Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 230 insertions, 27 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 21a757814..7025b3751 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -416,6 +416,13 @@ Reads the general purpose registers from the vcpu.
 	__u64 pc;
   };
 
+  /* LoongArch */
+  struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	unsigned long gpr[32];
+	unsigned long pc;
+  };
+
 
 4.12 KVM_SET_REGS
 -----------------
@@ -506,7 +513,7 @@ translation mode.
 ------------------
 
 :Capability: basic
-:Architectures: x86, ppc, mips, riscv
+:Architectures: x86, ppc, mips, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_interrupt (in)
 :Returns: 0 on success, negative on failure.
@@ -540,7 +547,7 @@ ioctl is useful if the in-kernel PIC is not used.
 PPC:
 ^^^^
 
-Queues an external interrupt to be injected. This ioctl is overleaded
+Queues an external interrupt to be injected. This ioctl is overloaded
 with 3 different irq values:
 
 a) KVM_INTERRUPT_SET
@@ -592,6 +599,14 @@ b) KVM_INTERRUPT_UNSET
 
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
+LOONGARCH:
+^^^^^^^^^^
+
+Queues an external interrupt to be injected into the virtual CPU. A negative
+interrupt number dequeues the interrupt.
+
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
 
 4.17 KVM_DEBUG_GUEST
 --------------------
@@ -737,7 +752,7 @@ signal mask.
 ----------------
 
 :Capability: basic
-:Architectures: x86
+:Architectures: x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_fpu (out)
 :Returns: 0 on success, -1 on error
@@ -746,7 +761,7 @@ Reads the floating point state from the vcpu.
 
 ::
 
-  /* for KVM_GET_FPU and KVM_SET_FPU */
+  /* x86: for KVM_GET_FPU and KVM_SET_FPU */
   struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
@@ -761,12 +776,21 @@ Reads the floating point state from the vcpu.
 	__u32 pad2;
   };
 
+  /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
+	__u32 fcsr;
+	__u64 fcc;
+	struct kvm_fpureg {
+		__u64 val64[4];
+	}fpr[32];
+  };
+
 
 4.23 KVM_SET_FPU
 ----------------
 
 :Capability: basic
-:Architectures: x86
+:Architectures: x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_fpu (in)
 :Returns: 0 on success, -1 on error
@@ -775,7 +799,7 @@ Writes the floating point state to the vcpu.
 
 ::
 
-  /* for KVM_GET_FPU and KVM_SET_FPU */
+  /* x86: for KVM_GET_FPU and KVM_SET_FPU */
   struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
@@ -790,6 +814,15 @@ Writes the floating point state to the vcpu.
 	__u32 pad2;
   };
 
+  /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
+	__u32 fcsr;
+	__u64 fcc;
+	struct kvm_fpureg {
+		__u64 val64[4];
+	}fpr[32];
+  };
+
 
 4.24 KVM_CREATE_IRQCHIP
 -----------------------
@@ -965,7 +998,7 @@ be set in the flags field of this ioctl:
 The KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag requests KVM to generate
 the contents of the hypercall page automatically; hypercalls will be
 intercepted and passed to userspace through KVM_EXIT_XEN.  In this
-ase, all of the blob size and address fields must be zero.
+case, all of the blob size and address fields must be zero.
 
 The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates to KVM that userspace
 will always use the KVM_XEN_HVM_EVTCHN_SEND ioctl to deliver event
@@ -1070,7 +1103,7 @@ Other flags returned by ``KVM_GET_CLOCK`` are accepted but ignored.
 :Extended by: KVM_CAP_INTR_SHADOW
 :Architectures: x86, arm64
 :Type: vcpu ioctl
-:Parameters: struct kvm_vcpu_event (out)
+:Parameters: struct kvm_vcpu_events (out)
 :Returns: 0 on success, -1 on error
 
 X86:
@@ -1193,7 +1226,7 @@ directly to the virtual CPU).
 :Extended by: KVM_CAP_INTR_SHADOW
 :Architectures: x86, arm64
 :Type: vcpu ioctl
-:Parameters: struct kvm_vcpu_event (in)
+:Parameters: struct kvm_vcpu_events (in)
 :Returns: 0 on success, -1 on error
 
 X86:
@@ -1387,7 +1420,7 @@ documentation when it pops into existence).
 -------------------
 
 :Capability: KVM_CAP_ENABLE_CAP
-:Architectures: mips, ppc, s390, x86
+:Architectures: mips, ppc, s390, x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_enable_cap (in)
 :Returns: 0 on success; -1 on error
@@ -1442,7 +1475,7 @@ for vm-wide capabilities.
 ---------------------
 
 :Capability: KVM_CAP_MP_STATE
-:Architectures: x86, s390, arm64, riscv
+:Architectures: x86, s390, arm64, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_mp_state (out)
 :Returns: 0 on success; -1 on error
@@ -1460,7 +1493,7 @@ Possible values are:
 
    ==========================    ===============================================
    KVM_MP_STATE_RUNNABLE         the vcpu is currently running
-                                 [x86,arm64,riscv]
+                                 [x86,arm64,riscv,loongarch]
    KVM_MP_STATE_UNINITIALIZED    the vcpu is an application processor (AP)
                                  which has not yet received an INIT signal [x86]
    KVM_MP_STATE_INIT_RECEIVED    the vcpu has received an INIT signal, and is
@@ -1516,11 +1549,14 @@ For riscv:
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
 
+On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect
+whether the vcpu is runnable.
+
 4.39 KVM_SET_MP_STATE
 ---------------------
 
 :Capability: KVM_CAP_MP_STATE
-:Architectures: x86, s390, arm64, riscv
+:Architectures: x86, s390, arm64, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_mp_state (in)
 :Returns: 0 on success; -1 on error
@@ -1538,6 +1574,9 @@ For arm64/riscv:
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
 
+On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect
+whether the vcpu is runnable.
+
 4.40 KVM_SET_IDENTITY_MAP_ADDR
 ------------------------------
 
@@ -2841,6 +2880,19 @@ Following are the RISC-V D-extension registers:
   0x8020 0000 0600 0020 fcsr      Floating point control and status register
 ======================= ========= =============================================
 
+LoongArch registers are mapped using the lower 32 bits. The upper 16 bits of
+that is the register group type.
+
+LoongArch csr registers are used to control guest cpu or get status of guest
+cpu, and they have the following id bit patterns::
+
+  0x9030 0000 0001 00 <reg:5> <sel:3>   (64-bit)
+
+LoongArch KVM control registers are used to implement some new defined functions
+such as set vcpu counter or reset vcpu, and they have the following id bit patterns::
+
+  0x9030 0000 0002 <reg:16>
+
 
 4.69 KVM_GET_ONE_REG
 --------------------
@@ -3063,7 +3115,7 @@ as follow::
    };
 
 An entry with a "page_shift" of 0 is unused. Because the array is
-organized in increasing order, a lookup can stop when encoutering
+organized in increasing order, a lookup can stop when encountering
 such an entry.
 
 The "slb_enc" field provides the encoding to use in the SLB for the
@@ -3370,6 +3422,8 @@ return indicates the attribute is implemented.  It does not necessarily
 indicate that the attribute can be read or written in the device's
 current state.  "addr" is ignored.
 
+.. _KVM_ARM_VCPU_INIT:
+
 4.82 KVM_ARM_VCPU_INIT
 ----------------------
 
@@ -3455,7 +3509,7 @@ Possible features:
 	      - KVM_RUN and KVM_GET_REG_LIST are not available;
 
 	      - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access
-	        the scalable archietctural SVE registers
+	        the scalable architectural SVE registers
 	        KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or
 	        KVM_REG_ARM64_SVE_FFR;
 
@@ -4401,7 +4455,7 @@ This will have undefined effects on the guest if it has not already
 placed itself in a quiescent state where no vcpu will make MMU enabled
 memory accesses.
 
-On succsful completion, the pending HPT will become the guest's active
+On successful completion, the pending HPT will become the guest's active
 HPT and the previous HPT will be discarded.
 
 On failure, the guest will still be operating on its previous HPT.
@@ -5016,7 +5070,7 @@ before the vcpu is fully usable.
 
 Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be
 configured by use of ioctls such as KVM_SET_ONE_REG.  The exact configuration
-that should be performaned and how to do it are feature-dependent.
+that should be performed and how to do it are feature-dependent.
 
 Other calls that depend on a particular feature being finalized, such as
 KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with
@@ -5124,6 +5178,24 @@ Valid values for 'action'::
   #define KVM_PMU_EVENT_ALLOW 0
   #define KVM_PMU_EVENT_DENY 1
 
+Via this API, KVM userspace can also control the behavior of the VM's fixed
+counters (if any) by configuring the "action" and "fixed_counter_bitmap" fields.
+
+Specifically, KVM follows the following pseudo-code when determining whether to
+allow the guest FixCtr[i] to count its pre-defined fixed event::
+
+  FixCtr[i]_is_allowed = (action == ALLOW) && (bitmap & BIT(i)) ||
+    (action == DENY) && !(bitmap & BIT(i));
+  FixCtr[i]_is_denied = !FixCtr[i]_is_allowed;
+
+KVM always consumes fixed_counter_bitmap, it's userspace's responsibility to
+ensure fixed_counter_bitmap is set correctly, e.g. if userspace wants to define
+a filter that only affects general purpose counters.
+
+Note, the "events" field also applies to fixed counters' hardcoded event_select
+and unit_mask values.  "fixed_counter_bitmap" has higher priority than "events"
+if there is a contradiction between the two.
+
 4.121 KVM_PPC_SVM_OFF
 ---------------------
 
@@ -5475,7 +5547,7 @@ KVM_XEN_ATTR_TYPE_EVTCHN
   from the guest. A given sending port number may be directed back to
   a specified vCPU (by APIC ID) / port / priority on the guest, or to
   trigger events on an eventfd. The vCPU and priority can be changed
-  by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other
+  by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but other
   fields cannot change for a given sending port. A port mapping is
   removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing
   KVM_XEN_EVTCHN_RESET in the flags field removes all interception of
@@ -6070,6 +6142,56 @@ writes to the CNTVCT_EL0 and CNTPCT_EL0 registers using the SET_ONE_REG
 interface. No error will be returned, but the resulting offset will not be
 applied.
 
+.. _KVM_ARM_GET_REG_WRITABLE_MASKS:
+
+4.139 KVM_ARM_GET_REG_WRITABLE_MASKS
+-------------------------------------------
+
+:Capability: KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES
+:Architectures: arm64
+:Type: vm ioctl
+:Parameters: struct reg_mask_range (in/out)
+:Returns: 0 on success, < 0 on error
+
+
+::
+
+        #define KVM_ARM_FEATURE_ID_RANGE	0
+        #define KVM_ARM_FEATURE_ID_RANGE_SIZE	(3 * 8 * 8)
+
+        struct reg_mask_range {
+                __u64 addr;             /* Pointer to mask array */
+                __u32 range;            /* Requested range */
+                __u32 reserved[13];
+        };
+
+This ioctl copies the writable masks for a selected range of registers to
+userspace.
+
+The ``addr`` field is a pointer to the destination array where KVM copies
+the writable masks.
+
+The ``range`` field indicates the requested range of registers.
+``KVM_CHECK_EXTENSION`` for the ``KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES``
+capability returns the supported ranges, expressed as a set of flags. Each
+flag's bit index represents a possible value for the ``range`` field.
+All other values are reserved for future use and KVM may return an error.
+
+The ``reserved[13]`` array is reserved for future use and should be 0, or
+KVM may return an error.
+
+KVM_ARM_FEATURE_ID_RANGE (0)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The Feature ID range is defined as the AArch64 System register space with
+op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7}, op2=={0-7}.
+
+The mask returned array pointed to by ``addr`` is indexed by the macro
+``ARM64_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)``, allowing userspace
+to know what fields can be changed for the system register described by
+``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a
+superset of the features supported by the system.
+
 5. The kvm_run structure
 ========================
 
diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst
index e84848432..7f231c724 100644
--- a/Documentation/virt/kvm/arm/index.rst
+++ b/Documentation/virt/kvm/arm/index.rst
@@ -11,3 +11,4 @@ ARM
    hypercalls
    pvtime
    ptp_kvm
+   vcpu-features
diff --git a/Documentation/virt/kvm/arm/vcpu-features.rst b/Documentation/virt/kvm/arm/vcpu-features.rst
new file mode 100644
index 000000000..f7cc6d8d8
--- /dev/null
+++ b/Documentation/virt/kvm/arm/vcpu-features.rst
@@ -0,0 +1,48 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================
+vCPU feature selection on arm64
+===============================
+
+KVM/arm64 provides two mechanisms that allow userspace to configure
+the CPU features presented to the guest.
+
+KVM_ARM_VCPU_INIT
+=================
+
+The ``KVM_ARM_VCPU_INIT`` ioctl accepts a bitmap of feature flags
+(``struct kvm_vcpu_init::features``). Features enabled by this interface are
+*opt-in* and may change/extend UAPI. See :ref:`KVM_ARM_VCPU_INIT` for complete
+documentation of the features controlled by the ioctl.
+
+Otherwise, all CPU features supported by KVM are described by the architected
+ID registers.
+
+The ID Registers
+================
+
+The Arm architecture specifies a range of *ID Registers* that describe the set
+of architectural features supported by the CPU implementation. KVM initializes
+the guest's ID registers to the maximum set of CPU features supported by the
+system. The ID register values may be VM-scoped in KVM, meaning that the
+values could be shared for all vCPUs in a VM.
+
+KVM allows userspace to *opt-out* of certain CPU features described by the ID
+registers by writing values to them via the ``KVM_SET_ONE_REG`` ioctl. The ID
+registers are mutable until the VM has started, i.e. userspace has called
+``KVM_RUN`` on at least one vCPU in the VM. Userspace can discover what fields
+are mutable in the ID registers using the ``KVM_ARM_GET_REG_WRITABLE_MASKS``.
+See the :ref:`ioctl documentation <KVM_ARM_GET_REG_WRITABLE_MASKS>` for more
+details.
+
+Userspace is allowed to *limit* or *mask* CPU features according to the rules
+outlined by the architecture in DDI0487J.a D19.1.3 'Principles of the ID
+scheme for fields in ID register'. KVM does not allow ID register values that
+exceed the capabilities of the system.
+
+.. warning::
+   It is **strongly recommended** that userspace modify the ID register values
+   before accessing the rest of the vCPU's CPU register state. KVM may use the
+   ID register values to control feature emulation. Interleaving ID register
+   modification with other system register accesses may lead to unpredictable
+   behavior.
diff --git a/Documentation/virt/kvm/devices/arm-vgic-v3.rst b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
index 51e5e5762..5817edb4e 100644
--- a/Documentation/virt/kvm/devices/arm-vgic-v3.rst
+++ b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
@@ -59,6 +59,13 @@ Groups:
   It is invalid to mix calls with KVM_VGIC_V3_ADDR_TYPE_REDIST and
   KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes.
 
+  Note that to obtain reproducible results (the same VCPU being associated
+  with the same redistributor across a save/restore operation), VCPU creation
+  order, redistributor region creation order as well as the respective
+  interleaves of VCPU and region creation MUST be preserved.  Any change in
+  either ordering may result in a different vcpu_id/redistributor association,
+  resulting in a VM that will fail to run at restore time.
+
   Errors:
 
     =======  =============================================================
diff --git a/Documentation/virt/kvm/x86/mmu.rst b/Documentation/virt/kvm/x86/mmu.rst
index d47595b33..2b3b6d442 100644
--- a/Documentation/virt/kvm/x86/mmu.rst
+++ b/Documentation/virt/kvm/x86/mmu.rst
@@ -202,10 +202,22 @@ Shadow pages contain the following information:
     Is 1 if the MMU instance cannot use A/D bits.  EPT did not have A/D
     bits before Haswell; shadow EPT page tables also cannot use A/D bits
     if the L1 hypervisor does not enable them.
+  role.guest_mode:
+    Indicates the shadow page is created for a nested guest.
   role.passthrough:
     The page is not backed by a guest page table, but its first entry
     points to one.  This is set if NPT uses 5-level page tables (host
     CR4.LA57=1) and is shadowing L1's 4-level NPT (L1 CR4.LA57=0).
+  mmu_valid_gen:
+    The MMU generation of this page, used to fast zap of all MMU pages within a
+    VM without blocking vCPUs too long. Specifically, KVM updates the per-VM
+    valid MMU generation which causes the mismatch of mmu_valid_gen for each mmu
+    page. This makes all existing MMU pages obsolete. Obsolete pages can't be
+    used. Therefore, vCPUs must load a new, valid root before re-entering the
+    guest. The MMU generation is only ever '0' or '1'. Note, the TDP MMU doesn't
+    use this field as non-root TDP MMU pages are reachable only from their
+    owning root. Thus it suffices for TDP MMU to use role.invalid in root pages
+    to invalidate all MMU pages.
   gfn:
     Either the guest page table containing the translations shadowed by this
     page, or the base page frame for linear translations.  See role.direct.
@@ -219,21 +231,30 @@ Shadow pages contain the following information:
     at __pa(sp2->spt).  sp2 will point back at sp1 through parent_pte.
     The spt array forms a DAG structure with the shadow page as a node, and
     guest pages as leaves.
-  gfns:
-    An array of 512 guest frame numbers, one for each present pte.  Used to
-    perform a reverse map from a pte to a gfn. When role.direct is set, any
-    element of this array can be calculated from the gfn field when used, in
-    this case, the array of gfns is not allocated. See role.direct and gfn.
-  root_count:
-    A counter keeping track of how many hardware registers (guest cr3 or
-    pdptrs) are now pointing at the page.  While this counter is nonzero, the
-    page cannot be destroyed.  See role.invalid.
+  shadowed_translation:
+    An array of 512 shadow translation entries, one for each present pte. Used
+    to perform a reverse map from a pte to a gfn as well as its access
+    permission. When role.direct is set, the shadow_translation array is not
+    allocated. This is because the gfn contained in any element of this array
+    can be calculated from the gfn field when used.  In addition, when
+    role.direct is set, KVM does not track access permission for each of the
+    gfn. See role.direct and gfn.
+  root_count / tdp_mmu_root_count:
+     root_count is a reference counter for root shadow pages in Shadow MMU.
+     vCPUs elevate the refcount when getting a shadow page that will be used as
+     a root page, i.e. page that will be loaded into hardware directly (CR3,
+     PDPTRs, nCR3 EPTP). Root pages cannot be destroyed while their refcount is
+     non-zero. See role.invalid. tdp_mmu_root_count is similar but exclusively
+     used in TDP MMU as an atomic refcount.
   parent_ptes:
     The reverse mapping for the pte/ptes pointing at this page's spt. If
     parent_ptes bit 0 is zero, only one spte points at this page and
     parent_ptes points at this single spte, otherwise, there exists multiple
     sptes pointing at this page and (parent_ptes & ~0x1) points at a data
     structure with a list of parent sptes.
+  ptep:
+    The kernel virtual address of the SPTE that points at this shadow page.
+    Used exclusively by the TDP MMU, this field is a union with parent_ptes.
   unsync:
     If true, then the translations in this page may not match the guest's
     translation.  This is equivalent to the state of the tlb when a pte is
@@ -261,6 +282,10 @@ Shadow pages contain the following information:
     since the last time the page table was actually used; if emulation
     is triggered too frequently on this page, KVM will unmap the page
     to avoid emulation in the future.
+  tdp_mmu_page:
+    Is 1 if the shadow page is a TDP MMU page. This variable is used to
+    bifurcate the control flows for KVM when walking any data structure that
+    may contain pages from both TDP MMU and shadow MMU.
 
 Reverse map
 ===========