Merge tag 'kvmarm-fixes-6.15-1' of https://git.kernel.org/pub/scm/lin…

…ux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64: First batch of fixes for 6.15

 - Rework heuristics for resolving the fault IPA (HPFAR_EL2 v. re-walk
   stage-1 page tables) to align with the architecture. This avoids
   possibly taking an SEA at EL2 on the page table walk or using an
   architecturally UNKNOWN fault IPA.

 - Use acquire/release semantics in the KVM FF-A proxy to avoid reading
   a stale value for the FF-A version.

 - Fix KVM guest driver to match PV CPUID hypercall ABI.

 - Use Inner Shareable Normal Write-Back mappings at stage-1 in KVM
   selftests, which is the only memory type for which atomic
   instructions are architecturally guaranteed to work.

arch/arm64/include/asm/esr.h

@@ -121,6 +121,15 @@
 #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_ADDRSZ	(0x00)
+
+/*
+ * Annoyingly, the negative levels for Address size faults aren't laid out
+ * contiguously (or in the desired order)
+ */
+#define ESR_ELx_FSC_ADDRSZ_nL(n)	((n) == -1 ? 0x25 : 0x2C)
+#define ESR_ELx_FSC_ADDRSZ_L(n)		((n) < 0 ? ESR_ELx_FSC_ADDRSZ_nL(n) : \
+						   (ESR_ELx_FSC_ADDRSZ + (n)))
 
 /* Status codes for individual page table levels */
 #define ESR_ELx_FSC_ACCESS_L(n)	(ESR_ELx_FSC_ACCESS + (n))
@@ -161,8 +170,6 @@
 #define ESR_ELx_Xs_MASK		(GENMASK_ULL(4, 0))
 
 /* ISS field definitions for exceptions taken in to Hyp */
-#define ESR_ELx_FSC_ADDRSZ	(0x00)
-#define ESR_ELx_FSC_ADDRSZ_L(n)	(ESR_ELx_FSC_ADDRSZ + (n))
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -464,6 +471,39 @@ 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_addr_sz_fault(unsigned long esr)
+{
+	esr &= ESR_ELx_FSC;
+
+	return (esr == ESR_ELx_FSC_ADDRSZ_L(3))	||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(2))	||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(1)) ||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(0))	||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(-1));
+}
+
+static inline bool esr_fsc_is_sea_ttw(unsigned long esr)
+{
+	esr = esr & ESR_ELx_FSC;
+
+	return (esr == ESR_ELx_FSC_SEA_TTW(3)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(2)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(1)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(0)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(-1));
+}
+
+static inline bool esr_fsc_is_secc_ttw(unsigned long esr)
+{
+	esr = esr & ESR_ELx_FSC;
+
+	return (esr == ESR_ELx_FSC_SECC_TTW(3)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(2)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(1)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(0)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(-1));
+}
+
 /* Indicate whether ESR.EC==0x1A is for an ERETAx instruction */
 static inline bool esr_iss_is_eretax(unsigned long esr)
 {

arch/arm64/include/asm/kvm_emulate.h

@@ -305,7 +305,12 @@ static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vc
 
 static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
 {
-	return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
+	u64 hpfar = vcpu->arch.fault.hpfar_el2;
+
+	if (unlikely(!(hpfar & HPFAR_EL2_NS)))
+		return INVALID_GPA;
+
+	return FIELD_GET(HPFAR_EL2_FIPA, hpfar) << 12;
 }
 
 static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)

arch/arm64/include/asm/kvm_ras.h

@@ -14,7 +14,7 @@
  * Was this synchronous external abort a RAS notification?
  * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
  */
-static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr)
+static inline int kvm_handle_guest_sea(void)
 {
 	/* apei_claim_sea(NULL) expects to mask interrupts itself */
 	lockdep_assert_irqs_enabled();

arch/arm64/kvm/hyp/include/hyp/fault.h

@@ -12,6 +12,16 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
+static inline bool __fault_safe_to_translate(u64 esr)
+{
+	u64 fsc = esr & ESR_ELx_FSC;
+
+	if (esr_fsc_is_sea_ttw(esr) || esr_fsc_is_secc_ttw(esr))
+		return false;
+
+	return !(fsc == ESR_ELx_FSC_EXTABT && (esr & ESR_ELx_FnV));
+}
+
 static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
 {
 	int ret;
@@ -44,34 +54,50 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
 	return true;
 }
 
-static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
+/*
+ * Checks for the conditions when HPFAR_EL2 is written, per ARM ARM R_FKLWR.
+ */
+static inline bool __hpfar_valid(u64 esr)
 {
-	u64 hpfar, far;
-
-	far = read_sysreg_el2(SYS_FAR);
-
 	/*
-	 * The HPFAR can be invalid if the stage 2 fault did not
-	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
-	 * bit is clear) and one of the two following cases are true:
-	 *   1. The fault was due to a permission fault
-	 *   2. The processor carries errata 834220
+	 * CPUs affected by ARM erratum #834220 may incorrectly report a
+	 * stage-2 translation fault when a stage-1 permission fault occurs.
 	 *
-	 * Therefore, for all non S1PTW faults where we either have a
-	 * permission fault or the errata workaround is enabled, we
-	 * resolve the IPA using the AT instruction.
+	 * Re-walk the page tables to determine if a stage-1 fault actually
+	 * occurred.
 	 */
-	if (!(esr & ESR_ELx_S1PTW) &&
-	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     esr_fsc_is_permission_fault(esr))) {
-		if (!__translate_far_to_hpfar(far, &hpfar))
-			return false;
-	} else {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_834220) &&
+	    esr_fsc_is_translation_fault(esr))
+		return false;
+
+	if (esr_fsc_is_translation_fault(esr) || esr_fsc_is_access_flag_fault(esr))
+		return true;
+
+	if ((esr & ESR_ELx_S1PTW) && esr_fsc_is_permission_fault(esr))
+		return true;
+
+	return esr_fsc_is_addr_sz_fault(esr);
+}
+
+static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
+{
+	u64 hpfar;
+
+	fault->far_el2		= read_sysreg_el2(SYS_FAR);
+	fault->hpfar_el2	= 0;
+
+	if (__hpfar_valid(esr))
 		hpfar = read_sysreg(hpfar_el2);
-	}
+	else if (unlikely(!__fault_safe_to_translate(esr)))
+		return true;
+	else if (!__translate_far_to_hpfar(fault->far_el2, &hpfar))
+		return false;
 
-	fault->far_el2 = far;
-	fault->hpfar_el2 = hpfar;
+	/*
+	 * Hijack HPFAR_EL2.NS (RES0 in Non-secure) to indicate a valid
+	 * HPFAR value.
+	 */
+	fault->hpfar_el2 = hpfar | HPFAR_EL2_NS;
 	return true;
 }
 

arch/arm64/kvm/hyp/nvhe/ffa.c

@@ -730,10 +730,10 @@ static void do_ffa_version(struct arm_smccc_res *res,
 		hyp_ffa_version = ffa_req_version;
 	}
 
-	if (hyp_ffa_post_init())
+	if (hyp_ffa_post_init()) {
 		res->a0 = FFA_RET_NOT_SUPPORTED;
-	else {
-		has_version_negotiated = true;
+	} else {
+		smp_store_release(&has_version_negotiated, true);
 		res->a0 = hyp_ffa_version;
 	}
 unlock:
@@ -809,7 +809,8 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 	if (!is_ffa_call(func_id))
 		return false;
 
-	if (!has_version_negotiated && func_id != FFA_VERSION) {
+	if (func_id != FFA_VERSION &&
+	    !smp_load_acquire(&has_version_negotiated)) {
 		ffa_to_smccc_error(&res, FFA_RET_INVALID_PARAMETERS);
 		goto out_handled;
 	}

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -578,7 +578,14 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 		return;
 	}
 
-	addr = (fault.hpfar_el2 & HPFAR_MASK) << 8;
+
+	/*
+	 * Yikes, we couldn't resolve the fault IPA. This should reinject an
+	 * abort into the host when we figure out how to do that.
+	 */
+	BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS));
+	addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;
+
 	ret = host_stage2_idmap(addr);
 	BUG_ON(ret && ret != -EAGAIN);
 }

arch/arm64/kvm/mmu.c

@@ -1794,9 +1794,28 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
+	/* Synchronous External Abort? */
+	if (kvm_vcpu_abt_issea(vcpu)) {
+		/*
+		 * For RAS the host kernel may handle this abort.
+		 * There is no need to pass the error into the guest.
+		 */
+		if (kvm_handle_guest_sea())
+			kvm_inject_vabt(vcpu);
+
+		return 1;
+	}
+
 	esr = kvm_vcpu_get_esr(vcpu);
 
+	/*
+	 * The fault IPA should be reliable at this point as we're not dealing
+	 * with an SEA.
+	 */
 	ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+	if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm))
+		return -EFAULT;
+
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	if (esr_fsc_is_translation_fault(esr)) {
@@ -1818,18 +1837,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	/* Synchronous External Abort? */
-	if (kvm_vcpu_abt_issea(vcpu)) {
-		/*
-		 * For RAS the host kernel may handle this abort.
-		 * There is no need to pass the error into the guest.
-		 */
-		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
-			kvm_inject_vabt(vcpu);
-
-		return 1;
-	}
-
 	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 

arch/arm64/tools/sysreg

@@ -3433,3 +3433,10 @@ Field	5	F
 Field	4	P
 Field	3:0	Align
 EndSysreg
+
+Sysreg	HPFAR_EL2	3	4	6	0	4
+Field	63	NS
+Res0	62:48
+Field	47:4	FIPA
+Res0	3:0
+EndSysreg

drivers/firmware/smccc/kvm_guest.c

@@ -95,15 +95,15 @@ void  __init kvm_arm_target_impl_cpu_init(void)
 
 	for (i = 0; i < max_cpus; i++) {
 		arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_DISCOVER_IMPL_CPUS_FUNC_ID,
-				     i, &res);
+				     i, 0, 0, &res);
 		if (res.a0 != SMCCC_RET_SUCCESS) {
 			pr_warn("Discovering target implementation CPUs failed\n");
 			goto mem_free;
 		}
 		target[i].midr = res.a1;
 		target[i].revidr = res.a2;
 		target[i].aidr = res.a3;
-	};
+	}
 
 	if (!cpu_errata_set_target_impl(max_cpus, target)) {
 		pr_warn("Failed to set target implementation CPUs\n");

tools/testing/selftests/kvm/arm64/page_fault_test.c

@@ -199,7 +199,7 @@ static bool guest_set_ha(void)
 	if (hadbs == 0)
 		return false;
 
-	tcr = read_sysreg(tcr_el1) | TCR_EL1_HA;
+	tcr = read_sysreg(tcr_el1) | TCR_HA;
 	write_sysreg(tcr, tcr_el1);
 	isb();
 

tools/testing/selftests/kvm/include/arm64/processor.h

@@ -62,6 +62,67 @@
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |				\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
 
+/* TCR_EL1 specific flags */
+#define TCR_T0SZ_OFFSET	0
+#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_T0SZ_OFFSET)
+
+#define TCR_IRGN0_SHIFT	8
+#define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NC		(UL(0) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBWA		(UL(1) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WT		(UL(2) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBnWA	(UL(3) << TCR_IRGN0_SHIFT)
+
+#define TCR_ORGN0_SHIFT	10
+#define TCR_ORGN0_MASK		(UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NC		(UL(0) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBWA		(UL(1) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WT		(UL(2) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBnWA	(UL(3) << TCR_ORGN0_SHIFT)
+
+#define TCR_SH0_SHIFT		12
+#define TCR_SH0_MASK		(UL(3) << TCR_SH0_SHIFT)
+#define TCR_SH0_INNER		(UL(3) << TCR_SH0_SHIFT)
+
+#define TCR_TG0_SHIFT		14
+#define TCR_TG0_MASK		(UL(3) << TCR_TG0_SHIFT)
+#define TCR_TG0_4K		(UL(0) << TCR_TG0_SHIFT)
+#define TCR_TG0_64K		(UL(1) << TCR_TG0_SHIFT)
+#define TCR_TG0_16K		(UL(2) << TCR_TG0_SHIFT)
+
+#define TCR_IPS_SHIFT		32
+#define TCR_IPS_MASK		(UL(7) << TCR_IPS_SHIFT)
+#define TCR_IPS_52_BITS	(UL(6) << TCR_IPS_SHIFT)
+#define TCR_IPS_48_BITS	(UL(5) << TCR_IPS_SHIFT)
+#define TCR_IPS_40_BITS	(UL(2) << TCR_IPS_SHIFT)
+#define TCR_IPS_36_BITS	(UL(1) << TCR_IPS_SHIFT)
+
+#define TCR_HA			(UL(1) << 39)
+#define TCR_DS			(UL(1) << 59)
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PTE_ATTRINDX(t)	((t) << 2)
+#define PTE_ATTRINDX_MASK	GENMASK(4, 2)
+#define PTE_ATTRINDX_SHIFT	2
+
+#define PTE_VALID		BIT(0)
+#define PGD_TYPE_TABLE		BIT(1)
+#define PUD_TYPE_TABLE		BIT(1)
+#define PMD_TYPE_TABLE		BIT(1)
+#define PTE_TYPE_PAGE		BIT(1)
+
+#define PTE_SHARED		(UL(3) << 8) /* SH[1:0], inner shareable */
+#define PTE_AF			BIT(10)
+
+#define PTE_ADDR_MASK(page_shift)	GENMASK(47, (page_shift))
+#define PTE_ADDR_51_48			GENMASK(15, 12)
+#define PTE_ADDR_51_48_SHIFT		12
+#define PTE_ADDR_MASK_LPA2(page_shift)	GENMASK(49, (page_shift))
+#define PTE_ADDR_51_50_LPA2		GENMASK(9, 8)
+#define PTE_ADDR_51_50_LPA2_SHIFT	8
+
 void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init);
 struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				  struct kvm_vcpu_init *init, void *guest_code);
@@ -102,12 +163,6 @@ enum {
 			   (v) == VECTOR_SYNC_LOWER_64    || \
 			   (v) == VECTOR_SYNC_LOWER_32)
 
-/* Access flag */
-#define PTE_AF			(1ULL << 10)
-
-/* Access flag update enable/disable */
-#define TCR_EL1_HA		(1ULL << 39)
-
 void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
 					uint32_t *ipa16k, uint32_t *ipa64k);