Merge tag 'kvm-s390-master-6.3-1' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

A small fix that repairs the external loop detection code for PV
guests.

18 files changed, 112 insertions, 55 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 8c45b198b62f..bccea57dee81 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -923,6 +923,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 
 		/* Event overflow */
 		handled++;
+		status &= ~mask;
 		perf_sample_data_init(&data, 0, hwc->last_period);
 
 		if (!x86_perf_event_set_period(event))
@@ -933,8 +934,6 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
-
-		status &= ~mask;
 	}
 
 	/*
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index b8357d6ecd47..b63be696b776 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -128,8 +128,9 @@ struct snp_psc_desc {
 	struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY];
 } __packed;
 
-/* Guest message request error code */
+/* Guest message request error codes */
 #define SNP_GUEST_REQ_INVALID_LEN	BIT_ULL(32)
+#define SNP_GUEST_REQ_ERR_BUSY		BIT_ULL(33)
 
 #define GHCB_MSR_TERM_REQ		0x100
 #define GHCB_MSR_TERM_REASON_SET_POS	12
diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h
index 6daa9b0c8d11..a3c29b1496c8 100644
--- a/arch/x86/include/asm/xen/cpuid.h
+++ b/arch/x86/include/asm/xen/cpuid.h
@@ -89,11 +89,21 @@
  * Sub-leaf 2: EAX: host tsc frequency in kHz
  */
 
+#define XEN_CPUID_TSC_EMULATED               (1u << 0)
+#define XEN_CPUID_HOST_TSC_RELIABLE          (1u << 1)
+#define XEN_CPUID_RDTSCP_INSTR_AVAIL         (1u << 2)
+
+#define XEN_CPUID_TSC_MODE_DEFAULT           (0)
+#define XEN_CPUID_TSC_MODE_ALWAYS_EMULATE    (1u)
+#define XEN_CPUID_TSC_MODE_NEVER_EMULATE     (2u)
+#define XEN_CPUID_TSC_MODE_PVRDTSCP          (3u)
+
 /*
  * Leaf 5 (0x40000x04)
  * HVM-specific features
  * Sub-leaf 0: EAX: Features
  * Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
+ * Sub-leaf 0: ECX: domain id (iff EAX has XEN_HVM_CPUID_DOMID_PRESENT flag)
  */
 #define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */
 #define XEN_HVM_CPUID_X2APIC_VIRT      (1u << 1) /* Virtualized x2APIC accesses */
@@ -102,12 +112,16 @@
 #define XEN_HVM_CPUID_VCPU_ID_PRESENT  (1u << 3) /* vcpu id is present in EBX */
 #define XEN_HVM_CPUID_DOMID_PRESENT    (1u << 4) /* domid is present in ECX */
 /*
- * Bits 55:49 from the IO-APIC RTE and bits 11:5 from the MSI address can be
- * used to store high bits for the Destination ID. This expands the Destination
- * ID field from 8 to 15 bits, allowing to target APIC IDs up 32768.
+ * With interrupt format set to 0 (non-remappable) bits 55:49 from the
+ * IO-APIC RTE and bits 11:5 from the MSI address can be used to store
+ * high bits for the Destination ID. This expands the Destination ID
+ * field from 8 to 15 bits, allowing to target APIC IDs up 32768.
  */
 #define XEN_HVM_CPUID_EXT_DEST_ID      (1u << 5)
-/* Per-vCPU event channel upcalls */
+/*
+ * Per-vCPU event channel upcalls work correctly with physical IRQs
+ * bound to event channels.
+ */
 #define XEN_HVM_CPUID_UPCALL_VECTOR    (1u << 6)
 
 /*
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7832a69d170e..2eec60f50057 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2355,6 +2355,7 @@ static void mce_restart(void)
 {
 	mce_timer_delete_all();
 	on_each_cpu(mce_cpu_restart, NULL, 1);
+	mce_schedule_work();
 }
 
 /* Toggle features for corrected errors */
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index eb07d4435391..b44c487727d4 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -368,7 +368,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 {
 	struct resctrl_schema *s;
 	struct rdtgroup *rdtgrp;
-	struct rdt_domain *dom;
 	struct rdt_resource *r;
 	char *tok, *resname;
 	int ret = 0;
@@ -397,10 +396,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 		goto out;
 	}
 
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		list_for_each_entry(dom, &s->res->domains, list)
-			memset(dom->staged_config, 0, sizeof(dom->staged_config));
-	}
+	rdt_staged_configs_clear();
 
 	while ((tok = strsep(&buf, "\n")) != NULL) {
 		resname = strim(strsep(&tok, ":"));
@@ -445,6 +441,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 
 out:
+	rdt_staged_configs_clear();
 	rdtgroup_kn_unlock(of->kn);
 	cpus_read_unlock();
 	return ret ?: nbytes;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 8edecc5763d8..85ceaf9a31ac 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -555,5 +555,6 @@ void __check_limbo(struct rdt_domain *d, bool force_free);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 void __init thread_throttle_mode_init(void);
 void __init mbm_config_rftype_init(const char *config);
+void rdt_staged_configs_clear(void);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 884b6e9a7e31..6ad33f355861 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -78,6 +78,19 @@ void rdt_last_cmd_printf(const char *fmt, ...)
 	va_end(ap);
 }
 
+void rdt_staged_configs_clear(void)
+{
+	struct rdt_resource *r;
+	struct rdt_domain *dom;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	for_each_alloc_capable_rdt_resource(r) {
+		list_for_each_entry(dom, &r->domains, list)
+			memset(dom->staged_config, 0, sizeof(dom->staged_config));
+	}
+}
+
 /*
  * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
  * we can keep a bitmap of free CLOSIDs in a single integer.
@@ -3107,7 +3120,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 {
 	struct resctrl_schema *s;
 	struct rdt_resource *r;
-	int ret;
+	int ret = 0;
+
+	rdt_staged_configs_clear();
 
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
@@ -3119,20 +3134,22 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 		} else {
 			ret = rdtgroup_init_cat(s, rdtgrp->closid);
 			if (ret < 0)
-				return ret;
+				goto out;
 		}
 
 		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
 		if (ret < 0) {
 			rdt_last_cmd_puts("Failed to initialize allocations\n");
-			return ret;
+			goto out;
 		}
 
 	}
 
 	rdtgrp->mode = RDT_MODE_SHAREABLE;
 
-	return 0;
+out:
+	rdt_staged_configs_clear();
+	return ret;
 }
 
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 714166cc25f2..0bab497c9436 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1118,21 +1118,20 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	zerofrom = offsetof(struct xregs_state, extended_state_area);
 
 	/*
-	 * The ptrace buffer is in non-compacted XSAVE format.  In
-	 * non-compacted format disabled features still occupy state space,
-	 * but there is no state to copy from in the compacted
-	 * init_fpstate. The gap tracking will zero these states.
-	 */
-	mask = fpstate->user_xfeatures;
-
-	/*
-	 * Dynamic features are not present in init_fpstate. When they are
-	 * in an all zeros init state, remove those from 'mask' to zero
-	 * those features in the user buffer instead of retrieving them
-	 * from init_fpstate.
+	 * This 'mask' indicates which states to copy from fpstate.
+	 * Those extended states that are not present in fpstate are
+	 * either disabled or initialized:
+	 *
+	 * In non-compacted format, disabled features still occupy
+	 * state space but there is no state to copy from in the
+	 * compacted init_fpstate. The gap tracking will zero these
+	 * states.
+	 *
+	 * The extended features have an all zeroes init state. Thus,
+	 * remove them from 'mask' to zero those features in the user
+	 * buffer instead of retrieving them from init_fpstate.
 	 */
-	if (fpu_state_size_dynamic())
-		mask &= (header.xfeatures | xinit->header.xcomp_bv);
+	mask = header.xfeatures;
 
 	for_each_extended_xfeature(i, mask) {
 		/*
@@ -1151,9 +1150,8 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 			pkru.pkru = pkru_val;
 			membuf_write(&to, &pkru, sizeof(pkru));
 		} else {
-			copy_feature(header.xfeatures & BIT_ULL(i), &to,
+			membuf_write(&to,
 				     __raw_xsave_addr(xsave, i),
-				     __raw_xsave_addr(xinit, i),
 				     xstate_sizes[i]);
 		}
 		/*
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 1265ad519249..fb4f1e01b64a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -136,10 +136,12 @@ SYM_TYPED_FUNC_START(ftrace_stub)
 	RET
 SYM_FUNC_END(ftrace_stub)
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 SYM_TYPED_FUNC_START(ftrace_stub_graph)
 	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(ftrace_stub_graph)
+#endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 679026a640ef..3f664ab277c4 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -2183,9 +2183,6 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
 	struct ghcb *ghcb;
 	int ret;
 
-	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
-		return -ENODEV;
-
 	if (!fw_err)
 		return -EINVAL;
 
@@ -2212,15 +2209,26 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
 	if (ret)
 		goto e_put;
 
-	if (ghcb->save.sw_exit_info_2) {
-		/* Number of expected pages are returned in RBX */
-		if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST &&
-		    ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN)
-			input->data_npages = ghcb_get_rbx(ghcb);
+	*fw_err = ghcb->save.sw_exit_info_2;
+	switch (*fw_err) {
+	case 0:
+		break;
 
-		*fw_err = ghcb->save.sw_exit_info_2;
+	case SNP_GUEST_REQ_ERR_BUSY:
+		ret = -EAGAIN;
+		break;
 
+	case SNP_GUEST_REQ_INVALID_LEN:
+		/* Number of expected pages are returned in RBX */
+		if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) {
+			input->data_npages = ghcb_get_rbx(ghcb);
+			ret = -ENOSPC;
+			break;
+		}
+		fallthrough;
+	default:
 		ret = -EIO;
+		break;
 	}
 
 e_put:
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 7316a8224259..e91500a80963 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -10,6 +10,7 @@
 #include <asm/fixmap.h>
 #include <asm/desc.h>
 #include <asm/kasan.h>
+#include <asm/setup.h>
 
 static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
 
@@ -29,6 +30,12 @@ static __init void init_cea_offsets(void)
 	unsigned int max_cea;
 	unsigned int i, j;
 
+	if (!kaslr_enabled()) {
+		for_each_possible_cpu(i)
+			per_cpu(_cea_offset, i) = i;
+		return;
+	}
+
 	max_cea = (CPU_ENTRY_AREA_MAP_SIZE - PAGE_SIZE) / CPU_ENTRY_AREA_SIZE;
 
 	/* O(sodding terrible) */
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 88cccd65029d..c6efcf559d88 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -600,7 +600,8 @@ void __init sme_enable(struct boot_params *bp)
 	cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
 				     ((u64)bp->ext_cmd_line_ptr << 32));
 
-	cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer));
+	if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0)
+		return;
 
 	if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
 		sme_me_mask = me_mask;
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 3c5b52fbe4a7..a9ec8c9f5c5d 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -45,6 +45,6 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 
-obj-$(CONFIG_XEN_PV_DOM0)	+= vga.o
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 
 obj-$(CONFIG_XEN_EFI)		+= efi.o
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index bb59cc6ddb2d..093b78c8bbec 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1390,7 +1390,8 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si)
 
 		x86_platform.set_legacy_features =
 				xen_dom0_set_legacy_features;
-		xen_init_vga(info, xen_start_info->console.dom0.info_size);
+		xen_init_vga(info, xen_start_info->console.dom0.info_size,
+			     &boot_params.screen_info);
 		xen_start_info->console.domU.mfn = 0;
 		xen_start_info->console.domU.evtchn = 0;
 
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index bcae606bbc5c..ada3868c02c2 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -43,6 +43,19 @@ void __init xen_pvh_init(struct boot_params *boot_params)
 	x86_init.oem.banner = xen_banner;
 
 	xen_efi_init(boot_params);
+
+	if (xen_initial_domain()) {
+		struct xen_platform_op op = {
+			.cmd = XENPF_get_dom0_console,
+		};
+		int ret = HYPERVISOR_platform_op(&op);
+
+		if (ret > 0)
+			xen_init_vga(&op.u.dom0_console,
+				     min(ret * sizeof(char),
+					 sizeof(op.u.dom0_console)),
+				     &boot_params->screen_info);
+	}
 }
 
 void __init mem_map_via_hcall(struct boot_params *boot_params_p)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 1d597364b49d..b74ac2562cfb 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -20,6 +20,7 @@
 #include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
+#include <asm/xen/cpuid.h>
 
 #include <xen/events.h>
 #include <xen/features.h>
@@ -503,11 +504,7 @@ static int __init xen_tsc_safe_clocksource(void)
 	/* Leaf 4, sub-leaf 0 (0x40000x03) */
 	cpuid_count(xen_cpuid_base() + 3, 0, &eax, &ebx, &ecx, &edx);
 
-	/* tsc_mode = no_emulate (2) */
-	if (ebx != 2)
-		return 0;
-
-	return 1;
+	return ebx == XEN_CPUID_TSC_MODE_NEVER_EMULATE;
 }
 
 static void __init xen_time_init(void)
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
index 14ea32e734d5..d97adab8420f 100644
--- a/arch/x86/xen/vga.c
+++ b/arch/x86/xen/vga.c
@@ -9,10 +9,9 @@
 
 #include "xen-ops.h"
 
-void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
+void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size,
+			 struct screen_info *screen_info)
 {
-	struct screen_info *screen_info = &boot_params.screen_info;
-
 	/* This is drawn from a dump from vgacon:startup in
 	 * standard Linux. */
 	screen_info->orig_video_mode = 3;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9a8bb972193d..a10903785a33 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -108,11 +108,12 @@ static inline void xen_uninit_lock_cpu(int cpu)
 
 struct dom0_vga_console_info;
 
-#ifdef CONFIG_XEN_PV_DOM0
-void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+#ifdef CONFIG_XEN_DOM0
+void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size,
+			 struct screen_info *);
 #else
 static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
-				       size_t size)
+				       size_t size, struct screen_info *si)
 {
 }
 #endif