Merge tag 'x86-urgent-2024-03-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

torvalds · torvalds · commit 5e74df2f8f15 · 2024-03-24T11:13:56.000-07:00
Pull x86 fixes from Thomas Gleixner:

 - Ensure that the encryption mask at boot is properly propagated on
   5-level page tables, otherwise the PGD entry is incorrectly set to
   non-encrypted, which causes system crashes during boot.

 - Undo the deferred 5-level page table setup as it cannot work with
   memory encryption enabled.

 - Prevent inconsistent XFD state on CPU hotplug, where the MSR is reset
   to the default value but the cached variable is not, so subsequent
   comparisons might yield the wrong result and as a consequence the
   result prevents updating the MSR.

 - Register the local APIC address only once in the MPPARSE enumeration
   to prevent triggering the related WARN_ONs() in the APIC and topology
   code.

 - Handle the case where no APIC is found gracefully by registering a
   fake APIC in the topology code. That makes all related topology
   functions work correctly and does not affect the actual APIC driver
   code at all.

 - Don't evaluate logical IDs during early boot as the local APIC IDs
   are not yet enumerated and the invoked function returns an error
   code. Nothing requires the logical IDs before the final CPUID
   enumeration takes place, which happens after the enumeration.

 - Cure the fallout of the per CPU rework on UP which misplaced the
   copying of boot_cpu_data to per CPU data so that the final update to
   boot_cpu_data got lost which caused inconsistent state and boot
   crashes.

 - Use copy_from_kernel_nofault() in the kprobes setup as there is no
   guarantee that the address can be safely accessed.

 - Reorder struct members in struct saved_context to work around another
   kmemleak false positive

 - Remove the buggy code which tries to update the E820 kexec table for
   setup_data as that is never passed to the kexec kernel.

 - Update the resource control documentation to use the proper units.

 - Fix a Kconfig warning observed with tinyconfig

* tag 'x86-urgent-2024-03-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot/64: Move 5-level paging global variable assignments back
  x86/boot/64: Apply encryption mask to 5-level pagetable update
  x86/cpu: Add model number for another Intel Arrow Lake mobile processor
  x86/fpu: Keep xfd_state in sync with MSR_IA32_XFD
  Documentation/x86: Document that resctrl bandwidth control units are MiB
  x86/mpparse: Register APIC address only once
  x86/topology: Handle the !APIC case gracefully
  x86/topology: Don't evaluate logical IDs during early boot
  x86/cpu: Ensure that CPU info updates are propagated on UP
  kprobes/x86: Use copy_from_kernel_nofault() to read from unsafe address
  x86/pm: Work around false positive kmemleak report in msr_build_context()
  x86/kexec: Do not update E820 kexec table for setup_data
  x86/config: Fix warning for 'make ARCH=x86_64 tinyconfig'
diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
@@ -45,7 +45,7 @@ mount options are:
 	Enable code/data prioritization in L2 cache allocations.
 "mba_MBps":
 	Enable the MBA Software Controller(mba_sc) to specify MBA
-	bandwidth in MBps
+	bandwidth in MiBps
 "debug":
 	Make debug files accessible. Available debug files are annotated with
 	"Available only with debug option".
@@ -526,7 +526,7 @@ threads start using more cores in an rdtgroup, the actual bandwidth may
 increase or vary although user specified bandwidth percentage is same.
 
 In order to mitigate this and make the interface more user friendly,
-resctrl added support for specifying the bandwidth in MBps as well.  The
+resctrl added support for specifying the bandwidth in MiBps as well.  The
 kernel underneath would use a software feedback mechanism or a "Software
 Controller(mba_sc)" which reads the actual bandwidth using MBM counters
 and adjust the memory bandwidth percentages to ensure::
@@ -573,13 +573,13 @@ Memory b/w domain is L3 cache.
 
 	MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
 
-Memory bandwidth Allocation specified in MBps
+Memory bandwidth Allocation specified in MiBps
 ---------------------------------------------
 
 Memory bandwidth domain is L3 cache.
 ::
 
-	MB:<cache_id0>=bw_MBps0;<cache_id1>=bw_MBps1;...
+	MB:<cache_id0>=bw_MiBps0;<cache_id1>=bw_MiBps1;...
 
 Slow Memory Bandwidth Allocation (SMBA)
 ---------------------------------------
diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config
@@ -1,5 +1,6 @@
 CONFIG_NOHIGHMEM=y
 # CONFIG_HIGHMEM4G is not set
 # CONFIG_HIGHMEM64G is not set
+# CONFIG_UNWINDER_ORC is not set
 CONFIG_UNWINDER_GUESS=y
 # CONFIG_UNWINDER_FRAME_POINTER is not set
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
@@ -127,6 +127,7 @@
 
 #define INTEL_FAM6_ARROWLAKE_H		0xC5
 #define INTEL_FAM6_ARROWLAKE		0xC6
+#define INTEL_FAM6_ARROWLAKE_U		0xB5
 
 #define INTEL_FAM6_LUNARLAKE_M		0xBD
 
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
@@ -12,11 +12,6 @@
 
 /* image of the saved processor state */
 struct saved_context {
-	/*
-	 * On x86_32, all segment registers except gs are saved at kernel
-	 * entry in pt_regs.
-	 */
-	u16 gs;
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	struct saved_msrs saved_msrs;
@@ -27,6 +22,11 @@ struct saved_context {
 	unsigned long tr;
 	unsigned long safety;
 	unsigned long return_address;
+	/*
+	 * On x86_32, all segment registers except gs are saved at kernel
+	 * entry in pt_regs.
+	 */
+	u16 gs;
 	bool misc_enable_saved;
 } __attribute__((packed));
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
@@ -2307,6 +2307,8 @@ void arch_smt_update(void)
 
 void __init arch_cpu_finalize_init(void)
 {
+	struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info);
+
 	identify_boot_cpu();
 
 	select_idle_routine();
@@ -2345,6 +2347,13 @@ void __init arch_cpu_finalize_init(void)
 	fpu__init_system();
 	fpu__init_cpu();
 
+	/*
+	 * Ensure that access to the per CPU representation has the initial
+	 * boot CPU configuration.
+	 */
+	*c = boot_cpu_data;
+	c->initialized = true;
+
 	alternative_instructions();
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
@@ -415,6 +415,17 @@ void __init topology_init_possible_cpus(void)
 	unsigned int total = assigned + disabled;
 	u32 apicid, firstid;
 
+	/*
+	 * If there was no APIC registered, then fake one so that the
+	 * topology bitmap is populated. That ensures that the code below
+	 * is valid and the various query interfaces can be used
+	 * unconditionally. This does not affect the actual APIC code in
+	 * any way because either the local APIC address has not been
+	 * registered or the local APIC was disabled on the command line.
+	 */
+	if (topo_info.boot_cpu_apic_id == BAD_APICID)
+		topology_register_boot_apic(0);
+
 	if (!restrict_to_up()) {
 		if (WARN_ON_ONCE(assigned > nr_cpu_ids)) {
 			disabled += assigned - nr_cpu_ids;
diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c
@@ -140,16 +140,18 @@ static void parse_topology(struct topo_scan *tscan, bool early)
 	}
 }
 
-static void topo_set_ids(struct topo_scan *tscan)
+static void topo_set_ids(struct topo_scan *tscan, bool early)
 {
 	struct cpuinfo_x86 *c = tscan->c;
 	u32 apicid = c->topo.apicid;
 
 	c->topo.pkg_id = topo_shift_apicid(apicid, TOPO_PKG_DOMAIN);
 	c->topo.die_id = topo_shift_apicid(apicid, TOPO_DIE_DOMAIN);
 
-	c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);
-	c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);
+	if (!early) {
+		c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);
+		c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);
+	}
 
 	/* Package relative core ID */
 	c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >>
@@ -187,7 +189,7 @@ void cpu_parse_topology(struct cpuinfo_x86 *c)
 		       tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]);
 	}
 
-	topo_set_ids(&tscan);
+	topo_set_ids(&tscan, false);
 }
 
 void __init cpu_init_topology(struct cpuinfo_x86 *c)
@@ -208,7 +210,7 @@ void __init cpu_init_topology(struct cpuinfo_x86 *c)
 		x86_topo_system.dom_size[dom] = 1U << sft;
 	}
 
-	topo_set_ids(&tscan);
+	topo_set_ids(&tscan, true);
 
 	/*
 	 * AMD systems have Nodes per package which cannot be mapped to
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
@@ -1016,17 +1016,6 @@ void __init e820__reserve_setup_data(void)
 
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 
-		/*
-		 * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by
-		 * kexec and do not need to be reserved.
-		 */
-		if (data->type != SETUP_EFI &&
-		    data->type != SETUP_IMA &&
-		    data->type != SETUP_RNG_SEED)
-			e820__range_update_kexec(pa_data,
-						 sizeof(*data) + data->len,
-						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-
 		if (data->type == SETUP_INDIRECT) {
 			len += data->len;
 			early_memunmap(data, sizeof(*data));
@@ -1038,20 +1027,16 @@ void __init e820__reserve_setup_data(void)
 
 			indirect = (struct setup_indirect *)data->data;
 
-			if (indirect->type != SETUP_INDIRECT) {
+			if (indirect->type != SETUP_INDIRECT)
 				e820__range_update(indirect->addr, indirect->len,
 						   E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-				e820__range_update_kexec(indirect->addr, indirect->len,
-							 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-			}
 		}
 
 		pa_data = pa_next;
 		early_memunmap(data, len);
 	}
 
 	e820__update_table(e820_table);
-	e820__update_table(e820_table_kexec);
 
 	pr_info("extended physical RAM map:\n");
 	e820__print_table("reserve setup_data");
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
@@ -178,10 +178,11 @@ void fpu__init_cpu_xstate(void)
 	 * Must happen after CR4 setup and before xsetbv() to allow KVM
 	 * lazy passthrough.  Write independent of the dynamic state static
 	 * key as that does not work on the boot CPU. This also ensures
-	 * that any stale state is wiped out from XFD.
+	 * that any stale state is wiped out from XFD. Reset the per CPU
+	 * xfd cache too.
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_XFD))
-		wrmsrl(MSR_IA32_XFD, init_fpstate.xfd);
+		xfd_set_state(init_fpstate.xfd);
 
 	/*
 	 * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
@@ -148,20 +148,26 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs
 #endif
 
 #ifdef CONFIG_X86_64
+static inline void xfd_set_state(u64 xfd)
+{
+	wrmsrl(MSR_IA32_XFD, xfd);
+	__this_cpu_write(xfd_state, xfd);
+}
+
 static inline void xfd_update_state(struct fpstate *fpstate)
 {
 	if (fpu_state_size_dynamic()) {
 		u64 xfd = fpstate->xfd;
 
-		if (__this_cpu_read(xfd_state) != xfd) {
-			wrmsrl(MSR_IA32_XFD, xfd);
-			__this_cpu_write(xfd_state, xfd);
-		}
+		if (__this_cpu_read(xfd_state) != xfd)
+			xfd_set_state(xfd);
 	}
 }
 
 extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu);
 #else
+static inline void xfd_set_state(u64 xfd) { }
+
 static inline void xfd_update_state(struct fpstate *fpstate) { }
 
 static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) {
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
@@ -81,6 +81,13 @@ static inline bool check_la57_support(void)
 	if (!(native_read_cr4() & X86_CR4_LA57))
 		return false;
 
+	RIP_REL_REF(__pgtable_l5_enabled)	= 1;
+	RIP_REL_REF(pgdir_shift)		= 48;
+	RIP_REL_REF(ptrs_per_p4d)		= 512;
+	RIP_REL_REF(page_offset_base)		= __PAGE_OFFSET_BASE_L5;
+	RIP_REL_REF(vmalloc_base)		= __VMALLOC_BASE_L5;
+	RIP_REL_REF(vmemmap_base)		= __VMEMMAP_BASE_L5;
+
 	return true;
 }
 
@@ -175,7 +182,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 		p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt);
 		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
 
-		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE_NOENC;
+		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
 	}
 
 	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta;
@@ -431,15 +438,6 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode
 				(__START_KERNEL & PGDIR_MASK)));
 	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
-	if (check_la57_support()) {
-		__pgtable_l5_enabled	= 1;
-		pgdir_shift		= 48;
-		ptrs_per_p4d		= 512;
-		page_offset_base	= __PAGE_OFFSET_BASE_L5;
-		vmalloc_base		= __VMALLOC_BASE_L5;
-		vmemmap_base		= __VMEMMAP_BASE_L5;
-	}
-
 	cr4_init_shadow();
 
 	/* Kill off the identity-map trampoline */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
@@ -373,7 +373,16 @@ static bool can_probe(unsigned long paddr)
 kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
 					 bool *on_func_entry)
 {
-	if (is_endbr(*(u32 *)addr)) {
+	u32 insn;
+
+	/*
+	 * Since 'addr' is not guaranteed to be safe to access, use
+	 * copy_from_kernel_nofault() to read the instruction:
+	 */
+	if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32)))
+		return NULL;
+
+	if (is_endbr(insn)) {
 		*on_func_entry = !offset || offset == 4;
 		if (*on_func_entry)
 			offset = 4;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
@@ -197,12 +197,12 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 	if (!smp_check_mpc(mpc, oem, str))
 		return 0;
 
-	/* Initialize the lapic mapping */
-	if (!acpi_lapic)
-		register_lapic_address(mpc->lapic);
-
-	if (early)
+	if (early) {
+		/* Initialize the lapic mapping */
+		if (!acpi_lapic)
+			register_lapic_address(mpc->lapic);
 		return 1;
+	}
 
 	/* Now process the configuration blocks. */
 	while (count < mpc->length) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
@@ -1206,16 +1206,6 @@ void __init i386_reserve_resources(void)
 
 #endif /* CONFIG_X86_32 */
 
-#ifndef CONFIG_SMP
-void __init smp_prepare_boot_cpu(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	*c = boot_cpu_data;
-	c->initialized = true;
-}
-#endif
-
 static struct notifier_block kernel_offset_notifier = {
 	.notifier_call = dump_kernel_offset
 };
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
@@ -313,14 +313,6 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
-static void __init smp_store_boot_cpu_info(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	*c = boot_cpu_data;
-	c->initialized = true;
-}
-
 /*
  * The bootstrap kernel entry code has set these up. Save them for
  * a given CPU
@@ -1039,29 +1031,15 @@ static __init void disable_smp(void)
 	cpumask_set_cpu(0, topology_die_cpumask(0));
 }
 
-static void __init smp_cpu_index_default(void)
-{
-	int i;
-	struct cpuinfo_x86 *c;
-
-	for_each_possible_cpu(i) {
-		c = &cpu_data(i);
-		/* mark all to hotplug */
-		c->cpu_index = nr_cpu_ids;
-	}
-}
-
 void __init smp_prepare_cpus_common(void)
 {
 	unsigned int i;
 
-	smp_cpu_index_default();
-
-	/*
-	 * Setup boot CPU information
-	 */
-	smp_store_boot_cpu_info(); /* Final full version of the data */
-	mb();
+	/* Mark all except the boot CPU as hotpluggable */
+	for_each_possible_cpu(i) {
+		if (i)
+			per_cpu(cpu_info.cpu_index, i) = nr_cpu_ids;
+	}
 
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);

Original file line number	Diff line number	Diff line change
`@@ -140,16 +140,18 @@ static void parse_topology(struct topo_scan *tscan, bool early)`
`140`	`140`	`}`
`141`	`141`	`}`
`142`	`142`
`143`		`-static void topo_set_ids(struct topo_scan *tscan)`
	`143`	`+static void topo_set_ids(struct topo_scan *tscan, bool early)`
`144`	`144`	`{`
`145`	`145`	`struct cpuinfo_x86 *c = tscan->c;`
`146`	`146`	`u32 apicid = c->topo.apicid;`
`147`	`147`
`148`	`148`	`c->topo.pkg_id = topo_shift_apicid(apicid, TOPO_PKG_DOMAIN);`
`149`	`149`	`c->topo.die_id = topo_shift_apicid(apicid, TOPO_DIE_DOMAIN);`
`150`	`150`
`151`		`- c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);`
`152`		`- c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);`
	`151`	`+ if (!early) {`
	`152`	`+ c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);`
	`153`	`+ c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);`
	`154`	`+ }`
`153`	`155`
`154`	`156`	`/* Package relative core ID */`
`155`	`157`	`c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >>`
`@@ -187,7 +189,7 @@ void cpu_parse_topology(struct cpuinfo_x86 *c)`
`187`	`189`	`tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]);`
`188`	`190`	`}`
`189`	`191`
`190`		`- topo_set_ids(&tscan);`
	`192`	`+ topo_set_ids(&tscan, false);`
`191`	`193`	`}`
`192`	`194`
`193`	`195`	`void __init cpu_init_topology(struct cpuinfo_x86 *c)`
`@@ -208,7 +210,7 @@ void __init cpu_init_topology(struct cpuinfo_x86 *c)`
`208`	`210`	`x86_topo_system.dom_size[dom] = 1U << sft;`
`209`	`211`	`}`
`210`	`212`
`211`		`- topo_set_ids(&tscan);`
	`213`	`+ topo_set_ids(&tscan, true);`
`212`	`214`
`213`	`215`	`/*`
`214`	`216`	`* AMD systems have Nodes per package which cannot be mapped to`