Merge 06afb0f into 28eb75e

Author: pull[bot]

Documentation/core-api/printk-formats.rst

@@ -209,12 +209,17 @@ Struct Resources
 ::
 
 	%pr	[mem 0x60000000-0x6fffffff flags 0x2200] or
+		[mem 0x60000000 flags 0x2200] or
 		[mem 0x0000000060000000-0x000000006fffffff flags 0x2200]
+		[mem 0x0000000060000000 flags 0x2200]
 	%pR	[mem 0x60000000-0x6fffffff pref] or
+		[mem 0x60000000 pref] or
 		[mem 0x0000000060000000-0x000000006fffffff pref]
+		[mem 0x0000000060000000 pref]
 
 For printing struct resources. The ``R`` and ``r`` specifiers result in a
-printed resource with (R) or without (r) a decoded flags member.
+printed resource with (R) or without (r) a decoded flags member.  If start is
+equal to end only print the start value.
 
 Passed by reference.
 
@@ -231,6 +236,19 @@ width of the CPU data path.
 
 Passed by reference.
 
+Struct Range
+------------
+
+::
+
+	%pra    [range 0x0000000060000000-0x000000006fffffff] or
+		[range 0x0000000060000000]
+
+For printing struct range.  struct range holds an arbitrary range of u64
+values.  If start is equal to end only print the start value.
+
+Passed by reference.
+
 DMA address types dma_addr_t
 ----------------------------
 

Documentation/tools/rtla/common_timerlat_options.rst

@@ -31,6 +31,14 @@
         *cyclictest* sets this value to *0* by default, use **--dma-latency** *0* to have
         similar results.
 
+**--deepest-idle-state** *n*
+        Disable idle states higher than *n* for cpus that are running timerlat threads to
+        reduce exit from idle latencies. If *n* is -1, all idle states are disabled.
+        On exit from timerlat, the idle state setting is restored to its original state
+        before running timerlat.
+
+        Requires rtla to be built with libcpupower.
+
 **-k**, **--kernel-threads**
 
         Use timerlat kernel-space threads, in contrast of **-u**.

Documentation/trace/ftrace.rst

@@ -1031,9 +1031,6 @@ explains which is which.
   CPU#: The CPU which the process was running on.
 
   irqs-off: 'd' interrupts are disabled. '.' otherwise.
-	.. caution:: If the architecture does not support a way to
-		read the irq flags variable, an 'X' will always
-		be printed here.
 
   need-resched:
 	- 'N' both TIF_NEED_RESCHED and PREEMPT_NEED_RESCHED is set,

arch/x86/Kconfig

@@ -2564,15 +2564,14 @@ config MITIGATION_CALL_DEPTH_TRACKING
 	default y
 	help
 	  Compile the kernel with call depth tracking to mitigate the Intel
-	  SKL Return-Speculation-Buffer (RSB) underflow issue. The
-	  mitigation is off by default and needs to be enabled on the
-	  kernel command line via the retbleed=stuff option. For
-	  non-affected systems the overhead of this option is marginal as
-	  the call depth tracking is using run-time generated call thunks
-	  in a compiler generated padding area and call patching. This
-	  increases text size by ~5%. For non affected systems this space
-	  is unused. On affected SKL systems this results in a significant
-	  performance gain over the IBRS mitigation.
+	  SKL Return-Stack-Buffer (RSB) underflow issue. The mitigation is off
+	  by default and needs to be enabled on the kernel command line via the
+	  retbleed=stuff option. For non-affected systems the overhead of this
+	  option is marginal as the call depth tracking is using run-time
+	  generated call thunks in a compiler generated padding area and call
+	  patching. This increases text size by ~5%. For non affected systems
+	  this space is unused. On affected SKL systems this results in a
+	  significant performance gain over the IBRS mitigation.
 
 config CALL_THUNKS_DEBUG
 	bool "Enable call thunks and call depth tracking debugging"

arch/x86/coco/tdx/tdx.c

@@ -78,6 +78,32 @@ static inline void tdcall(u64 fn, struct tdx_module_args *args)
 		panic("TDCALL %lld failed (Buggy TDX module!)\n", fn);
 }
 
+/* Read TD-scoped metadata */
+static inline u64 tdg_vm_rd(u64 field, u64 *value)
+{
+	struct tdx_module_args args = {
+		.rdx = field,
+	};
+	u64 ret;
+
+	ret = __tdcall_ret(TDG_VM_RD, &args);
+	*value = args.r8;
+
+	return ret;
+}
+
+/* Write TD-scoped metadata */
+static inline u64 tdg_vm_wr(u64 field, u64 value, u64 mask)
+{
+	struct tdx_module_args args = {
+		.rdx = field,
+		.r8 = value,
+		.r9 = mask,
+	};
+
+	return __tdcall(TDG_VM_WR, &args);
+}
+
 /**
  * tdx_mcall_get_report0() - Wrapper to get TDREPORT0 (a.k.a. TDREPORT
  *                           subtype 0) using TDG.MR.REPORT TDCALL.
@@ -168,7 +194,87 @@ static void __noreturn tdx_panic(const char *msg)
 		__tdx_hypercall(&args);
 }
 
-static void tdx_parse_tdinfo(u64 *cc_mask)
+/*
+ * The kernel cannot handle #VEs when accessing normal kernel memory. Ensure
+ * that no #VE will be delivered for accesses to TD-private memory.
+ *
+ * TDX 1.0 does not allow the guest to disable SEPT #VE on its own. The VMM
+ * controls if the guest will receive such #VE with TD attribute
+ * ATTR_SEPT_VE_DISABLE.
+ *
+ * Newer TDX modules allow the guest to control if it wants to receive SEPT
+ * violation #VEs.
+ *
+ * Check if the feature is available and disable SEPT #VE if possible.
+ *
+ * If the TD is allowed to disable/enable SEPT #VEs, the ATTR_SEPT_VE_DISABLE
+ * attribute is no longer reliable. It reflects the initial state of the
+ * control for the TD, but it will not be updated if someone (e.g. bootloader)
+ * changes it before the kernel starts. Kernel must check TDCS_TD_CTLS bit to
+ * determine if SEPT #VEs are enabled or disabled.
+ */
+static void disable_sept_ve(u64 td_attr)
+{
+	const char *msg = "TD misconfiguration: SEPT #VE has to be disabled";
+	bool debug = td_attr & ATTR_DEBUG;
+	u64 config, controls;
+
+	/* Is this TD allowed to disable SEPT #VE */
+	tdg_vm_rd(TDCS_CONFIG_FLAGS, &config);
+	if (!(config & TDCS_CONFIG_FLEXIBLE_PENDING_VE)) {
+		/* No SEPT #VE controls for the guest: check the attribute */
+		if (td_attr & ATTR_SEPT_VE_DISABLE)
+			return;
+
+		/* Relax SEPT_VE_DISABLE check for debug TD for backtraces */
+		if (debug)
+			pr_warn("%s\n", msg);
+		else
+			tdx_panic(msg);
+		return;
+	}
+
+	/* Check if SEPT #VE has been disabled before us */
+	tdg_vm_rd(TDCS_TD_CTLS, &controls);
+	if (controls & TD_CTLS_PENDING_VE_DISABLE)
+		return;
+
+	/* Keep #VEs enabled for splats in debugging environments */
+	if (debug)
+		return;
+
+	/* Disable SEPT #VEs */
+	tdg_vm_wr(TDCS_TD_CTLS, TD_CTLS_PENDING_VE_DISABLE,
+		  TD_CTLS_PENDING_VE_DISABLE);
+}
+
+/*
+ * TDX 1.0 generates a #VE when accessing topology-related CPUID leafs (0xB and
+ * 0x1F) and the X2APIC_APICID MSR. The kernel returns all zeros on CPUID #VEs.
+ * In practice, this means that the kernel can only boot with a plain topology.
+ * Any complications will cause problems.
+ *
+ * The ENUM_TOPOLOGY feature allows the VMM to provide topology information.
+ * Enabling the feature  eliminates topology-related #VEs: the TDX module
+ * virtualizes accesses to the CPUID leafs and the MSR.
+ *
+ * Enable ENUM_TOPOLOGY if it is available.
+ */
+static void enable_cpu_topology_enumeration(void)
+{
+	u64 configured;
+
+	/* Has the VMM provided a valid topology configuration? */
+	tdg_vm_rd(TDCS_TOPOLOGY_ENUM_CONFIGURED, &configured);
+	if (!configured) {
+		pr_err("VMM did not configure X2APIC_IDs properly\n");
+		return;
+	}
+
+	tdg_vm_wr(TDCS_TD_CTLS, TD_CTLS_ENUM_TOPOLOGY, TD_CTLS_ENUM_TOPOLOGY);
+}
+
+static void tdx_setup(u64 *cc_mask)
 {
 	struct tdx_module_args args = {};
 	unsigned int gpa_width;
@@ -193,21 +299,13 @@ static void tdx_parse_tdinfo(u64 *cc_mask)
 	gpa_width = args.rcx & GENMASK(5, 0);
 	*cc_mask = BIT_ULL(gpa_width - 1);
 
-	/*
-	 * The kernel can not handle #VE's when accessing normal kernel
-	 * memory.  Ensure that no #VE will be delivered for accesses to
-	 * TD-private memory.  Only VMM-shared memory (MMIO) will #VE.
-	 */
 	td_attr = args.rdx;
-	if (!(td_attr & ATTR_SEPT_VE_DISABLE)) {
-		const char *msg = "TD misconfiguration: SEPT_VE_DISABLE attribute must be set.";
 
-		/* Relax SEPT_VE_DISABLE check for debug TD. */
-		if (td_attr & ATTR_DEBUG)
-			pr_warn("%s\n", msg);
-		else
-			tdx_panic(msg);
-	}
+	/* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */
+	tdg_vm_wr(TDCS_NOTIFY_ENABLES, 0, -1ULL);
+
+	disable_sept_ve(td_attr);
+	enable_cpu_topology_enumeration();
 }
 
 /*
@@ -929,10 +1027,6 @@ static void tdx_kexec_finish(void)
 
 void __init tdx_early_init(void)
 {
-	struct tdx_module_args args = {
-		.rdx = TDCS_NOTIFY_ENABLES,
-		.r9 = -1ULL,
-	};
 	u64 cc_mask;
 	u32 eax, sig[3];
 
@@ -947,11 +1041,11 @@ void __init tdx_early_init(void)
 	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
 
 	cc_vendor = CC_VENDOR_INTEL;
-	tdx_parse_tdinfo(&cc_mask);
-	cc_set_mask(cc_mask);
 
-	/* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */
-	tdcall(TDG_VM_WR, &args);
+	/* Configure the TD */
+	tdx_setup(&cc_mask);
+
+	cc_set_mask(cc_mask);
 
 	/*
 	 * All bits above GPA width are reserved and kernel treats shared bit

arch/x86/include/asm/cpuid.h

@@ -6,6 +6,8 @@
 #ifndef _ASM_X86_CPUID_H
 #define _ASM_X86_CPUID_H
 
+#include <linux/types.h>
+
 #include <asm/string.h>
 
 struct cpuid_regs {
@@ -20,11 +22,11 @@ enum cpuid_regs_idx {
 };
 
 #ifdef CONFIG_X86_32
-extern int have_cpuid_p(void);
+bool have_cpuid_p(void);
 #else
-static inline int have_cpuid_p(void)
+static inline bool have_cpuid_p(void)
 {
-	return 1;
+	return true;
 }
 #endif
 static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,

arch/x86/include/asm/shared/tdx.h

@@ -16,10 +16,21 @@
 #define TDG_VP_VEINFO_GET		3
 #define TDG_MR_REPORT			4
 #define TDG_MEM_PAGE_ACCEPT		6
+#define TDG_VM_RD			7
 #define TDG_VM_WR			8
 
-/* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */
+/* TDX TD-Scope Metadata. To be used by TDG.VM.WR and TDG.VM.RD */
+#define TDCS_CONFIG_FLAGS		0x1110000300000016
+#define TDCS_TD_CTLS			0x1110000300000017
 #define TDCS_NOTIFY_ENABLES		0x9100000000000010
+#define TDCS_TOPOLOGY_ENUM_CONFIGURED	0x9100000000000019
+
+/* TDCS_CONFIG_FLAGS bits */
+#define TDCS_CONFIG_FLEXIBLE_PENDING_VE	BIT_ULL(1)
+
+/* TDCS_TD_CTLS bits */
+#define TD_CTLS_PENDING_VE_DISABLE	BIT_ULL(0)
+#define TD_CTLS_ENUM_TOPOLOGY		BIT_ULL(1)
 
 /* TDX hypercall Leaf IDs */
 #define TDVMCALL_MAP_GPA		0x10001

arch/x86/kernel/cpu/common.c

@@ -276,21 +276,13 @@ static int __init x86_noinvpcid_setup(char *s)
 }
 early_param("noinvpcid", x86_noinvpcid_setup);
 
-#ifdef CONFIG_X86_32
-static int cachesize_override = -1;
-static int disable_x86_serial_nr = 1;
-
-static int __init cachesize_setup(char *str)
-{
-	get_option(&str, &cachesize_override);
-	return 1;
-}
-__setup("cachesize=", cachesize_setup);
-
 /* Standard macro to see if a specific flag is changeable */
-static inline int flag_is_changeable_p(u32 flag)
+static inline bool flag_is_changeable_p(unsigned long flag)
 {
-	u32 f1, f2;
+	unsigned long f1, f2;
+
+	if (!IS_ENABLED(CONFIG_X86_32))
+		return true;
 
 	/*
 	 * Cyrix and IDT cpus allow disabling of CPUID
@@ -313,11 +305,22 @@ static inline int flag_is_changeable_p(u32 flag)
 		      : "=&r" (f1), "=&r" (f2)
 		      : "ir" (flag));
 
-	return ((f1^f2) & flag) != 0;
+	return (f1 ^ f2) & flag;
 }
 
+#ifdef CONFIG_X86_32
+static int cachesize_override = -1;
+static int disable_x86_serial_nr = 1;
+
+static int __init cachesize_setup(char *str)
+{
+	get_option(&str, &cachesize_override);
+	return 1;
+}
+__setup("cachesize=", cachesize_setup);
+
 /* Probe for the CPUID instruction */
-int have_cpuid_p(void)
+bool have_cpuid_p(void)
 {
 	return flag_is_changeable_p(X86_EFLAGS_ID);
 }
@@ -349,10 +352,6 @@ static int __init x86_serial_nr_setup(char *s)
 }
 __setup("serialnumber", x86_serial_nr_setup);
 #else
-static inline int flag_is_changeable_p(u32 flag)
-{
-	return 1;
-}
 static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
 {
 }
@@ -1088,7 +1087,6 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_32
 	int i;
 
 	/*
@@ -1109,7 +1107,6 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 				break;
 			}
 		}
-#endif
 }
 
 #define NO_SPECULATION		BIT(0)

arch/x86/kernel/cpu/sgx/main.c

@@ -630,7 +630,7 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
 	if (!section->virt_addr)
 		return false;
 
-	section->pages = vmalloc(nr_pages * sizeof(struct sgx_epc_page));
+	section->pages = vmalloc_array(nr_pages, sizeof(struct sgx_epc_page));
 	if (!section->pages) {
 		memunmap(section->virt_addr);
 		return false;