[linux-nvidia-6.18] Backport support for FEAT_LS64

Documentation/arch/arm64/booting.rst

@@ -556,6 +556,18 @@ Before jumping into the kernel, the following conditions must be met:
 
    - MDCR_EL3.TPM (bit 6) must be initialized to 0b0
 
+  For CPUs with support for 64-byte loads and stores without status (FEAT_LS64):
+
+  - If the kernel is entered at EL1 and EL2 is present:
+
+    - HCRX_EL2.EnALS (bit 1) must be initialised to 0b1.
+
+  For CPUs with support for 64-byte stores with status (FEAT_LS64_V):
+
+  - If the kernel is entered at EL1 and EL2 is present:
+
+    - HCRX_EL2.EnASR (bit 2) must be initialised to 0b1.
+
 The requirements described above for CPU mode, caches, MMUs, architected
 timers, coherency and system registers apply to all CPUs.  All CPUs must
 enter the kernel in the same exception level.  Where the values documented

Documentation/arch/arm64/elf_hwcaps.rst

@@ -444,6 +444,13 @@ HWCAP3_MTE_STORE_ONLY
 HWCAP3_LSFE
     Functionality implied by ID_AA64ISAR3_EL1.LSFE == 0b0001
 
+HWCAP3_LS64
+    Functionality implied by ID_AA64ISAR1_EL1.LS64 == 0b0001. Note that
+    the function of instruction ld64b/st64b requires support by CPU, system
+    and target (device) memory location and HWCAP3_LS64 implies the support
+    of CPU. User should only use ld64b/st64b on supported target (device)
+    memory location, otherwise fallback to the non-atomic alternatives.
+
 
 4. Unused AT_HWCAP bits
 -----------------------

Documentation/virt/kvm/api.rst

@@ -1303,12 +1303,13 @@ userspace, for example because of missing instruction syndrome decode
 information or because there is no device mapped at the accessed IPA, then
 userspace can ask the kernel to inject an external abort using the address
 from the exiting fault on the VCPU. It is a programming error to set
-ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or
-KVM_EXIT_ARM_NISV. This feature is only available if the system supports
-KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in
-how userspace reports accesses for the above cases to guests, across different
-userspace implementations. Nevertheless, userspace can still emulate all Arm
-exceptions by manipulating individual registers using the KVM_SET_ONE_REG API.
+ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO,
+KVM_EXIT_ARM_NISV, or KVM_EXIT_ARM_LDST64B. This feature is only available if
+the system supports KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which
+provides commonality in how userspace reports accesses for the above cases to
+guests, across different userspace implementations. Nevertheless, userspace
+can still emulate all Arm exceptions by manipulating individual registers
+using the KVM_SET_ONE_REG API.
 
 See KVM_GET_VCPU_EVENTS for the data structure.
 
@@ -7050,12 +7051,14 @@ in send_page or recv a buffer to recv_page).
 
 ::
 
-		/* KVM_EXIT_ARM_NISV */
+		/* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */
 		struct {
 			__u64 esr_iss;
 			__u64 fault_ipa;
 		} arm_nisv;
 
+- KVM_EXIT_ARM_NISV:
+
 Used on arm64 systems. If a guest accesses memory not in a memslot,
 KVM will typically return to userspace and ask it to do MMIO emulation on its
 behalf. However, for certain classes of instructions, no instruction decode
@@ -7089,6 +7092,32 @@ Note that although KVM_CAP_ARM_NISV_TO_USER will be reported if
 queried outside of a protected VM context, the feature will not be
 exposed if queried on a protected VM file descriptor.
 
+- KVM_EXIT_ARM_LDST64B:
+
+Used on arm64 systems. When a guest using a LD64B, ST64B, ST64BV, ST64BV0,
+outside of a memslot, KVM will return to userspace with KVM_EXIT_ARM_LDST64B,
+exposing the relevant ESR_EL2 information and faulting IPA, similarly to
+KVM_EXIT_ARM_NISV.
+
+Userspace is supposed to fully emulate the instructions, which includes:
+
+	- fetch of the operands for a store, including ACCDATA_EL1 in the case
+	  of a ST64BV0 instruction
+	- deal with the endianness if the guest is big-endian
+	- emulate the access, including the delivery of an exception if the
+	  access didn't succeed
+	- provide a return value in the case of ST64BV/ST64BV0
+	- return the data in the case of a load
+	- increment PC if the instruction was successfully executed
+
+Note that there is no expectation of performance for this emulation, as it
+involves a large number of interaction with the guest state. It is, however,
+expected that the instruction's semantics are preserved, specially the
+single-copy atomicity property of the 64 byte access.
+
+This exit reason must be handled if userspace sets ID_AA64ISAR1_EL1.LS64 to a
+non-zero value, indicating that FEAT_LS64* is enabled.
+
 ::
 
 		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
@@ -7286,6 +7315,41 @@ exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,
 it will enter with output fields already valid; in the common case, the
 ``unknown.ret`` field of the union will be ``TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED``.
 Userspace need not do anything if it does not wish to support a TDVMCALL.
+
+::
+
+		/* KVM_EXIT_ARM_SEA */
+		struct {
+  #define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID   (1ULL << 0)
+			__u64 flags;
+			__u64 esr;
+			__u64 gva;
+			__u64 gpa;
+		} arm_sea;
+
+Used on arm64 systems. When the VM capability ``KVM_CAP_ARM_SEA_TO_USER`` is
+enabled, a KVM exits to userspace if a guest access causes a synchronous
+external abort (SEA) and the host APEI fails to handle the SEA.
+
+``esr`` is set to a sanitized value of ESR_EL2 from the exception taken to KVM,
+consisting of the following fields:
+
+ - ``ESR_EL2.EC``
+ - ``ESR_EL2.IL``
+ - ``ESR_EL2.FnV``
+ - ``ESR_EL2.EA``
+ - ``ESR_EL2.CM``
+ - ``ESR_EL2.WNR``
+ - ``ESR_EL2.FSC``
+ - ``ESR_EL2.SET`` (when FEAT_RAS is implemented for the VM)
+
+``gva`` is set to the value of FAR_EL2 from the exception taken to KVM when
+``ESR_EL2.FnV == 0``. Otherwise, the value of ``gva`` is unknown.
+
+``gpa`` is set to the faulting IPA from the exception taken to KVM when
+the ``KVM_EXIT_ARM_SEA_FLAG_GPA_VALID`` flag is set. Otherwise, the value of
+``gpa`` is unknown.
+
 ::
 
 		/* Fix the size of the union. */
@@ -8703,6 +8767,18 @@ This capability indicate to the userspace whether a PFNMAP memory region
 can be safely mapped as cacheable. This relies on the presence of
 force write back (FWB) feature support on the hardware.
 
+7.45 KVM_CAP_ARM_SEA_TO_USER
+----------------------------
+
+:Architecture: arm64
+:Target: VM
+:Parameters: none
+:Returns: 0 on success, -EINVAL if unsupported.
+
+When this capability is enabled, KVM may exit to userspace for SEAs taken to
+EL2 resulting from a guest access. See ``KVM_EXIT_ARM_SEA`` for more
+information.
+
 8. Other capabilities.
 ======================
 

arch/arm64/Kconfig

@@ -1695,6 +1695,36 @@ config ARM64_TAGGED_ADDR_ABI
 	  to system calls as pointer arguments. For details, see
 	  Documentation/arch/arm64/tagged-address-abi.rst.
 
+config ARM64_WORKAROUND_NC_TO_NGNRE
+	bool "Workaround: Convert MT_NORMAL_NC to Device-nGnRE"
+	default y
+	help
+	  This option enables a workaround that converts the MT_NORMAL_NC
+	  (Non-Cacheable) memory attribute to Device-nGnRE memory type in
+	  MAIR_EL1 (Memory Attribute Indirection Register).
+
+	  This workaround is useful for hardware that requires stricter
+	  memory ordering or has issues with Non-Cacheable memory mappings.
+
+	  A new memory type index MT_NORMAL_NC_DMA (Attr5) has been introduced
+	  specifically for DMA coherent memory mappings (pgprot_dmacoherent),
+	  configured with the same Normal Non-Cacheable attribute (0x44) as
+	  MT_NORMAL_NC (Attr2). When this workaround is enabled, it converts
+	  the NC attribute to Device-nGnRE (0x04), and pgprot_dmacoherent
+	  behavior remains the same as before.
+
+	  The workaround uses the ARM64 alternatives framework for efficient
+	  runtime patching with no performance overhead when disabled.
+
+	  This workaround can only be enabled at boot time via kernel command
+	  line parameter. Runtime changes are not supported because CPU
+	  alternatives cannot be re-patched after boot.
+
+	  Boot-time activation (kernel command line):
+	    mair_el1_nc_to_ngnre=1
+
+	  If unsure, say Y.
+
 menuconfig COMPAT
 	bool "Kernel support for 32-bit EL0"
 	depends on ARM64_4K_PAGES || EXPERT

arch/arm64/include/asm/cpucaps.h

@@ -73,6 +73,8 @@ cpucap_is_possible(const unsigned int cap)
 		return true;
 	case ARM64_HAS_PMUV3:
 		return IS_ENABLED(CONFIG_HW_PERF_EVENTS);
+	case ARM64_WORKAROUND_NC_TO_NGNRE:
+		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_NC_TO_NGNRE);
 	}
 
 	return true;

arch/arm64/include/asm/el2_setup.h

@@ -83,9 +83,19 @@
         /* Enable GCS if supported */
 	mrs_s	x1, SYS_ID_AA64PFR1_EL1
 	ubfx	x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
-	cbz	x1, .Lset_hcrx_\@
+	cbz	x1, .Lskip_gcs_hcrx_\@
 	orr	x0, x0, #HCRX_EL2_GCSEn
 
+.Lskip_gcs_hcrx_\@:
+	/* Enable LS64, LS64_V if supported */
+	mrs_s	x1, SYS_ID_AA64ISAR1_EL1
+	ubfx	x1, x1, #ID_AA64ISAR1_EL1_LS64_SHIFT, #4
+	cbz	x1, .Lset_hcrx_\@
+	orr	x0, x0, #HCRX_EL2_EnALS
+	cmp	x1, #ID_AA64ISAR1_EL1_LS64_LS64_V
+	b.lt	.Lset_hcrx_\@
+	orr	x0, x0, #HCRX_EL2_EnASR
+
 .Lset_hcrx_\@:
 	msr_s	SYS_HCRX_EL2, x0
 .Lskip_hcrx_\@:

arch/arm64/include/asm/esr.h

@@ -124,6 +124,7 @@
 #define ESR_ELx_FSC_SEA_TTW(n)	(0x14 + (n))
 #define ESR_ELx_FSC_SECC	(0x18)
 #define ESR_ELx_FSC_SECC_TTW(n)	(0x1c + (n))
+#define ESR_ELx_FSC_EXCL_ATOMIC	(0x35)
 #define ESR_ELx_FSC_ADDRSZ	(0x00)
 
 /*
@@ -488,6 +489,13 @@ static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
 	       (esr == ESR_ELx_FSC_ACCESS_L(0));
 }
 
+static inline bool esr_fsc_is_excl_atomic_fault(unsigned long esr)
+{
+	esr = esr & ESR_ELx_FSC;
+
+	return esr == ESR_ELx_FSC_EXCL_ATOMIC;
+}
+
 static inline bool esr_fsc_is_addr_sz_fault(unsigned long esr)
 {
 	esr &= ESR_ELx_FSC;

arch/arm64/include/asm/hwcap.h

@@ -179,6 +179,7 @@
 #define KERNEL_HWCAP_MTE_FAR		__khwcap3_feature(MTE_FAR)
 #define KERNEL_HWCAP_MTE_STORE_ONLY	__khwcap3_feature(MTE_STORE_ONLY)
 #define KERNEL_HWCAP_LSFE		__khwcap3_feature(LSFE)
+#define KERNEL_HWCAP_LS64		__khwcap3_feature(LS64)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/kvm_emulate.h

@@ -47,6 +47,7 @@ void kvm_skip_instr32(struct kvm_vcpu *vcpu);
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 int kvm_inject_serror_esr(struct kvm_vcpu *vcpu, u64 esr);
 int kvm_inject_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr);
+int kvm_inject_dabt_excl_atomic(struct kvm_vcpu *vcpu, u64 addr);
 void kvm_inject_size_fault(struct kvm_vcpu *vcpu);
 
 static inline int kvm_inject_sea_dabt(struct kvm_vcpu *vcpu, u64 addr)
@@ -694,6 +695,12 @@ static inline void vcpu_set_hcrx(struct kvm_vcpu *vcpu)
 
 		if (kvm_has_sctlr2(kvm))
 			vcpu->arch.hcrx_el2 |= HCRX_EL2_SCTLR2En;
+
+		if (kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64))
+			vcpu->arch.hcrx_el2 |= HCRX_EL2_EnALS;
+
+		if (kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V))
+			vcpu->arch.hcrx_el2 |= HCRX_EL2_EnASR;
 	}
 }
 #endif /* __ARM64_KVM_EMULATE_H__ */

arch/arm64/include/asm/kvm_host.h

@@ -350,6 +350,8 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_GUEST_HAS_SVE			9
 	/* MIDR_EL1, REVIDR_EL1, and AIDR_EL1 are writable from userspace */
 #define KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS		10
+	/* Unhandled SEAs are taken to userspace */
+#define KVM_ARCH_FLAG_EXIT_SEA				11
 	unsigned long flags;
 
 	/* VM-wide vCPU feature set */

arch/arm64/include/asm/memory.h

@@ -173,6 +173,7 @@
 #define MT_NORMAL_NC		2
 #define MT_DEVICE_nGnRnE	3
 #define MT_DEVICE_nGnRE		4
+#define MT_NORMAL_NC_DMA	5
 
 /*
  * Memory types for Stage-2 translation

arch/arm64/include/asm/pgtable.h

@@ -800,9 +800,15 @@ static inline void __set_puds(struct mm_struct *mm,
  * requires strict alignment and can also force write responses to come from the
  * endpoint.
  */
+#ifdef CONFIG_ARM64_WORKAROUND_NC_TO_NGNRE
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, \
+			PTE_ATTRINDX(MT_NORMAL_NC_DMA) | PTE_PXN | PTE_UXN)
+#else
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, \
 			PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
+#endif
 
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;

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

@@ -146,5 +146,6 @@
 #define HWCAP3_MTE_FAR		(1UL << 0)
 #define HWCAP3_MTE_STORE_ONLY		(1UL << 1)
 #define HWCAP3_LSFE		(1UL << 2)
+#define HWCAP3_LS64		(1UL << 3)
 
 #endif /* _UAPI__ASM_HWCAP_H */