Merge tag 'x86_urgent_for_v6.13_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Have the Automatic IBRS setting check on AMD does not falsely fire in
   the guest when it has been set already on the host

 - Make sure cacheinfo structures memory is allocated to address a boot
   NULL ptr dereference on Intel Meteor Lake which has different numbers
   of subleafs in its CPUID(4) leaf

 - Take care of the GDT restoring on the kexec path too, as expected by
   the kernel

 - Make sure SMP is not disabled when IO-APIC is disabled on the kernel
   cmdline

 - Add a PGD flag _PAGE_NOPTISHADOW to instruct machinery not to
   propagate changes to the kernelmode page tables, to the user portion,
   in PTI

 - Mark Intel Lunar Lake as affected by an issue where MONITOR wakeups
   can get lost and thus user-visible delays happen

 - Make sure PKRU is properly restored with XRSTOR on AMD after a PRKU
   write of 0 (WRPKRU) which will mark PKRU in its init state and thus
   lose the actual buffer

* tag 'x86_urgent_for_v6.13_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/CPU/AMD: WARN when setting EFER.AUTOIBRS if and only if the WRMSR fails
  x86/cacheinfo: Delete global num_cache_leaves
  cacheinfo: Allocate memory during CPU hotplug if not done from the primary CPU
  x86/kexec: Restore GDT on return from ::preserve_context kexec
  x86/cpu/topology: Remove limit of CPUs due to disabled IO/APIC
  x86/mm: Add _PAGE_NOPTISHADOW bit to avoid updating userspace page tables
  x86/cpu: Add Lunar Lake to list of CPUs with a broken MONITOR implementation
  x86/pkeys: Ensure updated PKRU value is XRSTOR'd
  x86/pkeys: Change caller of update_pkru_in_sigframe()

Author: torvalds

arch/x86/include/asm/pgtable_types.h

@@ -36,10 +36,12 @@
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 #ifdef CONFIG_X86_64
-#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW5 /* Saved Dirty bit */
+#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW5 /* Saved Dirty bit (leaf) */
+#define _PAGE_BIT_NOPTISHADOW	_PAGE_BIT_SOFTW5 /* No PTI shadow (root PGD) */
 #else
 /* Shared with _PAGE_BIT_UFFD_WP which is not supported on 32 bit */
-#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW2 /* Saved Dirty bit */
+#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW2 /* Saved Dirty bit (leaf) */
+#define _PAGE_BIT_NOPTISHADOW	_PAGE_BIT_SOFTW2 /* No PTI shadow (root PGD) */
 #endif
 
 /* If _PAGE_BIT_PRESENT is clear, we use these: */
@@ -139,6 +141,8 @@
 
 #define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
+#define _PAGE_NOPTISHADOW (_AT(pteval_t, 1) << _PAGE_BIT_NOPTISHADOW)
+
 /*
  * Set of bits not changed in pte_modify.  The pte's
  * protection key is treated like _PAGE_RW, for

arch/x86/kernel/cpu/amd.c

@@ -1065,7 +1065,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 */
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
 	    cpu_has(c, X86_FEATURE_AUTOIBRS))
-		WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS));
+		WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS) < 0);
 
 	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
 	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);

arch/x86/kernel/cpu/cacheinfo.c

@@ -178,8 +178,6 @@ struct _cpuid4_info_regs {
 	struct amd_northbridge *nb;
 };
 
-static unsigned short num_cache_leaves;
-
 /* AMD doesn't have CPUID4. Emulate it here to report the same
    information to the user.  This makes some assumptions about the machine:
    L2 not shared, no SMT etc. that is currently true on AMD CPUs.
@@ -717,20 +715,23 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
 
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		num_cache_leaves = find_num_cache_leaves(c);
+		ci->num_leaves = find_num_cache_leaves(c);
 	} else if (c->extended_cpuid_level >= 0x80000006) {
 		if (cpuid_edx(0x80000006) & 0xf000)
-			num_cache_leaves = 4;
+			ci->num_leaves = 4;
 		else
-			num_cache_leaves = 3;
+			ci->num_leaves = 3;
 	}
 }
 
 void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
 {
-	num_cache_leaves = find_num_cache_leaves(c);
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+
+	ci->num_leaves = find_num_cache_leaves(c);
 }
 
 void init_intel_cacheinfo(struct cpuinfo_x86 *c)
@@ -740,21 +741,21 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
 	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
 	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
 	if (c->cpuid_level > 3) {
-		static int is_initialized;
-
-		if (is_initialized == 0) {
-			/* Init num_cache_leaves from boot CPU */
-			num_cache_leaves = find_num_cache_leaves(c);
-			is_initialized++;
-		}
+		/*
+		 * There should be at least one leaf. A non-zero value means
+		 * that the number of leaves has been initialized.
+		 */
+		if (!ci->num_leaves)
+			ci->num_leaves = find_num_cache_leaves(c);
 
 		/*
 		 * Whenever possible use cpuid(4), deterministic cache
 		 * parameters cpuid leaf to find the cache details
 		 */
-		for (i = 0; i < num_cache_leaves; i++) {
+		for (i = 0; i < ci->num_leaves; i++) {
 			struct _cpuid4_info_regs this_leaf = {};
 			int retval;
 
@@ -790,14 +791,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
 	 * trace cache
 	 */
-	if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) {
+	if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
 		/* supports eax=2  call */
 		int j, n;
 		unsigned int regs[4];
 		unsigned char *dp = (unsigned char *)regs;
 		int only_trace = 0;
 
-		if (num_cache_leaves != 0 && c->x86 == 15)
+		if (ci->num_leaves && c->x86 == 15)
 			only_trace = 1;
 
 		/* Number of times to iterate */
@@ -991,14 +992,12 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 int init_cache_level(unsigned int cpu)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
 
-	if (!num_cache_leaves)
+	/* There should be at least one leaf. */
+	if (!ci->num_leaves)
 		return -ENOENT;
-	if (!this_cpu_ci)
-		return -EINVAL;
-	this_cpu_ci->num_levels = 3;
-	this_cpu_ci->num_leaves = num_cache_leaves;
+
 	return 0;
 }
 

arch/x86/kernel/cpu/intel.c

@@ -555,7 +555,9 @@ static void init_intel(struct cpuinfo_x86 *c)
 	     c->x86_vfm == INTEL_WESTMERE_EX))
 		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
-	if (boot_cpu_has(X86_FEATURE_MWAIT) && c->x86_vfm == INTEL_ATOM_GOLDMONT)
+	if (boot_cpu_has(X86_FEATURE_MWAIT) &&
+	    (c->x86_vfm == INTEL_ATOM_GOLDMONT ||
+	     c->x86_vfm == INTEL_LUNARLAKE_M))
 		set_cpu_bug(c, X86_BUG_MONITOR);
 
 #ifdef CONFIG_X86_64

arch/x86/kernel/cpu/topology.c

@@ -428,8 +428,8 @@ void __init topology_apply_cmdline_limits_early(void)
 {
 	unsigned int possible = nr_cpu_ids;
 
-	/* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' 'noapic' */
-	if (!setup_max_cpus || ioapic_is_disabled || apic_is_disabled)
+	/* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */
+	if (!setup_max_cpus || apic_is_disabled)
 		possible = 1;
 
 	/* 'possible_cpus=N' */
@@ -443,7 +443,7 @@ void __init topology_apply_cmdline_limits_early(void)
 
 static __init bool restrict_to_up(void)
 {
-	if (!smp_found_config || ioapic_is_disabled)
+	if (!smp_found_config)
 		return true;
 	/*
 	 * XEN PV is special as it does not advertise the local APIC

arch/x86/kernel/fpu/signal.c

@@ -63,16 +63,6 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 	return true;
 }
 
-/*
- * Update the value of PKRU register that was already pushed onto the signal frame.
- */
-static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru)
-{
-	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
-		return 0;
-	return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
-}
-
 /*
  * Signal frame handlers.
  */
@@ -168,14 +158,8 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 
 static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
-	int err = 0;
-
-	if (use_xsave()) {
-		err = xsave_to_user_sigframe(buf);
-		if (!err)
-			err = update_pkru_in_sigframe(buf, pkru);
-		return err;
-	}
+	if (use_xsave())
+		return xsave_to_user_sigframe(buf, pkru);
 
 	if (use_fxsr())
 		return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);

arch/x86/kernel/fpu/xstate.h

@@ -69,6 +69,28 @@ static inline u64 xfeatures_mask_independent(void)
 	return fpu_kernel_cfg.independent_features;
 }
 
+/*
+ * Update the value of PKRU register that was already pushed onto the signal frame.
+ */
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru)
+{
+	u64 xstate_bv;
+	int err;
+
+	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
+		return 0;
+
+	/* Mark PKRU as in-use so that it is restored correctly. */
+	xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU;
+
+	err =  __put_user(xstate_bv, &buf->header.xfeatures);
+	if (err)
+		return err;
+
+	/* Update PKRU value in the userspace xsave buffer. */
+	return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
+}
+
 /* XSAVE/XRSTOR wrapper functions */
 
 #ifdef CONFIG_X86_64
@@ -256,7 +278,7 @@ static inline u64 xfeatures_need_sigframe_write(void)
  * The caller has to zero buf::header before calling this because XSAVE*
  * does not touch the reserved fields in the header.
  */
-static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
+static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
 	/*
 	 * Include the features which are not xsaved/rstored by the kernel
@@ -281,6 +303,9 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
 	XSTATE_OP(XSAVE, buf, lmask, hmask, err);
 	clac();
 
+	if (!err)
+		err = update_pkru_in_sigframe(buf, mask, pkru);
+
 	return err;
 }
 

arch/x86/kernel/relocate_kernel_64.S

@@ -242,6 +242,13 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	movq	CR0(%r8), %r8
 	movq	%rax, %cr3
 	movq	%r8, %cr0
+
+#ifdef CONFIG_KEXEC_JUMP
+	/* Saved in save_processor_state. */
+	movq    $saved_context, %rax
+	lgdt    saved_context_gdt_desc(%rax)
+#endif
+
 	movq	%rbp, %rax
 
 	popf

arch/x86/mm/ident_map.c

@@ -174,7 +174,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
 		if (result)
 			return result;
 
-		set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag));
+		set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
 	}
 
 	return 0;
@@ -218,14 +218,14 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		if (result)
 			return result;
 		if (pgtable_l5_enabled()) {
-			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
+			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag | _PAGE_NOPTISHADOW));
 		} else {
 			/*
 			 * With p4d folded, pgd is equal to p4d.
 			 * The pgd entry has to point to the pud page table in this case.
 			 */
 			pud_t *pud = pud_offset(p4d, 0);
-			set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag));
+			set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
 		}
 	}
 

arch/x86/mm/pti.c

@@ -132,7 +132,7 @@ pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 	 * Top-level entries added to init_mm's usermode pgd after boot
 	 * will not be automatically propagated to other mms.
 	 */
-	if (!pgdp_maps_userspace(pgdp))
+	if (!pgdp_maps_userspace(pgdp) || (pgd.pgd & _PAGE_NOPTISHADOW))
 		return pgd;
 
 	/*

drivers/base/cacheinfo.c

@@ -58,7 +58,7 @@ bool last_level_cache_is_valid(unsigned int cpu)
 {
 	struct cacheinfo *llc;
 
-	if (!cache_leaves(cpu))
+	if (!cache_leaves(cpu) || !per_cpu_cacheinfo(cpu))
 		return false;
 
 	llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1);
@@ -458,11 +458,9 @@ int __weak populate_cache_leaves(unsigned int cpu)
 	return -ENOENT;
 }
 
-static inline
-int allocate_cache_info(int cpu)
+static inline int allocate_cache_info(int cpu)
 {
-	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
-					 sizeof(struct cacheinfo), GFP_ATOMIC);
+	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu), sizeof(struct cacheinfo), GFP_ATOMIC);
 	if (!per_cpu_cacheinfo(cpu)) {
 		cache_leaves(cpu) = 0;
 		return -ENOMEM;
@@ -534,7 +532,11 @@ static inline int init_level_allocate_ci(unsigned int cpu)
 	 */
 	ci_cacheinfo(cpu)->early_ci_levels = false;
 
-	if (cache_leaves(cpu) <= early_leaves)
+	/*
+	 * Some architectures (e.g., x86) do not use early initialization.
+	 * Allocate memory now in such case.
+	 */
+	if (cache_leaves(cpu) <= early_leaves && per_cpu_cacheinfo(cpu))
 		return 0;
 
 	kfree(per_cpu_cacheinfo(cpu));