Merge branch 'x86/urgent' into x86/core, to resolve conflict

There's a conflict between the call-depth tracking commits in x86/core:

  ee3e2469b346 ("x86/ftrace: Make it call depth tracking aware")
  36b64f101219 ("x86/ftrace: Rebalance RSB")
  eac828eaef29 ("x86/ftrace: Remove ftrace_epilogue()")

And these fixes in x86/urgent:

  883bbbffa5a4 ("ftrace,kcfi: Separate ftrace_stub() and ftrace_stub_graph()")
  b5f1fc318440 ("x86/ftrace: Remove ftrace_epilogue()")

It's non-trivial overlapping modifications - resolve them.

 Conflicts:
	arch/x86/kernel/ftrace_64.S

Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 120 insertions, 73 deletions

diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index bd5df50e4643..795344ab4ec4 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/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)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a1dae9d5e3da..b52ad13f0f44 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1975,7 +1975,6 @@ 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
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4fce1a4226e3..8259d725054d 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/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);
 }
 
 /**
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index e7410e98fc1f..3a35dec3ec55 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/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;
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index de62b0b87ced..3266ea36667c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/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;
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 132a2de44d2f..5e868b62a7c4 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/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.
 	 */
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 621f4b6cac4a..8946f89761cc 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/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();
 }
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8340156bfd2..59e543b95a3c 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/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
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 6a7e6d666a12..1265ad519249 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -3,6 +3,7 @@
  *  Copyright (C) 2014  Steven Rostedt, Red Hat Inc
  */
 
+#include <linux/cfi_types.h>
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
@@ -130,6 +131,16 @@
 
 	.endm
 
+SYM_TYPED_FUNC_START(ftrace_stub)
+	CALL_DEPTH_ACCOUNT
+	RET
+SYM_FUNC_END(ftrace_stub)
+
+SYM_TYPED_FUNC_START(ftrace_stub_graph)
+	CALL_DEPTH_ACCOUNT
+	RET
+SYM_FUNC_END(ftrace_stub_graph)
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
@@ -183,11 +194,6 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
 SYM_FUNC_END(ftrace_caller);
 STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
 
-SYM_FUNC_START(ftrace_stub)
-	UNWIND_HINT_FUNC
-	RET
-SYM_FUNC_END(ftrace_stub)
-
 SYM_FUNC_START(ftrace_regs_caller)
 	/* Save the current flags before any operations that can change them */
 	pushfq
@@ -309,9 +315,6 @@ SYM_FUNC_START(__fentry__)
 
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
-
-SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
-	ENDBR
 	RET
 
 trace:
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ccf0af5b988a..8bf32c6c85d9 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -46,9 +46,6 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
 #define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
 
-#define TO_CORE_ID(cpu)		(cpu_data(cpu).cpu_core_id)
-#define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
-
 #ifdef CONFIG_SMP
 #define for_each_sibling(i, cpu) \
 	for_each_cpu(i, topology_sibling_cpumask(cpu))
@@ -91,6 +88,8 @@ struct temp_data {
 struct platform_data {
 	struct device		*hwmon_dev;
 	u16			pkg_id;
+	u16			cpu_map[NUM_REAL_CORES];
+	struct ida		ida;
 	struct cpumask		cpumask;
 	struct temp_data	*core_data[MAX_CORE_DATA];
 	struct device_attribute name_attr;
@@ -441,7 +440,7 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag)
 							MSR_IA32_THERM_STATUS;
 	tdata->is_pkg_data = pkg_flag;
 	tdata->cpu = cpu;
-	tdata->cpu_core_id = TO_CORE_ID(cpu);
+	tdata->cpu_core_id = topology_core_id(cpu);
 	tdata->attr_size = MAX_CORE_ATTRS;
 	mutex_init(&tdata->update_lock);
 	return tdata;
@@ -454,7 +453,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
-	int err, attr_no;
+	int err, index, attr_no;
 
 	/*
 	 * Find attr number for sysfs:
@@ -462,14 +461,26 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	 * The attr number is always core id + 2
 	 * The Pkgtemp will always show up as temp1_*, if available
 	 */
-	attr_no = pkg_flag ? PKG_SYSFS_ATTR_NO : TO_ATTR_NO(cpu);
+	if (pkg_flag) {
+		attr_no = PKG_SYSFS_ATTR_NO;
+	} else {
+		index = ida_alloc(&pdata->ida, GFP_KERNEL);
+		if (index < 0)
+			return index;
+		pdata->cpu_map[index] = topology_core_id(cpu);
+		attr_no = index + BASE_SYSFS_ATTR_NO;
+	}
 
-	if (attr_no > MAX_CORE_DATA - 1)
-		return -ERANGE;
+	if (attr_no > MAX_CORE_DATA - 1) {
+		err = -ERANGE;
+		goto ida_free;
+	}
 
 	tdata = init_temp_data(cpu, pkg_flag);
-	if (!tdata)
-		return -ENOMEM;
+	if (!tdata) {
+		err = -ENOMEM;
+		goto ida_free;
+	}
 
 	/* Test if we can access the status register */
 	err = rdmsr_safe_on_cpu(cpu, tdata->status_reg, &eax, &edx);
@@ -505,6 +516,9 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 exit_free:
 	pdata->core_data[attr_no] = NULL;
 	kfree(tdata);
+ida_free:
+	if (!pkg_flag)
+		ida_free(&pdata->ida, index);
 	return err;
 }
 
@@ -524,6 +538,9 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx)
 
 	kfree(pdata->core_data[indx]);
 	pdata->core_data[indx] = NULL;
+
+	if (indx >= BASE_SYSFS_ATTR_NO)
+		ida_free(&pdata->ida, indx - BASE_SYSFS_ATTR_NO);
 }
 
 static int coretemp_probe(struct platform_device *pdev)
@@ -537,6 +554,7 @@ static int coretemp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	pdata->pkg_id = pdev->id;
+	ida_init(&pdata->ida);
 	platform_set_drvdata(pdev, pdata);
 
 	pdata->hwmon_dev = devm_hwmon_device_register_with_groups(dev, DRVNAME,
@@ -553,6 +571,7 @@ static int coretemp_remove(struct platform_device *pdev)
 		if (pdata->core_data[i])
 			coretemp_remove_core(pdata, i);
 
+	ida_destroy(&pdata->ida);
 	return 0;
 }
 
@@ -647,7 +666,7 @@ static int coretemp_cpu_offline(unsigned int cpu)
 	struct platform_device *pdev = coretemp_get_pdev(cpu);
 	struct platform_data *pd;
 	struct temp_data *tdata;
-	int indx, target;
+	int i, indx = -1, target;
 
 	/*
 	 * Don't execute this on suspend as the device remove locks
@@ -660,12 +679,19 @@ static int coretemp_cpu_offline(unsigned int cpu)
 	if (!pdev)
 		return 0;
 
-	/* The core id is too big, just return */
-	indx = TO_ATTR_NO(cpu);
-	if (indx > MAX_CORE_DATA - 1)
+	pd = platform_get_drvdata(pdev);
+
+	for (i = 0; i < NUM_REAL_CORES; i++) {
+		if (pd->cpu_map[i] == topology_core_id(cpu)) {
+			indx = i + BASE_SYSFS_ATTR_NO;
+			break;
+		}
+	}
+
+	/* Too many cores and this core is not populated, just return */
+	if (indx < 0)
 		return 0;
 
-	pd = platform_get_drvdata(pdev);
 	tdata = pd->core_data[indx];
 
 	cpumask_clear_cpu(cpu, &pd->cpumask);
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 335b5711a7ed..735c78114324 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -162,6 +162,16 @@
 #define PATCHABLE_DISCARDS	*(__patchable_function_entries)
 #endif
 
+#ifndef CONFIG_ARCH_SUPPORTS_CFI_CLANG
+/*
+ * Simply points to ftrace_stub, but with the proper protocol.
+ * Defined by the linker script in linux/vmlinux.lds.h
+ */
+#define	FTRACE_STUB_HACK	ftrace_stub_graph = ftrace_stub;
+#else
+#define FTRACE_STUB_HACK
+#endif
+
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 /*
  * The ftrace call sites are logged to a section whose name depends on the
@@ -169,10 +179,6 @@
  * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header
  * dependencies for FTRACE_CALLSITE_SECTION's definition.
  *
- * Need to also make ftrace_stub_graph point to ftrace_stub
- * so that the same stub location may have different protocols
- * and not mess up with C verifiers.
- *
  * ftrace_ops_list_func will be defined as arch_ftrace_ops_list_func
  * as some archs will have a different prototype for that function
  * but ftrace_ops_list_func() will have a single prototype.
@@ -182,11 +188,11 @@
 			KEEP(*(__mcount_loc))			\
 			KEEP_PATCHABLE				\
 			__stop_mcount_loc = .;			\
-			ftrace_stub_graph = ftrace_stub;	\
+			FTRACE_STUB_HACK			\
 			ftrace_ops_list_func = arch_ftrace_ops_list_func;
 #else
 # ifdef CONFIG_FUNCTION_TRACER
-#  define MCOUNT_REC()	ftrace_stub_graph = ftrace_stub;	\
+#  define MCOUNT_REC()	FTRACE_STUB_HACK			\
 			ftrace_ops_list_func = arch_ftrace_ops_list_func;
 # else
 #  define MCOUNT_REC()