_accessible(mm, pte)	\
 	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))
 
+/*
+ * p??_access_permitted() is true for valid user mappings (subject to the
+ * write permission check) other than user execute-only which do not have the
+ * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ */
+#define pte_access_permitted(pte, write) \
+	(pte_valid_user(pte) && (!(write) || pte_write(pte)))
+#define pmd_access_permitted(pmd, write) \
+	(pte_access_permitted(pmd_pte(pmd), (write)))
+#define pud_access_permitted(pud, write) \
+	(pte_access_permitted(pud_pte(pud), (write)))
+
 static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
 {
 	pte_val(pte) &= ~pgprot_val(prot);

arch/arm64/include/asm/processor.h

@@ -19,6 +19,10 @@
 #ifndef __ASM_PROCESSOR_H
 #define __ASM_PROCESSOR_H
 
+#define TASK_SIZE_64		(UL(1) << VA_BITS)
+
+#ifndef __ASSEMBLY__
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -37,6 +41,22 @@
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
+/*
+ * TASK_SIZE - the maximum size of a user space task.
+ * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
+ */
+#ifdef CONFIG_COMPAT
+#define TASK_SIZE_32		UL(0x100000000)
+#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#else
+#define TASK_SIZE		TASK_SIZE_64
+#endif /* CONFIG_COMPAT */
+
+#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
+
 #define STACK_TOP_MAX		TASK_SIZE_64
 #ifdef CONFIG_COMPAT
 #define AARCH32_VECTORS_BASE	0xffff0000
@@ -85,6 +105,9 @@ struct thread_struct {
 	unsigned long		tp2_value;
 #endif
 	struct fpsimd_state	fpsimd_state;
+	void			*sve_state;	/* SVE registers, if any */
+	unsigned int		sve_vl;		/* SVE vector length */
+	unsigned int		sve_vl_onexec;	/* SVE vl after next exec */
 	unsigned long		fault_address;	/* fault info */
 	unsigned long		fault_code;	/* ESR_EL1 value */
 	struct debug_info	debug;		/* debugging */
@@ -194,4 +217,9 @@ static inline void spin_lock_prefetch(const void *ptr)
 int cpu_enable_pan(void *__unused);
 int cpu_enable_cache_maint_trap(void *__unused);
 
+/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
+#define SVE_SET_VL(arg)	sve_set_current_vl(arg)
+#define SVE_GET_VL()	sve_get_current_vl()
+
+#endif /* __ASSEMBLY__ */
 #endif /* __ASM_PROCESSOR_H */

arch/arm64/include/asm/sysreg.h

@@ -145,10 +145,14 @@
 
 #define SYS_ID_AA64PFR0_EL1		sys_reg(3, 0, 0, 4, 0)
 #define SYS_ID_AA64PFR1_EL1		sys_reg(3, 0, 0, 4, 1)
+#define SYS_ID_AA64ZFR0_EL1		sys_reg(3, 0, 0, 4, 4)
 
 #define SYS_ID_AA64DFR0_EL1		sys_reg(3, 0, 0, 5, 0)
 #define SYS_ID_AA64DFR1_EL1		sys_reg(3, 0, 0, 5, 1)
 
+#define SYS_ID_AA64AFR0_EL1		sys_reg(3, 0, 0, 5, 4)
+#define SYS_ID_AA64AFR1_EL1		sys_reg(3, 0, 0, 5, 5)
+
 #define SYS_ID_AA64ISAR0_EL1		sys_reg(3, 0, 0, 6, 0)
 #define SYS_ID_AA64ISAR1_EL1		sys_reg(3, 0, 0, 6, 1)
 
@@ -160,6 +164,8 @@
 #define SYS_ACTLR_EL1			sys_reg(3, 0, 1, 0, 1)
 #define SYS_CPACR_EL1			sys_reg(3, 0, 1, 0, 2)
 
+#define SYS_ZCR_EL1			sys_reg(3, 0, 1, 2, 0)
+
 #define SYS_TTBR0_EL1			sys_reg(3, 0, 2, 0, 0)
 #define SYS_TTBR1_EL1			sys_reg(3, 0, 2, 0, 1)
 #define SYS_TCR_EL1			sys_reg(3, 0, 2, 0, 2)
@@ -172,6 +178,99 @@
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
+/*** Statistical Profiling Extension ***/
+/* ID registers */
+#define SYS_PMSIDR_EL1			sys_reg(3, 0, 9, 9, 7)
+#define SYS_PMSIDR_EL1_FE_SHIFT		0
+#define SYS_PMSIDR_EL1_FT_SHIFT		1
+#define SYS_PMSIDR_EL1_FL_SHIFT		2
+#define SYS_PMSIDR_EL1_ARCHINST_SHIFT	3
+#define SYS_PMSIDR_EL1_LDS_SHIFT	4
+#define SYS_PMSIDR_EL1_ERND_SHIFT	5
+#define SYS_PMSIDR_EL1_INTERVAL_SHIFT	8
+#define SYS_PMSIDR_EL1_INTERVAL_MASK	0xfUL
+#define SYS_PMSIDR_EL1_MAXSIZE_SHIFT	12
+#define SYS_PMSIDR_EL1_MAXSIZE_MASK	0xfUL
+#define SYS_PMSIDR_EL1_COUNTSIZE_SHIFT	16
+#define SYS_PMSIDR_EL1_COUNTSIZE_MASK	0xfUL
+
+#define SYS_PMBIDR_EL1			sys_reg(3, 0, 9, 10, 7)
+#define SYS_PMBIDR_EL1_ALIGN_SHIFT	0
+#define SYS_PMBIDR_EL1_ALIGN_MASK	0xfU
+#define SYS_PMBIDR_EL1_P_SHIFT		4
+#define SYS_PMBIDR_EL1_F_SHIFT		5
+
+/* Sampling controls */
+#define SYS_PMSCR_EL1			sys_reg(3, 0, 9, 9, 0)
+#define SYS_PMSCR_EL1_E0SPE_SHIFT	0
+#define SYS_PMSCR_EL1_E1SPE_SHIFT	1
+#define SYS_PMSCR_EL1_CX_SHIFT		3
+#define SYS_PMSCR_EL1_PA_SHIFT		4
+#define SYS_PMSCR_EL1_TS_SHIFT		5
+#define SYS_PMSCR_EL1_PCT_SHIFT		6
+
+#define SYS_PMSCR_EL2			sys_reg(3, 4, 9, 9, 0)
+#define SYS_PMSCR_EL2_E0HSPE_SHIFT	0
+#define SYS_PMSCR_EL2_E2SPE_SHIFT	1
+#define SYS_PMSCR_EL2_CX_SHIFT		3
+#define SYS_PMSCR_EL2_PA_SHIFT		4
+#define SYS_PMSCR_EL2_TS_SHIFT		5
+#define SYS_PMSCR_EL2_PCT_SHIFT		6
+
+#define SYS_PMSICR_EL1			sys_reg(3, 0, 9, 9, 2)
+
+#define SYS_PMSIRR_EL1			sys_reg(3, 0, 9, 9, 3)
+#define SYS_PMSIRR_EL1_RND_SHIFT	0
+#define SYS_PMSIRR_EL1_INTERVAL_SHIFT	8
+#define SYS_PMSIRR_EL1_INTERVAL_MASK	0xffffffUL
+
+/* Filtering controls */
+#define SYS_PMSFCR_EL1			sys_reg(3, 0, 9, 9, 4)
+#define SYS_PMSFCR_EL1_FE_SHIFT		0
+#define SYS_PMSFCR_EL1_FT_SHIFT		1
+#define SYS_PMSFCR_EL1_FL_SHIFT		2
+#define SYS_PMSFCR_EL1_B_SHIFT		16
+#define SYS_PMSFCR_EL1_LD_SHIFT		17
+#define SYS_PMSFCR_EL1_ST_SHIFT		18
+
+#define SYS_PMSEVFR_EL1			sys_reg(3, 0, 9, 9, 5)
+#define SYS_PMSEVFR_EL1_RES0		0x0000ffff00ff0f55UL
+
+#define SYS_PMSLATFR_EL1		sys_reg(3, 0, 9, 9, 6)
+#define SYS_PMSLATFR_EL1_MINLAT_SHIFT	0
+
+/* Buffer controls */
+#define SYS_PMBLIMITR_EL1		sys_reg(3, 0, 9, 10, 0)
+#define SYS_PMBLIMITR_EL1_E_SHIFT	0
+#define SYS_PMBLIMITR_EL1_FM_SHIFT	1
+#define SYS_PMBLIMITR_EL1_FM_MASK	0x3UL
+#define SYS_PMBLIMITR_EL1_FM_STOP_IRQ	(0 << SYS_PMBLIMITR_EL1_FM_SHIFT)
+
+#define SYS_PMBPTR_EL1			sys_reg(3, 0, 9, 10, 1)
+
+/* Buffer error reporting */
+#define SYS_PMBSR_EL1			sys_reg(3, 0, 9, 10, 3)
+#define SYS_PMBSR_EL1_COLL_SHIFT	16
+#define SYS_PMBSR_EL1_S_SHIFT		17
+#define SYS_PMBSR_EL1_EA_SHIFT		18
+#define SYS_PMBSR_EL1_DL_SHIFT		19
+#define SYS_PMBSR_EL1_EC_SHIFT		26
+#define SYS_PMBSR_EL1_EC_MASK		0x3fUL
+
+#define SYS_PMBSR_EL1_EC_BUF		(0x0UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S1	(0x24UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S2	(0x25UL << SYS_PMBSR_EL1_EC_SHIFT)
+
+#define SYS_PMBSR_EL1_FAULT_FSC_SHIFT	0
+#define SYS_PMBSR_EL1_FAULT_FSC_MASK	0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_SHIFT	0
+#define SYS_PMBSR_EL1_BUF_BSC_MASK	0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_FULL	(0x1UL << SYS_PMBSR_EL1_BUF_BSC_SHIFT)
+
+/*** End of Statistical Profiling Extension ***/
+
 #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
 #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
 
@@ -250,6 +349,8 @@
 
 #define SYS_PMCCFILTR_EL0		sys_reg (3, 3, 14, 15, 7)
 
+#define SYS_ZCR_EL2			sys_reg(3, 4, 1, 2, 0)
+
 #define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
 #define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
 #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
@@ -318,6 +419,10 @@
 #define SCTLR_EL1_CP15BEN	(1 << 5)
 
 /* id_aa64isar0 */
+#define ID_AA64ISAR0_DP_SHIFT		44
+#define ID_AA64ISAR0_SM4_SHIFT		40
+#define ID_AA64ISAR0_SM3_SHIFT		36
+#define ID_AA64ISAR0_SHA3_SHIFT		32
 #define ID_AA64ISAR0_RDM_SHIFT		28
 #define ID_AA64ISAR0_ATOMICS_SHIFT	20
 #define ID_AA64ISAR0_CRC32_SHIFT	16
@@ -332,6 +437,7 @@
 #define ID_AA64ISAR1_DPB_SHIFT		0
 
 /* id_aa64pfr0 */
+#define ID_AA64PFR0_SVE_SHIFT		32
 #define ID_AA64PFR0_GIC_SHIFT		24
 #define ID_AA64PFR0_ASIMD_SHIFT		20
 #define ID_AA64PFR0_FP_SHIFT		16
@@ -340,6 +446,7 @@
 #define ID_AA64PFR0_EL1_SHIFT		4
 #define ID_AA64PFR0_EL0_SHIFT		0
 
+#define ID_AA64PFR0_SVE			0x1
 #define ID_AA64PFR0_FP_NI		0xf
 #define ID_AA64PFR0_FP_SUPPORTED	0x0
 #define ID_AA64PFR0_ASIMD_NI		0xf
@@ -441,6 +548,20 @@
 #endif
 
 
+/*
+ * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which
+ * are reserved by the SVE architecture for future expansion of the LEN
+ * field, with compatible semantics.
+ */
+#define ZCR_ELx_LEN_SHIFT	0
+#define ZCR_ELx_LEN_SIZE	9
+#define ZCR_ELx_LEN_MASK	0x1ff
+
+#define CPACR_EL1_ZEN_EL1EN	(1 << 16) /* enable EL1 access */
+#define CPACR_EL1_ZEN_EL0EN	(1 << 17) /* enable EL0 access, if EL1EN set */
+#define CPACR_EL1_ZEN		(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
+
+
 /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
 #define SYS_MPIDR_SAFE_VAL		(1UL << 31)
 

arch/arm64/include/asm/thread_info.h

@@ -63,6 +63,8 @@ struct thread_info {
 void arch_setup_new_exec(void);
 #define arch_setup_new_exec     arch_setup_new_exec
 
+void arch_release_task_struct(struct task_struct *tsk);
+
 #endif
 
 /*
@@ -92,6 +94,8 @@ void arch_setup_new_exec(void);
 #define TIF_RESTORE_SIGMASK	20
 #define TIF_SINGLESTEP		21
 #define TIF_32BIT		22	/* 32bit process */
+#define TIF_SVE			23	/* Scalable Vector Extension in use */
+#define TIF_SVE_VL_INHERIT	24	/* Inherit sve_vl_onexec across exec */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
@@ -105,6 +109,7 @@ void arch_setup_new_exec(void);
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 #define _TIF_32BIT		(1 << TIF_32BIT)
+#define _TIF_SVE		(1 << TIF_SVE)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \

arch/arm64/include/asm/traps.h

@@ -34,9 +34,17 @@ struct undef_hook {
 
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
+void force_signal_inject(int signal, int code, struct pt_regs *regs,
+			 unsigned long address);
 
 void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
 
+/*
+ * Move regs->pc to next instruction and do necessary setup before it
+ * is executed.
+ */
+void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size);
+
 static inline int __in_irqentry_text(unsigned long ptr)
 {
 	return ptr >= (unsigned long)&__irqentry_text_start &&

arch/arm64/include/uapi/asm/hwcap.h

@@ -37,5 +37,11 @@
 #define HWCAP_FCMA		(1 << 14)
 #define HWCAP_LRCPC		(1 << 15)
 #define HWCAP_DCPOP		(1 << 16)
+#define HWCAP_SHA3		(1 << 17)
+#define HWCAP_SM3		(1 << 18)
+#define HWCAP_SM4		(1 << 19)
+#define HWCAP_ASIMDDP		(1 << 20)
+#define HWCAP_SHA512		(1 << 21)
+#define HWCAP_SVE		(1 << 22)
 
 #endif /* _UAPI__ASM_HWCAP_H */

arch/arm64/include/uapi/asm/ptrace.h

@@ -23,6 +23,7 @@
 #include <linux/types.h>
 
 #include <asm/hwcap.h>
+#include <asm/sigcontext.h>
 
 
 /*
@@ -47,7 +48,6 @@
 #define PSR_D_BIT	0x00000200
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
-#define PSR_Q_BIT	0x08000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
@@ -64,6 +64,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/prctl.h>
+
 /*
  * User structures for general purpose, floating point and debug registers.
  */
@@ -91,6 +93,141 @@ struct user_hwdebug_state {
 	}		dbg_regs[16];
 };
 
+/* SVE/FP/SIMD state (NT_ARM_SVE) */
+
+struct user_sve_header {
+	__u32 size; /* total meaningful regset content in bytes */
+	__u32 max_size; /* maxmium possible size for this thread */
+	__u16 vl; /* current vector length */
+	__u16 max_vl; /* maximum possible vector length */
+	__u16 flags;
+	__u16 __reserved;
+};
+
+/* Definitions for user_sve_header.flags: */
+#define SVE_PT_REGS_MASK		(1 << 0)
+
+#define SVE_PT_REGS_FPSIMD		0
+#define SVE_PT_REGS_SVE			SVE_PT_REGS_MASK
+
+/*
+ * Common SVE_PT_* flags:
+ * These must be kept in sync with prctl interface in <linux/ptrace.h>
+ */
+#define SVE_PT_VL_INHERIT		(PR_SVE_VL_INHERIT >> 16)
+#define SVE_PT_VL_ONEXEC		(PR_SVE_SET_VL_ONEXEC >> 16)
+
+
+/*
+ * The remainder of the SVE state follows struct user_sve_header.  The
+ * total size of the SVE state (including header) depends on the
+ * metadata in the header:  SVE_PT_SIZE(vq, flags) gives the total size
+ * of the state in bytes, including the header.
+ *
+ * Refer to <asm/sigcontext.h> for details of how to pass the correct
+ * "vq" argument to these macros.
+ */
+
+/* Offset from the start of struct user_sve_header to the register data */
+#define SVE_PT_REGS_OFFSET					\
+	((sizeof(struct sve_context) + (SVE_VQ_BYTES - 1))	\
+		/ SVE_VQ_BYTES * SVE_VQ_BYTES)
+
+/*
+ * The register data content and layout depends on the value of the
+ * flags field.
+ */
+
+/*
+ * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD case:
+ *
+ * The payload starts at offset SVE_PT_FPSIMD_OFFSET, and is of type
+ * struct user_fpsimd_state.  Additional data might be appended in the
+ * future: use SVE_PT_FPSIMD_SIZE(vq, flags) to compute the total size.
+ * SVE_PT_FPSIMD_SIZE(vq, flags) will never be less than
+ * sizeof(struct user_fpsimd_state).
+ */
+
+#define SVE_PT_FPSIMD_OFFSET		SVE_PT_REGS_OFFSET
+
+#define SVE_PT_FPSIMD_SIZE(vq, flags)	(sizeof(struct user_fpsimd_state))
+
+/*
+ * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE case:
+ *
+ * The payload starts at offset SVE_PT_SVE_OFFSET, and is of size
+ * SVE_PT_SVE_SIZE(vq, flags).
+ *
+ * Additional macros describe the contents and layout of the payload.
+ * For each, SVE_PT_SVE_x_OFFSET(args) is the start offset relative to
+ * the start of struct user_sve_header, and SVE_PT_SVE_x_SIZE(args) is
+ * the size in bytes:
+ *
+ *	x	type				description
+ *	-	----				-----------
+ *	ZREGS		\
+ *	ZREG		|
+ *	PREGS		| refer to <asm/sigcontext.h>
+ *	PREG		|
+ *	FFR		/
+ *
+ *	FPSR	uint32_t			FPSR
+ *	FPCR	uint32_t			FPCR
+ *
+ * Additional data might be appended in the future.
+ */
+
+#define SVE_PT_SVE_ZREG_SIZE(vq)	SVE_SIG_ZREG_SIZE(vq)
+#define SVE_PT_SVE_PREG_SIZE(vq)	SVE_SIG_PREG_SIZE(vq)
+#define SVE_PT_SVE_FFR_SIZE(vq)		SVE_SIG_FFR_SIZE(vq)
+#define SVE_PT_SVE_FPSR_SIZE		sizeof(__u32)
+#define SVE_PT_SVE_FPCR_SIZE		sizeof(__u32)
+
+#define __SVE_SIG_TO_PT(offset) \
+	((offset) - SVE_SIG_REGS_OFFSET + SVE_PT_REGS_OFFSET)
+
+#define SVE_PT_SVE_OFFSET		SVE_PT_REGS_OFFSET
+
+#define SVE_PT_SVE_ZREGS_OFFSET \
+	__SVE_SIG_TO_PT(SVE_SIG_ZREGS_OFFSET)
+#define SVE_PT_SVE_ZREG_OFFSET(vq, n) \
+	__SVE_SIG_TO_PT(SVE_SIG_ZREG_OFFSET(vq, n))
+#define SVE_PT_SVE_ZREGS_SIZE(vq) \
+	(SVE_PT_SVE_ZREG_OFFSET(vq, SVE_NUM_ZREGS) - SVE_PT_SVE_ZREGS_OFFSET)
+
+#define SVE_PT_SVE_PREGS_OFFSET(vq) \
+	__SVE_SIG_TO_PT(SVE_SIG_PREGS_OFFSET(vq))
+#define SVE_PT_SVE_PREG_OFFSET(vq, n) \
+	__SVE_SIG_TO_PT(SVE_SIG_PREG_OFFSET(vq, n))
+#define SVE_PT_SVE_PREGS_SIZE(vq) \
+	(SVE_PT_SVE_PREG_OFFSET(vq, SVE_NUM_PREGS) - \
+		SVE_PT_SVE_PREGS_OFFSET(vq))
+
+#define SVE_PT_SVE_FFR_OFFSET(vq) \
+	__SVE_SIG_TO_PT(SVE_SIG_FFR_OFFSET(vq))
+
+#define SVE_PT_SVE_FPSR_OFFSET(vq)				\
+	((SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq) +	\
+			(SVE_VQ_BYTES - 1))			\
+		/ SVE_VQ_BYTES * SVE_VQ_BYTES)
+#define SVE_PT_SVE_FPCR_OFFSET(vq) \
+	(SVE_PT_SVE_FPSR_OFFSET(vq) + SVE_PT_SVE_FPSR_SIZE)
+
+/*
+ * Any future extension appended after FPCR must be aligned to the next
+ * 128-bit boundary.
+ */
+
+#define SVE_PT_SVE_SIZE(vq, flags)					\
+	((SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE		\
+			- SVE_PT_SVE_OFFSET + (SVE_VQ_BYTES - 1))	\
+		/ SVE_VQ_BYTES * SVE_VQ_BYTES)
+
+#define SVE_PT_SIZE(vq, flags)						\
+	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		\
+		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	\
+		: SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI__ASM_PTRACE_H */

arch/arm64/include/uapi/asm/sigcontext.h

@@ -17,6 +17,8 @@
 #ifndef _UAPI__ASM_SIGCONTEXT_H
 #define _UAPI__ASM_SIGCONTEXT_H
 
+#ifndef __ASSEMBLY__
+
 #include <linux/types.h>
 
 /*
@@ -42,10 +44,11 @@ struct sigcontext {
  *
  *	0x210		fpsimd_context
  *	 0x10		esr_context
+ *	0x8a0		sve_context (vl <= 64) (optional)
  *	 0x20		extra_context (optional)
  *	 0x10		terminator (null _aarch64_ctx)
  *
- *	0xdb0		(reserved for future allocation)
+ *	0x510		(reserved for future allocation)
  *
  * New records that can exceed this space need to be opt-in for userspace, so
  * that an expanded signal frame is not generated unexpectedly.  The mechanism
@@ -117,4 +120,119 @@ struct extra_context {
 	__u32 __reserved[3];
 };
 
+#define SVE_MAGIC	0x53564501
+
+struct sve_context {
+	struct _aarch64_ctx head;
+	__u16 vl;
+	__u16 __reserved[3];
+};
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * The SVE architecture leaves space for future expansion of the
+ * vector length beyond its initial architectural limit of 2048 bits
+ * (16 quadwords).
+ *
+ * See linux/Documentation/arm64/sve.txt for a description of the VL/VQ
+ * terminology.
+ */
+#define SVE_VQ_BYTES		16	/* number of bytes per quadword */
+
+#define SVE_VQ_MIN		1
+#define SVE_VQ_MAX		512
+
+#define SVE_VL_MIN		(SVE_VQ_MIN * SVE_VQ_BYTES)
+#define SVE_VL_MAX		(SVE_VQ_MAX * SVE_VQ_BYTES)
+
+#define SVE_NUM_ZREGS		32
+#define SVE_NUM_PREGS		16
+
+#define sve_vl_valid(vl) \
+	((vl) % SVE_VQ_BYTES == 0 && (vl) >= SVE_VL_MIN && (vl) <= SVE_VL_MAX)
+#define sve_vq_from_vl(vl)	((vl) / SVE_VQ_BYTES)
+#define sve_vl_from_vq(vq)	((vq) * SVE_VQ_BYTES)
+
+/*
+ * If the SVE registers are currently live for the thread at signal delivery,
+ * sve_context.head.size >=
+ *	SVE_SIG_CONTEXT_SIZE(sve_vq_from_vl(sve_context.vl))
+ * and the register data may be accessed using the SVE_SIG_*() macros.
+ *
+ * If sve_context.head.size <
+ *	SVE_SIG_CONTEXT_SIZE(sve_vq_from_vl(sve_context.vl)),
+ * the SVE registers were not live for the thread and no register data
+ * is included: in this case, the SVE_SIG_*() macros should not be
+ * used except for this check.
+ *
+ * The same convention applies when returning from a signal: a caller
+ * will need to remove or resize the sve_context block if it wants to
+ * make the SVE registers live when they were previously non-live or
+ * vice-versa.  This may require the the caller to allocate fresh
+ * memory and/or move other context blocks in the signal frame.
+ *
+ * Changing the vector length during signal return is not permitted:
+ * sve_context.vl must equal the thread's current vector length when
+ * doing a sigreturn.
+ *
+ *
+ * Note: for all these macros, the "vq" argument denotes the SVE
+ * vector length in quadwords (i.e., units of 128 bits).
+ *
+ * The correct way to obtain vq is to use sve_vq_from_vl(vl).  The
+ * result is valid if and only if sve_vl_valid(vl) is true.  This is
+ * guaranteed for a struct sve_context written by the kernel.
+ *
+ *
+ * Additional macros describe the contents and layout of the payload.
+ * For each, SVE_SIG_x_OFFSET(args) is the start offset relative to
+ * the start of struct sve_context, and SVE_SIG_x_SIZE(args) is the
+ * size in bytes:
+ *
+ *	x	type				description
+ *	-	----				-----------
+ *	REGS					the entire SVE context
+ *
+ *	ZREGS	__uint128_t[SVE_NUM_ZREGS][vq]	all Z-registers
+ *	ZREG	__uint128_t[vq]			individual Z-register Zn
+ *
+ *	PREGS	uint16_t[SVE_NUM_PREGS][vq]	all P-registers
+ *	PREG	uint16_t[vq]			individual P-register Pn
+ *
+ *	FFR	uint16_t[vq]			first-fault status register
+ *
+ * Additional data might be appended in the future.
+ */
+
+#define SVE_SIG_ZREG_SIZE(vq)	((__u32)(vq) * SVE_VQ_BYTES)
+#define SVE_SIG_PREG_SIZE(vq)	((__u32)(vq) * (SVE_VQ_BYTES / 8))
+#define SVE_SIG_FFR_SIZE(vq)	SVE_SIG_PREG_SIZE(vq)
+
+#define SVE_SIG_REGS_OFFSET					\
+	((sizeof(struct sve_context) + (SVE_VQ_BYTES - 1))	\
+		/ SVE_VQ_BYTES * SVE_VQ_BYTES)
+
+#define SVE_SIG_ZREGS_OFFSET	SVE_SIG_REGS_OFFSET
+#define SVE_SIG_ZREG_OFFSET(vq, n) \
+	(SVE_SIG_ZREGS_OFFSET + SVE_SIG_ZREG_SIZE(vq) * (n))
+#define SVE_SIG_ZREGS_SIZE(vq) \
+	(SVE_SIG_ZREG_OFFSET(vq, SVE_NUM_ZREGS) - SVE_SIG_ZREGS_OFFSET)
+
+#define SVE_SIG_PREGS_OFFSET(vq) \
+	(SVE_SIG_ZREGS_OFFSET + SVE_SIG_ZREGS_SIZE(vq))
+#define SVE_SIG_PREG_OFFSET(vq, n) \
+	(SVE_SIG_PREGS_OFFSET(vq) + SVE_SIG_PREG_SIZE(vq) * (n))
+#define SVE_SIG_PREGS_SIZE(vq) \
+	(SVE_SIG_PREG_OFFSET(vq, SVE_NUM_PREGS) - SVE_SIG_PREGS_OFFSET(vq))
+
+#define SVE_SIG_FFR_OFFSET(vq) \
+	(SVE_SIG_PREGS_OFFSET(vq) + SVE_SIG_PREGS_SIZE(vq))
+
+#define SVE_SIG_REGS_SIZE(vq) \
+	(SVE_SIG_FFR_OFFSET(vq) + SVE_SIG_FFR_SIZE(vq) - SVE_SIG_REGS_OFFSET)
+
+#define SVE_SIG_CONTEXT_SIZE(vq) (SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq))
+
+
 #endif /* _UAPI__ASM_SIGCONTEXT_H */

arch/arm64/kernel/Makefile

@@ -11,8 +11,6 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_insn.o = -pg
 CFLAGS_REMOVE_return_address.o = -pg
 
-CFLAGS_setup.o = -DUTS_MACHINE='"$(UTS_MACHINE)"'
-
 # Object file lists.
 arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\

arch/arm64/kernel/armv8_deprecated.c

@@ -228,15 +228,7 @@ ret:
 	return ret;
 }
 
-static struct ctl_table ctl_abi[] = {
-	{
-		.procname = "abi",
-		.mode = 0555,
-	},
-	{ }
-};
-
-static void __init register_insn_emulation_sysctl(struct ctl_table *table)
+static void __init register_insn_emulation_sysctl(void)
 {
 	unsigned long flags;
 	int i = 0;
@@ -262,8 +254,7 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 	}
 	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
 
-	table->child = insns_sysctl;
-	register_sysctl_table(table);
+	register_sysctl("abi", insns_sysctl);
 }
 
 /*
@@ -431,7 +422,7 @@ ret:
 	pr_warn_ratelimited("\"%s\" (%ld) uses obsolete SWP{B} instruction at 0x%llx\n",
 			current->comm, (unsigned long)current->pid, regs->pc);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return 0;
 
 fault:
@@ -512,7 +503,7 @@ ret:
 	pr_warn_ratelimited("\"%s\" (%ld) uses deprecated CP15 Barrier instruction at 0x%llx\n",
 			current->comm, (unsigned long)current->pid, regs->pc);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return 0;
 }
 
@@ -586,14 +577,14 @@ static int compat_setend_handler(struct pt_regs *regs, u32 big_endian)
 static int a32_setend_handler(struct pt_regs *regs, u32 instr)
 {
 	int rc = compat_setend_handler(regs, (instr >> 9) & 1);
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return rc;
 }
 
 static int t16_setend_handler(struct pt_regs *regs, u32 instr)
 {
 	int rc = compat_setend_handler(regs, (instr >> 3) & 1);
-	regs->pc += 2;
+	arm64_skip_faulting_instruction(regs, 2);
 	return rc;
 }
 
@@ -644,7 +635,7 @@ static int __init armv8_deprecated_init(void)
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
 				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
-	register_insn_emulation_sysctl(ctl_abi);
+	register_insn_emulation_sysctl();
 
 	return 0;
 }

arch/arm64/kernel/cpufeature.c

@@ -27,6 +27,7 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
+#include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
@@ -51,6 +52,21 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcaps);
 
+/*
+ * Flag to indicate if we have computed the system wide
+ * capabilities based on the boot time active CPUs. This
+ * will be used to determine if a new booting CPU should
+ * go through the verification process to make sure that it
+ * supports the system capabilities, without using a hotplug
+ * notifier.
+ */
+static bool sys_caps_initialised;
+
+static inline void set_sys_caps_initialised(void)
+{
+	sys_caps_initialised = true;
+}
+
 static int dump_cpu_hwcaps(struct notifier_block *self, unsigned long v, void *p)
 {
 	/* file-wide pr_fmt adds "CPU features: " prefix */
@@ -107,7 +123,11 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
  * sync with the documentation of the CPU feature register ABI.
  */
 static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0),
@@ -117,34 +137,35 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_DPB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DPB_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
 	/* Linux doesn't care about the EL3 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
 	/* Linux shouldn't care about secure memory */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_ASID_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ASID_SHIFT, 4, 0),
 	/*
 	 * Differing PARange is fine as long as all peripherals and memory are mapped
 	 * within the minimum PARange of all CPUs
@@ -155,20 +176,20 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HPD_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VHE_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HADBS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HPD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VHE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HADBS_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_UAO_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_CNP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_UAO_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CNP_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -193,14 +214,14 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 28, 4, 0xf),	/* InnerShr */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 24, 4, 0),	/* FCSE */
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0xf),	/* InnerShr */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0),	/* FCSE */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* AuxReg */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 16, 4, 0),	/* TCM */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0),	/* ShareLvl */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0xf),	/* OuterShr */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),	/* PMSA */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0),	/* VMSA */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),	/* TCM */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),	/* ShareLvl */
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0xf),	/* OuterShr */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),	/* PMSA */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* VMSA */
 	ARM64_FTR_END,
 };
 
@@ -221,8 +242,8 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_mvfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* FPMisc */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0),		/* SIMDMisc */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),		/* FPMisc */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),		/* SIMDMisc */
 	ARM64_FTR_END,
 };
 
@@ -234,25 +255,25 @@ static const struct arm64_ftr_bits ftr_dczid[] = {
 
 
 static const struct arm64_ftr_bits ftr_id_isar5[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA1_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SEVL_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* ac2 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),	/* ac2 */
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0),	/* State3 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0),		/* State2 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* State1 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0),		/* State0 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),		/* State3 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0),		/* State2 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),		/* State1 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),		/* State0 */
 	ARM64_FTR_END,
 };
 
@@ -268,6 +289,12 @@ static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_zcr[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
+		ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_SIZE, 0),	/* LEN */
+	ARM64_FTR_END,
+};
+
 /*
  * Common ftr bits for a 32bit register with all hidden, strict
  * attributes, with 4bit feature fields and a default safe value of
@@ -334,6 +361,7 @@ static const struct __ftr_reg_entry {
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
 	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz),
+	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -348,6 +376,9 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1),
 	ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
 
+	/* Op1 = 0, CRn = 1, CRm = 2 */
+	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
+
 	/* Op1 = 3, CRn = 0, CRm = 0 */
 	{ SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
 	ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
@@ -485,6 +516,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
+	init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
 
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
 		init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
@@ -505,6 +537,10 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
 	}
 
+	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
+		init_cpu_ftr_reg(SYS_ZCR_EL1, info->reg_zcr);
+		sve_init_vq_map();
+	}
 }
 
 static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
@@ -608,6 +644,9 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
 				      info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1);
 
+	taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu,
+				      info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0);
+
 	/*
 	 * If we have AArch32, we care about 32-bit features for compat.
 	 * If the system doesn't support AArch32, don't update them.
@@ -655,6 +694,16 @@ void update_cpu_features(int cpu,
 					info->reg_mvfr2, boot->reg_mvfr2);
 	}
 
+	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
+		taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
+					info->reg_zcr, boot->reg_zcr);
+
+		/* Probe vector lengths, unless we already gave up on SVE */
+		if (id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1)) &&
+		    !sys_caps_initialised)
+			sve_update_vq_map();
+	}
+
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
 	 * pretend to support them.
@@ -900,6 +949,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 1,
 	},
 #endif
+#ifdef CONFIG_ARM64_SVE
+	{
+		.desc = "Scalable Vector Extension",
+		.capability = ARM64_SVE,
+		.def_scope = SCOPE_SYSTEM,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR0_SVE_SHIFT,
+		.min_field_value = ID_AA64PFR0_SVE,
+		.matches = has_cpuid_feature,
+		.enable = sve_kernel_enable,
+	},
+#endif /* CONFIG_ARM64_SVE */
 	{},
 };
 
@@ -921,9 +983,14 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
@@ -932,6 +999,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
+#ifdef CONFIG_ARM64_SVE
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
+#endif
 	{},
 };
 
@@ -1040,21 +1110,6 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 	}
 }
 
-/*
- * Flag to indicate if we have computed the system wide
- * capabilities based on the boot time active CPUs. This
- * will be used to determine if a new booting CPU should
- * go through the verification process to make sure that it
- * supports the system capabilities, without using a hotplug
- * notifier.
- */
-static bool sys_caps_initialised;
-
-static inline void set_sys_caps_initialised(void)
-{
-	sys_caps_initialised = true;
-}
-
 /*
  * Check for CPU features that are used in early boot
  * based on the Boot CPU value.
@@ -1097,6 +1152,23 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
 	}
 }
 
+static void verify_sve_features(void)
+{
+	u64 safe_zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
+	u64 zcr = read_zcr_features();
+
+	unsigned int safe_len = safe_zcr & ZCR_ELx_LEN_MASK;
+	unsigned int len = zcr & ZCR_ELx_LEN_MASK;
+
+	if (len < safe_len || sve_verify_vq_map()) {
+		pr_crit("CPU%d: SVE: required vector length(s) missing\n",
+			smp_processor_id());
+		cpu_die_early();
+	}
+
+	/* Add checks on other ZCR bits here if necessary */
+}
+
 /*
  * Run through the enabled system capabilities and enable() it on this CPU.
  * The capabilities were decided based on the available CPUs at the boot time.
@@ -1110,8 +1182,12 @@ static void verify_local_cpu_capabilities(void)
 	verify_local_cpu_errata_workarounds();
 	verify_local_cpu_features(arm64_features);
 	verify_local_elf_hwcaps(arm64_elf_hwcaps);
+
 	if (system_supports_32bit_el0())
 		verify_local_elf_hwcaps(compat_elf_hwcaps);
+
+	if (system_supports_sve())
+		verify_sve_features();
 }
 
 void check_local_cpu_capabilities(void)
@@ -1189,6 +1265,8 @@ void __init setup_cpu_features(void)
 	if (system_supports_32bit_el0())
 		setup_elf_hwcaps(compat_elf_hwcaps);
 
+	sve_setup();
+
 	/* Advertise that we have computed the system capabilities */
 	set_sys_caps_initialised();
 
@@ -1287,7 +1365,7 @@ static int emulate_mrs(struct pt_regs *regs, u32 insn)
 	if (!rc) {
 		dst = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
 		pt_regs_write_reg(regs, dst, val);
-		regs->pc += 4;
+		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 	}
 
 	return rc;

arch/arm64/kernel/cpuinfo.c

@@ -19,6 +19,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
@@ -69,6 +70,12 @@ static const char *const hwcap_str[] = {
 	"fcma",
 	"lrcpc",
 	"dcpop",
+	"sha3",
+	"sm3",
+	"sm4",
+	"asimddp",
+	"sha512",
+	"sve",
 	NULL
 };
 
@@ -326,6 +333,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1);
 	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
+	info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
 
 	/* Update the 32bit ID registers only if AArch32 is implemented */
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
@@ -348,6 +356,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 		info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
 	}
 
+	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
+	    id_aa64pfr0_sve(info->reg_id_aa64pfr0))
+		info->reg_zcr = read_zcr_features();
+
 	cpuinfo_detect_icache_policy(info);
 }
 

arch/arm64/kernel/debug-monitors.c

@@ -30,6 +30,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cputype.h>
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/system_misc.h>
 
@@ -46,9 +47,9 @@ u8 debug_monitors_arch(void)
 static void mdscr_write(u32 mdscr)
 {
 	unsigned long flags;
-	local_dbg_save(flags);
+	flags = local_daif_save();
 	write_sysreg(mdscr, mdscr_el1);
-	local_dbg_restore(flags);
+	local_daif_restore(flags);
 }
 NOKPROBE_SYMBOL(mdscr_write);
 

arch/arm64/kernel/entry-fpsimd.S

@@ -41,3 +41,20 @@ ENTRY(fpsimd_load_state)
 	fpsimd_restore x0, 8
 	ret
 ENDPROC(fpsimd_load_state)
+
+#ifdef CONFIG_ARM64_SVE
+ENTRY(sve_save_state)
+	sve_save 0, x1, 2
+	ret
+ENDPROC(sve_save_state)
+
+ENTRY(sve_load_state)
+	sve_load 0, x1, x2, 3
+	ret
+ENDPROC(sve_load_state)
+
+ENTRY(sve_get_vl)
+	_sve_rdvl	0, 1
+	ret
+ENDPROC(sve_get_vl)
+#endif /* CONFIG_ARM64_SVE */

arch/arm64/kernel/entry-ftrace.S

@@ -108,13 +108,8 @@ ENTRY(_mcount)
 	mcount_get_lr	x1		//       function's lr (= parent's pc)
 	blr	x2			//   (*ftrace_trace_function)(pc, lr);
 
-#ifndef CONFIG_FUNCTION_GRAPH_TRACER
-skip_ftrace_call:			//   return;
-	mcount_exit			// }
-#else
-	mcount_exit			//   return;
-					// }
-skip_ftrace_call:
+skip_ftrace_call:			// }
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	ldr_l	x2, ftrace_graph_return
 	cmp	x0, x2			//   if ((ftrace_graph_return
 	b.ne	ftrace_graph_caller	//        != ftrace_stub)
@@ -123,9 +118,8 @@ skip_ftrace_call:
 	adr_l	x0, ftrace_graph_entry_stub //     != ftrace_graph_entry_stub))
 	cmp	x0, x2
 	b.ne	ftrace_graph_caller	//     ftrace_graph_caller();
-
-	mcount_exit
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+	mcount_exit
 ENDPROC(_mcount)
 
 #else /* CONFIG_DYNAMIC_FTRACE */

arch/arm64/kernel/entry.S

@@ -28,7 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
-#include <asm/memory.h>
+#include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/asm-uaccess.h>
@@ -221,6 +221,8 @@ alternative_else_nop_endif
 
 	.macro	kernel_exit, el
 	.if	\el != 0
+	disable_daif
+
 	/* Restore the task's original addr_limit. */
 	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
 	str	x20, [tsk, #TSK_TI_ADDR_LIMIT]
@@ -373,18 +375,18 @@ ENTRY(vectors)
 	kernel_ventry	el1_sync			// Synchronous EL1h
 	kernel_ventry	el1_irq				// IRQ EL1h
 	kernel_ventry	el1_fiq_invalid			// FIQ EL1h
-	kernel_ventry	el1_error_invalid		// Error EL1h
+	kernel_ventry	el1_error			// Error EL1h
 
 	kernel_ventry	el0_sync			// Synchronous 64-bit EL0
 	kernel_ventry	el0_irq				// IRQ 64-bit EL0
 	kernel_ventry	el0_fiq_invalid			// FIQ 64-bit EL0
-	kernel_ventry	el0_error_invalid		// Error 64-bit EL0
+	kernel_ventry	el0_error			// Error 64-bit EL0
 
 #ifdef CONFIG_COMPAT
 	kernel_ventry	el0_sync_compat			// Synchronous 32-bit EL0
 	kernel_ventry	el0_irq_compat			// IRQ 32-bit EL0
 	kernel_ventry	el0_fiq_invalid_compat		// FIQ 32-bit EL0
-	kernel_ventry	el0_error_invalid_compat	// Error 32-bit EL0
+	kernel_ventry	el0_error_compat		// Error 32-bit EL0
 #else
 	kernel_ventry	el0_sync_invalid		// Synchronous 32-bit EL0
 	kernel_ventry	el0_irq_invalid			// IRQ 32-bit EL0
@@ -453,10 +455,6 @@ ENDPROC(el0_error_invalid)
 el0_fiq_invalid_compat:
 	inv_entry 0, BAD_FIQ, 32
 ENDPROC(el0_fiq_invalid_compat)
-
-el0_error_invalid_compat:
-	inv_entry 0, BAD_ERROR, 32
-ENDPROC(el0_error_invalid_compat)
 #endif
 
 el1_sync_invalid:
@@ -508,24 +506,18 @@ el1_da:
 	 * Data abort handling
 	 */
 	mrs	x3, far_el1
-	enable_dbg
-	// re-enable interrupts if they were enabled in the aborted context
-	tbnz	x23, #7, 1f			// PSR_I_BIT
-	enable_irq
-1:
+	inherit_daif	pstate=x23, tmp=x2
 	clear_address_tag x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
-	// disable interrupts before pulling preserved data off the stack
-	disable_irq
 	kernel_exit 1
 el1_sp_pc:
 	/*
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x0, far_el1
-	enable_dbg
+	inherit_daif	pstate=x23, tmp=x2
 	mov	x2, sp
 	bl	do_sp_pc_abort
 	ASM_BUG()
@@ -533,7 +525,7 @@ el1_undef:
 	/*
 	 * Undefined instruction
 	 */
-	enable_dbg
+	inherit_daif	pstate=x23, tmp=x2
 	mov	x0, sp
 	bl	do_undefinstr
 	ASM_BUG()
@@ -550,7 +542,7 @@ el1_dbg:
 	kernel_exit 1
 el1_inv:
 	// TODO: add support for undefined instructions in kernel mode
-	enable_dbg
+	inherit_daif	pstate=x23, tmp=x2
 	mov	x0, sp
 	mov	x2, x1
 	mov	x1, #BAD_SYNC
@@ -561,7 +553,7 @@ ENDPROC(el1_sync)
 	.align	6
 el1_irq:
 	kernel_entry 1
-	enable_dbg
+	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -607,6 +599,8 @@ el0_sync:
 	b.eq	el0_ia
 	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
 	b.eq	el0_fpsimd_acc
+	cmp	x24, #ESR_ELx_EC_SVE		// SVE access
+	b.eq	el0_sve_acc
 	cmp	x24, #ESR_ELx_EC_FP_EXC64	// FP/ASIMD exception
 	b.eq	el0_fpsimd_exc
 	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
@@ -658,6 +652,7 @@ el0_svc_compat:
 	/*
 	 * AArch32 syscall handling
 	 */
+	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
 	adrp	stbl, compat_sys_call_table	// load compat syscall table pointer
 	mov	wscno, w7			// syscall number in w7 (r7)
 	mov     wsc_nr, #__NR_compat_syscalls
@@ -667,6 +662,10 @@ el0_svc_compat:
 el0_irq_compat:
 	kernel_entry 0, 32
 	b	el0_irq_naked
+
+el0_error_compat:
+	kernel_entry 0, 32
+	b	el0_error_naked
 #endif
 
 el0_da:
@@ -674,8 +673,7 @@ el0_da:
 	 * Data abort handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	clear_address_tag x0, x26
 	mov	x1, x25
@@ -687,8 +685,7 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
@@ -699,17 +696,27 @@ el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_fpsimd_acc
 	b	ret_to_user
+el0_sve_acc:
+	/*
+	 * Scalable Vector Extension access
+	 */
+	enable_daif
+	ct_user_exit
+	mov	x0, x25
+	mov	x1, sp
+	bl	do_sve_acc
+	b	ret_to_user
 el0_fpsimd_exc:
 	/*
-	 * Floating Point or Advanced SIMD exception
+	 * Floating Point, Advanced SIMD or SVE exception
 	 */
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
@@ -720,8 +727,7 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
@@ -732,8 +738,7 @@ el0_undef:
 	/*
 	 * Undefined instruction
 	 */
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, sp
 	bl	do_undefinstr
@@ -742,7 +747,7 @@ el0_sys:
 	/*
 	 * System instructions, for trapped cache maintenance instructions
 	 */
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
@@ -757,11 +762,11 @@ el0_dbg:
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_debug_exception
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	b	ret_to_user
 el0_inv:
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
@@ -774,7 +779,7 @@ ENDPROC(el0_sync)
 el0_irq:
 	kernel_entry 0
 el0_irq_naked:
-	enable_dbg
+	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -788,12 +793,34 @@ el0_irq_naked:
 	b	ret_to_user
 ENDPROC(el0_irq)
 
+el1_error:
+	kernel_entry 1
+	mrs	x1, esr_el1
+	enable_dbg
+	mov	x0, sp
+	bl	do_serror
+	kernel_exit 1
+ENDPROC(el1_error)
+
+el0_error:
+	kernel_entry 0
+el0_error_naked:
+	mrs	x1, esr_el1
+	enable_dbg
+	mov	x0, sp
+	bl	do_serror
+	enable_daif
+	ct_user_exit
+	b	ret_to_user
+ENDPROC(el0_error)
+
+
 /*
  * This is the fast syscall return path.  We do as little as possible here,
  * and this includes saving x0 back into the kernel stack.
  */
 ret_fast_syscall:
-	disable_irq				// disable interrupts
+	disable_daif
 	str	x0, [sp, #S_X0]			// returned x0
 	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
@@ -803,7 +830,7 @@ ret_fast_syscall:
 	enable_step_tsk x1, x2
 	kernel_exit 0
 ret_fast_syscall_trace:
-	enable_irq				// enable interrupts
+	enable_daif
 	b	__sys_trace_return_skipped	// we already saved x0
 
 /*
@@ -821,7 +848,7 @@ work_pending:
  * "slow" syscall return path.
  */
 ret_to_user:
-	disable_irq				// disable interrupts
+	disable_daif
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
@@ -835,16 +862,37 @@ ENDPROC(ret_to_user)
  */
 	.align	6
 el0_svc:
+	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
 	adrp	stbl, sys_call_table		// load syscall table pointer
 	mov	wscno, w8			// syscall number in w8
 	mov	wsc_nr, #__NR_syscalls
+
+#ifdef CONFIG_ARM64_SVE
+alternative_if_not ARM64_SVE
+	b	el0_svc_naked
+alternative_else_nop_endif
+	tbz	x16, #TIF_SVE, el0_svc_naked	// Skip unless TIF_SVE set:
+	bic	x16, x16, #_TIF_SVE		// discard SVE state
+	str	x16, [tsk, #TSK_TI_FLAGS]
+
+	/*
+	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
+	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
+	 * happens if a context switch or kernel_neon_begin() or context
+	 * modification (sigreturn, ptrace) intervenes.
+	 * So, ensure that CPACR_EL1 is already correct for the fast-path case:
+	 */
+	mrs	x9, cpacr_el1
+	bic	x9, x9, #CPACR_EL1_ZEN_EL0EN	// disable SVE for el0
+	msr	cpacr_el1, x9			// synchronised by eret to el0
+#endif
+
 el0_svc_naked:					// compat entry point
 	stp	x0, xscno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit 1
 
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// check for syscall hooks
-	tst	x16, #_TIF_SYSCALL_WORK
+	tst	x16, #_TIF_SYSCALL_WORK		// check for syscall hooks
 	b.ne	__sys_trace
 	cmp     wscno, wsc_nr			// check upper syscall limit
 	b.hs	ni_sys

arch/arm64/kernel/fpsimd.c

@@ -17,19 +17,34 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bitmap.h>
 #include <linux/bottom_half.h>
+#include <linux/bug.h>
+#include <linux/cache.h>
+#include <linux/compat.h>
 #include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
+#include <linux/linkage.h>
+#include <linux/irqflags.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
+#include <linux/prctl.h>
 #include <linux/preempt.h>
+#include <linux/prctl.h>
+#include <linux/ptrace.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
 
 #include <asm/fpsimd.h>
 #include <asm/cputype.h>
 #include <asm/simd.h>
+#include <asm/sigcontext.h>
+#include <asm/sysreg.h>
+#include <asm/traps.h>
 
 #define FPEXC_IOF	(1 << 0)
 #define FPEXC_DZF	(1 << 1)
@@ -39,6 +54,8 @@
 #define FPEXC_IDF	(1 << 7)
 
 /*
+ * (Note: in this discussion, statements about FPSIMD apply equally to SVE.)
+ *
  * In order to reduce the number of times the FPSIMD state is needlessly saved
  * and restored, we need to keep track of two things:
  * (a) for each task, we need to remember which CPU was the last one to have
@@ -99,10 +116,741 @@
  */
 static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
 
+/* Default VL for tasks that don't set it explicitly: */
+static int sve_default_vl = -1;
+
+#ifdef CONFIG_ARM64_SVE
+
+/* Maximum supported vector length across all CPUs (initially poisoned) */
+int __ro_after_init sve_max_vl = -1;
+/* Set of available vector lengths, as vq_to_bit(vq): */
+static __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+static void __percpu *efi_sve_state;
+
+#else /* ! CONFIG_ARM64_SVE */
+
+/* Dummy declaration for code that will be optimised out: */
+extern __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+extern void __percpu *efi_sve_state;
+
+#endif /* ! CONFIG_ARM64_SVE */
+
+/*
+ * Call __sve_free() directly only if you know task can't be scheduled
+ * or preempted.
+ */
+static void __sve_free(struct task_struct *task)
+{
+	kfree(task->thread.sve_state);
+	task->thread.sve_state = NULL;
+}
+
+static void sve_free(struct task_struct *task)
+{
+	WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
+
+	__sve_free(task);
+}
+
+
+/* Offset of FFR in the SVE register dump */
+static size_t sve_ffr_offset(int vl)
+{
+	return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET;
+}
+
+static void *sve_pffr(struct task_struct *task)
+{
+	return (char *)task->thread.sve_state +
+		sve_ffr_offset(task->thread.sve_vl);
+}
+
+static void change_cpacr(u64 val, u64 mask)
+{
+	u64 cpacr = read_sysreg(CPACR_EL1);
+	u64 new = (cpacr & ~mask) | val;
+
+	if (new != cpacr)
+		write_sysreg(new, CPACR_EL1);
+}
+
+static void sve_user_disable(void)
+{
+	change_cpacr(0, CPACR_EL1_ZEN_EL0EN);
+}
+
+static void sve_user_enable(void)
+{
+	change_cpacr(CPACR_EL1_ZEN_EL0EN, CPACR_EL1_ZEN_EL0EN);
+}
+
+/*
+ * TIF_SVE controls whether a task can use SVE without trapping while
+ * in userspace, and also the way a task's FPSIMD/SVE state is stored
+ * in thread_struct.
+ *
+ * The kernel uses this flag to track whether a user task is actively
+ * using SVE, and therefore whether full SVE register state needs to
+ * be tracked.  If not, the cheaper FPSIMD context handling code can
+ * be used instead of the more costly SVE equivalents.
+ *
+ *  * TIF_SVE set:
+ *
+ *    The task can execute SVE instructions while in userspace without
+ *    trapping to the kernel.
+ *
+ *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
+ *    corresponding Zn), P0-P15 and FFR are encoded in in
+ *    task->thread.sve_state, formatted appropriately for vector
+ *    length task->thread.sve_vl.
+ *
+ *    task->thread.sve_state must point to a valid buffer at least
+ *    sve_state_size(task) bytes in size.
+ *
+ *    During any syscall, the kernel may optionally clear TIF_SVE and
+ *    discard the vector state except for the FPSIMD subset.
+ *
+ *  * TIF_SVE clear:
+ *
+ *    An attempt by the user task to execute an SVE instruction causes
+ *    do_sve_acc() to be called, which does some preparation and then
+ *    sets TIF_SVE.
+ *
+ *    When stored, FPSIMD registers V0-V31 are encoded in
+ *    task->fpsimd_state; bits [max : 128] for each of Z0-Z31 are
+ *    logically zero but not stored anywhere; P0-P15 and FFR are not
+ *    stored and have unspecified values from userspace's point of
+ *    view.  For hygiene purposes, the kernel zeroes them on next use,
+ *    but userspace is discouraged from relying on this.
+ *
+ *    task->thread.sve_state does not need to be non-NULL, valid or any
+ *    particular size: it must not be dereferenced.
+ *
+ *  * FPSR and FPCR are always stored in task->fpsimd_state irrespctive of
+ *    whether TIF_SVE is clear or set, since these are not vector length
+ *    dependent.
+ */
+
+/*
+ * Update current's FPSIMD/SVE registers from thread_struct.
+ *
+ * This function should be called only when the FPSIMD/SVE state in
+ * thread_struct is known to be up to date, when preparing to enter
+ * userspace.
+ *
+ * Softirqs (and preemption) must be disabled.
+ */
+static void task_fpsimd_load(void)
+{
+	WARN_ON(!in_softirq() && !irqs_disabled());
+
+	if (system_supports_sve() && test_thread_flag(TIF_SVE))
+		sve_load_state(sve_pffr(current),
+			       &current->thread.fpsimd_state.fpsr,
+			       sve_vq_from_vl(current->thread.sve_vl) - 1);
+	else
+		fpsimd_load_state(&current->thread.fpsimd_state);
+
+	if (system_supports_sve()) {
+		/* Toggle SVE trapping for userspace if needed */
+		if (test_thread_flag(TIF_SVE))
+			sve_user_enable();
+		else
+			sve_user_disable();
+
+		/* Serialised by exception return to user */
+	}
+}
+
+/*
+ * Ensure current's FPSIMD/SVE storage in thread_struct is up to date
+ * with respect to the CPU registers.
+ *
+ * Softirqs (and preemption) must be disabled.
+ */
+static void task_fpsimd_save(void)
+{
+	WARN_ON(!in_softirq() && !irqs_disabled());
+
+	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
+			if (WARN_ON(sve_get_vl() != current->thread.sve_vl)) {
+				/*
+				 * Can't save the user regs, so current would
+				 * re-enter user with corrupt state.
+				 * There's no way to recover, so kill it:
+				 */
+				force_signal_inject(
+					SIGKILL, 0, current_pt_regs(), 0);
+				return;
+			}
+
+			sve_save_state(sve_pffr(current),
+				       &current->thread.fpsimd_state.fpsr);
+		} else
+			fpsimd_save_state(&current->thread.fpsimd_state);
+	}
+}
+
+/*
+ * Helpers to translate bit indices in sve_vq_map to VQ values (and
+ * vice versa).  This allows find_next_bit() to be used to find the
+ * _maximum_ VQ not exceeding a certain value.
+ */
+
+static unsigned int vq_to_bit(unsigned int vq)
+{
+	return SVE_VQ_MAX - vq;
+}
+
+static unsigned int bit_to_vq(unsigned int bit)
+{
+	if (WARN_ON(bit >= SVE_VQ_MAX))
+		bit = SVE_VQ_MAX - 1;
+
+	return SVE_VQ_MAX - bit;
+}
+
+/*
+ * All vector length selection from userspace comes through here.
+ * We're on a slow path, so some sanity-checks are included.
+ * If things go wrong there's a bug somewhere, but try to fall back to a
+ * safe choice.
+ */
+static unsigned int find_supported_vector_length(unsigned int vl)
+{
+	int bit;
+	int max_vl = sve_max_vl;
+
+	if (WARN_ON(!sve_vl_valid(vl)))
+		vl = SVE_VL_MIN;
+
+	if (WARN_ON(!sve_vl_valid(max_vl)))
+		max_vl = SVE_VL_MIN;
+
+	if (vl > max_vl)
+		vl = max_vl;
+
+	bit = find_next_bit(sve_vq_map, SVE_VQ_MAX,
+			    vq_to_bit(sve_vq_from_vl(vl)));
+	return sve_vl_from_vq(bit_to_vq(bit));
+}
+
+#ifdef CONFIG_SYSCTL
+
+static int sve_proc_do_default_vl(struct ctl_table *table, int write,
+				  void __user *buffer, size_t *lenp,
+				  loff_t *ppos)
+{
+	int ret;
+	int vl = sve_default_vl;
+	struct ctl_table tmp_table = {
+		.data = &vl,
+		.maxlen = sizeof(vl),
+	};
+
+	ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
+	if (ret || !write)
+		return ret;
+
+	/* Writing -1 has the special meaning "set to max": */
+	if (vl == -1) {
+		/* Fail safe if sve_max_vl wasn't initialised */
+		if (WARN_ON(!sve_vl_valid(sve_max_vl)))
+			vl = SVE_VL_MIN;
+		else
+			vl = sve_max_vl;
+
+		goto chosen;
+	}
+
+	if (!sve_vl_valid(vl))
+		return -EINVAL;
+
+	vl = find_supported_vector_length(vl);
+chosen:
+	sve_default_vl = vl;
+	return 0;
+}
+
+static struct ctl_table sve_default_vl_table[] = {
+	{
+		.procname	= "sve_default_vector_length",
+		.mode		= 0644,
+		.proc_handler	= sve_proc_do_default_vl,
+	},
+	{ }
+};
+
+static int __init sve_sysctl_init(void)
+{
+	if (system_supports_sve())
+		if (!register_sysctl("abi", sve_default_vl_table))
+			return -EINVAL;
+
+	return 0;
+}
+
+#else /* ! CONFIG_SYSCTL */
+static int __init sve_sysctl_init(void) { return 0; }
+#endif /* ! CONFIG_SYSCTL */
+
+#define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
+	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
+
+/*
+ * Transfer the FPSIMD state in task->thread.fpsimd_state to
+ * task->thread.sve_state.
+ *
+ * Task can be a non-runnable task, or current.  In the latter case,
+ * softirqs (and preemption) must be disabled.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ * task->thread.fpsimd_state must be up to date before calling this function.
+ */
+static void fpsimd_to_sve(struct task_struct *task)
+{
+	unsigned int vq;
+	void *sst = task->thread.sve_state;
+	struct fpsimd_state const *fst = &task->thread.fpsimd_state;
+	unsigned int i;
+
+	if (!system_supports_sve())
+		return;
+
+	vq = sve_vq_from_vl(task->thread.sve_vl);
+	for (i = 0; i < 32; ++i)
+		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
+		       sizeof(fst->vregs[i]));
+}
+
+/*
+ * Transfer the SVE state in task->thread.sve_state to
+ * task->thread.fpsimd_state.
+ *
+ * Task can be a non-runnable task, or current.  In the latter case,
+ * softirqs (and preemption) must be disabled.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ * task->thread.sve_state must be up to date before calling this function.
+ */
+static void sve_to_fpsimd(struct task_struct *task)
+{
+	unsigned int vq;
+	void const *sst = task->thread.sve_state;
+	struct fpsimd_state *fst = &task->thread.fpsimd_state;
+	unsigned int i;
+
+	if (!system_supports_sve())
+		return;
+
+	vq = sve_vq_from_vl(task->thread.sve_vl);
+	for (i = 0; i < 32; ++i)
+		memcpy(&fst->vregs[i], ZREG(sst, vq, i),
+		       sizeof(fst->vregs[i]));
+}
+
+#ifdef CONFIG_ARM64_SVE
+
+/*
+ * Return how many bytes of memory are required to store the full SVE
+ * state for task, given task's currently configured vector length.
+ */
+size_t sve_state_size(struct task_struct const *task)
+{
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task->thread.sve_vl));
+}
+
+/*
+ * Ensure that task->thread.sve_state is allocated and sufficiently large.
+ *
+ * This function should be used only in preparation for replacing
+ * task->thread.sve_state with new data.  The memory is always zeroed
+ * here to prevent stale data from showing through: this is done in
+ * the interest of testability and predictability: except in the
+ * do_sve_acc() case, there is no ABI requirement to hide stale data
+ * written previously be task.
+ */
+void sve_alloc(struct task_struct *task)
+{
+	if (task->thread.sve_state) {
+		memset(task->thread.sve_state, 0, sve_state_size(current));
+		return;
+	}
+
+	/* This is a small allocation (maximum ~8KB) and Should Not Fail. */
+	task->thread.sve_state =
+		kzalloc(sve_state_size(task), GFP_KERNEL);
+
+	/*
+	 * If future SVE revisions can have larger vectors though,
+	 * this may cease to be true:
+	 */
+	BUG_ON(!task->thread.sve_state);
+}
+
+
+/*
+ * Ensure that task->thread.sve_state is up to date with respect to
+ * the user task, irrespective of when SVE is in use or not.
+ *
+ * This should only be called by ptrace.  task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void fpsimd_sync_to_sve(struct task_struct *task)
+{
+	if (!test_tsk_thread_flag(task, TIF_SVE))
+		fpsimd_to_sve(task);
+}
+
+/*
+ * Ensure that task->thread.fpsimd_state is up to date with respect to
+ * the user task, irrespective of whether SVE is in use or not.
+ *
+ * This should only be called by ptrace.  task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void sve_sync_to_fpsimd(struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SVE))
+		sve_to_fpsimd(task);
+}
+
+/*
+ * Ensure that task->thread.sve_state is up to date with respect to
+ * the task->thread.fpsimd_state.
+ *
+ * This should only be called by ptrace to merge new FPSIMD register
+ * values into a task for which SVE is currently active.
+ * task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ * task->thread.fpsimd_state must already have been initialised with
+ * the new FPSIMD register values to be merged in.
+ */
+void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
+{
+	unsigned int vq;
+	void *sst = task->thread.sve_state;
+	struct fpsimd_state const *fst = &task->thread.fpsimd_state;
+	unsigned int i;
+
+	if (!test_tsk_thread_flag(task, TIF_SVE))
+		return;
+
+	vq = sve_vq_from_vl(task->thread.sve_vl);
+
+	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
+
+	for (i = 0; i < 32; ++i)
+		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
+		       sizeof(fst->vregs[i]));
+}
+
+int sve_set_vector_length(struct task_struct *task,
+			  unsigned long vl, unsigned long flags)
+{
+	if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
+				     PR_SVE_SET_VL_ONEXEC))
+		return -EINVAL;
+
+	if (!sve_vl_valid(vl))
+		return -EINVAL;
+
+	/*
+	 * Clamp to the maximum vector length that VL-agnostic SVE code can
+	 * work with.  A flag may be assigned in the future to allow setting
+	 * of larger vector lengths without confusing older software.
+	 */
+	if (vl > SVE_VL_ARCH_MAX)
+		vl = SVE_VL_ARCH_MAX;
+
+	vl = find_supported_vector_length(vl);
+
+	if (flags & (PR_SVE_VL_INHERIT |
+		     PR_SVE_SET_VL_ONEXEC))
+		task->thread.sve_vl_onexec = vl;
+	else
+		/* Reset VL to system default on next exec: */
+		task->thread.sve_vl_onexec = 0;
+
+	/* Only actually set the VL if not deferred: */
+	if (flags & PR_SVE_SET_VL_ONEXEC)
+		goto out;
+
+	if (vl == task->thread.sve_vl)
+		goto out;
+
+	/*
+	 * To ensure the FPSIMD bits of the SVE vector registers are preserved,
+	 * write any live register state back to task_struct, and convert to a
+	 * non-SVE thread.
+	 */
+	if (task == current) {
+		local_bh_disable();
+
+		task_fpsimd_save();
+		set_thread_flag(TIF_FOREIGN_FPSTATE);
+	}
+
+	fpsimd_flush_task_state(task);
+	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+		sve_to_fpsimd(task);
+
+	if (task == current)
+		local_bh_enable();
+
+	/*
+	 * Force reallocation of task SVE state to the correct size
+	 * on next use:
+	 */
+	sve_free(task);
+
+	task->thread.sve_vl = vl;
+
+out:
+	if (flags & PR_SVE_VL_INHERIT)
+		set_tsk_thread_flag(task, TIF_SVE_VL_INHERIT);
+	else
+		clear_tsk_thread_flag(task, TIF_SVE_VL_INHERIT);
+
+	return 0;
+}
+
+/*
+ * Encode the current vector length and flags for return.
+ * This is only required for prctl(): ptrace has separate fields
+ *
+ * flags are as for sve_set_vector_length().
+ */
+static int sve_prctl_status(unsigned long flags)
+{
+	int ret;
+
+	if (flags & PR_SVE_SET_VL_ONEXEC)
+		ret = current->thread.sve_vl_onexec;
+	else
+		ret = current->thread.sve_vl;
+
+	if (test_thread_flag(TIF_SVE_VL_INHERIT))
+		ret |= PR_SVE_VL_INHERIT;
+
+	return ret;
+}
+
+/* PR_SVE_SET_VL */
+int sve_set_current_vl(unsigned long arg)
+{
+	unsigned long vl, flags;
+	int ret;
+
+	vl = arg & PR_SVE_VL_LEN_MASK;
+	flags = arg & ~vl;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	ret = sve_set_vector_length(current, vl, flags);
+	if (ret)
+		return ret;
+
+	return sve_prctl_status(flags);
+}
+
+/* PR_SVE_GET_VL */
+int sve_get_current_vl(void)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	return sve_prctl_status(0);
+}
+
+/*
+ * Bitmap for temporary storage of the per-CPU set of supported vector lengths
+ * during secondary boot.
+ */
+static DECLARE_BITMAP(sve_secondary_vq_map, SVE_VQ_MAX);
+
+static void sve_probe_vqs(DECLARE_BITMAP(map, SVE_VQ_MAX))
+{
+	unsigned int vq, vl;
+	unsigned long zcr;
+
+	bitmap_zero(map, SVE_VQ_MAX);
+
+	zcr = ZCR_ELx_LEN_MASK;
+	zcr = read_sysreg_s(SYS_ZCR_EL1) & ~zcr;
+
+	for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) {
+		write_sysreg_s(zcr | (vq - 1), SYS_ZCR_EL1); /* self-syncing */
+		vl = sve_get_vl();
+		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
+		set_bit(vq_to_bit(vq), map);
+	}
+}
+
+void __init sve_init_vq_map(void)
+{
+	sve_probe_vqs(sve_vq_map);
+}
+
+/*
+ * If we haven't committed to the set of supported VQs yet, filter out
+ * those not supported by the current CPU.
+ */
+void sve_update_vq_map(void)
+{
+	sve_probe_vqs(sve_secondary_vq_map);
+	bitmap_and(sve_vq_map, sve_vq_map, sve_secondary_vq_map, SVE_VQ_MAX);
+}
+
+/* Check whether the current CPU supports all VQs in the committed set */
+int sve_verify_vq_map(void)
+{
+	int ret = 0;
+
+	sve_probe_vqs(sve_secondary_vq_map);
+	bitmap_andnot(sve_secondary_vq_map, sve_vq_map, sve_secondary_vq_map,
+		      SVE_VQ_MAX);
+	if (!bitmap_empty(sve_secondary_vq_map, SVE_VQ_MAX)) {
+		pr_warn("SVE: cpu%d: Required vector length(s) missing\n",
+			smp_processor_id());
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void __init sve_efi_setup(void)
+{
+	if (!IS_ENABLED(CONFIG_EFI))
+		return;
+
+	/*
+	 * alloc_percpu() warns and prints a backtrace if this goes wrong.
+	 * This is evidence of a crippled system and we are returning void,
+	 * so no attempt is made to handle this situation here.
+	 */
+	if (!sve_vl_valid(sve_max_vl))
+		goto fail;
+
+	efi_sve_state = __alloc_percpu(
+		SVE_SIG_REGS_SIZE(sve_vq_from_vl(sve_max_vl)), SVE_VQ_BYTES);
+	if (!efi_sve_state)
+		goto fail;
+
+	return;
+
+fail:
+	panic("Cannot allocate percpu memory for EFI SVE save/restore");
+}
+
+/*
+ * Enable SVE for EL1.
+ * Intended for use by the cpufeatures code during CPU boot.
+ */
+int sve_kernel_enable(void *__always_unused p)
+{
+	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1);
+	isb();
+
+	return 0;
+}
+
+void __init sve_setup(void)
+{
+	u64 zcr;
+
+	if (!system_supports_sve())
+		return;
+
+	/*
+	 * The SVE architecture mandates support for 128-bit vectors,
+	 * so sve_vq_map must have at least SVE_VQ_MIN set.
+	 * If something went wrong, at least try to patch it up:
+	 */
+	if (WARN_ON(!test_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
+		set_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map);
+
+	zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
+	sve_max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);
+
+	/*
+	 * Sanity-check that the max VL we determined through CPU features
+	 * corresponds properly to sve_vq_map.  If not, do our best:
+	 */
+	if (WARN_ON(sve_max_vl != find_supported_vector_length(sve_max_vl)))
+		sve_max_vl = find_supported_vector_length(sve_max_vl);
+
+	/*
+	 * For the default VL, pick the maximum supported value <= 64.
+	 * VL == 64 is guaranteed not to grow the signal frame.
+	 */
+	sve_default_vl = find_supported_vector_length(64);
+
+	pr_info("SVE: maximum available vector length %u bytes per vector\n",
+		sve_max_vl);
+	pr_info("SVE: default vector length %u bytes per vector\n",
+		sve_default_vl);
+
+	sve_efi_setup();
+}
+
+/*
+ * Called from the put_task_struct() path, which cannot get here
+ * unless dead_task is really dead and not schedulable.
+ */
+void fpsimd_release_task(struct task_struct *dead_task)
+{
+	__sve_free(dead_task);
+}
+
+#endif /* CONFIG_ARM64_SVE */
+
+/*
+ * Trapped SVE access
+ *
+ * Storage is allocated for the full SVE state, the current FPSIMD
+ * register contents are migrated across, and TIF_SVE is set so that
+ * the SVE access trap will be disabled the next time this task
+ * reaches ret_to_user.
+ *
+ * TIF_SVE should be clear on entry: otherwise, task_fpsimd_load()
+ * would have disabled the SVE access trap for userspace during
+ * ret_to_user, making an SVE access trap impossible in that case.
+ */
+asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
+{
+	/* Even if we chose not to use SVE, the hardware could still trap: */
+	if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+		return;
+	}
+
+	sve_alloc(current);
+
+	local_bh_disable();
+
+	task_fpsimd_save();
+	fpsimd_to_sve(current);
+
+	/* Force ret_to_user to reload the registers: */
+	fpsimd_flush_task_state(current);
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+
+	if (test_and_set_thread_flag(TIF_SVE))
+		WARN_ON(1); /* SVE access shouldn't have trapped */
+
+	local_bh_enable();
+}
+
 /*
  * Trapped FP/ASIMD access.
  */
-void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
+asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* TODO: implement lazy context saving/restoring */
 	WARN_ON(1);
@@ -111,7 +859,7 @@ void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Raise a SIGFPE for the current process.
  */
-void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
+asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 {
 	siginfo_t info;
 	unsigned int si_code = 0;
@@ -144,8 +892,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 	 * the registers is in fact the most recent userland FPSIMD state of
 	 * 'current'.
 	 */
-	if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
-		fpsimd_save_state(&current->thread.fpsimd_state);
+	if (current->mm)
+		task_fpsimd_save();
 
 	if (next->mm) {
 		/*
@@ -159,16 +907,16 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 		if (__this_cpu_read(fpsimd_last_state) == st
 		    && st->cpu == smp_processor_id())
-			clear_ti_thread_flag(task_thread_info(next),
-					     TIF_FOREIGN_FPSTATE);
+			clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
 		else
-			set_ti_thread_flag(task_thread_info(next),
-					   TIF_FOREIGN_FPSTATE);
+			set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
 	}
 }
 
 void fpsimd_flush_thread(void)
 {
+	int vl, supported_vl;
+
 	if (!system_supports_fpsimd())
 		return;
 
@@ -176,6 +924,42 @@ void fpsimd_flush_thread(void)
 
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_flush_task_state(current);
+
+	if (system_supports_sve()) {
+		clear_thread_flag(TIF_SVE);
+		sve_free(current);
+
+		/*
+		 * Reset the task vector length as required.
+		 * This is where we ensure that all user tasks have a valid
+		 * vector length configured: no kernel task can become a user
+		 * task without an exec and hence a call to this function.
+		 * By the time the first call to this function is made, all
+		 * early hardware probing is complete, so sve_default_vl
+		 * should be valid.
+		 * If a bug causes this to go wrong, we make some noise and
+		 * try to fudge thread.sve_vl to a safe value here.
+		 */
+		vl = current->thread.sve_vl_onexec ?
+			current->thread.sve_vl_onexec : sve_default_vl;
+
+		if (WARN_ON(!sve_vl_valid(vl)))
+			vl = SVE_VL_MIN;
+
+		supported_vl = find_supported_vector_length(vl);
+		if (WARN_ON(supported_vl != vl))
+			vl = supported_vl;
+
+		current->thread.sve_vl = vl;
+
+		/*
+		 * If the task is not set to inherit, ensure that the vector
+		 * length will be reset by a subsequent exec:
+		 */
+		if (!test_thread_flag(TIF_SVE_VL_INHERIT))
+			current->thread.sve_vl_onexec = 0;
+	}
+
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 
 	local_bh_enable();
@@ -191,13 +975,22 @@ void fpsimd_preserve_current_state(void)
 		return;
 
 	local_bh_disable();
-
-	if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
-		fpsimd_save_state(&current->thread.fpsimd_state);
-
+	task_fpsimd_save();
 	local_bh_enable();
 }
 
+/*
+ * Like fpsimd_preserve_current_state(), but ensure that
+ * current->thread.fpsimd_state is updated so that it can be copied to
+ * the signal frame.
+ */
+void fpsimd_signal_preserve_current_state(void)
+{
+	fpsimd_preserve_current_state();
+	if (system_supports_sve() && test_thread_flag(TIF_SVE))
+		sve_to_fpsimd(current);
+}
+
 /*
  * Load the userland FPSIMD state of 'current' from memory, but only if the
  * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
@@ -213,7 +1006,7 @@ void fpsimd_restore_current_state(void)
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		struct fpsimd_state *st = &current->thread.fpsimd_state;
 
-		fpsimd_load_state(st);
+		task_fpsimd_load();
 		__this_cpu_write(fpsimd_last_state, st);
 		st->cpu = smp_processor_id();
 	}
@@ -233,7 +1026,12 @@ void fpsimd_update_current_state(struct fpsimd_state *state)
 
 	local_bh_disable();
 
-	fpsimd_load_state(state);
+	if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
+		current->thread.fpsimd_state = *state;
+		fpsimd_to_sve(current);
+	}
+	task_fpsimd_load();
+
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		struct fpsimd_state *st = &current->thread.fpsimd_state;
 
@@ -252,6 +1050,33 @@ void fpsimd_flush_task_state(struct task_struct *t)
 	t->thread.fpsimd_state.cpu = NR_CPUS;
 }
 
+static inline void fpsimd_flush_cpu_state(void)
+{
+	__this_cpu_write(fpsimd_last_state, NULL);
+}
+
+/*
+ * Invalidate any task SVE state currently held in this CPU's regs.
+ *
+ * This is used to prevent the kernel from trying to reuse SVE register data
+ * that is detroyed by KVM guest enter/exit.  This function should go away when
+ * KVM SVE support is implemented.  Don't use it for anything else.
+ */
+#ifdef CONFIG_ARM64_SVE
+void sve_flush_cpu_state(void)
+{
+	struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state);
+	struct task_struct *tsk;
+
+	if (!fpstate)
+		return;
+
+	tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state);
+	if (test_tsk_thread_flag(tsk, TIF_SVE))
+		fpsimd_flush_cpu_state();
+}
+#endif /* CONFIG_ARM64_SVE */
+
 #ifdef CONFIG_KERNEL_MODE_NEON
 
 DEFINE_PER_CPU(bool, kernel_neon_busy);
@@ -286,11 +1111,13 @@ void kernel_neon_begin(void)
 	__this_cpu_write(kernel_neon_busy, true);
 
 	/* Save unsaved task fpsimd state, if any: */
-	if (current->mm && !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
-		fpsimd_save_state(&current->thread.fpsimd_state);
+	if (current->mm) {
+		task_fpsimd_save();
+		set_thread_flag(TIF_FOREIGN_FPSTATE);
+	}
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
-	__this_cpu_write(fpsimd_last_state, NULL);
+	fpsimd_flush_cpu_state();
 
 	preempt_disable();
 
@@ -325,6 +1152,7 @@ EXPORT_SYMBOL(kernel_neon_end);
 
 static DEFINE_PER_CPU(struct fpsimd_state, efi_fpsimd_state);
 static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
+static DEFINE_PER_CPU(bool, efi_sve_state_used);
 
 /*
  * EFI runtime services support functions
@@ -350,10 +1178,24 @@ void __efi_fpsimd_begin(void)
 
 	WARN_ON(preemptible());
 
-	if (may_use_simd())
+	if (may_use_simd()) {
 		kernel_neon_begin();
-	else {
-		fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
+	} else {
+		/*
+		 * If !efi_sve_state, SVE can't be in use yet and doesn't need
+		 * preserving:
+		 */
+		if (system_supports_sve() && likely(efi_sve_state)) {
+			char *sve_state = this_cpu_ptr(efi_sve_state);
+
+			__this_cpu_write(efi_sve_state_used, true);
+
+			sve_save_state(sve_state + sve_ffr_offset(sve_max_vl),
+				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr);
+		} else {
+			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
+		}
+
 		__this_cpu_write(efi_fpsimd_state_used, true);
 	}
 }
@@ -366,10 +1208,22 @@ void __efi_fpsimd_end(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	if (__this_cpu_xchg(efi_fpsimd_state_used, false))
-		fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
-	else
+	if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) {
 		kernel_neon_end();
+	} else {
+		if (system_supports_sve() &&
+		    likely(__this_cpu_read(efi_sve_state_used))) {
+			char const *sve_state = this_cpu_ptr(efi_sve_state);
+
+			sve_load_state(sve_state + sve_ffr_offset(sve_max_vl),
+				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
+				       sve_vq_from_vl(sve_get_vl()) - 1);
+
+			__this_cpu_write(efi_sve_state_used, false);
+		} else {
+			fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
+		}
+	}
 }
 
 #endif /* CONFIG_EFI */
@@ -382,9 +1236,9 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
-			fpsimd_save_state(&current->thread.fpsimd_state);
-		this_cpu_write(fpsimd_last_state, NULL);
+		if (current->mm)
+			task_fpsimd_save();
+		fpsimd_flush_cpu_state();
 		break;
 	case CPU_PM_EXIT:
 		if (current->mm)
@@ -442,6 +1296,6 @@ static int __init fpsimd_init(void)
 	if (!(elf_hwcap & HWCAP_ASIMD))
 		pr_notice("Advanced SIMD is not implemented\n");
 
-	return 0;
+	return sve_sysctl_init();
 }
 core_initcall(fpsimd_init);

arch/arm64/kernel/head.S

@@ -480,14 +480,21 @@ set_hcr:
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #32, #4			// Check ID_AA64DFR0_EL1 PMSVer
-	cbz	x0, 6f				// Skip if SPE not present
-	cbnz	x2, 5f				// VHE?
+	cbz	x0, 7f				// Skip if SPE not present
+	cbnz	x2, 6f				// VHE?
+	mrs_s	x4, SYS_PMBIDR_EL1		// If SPE available at EL2,
+	and	x4, x4, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
+	cbnz	x4, 5f				// then permit sampling of physical
+	mov	x4, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
+		      1 << SYS_PMSCR_EL2_PA_SHIFT)
+	msr_s	SYS_PMSCR_EL2, x4		// addresses and physical counter
+5:
 	mov	x1, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
 	orr	x3, x3, x1			// If we don't have VHE, then
-	b	6f				// use EL1&0 translation.
-5:						// For VHE, use EL2 translation
+	b	7f				// use EL1&0 translation.
+6:						// For VHE, use EL2 translation
 	orr	x3, x3, #MDCR_EL2_TPMS		// and disable access from EL1
-6:
+7:
 	msr	mdcr_el2, x3			// Configure debug traps
 
 	/* Stage-2 translation */
@@ -517,8 +524,19 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	mov	x0, #0x33ff
 	msr	cptr_el2, x0			// Disable copro. traps to EL2
 
+	/* SVE register access */
+	mrs	x1, id_aa64pfr0_el1
+	ubfx	x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4
+	cbz	x1, 7f
+
+	bic	x0, x0, #CPTR_EL2_TZ		// Also disable SVE traps
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	isb
+	mov	x1, #ZCR_ELx_LEN_MASK		// SVE: Enable full vector
+	msr_s	SYS_ZCR_EL2, x1			// length for EL1.
+
 	/* Hypervisor stub */
-	adr_l	x0, __hyp_stub_vectors
+7:	adr_l	x0, __hyp_stub_vectors
 	msr	vbar_el2, x0
 
 	/* spsr */

arch/arm64/kernel/hibernate.c

@@ -27,6 +27,7 @@
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/daifflags.h>
 #include <asm/irqflags.h>
 #include <asm/kexec.h>
 #include <asm/memory.h>
@@ -285,7 +286,7 @@ int swsusp_arch_suspend(void)
 		return -EBUSY;
 	}
 
-	local_dbg_save(flags);
+	flags = local_daif_save();
 
 	if (__cpu_suspend_enter(&state)) {
 		/* make the crash dump kernel image visible/saveable */
@@ -315,7 +316,7 @@ int swsusp_arch_suspend(void)
 		__cpu_suspend_exit();
 	}
 
-	local_dbg_restore(flags);
+	local_daif_restore(flags);
 
 	return ret;
 }

arch/arm64/kernel/io.c

@@ -25,8 +25,7 @@
  */
 void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)from, 8) ||
-			 !IS_ALIGNED((unsigned long)to, 8))) {
+	while (count && !IS_ALIGNED((unsigned long)from, 8)) {
 		*(u8 *)to = __raw_readb(from);
 		from++;
 		to++;
@@ -54,23 +53,22 @@ EXPORT_SYMBOL(__memcpy_fromio);
  */
 void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)to, 8) ||
-			 !IS_ALIGNED((unsigned long)from, 8))) {
-		__raw_writeb(*(volatile u8 *)from, to);
+	while (count && !IS_ALIGNED((unsigned long)to, 8)) {
+		__raw_writeb(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;
 	}
 
 	while (count >= 8) {
-		__raw_writeq(*(volatile u64 *)from, to);
+		__raw_writeq(*(u64 *)from, to);
 		from += 8;
 		to += 8;
 		count -= 8;
 	}
 
 	while (count) {
-		__raw_writeb(*(volatile u8 *)from, to);
+		__raw_writeb(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;

arch/arm64/kernel/machine_kexec.c

@@ -18,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
+#include <asm/daifflags.h>
 #include <asm/memory.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
@@ -195,8 +196,7 @@ void machine_kexec(struct kimage *kimage)
 
 	pr_info("Bye!\n");
 
-	/* Disable all DAIF exceptions. */
-	asm volatile ("msr daifset, #0xf" : : : "memory");
+	local_daif_mask();
 
 	/*
 	 * cpu_soft_restart will shutdown the MMU, disable data caches, then

arch/arm64/kernel/process.c

@@ -49,6 +49,7 @@
 #include <linux/notifier.h>
 #include <trace/events/power.h>
 #include <linux/percpu.h>
+#include <linux/thread_info.h>
 
 #include <asm/alternative.h>
 #include <asm/compat.h>
@@ -170,6 +171,39 @@ void machine_restart(char *cmd)
 	while (1);
 }
 
+static void print_pstate(struct pt_regs *regs)
+{
+	u64 pstate = regs->pstate;
+
+	if (compat_user_mode(regs)) {
+		printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c)\n",
+			pstate,
+			pstate & COMPAT_PSR_N_BIT ? 'N' : 'n',
+			pstate & COMPAT_PSR_Z_BIT ? 'Z' : 'z',
+			pstate & COMPAT_PSR_C_BIT ? 'C' : 'c',
+			pstate & COMPAT_PSR_V_BIT ? 'V' : 'v',
+			pstate & COMPAT_PSR_Q_BIT ? 'Q' : 'q',
+			pstate & COMPAT_PSR_T_BIT ? "T32" : "A32",
+			pstate & COMPAT_PSR_E_BIT ? "BE" : "LE",
+			pstate & COMPAT_PSR_A_BIT ? 'A' : 'a',
+			pstate & COMPAT_PSR_I_BIT ? 'I' : 'i',
+			pstate & COMPAT_PSR_F_BIT ? 'F' : 'f');
+	} else {
+		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n",
+			pstate,
+			pstate & PSR_N_BIT ? 'N' : 'n',
+			pstate & PSR_Z_BIT ? 'Z' : 'z',
+			pstate & PSR_C_BIT ? 'C' : 'c',
+			pstate & PSR_V_BIT ? 'V' : 'v',
+			pstate & PSR_D_BIT ? 'D' : 'd',
+			pstate & PSR_A_BIT ? 'A' : 'a',
+			pstate & PSR_I_BIT ? 'I' : 'i',
+			pstate & PSR_F_BIT ? 'F' : 'f',
+			pstate & PSR_PAN_BIT ? '+' : '-',
+			pstate & PSR_UAO_BIT ? '+' : '-');
+	}
+}
+
 void __show_regs(struct pt_regs *regs)
 {
 	int i, top_reg;
@@ -186,10 +220,9 @@ void __show_regs(struct pt_regs *regs)
 	}
 
 	show_regs_print_info(KERN_DEFAULT);
-	print_symbol("PC is at %s\n", instruction_pointer(regs));
-	print_symbol("LR is at %s\n", lr);
-	printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
-	       regs->pc, lr, regs->pstate);
+	print_pstate(regs);
+	print_symbol("pc : %s\n", regs->pc);
+	print_symbol("lr : %s\n", lr);
 	printk("sp : %016llx\n", sp);
 
 	i = top_reg;
@@ -241,11 +274,27 @@ void release_thread(struct task_struct *dead_task)
 {
 }
 
+void arch_release_task_struct(struct task_struct *tsk)
+{
+	fpsimd_release_task(tsk);
+}
+
+/*
+ * src and dst may temporarily have aliased sve_state after task_struct
+ * is copied.  We cannot fix this properly here, because src may have
+ * live SVE state and dst's thread_info may not exist yet, so tweaking
+ * either src's or dst's TIF_SVE is not safe.
+ *
+ * The unaliasing is done in copy_thread() instead.  This works because
+ * dst is not schedulable or traceable until both of these functions
+ * have been called.
+ */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	if (current->mm)
 		fpsimd_preserve_current_state();
 	*dst = *src;
+
 	return 0;
 }
 
@@ -258,6 +307,13 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
+	/*
+	 * Unalias p->thread.sve_state (if any) from the parent task
+	 * and disable discard SVE state for p:
+	 */
+	clear_tsk_thread_flag(p, TIF_SVE);
+	p->thread.sve_state = NULL;
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;

arch/arm64/kernel/ptrace.c

@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/signal.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
@@ -40,6 +41,7 @@
 #include <linux/elf.h>
 
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/stacktrace.h>
@@ -618,17 +620,56 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 /*
  * TODO: update fp accessors for lazy context switching (sync/flush hwstate)
  */
-static int fpr_get(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+static int __fpr_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf, unsigned int start_pos)
 {
 	struct user_fpsimd_state *uregs;
+
+	sve_sync_to_fpsimd(target);
+
 	uregs = &target->thread.fpsimd_state.user_fpsimd;
 
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs,
+				   start_pos, start_pos + sizeof(*uregs));
+}
+
+static int fpr_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
 	if (target == current)
 		fpsimd_preserve_current_state();
 
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, -1);
+	return __fpr_get(target, regset, pos, count, kbuf, ubuf, 0);
+}
+
+static int __fpr_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf,
+		     unsigned int start_pos)
+{
+	int ret;
+	struct user_fpsimd_state newstate;
+
+	/*
+	 * Ensure target->thread.fpsimd_state is up to date, so that a
+	 * short copyin can't resurrect stale data.
+	 */
+	sve_sync_to_fpsimd(target);
+
+	newstate = target->thread.fpsimd_state.user_fpsimd;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate,
+				 start_pos, start_pos + sizeof(newstate));
+	if (ret)
+		return ret;
+
+	target->thread.fpsimd_state.user_fpsimd = newstate;
+
+	return ret;
 }
 
 static int fpr_set(struct task_struct *target, const struct user_regset *regset,
@@ -636,15 +677,14 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_fpsimd_state newstate =
-		target->thread.fpsimd_state.user_fpsimd;
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
+	ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0);
 	if (ret)
 		return ret;
 
-	target->thread.fpsimd_state.user_fpsimd = newstate;
+	sve_sync_from_fpsimd_zeropad(target);
 	fpsimd_flush_task_state(target);
+
 	return ret;
 }
 
@@ -702,6 +742,215 @@ static int system_call_set(struct task_struct *target,
 	return ret;
 }
 
+#ifdef CONFIG_ARM64_SVE
+
+static void sve_init_header_from_task(struct user_sve_header *header,
+				      struct task_struct *target)
+{
+	unsigned int vq;
+
+	memset(header, 0, sizeof(*header));
+
+	header->flags = test_tsk_thread_flag(target, TIF_SVE) ?
+		SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD;
+	if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
+		header->flags |= SVE_PT_VL_INHERIT;
+
+	header->vl = target->thread.sve_vl;
+	vq = sve_vq_from_vl(header->vl);
+
+	header->max_vl = sve_max_vl;
+	if (WARN_ON(!sve_vl_valid(sve_max_vl)))
+		header->max_vl = header->vl;
+
+	header->size = SVE_PT_SIZE(vq, header->flags);
+	header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),
+				      SVE_PT_REGS_SVE);
+}
+
+static unsigned int sve_size_from_header(struct user_sve_header const *header)
+{
+	return ALIGN(header->size, SVE_VQ_BYTES);
+}
+
+static unsigned int sve_get_size(struct task_struct *target,
+				 const struct user_regset *regset)
+{
+	struct user_sve_header header;
+
+	if (!system_supports_sve())
+		return 0;
+
+	sve_init_header_from_task(&header, target);
+	return sve_size_from_header(&header);
+}
+
+static int sve_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
+	int ret;
+	struct user_sve_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	/* Header */
+	sve_init_header_from_task(&header, target);
+	vq = sve_vq_from_vl(header.vl);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &header,
+				  0, sizeof(header));
+	if (ret)
+		return ret;
+
+	if (target == current)
+		fpsimd_preserve_current_state();
+
+	/* Registers: FPSIMD-only case */
+
+	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
+	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD)
+		return __fpr_get(target, regset, pos, count, kbuf, ubuf,
+				 SVE_PT_FPSIMD_OFFSET);
+
+	/* Otherwise: full SVE case */
+
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+	start = SVE_PT_SVE_OFFSET;
+	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  target->thread.sve_state,
+				  start, end);
+	if (ret)
+		return ret;
+
+	start = end;
+	end = SVE_PT_SVE_FPSR_OFFSET(vq);
+	ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+				       start, end);
+	if (ret)
+		return ret;
+
+	/*
+	 * Copy fpsr, and fpcr which must follow contiguously in
+	 * struct fpsimd_state:
+	 */
+	start = end;
+	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpsimd_state.fpsr,
+				  start, end);
+	if (ret)
+		return ret;
+
+	start = end;
+	end = sve_size_from_header(&header);
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					start, end);
+}
+
+static int sve_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct user_sve_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	/* Header */
+	if (count < sizeof(header))
+		return -EINVAL;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header,
+				 0, sizeof(header));
+	if (ret)
+		goto out;
+
+	/*
+	 * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by
+	 * sve_set_vector_length(), which will also validate them for us:
+	 */
+	ret = sve_set_vector_length(target, header.vl,
+		((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
+	if (ret)
+		goto out;
+
+	/* Actual VL set may be less than the user asked for: */
+	vq = sve_vq_from_vl(target->thread.sve_vl);
+
+	/* Registers: FPSIMD-only case */
+
+	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
+	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) {
+		ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
+				SVE_PT_FPSIMD_OFFSET);
+		clear_tsk_thread_flag(target, TIF_SVE);
+		goto out;
+	}
+
+	/* Otherwise: full SVE case */
+
+	/*
+	 * If setting a different VL from the requested VL and there is
+	 * register data, the data layout will be wrong: don't even
+	 * try to set the registers in this case.
+	 */
+	if (count && vq != sve_vq_from_vl(header.vl)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	sve_alloc(target);
+
+	/*
+	 * Ensure target->thread.sve_state is up to date with target's
+	 * FPSIMD regs, so that a short copyin leaves trailing registers
+	 * unmodified.
+	 */
+	fpsimd_sync_to_sve(target);
+	set_tsk_thread_flag(target, TIF_SVE);
+
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+	start = SVE_PT_SVE_OFFSET;
+	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 target->thread.sve_state,
+				 start, end);
+	if (ret)
+		goto out;
+
+	start = end;
+	end = SVE_PT_SVE_FPSR_OFFSET(vq);
+	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					start, end);
+	if (ret)
+		goto out;
+
+	/*
+	 * Copy fpsr, and fpcr which must follow contiguously in
+	 * struct fpsimd_state:
+	 */
+	start = end;
+	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.fpsimd_state.fpsr,
+				 start, end);
+
+out:
+	fpsimd_flush_task_state(target);
+	return ret;
+}
+
+#endif /* CONFIG_ARM64_SVE */
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -711,6 +960,9 @@ enum aarch64_regset {
 	REGSET_HW_WATCH,
 #endif
 	REGSET_SYSTEM_CALL,
+#ifdef CONFIG_ARM64_SVE
+	REGSET_SVE,
+#endif
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -768,6 +1020,18 @@ static const struct user_regset aarch64_regsets[] = {
 		.get = system_call_get,
 		.set = system_call_set,
 	},
+#ifdef CONFIG_ARM64_SVE
+	[REGSET_SVE] = { /* Scalable Vector Extension */
+		.core_note_type = NT_ARM_SVE,
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+				  SVE_VQ_BYTES),
+		.size = SVE_VQ_BYTES,
+		.align = SVE_VQ_BYTES,
+		.get = sve_get,
+		.set = sve_set,
+		.get_size = sve_get_size,
+	},
+#endif
 };
 
 static const struct user_regset_view user_aarch64_view = {

arch/arm64/kernel/setup.c

@@ -23,7 +23,6 @@
 #include <linux/stddef.h>
 #include <linux/ioport.h>
 #include <linux/delay.h>
-#include <linux/utsname.h>
 #include <linux/initrd.h>
 #include <linux/console.h>
 #include <linux/cache.h>
@@ -48,6 +47,7 @@
 #include <asm/fixmap.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/daifflags.h>
 #include <asm/elf.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -103,7 +103,8 @@ void __init smp_setup_processor_id(void)
 	 * access percpu variable inside lock_release
 	 */
 	set_my_cpu_offset(0);
-	pr_info("Booting Linux on physical CPU 0x%lx\n", (unsigned long)mpidr);
+	pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n",
+		(unsigned long)mpidr, read_cpuid_id());
 }
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
@@ -244,9 +245,6 @@ u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
 {
-	pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
-
-	sprintf(init_utsname()->machine, UTS_MACHINE);
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
 	init_mm.end_data   = (unsigned long) _edata;
@@ -262,10 +260,11 @@ void __init setup_arch(char **cmdline_p)
 	parse_early_param();
 
 	/*
-	 *  Unmask asynchronous aborts after bringing up possible earlycon.
-	 * (Report possible System Errors once we can report this occurred)
+	 * Unmask asynchronous aborts and fiq after bringing up possible
+	 * earlycon. (Report possible System Errors once we can report this
+	 * occurred).
 	 */
-	local_async_enable();
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
 
 	/*
 	 * TTBR0 is only used for the identity mapping at this stage. Make it

arch/arm64/kernel/signal.c

@@ -31,6 +31,7 @@
 #include <linux/ratelimit.h>
 #include <linux/syscalls.h>
 
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -63,6 +64,7 @@ struct rt_sigframe_user_layout {
 
 	unsigned long fpsimd_offset;
 	unsigned long esr_offset;
+	unsigned long sve_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
 };
@@ -179,9 +181,6 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
 	int err;
 
-	/* dump the hardware registers to the fpsimd_state structure */
-	fpsimd_preserve_current_state();
-
 	/* copy the FP and status/control registers */
 	err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
 	__put_user_error(fpsimd->fpsr, &ctx->fpsr, err);
@@ -214,6 +213,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpsr, &ctx->fpsr, err);
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
+	clear_thread_flag(TIF_SVE);
+
 	/* load the hardware registers from the fpsimd_state structure */
 	if (!err)
 		fpsimd_update_current_state(&fpsimd);
@@ -221,10 +222,118 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	return err ? -EFAULT : 0;
 }
 
+
 struct user_ctxs {
 	struct fpsimd_context __user *fpsimd;
+	struct sve_context __user *sve;
 };
 
+#ifdef CONFIG_ARM64_SVE
+
+static int preserve_sve_context(struct sve_context __user *ctx)
+{
+	int err = 0;
+	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+	unsigned int vl = current->thread.sve_vl;
+	unsigned int vq = 0;
+
+	if (test_thread_flag(TIF_SVE))
+		vq = sve_vq_from_vl(vl);
+
+	memset(reserved, 0, sizeof(reserved));
+
+	__put_user_error(SVE_MAGIC, &ctx->head.magic, err);
+	__put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16),
+			 &ctx->head.size, err);
+	__put_user_error(vl, &ctx->vl, err);
+	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+	if (vq) {
+		/*
+		 * This assumes that the SVE state has already been saved to
+		 * the task struct by calling preserve_fpsimd_context().
+		 */
+		err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET,
+				      current->thread.sve_state,
+				      SVE_SIG_REGS_SIZE(vq));
+	}
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_sve_fpsimd_context(struct user_ctxs *user)
+{
+	int err;
+	unsigned int vq;
+	struct fpsimd_state fpsimd;
+	struct sve_context sve;
+
+	if (__copy_from_user(&sve, user->sve, sizeof(sve)))
+		return -EFAULT;
+
+	if (sve.vl != current->thread.sve_vl)
+		return -EINVAL;
+
+	if (sve.head.size <= sizeof(*user->sve)) {
+		clear_thread_flag(TIF_SVE);
+		goto fpsimd_only;
+	}
+
+	vq = sve_vq_from_vl(sve.vl);
+
+	if (sve.head.size < SVE_SIG_CONTEXT_SIZE(vq))
+		return -EINVAL;
+
+	/*
+	 * Careful: we are about __copy_from_user() directly into
+	 * thread.sve_state with preemption enabled, so protection is
+	 * needed to prevent a racing context switch from writing stale
+	 * registers back over the new data.
+	 */
+
+	fpsimd_flush_task_state(current);
+	barrier();
+	/* From now, fpsimd_thread_switch() won't clear TIF_FOREIGN_FPSTATE */
+
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+	barrier();
+	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
+
+	sve_alloc(current);
+	err = __copy_from_user(current->thread.sve_state,
+			       (char __user const *)user->sve +
+					SVE_SIG_REGS_OFFSET,
+			       SVE_SIG_REGS_SIZE(vq));
+	if (err)
+		return -EFAULT;
+
+	set_thread_flag(TIF_SVE);
+
+fpsimd_only:
+	/* copy the FP and status/control registers */
+	/* restore_sigframe() already checked that user->fpsimd != NULL. */
+	err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs,
+			       sizeof(fpsimd.vregs));
+	__get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err);
+	__get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err);
+
+	/* load the hardware registers from the fpsimd_state structure */
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
+
+	return err ? -EFAULT : 0;
+}
+
+#else /* ! CONFIG_ARM64_SVE */
+
+/* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_sve_context(void __user *ctx);
+extern int restore_sve_fpsimd_context(struct user_ctxs *user);
+
+#endif /* ! CONFIG_ARM64_SVE */
+
+
 static int parse_user_sigframe(struct user_ctxs *user,
 			       struct rt_sigframe __user *sf)
 {
@@ -237,6 +346,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	char const __user *const sfp = (char const __user *)sf;
 
 	user->fpsimd = NULL;
+	user->sve = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -287,6 +397,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			/* ignore */
 			break;
 
+		case SVE_MAGIC:
+			if (!system_supports_sve())
+				goto invalid;
+
+			if (user->sve)
+				goto invalid;
+
+			if (size < sizeof(*user->sve))
+				goto invalid;
+
+			user->sve = (struct sve_context __user *)head;
+			break;
+
 		case EXTRA_MAGIC:
 			if (have_extra_context)
 				goto invalid;
@@ -343,6 +466,10 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			 */
 			offset = 0;
 			limit = extra_size;
+
+			if (!access_ok(VERIFY_READ, base, limit))
+				goto invalid;
+
 			continue;
 
 		default:
@@ -359,9 +486,6 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	}
 
 done:
-	if (!user->fpsimd)
-		goto invalid;
-
 	return 0;
 
 invalid:
@@ -395,8 +519,19 @@ static int restore_sigframe(struct pt_regs *regs,
 	if (err == 0)
 		err = parse_user_sigframe(&user, sf);
 
-	if (err == 0)
-		err = restore_fpsimd_context(user.fpsimd);
+	if (err == 0) {
+		if (!user.fpsimd)
+			return -EINVAL;
+
+		if (user.sve) {
+			if (!system_supports_sve())
+				return -EINVAL;
+
+			err = restore_sve_fpsimd_context(&user);
+		} else {
+			err = restore_fpsimd_context(user.fpsimd);
+		}
+	}
 
 	return err;
 }
@@ -455,6 +590,18 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 			return err;
 	}
 
+	if (system_supports_sve()) {
+		unsigned int vq = 0;
+
+		if (test_thread_flag(TIF_SVE))
+			vq = sve_vq_from_vl(current->thread.sve_vl);
+
+		err = sigframe_alloc(user, &user->sve_offset,
+				     SVE_SIG_CONTEXT_SIZE(vq));
+		if (err)
+			return err;
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -496,6 +643,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
 	}
 
+	/* Scalable Vector Extension state, if present */
+	if (system_supports_sve() && err == 0 && user->sve_offset) {
+		struct sve_context __user *sve_ctx =
+			apply_user_offset(user, user->sve_offset);
+		err |= preserve_sve_context(sve_ctx);
+	}
+
 	if (err == 0 && user->extra_offset) {
 		char __user *sfp = (char __user *)user->sigframe;
 		char __user *userp =
@@ -595,6 +749,8 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 	struct rt_sigframe __user *frame;
 	int err = 0;
 
+	fpsimd_signal_preserve_current_state();
+
 	if (get_sigframe(&user, ksig, regs))
 		return 1;
 
@@ -756,9 +912,12 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		addr_limit_user_check();
 
 		if (thread_flags & _TIF_NEED_RESCHED) {
+			/* Unmask Debug and SError for the next task */
+			local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
 			schedule();
 		} else {
-			local_irq_enable();
+			local_daif_restore(DAIF_PROCCTX);
 
 			if (thread_flags & _TIF_UPROBE)
 				uprobe_notify_resume(regs);
@@ -775,7 +934,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 				fpsimd_restore_current_state();
 		}
 
-		local_irq_disable();
+		local_daif_mask();
 		thread_flags = READ_ONCE(current_thread_info()->flags);
 	} while (thread_flags & _TIF_WORK_MASK);
 }

arch/arm64/kernel/signal32.c

@@ -239,7 +239,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * Note that this also saves V16-31, which aren't visible
 	 * in AArch32.
 	 */
-	fpsimd_preserve_current_state();
+	fpsimd_signal_preserve_current_state();
 
 	/* Place structure header on the stack */
 	__put_user_error(magic, &frame->magic, err);

arch/arm64/kernel/smp.c

@@ -47,6 +47,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
+#include <asm/daifflags.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
 #include <asm/pgtable.h>
@@ -216,6 +217,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
  */
 asmlinkage void secondary_start_kernel(void)
 {
+	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu;
 
@@ -265,14 +267,14 @@ asmlinkage void secondary_start_kernel(void)
 	 * the CPU migration code to notice that the CPU is online
 	 * before we continue.
 	 */
-	pr_info("CPU%u: Booted secondary processor [%08x]\n",
-					 cpu, read_cpuid_id());
+	pr_info("CPU%u: Booted secondary processor 0x%010lx [0x%08x]\n",
+					 cpu, (unsigned long)mpidr,
+					 read_cpuid_id());
 	update_cpu_boot_status(CPU_BOOT_SUCCESS);
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	local_irq_enable();
-	local_async_enable();
+	local_daif_restore(DAIF_PROCCTX);
 
 	/*
 	 * OK, it's off to the idle thread for us
@@ -368,10 +370,6 @@ void __cpu_die(unsigned int cpu)
 /*
  * Called from the idle thread for the CPU which has been shutdown.
  *
- * Note that we disable IRQs here, but do not re-enable them
- * before returning to the caller. This is also the behaviour
- * of the other hotplug-cpu capable cores, so presumably coming
- * out of idle fixes this.
  */
 void cpu_die(void)
 {
@@ -379,7 +377,7 @@ void cpu_die(void)
 
 	idle_task_exit();
 
-	local_irq_disable();
+	local_daif_mask();
 
 	/* Tell __cpu_die() that this CPU is now safe to dispose of */
 	(void)cpu_report_death();
@@ -837,7 +835,7 @@ static void ipi_cpu_stop(unsigned int cpu)
 {
 	set_cpu_online(cpu, false);
 
-	local_irq_disable();
+	local_daif_mask();
 
 	while (1)
 		cpu_relax();

arch/arm64/kernel/suspend.c

@@ -5,6 +5,7 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exec.h>
 #include <asm/pgtable.h>
@@ -12,7 +13,6 @@
 #include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
-#include <asm/tlbflush.h>
 
 /*
  * This is allocated by cpu_suspend_init(), and used to store a pointer to
@@ -58,7 +58,7 @@ void notrace __cpu_suspend_exit(void)
 	/*
 	 * Restore HW breakpoint registers to sane values
 	 * before debug exceptions are possibly reenabled
-	 * through local_dbg_restore.
+	 * by cpu_suspend()s local_daif_restore() call.
 	 */
 	if (hw_breakpoint_restore)
 		hw_breakpoint_restore(cpu);
@@ -82,7 +82,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * updates to mdscr register (saved and restored along with
 	 * general purpose registers) from kernel debuggers.
 	 */
-	local_dbg_save(flags);
+	flags = local_daif_save();
 
 	/*
 	 * Function graph tracer state gets incosistent when the kernel
@@ -115,7 +115,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * restored, so from this point onwards, debugging is fully
 	 * renabled if it was enabled when core started shutdown.
 	 */
-	local_dbg_restore(flags);
+	local_daif_restore(flags);
 
 	return ret;
 }

arch/arm64/kernel/traps.c

@@ -38,6 +38,7 @@
 
 #include <asm/atomic.h>
 #include <asm/bug.h>
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/insn.h>
@@ -58,55 +59,9 @@ static const char *handler[]= {
 
 int show_unhandled_signals = 1;
 
-/*
- * Dump out the contents of some kernel memory nicely...
- */
-static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
-		     unsigned long top)
-{
-	unsigned long first;
-	mm_segment_t fs;
-	int i;
-
-	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.
-	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-
-	printk("%s%s(0x%016lx to 0x%016lx)\n", lvl, str, bottom, top);
-
-	for (first = bottom & ~31; first < top; first += 32) {
-		unsigned long p;
-		char str[sizeof(" 12345678") * 8 + 1];
-
-		memset(str, ' ', sizeof(str));
-		str[sizeof(str) - 1] = '\0';
-
-		for (p = first, i = 0; i < (32 / 8)
-					&& p < top; i++, p += 8) {
-			if (p >= bottom && p < top) {
-				unsigned long val;
-
-				if (__get_user(val, (unsigned long *)p) == 0)
-					sprintf(str + i * 17, " %016lx", val);
-				else
-					sprintf(str + i * 17, " ????????????????");
-			}
-		}
-		printk("%s%04lx:%s\n", lvl, first & 0xffff, str);
-	}
-
-	set_fs(fs);
-}
-
 static void dump_backtrace_entry(unsigned long where)
 {
-	/*
-	 * Note that 'where' can have a physical address, but it's not handled.
-	 */
-	print_ip_sym(where);
+	printk(" %pS\n", (void *)where);
 }
 
 static void __dump_instr(const char *lvl, struct pt_regs *regs)
@@ -171,10 +126,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 
 	skip = !!regs;
 	printk("Call trace:\n");
-	while (1) {
-		unsigned long stack;
-		int ret;
-
+	do {
 		/* skip until specified stack frame */
 		if (!skip) {
 			dump_backtrace_entry(frame.pc);
@@ -189,17 +141,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 			 */
 			dump_backtrace_entry(regs->pc);
 		}
-		ret = unwind_frame(tsk, &frame);
-		if (ret < 0)
-			break;
-		if (in_entry_text(frame.pc)) {
-			stack = frame.fp - offsetof(struct pt_regs, stackframe);
-
-			if (on_accessible_stack(tsk, stack))
-				dump_mem("", "Exception stack", stack,
-					 stack + sizeof(struct pt_regs));
-		}
-	}
+	} while (!unwind_frame(tsk, &frame));
 
 	put_task_stack(tsk);
 }
@@ -293,6 +235,17 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 	}
 }
 
+void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
+{
+	regs->pc += size;
+
+	/*
+	 * If we were single stepping, we want to get the step exception after
+	 * we return from the trap.
+	 */
+	user_fastforward_single_step(current);
+}
+
 static LIST_HEAD(undef_hook);
 static DEFINE_RAW_SPINLOCK(undef_lock);
 
@@ -358,8 +311,8 @@ exit:
 	return fn ? fn(regs, instr) : 1;
 }
 
-static void force_signal_inject(int signal, int code, struct pt_regs *regs,
-				unsigned long address)
+void force_signal_inject(int signal, int code, struct pt_regs *regs,
+			 unsigned long address)
 {
 	siginfo_t info;
 	void __user *pc = (void __user *)instruction_pointer(regs);
@@ -373,7 +326,7 @@ static void force_signal_inject(int signal, int code, struct pt_regs *regs,
 		desc = "illegal memory access";
 		break;
 	default:
-		desc = "bad mode";
+		desc = "unknown or unrecoverable error";
 		break;
 	}
 
@@ -480,7 +433,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 	if (ret)
 		arm64_notify_segfault(regs, address);
 	else
-		regs->pc += 4;
+		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -490,7 +443,7 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 
 	pt_regs_write_reg(regs, rt, val);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -498,7 +451,7 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
 
 	pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -506,7 +459,7 @@ static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
 
 	pt_regs_write_reg(regs, rt, arch_timer_get_rate());
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 struct sys64_hook {
@@ -603,6 +556,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_HVC64]		= "HVC (AArch64)",
 	[ESR_ELx_EC_SMC64]		= "SMC (AArch64)",
 	[ESR_ELx_EC_SYS64]		= "MSR/MRS (AArch64)",
+	[ESR_ELx_EC_SVE]		= "SVE",
 	[ESR_ELx_EC_IMP_DEF]		= "EL3 IMP DEF",
 	[ESR_ELx_EC_IABT_LOW]		= "IABT (lower EL)",
 	[ESR_ELx_EC_IABT_CUR]		= "IABT (current EL)",
@@ -642,7 +596,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 		esr_get_class_string(esr));
 
 	die("Oops - bad mode", regs, 0);
-	local_irq_disable();
+	local_daif_mask();
 	panic("bad mode");
 }
 
@@ -708,6 +662,19 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs)
 }
 #endif
 
+asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+{
+	nmi_enter();
+
+	console_verbose();
+
+	pr_crit("SError Interrupt on CPU%d, code 0x%08x -- %s\n",
+		smp_processor_id(), esr, esr_get_class_string(esr));
+	__show_regs(regs);
+
+	panic("Asynchronous SError Interrupt");
+}
+
 void __pte_error(const char *file, int line, unsigned long val)
 {
 	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
@@ -761,7 +728,7 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr)
 	}
 
 	/* If thread survives, skip over the BUG instruction and continue: */
-	regs->pc += AARCH64_INSN_SIZE;	/* skip BRK and resume */
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 	return DBG_HOOK_HANDLED;
 }
 

arch/arm64/kernel/vdso/gettimeofday.S

@@ -309,7 +309,7 @@ ENTRY(__kernel_clock_getres)
 	b.ne	4f
 	ldr	x2, 6f
 2:
-	cbz	w1, 3f
+	cbz	x1, 3f
 	stp	xzr, x2, [x1]
 
 3:	/* res == NULL. */

arch/arm64/kvm/handle_exit.c

@@ -147,6 +147,13 @@ static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+static int handle_sve(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* Until SVE is supported for guests: */
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
@@ -160,6 +167,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_HVC64]	= handle_hvc,
 	[ESR_ELx_EC_SMC64]	= handle_smc,
 	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
+	[ESR_ELx_EC_SVE]	= handle_sve,
 	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,

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

@@ -65,16 +65,6 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-#define PMSCR_EL1		sys_reg(3, 0, 9, 9, 0)
-
-#define PMBLIMITR_EL1		sys_reg(3, 0, 9, 10, 0)
-#define PMBLIMITR_EL1_E		BIT(0)
-
-#define PMBIDR_EL1		sys_reg(3, 0, 9, 10, 7)
-#define PMBIDR_EL1_P		BIT(4)
-
-#define psb_csync()		asm volatile("hint #17")
-
 static void __hyp_text __debug_save_spe_vhe(u64 *pmscr_el1)
 {
 	/* The vcpu can run. but it can't hide. */
@@ -90,18 +80,18 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 		return;
 
 	/* Yes; is it owned by EL3? */
-	reg = read_sysreg_s(PMBIDR_EL1);
-	if (reg & PMBIDR_EL1_P)
+	reg = read_sysreg_s(SYS_PMBIDR_EL1);
+	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
 		return;
 
 	/* No; is the host actually using the thing? */
-	reg = read_sysreg_s(PMBLIMITR_EL1);
-	if (!(reg & PMBLIMITR_EL1_E))
+	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
+	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
 		return;
 
 	/* Yes; save the control register and disable data generation */
-	*pmscr_el1 = read_sysreg_s(PMSCR_EL1);
-	write_sysreg_s(0, PMSCR_EL1);
+	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
+	write_sysreg_s(0, SYS_PMSCR_EL1);
 	isb();
 
 	/* Now drain all buffered data to memory */
@@ -122,7 +112,7 @@ static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
 	isb();
 
 	/* Re-enable data generation */
-	write_sysreg_s(pmscr_el1, PMSCR_EL1);
+	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
 void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,

arch/arm64/kvm/hyp/switch.c

@@ -48,7 +48,7 @@ static void __hyp_text __activate_traps_vhe(void)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
-	val &= ~CPACR_EL1_FPEN;
+	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(__kvm_hyp_vector, vbar_el1);
@@ -59,7 +59,7 @@ static void __hyp_text __activate_traps_nvhe(void)
 	u64 val;
 
 	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ;
 	write_sysreg(val, cptr_el2);
 }
 
@@ -81,11 +81,17 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	 * it will cause an exception.
 	 */
 	val = vcpu->arch.hcr_el2;
+
 	if (!(val & HCR_RW) && system_supports_fpsimd()) {
 		write_sysreg(1 << 30, fpexc32_el2);
 		isb();
 	}
+
+	if (val & HCR_RW) /* for AArch64 only: */
+		val |= HCR_TID3; /* TID3: trap feature register accesses */
+
 	write_sysreg(val, hcr_el2);
+
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
 	/*
@@ -111,7 +117,7 @@ static void __hyp_text __deactivate_traps_vhe(void)
 
 	write_sysreg(mdcr_el2, mdcr_el2);
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
-	write_sysreg(CPACR_EL1_FPEN, cpacr_el1);
+	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
 }
 

arch/arm64/kvm/sys_regs.c

@@ -23,6 +23,7 @@
 #include <linux/bsearch.h>
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
+#include <linux/printk.h>
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
@@ -892,6 +893,146 @@ static bool access_cntp_cval(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+/* Read a sanitised cpufeature ID register by sys_reg_desc */
+static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
+{
+	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
+			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
+
+	if (id == SYS_ID_AA64PFR0_EL1) {
+		if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT))
+			pr_err_once("kvm [%i]: SVE unsupported for guests, suppressing\n",
+				    task_pid_nr(current));
+
+		val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+	}
+
+	return val;
+}
+
+/* cpufeature ID register access trap handlers */
+
+static bool __access_id_reg(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r,
+			    bool raz)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = read_id_reg(r, raz);
+	return true;
+}
+
+static bool access_id_reg(struct kvm_vcpu *vcpu,
+			  struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	return __access_id_reg(vcpu, p, r, false);
+}
+
+static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
+			      struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	return __access_id_reg(vcpu, p, r, true);
+}
+
+static int reg_from_user(u64 *val, const void __user *uaddr, u64 id);
+static int reg_to_user(void __user *uaddr, const u64 *val, u64 id);
+static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
+
+/*
+ * cpufeature ID register user accessors
+ *
+ * For now, these registers are immutable for userspace, so no values
+ * are stored, and for set_id_reg() we don't allow the effective value
+ * to be changed.
+ */
+static int __get_id_reg(const struct sys_reg_desc *rd, void __user *uaddr,
+			bool raz)
+{
+	const u64 id = sys_reg_to_index(rd);
+	const u64 val = read_id_reg(rd, raz);
+
+	return reg_to_user(uaddr, &val, id);
+}
+
+static int __set_id_reg(const struct sys_reg_desc *rd, void __user *uaddr,
+			bool raz)
+{
+	const u64 id = sys_reg_to_index(rd);
+	int err;
+	u64 val;
+
+	err = reg_from_user(&val, uaddr, id);
+	if (err)
+		return err;
+
+	/* This is what we mean by invariant: you can't change it. */
+	if (val != read_id_reg(rd, raz))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+		      const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	return __get_id_reg(rd, uaddr, false);
+}
+
+static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+		      const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	return __set_id_reg(rd, uaddr, false);
+}
+
+static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+			  const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	return __get_id_reg(rd, uaddr, true);
+}
+
+static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+			  const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	return __set_id_reg(rd, uaddr, true);
+}
+
+/* sys_reg_desc initialiser for known cpufeature ID registers */
+#define ID_SANITISED(name) {			\
+	SYS_DESC(SYS_##name),			\
+	.access	= access_id_reg,		\
+	.get_user = get_id_reg,			\
+	.set_user = set_id_reg,			\
+}
+
+/*
+ * sys_reg_desc initialiser for architecturally unallocated cpufeature ID
+ * register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2
+ * (1 <= crm < 8, 0 <= Op2 < 8).
+ */
+#define ID_UNALLOCATED(crm, op2) {			\
+	Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2),	\
+	.access = access_raz_id_reg,			\
+	.get_user = get_raz_id_reg,			\
+	.set_user = set_raz_id_reg,			\
+}
+
+/*
+ * sys_reg_desc initialiser for known ID registers that we hide from guests.
+ * For now, these are exposed just like unallocated ID regs: they appear
+ * RAZ for the guest.
+ */
+#define ID_HIDDEN(name) {			\
+	SYS_DESC(SYS_##name),			\
+	.access = access_raz_id_reg,		\
+	.get_user = get_raz_id_reg,		\
+	.set_user = set_raz_id_reg,		\
+}
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -944,6 +1085,84 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_DBGVCR32_EL2), NULL, reset_val, DBGVCR32_EL2, 0 },
 
 	{ SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 },
+
+	/*
+	 * ID regs: all ID_SANITISED() entries here must have corresponding
+	 * entries in arm64_ftr_regs[].
+	 */
+
+	/* AArch64 mappings of the AArch32 ID registers */
+	/* CRm=1 */
+	ID_SANITISED(ID_PFR0_EL1),
+	ID_SANITISED(ID_PFR1_EL1),
+	ID_SANITISED(ID_DFR0_EL1),
+	ID_HIDDEN(ID_AFR0_EL1),
+	ID_SANITISED(ID_MMFR0_EL1),
+	ID_SANITISED(ID_MMFR1_EL1),
+	ID_SANITISED(ID_MMFR2_EL1),
+	ID_SANITISED(ID_MMFR3_EL1),
+
+	/* CRm=2 */
+	ID_SANITISED(ID_ISAR0_EL1),
+	ID_SANITISED(ID_ISAR1_EL1),
+	ID_SANITISED(ID_ISAR2_EL1),
+	ID_SANITISED(ID_ISAR3_EL1),
+	ID_SANITISED(ID_ISAR4_EL1),
+	ID_SANITISED(ID_ISAR5_EL1),
+	ID_SANITISED(ID_MMFR4_EL1),
+	ID_UNALLOCATED(2,7),
+
+	/* CRm=3 */
+	ID_SANITISED(MVFR0_EL1),
+	ID_SANITISED(MVFR1_EL1),
+	ID_SANITISED(MVFR2_EL1),
+	ID_UNALLOCATED(3,3),
+	ID_UNALLOCATED(3,4),
+	ID_UNALLOCATED(3,5),
+	ID_UNALLOCATED(3,6),
+	ID_UNALLOCATED(3,7),
+
+	/* AArch64 ID registers */
+	/* CRm=4 */
+	ID_SANITISED(ID_AA64PFR0_EL1),
+	ID_SANITISED(ID_AA64PFR1_EL1),
+	ID_UNALLOCATED(4,2),
+	ID_UNALLOCATED(4,3),
+	ID_UNALLOCATED(4,4),
+	ID_UNALLOCATED(4,5),
+	ID_UNALLOCATED(4,6),
+	ID_UNALLOCATED(4,7),
+
+	/* CRm=5 */
+	ID_SANITISED(ID_AA64DFR0_EL1),
+	ID_SANITISED(ID_AA64DFR1_EL1),
+	ID_UNALLOCATED(5,2),
+	ID_UNALLOCATED(5,3),
+	ID_HIDDEN(ID_AA64AFR0_EL1),
+	ID_HIDDEN(ID_AA64AFR1_EL1),
+	ID_UNALLOCATED(5,6),
+	ID_UNALLOCATED(5,7),
+
+	/* CRm=6 */
+	ID_SANITISED(ID_AA64ISAR0_EL1),
+	ID_SANITISED(ID_AA64ISAR1_EL1),
+	ID_UNALLOCATED(6,2),
+	ID_UNALLOCATED(6,3),
+	ID_UNALLOCATED(6,4),
+	ID_UNALLOCATED(6,5),
+	ID_UNALLOCATED(6,6),
+	ID_UNALLOCATED(6,7),
+
+	/* CRm=7 */
+	ID_SANITISED(ID_AA64MMFR0_EL1),
+	ID_SANITISED(ID_AA64MMFR1_EL1),
+	ID_SANITISED(ID_AA64MMFR2_EL1),
+	ID_UNALLOCATED(7,3),
+	ID_UNALLOCATED(7,4),
+	ID_UNALLOCATED(7,5),
+	ID_UNALLOCATED(7,6),
+	ID_UNALLOCATED(7,7),
+
 	{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
 	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
@@ -1790,8 +2009,8 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	if (!r)
 		r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 
-	/* Not saved in the sys_reg array? */
-	if (r && !r->reg)
+	/* Not saved in the sys_reg array and not otherwise accessible? */
+	if (r && !(r->reg || r->get_user))
 		r = NULL;
 
 	return r;
@@ -1815,20 +2034,6 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 FUNCTION_INVARIANT(midr_el1)
 FUNCTION_INVARIANT(ctr_el0)
 FUNCTION_INVARIANT(revidr_el1)
-FUNCTION_INVARIANT(id_pfr0_el1)
-FUNCTION_INVARIANT(id_pfr1_el1)
-FUNCTION_INVARIANT(id_dfr0_el1)
-FUNCTION_INVARIANT(id_afr0_el1)
-FUNCTION_INVARIANT(id_mmfr0_el1)
-FUNCTION_INVARIANT(id_mmfr1_el1)
-FUNCTION_INVARIANT(id_mmfr2_el1)
-FUNCTION_INVARIANT(id_mmfr3_el1)
-FUNCTION_INVARIANT(id_isar0_el1)
-FUNCTION_INVARIANT(id_isar1_el1)
-FUNCTION_INVARIANT(id_isar2_el1)
-FUNCTION_INVARIANT(id_isar3_el1)
-FUNCTION_INVARIANT(id_isar4_el1)
-FUNCTION_INVARIANT(id_isar5_el1)
 FUNCTION_INVARIANT(clidr_el1)
 FUNCTION_INVARIANT(aidr_el1)
 
@@ -1836,20 +2041,6 @@ FUNCTION_INVARIANT(aidr_el1)
 static struct sys_reg_desc invariant_sys_regs[] = {
 	{ SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },
 	{ SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 },
-	{ SYS_DESC(SYS_ID_PFR0_EL1), NULL, get_id_pfr0_el1 },
-	{ SYS_DESC(SYS_ID_PFR1_EL1), NULL, get_id_pfr1_el1 },
-	{ SYS_DESC(SYS_ID_DFR0_EL1), NULL, get_id_dfr0_el1 },
-	{ SYS_DESC(SYS_ID_AFR0_EL1), NULL, get_id_afr0_el1 },
-	{ SYS_DESC(SYS_ID_MMFR0_EL1), NULL, get_id_mmfr0_el1 },
-	{ SYS_DESC(SYS_ID_MMFR1_EL1), NULL, get_id_mmfr1_el1 },
-	{ SYS_DESC(SYS_ID_MMFR2_EL1), NULL, get_id_mmfr2_el1 },
-	{ SYS_DESC(SYS_ID_MMFR3_EL1), NULL, get_id_mmfr3_el1 },
-	{ SYS_DESC(SYS_ID_ISAR0_EL1), NULL, get_id_isar0_el1 },
-	{ SYS_DESC(SYS_ID_ISAR1_EL1), NULL, get_id_isar1_el1 },
-	{ SYS_DESC(SYS_ID_ISAR2_EL1), NULL, get_id_isar2_el1 },
-	{ SYS_DESC(SYS_ID_ISAR3_EL1), NULL, get_id_isar3_el1 },
-	{ SYS_DESC(SYS_ID_ISAR4_EL1), NULL, get_id_isar4_el1 },
-	{ SYS_DESC(SYS_ID_ISAR5_EL1), NULL, get_id_isar5_el1 },
 	{ SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 },
 	{ SYS_DESC(SYS_AIDR_EL1), NULL, get_aidr_el1 },
 	{ SYS_DESC(SYS_CTR_EL0), NULL, get_ctr_el0 },
@@ -2079,12 +2270,31 @@ static bool copy_reg_to_user(const struct sys_reg_desc *reg, u64 __user **uind)
 	return true;
 }
 
+static int walk_one_sys_reg(const struct sys_reg_desc *rd,
+			    u64 __user **uind,
+			    unsigned int *total)
+{
+	/*
+	 * Ignore registers we trap but don't save,
+	 * and for which no custom user accessor is provided.
+	 */
+	if (!(rd->reg || rd->get_user))
+		return 0;
+
+	if (!copy_reg_to_user(rd, uind))
+		return -EFAULT;
+
+	(*total)++;
+	return 0;
+}
+
 /* Assumed ordered tables, see kvm_sys_reg_table_init. */
 static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 {
 	const struct sys_reg_desc *i1, *i2, *end1, *end2;
 	unsigned int total = 0;
 	size_t num;
+	int err;
 
 	/* We check for duplicates here, to allow arch-specific overrides. */
 	i1 = get_target_table(vcpu->arch.target, true, &num);
@@ -2098,21 +2308,13 @@ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 	while (i1 || i2) {
 		int cmp = cmp_sys_reg(i1, i2);
 		/* target-specific overrides generic entry. */
-		if (cmp <= 0) {
-			/* Ignore registers we trap but don't save. */
-			if (i1->reg) {
-				if (!copy_reg_to_user(i1, &uind))
-					return -EFAULT;
-				total++;
-			}
-		} else {
-			/* Ignore registers we trap but don't save. */
-			if (i2->reg) {
-				if (!copy_reg_to_user(i2, &uind))
-					return -EFAULT;
-				total++;
-			}
-		}
+		if (cmp <= 0)
+			err = walk_one_sys_reg(i1, &uind, &total);
+		else
+			err = walk_one_sys_reg(i2, &uind, &total);
+
+		if (err)
+			return err;
 
 		if (cmp <= 0 && ++i1 == end1)
 			i1 = NULL;

arch/arm64/lib/Makefile

@@ -3,7 +3,7 @@ lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
 		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
-		   strchr.o strrchr.o
+		   strchr.o strrchr.o tishift.o
 
 # Tell the compiler to treat all general purpose registers (with the
 # exception of the IP registers, which are already handled by the caller

arch/arm64/lib/delay.c

@@ -24,10 +24,28 @@
 #include <linux/module.h>
 #include <linux/timex.h>
 
+#include <clocksource/arm_arch_timer.h>
+
+#define USECS_TO_CYCLES(time_usecs)			\
+	xloops_to_cycles((time_usecs) * 0x10C7UL)
+
+static inline unsigned long xloops_to_cycles(unsigned long xloops)
+{
+	return (xloops * loops_per_jiffy * HZ) >> 32;
+}
+
 void __delay(unsigned long cycles)
 {
 	cycles_t start = get_cycles();
 
+	if (arch_timer_evtstrm_available()) {
+		const cycles_t timer_evt_period =
+			USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US);
+
+		while ((get_cycles() - start + timer_evt_period) < cycles)
+			wfe();
+	}
+
 	while ((get_cycles() - start) < cycles)
 		cpu_relax();
 }
@@ -35,10 +53,7 @@ EXPORT_SYMBOL(__delay);
 
 inline void __const_udelay(unsigned long xloops)
 {
-	unsigned long loops;
-
-	loops = xloops * loops_per_jiffy * HZ;
-	__delay(loops >> 32);
+	__delay(xloops_to_cycles(xloops));
 }
 EXPORT_SYMBOL(__const_udelay);
 

arch/arm64/lib/tishift.S

@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+ENTRY(__ashlti3)
+	cbz	x2, 1f
+	mov	x3, #64
+	sub	x3, x3, x2
+	cmp	x3, #0
+	b.le	2f
+	lsl	x1, x1, x2
+	lsr	x3, x0, x3
+	lsl	x2, x0, x2
+	orr	x1, x1, x3
+	mov	x0, x2
+1:
+	ret
+2:
+	neg	w1, w3
+	mov	x2, #0
+	lsl	x1, x0, x1
+	mov	x0, x2
+	ret
+ENDPROC(__ashlti3)
+
+ENTRY(__ashrti3)
+	cbz	x2, 3f
+	mov	x3, #64
+	sub	x3, x3, x2
+	cmp	x3, #0
+	b.le	4f
+	lsr	x0, x0, x2
+	lsl	x3, x1, x3
+	asr	x2, x1, x2
+	orr	x0, x0, x3
+	mov	x1, x2
+3:
+	ret
+4:
+	neg	w0, w3
+	asr	x2, x1, #63
+	asr	x0, x1, x0
+	mov	x1, x2
+	ret
+ENDPROC(__ashrti3)
+
+ENTRY(__lshrti3)
+	cbz	x2, 1f
+	mov	x3, #64
+	sub	x3, x3, x2
+	cmp	x3, #0
+	b.le	2f
+	lsr	x0, x0, x2
+	lsl	x3, x1, x3
+	lsr	x2, x1, x2
+	orr	x0, x0, x3
+	mov	x1, x2
+1:
+	ret
+2:
+	neg	w0, w3
+	mov	x2, #0
+	lsr	x0, x1, x0
+	mov	x1, x2
+	ret
+ENDPROC(__lshrti3)

arch/arm64/mm/dma-mapping.c

@@ -166,7 +166,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	/* create a coherent mapping */
 	page = virt_to_page(ptr);
 	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
-						   prot, NULL);
+						   prot, __builtin_return_address(0));
 	if (!coherent_ptr)
 		goto no_map;
 
@@ -303,8 +303,7 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
 			      unsigned long pfn, size_t size)
 {
 	int ret = -ENXIO;
-	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
-					PAGE_SHIFT;
+	unsigned long nr_vma_pages = vma_pages(vma);
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 

arch/arm64/mm/fault.c

@@ -105,13 +105,11 @@ static void data_abort_decode(unsigned int esr)
 		 (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
 }
 
-/*
- * Decode mem abort information
- */
 static void mem_abort_decode(unsigned int esr)
 {
 	pr_alert("Mem abort info:\n");
 
+	pr_alert("  ESR = 0x%08x\n", esr);
 	pr_alert("  Exception class = %s, IL = %u bits\n",
 		 esr_get_class_string(esr),
 		 (esr & ESR_ELx_IL) ? 32 : 16);
@@ -249,9 +247,6 @@ static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
 	return false;
 }
 
-/*
- * The kernel tried to access some page that wasn't present.
- */
 static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -264,9 +259,6 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
 		return;
 
-	/*
-	 * No handler, we'll have to terminate things with extreme prejudice.
-	 */
 	bust_spinlocks(1);
 
 	if (is_permission_fault(esr, regs, addr)) {
@@ -291,10 +283,6 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	do_exit(SIGKILL);
 }
 
-/*
- * Something tried to access memory that isn't in our memory map. User mode
- * accesses just cause a SIGSEGV
- */
 static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 			    unsigned int esr, unsigned int sig, int code,
 			    struct pt_regs *regs, int fault)
@@ -559,23 +547,6 @@ no_context:
 	return 0;
 }
 
-/*
- * First Level Translation Fault Handler
- *
- * We enter here because the first level page table doesn't contain a valid
- * entry for the address.
- *
- * If the address is in kernel space (>= TASK_SIZE), then we are probably
- * faulting in the vmalloc() area.
- *
- * If the init_task's first level page tables contains the relevant entry, we
- * copy the it to this task.  If not, we send the process a signal, fixup the
- * exception, or oops the kernel.
- *
- * NOTE! We MUST NOT take any locks for this case. We may be in an interrupt
- * or a critical region, and should only copy the information from the master
- * page table, nothing more.
- */
 static int __kprobes do_translation_fault(unsigned long addr,
 					  unsigned int esr,
 					  struct pt_regs *regs)
@@ -594,18 +565,11 @@ static int do_alignment_fault(unsigned long addr, unsigned int esr,
 	return 0;
 }
 
-/*
- * This abort handler always returns "fault".
- */
 static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
-	return 1;
+	return 1; /* "fault" */
 }
 
-/*
- * This abort handler deals with Synchronous External Abort.
- * It calls notifiers, and then returns "fault".
- */
 static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	struct siginfo info;
@@ -668,14 +632,14 @@ static const struct fault_info fault_info[] = {
 	{ do_sea,		SIGBUS,  0,		"level 1 (translation table walk)"	},
 	{ do_sea,		SIGBUS,  0,		"level 2 (translation table walk)"	},
 	{ do_sea,		SIGBUS,  0,		"level 3 (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"synchronous parity or ECC error" },
+	{ do_sea,		SIGBUS,  0,		"synchronous parity or ECC error" },	// Reserved when RAS is implemented
 	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_sea,		SIGBUS,  0,		"level 0 synchronous parity error (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"level 1 synchronous parity error (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"level 2 synchronous parity error (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"level 3 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 0 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
+	{ do_sea,		SIGBUS,  0,		"level 1 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
+	{ do_sea,		SIGBUS,  0,		"level 2 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
+	{ do_sea,		SIGBUS,  0,		"level 3 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
 	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
@@ -693,7 +657,7 @@ static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
 	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
-	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
+	{ do_bad,		SIGBUS,  0,		"Unsupported atomic hardware update fault"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
 	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
@@ -710,13 +674,6 @@ static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
 };
 
-/*
- * Handle Synchronous External Aborts that occur in a guest kernel.
- *
- * The return value will be zero if the SEA was successfully handled
- * and non-zero if there was an error processing the error or there was
- * no error to process.
- */
 int handle_guest_sea(phys_addr_t addr, unsigned int esr)
 {
 	int ret = -ENOENT;
@@ -727,9 +684,6 @@ int handle_guest_sea(phys_addr_t addr, unsigned int esr)
 	return ret;
 }
 
-/*
- * Dispatch a data abort to the relevant handler.
- */
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 					 struct pt_regs *regs)
 {
@@ -739,11 +693,14 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	if (!inf->fn(addr, esr, regs))
 		return;
 
-	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
-		 inf->name, esr, addr);
+	pr_alert("Unhandled fault: %s at 0x%016lx\n",
+		 inf->name, addr);
 
 	mem_abort_decode(esr);
 
+	if (!user_mode(regs))
+		show_pte(addr);
+
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;
@@ -751,9 +708,6 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	arm64_notify_die("", regs, &info, esr);
 }
 
-/*
- * Handle stack alignment exceptions.
- */
 asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 					   unsigned int esr,
 					   struct pt_regs *regs)

arch/arm64/mm/proc.S

@@ -109,10 +109,10 @@ ENTRY(cpu_do_resume)
 	/*
 	 * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking
 	 * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug
-	 * exception. Mask them until local_dbg_restore() in cpu_suspend()
+	 * exception. Mask them until local_daif_restore() in cpu_suspend()
 	 * resets them.
 	 */
-	disable_dbg
+	disable_daif
 	msr	mdscr_el1, x10
 
 	msr	sctlr_el1, x12
@@ -155,8 +155,7 @@ ENDPROC(cpu_do_switch_mm)
  * called by anything else. It can only be executed from a TTBR0 mapping.
  */
 ENTRY(idmap_cpu_replace_ttbr1)
-	mrs	x2, daif
-	msr	daifset, #0xf
+	save_and_disable_daif flags=x2
 
 	adrp	x1, empty_zero_page
 	msr	ttbr1_el1, x1
@@ -169,7 +168,7 @@ ENTRY(idmap_cpu_replace_ttbr1)
 	msr	ttbr1_el1, x0
 	isb
 
-	msr	daif, x2
+	restore_daif x2
 
 	ret
 ENDPROC(idmap_cpu_replace_ttbr1)

drivers/acpi/arm64/gtdt.c

@@ -199,7 +199,7 @@ static int __init gtdt_parse_timer_block(struct acpi_gtdt_timer_block *block,
 	struct acpi_gtdt_timer_entry *gtdt_frame;
 
 	if (!block->timer_count) {
-		pr_err(FW_BUG "GT block present, but frame count is zero.");
+		pr_err(FW_BUG "GT block present, but frame count is zero.\n");
 		return -ENODEV;
 	}
 

drivers/acpi/arm64/iort.c

@@ -88,8 +88,8 @@ static inline int iort_set_fwnode(struct acpi_iort_node *iort_node,
  *
  * Returns: fwnode_handle pointer on success, NULL on failure
  */
-static inline
-struct fwnode_handle *iort_get_fwnode(struct acpi_iort_node *node)
+static inline struct fwnode_handle *iort_get_fwnode(
+			struct acpi_iort_node *node)
 {
 	struct iort_fwnode *curr;
 	struct fwnode_handle *fwnode = NULL;
@@ -126,6 +126,31 @@ static inline void iort_delete_fwnode(struct acpi_iort_node *node)
 	spin_unlock(&iort_fwnode_lock);
 }
 
+/**
+ * iort_get_iort_node() - Retrieve iort_node associated with an fwnode
+ *
+ * @fwnode: fwnode associated with device to be looked-up
+ *
+ * Returns: iort_node pointer on success, NULL on failure
+ */
+static inline struct acpi_iort_node *iort_get_iort_node(
+			struct fwnode_handle *fwnode)
+{
+	struct iort_fwnode *curr;
+	struct acpi_iort_node *iort_node = NULL;
+
+	spin_lock(&iort_fwnode_lock);
+	list_for_each_entry(curr, &iort_fwnode_list, list) {
+		if (curr->fwnode == fwnode) {
+			iort_node = curr->iort_node;
+			break;
+		}
+	}
+	spin_unlock(&iort_fwnode_lock);
+
+	return iort_node;
+}
+
 typedef acpi_status (*iort_find_node_callback)
 	(struct acpi_iort_node *node, void *context);
 
@@ -306,9 +331,8 @@ static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 	return 0;
 }
 
-static
-struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
-					u32 *id_out, int index)
+static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
+					       u32 *id_out, int index)
 {
 	struct acpi_iort_node *parent;
 	struct acpi_iort_id_mapping *map;
@@ -332,7 +356,8 @@ struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 
 	if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) {
 		if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT ||
-		    node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) {
+		    node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX ||
+		    node->type == ACPI_IORT_NODE_SMMU_V3) {
 			*id_out = map->output_base;
 			return parent;
 		}
@@ -341,6 +366,47 @@ struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 	return NULL;
 }
 
+#if (ACPI_CA_VERSION > 0x20170929)
+static int iort_get_id_mapping_index(struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu_v3 *smmu;
+
+	switch (node->type) {
+	case ACPI_IORT_NODE_SMMU_V3:
+		/*
+		 * SMMUv3 dev ID mapping index was introduced in revision 1
+		 * table, not available in revision 0
+		 */
+		if (node->revision < 1)
+			return -EINVAL;
+
+		smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+		/*
+		 * ID mapping index is only ignored if all interrupts are
+		 * GSIV based
+		 */
+		if (smmu->event_gsiv && smmu->pri_gsiv && smmu->gerr_gsiv
+		    && smmu->sync_gsiv)
+			return -EINVAL;
+
+		if (smmu->id_mapping_index >= node->mapping_count) {
+			pr_err(FW_BUG "[node %p type %d] ID mapping index overflows valid mappings\n",
+			       node, node->type);
+			return -EINVAL;
+		}
+
+		return smmu->id_mapping_index;
+	default:
+		return -EINVAL;
+	}
+}
+#else
+static inline int iort_get_id_mapping_index(struct acpi_iort_node *node)
+{
+	return -EINVAL;
+}
+#endif
+
 static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 					       u32 id_in, u32 *id_out,
 					       u8 type_mask)
@@ -350,7 +416,7 @@ static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 	/* Parse the ID mapping tree to find specified node type */
 	while (node) {
 		struct acpi_iort_id_mapping *map;
-		int i;
+		int i, index;
 
 		if (IORT_TYPE_MASK(node->type) & type_mask) {
 			if (id_out)
@@ -371,8 +437,19 @@ static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 			goto fail_map;
 		}
 
+		/*
+		 * Get the special ID mapping index (if any) and skip its
+		 * associated ID map to prevent erroneous multi-stage
+		 * IORT ID translations.
+		 */
+		index = iort_get_id_mapping_index(node);
+
 		/* Do the ID translation */
 		for (i = 0; i < node->mapping_count; i++, map++) {
+			/* if it is special mapping index, skip it */
+			if (i == index)
+				continue;
+
 			if (!iort_id_map(map, node->type, id, &id))
 				break;
 		}
@@ -392,10 +469,9 @@ fail_map:
 	return NULL;
 }
 
-static
-struct acpi_iort_node *iort_node_map_platform_id(struct acpi_iort_node *node,
-						 u32 *id_out, u8 type_mask,
-						 int index)
+static struct acpi_iort_node *iort_node_map_platform_id(
+		struct acpi_iort_node *node, u32 *id_out, u8 type_mask,
+		int index)
 {
 	struct acpi_iort_node *parent;
 	u32 id;
@@ -424,9 +500,25 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev)
 {
 	struct pci_bus *pbus;
 
-	if (!dev_is_pci(dev))
+	if (!dev_is_pci(dev)) {
+		struct acpi_iort_node *node;
+		/*
+		 * scan iort_fwnode_list to see if it's an iort platform
+		 * device (such as SMMU, PMCG),its iort node already cached
+		 * and associated with fwnode when iort platform devices
+		 * were initialized.
+		 */
+		node = iort_get_iort_node(dev->fwnode);
+		if (node)
+			return node;
+
+		/*
+		 * if not, then it should be a platform device defined in
+		 * DSDT/SSDT (with Named Component node in IORT)
+		 */
 		return iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT,
 				      iort_match_node_callback, dev);
+	}
 
 	/* Find a PCI root bus */
 	pbus = to_pci_dev(dev)->bus;
@@ -466,16 +558,24 @@ u32 iort_msi_map_rid(struct device *dev, u32 req_id)
  */
 int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
 {
-	int i;
+	int i, index;
 	struct acpi_iort_node *node;
 
 	node = iort_find_dev_node(dev);
 	if (!node)
 		return -ENODEV;
 
-	for (i = 0; i < node->mapping_count; i++) {
-		if (iort_node_map_platform_id(node, dev_id, IORT_MSI_TYPE, i))
+	index = iort_get_id_mapping_index(node);
+	/* if there is a valid index, go get the dev_id directly */
+	if (index >= 0) {
+		if (iort_node_get_id(node, dev_id, index))
 			return 0;
+	} else {
+		for (i = 0; i < node->mapping_count; i++) {
+			if (iort_node_map_platform_id(node, dev_id,
+						      IORT_MSI_TYPE, i))
+				return 0;
+		}
 	}
 
 	return -ENODEV;
@@ -538,6 +638,49 @@ struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id)
 	return irq_find_matching_fwnode(handle, DOMAIN_BUS_PCI_MSI);
 }
 
+static void iort_set_device_domain(struct device *dev,
+				   struct acpi_iort_node *node)
+{
+	struct acpi_iort_its_group *its;
+	struct acpi_iort_node *msi_parent;
+	struct acpi_iort_id_mapping *map;
+	struct fwnode_handle *iort_fwnode;
+	struct irq_domain *domain;
+	int index;
+
+	index = iort_get_id_mapping_index(node);
+	if (index < 0)
+		return;
+
+	map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, node,
+			   node->mapping_offset + index * sizeof(*map));
+
+	/* Firmware bug! */
+	if (!map->output_reference ||
+	    !(map->flags & ACPI_IORT_ID_SINGLE_MAPPING)) {
+		pr_err(FW_BUG "[node %p type %d] Invalid MSI mapping\n",
+		       node, node->type);
+		return;
+	}
+
+	msi_parent = ACPI_ADD_PTR(struct acpi_iort_node, iort_table,
+				  map->output_reference);
+
+	if (!msi_parent || msi_parent->type != ACPI_IORT_NODE_ITS_GROUP)
+		return;
+
+	/* Move to ITS specific data */
+	its = (struct acpi_iort_its_group *)msi_parent->node_data;
+
+	iort_fwnode = iort_find_domain_token(its->identifiers[0]);
+	if (!iort_fwnode)
+		return;
+
+	domain = irq_find_matching_fwnode(iort_fwnode, DOMAIN_BUS_PLATFORM_MSI);
+	if (domain)
+		dev_set_msi_domain(dev, domain);
+}
+
 /**
  * iort_get_platform_device_domain() - Find MSI domain related to a
  * platform device
@@ -623,14 +766,14 @@ static inline bool iort_iommu_driver_enabled(u8 type)
 }
 
 #ifdef CONFIG_IOMMU_API
-static inline
-const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+static inline const struct iommu_ops *iort_fwspec_iommu_ops(
+				struct iommu_fwspec *fwspec)
 {
 	return (fwspec && fwspec->ops) ? fwspec->ops : NULL;
 }
 
-static inline
-int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+static inline int iort_add_device_replay(const struct iommu_ops *ops,
+					 struct device *dev)
 {
 	int err = 0;
 
@@ -640,11 +783,11 @@ int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
 	return err;
 }
 #else
-static inline
-const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+static inline const struct iommu_ops *iort_fwspec_iommu_ops(
+				struct iommu_fwspec *fwspec)
 { return NULL; }
-static inline
-int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+static inline int iort_add_device_replay(const struct iommu_ops *ops,
+					 struct device *dev)
 { return 0; }
 #endif
 
@@ -968,7 +1111,7 @@ static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
 	return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
 }
 
-#if defined(CONFIG_ACPI_NUMA) && defined(ACPI_IORT_SMMU_V3_PXM_VALID)
+#if defined(CONFIG_ACPI_NUMA)
 /*
  * set numa proximity domain for smmuv3 device
  */
@@ -1051,34 +1194,34 @@ static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node)
 	return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK;
 }
 
-struct iort_iommu_config {
+struct iort_dev_config {
 	const char *name;
-	int (*iommu_init)(struct acpi_iort_node *node);
-	bool (*iommu_is_coherent)(struct acpi_iort_node *node);
-	int (*iommu_count_resources)(struct acpi_iort_node *node);
-	void (*iommu_init_resources)(struct resource *res,
+	int (*dev_init)(struct acpi_iort_node *node);
+	bool (*dev_is_coherent)(struct acpi_iort_node *node);
+	int (*dev_count_resources)(struct acpi_iort_node *node);
+	void (*dev_init_resources)(struct resource *res,
 				     struct acpi_iort_node *node);
-	void (*iommu_set_proximity)(struct device *dev,
+	void (*dev_set_proximity)(struct device *dev,
 				    struct acpi_iort_node *node);
 };
 
-static const struct iort_iommu_config iort_arm_smmu_v3_cfg __initconst = {
+static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 	.name = "arm-smmu-v3",
-	.iommu_is_coherent = arm_smmu_v3_is_coherent,
-	.iommu_count_resources = arm_smmu_v3_count_resources,
-	.iommu_init_resources = arm_smmu_v3_init_resources,
-	.iommu_set_proximity = arm_smmu_v3_set_proximity,
+	.dev_is_coherent = arm_smmu_v3_is_coherent,
+	.dev_count_resources = arm_smmu_v3_count_resources,
+	.dev_init_resources = arm_smmu_v3_init_resources,
+	.dev_set_proximity = arm_smmu_v3_set_proximity,
 };
 
-static const struct iort_iommu_config iort_arm_smmu_cfg __initconst = {
+static const struct iort_dev_config iort_arm_smmu_cfg __initconst = {
 	.name = "arm-smmu",
-	.iommu_is_coherent = arm_smmu_is_coherent,
-	.iommu_count_resources = arm_smmu_count_resources,
-	.iommu_init_resources = arm_smmu_init_resources
+	.dev_is_coherent = arm_smmu_is_coherent,
+	.dev_count_resources = arm_smmu_count_resources,
+	.dev_init_resources = arm_smmu_init_resources
 };
 
-static __init
-const struct iort_iommu_config *iort_get_iommu_cfg(struct acpi_iort_node *node)
+static __init const struct iort_dev_config *iort_get_dev_cfg(
+			struct acpi_iort_node *node)
 {
 	switch (node->type) {
 	case ACPI_IORT_NODE_SMMU_V3:
@@ -1091,31 +1234,28 @@ const struct iort_iommu_config *iort_get_iommu_cfg(struct acpi_iort_node *node)
 }
 
 /**
- * iort_add_smmu_platform_device() - Allocate a platform device for SMMU
- * @node: Pointer to SMMU ACPI IORT node
+ * iort_add_platform_device() - Allocate a platform device for IORT node
+ * @node: Pointer to device ACPI IORT node
  *
  * Returns: 0 on success, <0 failure
  */
-static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
+static int __init iort_add_platform_device(struct acpi_iort_node *node,
+					   const struct iort_dev_config *ops)
 {
 	struct fwnode_handle *fwnode;
 	struct platform_device *pdev;
 	struct resource *r;
 	enum dev_dma_attr attr;
 	int ret, count;
-	const struct iort_iommu_config *ops = iort_get_iommu_cfg(node);
-
-	if (!ops)
-		return -ENODEV;
 
 	pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO);
 	if (!pdev)
 		return -ENOMEM;
 
-	if (ops->iommu_set_proximity)
-		ops->iommu_set_proximity(&pdev->dev, node);
+	if (ops->dev_set_proximity)
+		ops->dev_set_proximity(&pdev->dev, node);
 
-	count = ops->iommu_count_resources(node);
+	count = ops->dev_count_resources(node);
 
 	r = kcalloc(count, sizeof(*r), GFP_KERNEL);
 	if (!r) {
@@ -1123,7 +1263,7 @@ static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
 		goto dev_put;
 	}
 
-	ops->iommu_init_resources(r, node);
+	ops->dev_init_resources(r, node);
 
 	ret = platform_device_add_resources(pdev, r, count);
 	/*
@@ -1158,12 +1298,14 @@ static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
 
 	pdev->dev.fwnode = fwnode;
 
-	attr = ops->iommu_is_coherent(node) ?
-			     DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+	attr = ops->dev_is_coherent && ops->dev_is_coherent(node) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
 
 	/* Configure DMA for the page table walker */
 	acpi_dma_configure(&pdev->dev, attr);
 
+	iort_set_device_domain(&pdev->dev, node);
+
 	ret = platform_device_add(pdev);
 	if (ret)
 		goto dma_deconfigure;
@@ -1216,6 +1358,7 @@ static void __init iort_init_platform_devices(void)
 	struct fwnode_handle *fwnode;
 	int i, ret;
 	bool acs_enabled = false;
+	const struct iort_dev_config *ops;
 
 	/*
 	 * iort_table and iort both point to the start of IORT table, but
@@ -1238,16 +1381,15 @@ static void __init iort_init_platform_devices(void)
 		if (!acs_enabled)
 			acs_enabled = iort_enable_acs(iort_node);
 
-		if ((iort_node->type == ACPI_IORT_NODE_SMMU) ||
-			(iort_node->type == ACPI_IORT_NODE_SMMU_V3)) {
-
+		ops = iort_get_dev_cfg(iort_node);
+		if (ops) {
 			fwnode = acpi_alloc_fwnode_static();
 			if (!fwnode)
 				return;
 
 			iort_set_fwnode(iort_node, fwnode);
 
-			ret = iort_add_smmu_platform_device(iort_node);
+			ret = iort_add_platform_device(iort_node, ops);
 			if (ret) {
 				iort_delete_fwnode(iort_node);
 				acpi_free_fwnode_static(fwnode);

drivers/bus/arm-ccn.c

@@ -1276,6 +1276,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 
 	/* Perf driver registration */
 	ccn->dt.pmu = (struct pmu) {
+		.module = THIS_MODULE,
 		.attr_groups = arm_ccn_pmu_attr_groups,
 		.task_ctx_nr = perf_invalid_context,
 		.event_init = arm_ccn_pmu_event_init,

drivers/clocksource/arm_arch_timer.c

@@ -77,6 +77,7 @@ static bool arch_timer_mem_use_virtual;
 static bool arch_counter_suspend_stop;
 static bool vdso_default = true;
 
+static cpumask_t evtstrm_available = CPU_MASK_NONE;
 static bool evtstrm_enable = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
 
 static int __init early_evtstrm_cfg(char *buf)
@@ -739,6 +740,7 @@ static void arch_timer_evtstrm_enable(int divider)
 #ifdef CONFIG_COMPAT
 	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
 #endif
+	cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
 }
 
 static void arch_timer_configure_evtstream(void)
@@ -863,6 +865,16 @@ u32 arch_timer_get_rate(void)
 	return arch_timer_rate;
 }
 
+bool arch_timer_evtstrm_available(void)
+{
+	/*
+	 * We might get called from a preemptible context. This is fine
+	 * because availability of the event stream should be always the same
+	 * for a preemptible context and context where we might resume a task.
+	 */
+	return cpumask_test_cpu(raw_smp_processor_id(), &evtstrm_available);
+}
+
 static u64 arch_counter_get_cntvct_mem(void)
 {
 	u32 vct_lo, vct_hi, tmp_hi;
@@ -928,6 +940,8 @@ static int arch_timer_dying_cpu(unsigned int cpu)
 {
 	struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt);
 
+	cpumask_clear_cpu(smp_processor_id(), &evtstrm_available);
+
 	arch_timer_stop(clk);
 	return 0;
 }
@@ -937,10 +951,16 @@ static DEFINE_PER_CPU(unsigned long, saved_cntkctl);
 static int arch_timer_cpu_pm_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
-	if (action == CPU_PM_ENTER)
+	if (action == CPU_PM_ENTER) {
 		__this_cpu_write(saved_cntkctl, arch_timer_get_cntkctl());
-	else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT)
+
+		cpumask_clear_cpu(smp_processor_id(), &evtstrm_available);
+	} else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) {
 		arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
+
+		if (elf_hwcap & HWCAP_EVTSTRM)
+			cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
+	}
 	return NOTIFY_OK;
 }
 
@@ -1016,7 +1036,6 @@ static int __init arch_timer_register(void)
 	if (err)
 		goto out_unreg_notify;
 
-
 	/* Register and immediately configure the timer on the boot CPU */
 	err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING,
 				"clockevents/arm/arch_timer:starting",

drivers/perf/Kconfig

@@ -17,6 +17,13 @@ config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
 
+config HISI_PMU
+       bool "HiSilicon SoC PMU"
+       depends on ARM64 && ACPI
+       help
+         Support for HiSilicon SoC uncore performance monitoring
+         unit (PMU), such as: L3C, HHA and DDRC.
+
 config QCOM_L2_PMU
 	bool "Qualcomm Technologies L2-cache PMU"
 	depends on ARCH_QCOM && ARM64 && ACPI
@@ -43,4 +50,12 @@ config XGENE_PMU
         help
           Say y if you want to use APM X-Gene SoC performance monitors.
 
+config ARM_SPE_PMU
+	tristate "Enable support for the ARMv8.2 Statistical Profiling Extension"
+	depends on PERF_EVENTS && ARM64
+	help
+	  Enable perf support for the ARMv8.2 Statistical Profiling
+	  Extension, which provides periodic sampling of operations in
+	  the CPU pipeline and reports this via the perf AUX interface.
+
 endmenu

drivers/perf/Makefile

@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
+obj-$(CONFIG_HISI_PMU) += hisilicon/
 obj-$(CONFIG_QCOM_L2_PMU)	+= qcom_l2_pmu.o
 obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
 obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o
+obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o

drivers/perf/arm_pmu.c

@@ -539,7 +539,7 @@ void armpmu_free_irq(struct arm_pmu *armpmu, int cpu)
 	if (!cpumask_test_and_clear_cpu(cpu, &armpmu->active_irqs))
 		return;
 
-	if (irq_is_percpu(irq)) {
+	if (irq_is_percpu_devid(irq)) {
 		free_percpu_irq(irq, &hw_events->percpu_pmu);
 		cpumask_clear(&armpmu->active_irqs);
 		return;
@@ -565,10 +565,10 @@ int armpmu_request_irq(struct arm_pmu *armpmu, int cpu)
 	if (!irq)
 		return 0;
 
-	if (irq_is_percpu(irq) && cpumask_empty(&armpmu->active_irqs)) {
+	if (irq_is_percpu_devid(irq) && cpumask_empty(&armpmu->active_irqs)) {
 		err = request_percpu_irq(irq, handler, "arm-pmu",
 					 &hw_events->percpu_pmu);
-	} else if (irq_is_percpu(irq)) {
+	} else if (irq_is_percpu_devid(irq)) {
 		int other_cpu = cpumask_first(&armpmu->active_irqs);
 		int other_irq = per_cpu(hw_events->irq, other_cpu);
 
@@ -649,7 +649,7 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
 
 	irq = armpmu_get_cpu_irq(pmu, cpu);
 	if (irq) {
-		if (irq_is_percpu(irq)) {
+		if (irq_is_percpu_devid(irq)) {
 			enable_percpu_irq(irq, IRQ_TYPE_NONE);
 			return 0;
 		}
@@ -667,7 +667,7 @@ static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	irq = armpmu_get_cpu_irq(pmu, cpu);
-	if (irq && irq_is_percpu(irq))
+	if (irq && irq_is_percpu_devid(irq))
 		disable_percpu_irq(irq);
 
 	return 0;

drivers/perf/arm_pmu_acpi.c

@@ -193,9 +193,6 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn)
 	int pmu_idx = 0;
 	int cpu, ret;
 
-	if (acpi_disabled)
-		return 0;
-
 	/*
 	 * Initialise and register the set of PMUs which we know about right
 	 * now. Ideally we'd do this in arm_pmu_acpi_cpu_starting() so that we

drivers/perf/arm_pmu_platform.c

@@ -127,7 +127,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 
 	if (num_irqs == 1) {
 		int irq = platform_get_irq(pdev, 0);
-		if (irq && irq_is_percpu(irq))
+		if (irq && irq_is_percpu_devid(irq))
 			return pmu_parse_percpu_irq(pmu, irq);
 	}
 
@@ -150,7 +150,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 		if (WARN_ON(irq <= 0))
 			continue;
 
-		if (irq_is_percpu(irq)) {
+		if (irq_is_percpu_devid(irq)) {
 			pr_warn("multiple PPIs or mismatched SPI/PPI detected\n");
 			return -EINVAL;
 		}

drivers/perf/arm_spe_pmu.c

@@ -0,0 +1,1249 @@
+/*
+ * Perf support for the Statistical Profiling Extension, introduced as
+ * part of ARMv8.2.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2016 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define PMUNAME					"arm_spe"
+#define DRVNAME					PMUNAME "_pmu"
+#define pr_fmt(fmt)				DRVNAME ": " fmt
+
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <asm/sysreg.h>
+
+#define ARM_SPE_BUF_PAD_BYTE			0
+
+struct arm_spe_pmu_buf {
+	int					nr_pages;
+	bool					snapshot;
+	void					*base;
+};
+
+struct arm_spe_pmu {
+	struct pmu				pmu;
+	struct platform_device			*pdev;
+	cpumask_t				supported_cpus;
+	struct hlist_node			hotplug_node;
+
+	int					irq; /* PPI */
+
+	u16					min_period;
+	u16					counter_sz;
+
+#define SPE_PMU_FEAT_FILT_EVT			(1UL << 0)
+#define SPE_PMU_FEAT_FILT_TYP			(1UL << 1)
+#define SPE_PMU_FEAT_FILT_LAT			(1UL << 2)
+#define SPE_PMU_FEAT_ARCH_INST			(1UL << 3)
+#define SPE_PMU_FEAT_LDS			(1UL << 4)
+#define SPE_PMU_FEAT_ERND			(1UL << 5)
+#define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
+	u64					features;
+
+	u16					max_record_sz;
+	u16					align;
+	struct perf_output_handle __percpu	*handle;
+};
+
+#define to_spe_pmu(p) (container_of(p, struct arm_spe_pmu, pmu))
+
+/* Convert a free-running index from perf into an SPE buffer offset */
+#define PERF_IDX2OFF(idx, buf)	((idx) % ((buf)->nr_pages << PAGE_SHIFT))
+
+/* Keep track of our dynamic hotplug state */
+static enum cpuhp_state arm_spe_pmu_online;
+
+enum arm_spe_pmu_buf_fault_action {
+	SPE_PMU_BUF_FAULT_ACT_SPURIOUS,
+	SPE_PMU_BUF_FAULT_ACT_FATAL,
+	SPE_PMU_BUF_FAULT_ACT_OK,
+};
+
+/* This sysfs gunk was really good fun to write. */
+enum arm_spe_pmu_capabilities {
+	SPE_PMU_CAP_ARCH_INST = 0,
+	SPE_PMU_CAP_ERND,
+	SPE_PMU_CAP_FEAT_MAX,
+	SPE_PMU_CAP_CNT_SZ = SPE_PMU_CAP_FEAT_MAX,
+	SPE_PMU_CAP_MIN_IVAL,
+};
+
+static int arm_spe_pmu_feat_caps[SPE_PMU_CAP_FEAT_MAX] = {
+	[SPE_PMU_CAP_ARCH_INST]	= SPE_PMU_FEAT_ARCH_INST,
+	[SPE_PMU_CAP_ERND]	= SPE_PMU_FEAT_ERND,
+};
+
+static u32 arm_spe_pmu_cap_get(struct arm_spe_pmu *spe_pmu, int cap)
+{
+	if (cap < SPE_PMU_CAP_FEAT_MAX)
+		return !!(spe_pmu->features & arm_spe_pmu_feat_caps[cap]);
+
+	switch (cap) {
+	case SPE_PMU_CAP_CNT_SZ:
+		return spe_pmu->counter_sz;
+	case SPE_PMU_CAP_MIN_IVAL:
+		return spe_pmu->min_period;
+	default:
+		WARN(1, "unknown cap %d\n", cap);
+	}
+
+	return 0;
+}
+
+static ssize_t arm_spe_pmu_cap_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
+	struct dev_ext_attribute *ea =
+		container_of(attr, struct dev_ext_attribute, attr);
+	int cap = (long)ea->var;
+
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+		arm_spe_pmu_cap_get(spe_pmu, cap));
+}
+
+#define SPE_EXT_ATTR_ENTRY(_name, _func, _var)				\
+	&((struct dev_ext_attribute[]) {				\
+		{ __ATTR(_name, S_IRUGO, _func, NULL), (void *)_var }	\
+	})[0].attr.attr
+
+#define SPE_CAP_EXT_ATTR_ENTRY(_name, _var)				\
+	SPE_EXT_ATTR_ENTRY(_name, arm_spe_pmu_cap_show, _var)
+
+static struct attribute *arm_spe_pmu_cap_attr[] = {
+	SPE_CAP_EXT_ATTR_ENTRY(arch_inst, SPE_PMU_CAP_ARCH_INST),
+	SPE_CAP_EXT_ATTR_ENTRY(ernd, SPE_PMU_CAP_ERND),
+	SPE_CAP_EXT_ATTR_ENTRY(count_size, SPE_PMU_CAP_CNT_SZ),
+	SPE_CAP_EXT_ATTR_ENTRY(min_interval, SPE_PMU_CAP_MIN_IVAL),
+	NULL,
+};
+
+static struct attribute_group arm_spe_pmu_cap_group = {
+	.name	= "caps",
+	.attrs	= arm_spe_pmu_cap_attr,
+};
+
+/* User ABI */
+#define ATTR_CFG_FLD_ts_enable_CFG		config	/* PMSCR_EL1.TS */
+#define ATTR_CFG_FLD_ts_enable_LO		0
+#define ATTR_CFG_FLD_ts_enable_HI		0
+#define ATTR_CFG_FLD_pa_enable_CFG		config	/* PMSCR_EL1.PA */
+#define ATTR_CFG_FLD_pa_enable_LO		1
+#define ATTR_CFG_FLD_pa_enable_HI		1
+#define ATTR_CFG_FLD_pct_enable_CFG		config	/* PMSCR_EL1.PCT */
+#define ATTR_CFG_FLD_pct_enable_LO		2
+#define ATTR_CFG_FLD_pct_enable_HI		2
+#define ATTR_CFG_FLD_jitter_CFG			config	/* PMSIRR_EL1.RND */
+#define ATTR_CFG_FLD_jitter_LO			16
+#define ATTR_CFG_FLD_jitter_HI			16
+#define ATTR_CFG_FLD_branch_filter_CFG		config	/* PMSFCR_EL1.B */
+#define ATTR_CFG_FLD_branch_filter_LO		32
+#define ATTR_CFG_FLD_branch_filter_HI		32
+#define ATTR_CFG_FLD_load_filter_CFG		config	/* PMSFCR_EL1.LD */
+#define ATTR_CFG_FLD_load_filter_LO		33
+#define ATTR_CFG_FLD_load_filter_HI		33
+#define ATTR_CFG_FLD_store_filter_CFG		config	/* PMSFCR_EL1.ST */
+#define ATTR_CFG_FLD_store_filter_LO		34
+#define ATTR_CFG_FLD_store_filter_HI		34
+
+#define ATTR_CFG_FLD_event_filter_CFG		config1	/* PMSEVFR_EL1 */
+#define ATTR_CFG_FLD_event_filter_LO		0
+#define ATTR_CFG_FLD_event_filter_HI		63
+
+#define ATTR_CFG_FLD_min_latency_CFG		config2	/* PMSLATFR_EL1.MINLAT */
+#define ATTR_CFG_FLD_min_latency_LO		0
+#define ATTR_CFG_FLD_min_latency_HI		11
+
+/* Why does everything I do descend into this? */
+#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
+
+#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
+
+#define GEN_PMU_FORMAT_ATTR(name)					\
+	PMU_FORMAT_ATTR(name,						\
+	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
+			     ATTR_CFG_FLD_##name##_LO,			\
+			     ATTR_CFG_FLD_##name##_HI))
+
+#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
+	((((attr)->cfg) >> lo) & GENMASK(hi - lo, 0))
+
+#define ATTR_CFG_GET_FLD(attr, name)					\
+	_ATTR_CFG_GET_FLD(attr,						\
+			  ATTR_CFG_FLD_##name##_CFG,			\
+			  ATTR_CFG_FLD_##name##_LO,			\
+			  ATTR_CFG_FLD_##name##_HI)
+
+GEN_PMU_FORMAT_ATTR(ts_enable);
+GEN_PMU_FORMAT_ATTR(pa_enable);
+GEN_PMU_FORMAT_ATTR(pct_enable);
+GEN_PMU_FORMAT_ATTR(jitter);
+GEN_PMU_FORMAT_ATTR(branch_filter);
+GEN_PMU_FORMAT_ATTR(load_filter);
+GEN_PMU_FORMAT_ATTR(store_filter);
+GEN_PMU_FORMAT_ATTR(event_filter);
+GEN_PMU_FORMAT_ATTR(min_latency);
+
+static struct attribute *arm_spe_pmu_formats_attr[] = {
+	&format_attr_ts_enable.attr,
+	&format_attr_pa_enable.attr,
+	&format_attr_pct_enable.attr,
+	&format_attr_jitter.attr,
+	&format_attr_branch_filter.attr,
+	&format_attr_load_filter.attr,
+	&format_attr_store_filter.attr,
+	&format_attr_event_filter.attr,
+	&format_attr_min_latency.attr,
+	NULL,
+};
+
+static struct attribute_group arm_spe_pmu_format_group = {
+	.name	= "format",
+	.attrs	= arm_spe_pmu_formats_attr,
+};
+
+static ssize_t arm_spe_pmu_get_attr_cpumask(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
+
+	return cpumap_print_to_pagebuf(true, buf, &spe_pmu->supported_cpus);
+}
+static DEVICE_ATTR(cpumask, S_IRUGO, arm_spe_pmu_get_attr_cpumask, NULL);
+
+static struct attribute *arm_spe_pmu_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group arm_spe_pmu_group = {
+	.attrs	= arm_spe_pmu_attrs,
+};
+
+static const struct attribute_group *arm_spe_pmu_attr_groups[] = {
+	&arm_spe_pmu_group,
+	&arm_spe_pmu_cap_group,
+	&arm_spe_pmu_format_group,
+	NULL,
+};
+
+/* Convert between user ABI and register values */
+static u64 arm_spe_event_to_pmscr(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	u64 reg = 0;
+
+	reg |= ATTR_CFG_GET_FLD(attr, ts_enable) << SYS_PMSCR_EL1_TS_SHIFT;
+	reg |= ATTR_CFG_GET_FLD(attr, pa_enable) << SYS_PMSCR_EL1_PA_SHIFT;
+	reg |= ATTR_CFG_GET_FLD(attr, pct_enable) << SYS_PMSCR_EL1_PCT_SHIFT;
+
+	if (!attr->exclude_user)
+		reg |= BIT(SYS_PMSCR_EL1_E0SPE_SHIFT);
+
+	if (!attr->exclude_kernel)
+		reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT);
+
+	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && capable(CAP_SYS_ADMIN))
+		reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT);
+
+	return reg;
+}
+
+static void arm_spe_event_sanitise_period(struct perf_event *event)
+{
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
+	u64 period = event->hw.sample_period;
+	u64 max_period = SYS_PMSIRR_EL1_INTERVAL_MASK
+			 << SYS_PMSIRR_EL1_INTERVAL_SHIFT;
+
+	if (period < spe_pmu->min_period)
+		period = spe_pmu->min_period;
+	else if (period > max_period)
+		period = max_period;
+	else
+		period &= max_period;
+
+	event->hw.sample_period = period;
+}
+
+static u64 arm_spe_event_to_pmsirr(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	u64 reg = 0;
+
+	arm_spe_event_sanitise_period(event);
+
+	reg |= ATTR_CFG_GET_FLD(attr, jitter) << SYS_PMSIRR_EL1_RND_SHIFT;
+	reg |= event->hw.sample_period;
+
+	return reg;
+}
+
+static u64 arm_spe_event_to_pmsfcr(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	u64 reg = 0;
+
+	reg |= ATTR_CFG_GET_FLD(attr, load_filter) << SYS_PMSFCR_EL1_LD_SHIFT;
+	reg |= ATTR_CFG_GET_FLD(attr, store_filter) << SYS_PMSFCR_EL1_ST_SHIFT;
+	reg |= ATTR_CFG_GET_FLD(attr, branch_filter) << SYS_PMSFCR_EL1_B_SHIFT;
+
+	if (reg)
+		reg |= BIT(SYS_PMSFCR_EL1_FT_SHIFT);
+
+	if (ATTR_CFG_GET_FLD(attr, event_filter))
+		reg |= BIT(SYS_PMSFCR_EL1_FE_SHIFT);
+
+	if (ATTR_CFG_GET_FLD(attr, min_latency))
+		reg |= BIT(SYS_PMSFCR_EL1_FL_SHIFT);
+
+	return reg;
+}
+
+static u64 arm_spe_event_to_pmsevfr(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	return ATTR_CFG_GET_FLD(attr, event_filter);
+}
+
+static u64 arm_spe_event_to_pmslatfr(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	return ATTR_CFG_GET_FLD(attr, min_latency)
+	       << SYS_PMSLATFR_EL1_MINLAT_SHIFT;
+}
+
+static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len)
+{
+	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
+	u64 head = PERF_IDX2OFF(handle->head, buf);
+
+	memset(buf->base + head, ARM_SPE_BUF_PAD_BYTE, len);
+	if (!buf->snapshot)
+		perf_aux_output_skip(handle, len);
+}
+
+static u64 arm_spe_pmu_next_snapshot_off(struct perf_output_handle *handle)
+{
+	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(handle->event->pmu);
+	u64 head = PERF_IDX2OFF(handle->head, buf);
+	u64 limit = buf->nr_pages * PAGE_SIZE;
+
+	/*
+	 * The trace format isn't parseable in reverse, so clamp
+	 * the limit to half of the buffer size in snapshot mode
+	 * so that the worst case is half a buffer of records, as
+	 * opposed to a single record.
+	 */
+	if (head < limit >> 1)
+		limit >>= 1;
+
+	/*
+	 * If we're within max_record_sz of the limit, we must
+	 * pad, move the head index and recompute the limit.
+	 */
+	if (limit - head < spe_pmu->max_record_sz) {
+		arm_spe_pmu_pad_buf(handle, limit - head);
+		handle->head = PERF_IDX2OFF(limit, buf);
+		limit = ((buf->nr_pages * PAGE_SIZE) >> 1) + handle->head;
+	}
+
+	return limit;
+}
+
+static u64 __arm_spe_pmu_next_off(struct perf_output_handle *handle)
+{
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(handle->event->pmu);
+	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
+	const u64 bufsize = buf->nr_pages * PAGE_SIZE;
+	u64 limit = bufsize;
+	u64 head, tail, wakeup;
+
+	/*
+	 * The head can be misaligned for two reasons:
+	 *
+	 * 1. The hardware left PMBPTR pointing to the first byte after
+	 *    a record when generating a buffer management event.
+	 *
+	 * 2. We used perf_aux_output_skip to consume handle->size bytes
+	 *    and CIRC_SPACE was used to compute the size, which always
+	 *    leaves one entry free.
+	 *
+	 * Deal with this by padding to the next alignment boundary and
+	 * moving the head index. If we run out of buffer space, we'll
+	 * reduce handle->size to zero and end up reporting truncation.
+	 */
+	head = PERF_IDX2OFF(handle->head, buf);
+	if (!IS_ALIGNED(head, spe_pmu->align)) {
+		unsigned long delta = roundup(head, spe_pmu->align) - head;
+
+		delta = min(delta, handle->size);
+		arm_spe_pmu_pad_buf(handle, delta);
+		head = PERF_IDX2OFF(handle->head, buf);
+	}
+
+	/* If we've run out of free space, then nothing more to do */
+	if (!handle->size)
+		goto no_space;
+
+	/* Compute the tail and wakeup indices now that we've aligned head */
+	tail = PERF_IDX2OFF(handle->head + handle->size, buf);
+	wakeup = PERF_IDX2OFF(handle->wakeup, buf);
+
+	/*
+	 * Avoid clobbering unconsumed data. We know we have space, so
+	 * if we see head == tail we know that the buffer is empty. If
+	 * head > tail, then there's nothing to clobber prior to
+	 * wrapping.
+	 */
+	if (head < tail)
+		limit = round_down(tail, PAGE_SIZE);
+
+	/*
+	 * Wakeup may be arbitrarily far into the future. If it's not in
+	 * the current generation, either we'll wrap before hitting it,
+	 * or it's in the past and has been handled already.
+	 *
+	 * If there's a wakeup before we wrap, arrange to be woken up by
+	 * the page boundary following it. Keep the tail boundary if
+	 * that's lower.
+	 */
+	if (handle->wakeup < (handle->head + handle->size) && head <= wakeup)
+		limit = min(limit, round_up(wakeup, PAGE_SIZE));
+
+	if (limit > head)
+		return limit;
+
+	arm_spe_pmu_pad_buf(handle, handle->size);
+no_space:
+	perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+	perf_aux_output_end(handle, 0);
+	return 0;
+}
+
+static u64 arm_spe_pmu_next_off(struct perf_output_handle *handle)
+{
+	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(handle->event->pmu);
+	u64 limit = __arm_spe_pmu_next_off(handle);
+	u64 head = PERF_IDX2OFF(handle->head, buf);
+
+	/*
+	 * If the head has come too close to the end of the buffer,
+	 * then pad to the end and recompute the limit.
+	 */
+	if (limit && (limit - head < spe_pmu->max_record_sz)) {
+		arm_spe_pmu_pad_buf(handle, limit - head);
+		limit = __arm_spe_pmu_next_off(handle);
+	}
+
+	return limit;
+}
+
+static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle,
+					  struct perf_event *event)
+{
+	u64 base, limit;
+	struct arm_spe_pmu_buf *buf;
+
+	/* Start a new aux session */
+	buf = perf_aux_output_begin(handle, event);
+	if (!buf) {
+		event->hw.state |= PERF_HES_STOPPED;
+		/*
+		 * We still need to clear the limit pointer, since the
+		 * profiler might only be disabled by virtue of a fault.
+		 */
+		limit = 0;
+		goto out_write_limit;
+	}
+
+	limit = buf->snapshot ? arm_spe_pmu_next_snapshot_off(handle)
+			      : arm_spe_pmu_next_off(handle);
+	if (limit)
+		limit |= BIT(SYS_PMBLIMITR_EL1_E_SHIFT);
+
+	limit += (u64)buf->base;
+	base = (u64)buf->base + PERF_IDX2OFF(handle->head, buf);
+	write_sysreg_s(base, SYS_PMBPTR_EL1);
+
+out_write_limit:
+	write_sysreg_s(limit, SYS_PMBLIMITR_EL1);
+}
+
+static void arm_spe_perf_aux_output_end(struct perf_output_handle *handle)
+{
+	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
+	u64 offset, size;
+
+	offset = read_sysreg_s(SYS_PMBPTR_EL1) - (u64)buf->base;
+	size = offset - PERF_IDX2OFF(handle->head, buf);
+
+	if (buf->snapshot)
+		handle->head = offset;
+
+	perf_aux_output_end(handle, size);
+}
+
+static void arm_spe_pmu_disable_and_drain_local(void)
+{
+	/* Disable profiling at EL0 and EL1 */
+	write_sysreg_s(0, SYS_PMSCR_EL1);
+	isb();
+
+	/* Drain any buffered data */
+	psb_csync();
+	dsb(nsh);
+
+	/* Disable the profiling buffer */
+	write_sysreg_s(0, SYS_PMBLIMITR_EL1);
+	isb();
+}
+
+/* IRQ handling */
+static enum arm_spe_pmu_buf_fault_action
+arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle)
+{
+	const char *err_str;
+	u64 pmbsr;
+	enum arm_spe_pmu_buf_fault_action ret;
+
+	/*
+	 * Ensure new profiling data is visible to the CPU and any external
+	 * aborts have been resolved.
+	 */
+	psb_csync();
+	dsb(nsh);
+
+	/* Ensure hardware updates to PMBPTR_EL1 are visible */
+	isb();
+
+	/* Service required? */
+	pmbsr = read_sysreg_s(SYS_PMBSR_EL1);
+	if (!(pmbsr & BIT(SYS_PMBSR_EL1_S_SHIFT)))
+		return SPE_PMU_BUF_FAULT_ACT_SPURIOUS;
+
+	/*
+	 * If we've lost data, disable profiling and also set the PARTIAL
+	 * flag to indicate that the last record is corrupted.
+	 */
+	if (pmbsr & BIT(SYS_PMBSR_EL1_DL_SHIFT))
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED |
+					     PERF_AUX_FLAG_PARTIAL);
+
+	/* Report collisions to userspace so that it can up the period */
+	if (pmbsr & BIT(SYS_PMBSR_EL1_COLL_SHIFT))
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION);
+
+	/* We only expect buffer management events */
+	switch (pmbsr & (SYS_PMBSR_EL1_EC_MASK << SYS_PMBSR_EL1_EC_SHIFT)) {
+	case SYS_PMBSR_EL1_EC_BUF:
+		/* Handled below */
+		break;
+	case SYS_PMBSR_EL1_EC_FAULT_S1:
+	case SYS_PMBSR_EL1_EC_FAULT_S2:
+		err_str = "Unexpected buffer fault";
+		goto out_err;
+	default:
+		err_str = "Unknown error code";
+		goto out_err;
+	}
+
+	/* Buffer management event */
+	switch (pmbsr &
+		(SYS_PMBSR_EL1_BUF_BSC_MASK << SYS_PMBSR_EL1_BUF_BSC_SHIFT)) {
+	case SYS_PMBSR_EL1_BUF_BSC_FULL:
+		ret = SPE_PMU_BUF_FAULT_ACT_OK;
+		goto out_stop;
+	default:
+		err_str = "Unknown buffer status code";
+	}
+
+out_err:
+	pr_err_ratelimited("%s on CPU %d [PMBSR=0x%016llx, PMBPTR=0x%016llx, PMBLIMITR=0x%016llx]\n",
+			   err_str, smp_processor_id(), pmbsr,
+			   read_sysreg_s(SYS_PMBPTR_EL1),
+			   read_sysreg_s(SYS_PMBLIMITR_EL1));
+	ret = SPE_PMU_BUF_FAULT_ACT_FATAL;
+
+out_stop:
+	arm_spe_perf_aux_output_end(handle);
+	return ret;
+}
+
+static irqreturn_t arm_spe_pmu_irq_handler(int irq, void *dev)
+{
+	struct perf_output_handle *handle = dev;
+	struct perf_event *event = handle->event;
+	enum arm_spe_pmu_buf_fault_action act;
+
+	if (!perf_get_aux(handle))
+		return IRQ_NONE;
+
+	act = arm_spe_pmu_buf_get_fault_act(handle);
+	if (act == SPE_PMU_BUF_FAULT_ACT_SPURIOUS)
+		return IRQ_NONE;
+
+	/*
+	 * Ensure perf callbacks have completed, which may disable the
+	 * profiling buffer in response to a TRUNCATION flag.
+	 */
+	irq_work_run();
+
+	switch (act) {
+	case SPE_PMU_BUF_FAULT_ACT_FATAL:
+		/*
+		 * If a fatal exception occurred then leaving the profiling
+		 * buffer enabled is a recipe waiting to happen. Since
+		 * fatal faults don't always imply truncation, make sure
+		 * that the profiling buffer is disabled explicitly before
+		 * clearing the syndrome register.
+		 */
+		arm_spe_pmu_disable_and_drain_local();
+		break;
+	case SPE_PMU_BUF_FAULT_ACT_OK:
+		/*
+		 * We handled the fault (the buffer was full), so resume
+		 * profiling as long as we didn't detect truncation.
+		 * PMBPTR might be misaligned, but we'll burn that bridge
+		 * when we get to it.
+		 */
+		if (!(handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)) {
+			arm_spe_perf_aux_output_begin(handle, event);
+			isb();
+		}
+		break;
+	case SPE_PMU_BUF_FAULT_ACT_SPURIOUS:
+		/* We've seen you before, but GCC has the memory of a sieve. */
+		break;
+	}
+
+	/* The buffer pointers are now sane, so resume profiling. */
+	write_sysreg_s(0, SYS_PMBSR_EL1);
+	return IRQ_HANDLED;
+}
+
+/* Perf callbacks */
+static int arm_spe_pmu_event_init(struct perf_event *event)
+{
+	u64 reg;
+	struct perf_event_attr *attr = &event->attr;
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
+
+	/* This is, of course, deeply driver-specific */
+	if (attr->type != event->pmu->type)
+		return -ENOENT;
+
+	if (event->cpu >= 0 &&
+	    !cpumask_test_cpu(event->cpu, &spe_pmu->supported_cpus))
+		return -ENOENT;
+
+	if (arm_spe_event_to_pmsevfr(event) & SYS_PMSEVFR_EL1_RES0)
+		return -EOPNOTSUPP;
+
+	if (attr->exclude_idle)
+		return -EOPNOTSUPP;
+
+	/*
+	 * Feedback-directed frequency throttling doesn't work when we
+	 * have a buffer of samples. We'd need to manually count the
+	 * samples in the buffer when it fills up and adjust the event
+	 * count to reflect that. Instead, just force the user to specify
+	 * a sample period.
+	 */
+	if (attr->freq)
+		return -EINVAL;
+
+	reg = arm_spe_event_to_pmsfcr(event);
+	if ((reg & BIT(SYS_PMSFCR_EL1_FE_SHIFT)) &&
+	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_EVT))
+		return -EOPNOTSUPP;
+
+	if ((reg & BIT(SYS_PMSFCR_EL1_FT_SHIFT)) &&
+	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_TYP))
+		return -EOPNOTSUPP;
+
+	if ((reg & BIT(SYS_PMSFCR_EL1_FL_SHIFT)) &&
+	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT))
+		return -EOPNOTSUPP;
+
+	reg = arm_spe_event_to_pmscr(event);
+	if (!capable(CAP_SYS_ADMIN) &&
+	    (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) |
+		    BIT(SYS_PMSCR_EL1_CX_SHIFT) |
+		    BIT(SYS_PMSCR_EL1_PCT_SHIFT))))
+		return -EACCES;
+
+	return 0;
+}
+
+static void arm_spe_pmu_start(struct perf_event *event, int flags)
+{
+	u64 reg;
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_output_handle *handle = this_cpu_ptr(spe_pmu->handle);
+
+	hwc->state = 0;
+	arm_spe_perf_aux_output_begin(handle, event);
+	if (hwc->state)
+		return;
+
+	reg = arm_spe_event_to_pmsfcr(event);
+	write_sysreg_s(reg, SYS_PMSFCR_EL1);
+
+	reg = arm_spe_event_to_pmsevfr(event);
+	write_sysreg_s(reg, SYS_PMSEVFR_EL1);
+
+	reg = arm_spe_event_to_pmslatfr(event);
+	write_sysreg_s(reg, SYS_PMSLATFR_EL1);
+
+	if (flags & PERF_EF_RELOAD) {
+		reg = arm_spe_event_to_pmsirr(event);
+		write_sysreg_s(reg, SYS_PMSIRR_EL1);
+		isb();
+		reg = local64_read(&hwc->period_left);
+		write_sysreg_s(reg, SYS_PMSICR_EL1);
+	}
+
+	reg = arm_spe_event_to_pmscr(event);
+	isb();
+	write_sysreg_s(reg, SYS_PMSCR_EL1);
+}
+
+static void arm_spe_pmu_stop(struct perf_event *event, int flags)
+{
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_output_handle *handle = this_cpu_ptr(spe_pmu->handle);
+
+	/* If we're already stopped, then nothing to do */
+	if (hwc->state & PERF_HES_STOPPED)
+		return;
+
+	/* Stop all trace generation */
+	arm_spe_pmu_disable_and_drain_local();
+
+	if (flags & PERF_EF_UPDATE) {
+		/*
+		 * If there's a fault pending then ensure we contain it
+		 * to this buffer, since we might be on the context-switch
+		 * path.
+		 */
+		if (perf_get_aux(handle)) {
+			enum arm_spe_pmu_buf_fault_action act;
+
+			act = arm_spe_pmu_buf_get_fault_act(handle);
+			if (act == SPE_PMU_BUF_FAULT_ACT_SPURIOUS)
+				arm_spe_perf_aux_output_end(handle);
+			else
+				write_sysreg_s(0, SYS_PMBSR_EL1);
+		}
+
+		/*
+		 * This may also contain ECOUNT, but nobody else should
+		 * be looking at period_left, since we forbid frequency
+		 * based sampling.
+		 */
+		local64_set(&hwc->period_left, read_sysreg_s(SYS_PMSICR_EL1));
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	hwc->state |= PERF_HES_STOPPED;
+}
+
+static int arm_spe_pmu_add(struct perf_event *event, int flags)
+{
+	int ret = 0;
+	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int cpu = event->cpu == -1 ? smp_processor_id() : event->cpu;
+
+	if (!cpumask_test_cpu(cpu, &spe_pmu->supported_cpus))
+		return -ENOENT;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START) {
+		arm_spe_pmu_start(event, PERF_EF_RELOAD);
+		if (hwc->state & PERF_HES_STOPPED)
+			ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void arm_spe_pmu_del(struct perf_event *event, int flags)
+{
+	arm_spe_pmu_stop(event, PERF_EF_UPDATE);
+}
+
+static void arm_spe_pmu_read(struct perf_event *event)
+{
+}
+
+static void *arm_spe_pmu_setup_aux(int cpu, void **pages, int nr_pages,
+				   bool snapshot)
+{
+	int i;
+	struct page **pglist;
+	struct arm_spe_pmu_buf *buf;
+
+	/* We need at least two pages for this to work. */
+	if (nr_pages < 2)
+		return NULL;
+
+	/*
+	 * We require an even number of pages for snapshot mode, so that
+	 * we can effectively treat the buffer as consisting of two equal
+	 * parts and give userspace a fighting chance of getting some
+	 * useful data out of it.
+	 */
+	if (!nr_pages || (snapshot && (nr_pages & 1)))
+		return NULL;
+
+	if (cpu == -1)
+		cpu = raw_smp_processor_id();
+
+	buf = kzalloc_node(sizeof(*buf), GFP_KERNEL, cpu_to_node(cpu));
+	if (!buf)
+		return NULL;
+
+	pglist = kcalloc(nr_pages, sizeof(*pglist), GFP_KERNEL);
+	if (!pglist)
+		goto out_free_buf;
+
+	for (i = 0; i < nr_pages; ++i) {
+		struct page *page = virt_to_page(pages[i]);
+
+		if (PagePrivate(page)) {
+			pr_warn("unexpected high-order page for auxbuf!");
+			goto out_free_pglist;
+		}
+
+		pglist[i] = virt_to_page(pages[i]);
+	}
+
+	buf->base = vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!buf->base)
+		goto out_free_pglist;
+
+	buf->nr_pages	= nr_pages;
+	buf->snapshot	= snapshot;
+
+	kfree(pglist);
+	return buf;
+
+out_free_pglist:
+	kfree(pglist);
+out_free_buf:
+	kfree(buf);
+	return NULL;
+}
+
+static void arm_spe_pmu_free_aux(void *aux)
+{
+	struct arm_spe_pmu_buf *buf = aux;
+
+	vunmap(buf->base);
+	kfree(buf);
+}
+
+/* Initialisation and teardown functions */
+static int arm_spe_pmu_perf_init(struct arm_spe_pmu *spe_pmu)
+{
+	static atomic_t pmu_idx = ATOMIC_INIT(-1);
+
+	int idx;
+	char *name;
+	struct device *dev = &spe_pmu->pdev->dev;
+
+	spe_pmu->pmu = (struct pmu) {
+		.module = THIS_MODULE,
+		.capabilities	= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE,
+		.attr_groups	= arm_spe_pmu_attr_groups,
+		/*
+		 * We hitch a ride on the software context here, so that
+		 * we can support per-task profiling (which is not possible
+		 * with the invalid context as it doesn't get sched callbacks).
+		 * This requires that userspace either uses a dummy event for
+		 * perf_event_open, since the aux buffer is not setup until
+		 * a subsequent mmap, or creates the profiling event in a
+		 * disabled state and explicitly PERF_EVENT_IOC_ENABLEs it
+		 * once the buffer has been created.
+		 */
+		.task_ctx_nr	= perf_sw_context,
+		.event_init	= arm_spe_pmu_event_init,
+		.add		= arm_spe_pmu_add,
+		.del		= arm_spe_pmu_del,
+		.start		= arm_spe_pmu_start,
+		.stop		= arm_spe_pmu_stop,
+		.read		= arm_spe_pmu_read,
+		.setup_aux	= arm_spe_pmu_setup_aux,
+		.free_aux	= arm_spe_pmu_free_aux,
+	};
+
+	idx = atomic_inc_return(&pmu_idx);
+	name = devm_kasprintf(dev, GFP_KERNEL, "%s_%d", PMUNAME, idx);
+	return perf_pmu_register(&spe_pmu->pmu, name, -1);
+}
+
+static void arm_spe_pmu_perf_destroy(struct arm_spe_pmu *spe_pmu)
+{
+	perf_pmu_unregister(&spe_pmu->pmu);
+}
+
+static void __arm_spe_pmu_dev_probe(void *info)
+{
+	int fld;
+	u64 reg;
+	struct arm_spe_pmu *spe_pmu = info;
+	struct device *dev = &spe_pmu->pdev->dev;
+
+	fld = cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64DFR0_EL1),
+						   ID_AA64DFR0_PMSVER_SHIFT);
+	if (!fld) {
+		dev_err(dev,
+			"unsupported ID_AA64DFR0_EL1.PMSVer [%d] on CPU %d\n",
+			fld, smp_processor_id());
+		return;
+	}
+
+	/* Read PMBIDR first to determine whether or not we have access */
+	reg = read_sysreg_s(SYS_PMBIDR_EL1);
+	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT)) {
+		dev_err(dev,
+			"profiling buffer owned by higher exception level\n");
+		return;
+	}
+
+	/* Minimum alignment. If it's out-of-range, then fail the probe */
+	fld = reg >> SYS_PMBIDR_EL1_ALIGN_SHIFT & SYS_PMBIDR_EL1_ALIGN_MASK;
+	spe_pmu->align = 1 << fld;
+	if (spe_pmu->align > SZ_2K) {
+		dev_err(dev, "unsupported PMBIDR.Align [%d] on CPU %d\n",
+			fld, smp_processor_id());
+		return;
+	}
+
+	/* It's now safe to read PMSIDR and figure out what we've got */
+	reg = read_sysreg_s(SYS_PMSIDR_EL1);
+	if (reg & BIT(SYS_PMSIDR_EL1_FE_SHIFT))
+		spe_pmu->features |= SPE_PMU_FEAT_FILT_EVT;
+
+	if (reg & BIT(SYS_PMSIDR_EL1_FT_SHIFT))
+		spe_pmu->features |= SPE_PMU_FEAT_FILT_TYP;
+
+	if (reg & BIT(SYS_PMSIDR_EL1_FL_SHIFT))
+		spe_pmu->features |= SPE_PMU_FEAT_FILT_LAT;
+
+	if (reg & BIT(SYS_PMSIDR_EL1_ARCHINST_SHIFT))
+		spe_pmu->features |= SPE_PMU_FEAT_ARCH_INST;
+
+	if (reg & BIT(SYS_PMSIDR_EL1_LDS_SHIFT))
+		spe_pmu->features |= SPE_PMU_FEAT_LDS;
+
+	if (reg & BIT(SYS_PMSIDR_EL1_ERND_SHIFT))
+		spe_pmu->features |= SPE_PMU_FEAT_ERND;
+
+	/* This field has a spaced out encoding, so just use a look-up */
+	fld = reg >> SYS_PMSIDR_EL1_INTERVAL_SHIFT & SYS_PMSIDR_EL1_INTERVAL_MASK;
+	switch (fld) {
+	case 0:
+		spe_pmu->min_period = 256;
+		break;
+	case 2:
+		spe_pmu->min_period = 512;
+		break;
+	case 3:
+		spe_pmu->min_period = 768;
+		break;
+	case 4:
+		spe_pmu->min_period = 1024;
+		break;
+	case 5:
+		spe_pmu->min_period = 1536;
+		break;
+	case 6:
+		spe_pmu->min_period = 2048;
+		break;
+	case 7:
+		spe_pmu->min_period = 3072;
+		break;
+	default:
+		dev_warn(dev, "unknown PMSIDR_EL1.Interval [%d]; assuming 8\n",
+			 fld);
+		/* Fallthrough */
+	case 8:
+		spe_pmu->min_period = 4096;
+	}
+
+	/* Maximum record size. If it's out-of-range, then fail the probe */
+	fld = reg >> SYS_PMSIDR_EL1_MAXSIZE_SHIFT & SYS_PMSIDR_EL1_MAXSIZE_MASK;
+	spe_pmu->max_record_sz = 1 << fld;
+	if (spe_pmu->max_record_sz > SZ_2K || spe_pmu->max_record_sz < 16) {
+		dev_err(dev, "unsupported PMSIDR_EL1.MaxSize [%d] on CPU %d\n",
+			fld, smp_processor_id());
+		return;
+	}
+
+	fld = reg >> SYS_PMSIDR_EL1_COUNTSIZE_SHIFT & SYS_PMSIDR_EL1_COUNTSIZE_MASK;
+	switch (fld) {
+	default:
+		dev_warn(dev, "unknown PMSIDR_EL1.CountSize [%d]; assuming 2\n",
+			 fld);
+		/* Fallthrough */
+	case 2:
+		spe_pmu->counter_sz = 12;
+	}
+
+	dev_info(dev,
+		 "probed for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n",
+		 cpumask_pr_args(&spe_pmu->supported_cpus),
+		 spe_pmu->max_record_sz, spe_pmu->align, spe_pmu->features);
+
+	spe_pmu->features |= SPE_PMU_FEAT_DEV_PROBED;
+	return;
+}
+
+static void __arm_spe_pmu_reset_local(void)
+{
+	/*
+	 * This is probably overkill, as we have no idea where we're
+	 * draining any buffered data to...
+	 */
+	arm_spe_pmu_disable_and_drain_local();
+
+	/* Reset the buffer base pointer */
+	write_sysreg_s(0, SYS_PMBPTR_EL1);
+	isb();
+
+	/* Clear any pending management interrupts */
+	write_sysreg_s(0, SYS_PMBSR_EL1);
+	isb();
+}
+
+static void __arm_spe_pmu_setup_one(void *info)
+{
+	struct arm_spe_pmu *spe_pmu = info;
+
+	__arm_spe_pmu_reset_local();
+	enable_percpu_irq(spe_pmu->irq, IRQ_TYPE_NONE);
+}
+
+static void __arm_spe_pmu_stop_one(void *info)
+{
+	struct arm_spe_pmu *spe_pmu = info;
+
+	disable_percpu_irq(spe_pmu->irq);
+	__arm_spe_pmu_reset_local();
+}
+
+static int arm_spe_pmu_cpu_startup(unsigned int cpu, struct hlist_node *node)
+{
+	struct arm_spe_pmu *spe_pmu;
+
+	spe_pmu = hlist_entry_safe(node, struct arm_spe_pmu, hotplug_node);
+	if (!cpumask_test_cpu(cpu, &spe_pmu->supported_cpus))
+		return 0;
+
+	__arm_spe_pmu_setup_one(spe_pmu);
+	return 0;
+}
+
+static int arm_spe_pmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
+{
+	struct arm_spe_pmu *spe_pmu;
+
+	spe_pmu = hlist_entry_safe(node, struct arm_spe_pmu, hotplug_node);
+	if (!cpumask_test_cpu(cpu, &spe_pmu->supported_cpus))
+		return 0;
+
+	__arm_spe_pmu_stop_one(spe_pmu);
+	return 0;
+}
+
+static int arm_spe_pmu_dev_init(struct arm_spe_pmu *spe_pmu)
+{
+	int ret;
+	cpumask_t *mask = &spe_pmu->supported_cpus;
+
+	/* Make sure we probe the hardware on a relevant CPU */
+	ret = smp_call_function_any(mask,  __arm_spe_pmu_dev_probe, spe_pmu, 1);
+	if (ret || !(spe_pmu->features & SPE_PMU_FEAT_DEV_PROBED))
+		return -ENXIO;
+
+	/* Request our PPIs (note that the IRQ is still disabled) */
+	ret = request_percpu_irq(spe_pmu->irq, arm_spe_pmu_irq_handler, DRVNAME,
+				 spe_pmu->handle);
+	if (ret)
+		return ret;
+
+	/*
+	 * Register our hotplug notifier now so we don't miss any events.
+	 * This will enable the IRQ for any supported CPUs that are already
+	 * up.
+	 */
+	ret = cpuhp_state_add_instance(arm_spe_pmu_online,
+				       &spe_pmu->hotplug_node);
+	if (ret)
+		free_percpu_irq(spe_pmu->irq, spe_pmu->handle);
+
+	return ret;
+}
+
+static void arm_spe_pmu_dev_teardown(struct arm_spe_pmu *spe_pmu)
+{
+	cpuhp_state_remove_instance(arm_spe_pmu_online, &spe_pmu->hotplug_node);
+	free_percpu_irq(spe_pmu->irq, spe_pmu->handle);
+}
+
+/* Driver and device probing */
+static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu)
+{
+	struct platform_device *pdev = spe_pmu->pdev;
+	int irq = platform_get_irq(pdev, 0);
+
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ (%d)\n", irq);
+		return -ENXIO;
+	}
+
+	if (!irq_is_percpu(irq)) {
+		dev_err(&pdev->dev, "expected PPI but got SPI (%d)\n", irq);
+		return -EINVAL;
+	}
+
+	if (irq_get_percpu_devid_partition(irq, &spe_pmu->supported_cpus)) {
+		dev_err(&pdev->dev, "failed to get PPI partition (%d)\n", irq);
+		return -EINVAL;
+	}
+
+	spe_pmu->irq = irq;
+	return 0;
+}
+
+static const struct of_device_id arm_spe_pmu_of_match[] = {
+	{ .compatible = "arm,statistical-profiling-extension-v1", .data = (void *)1 },
+	{ /* Sentinel */ },
+};
+
+static int arm_spe_pmu_device_dt_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct arm_spe_pmu *spe_pmu;
+	struct device *dev = &pdev->dev;
+
+	spe_pmu = devm_kzalloc(dev, sizeof(*spe_pmu), GFP_KERNEL);
+	if (!spe_pmu) {
+		dev_err(dev, "failed to allocate spe_pmu\n");
+		return -ENOMEM;
+	}
+
+	spe_pmu->handle = alloc_percpu(typeof(*spe_pmu->handle));
+	if (!spe_pmu->handle)
+		return -ENOMEM;
+
+	spe_pmu->pdev = pdev;
+	platform_set_drvdata(pdev, spe_pmu);
+
+	ret = arm_spe_pmu_irq_probe(spe_pmu);
+	if (ret)
+		goto out_free_handle;
+
+	ret = arm_spe_pmu_dev_init(spe_pmu);
+	if (ret)
+		goto out_free_handle;
+
+	ret = arm_spe_pmu_perf_init(spe_pmu);
+	if (ret)
+		goto out_teardown_dev;
+
+	return 0;
+
+out_teardown_dev:
+	arm_spe_pmu_dev_teardown(spe_pmu);
+out_free_handle:
+	free_percpu(spe_pmu->handle);
+	return ret;
+}
+
+static int arm_spe_pmu_device_remove(struct platform_device *pdev)
+{
+	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
+
+	arm_spe_pmu_perf_destroy(spe_pmu);
+	arm_spe_pmu_dev_teardown(spe_pmu);
+	free_percpu(spe_pmu->handle);
+	return 0;
+}
+
+static struct platform_driver arm_spe_pmu_driver = {
+	.driver	= {
+		.name		= DRVNAME,
+		.of_match_table	= of_match_ptr(arm_spe_pmu_of_match),
+	},
+	.probe	= arm_spe_pmu_device_dt_probe,
+	.remove	= arm_spe_pmu_device_remove,
+};
+
+static int __init arm_spe_pmu_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, DRVNAME,
+				      arm_spe_pmu_cpu_startup,
+				      arm_spe_pmu_cpu_teardown);
+	if (ret < 0)
+		return ret;
+	arm_spe_pmu_online = ret;
+
+	ret = platform_driver_register(&arm_spe_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(arm_spe_pmu_online);
+
+	return ret;
+}
+
+static void __exit arm_spe_pmu_exit(void)
+{
+	platform_driver_unregister(&arm_spe_pmu_driver);
+	cpuhp_remove_multi_state(arm_spe_pmu_online);
+}
+
+module_init(arm_spe_pmu_init);
+module_exit(arm_spe_pmu_exit);
+
+MODULE_DESCRIPTION("Perf driver for the ARMv8.2 Statistical Profiling Extension");
+MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
+MODULE_LICENSE("GPL v2");

drivers/perf/hisilicon/Makefile

@@ -0,0 +1 @@
+obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o

drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c

@@ -0,0 +1,463 @@
+/*
+ * HiSilicon SoC DDRC uncore Hardware event counters support
+ *
+ * Copyright (C) 2017 Hisilicon Limited
+ * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *         Anurup M <anurup.m@huawei.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/acpi.h>
+#include <linux/bug.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* DDRC register definition */
+#define DDRC_PERF_CTRL		0x010
+#define DDRC_FLUX_WR		0x380
+#define DDRC_FLUX_RD		0x384
+#define DDRC_FLUX_WCMD          0x388
+#define DDRC_FLUX_RCMD          0x38c
+#define DDRC_PRE_CMD            0x3c0
+#define DDRC_ACT_CMD            0x3c4
+#define DDRC_BNK_CHG            0x3c8
+#define DDRC_RNK_CHG            0x3cc
+#define DDRC_EVENT_CTRL         0x6C0
+#define DDRC_INT_MASK		0x6c8
+#define DDRC_INT_STATUS		0x6cc
+#define DDRC_INT_CLEAR		0x6d0
+
+/* DDRC has 8-counters */
+#define DDRC_NR_COUNTERS	0x8
+#define DDRC_PERF_CTRL_EN	0x2
+
+/*
+ * For DDRC PMU, there are eight-events and every event has been mapped
+ * to fixed-purpose counters which register offset is not consistent.
+ * Therefore there is no write event type and we assume that event
+ * code (0 to 7) is equal to counter index in PMU driver.
+ */
+#define GET_DDRC_EVENTID(hwc)	(hwc->config_base & 0x7)
+
+static const u32 ddrc_reg_off[] = {
+	DDRC_FLUX_WR, DDRC_FLUX_RD, DDRC_FLUX_WCMD, DDRC_FLUX_RCMD,
+	DDRC_PRE_CMD, DDRC_ACT_CMD, DDRC_BNK_CHG, DDRC_RNK_CHG
+};
+
+/*
+ * Select the counter register offset using the counter index.
+ * In DDRC there are no programmable counter, the count
+ * is readed form the statistics counter register itself.
+ */
+static u32 hisi_ddrc_pmu_get_counter_offset(int cntr_idx)
+{
+	return ddrc_reg_off[cntr_idx];
+}
+
+static u64 hisi_ddrc_pmu_read_counter(struct hisi_pmu *ddrc_pmu,
+				      struct hw_perf_event *hwc)
+{
+	/* Use event code as counter index */
+	u32 idx = GET_DDRC_EVENTID(hwc);
+
+	if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) {
+		dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx);
+		return 0;
+	}
+
+	return readl(ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx));
+}
+
+static void hisi_ddrc_pmu_write_counter(struct hisi_pmu *ddrc_pmu,
+					struct hw_perf_event *hwc, u64 val)
+{
+	u32 idx = GET_DDRC_EVENTID(hwc);
+
+	if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) {
+		dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx);
+		return;
+	}
+
+	writel((u32)val,
+	       ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx));
+}
+
+/*
+ * For DDRC PMU, event has been mapped to fixed-purpose counter by hardware,
+ * so there is no need to write event type.
+ */
+static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx,
+				       u32 type)
+{
+}
+
+static void hisi_ddrc_pmu_start_counters(struct hisi_pmu *ddrc_pmu)
+{
+	u32 val;
+
+	/* Set perf_enable in DDRC_PERF_CTRL to start event counting */
+	val = readl(ddrc_pmu->base + DDRC_PERF_CTRL);
+	val |= DDRC_PERF_CTRL_EN;
+	writel(val, ddrc_pmu->base + DDRC_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_stop_counters(struct hisi_pmu *ddrc_pmu)
+{
+	u32 val;
+
+	/* Clear perf_enable in DDRC_PERF_CTRL to stop event counting */
+	val = readl(ddrc_pmu->base + DDRC_PERF_CTRL);
+	val &= ~DDRC_PERF_CTRL_EN;
+	writel(val, ddrc_pmu->base + DDRC_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_enable_counter(struct hisi_pmu *ddrc_pmu,
+					 struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Set counter index(event code) in DDRC_EVENT_CTRL register */
+	val = readl(ddrc_pmu->base + DDRC_EVENT_CTRL);
+	val |= (1 << GET_DDRC_EVENTID(hwc));
+	writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL);
+}
+
+static void hisi_ddrc_pmu_disable_counter(struct hisi_pmu *ddrc_pmu,
+					  struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Clear counter index(event code) in DDRC_EVENT_CTRL register */
+	val = readl(ddrc_pmu->base + DDRC_EVENT_CTRL);
+	val &= ~(1 << GET_DDRC_EVENTID(hwc));
+	writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL);
+}
+
+static int hisi_ddrc_pmu_get_event_idx(struct perf_event *event)
+{
+	struct hisi_pmu *ddrc_pmu = to_hisi_pmu(event->pmu);
+	unsigned long *used_mask = ddrc_pmu->pmu_events.used_mask;
+	struct hw_perf_event *hwc = &event->hw;
+	/* For DDRC PMU, we use event code as counter index */
+	int idx = GET_DDRC_EVENTID(hwc);
+
+	if (test_bit(idx, used_mask))
+		return -EAGAIN;
+
+	set_bit(idx, used_mask);
+
+	return idx;
+}
+
+static void hisi_ddrc_pmu_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+					     struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 0 to enable interrupt */
+	val = readl(ddrc_pmu->base + DDRC_INT_MASK);
+	val &= ~(1 << GET_DDRC_EVENTID(hwc));
+	writel(val, ddrc_pmu->base + DDRC_INT_MASK);
+}
+
+static void hisi_ddrc_pmu_disable_counter_int(struct hisi_pmu *ddrc_pmu,
+					      struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 1 to mask interrupt */
+	val = readl(ddrc_pmu->base + DDRC_INT_MASK);
+	val |= (1 << GET_DDRC_EVENTID(hwc));
+	writel(val, ddrc_pmu->base + DDRC_INT_MASK);
+}
+
+static irqreturn_t hisi_ddrc_pmu_isr(int irq, void *dev_id)
+{
+	struct hisi_pmu *ddrc_pmu = dev_id;
+	struct perf_event *event;
+	unsigned long overflown;
+	int idx;
+
+	/* Read the DDRC_INT_STATUS register */
+	overflown = readl(ddrc_pmu->base + DDRC_INT_STATUS);
+	if (!overflown)
+		return IRQ_NONE;
+
+	/*
+	 * Find the counter index which overflowed if the bit was set
+	 * and handle it
+	 */
+	for_each_set_bit(idx, &overflown, DDRC_NR_COUNTERS) {
+		/* Write 1 to clear the IRQ status flag */
+		writel((1 << idx), ddrc_pmu->base + DDRC_INT_CLEAR);
+
+		/* Get the corresponding event struct */
+		event = ddrc_pmu->pmu_events.hw_events[idx];
+		if (!event)
+			continue;
+
+		hisi_uncore_pmu_event_update(event);
+		hisi_uncore_pmu_set_event_period(event);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int hisi_ddrc_pmu_init_irq(struct hisi_pmu *ddrc_pmu,
+				  struct platform_device *pdev)
+{
+	int irq, ret;
+
+	/* Read and init IRQ */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "DDRC PMU get irq fail; irq:%d\n", irq);
+		return irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, hisi_ddrc_pmu_isr,
+			       IRQF_NOBALANCING | IRQF_NO_THREAD,
+			       dev_name(&pdev->dev), ddrc_pmu);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Fail to request IRQ:%d ret:%d\n", irq, ret);
+		return ret;
+	}
+
+	ddrc_pmu->irq = irq;
+
+	return 0;
+}
+
+static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = {
+	{ "HISI0233", },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match);
+
+static int hisi_ddrc_pmu_init_data(struct platform_device *pdev,
+				   struct hisi_pmu *ddrc_pmu)
+{
+	struct resource *res;
+
+	/*
+	 * Use the SCCL_ID and DDRC channel ID to identify the
+	 * DDRC PMU, while SCCL_ID is in MPIDR[aff2].
+	 */
+	if (device_property_read_u32(&pdev->dev, "hisilicon,ch-id",
+				     &ddrc_pmu->index_id)) {
+		dev_err(&pdev->dev, "Can not read ddrc channel-id!\n");
+		return -EINVAL;
+	}
+
+	if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+				     &ddrc_pmu->sccl_id)) {
+		dev_err(&pdev->dev, "Can not read ddrc sccl-id!\n");
+		return -EINVAL;
+	}
+	/* DDRC PMUs only share the same SCCL */
+	ddrc_pmu->ccl_id = -1;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ddrc_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ddrc_pmu->base)) {
+		dev_err(&pdev->dev, "ioremap failed for ddrc_pmu resource\n");
+		return PTR_ERR(ddrc_pmu->base);
+	}
+
+	return 0;
+}
+
+static struct attribute *hisi_ddrc_pmu_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-4"),
+	NULL,
+};
+
+static const struct attribute_group hisi_ddrc_pmu_format_group = {
+	.name = "format",
+	.attrs = hisi_ddrc_pmu_format_attr,
+};
+
+static struct attribute *hisi_ddrc_pmu_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(flux_wr,		0x00),
+	HISI_PMU_EVENT_ATTR(flux_rd,		0x01),
+	HISI_PMU_EVENT_ATTR(flux_wcmd,		0x02),
+	HISI_PMU_EVENT_ATTR(flux_rcmd,		0x03),
+	HISI_PMU_EVENT_ATTR(pre_cmd,		0x04),
+	HISI_PMU_EVENT_ATTR(act_cmd,		0x05),
+	HISI_PMU_EVENT_ATTR(rnk_chg,		0x06),
+	HISI_PMU_EVENT_ATTR(rw_chg,		0x07),
+	NULL,
+};
+
+static const struct attribute_group hisi_ddrc_pmu_events_group = {
+	.name = "events",
+	.attrs = hisi_ddrc_pmu_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_ddrc_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static const struct attribute_group hisi_ddrc_pmu_cpumask_attr_group = {
+	.attrs = hisi_ddrc_pmu_cpumask_attrs,
+};
+
+static const struct attribute_group *hisi_ddrc_pmu_attr_groups[] = {
+	&hisi_ddrc_pmu_format_group,
+	&hisi_ddrc_pmu_events_group,
+	&hisi_ddrc_pmu_cpumask_attr_group,
+	NULL,
+};
+
+static const struct hisi_uncore_ops hisi_uncore_ddrc_ops = {
+	.write_evtype           = hisi_ddrc_pmu_write_evtype,
+	.get_event_idx		= hisi_ddrc_pmu_get_event_idx,
+	.start_counters		= hisi_ddrc_pmu_start_counters,
+	.stop_counters		= hisi_ddrc_pmu_stop_counters,
+	.enable_counter		= hisi_ddrc_pmu_enable_counter,
+	.disable_counter	= hisi_ddrc_pmu_disable_counter,
+	.enable_counter_int	= hisi_ddrc_pmu_enable_counter_int,
+	.disable_counter_int	= hisi_ddrc_pmu_disable_counter_int,
+	.write_counter		= hisi_ddrc_pmu_write_counter,
+	.read_counter		= hisi_ddrc_pmu_read_counter,
+};
+
+static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev,
+				   struct hisi_pmu *ddrc_pmu)
+{
+	int ret;
+
+	ret = hisi_ddrc_pmu_init_data(pdev, ddrc_pmu);
+	if (ret)
+		return ret;
+
+	ret = hisi_ddrc_pmu_init_irq(ddrc_pmu, pdev);
+	if (ret)
+		return ret;
+
+	ddrc_pmu->num_counters = DDRC_NR_COUNTERS;
+	ddrc_pmu->counter_bits = 32;
+	ddrc_pmu->ops = &hisi_uncore_ddrc_ops;
+	ddrc_pmu->dev = &pdev->dev;
+	ddrc_pmu->on_cpu = -1;
+	ddrc_pmu->check_event = 7;
+
+	return 0;
+}
+
+static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
+{
+	struct hisi_pmu *ddrc_pmu;
+	char *name;
+	int ret;
+
+	ddrc_pmu = devm_kzalloc(&pdev->dev, sizeof(*ddrc_pmu), GFP_KERNEL);
+	if (!ddrc_pmu)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, ddrc_pmu);
+
+	ret = hisi_ddrc_pmu_dev_probe(pdev, ddrc_pmu);
+	if (ret)
+		return ret;
+
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+				       &ddrc_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug;\n", ret);
+		return ret;
+	}
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_ddrc%u",
+			      ddrc_pmu->sccl_id, ddrc_pmu->index_id);
+	ddrc_pmu->pmu = (struct pmu) {
+		.name		= name,
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= hisi_uncore_pmu_event_init,
+		.pmu_enable	= hisi_uncore_pmu_enable,
+		.pmu_disable	= hisi_uncore_pmu_disable,
+		.add		= hisi_uncore_pmu_add,
+		.del		= hisi_uncore_pmu_del,
+		.start		= hisi_uncore_pmu_start,
+		.stop		= hisi_uncore_pmu_stop,
+		.read		= hisi_uncore_pmu_read,
+		.attr_groups	= hisi_ddrc_pmu_attr_groups,
+	};
+
+	ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1);
+	if (ret) {
+		dev_err(ddrc_pmu->dev, "DDRC PMU register failed!\n");
+		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+					    &ddrc_pmu->node);
+	}
+
+	return ret;
+}
+
+static int hisi_ddrc_pmu_remove(struct platform_device *pdev)
+{
+	struct hisi_pmu *ddrc_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&ddrc_pmu->pmu);
+	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+				    &ddrc_pmu->node);
+
+	return 0;
+}
+
+static struct platform_driver hisi_ddrc_pmu_driver = {
+	.driver = {
+		.name = "hisi_ddrc_pmu",
+		.acpi_match_table = ACPI_PTR(hisi_ddrc_pmu_acpi_match),
+	},
+	.probe = hisi_ddrc_pmu_probe,
+	.remove = hisi_ddrc_pmu_remove,
+};
+
+static int __init hisi_ddrc_pmu_module_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+				      "AP_PERF_ARM_HISI_DDRC_ONLINE",
+				      hisi_uncore_pmu_online_cpu,
+				      hisi_uncore_pmu_offline_cpu);
+	if (ret) {
+		pr_err("DDRC PMU: setup hotplug, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = platform_driver_register(&hisi_ddrc_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE);
+
+	return ret;
+}
+module_init(hisi_ddrc_pmu_module_init);
+
+static void __exit hisi_ddrc_pmu_module_exit(void)
+{
+	platform_driver_unregister(&hisi_ddrc_pmu_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE);
+
+}
+module_exit(hisi_ddrc_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon SoC DDRC uncore PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Shaokun Zhang <zhangshaokun@hisilicon.com>");
+MODULE_AUTHOR("Anurup M <anurup.m@huawei.com>");

drivers/perf/hisilicon/hisi_uncore_hha_pmu.c

@@ -0,0 +1,473 @@
+/*
+ * HiSilicon SoC HHA uncore Hardware event counters support
+ *
+ * Copyright (C) 2017 Hisilicon Limited
+ * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *         Anurup M <anurup.m@huawei.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/acpi.h>
+#include <linux/bug.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* HHA register definition */
+#define HHA_INT_MASK		0x0804
+#define HHA_INT_STATUS		0x0808
+#define HHA_INT_CLEAR		0x080C
+#define HHA_PERF_CTRL		0x1E00
+#define HHA_EVENT_CTRL		0x1E04
+#define HHA_EVENT_TYPE0		0x1E80
+/*
+ * Each counter is 48-bits and [48:63] are reserved
+ * which are Read-As-Zero and Writes-Ignored.
+ */
+#define HHA_CNT0_LOWER		0x1F00
+
+/* HHA has 16-counters */
+#define HHA_NR_COUNTERS		0x10
+
+#define HHA_PERF_CTRL_EN	0x1
+#define HHA_EVTYPE_NONE		0xff
+
+/*
+ * Select the counter register offset using the counter index
+ * each counter is 48-bits.
+ */
+static u32 hisi_hha_pmu_get_counter_offset(int cntr_idx)
+{
+	return (HHA_CNT0_LOWER + (cntr_idx * 8));
+}
+
+static u64 hisi_hha_pmu_read_counter(struct hisi_pmu *hha_pmu,
+				     struct hw_perf_event *hwc)
+{
+	u32 idx = hwc->idx;
+
+	if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) {
+		dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx);
+		return 0;
+	}
+
+	/* Read 64 bits and like L3C, top 16 bits are RAZ */
+	return readq(hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx));
+}
+
+static void hisi_hha_pmu_write_counter(struct hisi_pmu *hha_pmu,
+				       struct hw_perf_event *hwc, u64 val)
+{
+	u32 idx = hwc->idx;
+
+	if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) {
+		dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx);
+		return;
+	}
+
+	/* Write 64 bits and like L3C, top 16 bits are WI */
+	writeq(val, hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx));
+}
+
+static void hisi_hha_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx,
+				      u32 type)
+{
+	u32 reg, reg_idx, shift, val;
+
+	/*
+	 * Select the appropriate event select register(HHA_EVENT_TYPEx).
+	 * There are 4 event select registers for the 16 hardware counters.
+	 * Event code is 8-bits and for the first 4 hardware counters,
+	 * HHA_EVENT_TYPE0 is chosen. For the next 4 hardware counters,
+	 * HHA_EVENT_TYPE1 is chosen and so on.
+	 */
+	reg = HHA_EVENT_TYPE0 + 4 * (idx / 4);
+	reg_idx = idx % 4;
+	shift = 8 * reg_idx;
+
+	/* Write event code to HHA_EVENT_TYPEx register */
+	val = readl(hha_pmu->base + reg);
+	val &= ~(HHA_EVTYPE_NONE << shift);
+	val |= (type << shift);
+	writel(val, hha_pmu->base + reg);
+}
+
+static void hisi_hha_pmu_start_counters(struct hisi_pmu *hha_pmu)
+{
+	u32 val;
+
+	/*
+	 * Set perf_enable bit in HHA_PERF_CTRL to start event
+	 * counting for all enabled counters.
+	 */
+	val = readl(hha_pmu->base + HHA_PERF_CTRL);
+	val |= HHA_PERF_CTRL_EN;
+	writel(val, hha_pmu->base + HHA_PERF_CTRL);
+}
+
+static void hisi_hha_pmu_stop_counters(struct hisi_pmu *hha_pmu)
+{
+	u32 val;
+
+	/*
+	 * Clear perf_enable bit in HHA_PERF_CTRL to stop event
+	 * counting for all enabled counters.
+	 */
+	val = readl(hha_pmu->base + HHA_PERF_CTRL);
+	val &= ~(HHA_PERF_CTRL_EN);
+	writel(val, hha_pmu->base + HHA_PERF_CTRL);
+}
+
+static void hisi_hha_pmu_enable_counter(struct hisi_pmu *hha_pmu,
+					struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Enable counter index in HHA_EVENT_CTRL register */
+	val = readl(hha_pmu->base + HHA_EVENT_CTRL);
+	val |= (1 << hwc->idx);
+	writel(val, hha_pmu->base + HHA_EVENT_CTRL);
+}
+
+static void hisi_hha_pmu_disable_counter(struct hisi_pmu *hha_pmu,
+					 struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Clear counter index in HHA_EVENT_CTRL register */
+	val = readl(hha_pmu->base + HHA_EVENT_CTRL);
+	val &= ~(1 << hwc->idx);
+	writel(val, hha_pmu->base + HHA_EVENT_CTRL);
+}
+
+static void hisi_hha_pmu_enable_counter_int(struct hisi_pmu *hha_pmu,
+					    struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 0 to enable interrupt */
+	val = readl(hha_pmu->base + HHA_INT_MASK);
+	val &= ~(1 << hwc->idx);
+	writel(val, hha_pmu->base + HHA_INT_MASK);
+}
+
+static void hisi_hha_pmu_disable_counter_int(struct hisi_pmu *hha_pmu,
+					     struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 1 to mask interrupt */
+	val = readl(hha_pmu->base + HHA_INT_MASK);
+	val |= (1 << hwc->idx);
+	writel(val, hha_pmu->base + HHA_INT_MASK);
+}
+
+static irqreturn_t hisi_hha_pmu_isr(int irq, void *dev_id)
+{
+	struct hisi_pmu *hha_pmu = dev_id;
+	struct perf_event *event;
+	unsigned long overflown;
+	int idx;
+
+	/* Read HHA_INT_STATUS register */
+	overflown = readl(hha_pmu->base + HHA_INT_STATUS);
+	if (!overflown)
+		return IRQ_NONE;
+
+	/*
+	 * Find the counter index which overflowed if the bit was set
+	 * and handle it
+	 */
+	for_each_set_bit(idx, &overflown, HHA_NR_COUNTERS) {
+		/* Write 1 to clear the IRQ status flag */
+		writel((1 << idx), hha_pmu->base + HHA_INT_CLEAR);
+
+		/* Get the corresponding event struct */
+		event = hha_pmu->pmu_events.hw_events[idx];
+		if (!event)
+			continue;
+
+		hisi_uncore_pmu_event_update(event);
+		hisi_uncore_pmu_set_event_period(event);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int hisi_hha_pmu_init_irq(struct hisi_pmu *hha_pmu,
+				 struct platform_device *pdev)
+{
+	int irq, ret;
+
+	/* Read and init IRQ */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "HHA PMU get irq fail; irq:%d\n", irq);
+		return irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, hisi_hha_pmu_isr,
+			      IRQF_NOBALANCING | IRQF_NO_THREAD,
+			      dev_name(&pdev->dev), hha_pmu);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Fail to request IRQ:%d ret:%d\n", irq, ret);
+		return ret;
+	}
+
+	hha_pmu->irq = irq;
+
+	return 0;
+}
+
+static const struct acpi_device_id hisi_hha_pmu_acpi_match[] = {
+	{ "HISI0243", },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, hisi_hha_pmu_acpi_match);
+
+static int hisi_hha_pmu_init_data(struct platform_device *pdev,
+				  struct hisi_pmu *hha_pmu)
+{
+	unsigned long long id;
+	struct resource *res;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
+				       "_UID", NULL, &id);
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+
+	hha_pmu->index_id = id;
+
+	/*
+	 * Use SCCL_ID and UID to identify the HHA PMU, while
+	 * SCCL_ID is in MPIDR[aff2].
+	 */
+	if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+				     &hha_pmu->sccl_id)) {
+		dev_err(&pdev->dev, "Can not read hha sccl-id!\n");
+		return -EINVAL;
+	}
+	/* HHA PMUs only share the same SCCL */
+	hha_pmu->ccl_id = -1;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	hha_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(hha_pmu->base)) {
+		dev_err(&pdev->dev, "ioremap failed for hha_pmu resource\n");
+		return PTR_ERR(hha_pmu->base);
+	}
+
+	return 0;
+}
+
+static struct attribute *hisi_hha_pmu_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	NULL,
+};
+
+static const struct attribute_group hisi_hha_pmu_format_group = {
+	.name = "format",
+	.attrs = hisi_hha_pmu_format_attr,
+};
+
+static struct attribute *hisi_hha_pmu_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(rx_ops_num,		0x00),
+	HISI_PMU_EVENT_ATTR(rx_outer,		0x01),
+	HISI_PMU_EVENT_ATTR(rx_sccl,		0x02),
+	HISI_PMU_EVENT_ATTR(rx_ccix,		0x03),
+	HISI_PMU_EVENT_ATTR(rx_wbi,		0x04),
+	HISI_PMU_EVENT_ATTR(rx_wbip,		0x05),
+	HISI_PMU_EVENT_ATTR(rx_wtistash,	0x11),
+	HISI_PMU_EVENT_ATTR(rd_ddr_64b,		0x1c),
+	HISI_PMU_EVENT_ATTR(wr_dr_64b,		0x1d),
+	HISI_PMU_EVENT_ATTR(rd_ddr_128b,	0x1e),
+	HISI_PMU_EVENT_ATTR(wr_ddr_128b,	0x1f),
+	HISI_PMU_EVENT_ATTR(spill_num,		0x20),
+	HISI_PMU_EVENT_ATTR(spill_success,	0x21),
+	HISI_PMU_EVENT_ATTR(bi_num,		0x23),
+	HISI_PMU_EVENT_ATTR(mediated_num,	0x32),
+	HISI_PMU_EVENT_ATTR(tx_snp_num,		0x33),
+	HISI_PMU_EVENT_ATTR(tx_snp_outer,	0x34),
+	HISI_PMU_EVENT_ATTR(tx_snp_ccix,	0x35),
+	HISI_PMU_EVENT_ATTR(rx_snprspdata,	0x38),
+	HISI_PMU_EVENT_ATTR(rx_snprsp_outer,	0x3c),
+	HISI_PMU_EVENT_ATTR(sdir-lookup,	0x40),
+	HISI_PMU_EVENT_ATTR(edir-lookup,	0x41),
+	HISI_PMU_EVENT_ATTR(sdir-hit,		0x42),
+	HISI_PMU_EVENT_ATTR(edir-hit,		0x43),
+	HISI_PMU_EVENT_ATTR(sdir-home-migrate,	0x4c),
+	HISI_PMU_EVENT_ATTR(edir-home-migrate,  0x4d),
+	NULL,
+};
+
+static const struct attribute_group hisi_hha_pmu_events_group = {
+	.name = "events",
+	.attrs = hisi_hha_pmu_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_hha_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static const struct attribute_group hisi_hha_pmu_cpumask_attr_group = {
+	.attrs = hisi_hha_pmu_cpumask_attrs,
+};
+
+static const struct attribute_group *hisi_hha_pmu_attr_groups[] = {
+	&hisi_hha_pmu_format_group,
+	&hisi_hha_pmu_events_group,
+	&hisi_hha_pmu_cpumask_attr_group,
+	NULL,
+};
+
+static const struct hisi_uncore_ops hisi_uncore_hha_ops = {
+	.write_evtype		= hisi_hha_pmu_write_evtype,
+	.get_event_idx		= hisi_uncore_pmu_get_event_idx,
+	.start_counters		= hisi_hha_pmu_start_counters,
+	.stop_counters		= hisi_hha_pmu_stop_counters,
+	.enable_counter		= hisi_hha_pmu_enable_counter,
+	.disable_counter	= hisi_hha_pmu_disable_counter,
+	.enable_counter_int	= hisi_hha_pmu_enable_counter_int,
+	.disable_counter_int	= hisi_hha_pmu_disable_counter_int,
+	.write_counter		= hisi_hha_pmu_write_counter,
+	.read_counter		= hisi_hha_pmu_read_counter,
+};
+
+static int hisi_hha_pmu_dev_probe(struct platform_device *pdev,
+				  struct hisi_pmu *hha_pmu)
+{
+	int ret;
+
+	ret = hisi_hha_pmu_init_data(pdev, hha_pmu);
+	if (ret)
+		return ret;
+
+	ret = hisi_hha_pmu_init_irq(hha_pmu, pdev);
+	if (ret)
+		return ret;
+
+	hha_pmu->num_counters = HHA_NR_COUNTERS;
+	hha_pmu->counter_bits = 48;
+	hha_pmu->ops = &hisi_uncore_hha_ops;
+	hha_pmu->dev = &pdev->dev;
+	hha_pmu->on_cpu = -1;
+	hha_pmu->check_event = 0x65;
+
+	return 0;
+}
+
+static int hisi_hha_pmu_probe(struct platform_device *pdev)
+{
+	struct hisi_pmu *hha_pmu;
+	char *name;
+	int ret;
+
+	hha_pmu = devm_kzalloc(&pdev->dev, sizeof(*hha_pmu), GFP_KERNEL);
+	if (!hha_pmu)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, hha_pmu);
+
+	ret = hisi_hha_pmu_dev_probe(pdev, hha_pmu);
+	if (ret)
+		return ret;
+
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
+				       &hha_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+		return ret;
+	}
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u",
+			      hha_pmu->sccl_id, hha_pmu->index_id);
+	hha_pmu->pmu = (struct pmu) {
+		.name		= name,
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= hisi_uncore_pmu_event_init,
+		.pmu_enable	= hisi_uncore_pmu_enable,
+		.pmu_disable	= hisi_uncore_pmu_disable,
+		.add		= hisi_uncore_pmu_add,
+		.del		= hisi_uncore_pmu_del,
+		.start		= hisi_uncore_pmu_start,
+		.stop		= hisi_uncore_pmu_stop,
+		.read		= hisi_uncore_pmu_read,
+		.attr_groups	= hisi_hha_pmu_attr_groups,
+	};
+
+	ret = perf_pmu_register(&hha_pmu->pmu, name, -1);
+	if (ret) {
+		dev_err(hha_pmu->dev, "HHA PMU register failed!\n");
+		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
+					    &hha_pmu->node);
+	}
+
+	return ret;
+}
+
+static int hisi_hha_pmu_remove(struct platform_device *pdev)
+{
+	struct hisi_pmu *hha_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&hha_pmu->pmu);
+	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
+				    &hha_pmu->node);
+
+	return 0;
+}
+
+static struct platform_driver hisi_hha_pmu_driver = {
+	.driver = {
+		.name = "hisi_hha_pmu",
+		.acpi_match_table = ACPI_PTR(hisi_hha_pmu_acpi_match),
+	},
+	.probe = hisi_hha_pmu_probe,
+	.remove = hisi_hha_pmu_remove,
+};
+
+static int __init hisi_hha_pmu_module_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
+				      "AP_PERF_ARM_HISI_HHA_ONLINE",
+				      hisi_uncore_pmu_online_cpu,
+				      hisi_uncore_pmu_offline_cpu);
+	if (ret) {
+		pr_err("HHA PMU: Error setup hotplug, ret = %d;\n", ret);
+		return ret;
+	}
+
+	ret = platform_driver_register(&hisi_hha_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE);
+
+	return ret;
+}
+module_init(hisi_hha_pmu_module_init);
+
+static void __exit hisi_hha_pmu_module_exit(void)
+{
+	platform_driver_unregister(&hisi_hha_pmu_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE);
+}
+module_exit(hisi_hha_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon SoC HHA uncore PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Shaokun Zhang <zhangshaokun@hisilicon.com>");
+MODULE_AUTHOR("Anurup M <anurup.m@huawei.com>");

drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c

@@ -0,0 +1,463 @@
+/*
+ * HiSilicon SoC L3C uncore Hardware event counters support
+ *
+ * Copyright (C) 2017 Hisilicon Limited
+ * Author: Anurup M <anurup.m@huawei.com>
+ *         Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/acpi.h>
+#include <linux/bug.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* L3C register definition */
+#define L3C_PERF_CTRL		0x0408
+#define L3C_INT_MASK		0x0800
+#define L3C_INT_STATUS		0x0808
+#define L3C_INT_CLEAR		0x080c
+#define L3C_EVENT_CTRL	        0x1c00
+#define L3C_EVENT_TYPE0		0x1d00
+/*
+ * Each counter is 48-bits and [48:63] are reserved
+ * which are Read-As-Zero and Writes-Ignored.
+ */
+#define L3C_CNTR0_LOWER		0x1e00
+
+/* L3C has 8-counters */
+#define L3C_NR_COUNTERS		0x8
+
+#define L3C_PERF_CTRL_EN	0x20000
+#define L3C_EVTYPE_NONE		0xff
+
+/*
+ * Select the counter register offset using the counter index
+ */
+static u32 hisi_l3c_pmu_get_counter_offset(int cntr_idx)
+{
+	return (L3C_CNTR0_LOWER + (cntr_idx * 8));
+}
+
+static u64 hisi_l3c_pmu_read_counter(struct hisi_pmu *l3c_pmu,
+				     struct hw_perf_event *hwc)
+{
+	u32 idx = hwc->idx;
+
+	if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) {
+		dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx);
+		return 0;
+	}
+
+	/* Read 64-bits and the upper 16 bits are RAZ */
+	return readq(l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx));
+}
+
+static void hisi_l3c_pmu_write_counter(struct hisi_pmu *l3c_pmu,
+				       struct hw_perf_event *hwc, u64 val)
+{
+	u32 idx = hwc->idx;
+
+	if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) {
+		dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx);
+		return;
+	}
+
+	/* Write 64-bits and the upper 16 bits are WI */
+	writeq(val, l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx));
+}
+
+static void hisi_l3c_pmu_write_evtype(struct hisi_pmu *l3c_pmu, int idx,
+				      u32 type)
+{
+	u32 reg, reg_idx, shift, val;
+
+	/*
+	 * Select the appropriate event select register(L3C_EVENT_TYPE0/1).
+	 * There are 2 event select registers for the 8 hardware counters.
+	 * Event code is 8-bits and for the former 4 hardware counters,
+	 * L3C_EVENT_TYPE0 is chosen. For the latter 4 hardware counters,
+	 * L3C_EVENT_TYPE1 is chosen.
+	 */
+	reg = L3C_EVENT_TYPE0 + (idx / 4) * 4;
+	reg_idx = idx % 4;
+	shift = 8 * reg_idx;
+
+	/* Write event code to L3C_EVENT_TYPEx Register */
+	val = readl(l3c_pmu->base + reg);
+	val &= ~(L3C_EVTYPE_NONE << shift);
+	val |= (type << shift);
+	writel(val, l3c_pmu->base + reg);
+}
+
+static void hisi_l3c_pmu_start_counters(struct hisi_pmu *l3c_pmu)
+{
+	u32 val;
+
+	/*
+	 * Set perf_enable bit in L3C_PERF_CTRL register to start counting
+	 * for all enabled counters.
+	 */
+	val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+	val |= L3C_PERF_CTRL_EN;
+	writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+}
+
+static void hisi_l3c_pmu_stop_counters(struct hisi_pmu *l3c_pmu)
+{
+	u32 val;
+
+	/*
+	 * Clear perf_enable bit in L3C_PERF_CTRL register to stop counting
+	 * for all enabled counters.
+	 */
+	val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+	val &= ~(L3C_PERF_CTRL_EN);
+	writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+}
+
+static void hisi_l3c_pmu_enable_counter(struct hisi_pmu *l3c_pmu,
+					struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Enable counter index in L3C_EVENT_CTRL register */
+	val = readl(l3c_pmu->base + L3C_EVENT_CTRL);
+	val |= (1 << hwc->idx);
+	writel(val, l3c_pmu->base + L3C_EVENT_CTRL);
+}
+
+static void hisi_l3c_pmu_disable_counter(struct hisi_pmu *l3c_pmu,
+					 struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Clear counter index in L3C_EVENT_CTRL register */
+	val = readl(l3c_pmu->base + L3C_EVENT_CTRL);
+	val &= ~(1 << hwc->idx);
+	writel(val, l3c_pmu->base + L3C_EVENT_CTRL);
+}
+
+static void hisi_l3c_pmu_enable_counter_int(struct hisi_pmu *l3c_pmu,
+					    struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(l3c_pmu->base + L3C_INT_MASK);
+	/* Write 0 to enable interrupt */
+	val &= ~(1 << hwc->idx);
+	writel(val, l3c_pmu->base + L3C_INT_MASK);
+}
+
+static void hisi_l3c_pmu_disable_counter_int(struct hisi_pmu *l3c_pmu,
+					     struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(l3c_pmu->base + L3C_INT_MASK);
+	/* Write 1 to mask interrupt */
+	val |= (1 << hwc->idx);
+	writel(val, l3c_pmu->base + L3C_INT_MASK);
+}
+
+static irqreturn_t hisi_l3c_pmu_isr(int irq, void *dev_id)
+{
+	struct hisi_pmu *l3c_pmu = dev_id;
+	struct perf_event *event;
+	unsigned long overflown;
+	int idx;
+
+	/* Read L3C_INT_STATUS register */
+	overflown = readl(l3c_pmu->base + L3C_INT_STATUS);
+	if (!overflown)
+		return IRQ_NONE;
+
+	/*
+	 * Find the counter index which overflowed if the bit was set
+	 * and handle it.
+	 */
+	for_each_set_bit(idx, &overflown, L3C_NR_COUNTERS) {
+		/* Write 1 to clear the IRQ status flag */
+		writel((1 << idx), l3c_pmu->base + L3C_INT_CLEAR);
+
+		/* Get the corresponding event struct */
+		event = l3c_pmu->pmu_events.hw_events[idx];
+		if (!event)
+			continue;
+
+		hisi_uncore_pmu_event_update(event);
+		hisi_uncore_pmu_set_event_period(event);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int hisi_l3c_pmu_init_irq(struct hisi_pmu *l3c_pmu,
+				 struct platform_device *pdev)
+{
+	int irq, ret;
+
+	/* Read and init IRQ */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "L3C PMU get irq fail; irq:%d\n", irq);
+		return irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, hisi_l3c_pmu_isr,
+			       IRQF_NOBALANCING | IRQF_NO_THREAD,
+			       dev_name(&pdev->dev), l3c_pmu);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Fail to request IRQ:%d ret:%d\n", irq, ret);
+		return ret;
+	}
+
+	l3c_pmu->irq = irq;
+
+	return 0;
+}
+
+static const struct acpi_device_id hisi_l3c_pmu_acpi_match[] = {
+	{ "HISI0213", },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match);
+
+static int hisi_l3c_pmu_init_data(struct platform_device *pdev,
+				  struct hisi_pmu *l3c_pmu)
+{
+	unsigned long long id;
+	struct resource *res;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
+				       "_UID", NULL, &id);
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+
+	l3c_pmu->index_id = id;
+
+	/*
+	 * Use the SCCL_ID and CCL_ID to identify the L3C PMU, while
+	 * SCCL_ID is in MPIDR[aff2] and CCL_ID is in MPIDR[aff1].
+	 */
+	if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+				     &l3c_pmu->sccl_id)) {
+		dev_err(&pdev->dev, "Can not read l3c sccl-id!\n");
+		return -EINVAL;
+	}
+
+	if (device_property_read_u32(&pdev->dev, "hisilicon,ccl-id",
+				     &l3c_pmu->ccl_id)) {
+		dev_err(&pdev->dev, "Can not read l3c ccl-id!\n");
+		return -EINVAL;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	l3c_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(l3c_pmu->base)) {
+		dev_err(&pdev->dev, "ioremap failed for l3c_pmu resource\n");
+		return PTR_ERR(l3c_pmu->base);
+	}
+
+	return 0;
+}
+
+static struct attribute *hisi_l3c_pmu_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	NULL,
+};
+
+static const struct attribute_group hisi_l3c_pmu_format_group = {
+	.name = "format",
+	.attrs = hisi_l3c_pmu_format_attr,
+};
+
+static struct attribute *hisi_l3c_pmu_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(rd_cpipe,		0x00),
+	HISI_PMU_EVENT_ATTR(wr_cpipe,		0x01),
+	HISI_PMU_EVENT_ATTR(rd_hit_cpipe,	0x02),
+	HISI_PMU_EVENT_ATTR(wr_hit_cpipe,	0x03),
+	HISI_PMU_EVENT_ATTR(victim_num,		0x04),
+	HISI_PMU_EVENT_ATTR(rd_spipe,		0x20),
+	HISI_PMU_EVENT_ATTR(wr_spipe,		0x21),
+	HISI_PMU_EVENT_ATTR(rd_hit_spipe,	0x22),
+	HISI_PMU_EVENT_ATTR(wr_hit_spipe,	0x23),
+	HISI_PMU_EVENT_ATTR(back_invalid,	0x29),
+	HISI_PMU_EVENT_ATTR(retry_cpu,		0x40),
+	HISI_PMU_EVENT_ATTR(retry_ring,		0x41),
+	HISI_PMU_EVENT_ATTR(prefetch_drop,	0x42),
+	NULL,
+};
+
+static const struct attribute_group hisi_l3c_pmu_events_group = {
+	.name = "events",
+	.attrs = hisi_l3c_pmu_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_l3c_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static const struct attribute_group hisi_l3c_pmu_cpumask_attr_group = {
+	.attrs = hisi_l3c_pmu_cpumask_attrs,
+};
+
+static const struct attribute_group *hisi_l3c_pmu_attr_groups[] = {
+	&hisi_l3c_pmu_format_group,
+	&hisi_l3c_pmu_events_group,
+	&hisi_l3c_pmu_cpumask_attr_group,
+	NULL,
+};
+
+static const struct hisi_uncore_ops hisi_uncore_l3c_ops = {
+	.write_evtype		= hisi_l3c_pmu_write_evtype,
+	.get_event_idx		= hisi_uncore_pmu_get_event_idx,
+	.start_counters		= hisi_l3c_pmu_start_counters,
+	.stop_counters		= hisi_l3c_pmu_stop_counters,
+	.enable_counter		= hisi_l3c_pmu_enable_counter,
+	.disable_counter	= hisi_l3c_pmu_disable_counter,
+	.enable_counter_int	= hisi_l3c_pmu_enable_counter_int,
+	.disable_counter_int	= hisi_l3c_pmu_disable_counter_int,
+	.write_counter		= hisi_l3c_pmu_write_counter,
+	.read_counter		= hisi_l3c_pmu_read_counter,
+};
+
+static int hisi_l3c_pmu_dev_probe(struct platform_device *pdev,
+				  struct hisi_pmu *l3c_pmu)
+{
+	int ret;
+
+	ret = hisi_l3c_pmu_init_data(pdev, l3c_pmu);
+	if (ret)
+		return ret;
+
+	ret = hisi_l3c_pmu_init_irq(l3c_pmu, pdev);
+	if (ret)
+		return ret;
+
+	l3c_pmu->num_counters = L3C_NR_COUNTERS;
+	l3c_pmu->counter_bits = 48;
+	l3c_pmu->ops = &hisi_uncore_l3c_ops;
+	l3c_pmu->dev = &pdev->dev;
+	l3c_pmu->on_cpu = -1;
+	l3c_pmu->check_event = 0x59;
+
+	return 0;
+}
+
+static int hisi_l3c_pmu_probe(struct platform_device *pdev)
+{
+	struct hisi_pmu *l3c_pmu;
+	char *name;
+	int ret;
+
+	l3c_pmu = devm_kzalloc(&pdev->dev, sizeof(*l3c_pmu), GFP_KERNEL);
+	if (!l3c_pmu)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, l3c_pmu);
+
+	ret = hisi_l3c_pmu_dev_probe(pdev, l3c_pmu);
+	if (ret)
+		return ret;
+
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
+				       &l3c_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+		return ret;
+	}
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
+			      l3c_pmu->sccl_id, l3c_pmu->index_id);
+	l3c_pmu->pmu = (struct pmu) {
+		.name		= name,
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= hisi_uncore_pmu_event_init,
+		.pmu_enable	= hisi_uncore_pmu_enable,
+		.pmu_disable	= hisi_uncore_pmu_disable,
+		.add		= hisi_uncore_pmu_add,
+		.del		= hisi_uncore_pmu_del,
+		.start		= hisi_uncore_pmu_start,
+		.stop		= hisi_uncore_pmu_stop,
+		.read		= hisi_uncore_pmu_read,
+		.attr_groups	= hisi_l3c_pmu_attr_groups,
+	};
+
+	ret = perf_pmu_register(&l3c_pmu->pmu, name, -1);
+	if (ret) {
+		dev_err(l3c_pmu->dev, "L3C PMU register failed!\n");
+		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
+					    &l3c_pmu->node);
+	}
+
+	return ret;
+}
+
+static int hisi_l3c_pmu_remove(struct platform_device *pdev)
+{
+	struct hisi_pmu *l3c_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&l3c_pmu->pmu);
+	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
+				    &l3c_pmu->node);
+
+	return 0;
+}
+
+static struct platform_driver hisi_l3c_pmu_driver = {
+	.driver = {
+		.name = "hisi_l3c_pmu",
+		.acpi_match_table = ACPI_PTR(hisi_l3c_pmu_acpi_match),
+	},
+	.probe = hisi_l3c_pmu_probe,
+	.remove = hisi_l3c_pmu_remove,
+};
+
+static int __init hisi_l3c_pmu_module_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
+				      "AP_PERF_ARM_HISI_L3_ONLINE",
+				      hisi_uncore_pmu_online_cpu,
+				      hisi_uncore_pmu_offline_cpu);
+	if (ret) {
+		pr_err("L3C PMU: Error setup hotplug, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = platform_driver_register(&hisi_l3c_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE);
+
+	return ret;
+}
+module_init(hisi_l3c_pmu_module_init);
+
+static void __exit hisi_l3c_pmu_module_exit(void)
+{
+	platform_driver_unregister(&hisi_l3c_pmu_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE);
+}
+module_exit(hisi_l3c_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon SoC L3C uncore PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Anurup M <anurup.m@huawei.com>");
+MODULE_AUTHOR("Shaokun Zhang <zhangshaokun@hisilicon.com>");

drivers/perf/hisilicon/hisi_uncore_pmu.c

@@ -0,0 +1,447 @@
+/*
+ * HiSilicon SoC Hardware event counters support
+ *
+ * Copyright (C) 2017 Hisilicon Limited
+ * Author: Anurup M <anurup.m@huawei.com>
+ *         Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+
+#include <asm/local64.h>
+
+#include "hisi_uncore_pmu.h"
+
+#define HISI_GET_EVENTID(ev) (ev->hw.config_base & 0xff)
+#define HISI_MAX_PERIOD(nr) (BIT_ULL(nr) - 1)
+
+/*
+ * PMU format attributes
+ */
+ssize_t hisi_format_sysfs_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct dev_ext_attribute *eattr;
+
+	eattr = container_of(attr, struct dev_ext_attribute, attr);
+
+	return sprintf(buf, "%s\n", (char *)eattr->var);
+}
+
+/*
+ * PMU event attributes
+ */
+ssize_t hisi_event_sysfs_show(struct device *dev,
+			      struct device_attribute *attr, char *page)
+{
+	struct dev_ext_attribute *eattr;
+
+	eattr = container_of(attr, struct dev_ext_attribute, attr);
+
+	return sprintf(page, "config=0x%lx\n", (unsigned long)eattr->var);
+}
+
+/*
+ * sysfs cpumask attributes. For uncore PMU, we only have a single CPU to show
+ */
+ssize_t hisi_cpumask_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev));
+
+	return sprintf(buf, "%d\n", hisi_pmu->on_cpu);
+}
+
+static bool hisi_validate_event_group(struct perf_event *event)
+{
+	struct perf_event *sibling, *leader = event->group_leader;
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	/* Include count for the event */
+	int counters = 1;
+
+	if (!is_software_event(leader)) {
+		/*
+		 * We must NOT create groups containing mixed PMUs, although
+		 * software events are acceptable
+		 */
+		if (leader->pmu != event->pmu)
+			return false;
+
+		/* Increment counter for the leader */
+		if (leader != event)
+			counters++;
+	}
+
+	list_for_each_entry(sibling, &event->group_leader->sibling_list,
+			    group_entry) {
+		if (is_software_event(sibling))
+			continue;
+		if (sibling->pmu != event->pmu)
+			return false;
+		/* Increment counter for each sibling */
+		counters++;
+	}
+
+	/* The group can not count events more than the counters in the HW */
+	return counters <= hisi_pmu->num_counters;
+}
+
+int hisi_uncore_pmu_counter_valid(struct hisi_pmu *hisi_pmu, int idx)
+{
+	return idx >= 0 && idx < hisi_pmu->num_counters;
+}
+
+int hisi_uncore_pmu_get_event_idx(struct perf_event *event)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	unsigned long *used_mask = hisi_pmu->pmu_events.used_mask;
+	u32 num_counters = hisi_pmu->num_counters;
+	int idx;
+
+	idx = find_first_zero_bit(used_mask, num_counters);
+	if (idx == num_counters)
+		return -EAGAIN;
+
+	set_bit(idx, used_mask);
+
+	return idx;
+}
+
+static void hisi_uncore_pmu_clear_event_idx(struct hisi_pmu *hisi_pmu, int idx)
+{
+	if (!hisi_uncore_pmu_counter_valid(hisi_pmu, idx)) {
+		dev_err(hisi_pmu->dev, "Unsupported event index:%d!\n", idx);
+		return;
+	}
+
+	clear_bit(idx, hisi_pmu->pmu_events.used_mask);
+}
+
+int hisi_uncore_pmu_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hisi_pmu *hisi_pmu;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/*
+	 * We do not support sampling as the counters are all
+	 * shared by all CPU cores in a CPU die(SCCL). Also we
+	 * do not support attach to a task(per-process mode)
+	 */
+	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+		return -EOPNOTSUPP;
+
+	/* counters do not have these bits */
+	if (event->attr.exclude_user	||
+	    event->attr.exclude_kernel	||
+	    event->attr.exclude_host	||
+	    event->attr.exclude_guest	||
+	    event->attr.exclude_hv	||
+	    event->attr.exclude_idle)
+		return -EINVAL;
+
+	/*
+	 *  The uncore counters not specific to any CPU, so cannot
+	 *  support per-task
+	 */
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	/*
+	 * Validate if the events in group does not exceed the
+	 * available counters in hardware.
+	 */
+	if (!hisi_validate_event_group(event))
+		return -EINVAL;
+
+	hisi_pmu = to_hisi_pmu(event->pmu);
+	if (event->attr.config > hisi_pmu->check_event)
+		return -EINVAL;
+
+	if (hisi_pmu->on_cpu == -1)
+		return -EINVAL;
+	/*
+	 * We don't assign an index until we actually place the event onto
+	 * hardware. Use -1 to signify that we haven't decided where to put it
+	 * yet.
+	 */
+	hwc->idx		= -1;
+	hwc->config_base	= event->attr.config;
+
+	/* Enforce to use the same CPU for all events in this PMU */
+	event->cpu = hisi_pmu->on_cpu;
+
+	return 0;
+}
+
+/*
+ * Set the counter to count the event that we're interested in,
+ * and enable interrupt and counter.
+ */
+static void hisi_uncore_pmu_enable_event(struct perf_event *event)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	hisi_pmu->ops->write_evtype(hisi_pmu, hwc->idx,
+				    HISI_GET_EVENTID(event));
+
+	hisi_pmu->ops->enable_counter_int(hisi_pmu, hwc);
+	hisi_pmu->ops->enable_counter(hisi_pmu, hwc);
+}
+
+/*
+ * Disable counter and interrupt.
+ */
+static void hisi_uncore_pmu_disable_event(struct perf_event *event)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	hisi_pmu->ops->disable_counter(hisi_pmu, hwc);
+	hisi_pmu->ops->disable_counter_int(hisi_pmu, hwc);
+}
+
+void hisi_uncore_pmu_set_event_period(struct perf_event *event)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * The HiSilicon PMU counters support 32 bits or 48 bits, depending on
+	 * the PMU. We reduce it to 2^(counter_bits - 1) to account for the
+	 * extreme interrupt latency. So we could hopefully handle the overflow
+	 * interrupt before another 2^(counter_bits - 1) events occur and the
+	 * counter overtakes its previous value.
+	 */
+	u64 val = BIT_ULL(hisi_pmu->counter_bits - 1);
+
+	local64_set(&hwc->prev_count, val);
+	/* Write start value to the hardware event counter */
+	hisi_pmu->ops->write_counter(hisi_pmu, hwc, val);
+}
+
+void hisi_uncore_pmu_event_update(struct perf_event *event)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	u64 delta, prev_raw_count, new_raw_count;
+
+	do {
+		/* Read the count from the counter register */
+		new_raw_count = hisi_pmu->ops->read_counter(hisi_pmu, hwc);
+		prev_raw_count = local64_read(&hwc->prev_count);
+	} while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+				 new_raw_count) != prev_raw_count);
+	/*
+	 * compute the delta
+	 */
+	delta = (new_raw_count - prev_raw_count) &
+		HISI_MAX_PERIOD(hisi_pmu->counter_bits);
+	local64_add(delta, &event->count);
+}
+
+void hisi_uncore_pmu_start(struct perf_event *event, int flags)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+	hwc->state = 0;
+	hisi_uncore_pmu_set_event_period(event);
+
+	if (flags & PERF_EF_RELOAD) {
+		u64 prev_raw_count =  local64_read(&hwc->prev_count);
+
+		hisi_pmu->ops->write_counter(hisi_pmu, hwc, prev_raw_count);
+	}
+
+	hisi_uncore_pmu_enable_event(event);
+	perf_event_update_userpage(event);
+}
+
+void hisi_uncore_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	hisi_uncore_pmu_disable_event(event);
+	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+	hwc->state |= PERF_HES_STOPPED;
+
+	if (hwc->state & PERF_HES_UPTODATE)
+		return;
+
+	/* Read hardware counter and update the perf counter statistics */
+	hisi_uncore_pmu_event_update(event);
+	hwc->state |= PERF_HES_UPTODATE;
+}
+
+int hisi_uncore_pmu_add(struct perf_event *event, int flags)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
+	/* Get an available counter index for counting */
+	idx = hisi_pmu->ops->get_event_idx(event);
+	if (idx < 0)
+		return idx;
+
+	event->hw.idx = idx;
+	hisi_pmu->pmu_events.hw_events[idx] = event;
+
+	if (flags & PERF_EF_START)
+		hisi_uncore_pmu_start(event, PERF_EF_RELOAD);
+
+	return 0;
+}
+
+void hisi_uncore_pmu_del(struct perf_event *event, int flags)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	hisi_uncore_pmu_stop(event, PERF_EF_UPDATE);
+	hisi_uncore_pmu_clear_event_idx(hisi_pmu, hwc->idx);
+	perf_event_update_userpage(event);
+	hisi_pmu->pmu_events.hw_events[hwc->idx] = NULL;
+}
+
+void hisi_uncore_pmu_read(struct perf_event *event)
+{
+	/* Read hardware counter and update the perf counter statistics */
+	hisi_uncore_pmu_event_update(event);
+}
+
+void hisi_uncore_pmu_enable(struct pmu *pmu)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(pmu);
+	int enabled = bitmap_weight(hisi_pmu->pmu_events.used_mask,
+				    hisi_pmu->num_counters);
+
+	if (!enabled)
+		return;
+
+	hisi_pmu->ops->start_counters(hisi_pmu);
+}
+
+void hisi_uncore_pmu_disable(struct pmu *pmu)
+{
+	struct hisi_pmu *hisi_pmu = to_hisi_pmu(pmu);
+
+	hisi_pmu->ops->stop_counters(hisi_pmu);
+}
+
+/*
+ * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1.
+ * If multi-threading is supported, SCCL_ID is in MPIDR[aff3] and CCL_ID
+ * is in MPIDR[aff2]; if not, SCCL_ID is in MPIDR[aff2] and CCL_ID is
+ * in MPIDR[aff1]. If this changes in future, this shall be updated.
+ */
+static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
+{
+	u64 mpidr = read_cpuid_mpidr();
+
+	if (mpidr & MPIDR_MT_BITMASK) {
+		if (sccl_id)
+			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3);
+		if (ccl_id)
+			*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+	} else {
+		if (sccl_id)
+			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+		if (ccl_id)
+			*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	}
+}
+
+/*
+ * Check whether the CPU is associated with this uncore PMU
+ */
+static bool hisi_pmu_cpu_is_associated_pmu(struct hisi_pmu *hisi_pmu)
+{
+	int sccl_id, ccl_id;
+
+	if (hisi_pmu->ccl_id == -1) {
+		/* If CCL_ID is -1, the PMU only shares the same SCCL */
+		hisi_read_sccl_and_ccl_id(&sccl_id, NULL);
+
+		return sccl_id == hisi_pmu->sccl_id;
+	}
+
+	hisi_read_sccl_and_ccl_id(&sccl_id, &ccl_id);
+
+	return sccl_id == hisi_pmu->sccl_id && ccl_id == hisi_pmu->ccl_id;
+}
+
+int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct hisi_pmu *hisi_pmu = hlist_entry_safe(node, struct hisi_pmu,
+						     node);
+
+	if (!hisi_pmu_cpu_is_associated_pmu(hisi_pmu))
+		return 0;
+
+	cpumask_set_cpu(cpu, &hisi_pmu->associated_cpus);
+
+	/* If another CPU is already managing this PMU, simply return. */
+	if (hisi_pmu->on_cpu != -1)
+		return 0;
+
+	/* Use this CPU in cpumask for event counting */
+	hisi_pmu->on_cpu = cpu;
+
+	/* Overflow interrupt also should use the same CPU */
+	WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(cpu)));
+
+	return 0;
+}
+
+int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct hisi_pmu *hisi_pmu = hlist_entry_safe(node, struct hisi_pmu,
+						     node);
+	cpumask_t pmu_online_cpus;
+	unsigned int target;
+
+	if (!cpumask_test_and_clear_cpu(cpu, &hisi_pmu->associated_cpus))
+		return 0;
+
+	/* Nothing to do if this CPU doesn't own the PMU */
+	if (hisi_pmu->on_cpu != cpu)
+		return 0;
+
+	/* Give up ownership of the PMU */
+	hisi_pmu->on_cpu = -1;
+
+	/* Choose a new CPU to migrate ownership of the PMU to */
+	cpumask_and(&pmu_online_cpus, &hisi_pmu->associated_cpus,
+		    cpu_online_mask);
+	target = cpumask_any_but(&pmu_online_cpus, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+
+	perf_pmu_migrate_context(&hisi_pmu->pmu, cpu, target);
+	/* Use this CPU for event counting */
+	hisi_pmu->on_cpu = target;
+	WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(target)));
+
+	return 0;
+}

drivers/perf/hisilicon/hisi_uncore_pmu.h

@@ -0,0 +1,102 @@
+/*
+ * HiSilicon SoC Hardware event counters support
+ *
+ * Copyright (C) 2017 Hisilicon Limited
+ * Author: Anurup M <anurup.m@huawei.com>
+ *         Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __HISI_UNCORE_PMU_H__
+#define __HISI_UNCORE_PMU_H__
+
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "hisi_pmu: " fmt
+
+#define HISI_MAX_COUNTERS 0x10
+#define to_hisi_pmu(p)	(container_of(p, struct hisi_pmu, pmu))
+
+#define HISI_PMU_ATTR(_name, _func, _config)				\
+	(&((struct dev_ext_attribute[]) {				\
+		{ __ATTR(_name, 0444, _func, NULL), (void *)_config }   \
+	})[0].attr.attr)
+
+#define HISI_PMU_FORMAT_ATTR(_name, _config)		\
+	HISI_PMU_ATTR(_name, hisi_format_sysfs_show, (void *)_config)
+#define HISI_PMU_EVENT_ATTR(_name, _config)		\
+	HISI_PMU_ATTR(_name, hisi_event_sysfs_show, (unsigned long)_config)
+
+struct hisi_pmu;
+
+struct hisi_uncore_ops {
+	void (*write_evtype)(struct hisi_pmu *, int, u32);
+	int (*get_event_idx)(struct perf_event *);
+	u64 (*read_counter)(struct hisi_pmu *, struct hw_perf_event *);
+	void (*write_counter)(struct hisi_pmu *, struct hw_perf_event *, u64);
+	void (*enable_counter)(struct hisi_pmu *, struct hw_perf_event *);
+	void (*disable_counter)(struct hisi_pmu *, struct hw_perf_event *);
+	void (*enable_counter_int)(struct hisi_pmu *, struct hw_perf_event *);
+	void (*disable_counter_int)(struct hisi_pmu *, struct hw_perf_event *);
+	void (*start_counters)(struct hisi_pmu *);
+	void (*stop_counters)(struct hisi_pmu *);
+};
+
+struct hisi_pmu_hwevents {
+	struct perf_event *hw_events[HISI_MAX_COUNTERS];
+	DECLARE_BITMAP(used_mask, HISI_MAX_COUNTERS);
+};
+
+/* Generic pmu struct for different pmu types */
+struct hisi_pmu {
+	struct pmu pmu;
+	const struct hisi_uncore_ops *ops;
+	struct hisi_pmu_hwevents pmu_events;
+	/* associated_cpus: All CPUs associated with the PMU */
+	cpumask_t associated_cpus;
+	/* CPU used for counting */
+	int on_cpu;
+	int irq;
+	struct device *dev;
+	struct hlist_node node;
+	int sccl_id;
+	int ccl_id;
+	void __iomem *base;
+	/* the ID of the PMU modules */
+	u32 index_id;
+	int num_counters;
+	int counter_bits;
+	/* check event code range */
+	int check_event;
+};
+
+int hisi_uncore_pmu_counter_valid(struct hisi_pmu *hisi_pmu, int idx);
+int hisi_uncore_pmu_get_event_idx(struct perf_event *event);
+void hisi_uncore_pmu_read(struct perf_event *event);
+int hisi_uncore_pmu_add(struct perf_event *event, int flags);
+void hisi_uncore_pmu_del(struct perf_event *event, int flags);
+void hisi_uncore_pmu_start(struct perf_event *event, int flags);
+void hisi_uncore_pmu_stop(struct perf_event *event, int flags);
+void hisi_uncore_pmu_set_event_period(struct perf_event *event);
+void hisi_uncore_pmu_event_update(struct perf_event *event);
+int hisi_uncore_pmu_event_init(struct perf_event *event);
+void hisi_uncore_pmu_enable(struct pmu *pmu);
+void hisi_uncore_pmu_disable(struct pmu *pmu);
+ssize_t hisi_event_sysfs_show(struct device *dev,
+			      struct device_attribute *attr, char *buf);
+ssize_t hisi_format_sysfs_show(struct device *dev,
+			       struct device_attribute *attr, char *buf);
+ssize_t hisi_cpumask_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *buf);
+int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node);
+int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node);
+#endif /* __HISI_UNCORE_PMU_H__ */

drivers/perf/qcom_l2_pmu.c

@@ -92,6 +92,21 @@
 
 #define reg_idx(reg, i)         (((i) * IA_L2_REG_OFFSET) + reg##_BASE)
 
+/*
+ * Events
+ */
+#define L2_EVENT_CYCLES                    0xfe
+#define L2_EVENT_DCACHE_OPS                0x400
+#define L2_EVENT_ICACHE_OPS                0x401
+#define L2_EVENT_TLBI                      0x402
+#define L2_EVENT_BARRIERS                  0x403
+#define L2_EVENT_TOTAL_READS               0x405
+#define L2_EVENT_TOTAL_WRITES              0x406
+#define L2_EVENT_TOTAL_REQUESTS            0x407
+#define L2_EVENT_LDREX                     0x420
+#define L2_EVENT_STREX                     0x421
+#define L2_EVENT_CLREX                     0x422
+
 static DEFINE_RAW_SPINLOCK(l2_access_lock);
 
 /**
@@ -700,9 +715,12 @@ static struct attribute_group l2_cache_pmu_cpumask_group = {
 /* CCG format for perf RAW codes. */
 PMU_FORMAT_ATTR(l2_code,   "config:4-11");
 PMU_FORMAT_ATTR(l2_group,  "config:0-3");
+PMU_FORMAT_ATTR(event,     "config:0-11");
+
 static struct attribute *l2_cache_pmu_formats[] = {
 	&format_attr_l2_code.attr,
 	&format_attr_l2_group.attr,
+	&format_attr_event.attr,
 	NULL,
 };
 
@@ -711,9 +729,45 @@ static struct attribute_group l2_cache_pmu_format_group = {
 	.attrs = l2_cache_pmu_formats,
 };
 
+static ssize_t l2cache_pmu_event_show(struct device *dev,
+				      struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define L2CACHE_EVENT_ATTR(_name, _id)					     \
+	(&((struct perf_pmu_events_attr[]) {				     \
+		{ .attr = __ATTR(_name, 0444, l2cache_pmu_event_show, NULL), \
+		  .id = _id, }						     \
+	})[0].attr.attr)
+
+static struct attribute *l2_cache_pmu_events[] = {
+	L2CACHE_EVENT_ATTR(cycles, L2_EVENT_CYCLES),
+	L2CACHE_EVENT_ATTR(dcache-ops, L2_EVENT_DCACHE_OPS),
+	L2CACHE_EVENT_ATTR(icache-ops, L2_EVENT_ICACHE_OPS),
+	L2CACHE_EVENT_ATTR(tlbi, L2_EVENT_TLBI),
+	L2CACHE_EVENT_ATTR(barriers, L2_EVENT_BARRIERS),
+	L2CACHE_EVENT_ATTR(total-reads, L2_EVENT_TOTAL_READS),
+	L2CACHE_EVENT_ATTR(total-writes, L2_EVENT_TOTAL_WRITES),
+	L2CACHE_EVENT_ATTR(total-requests, L2_EVENT_TOTAL_REQUESTS),
+	L2CACHE_EVENT_ATTR(ldrex, L2_EVENT_LDREX),
+	L2CACHE_EVENT_ATTR(strex, L2_EVENT_STREX),
+	L2CACHE_EVENT_ATTR(clrex, L2_EVENT_CLREX),
+	NULL
+};
+
+static struct attribute_group l2_cache_pmu_events_group = {
+	.name = "events",
+	.attrs = l2_cache_pmu_events,
+};
+
 static const struct attribute_group *l2_cache_pmu_attr_grps[] = {
 	&l2_cache_pmu_format_group,
 	&l2_cache_pmu_cpumask_group,
+	&l2_cache_pmu_events_group,
 	NULL,
 };
 

fs/binfmt_elf.c

@@ -1699,7 +1699,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 				 long signr, size_t *total)
 {
 	unsigned int i;
-	unsigned int regset_size = view->regsets[0].n * view->regsets[0].size;
+	unsigned int regset0_size = regset_size(t->task, &view->regsets[0]);
 
 	/*
 	 * NT_PRSTATUS is the one special case, because the regset data
@@ -1708,11 +1708,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	 * We assume that regset 0 is NT_PRSTATUS.
 	 */
 	fill_prstatus(&t->prstatus, t->task, signr);
-	(void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset_size,
+	(void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset0_size,
 				    &t->prstatus.pr_reg, NULL);
 
 	fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
-		  PRSTATUS_SIZE(t->prstatus, regset_size), &t->prstatus);
+		  PRSTATUS_SIZE(t->prstatus, regset0_size), &t->prstatus);
 	*total += notesize(&t->notes[0]);
 
 	do_thread_regset_writeback(t->task, &view->regsets[0]);
@@ -1728,7 +1728,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		if (regset->core_note_type && regset->get &&
 		    (!regset->active || regset->active(t->task, regset))) {
 			int ret;
-			size_t size = regset->n * regset->size;
+			size_t size = regset_size(t->task, regset);
 			void *data = kmalloc(size, GFP_KERNEL);
 			if (unlikely(!data))
 				return 0;
@@ -1743,7 +1743,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 						  size, data);
 				else {
 					SET_PR_FPVALID(&t->prstatus,
-							1, regset_size);
+							1, regset0_size);
 					fill_note(&t->notes[i], "CORE",
 						  NT_PRFPREG, size, data);
 				}

include/clocksource/arm_arch_timer.h

@@ -67,7 +67,9 @@ enum arch_timer_spi_nr {
 #define ARCH_TIMER_USR_VT_ACCESS_EN	(1 << 8) /* virtual timer registers */
 #define ARCH_TIMER_USR_PT_ACCESS_EN	(1 << 9) /* physical timer registers */
 
-#define ARCH_TIMER_EVT_STREAM_FREQ	10000	/* 100us */
+#define ARCH_TIMER_EVT_STREAM_PERIOD_US	100
+#define ARCH_TIMER_EVT_STREAM_FREQ				\
+	(USEC_PER_SEC / ARCH_TIMER_EVT_STREAM_PERIOD_US)
 
 struct arch_timer_kvm_info {
 	struct timecounter timecounter;
@@ -93,6 +95,7 @@ struct arch_timer_mem {
 extern u32 arch_timer_get_rate(void);
 extern u64 (*arch_timer_read_counter)(void);
 extern struct arch_timer_kvm_info *arch_timer_get_kvm_info(void);
+extern bool arch_timer_evtstrm_available(void);
 
 #else
 
@@ -106,6 +109,11 @@ static inline u64 arch_timer_read_counter(void)
 	return 0;
 }
 
+static inline bool arch_timer_evtstrm_available(void)
+{
+	return false;
+}
+
 #endif
 
 #endif

include/linux/acpi_iort.h

@@ -49,8 +49,8 @@ static inline void acpi_configure_pmsi_domain(struct device *dev) { }
 /* IOMMU interface */
 static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
 				  u64 *size) { }
-static inline
-const struct iommu_ops *iort_iommu_configure(struct device *dev)
+static inline const struct iommu_ops *iort_iommu_configure(
+				      struct device *dev)
 { return NULL; }
 #endif
 

include/linux/cpuhotplug.h

@@ -155,6 +155,9 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
 	CPUHP_AP_PERF_ARM_CCN_ONLINE,
+	CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+	CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
+	CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE,
 	CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE,

include/linux/irqdesc.h

@@ -246,6 +246,14 @@ static inline int irq_is_percpu(unsigned int irq)
 	return desc->status_use_accessors & IRQ_PER_CPU;
 }
 
+static inline int irq_is_percpu_devid(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	return desc->status_use_accessors & IRQ_PER_CPU_DEVID;
+}
+
 static inline void
 irq_set_lockdep_class(unsigned int irq, struct lock_class_key *class)
 {

include/linux/regset.h

@@ -106,6 +106,28 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
 				     const struct user_regset *regset,
 				     int immediate);
 
+/**
+ * user_regset_get_size_fn - type of @get_size function in &struct user_regset
+ * @target:	thread being examined
+ * @regset:	regset being examined
+ *
+ * This call is optional; usually the pointer is %NULL.
+ *
+ * When provided, this function must return the current size of regset
+ * data, as observed by the @get function in &struct user_regset.  The
+ * value returned must be a multiple of @size.  The returned size is
+ * required to be valid only until the next time (if any) @regset is
+ * modified for @target.
+ *
+ * This function is intended for dynamically sized regsets.  A regset
+ * that is statically sized does not need to implement it.
+ *
+ * This function should not be called directly: instead, callers should
+ * call regset_size() to determine the current size of a regset.
+ */
+typedef unsigned int user_regset_get_size_fn(struct task_struct *target,
+					     const struct user_regset *regset);
+
 /**
  * struct user_regset - accessible thread CPU state
  * @n:			Number of slots (registers).
@@ -117,19 +139,33 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
  * @set:		Function to store values.
  * @active:		Function to report if regset is active, or %NULL.
  * @writeback:		Function to write data back to user memory, or %NULL.
+ * @get_size:		Function to return the regset's size, or %NULL.
  *
  * This data structure describes a machine resource we call a register set.
  * This is part of the state of an individual thread, not necessarily
  * actual CPU registers per se.  A register set consists of a number of
  * similar slots, given by @n.  Each slot is @size bytes, and aligned to
- * @align bytes (which is at least @size).
+ * @align bytes (which is at least @size).  For dynamically-sized
+ * regsets, @n must contain the maximum possible number of slots for the
+ * regset, and @get_size must point to a function that returns the
+ * current regset size.
  *
- * These functions must be called only on the current thread or on a
- * thread that is in %TASK_STOPPED or %TASK_TRACED state, that we are
- * guaranteed will not be woken up and return to user mode, and that we
- * have called wait_task_inactive() on.  (The target thread always might
- * wake up for SIGKILL while these functions are working, in which case
- * that thread's user_regset state might be scrambled.)
+ * Callers that need to know only the current size of the regset and do
+ * not care about its internal structure should call regset_size()
+ * instead of inspecting @n or calling @get_size.
+ *
+ * For backward compatibility, the @get and @set methods must pad to, or
+ * accept, @n * @size bytes, even if the current regset size is smaller.
+ * The precise semantics of these operations depend on the regset being
+ * accessed.
+ *
+ * The functions to which &struct user_regset members point must be
+ * called only on the current thread or on a thread that is in
+ * %TASK_STOPPED or %TASK_TRACED state, that we are guaranteed will not
+ * be woken up and return to user mode, and that we have called
+ * wait_task_inactive() on.  (The target thread always might wake up for
+ * SIGKILL while these functions are working, in which case that
+ * thread's user_regset state might be scrambled.)
  *
  * The @pos argument must be aligned according to @align; the @count
  * argument must be a multiple of @size.  These functions are not
@@ -156,6 +192,7 @@ struct user_regset {
 	user_regset_set_fn		*set;
 	user_regset_active_fn		*active;
 	user_regset_writeback_fn	*writeback;
+	user_regset_get_size_fn		*get_size;
 	unsigned int			n;
 	unsigned int 			size;
 	unsigned int 			align;
@@ -371,5 +408,21 @@ static inline int copy_regset_from_user(struct task_struct *target,
 	return regset->set(target, regset, offset, size, NULL, data);
 }
 
+/**
+ * regset_size - determine the current size of a regset
+ * @target:	thread to be examined
+ * @regset:	regset to be examined
+ *
+ * Note that the returned size is valid only until the next time
+ * (if any) @regset is modified for @target.
+ */
+static inline unsigned int regset_size(struct task_struct *target,
+				       const struct user_regset *regset)
+{
+	if (!regset->get_size)
+		return regset->n * regset->size;
+	else
+		return regset->get_size(target, regset);
+}
 
 #endif	/* <linux/regset.h> */

include/uapi/linux/elf.h

@@ -418,6 +418,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
 #define NT_ARM_HW_WATCH	0x403		/* ARM hardware watchpoint registers */
 #define NT_ARM_SYSTEM_CALL	0x404	/* ARM system call number */
+#define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
 #define NT_METAG_CBUF	0x500		/* Metag catch buffer registers */
 #define NT_METAG_RPIPE	0x501		/* Metag read pipeline state */
 #define NT_METAG_TLS	0x502		/* Metag TLS pointer */

include/uapi/linux/perf_event.h

@@ -942,6 +942,7 @@ enum perf_callchain_context {
 #define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
 #define PERF_AUX_FLAG_PARTIAL		0x04	/* record contains gaps */
+#define PERF_AUX_FLAG_COLLISION		0x08	/* sample collided with another */
 
 #define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #define PERF_FLAG_FD_OUTPUT		(1UL << 1)

include/uapi/linux/prctl.h

@@ -198,4 +198,13 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL			50	/* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL			51	/* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK		0xffff
+# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #endif /* _LINUX_PRCTL_H */

kernel/events/ring_buffer.c

@@ -411,6 +411,7 @@ err:
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(perf_aux_output_begin);
 
 static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
 {
@@ -480,6 +481,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 	rb_free_aux(rb);
 	ring_buffer_put(rb);
 }
+EXPORT_SYMBOL_GPL(perf_aux_output_end);
 
 /*
  * Skip over a given number of bytes in the AUX buffer, due to, for example,
@@ -505,6 +507,7 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(perf_aux_output_skip);
 
 void *perf_get_aux(struct perf_output_handle *handle)
 {
@@ -514,6 +517,7 @@ void *perf_get_aux(struct perf_output_handle *handle)
 
 	return handle->rb->aux_priv;
 }
+EXPORT_SYMBOL_GPL(perf_get_aux);
 
 #define PERF_AUX_GFP	(GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY)
 

kernel/irq/irqdesc.c

@@ -862,6 +862,7 @@ int irq_get_percpu_devid_partition(unsigned int irq, struct cpumask *affinity)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(irq_get_percpu_devid_partition);
 
 void kstat_incr_irq_this_cpu(unsigned int irq)
 {

kernel/sys.c

@@ -111,6 +111,12 @@
 #ifndef SET_FP_MODE
 # define SET_FP_MODE(a,b)	(-EINVAL)
 #endif
+#ifndef SVE_SET_VL
+# define SVE_SET_VL(a)		(-EINVAL)
+#endif
+#ifndef SVE_GET_VL
+# define SVE_GET_VL()		(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -2386,6 +2392,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_FP_MODE:
 		error = GET_FP_MODE(me);
 		break;
+	case PR_SVE_SET_VL:
+		error = SVE_SET_VL(arg2);
+		break;
+	case PR_SVE_GET_VL:
+		error = SVE_GET_VL();
+		break;
 	default:
 		error = -EINVAL;
 		break;

virt/kvm/arm/arm.c

@@ -652,6 +652,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 */
 		preempt_disable();
 
+		/* Flush FP/SIMD state that can't survive guest entry/exit */
+		kvm_fpsimd_flush_cpu_state();
+
 		kvm_pmu_flush_hwstate(vcpu);
 
 		kvm_timer_flush_hwstate(vcpu);