Merge tag 'x86_urgent_for_v6.0_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:
 "As usually the case, right after a major release, the tip urgent
  branches accumulate a couple more fixes than normal. And here is the
  x86, a bit bigger, urgent pile.

   - Use the correct CPU capability clearing function on the error path
     in Intel perf LBR

   - A CFI fix to ftrace along with a simplification

   - Adjust handling of zero capacity bit mask for resctrl cache
     allocation on AMD

   - A fix to the AMD microcode loader to attempt patch application on
     every logical thread

   - A couple of topology fixes to handle CPUID leaf 0x1f enumeration
     info properly

   - Drop a -mabi=ms compiler option check as both compilers support it
     now anyway

   - A couple of fixes to how the initial, statically allocated FPU
     buffer state is setup and its interaction with dynamic states at
     runtime"

* tag 'x86_urgent_for_v6.0_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Fix copy_xstate_to_uabi() to copy init states correctly
  perf/x86/intel/lbr: Use setup_clear_cpu_cap() instead of clear_cpu_cap()
  ftrace,kcfi: Separate ftrace_stub() and ftrace_stub_graph()
  x86/ftrace: Remove ftrace_epilogue()
  x86/resctrl: Fix min_cbm_bits for AMD
  x86/microcode/AMD: Apply the patch early on every logical thread
  x86/topology: Fix duplicated core ID within a package
  x86/topology: Fix multiple packages shown on a single-package system
  hwmon/coretemp: Handle large core ID value
  x86/Kconfig: Drop check for -mabi=ms for CONFIG_EFI_STUB
  x86/fpu: Exclude dynamic states from init_fpstate
  x86/fpu: Fix the init_fpstate size check with the actual size
  x86/fpu: Configure init_fpstate attributes orderly

Author: torvalds

arch/arm64/kernel/entry-ftrace.S

@@ -7,6 +7,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
 #include <asm/ftrace.h>
@@ -294,10 +295,14 @@ SYM_FUNC_END(ftrace_graph_caller)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
-SYM_FUNC_START(ftrace_stub)
+SYM_TYPED_FUNC_START(ftrace_stub)
 	ret
 SYM_FUNC_END(ftrace_stub)
 
+SYM_TYPED_FUNC_START(ftrace_stub_graph)
+	ret
+SYM_FUNC_END(ftrace_stub_graph)
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * void return_to_handler(void)

arch/x86/Kconfig

@@ -1973,7 +1973,6 @@ config EFI
 config EFI_STUB
 	bool "EFI stub support"
 	depends on EFI
-	depends on $(cc-option,-mabi=ms) || X86_32
 	select RELOCATABLE
 	help
 	  This kernel feature allows a bzImage to be loaded directly

arch/x86/events/intel/lbr.c

@@ -1596,7 +1596,7 @@ void __init intel_pmu_arch_lbr_init(void)
 	return;
 
 clear_arch_lbr:
-	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR);
+	setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR);
 }
 
 /**

arch/x86/kernel/cpu/microcode/amd.c

@@ -440,7 +440,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p
 		return ret;
 
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-	if (rev >= mc->hdr.patch_id)
+
+	/*
+	 * Allow application of the same revision to pick up SMT-specific
+	 * changes even if the revision of the other SMT thread is already
+	 * up-to-date.
+	 */
+	if (rev > mc->hdr.patch_id)
 		return ret;
 
 	if (!__apply_microcode_amd(mc)) {
@@ -528,8 +534,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
-	/* Check whether we have saved a new patch already: */
-	if (*new_rev && rev < mc->hdr.patch_id) {
+	/*
+	 * Check whether a new patch has been saved already. Also, allow application of
+	 * the same revision in order to pick up SMT-thread-specific configuration even
+	 * if the sibling SMT thread already has an up-to-date revision.
+	 */
+	if (*new_rev && rev <= mc->hdr.patch_id) {
 		if (!__apply_microcode_amd(mc)) {
 			*new_rev = mc->hdr.patch_id;
 			return;

arch/x86/kernel/cpu/resctrl/core.c

@@ -66,9 +66,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
 			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
 			.cache_level		= 3,
-			.cache = {
-				.min_cbm_bits	= 1,
-			},
 			.domains		= domain_init(RDT_RESOURCE_L3),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -83,9 +80,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
 			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
 			.cache_level		= 2,
-			.cache = {
-				.min_cbm_bits	= 1,
-			},
 			.domains		= domain_init(RDT_RESOURCE_L2),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -836,6 +830,7 @@ static __init void rdt_init_res_defs_intel(void)
 			r->cache.arch_has_sparse_bitmaps = false;
 			r->cache.arch_has_empty_bitmaps = false;
 			r->cache.arch_has_per_cpu_cfg = false;
+			r->cache.min_cbm_bits = 1;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			hw_res->msr_update = mba_wrmsr_intel;
@@ -856,6 +851,7 @@ static __init void rdt_init_res_defs_amd(void)
 			r->cache.arch_has_sparse_bitmaps = true;
 			r->cache.arch_has_empty_bitmaps = true;
 			r->cache.arch_has_per_cpu_cfg = true;
+			r->cache.min_cbm_bits = 0;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			hw_res->msr_base = MSR_IA32_MBA_BW_BASE;
 			hw_res->msr_update = mba_wrmsr_amd;

arch/x86/kernel/cpu/topology.c

@@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
 	unsigned int die_select_mask, die_level_siblings;
+	unsigned int pkg_mask_width;
 	bool die_level_present = false;
 	int leaf;
 
@@ -111,10 +112,10 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 	die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
-	die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+	pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
 	sub_index = 1;
-	do {
+	while (true) {
 		cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
 
 		/*
@@ -132,10 +133,15 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
 
+		if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE)
+			pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+		else
+			break;
+
 		sub_index++;
-	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+	}
 
-	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
+	core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width;
 	die_select_mask = (~(-1 << die_plus_mask_width)) >>
 				core_plus_mask_width;
 
@@ -148,7 +154,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	}
 
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
-				die_plus_mask_width);
+				pkg_mask_width);
 	/*
 	 * Reinit the apicid, now that we have extended initial_apicid.
 	 */

arch/x86/kernel/fpu/init.c

@@ -210,13 +210,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	fpstate_reset(&current->thread.fpu);
 }
 
-static void __init fpu__init_init_fpstate(void)
-{
-	/* Bring init_fpstate size and features up to date */
-	init_fpstate.size		= fpu_kernel_cfg.max_size;
-	init_fpstate.xfeatures		= fpu_kernel_cfg.max_features;
-}
-
 /*
  * Called on the boot CPU once per system bootup, to set up the initial
  * FPU state that is later cloned into all processes:
@@ -236,5 +229,4 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate(fpu_kernel_cfg.max_size);
 	fpu__init_task_struct_size();
-	fpu__init_init_fpstate();
 }

arch/x86/kernel/fpu/xstate.c

@@ -360,7 +360,7 @@ static void __init setup_init_fpu_buf(void)
 
 	print_xstate_features();
 
-	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
+	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures);
 
 	/*
 	 * Init all the features state with header.xfeatures being 0x0
@@ -678,20 +678,6 @@ static unsigned int __init get_xsave_size_user(void)
 	return ebx;
 }
 
-/*
- * Will the runtime-enumerated 'xstate_size' fit in the init
- * task's statically-allocated buffer?
- */
-static bool __init is_supported_xstate_size(unsigned int test_xstate_size)
-{
-	if (test_xstate_size <= sizeof(init_fpstate.regs))
-		return true;
-
-	pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n",
-			sizeof(init_fpstate.regs), test_xstate_size);
-	return false;
-}
-
 static int __init init_xstate_size(void)
 {
 	/* Recompute the context size for enabled features: */
@@ -717,10 +703,6 @@ static int __init init_xstate_size(void)
 	kernel_default_size =
 		xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
 
-	/* Ensure we have the space to store all default enabled features. */
-	if (!is_supported_xstate_size(kernel_default_size))
-		return -EINVAL;
-
 	if (!paranoid_xstate_size_valid(kernel_size))
 		return -EINVAL;
 
@@ -875,6 +857,19 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	update_regset_xstate_info(fpu_user_cfg.max_size,
 				  fpu_user_cfg.max_features);
 
+	/*
+	 * init_fpstate excludes dynamic states as they are large but init
+	 * state is zero.
+	 */
+	init_fpstate.size		= fpu_kernel_cfg.default_size;
+	init_fpstate.xfeatures		= fpu_kernel_cfg.default_features;
+
+	if (init_fpstate.size > sizeof(init_fpstate.regs)) {
+		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+			sizeof(init_fpstate.regs), init_fpstate.size);
+		goto out_disable;
+	}
+
 	setup_init_fpu_buf();
 
 	/*
@@ -1130,6 +1125,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	 */
 	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.
+	 */
+	if (fpu_state_size_dynamic())
+		mask &= (header.xfeatures | xinit->header.xcomp_bv);
+
 	for_each_extended_xfeature(i, mask) {
 		/*
 		 * If there was a feature or alignment gap, zero the space

arch/x86/kernel/ftrace_64.S

@@ -4,6 +4,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
 #include <asm/export.h>
@@ -129,6 +130,14 @@
 
 	.endm
 
+SYM_TYPED_FUNC_START(ftrace_stub)
+	RET
+SYM_FUNC_END(ftrace_stub)
+
+SYM_TYPED_FUNC_START(ftrace_stub_graph)
+	RET
+SYM_FUNC_END(ftrace_stub_graph)
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
@@ -172,21 +181,10 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	 */
 SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
-
-	jmp ftrace_epilogue
+	RET
 SYM_FUNC_END(ftrace_caller);
 STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
 
-SYM_FUNC_START(ftrace_epilogue)
-/*
- * This is weak to keep gas from relaxing the jumps.
- */
-SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
-	UNWIND_HINT_FUNC
-	ENDBR
-	RET
-SYM_FUNC_END(ftrace_epilogue)
-
 SYM_FUNC_START(ftrace_regs_caller)
 	/* Save the current flags before any operations that can change them */
 	pushfq
@@ -262,14 +260,11 @@ SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL)
 	popfq
 
 	/*
-	 * As this jmp to ftrace_epilogue can be a short jump
-	 * it must not be copied into the trampoline.
-	 * The trampoline will add the code to jump
-	 * to the return.
+	 * The trampoline will add the return.
 	 */
 SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
-	jmp ftrace_epilogue
+	RET
 
 	/* Swap the flags with orig_rax */
 1:	movq MCOUNT_REG_SIZE(%rsp), %rdi
@@ -280,7 +275,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	/* Restore flags */
 	popfq
 	UNWIND_HINT_FUNC
-	jmp	ftrace_epilogue
+	RET
 
 SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
@@ -291,9 +286,6 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 SYM_FUNC_START(__fentry__)
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
-
-SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
-	ENDBR
 	RET
 
 trace: