Merge branch kvm-arm64/debug-6.14 into kvmarm-master/next

* kvm-arm64/debug-6.14:
  : .
  : Large rework of the debug code to make it a bit less horrid,
  : courtesy of Oliver Upton. From the original cover letter:
  :
  : "The debug code has become a bit difficult to reason about, especially
  : all the hacks and bandaids for state tracking + trap configuration.
  :
  : This series reworks the entire mess around using a single enumeration to
  : track the state of the debug registers (free, guest-owned, host-owned),
  : using that to drive trap configuration and save/restore.
  :
  : On top of that, this series wires most of the implementation into vCPU
  : load/put rather than the main KVM_RUN loop. This has been a long time
  : coming for VHE, as a lot of the trap configuration and EL1 state gets
  : loaded into hardware at that point anyway.
  :
  : The save/restore of the debug registers is simplified quite a bit as
  : well. KVM will now restore the registers for *any* access rather than
  : just writes, and keep doing so until the next vcpu_put() instead of
  : dropping it on the floor after the next exception."
  : .
  KVM: arm64: Promote guest ownership for DBGxVR/DBGxCR reads
  KVM: arm64: Fold DBGxVR/DBGxCR accessors into common set
  KVM: arm64: Avoid reading ID_AA64DFR0_EL1 for debug save/restore
  KVM: arm64: nv: Honor MDCR_EL2.TDE routing for debug exceptions
  KVM: arm64: Manage software step state at load/put
  KVM: arm64: Don't hijack guest context MDSCR_EL1
  KVM: arm64: Compute MDCR_EL2 at vcpu_load()
  KVM: arm64: Reload vCPU for accesses to OSLAR_EL1
  KVM: arm64: Use debug_owner to track if debug regs need save/restore
  KVM: arm64: Remove vestiges of debug_ptr
  KVM: arm64: Remove debug tracepoints
  KVM: arm64: Select debug state to save/restore based on debug owner
  KVM: arm64: Clean up KVM_SET_GUEST_DEBUG handler
  KVM: arm64: Evaluate debug owner at vcpu_load()
  KVM: arm64: Write MDCR_EL2 directly from kvm_arm_setup_mdcr_el2()
  KVM: arm64: Move host SME/SVE tracking flags to host data
  KVM: arm64: Track presence of SPE/TRBE in kvm_host_data instead of vCPU
  KVM: arm64: Get rid of __kvm_get_mdcr_el2() and related warts
  KVM: arm64: Drop MDSCR_EL1_DEBUG_MASK

Signed-off-by: Marc Zyngier <[email protected]>

Author: Marc Zyngier

arch/arm64/include/asm/kvm_asm.h

@@ -53,8 +53,7 @@
 enum __kvm_host_smccc_func {
 	/* Hypercalls available only prior to pKVM finalisation */
 	/* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */
-	__KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
-	__KVM_HOST_SMCCC_FUNC___pkvm_init,
+	__KVM_HOST_SMCCC_FUNC___pkvm_init = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
 	__KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping,
 	__KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector,
 	__KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs,
@@ -247,8 +246,6 @@ extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
 extern u64 __vgic_v3_get_gic_config(void);
 extern void __vgic_v3_init_lrs(void);
 
-extern u64 __kvm_get_mdcr_el2(void);
-
 #define __KVM_EXTABLE(from, to)						\
 	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
 	"	.align		3\n"					\

arch/arm64/include/asm/kvm_host.h

@@ -610,6 +610,12 @@ struct cpu_sve_state {
  * field.
  */
 struct kvm_host_data {
+#define KVM_HOST_DATA_FLAG_HAS_SPE			0
+#define KVM_HOST_DATA_FLAG_HAS_TRBE			1
+#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED		2
+#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED		3
+	unsigned long flags;
+
 	struct kvm_cpu_context host_ctxt;
 
 	/*
@@ -642,7 +648,7 @@ struct kvm_host_data {
 	 * host_debug_state contains the host registers which are
 	 * saved and restored during world switches.
 	 */
-	 struct {
+	struct {
 		/* {Break,watch}point registers */
 		struct kvm_guest_debug_arch regs;
 		/* Statistical profiling extension */
@@ -652,6 +658,13 @@ struct kvm_host_data {
 		/* Values of trap registers for the host before guest entry. */
 		u64 mdcr_el2;
 	} host_debug_state;
+
+	/* Number of programmable event counters (PMCR_EL0.N) for this CPU */
+	unsigned int nr_event_counters;
+
+	/* Number of debug breakpoints/watchpoints for this CPU (minus 1) */
+	unsigned int debug_brps;
+	unsigned int debug_wrps;
 };
 
 struct kvm_host_psci_config {
@@ -739,31 +752,22 @@ struct kvm_vcpu_arch {
 	 *
 	 * external_debug_state contains the debug values we want to debug the
 	 * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl.
-	 *
-	 * debug_ptr points to the set of debug registers that should be loaded
-	 * onto the hardware when running the guest.
 	 */
-	struct kvm_guest_debug_arch *debug_ptr;
 	struct kvm_guest_debug_arch vcpu_debug_state;
 	struct kvm_guest_debug_arch external_debug_state;
+	u64 external_mdscr_el1;
+
+	enum {
+		VCPU_DEBUG_FREE,
+		VCPU_DEBUG_HOST_OWNED,
+		VCPU_DEBUG_GUEST_OWNED,
+	} debug_owner;
 
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
 	struct arch_timer_cpu timer_cpu;
 	struct kvm_pmu pmu;
 
-	/*
-	 * Guest registers we preserve during guest debugging.
-	 *
-	 * These shadow registers are updated by the kvm_handle_sys_reg
-	 * trap handler if the guest accesses or updates them while we
-	 * are using guest debug.
-	 */
-	struct {
-		u32	mdscr_el1;
-		bool	pstate_ss;
-	} guest_debug_preserved;
-
 	/* vcpu power state */
 	struct kvm_mp_state mp_state;
 	spinlock_t mp_state_lock;
@@ -906,29 +910,21 @@ struct kvm_vcpu_arch {
 #define EXCEPT_AA64_EL2_IRQ	__vcpu_except_flags(5)
 #define EXCEPT_AA64_EL2_FIQ	__vcpu_except_flags(6)
 #define EXCEPT_AA64_EL2_SERR	__vcpu_except_flags(7)
-/* Guest debug is live */
-#define DEBUG_DIRTY		__vcpu_single_flag(iflags, BIT(4))
-/* Save SPE context if active  */
-#define DEBUG_STATE_SAVE_SPE	__vcpu_single_flag(iflags, BIT(5))
-/* Save TRBE context if active  */
-#define DEBUG_STATE_SAVE_TRBE	__vcpu_single_flag(iflags, BIT(6))
-
-/* SVE enabled for host EL0 */
-#define HOST_SVE_ENABLED	__vcpu_single_flag(sflags, BIT(0))
-/* SME enabled for EL0 */
-#define HOST_SME_ENABLED	__vcpu_single_flag(sflags, BIT(1))
+
 /* Physical CPU not in supported_cpus */
-#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(2))
+#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(0))
 /* WFIT instruction trapped */
-#define IN_WFIT			__vcpu_single_flag(sflags, BIT(3))
+#define IN_WFIT			__vcpu_single_flag(sflags, BIT(1))
 /* vcpu system registers loaded on physical CPU */
-#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))
-/* Software step state is Active-pending */
-#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
+#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(2))
+/* Software step state is Active-pending for external debug */
+#define HOST_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(3))
+/* Software step state is Active pending for guest debug */
+#define GUEST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(4))
 /* PMUSERENR for the guest EL0 is on physical CPU */
-#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(6))
+#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(5))
 /* WFI instruction trapped */
-#define IN_WFI			__vcpu_single_flag(sflags, BIT(7))
+#define IN_WFI			__vcpu_single_flag(sflags, BIT(6))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -1307,6 +1303,13 @@ DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);
 	 &this_cpu_ptr_hyp_sym(kvm_host_data)->f)
 #endif
 
+#define host_data_test_flag(flag)					\
+	(test_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)))
+#define host_data_set_flag(flag)					\
+	set_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))
+#define host_data_clear_flag(flag)					\
+	clear_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))
+
 /* Check whether the FP regs are owned by the guest */
 static inline bool guest_owns_fp_regs(void)
 {
@@ -1332,15 +1335,22 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 
-void kvm_arm_init_debug(void);
-void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
-void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
-void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
-void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+void kvm_init_host_debug_data(void);
+void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu);
+void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu);
+void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val);
 
 #define kvm_vcpu_os_lock_enabled(vcpu)		\
 	(!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & OSLSR_EL1_OSLK))
 
+#define kvm_debug_regs_in_use(vcpu)		\
+	((vcpu)->arch.debug_owner != VCPU_DEBUG_FREE)
+#define kvm_host_owns_debug_regs(vcpu)		\
+	((vcpu)->arch.debug_owner == VCPU_DEBUG_HOST_OWNED)
+#define kvm_guest_owns_debug_regs(vcpu)		\
+	((vcpu)->arch.debug_owner == VCPU_DEBUG_GUEST_OWNED)
+
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
@@ -1367,10 +1377,6 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
 	return (!has_vhe() && attr->exclude_host);
 }
 
-/* Flags for host debug state */
-void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu);
-void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
-
 #ifdef CONFIG_KVM
 void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u64 clr);

arch/arm64/include/asm/kvm_nested.h

@@ -64,6 +64,7 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
 }
 
 extern bool forward_smc_trap(struct kvm_vcpu *vcpu);
+extern bool forward_debug_exception(struct kvm_vcpu *vcpu);
 extern void kvm_init_nested(struct kvm *kvm);
 extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
 extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);

arch/arm64/kvm/arm.c

@@ -476,8 +476,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	kvm_pmu_vcpu_init(vcpu);
 
-	kvm_arm_reset_debug_ptr(vcpu);
-
 	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
 
 	vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
@@ -598,6 +596,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
+	kvm_vcpu_load_debug(vcpu);
 	if (has_vhe())
 		kvm_vcpu_load_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
@@ -617,15 +616,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	vcpu_set_pauth_traps(vcpu);
 
-	kvm_arch_vcpu_load_debug_state_flags(vcpu);
-
 	if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
 		vcpu_set_on_unsupported_cpu(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvm_arch_vcpu_put_debug_state_flags(vcpu);
+	kvm_vcpu_put_debug(vcpu);
 	kvm_arch_vcpu_put_fp(vcpu);
 	if (has_vhe())
 		kvm_vcpu_put_vhe(vcpu);
@@ -808,8 +805,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 
 	kvm_init_mpidr_data(kvm);
 
-	kvm_arm_vcpu_init_debug(vcpu);
-
 	if (likely(irqchip_in_kernel(kvm))) {
 		/*
 		 * Map the VGIC hardware resources before running a vcpu the
@@ -1187,7 +1182,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-		kvm_arm_setup_debug(vcpu);
 		kvm_arch_vcpu_ctxflush_fp(vcpu);
 
 		/**************************************************************
@@ -1204,8 +1198,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * Back from guest
 		 *************************************************************/
 
-		kvm_arm_clear_debug(vcpu);
-
 		/*
 		 * We must sync the PMU state before the vgic state so
 		 * that the vgic can properly sample the updated state of the
@@ -2109,6 +2101,7 @@ static void cpu_set_hyp_vector(void)
 static void cpu_hyp_init_context(void)
 {
 	kvm_init_host_cpu_context(host_data_ptr(host_ctxt));
+	kvm_init_host_debug_data();
 
 	if (!is_kernel_in_hyp_mode())
 		cpu_init_hyp_mode();
@@ -2117,7 +2110,6 @@ static void cpu_hyp_init_context(void)
 static void cpu_hyp_init_features(void)
 {
 	cpu_set_hyp_vector();
-	kvm_arm_init_debug();
 
 	if (is_kernel_in_hyp_mode())
 		kvm_timer_init_vhe();