Merge branch kvm-arm64/misc into kvmarm/next

* kvm-arm64/misc:
  : Miscellaneous updates
  :
  :  - Fix handling of features w/ nonzero safe values in set_id_regs
  :    selftest
  :
  :  - Cleanup the unused kern_hyp_va() asm macro
  :
  :  - Differentiate nVHE and hVHE in boot-time message
  :
  :  - Several selftests cleanups
  :
  :  - Drop bogus return value from kvm_arch_create_vm_debugfs()
  :
  :  - Make save/restore of SPE and TRBE control registers affect EL1 state
  :    in hVHE mode
  :
  :  - Typos
  KVM: arm64: Fix TRFCR_EL1/PMSCR_EL1 access in hVHE mode
  KVM: selftests: aarch64: Remove unused functions from vpmu test
  KVM: arm64: Fix typos
  KVM: Get rid of return value from kvm_arch_create_vm_debugfs()
  KVM: selftests: Print timer ctl register in ISTATUS assertion
  KVM: selftests: Fix GUEST_PRINTF() format warnings in ARM code
  KVM: arm64: removed unused kern_hyp_va asm macro
  KVM: arm64: add comments to __kern_hyp_va
  KVM: arm64: print Hyp mode
  KVM: arm64: selftests: Handle feature fields with nonzero minimum value correctly
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

arch/arm64/include/asm/kvm_hyp.h

@@ -70,7 +70,7 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 /*
  * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the
  * static inline can allow the compiler to out-of-line this. KVM always wants
- * the macro version as its always inlined.
+ * the macro version as it's always inlined.
  */
 #define __kvm_swab32(x)	___constant_swab32(x)
 

arch/arm64/include/asm/kvm_mmu.h

@@ -53,27 +53,6 @@
 
 #include <asm/alternative.h>
 
-/*
- * Convert a kernel VA into a HYP VA.
- * reg: VA to be converted.
- *
- * The actual code generation takes place in kvm_update_va_mask, and
- * the instructions below are only there to reserve the space and
- * perform the register allocation (kvm_update_va_mask uses the
- * specific registers encoded in the instructions).
- */
-.macro kern_hyp_va	reg
-#ifndef __KVM_VHE_HYPERVISOR__
-alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask
-	and     \reg, \reg, #1		/* mask with va_mask */
-	ror	\reg, \reg, #1		/* rotate to the first tag bit */
-	add	\reg, \reg, #0		/* insert the low 12 bits of the tag */
-	add	\reg, \reg, #0, lsl 12	/* insert the top 12 bits of the tag */
-	ror	\reg, \reg, #63		/* rotate back */
-alternative_cb_end
-#endif
-.endm
-
 /*
  * Convert a hypervisor VA to a PA
  * reg: hypervisor address to be converted in place
@@ -127,14 +106,29 @@ void kvm_apply_hyp_relocations(void);
 
 #define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
 
+/*
+ * Convert a kernel VA into a HYP VA.
+ *
+ * Can be called from hyp or non-hyp context.
+ *
+ * The actual code generation takes place in kvm_update_va_mask(), and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_update_va_mask() uses the
+ * specific registers encoded in the instructions).
+ */
 static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 {
+/*
+ * This #ifndef is an optimisation for when this is called from VHE hyp
+ * context.  When called from a VHE non-hyp context, kvm_update_va_mask() will
+ * replace the instructions with `nop`s.
+ */
 #ifndef __KVM_VHE_HYPERVISOR__
-	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
-				    "ror %0, %0, #1\n"
-				    "add %0, %0, #0\n"
-				    "add %0, %0, #0, lsl 12\n"
-				    "ror %0, %0, #63\n",
+	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"         /* mask with va_mask */
+				    "ror %0, %0, #1\n"         /* rotate to the first tag bit */
+				    "add %0, %0, #0\n"         /* insert the low 12 bits of the tag */
+				    "add %0, %0, #0, lsl 12\n" /* insert the top 12 bits of the tag */
+				    "ror %0, %0, #63\n",       /* rotate back */
 				    ARM64_ALWAYS_SYSTEM,
 				    kvm_update_va_mask)
 		     : "+r" (v));

arch/arm64/kvm/arch_timer.c

@@ -745,7 +745,7 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu,
 		WARN_ON_ONCE(ret);
 
 		/*
-		 * The virtual offset behaviour is "interresting", as it
+		 * The virtual offset behaviour is "interesting", as it
 		 * always applies when HCR_EL2.E2H==0, but only when
 		 * accessed from EL1 when HCR_EL2.E2H==1. So make sure we
 		 * track E2H when putting the HV timer in "direct" mode.

arch/arm64/kvm/arm.c

@@ -2591,7 +2591,8 @@ static __init int kvm_arm_init(void)
 	} else if (in_hyp_mode) {
 		kvm_info("VHE mode initialized successfully\n");
 	} else {
-		kvm_info("Hyp mode initialized successfully\n");
+		char mode = cpus_have_final_cap(ARM64_KVM_HVHE) ? 'h' : 'n';
+		kvm_info("Hyp mode (%cVHE) initialized successfully\n", mode);
 	}
 
 	/*

arch/arm64/kvm/fpsimd.c

@@ -117,7 +117,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Called just before entering the guest once we are no longer preemptable
+ * Called just before entering the guest once we are no longer preemptible
  * and interrupts are disabled. If we have managed to run anything using
  * FP while we were preemptible (such as off the back of an interrupt),
  * then neither the host nor the guest own the FP hardware (and it was the

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

@@ -31,8 +31,8 @@ static void __debug_save_spe(u64 *pmscr_el1)
 		return;
 
 	/* Yes; save the control register and disable data generation */
-	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
-	write_sysreg_s(0, SYS_PMSCR_EL1);
+	*pmscr_el1 = read_sysreg_el1(SYS_PMSCR);
+	write_sysreg_el1(0, SYS_PMSCR);
 	isb();
 
 	/* Now drain all buffered data to memory */
@@ -48,7 +48,7 @@ static void __debug_restore_spe(u64 pmscr_el1)
 	isb();
 
 	/* Re-enable data generation */
-	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
+	write_sysreg_el1(pmscr_el1, SYS_PMSCR);
 }
 
 static void __debug_save_trace(u64 *trfcr_el1)
@@ -63,8 +63,8 @@ static void __debug_save_trace(u64 *trfcr_el1)
 	 * Since access to TRFCR_EL1 is trapped, the guest can't
 	 * modify the filtering set by the host.
 	 */
-	*trfcr_el1 = read_sysreg_s(SYS_TRFCR_EL1);
-	write_sysreg_s(0, SYS_TRFCR_EL1);
+	*trfcr_el1 = read_sysreg_el1(SYS_TRFCR);
+	write_sysreg_el1(0, SYS_TRFCR);
 	isb();
 	/* Drain the trace buffer to memory */
 	tsb_csync();
@@ -76,7 +76,7 @@ static void __debug_restore_trace(u64 trfcr_el1)
 		return;
 
 	/* Restore trace filter controls */
-	write_sysreg_s(trfcr_el1, SYS_TRFCR_EL1);
+	write_sysreg_el1(trfcr_el1, SYS_TRFCR);
 }
 
 void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/nvhe/host.S

@@ -110,7 +110,7 @@ SYM_FUNC_END(__host_enter)
  * 				  u64 elr, u64 par);
  */
 SYM_FUNC_START(__hyp_do_panic)
-	/* Prepare and exit to the host's panic funciton. */
+	/* Prepare and exit to the host's panic function. */
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
 	msr	spsr_el2, lr

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

@@ -155,7 +155,7 @@ int hyp_back_vmemmap(phys_addr_t back)
 		start = hyp_memory[i].base;
 		start = ALIGN_DOWN((u64)hyp_phys_to_page(start), PAGE_SIZE);
 		/*
-		 * The begining of the hyp_vmemmap region for the current
+		 * The beginning of the hyp_vmemmap region for the current
 		 * memblock may already be backed by the page backing the end
 		 * the previous region, so avoid mapping it twice.
 		 */
@@ -408,7 +408,7 @@ static void *admit_host_page(void *arg)
 	return pop_hyp_memcache(host_mc, hyp_phys_to_virt);
 }
 
-/* Refill our local memcache by poping pages from the one provided by the host. */
+/* Refill our local memcache by popping pages from the one provided by the host. */
 int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages,
 		    struct kvm_hyp_memcache *host_mc)
 {

arch/arm64/kvm/inject_fault.c

@@ -134,7 +134,7 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr)
 	if (vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE) {
 		fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE;
 	} else {
-		/* no need to shuffle FS[4] into DFSR[10] as its 0 */
+		/* no need to shuffle FS[4] into DFSR[10] as it's 0 */
 		fsr = DFSR_FSC_EXTABT_nLPAE;
 	}
 

arch/arm64/kvm/vgic/vgic-init.c

@@ -309,7 +309,7 @@ int vgic_init(struct kvm *kvm)
 		vgic_lpi_translation_cache_init(kvm);
 
 	/*
-	 * If we have GICv4.1 enabled, unconditionnaly request enable the
+	 * If we have GICv4.1 enabled, unconditionally request enable the
 	 * v4 support so that we get HW-accelerated vSGIs. Otherwise, only
 	 * enable it if we present a virtual ITS to the guest.
 	 */

arch/arm64/kvm/vgic/vgic-its.c

@@ -1342,8 +1342,8 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
 }
 
 /**
- * vgic_its_invall - invalidate all LPIs targetting a given vcpu
- * @vcpu: the vcpu for which the RD is targetted by an invalidation
+ * vgic_its_invall - invalidate all LPIs targeting a given vcpu
+ * @vcpu: the vcpu for which the RD is targeted by an invalidation
  *
  * Contrary to the INVALL command, this targets a RD instead of a
  * collection, and we don't need to hold the its_lock, since no ITS is

arch/powerpc/kvm/powerpc.c

@@ -2538,9 +2538,8 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_
 		vcpu->kvm->arch.kvm_ops->create_vcpu_debugfs(vcpu, debugfs_dentry);
 }
 
-int kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void kvm_arch_create_vm_debugfs(struct kvm *kvm)
 {
 	if (kvm->arch.kvm_ops->create_vm_debugfs)
 		kvm->arch.kvm_ops->create_vm_debugfs(kvm);
-	return 0;
 }

arch/x86/kvm/debugfs.c

@@ -189,9 +189,8 @@ static const struct file_operations mmu_rmaps_stat_fops = {
 	.release	= kvm_mmu_rmaps_stat_release,
 };
 
-int kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void kvm_arch_create_vm_debugfs(struct kvm *kvm)
 {
 	debugfs_create_file("mmu_rmaps_stat", 0644, kvm->debugfs_dentry, kvm,
 			    &mmu_rmaps_stat_fops);
-	return 0;
 }

include/linux/kvm_host.h

@@ -1507,7 +1507,7 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_post_init_vm(struct kvm *kvm);
 void kvm_arch_pre_destroy_vm(struct kvm *kvm);
-int kvm_arch_create_vm_debugfs(struct kvm *kvm);
+void kvm_arch_create_vm_debugfs(struct kvm *kvm);
 
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC
 /*

tools/testing/selftests/kvm/aarch64/arch_timer.c

@@ -158,9 +158,9 @@ static void guest_validate_irq(unsigned int intid,
 
 	/* Basic 'timer condition met' check */
 	__GUEST_ASSERT(xcnt >= cval,
-		       "xcnt = 0x%llx, cval = 0x%llx, xcnt_diff_us = 0x%llx",
+		       "xcnt = 0x%lx, cval = 0x%lx, xcnt_diff_us = 0x%lx",
 		       xcnt, cval, xcnt_diff_us);
-	__GUEST_ASSERT(xctl & CTL_ISTATUS, "xcnt = 0x%llx", xcnt);
+	__GUEST_ASSERT(xctl & CTL_ISTATUS, "xctl = 0x%lx", xctl);
 
 	WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1);
 }

tools/testing/selftests/kvm/aarch64/debug-exceptions.c

@@ -365,7 +365,7 @@ static void guest_wp_handler(struct ex_regs *regs)
 
 static void guest_ss_handler(struct ex_regs *regs)
 {
-	__GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%u'", ss_idx);
+	__GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%lu'", ss_idx);
 	ss_addr[ss_idx++] = regs->pc;
 	regs->pstate |= SPSR_SS;
 }

tools/testing/selftests/kvm/aarch64/hypercalls.c

@@ -105,12 +105,12 @@ static void guest_test_hvc(const struct test_hvc_info *hc_info)
 		case TEST_STAGE_HVC_IFACE_FEAT_DISABLED:
 		case TEST_STAGE_HVC_IFACE_FALSE_INFO:
 			__GUEST_ASSERT(res.a0 == SMCCC_RET_NOT_SUPPORTED,
-				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u",
+				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%lx, stage = %u",
 					res.a0, hc_info->func_id, hc_info->arg1, stage);
 			break;
 		case TEST_STAGE_HVC_IFACE_FEAT_ENABLED:
 			__GUEST_ASSERT(res.a0 != SMCCC_RET_NOT_SUPPORTED,
-				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u",
+				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%lx, stage = %u",
 					res.a0, hc_info->func_id, hc_info->arg1, stage);
 			break;
 		default:

tools/testing/selftests/kvm/aarch64/page_fault_test.c

@@ -292,7 +292,7 @@ static void guest_code(struct test_desc *test)
 
 static void no_dabt_handler(struct ex_regs *regs)
 {
-	GUEST_FAIL("Unexpected dabt, far_el1 = 0x%llx", read_sysreg(far_el1));
+	GUEST_FAIL("Unexpected dabt, far_el1 = 0x%lx", read_sysreg(far_el1));
 }
 
 static void no_iabt_handler(struct ex_regs *regs)

tools/testing/selftests/kvm/aarch64/set_id_regs.c

@@ -32,6 +32,10 @@ struct reg_ftr_bits {
 	enum ftr_type type;
 	uint8_t shift;
 	uint64_t mask;
+	/*
+	 * For FTR_EXACT, safe_val is used as the exact safe value.
+	 * For FTR_LOWER_SAFE, safe_val is used as the minimal safe value.
+	 */
 	int64_t safe_val;
 };
 
@@ -65,13 +69,13 @@ struct test_feature_reg {
 
 static const struct reg_ftr_bits ftr_id_aa64dfr0_el1[] = {
 	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, PMUVer, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, ID_AA64DFR0_EL1_DebugVer_IMP),
 	REG_FTR_END,
 };
 
 static const struct reg_ftr_bits ftr_id_dfr0_el1[] = {
-	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, PerfMon, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, CopDbg, 0),
+	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, PerfMon, ID_DFR0_EL1_PerfMon_PMUv3),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, CopDbg, ID_DFR0_EL1_CopDbg_Armv8),
 	REG_FTR_END,
 };
 
@@ -224,13 +228,13 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
 {
 	uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
 
-	if (ftr_bits->type == FTR_UNSIGNED) {
+	if (ftr_bits->sign == FTR_UNSIGNED) {
 		switch (ftr_bits->type) {
 		case FTR_EXACT:
 			ftr = ftr_bits->safe_val;
 			break;
 		case FTR_LOWER_SAFE:
-			if (ftr > 0)
+			if (ftr > ftr_bits->safe_val)
 				ftr--;
 			break;
 		case FTR_HIGHER_SAFE:
@@ -252,7 +256,7 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
 			ftr = ftr_bits->safe_val;
 			break;
 		case FTR_LOWER_SAFE:
-			if (ftr > 0)
+			if (ftr > ftr_bits->safe_val)
 				ftr--;
 			break;
 		case FTR_HIGHER_SAFE:
@@ -276,7 +280,7 @@ uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
 {
 	uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
 
-	if (ftr_bits->type == FTR_UNSIGNED) {
+	if (ftr_bits->sign == FTR_UNSIGNED) {
 		switch (ftr_bits->type) {
 		case FTR_EXACT:
 			ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1);

tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c

@@ -93,22 +93,6 @@ static inline void write_sel_evtyper(int sel, unsigned long val)
 	isb();
 }
 
-static inline void enable_counter(int idx)
-{
-	uint64_t v = read_sysreg(pmcntenset_el0);
-
-	write_sysreg(BIT(idx) | v, pmcntenset_el0);
-	isb();
-}
-
-static inline void disable_counter(int idx)
-{
-	uint64_t v = read_sysreg(pmcntenset_el0);
-
-	write_sysreg(BIT(idx) | v, pmcntenclr_el0);
-	isb();
-}
-
 static void pmu_disable_reset(void)
 {
 	uint64_t pmcr = read_sysreg(pmcr_el0);
@@ -195,11 +179,11 @@ struct pmc_accessor pmc_accessors[] = {
 										 \
 	if (set_expected)							 \
 		__GUEST_ASSERT((_tval & mask),					 \
-				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: %u",	 \
 				_tval, mask, set_expected);			 \
 	else									 \
 		__GUEST_ASSERT(!(_tval & mask),					 \
-				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: %u",	 \
 				_tval, mask, set_expected);			 \
 }
 
@@ -286,7 +270,7 @@ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
 	acc->write_typer(pmc_idx, write_data);
 	read_data = acc->read_typer(pmc_idx);
 	__GUEST_ASSERT(read_data == write_data,
-		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
 		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
 
 	/*
@@ -297,14 +281,14 @@ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
 
 	/* The count value must be 0, as it is disabled and reset */
 	__GUEST_ASSERT(read_data == 0,
-		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx",
+		       "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx",
 		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data);
 
 	write_data = read_data + pmc_idx + 0x12345;
 	acc->write_cntr(pmc_idx, write_data);
 	read_data = acc->read_cntr(pmc_idx);
 	__GUEST_ASSERT(read_data == write_data,
-		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
 		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
 }
 
@@ -379,7 +363,7 @@ static void guest_code(uint64_t expected_pmcr_n)
 	int i, pmc;
 
 	__GUEST_ASSERT(expected_pmcr_n <= ARMV8_PMU_MAX_GENERAL_COUNTERS,
-			"Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%lx",
+			"Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%x",
 			expected_pmcr_n, ARMV8_PMU_MAX_GENERAL_COUNTERS);
 
 	pmcr = read_sysreg(pmcr_el0);

virt/kvm/kvm_main.c

@@ -1150,10 +1150,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
 				    &stat_fops_per_vm);
 	}
 
-	ret = kvm_arch_create_vm_debugfs(kvm);
-	if (ret)
-		goto out_err;
-
+	kvm_arch_create_vm_debugfs(kvm);
 	return 0;
 out_err:
 	kvm_destroy_vm_debugfs(kvm);
@@ -1183,9 +1180,8 @@ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
  * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so
  * a per-arch destroy interface is not needed.
  */
-int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
 {
-	return 0;
 }
 
 static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)