12 files changed, 134 insertions, 105 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ecfe7b497cad..ea1d984166cd 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -116,6 +116,24 @@ static struct module *its_mod;
 #endif
 static void *its_page;
 static unsigned int its_offset;
+struct its_array its_pages;
+
+static void *__its_alloc(struct its_array *pages)
+{
+	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+	if (!page)
+		return NULL;
+
+	void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *),
+			     GFP_KERNEL);
+	if (!tmp)
+		return NULL;
+
+	pages->pages = tmp;
+	pages->pages[pages->num++] = page;
+
+	return no_free_ptr(page);
+}
 
 /* Initialize a thunk with the "jmp *reg; int3" instructions. */
 static void *its_init_thunk(void *thunk, int reg)
@@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg)
 	return thunk + offset;
 }
 
+static void its_pages_protect(struct its_array *pages)
+{
+	for (int i = 0; i < pages->num; i++) {
+		void *page = pages->pages[i];
+		execmem_restore_rox(page, PAGE_SIZE);
+	}
+}
+
+static void its_fini_core(void)
+{
+	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+		its_pages_protect(&its_pages);
+	kfree(its_pages.pages);
+}
+
 #ifdef CONFIG_MODULES
 void its_init_mod(struct module *mod)
 {
@@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod)
 	its_page = NULL;
 	mutex_unlock(&text_mutex);
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
-		execmem_restore_rox(page, PAGE_SIZE);
-	}
+	if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		its_pages_protect(&mod->arch.its_pages);
 }
 
 void its_free_mod(struct module *mod)
@@ -184,37 +215,33 @@ void its_free_mod(struct module *mod)
 	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
 		return;
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
+	for (int i = 0; i < mod->arch.its_pages.num; i++) {
+		void *page = mod->arch.its_pages.pages[i];
 		execmem_free(page);
 	}
-	kfree(mod->its_page_array);
+	kfree(mod->arch.its_pages.pages);
 }
 #endif /* CONFIG_MODULES */
 
 static void *its_alloc(void)
 {
-	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
-
-	if (!page)
-		return NULL;
+	struct its_array *pages = &its_pages;
+	void *page;
 
 #ifdef CONFIG_MODULES
-	if (its_mod) {
-		void *tmp = krealloc(its_mod->its_page_array,
-				     (its_mod->its_num_pages+1) * sizeof(void *),
-				     GFP_KERNEL);
-		if (!tmp)
-			return NULL;
+	if (its_mod)
+		pages = &its_mod->arch.its_pages;
+#endif
 
-		its_mod->its_page_array = tmp;
-		its_mod->its_page_array[its_mod->its_num_pages++] = page;
+	page = __its_alloc(pages);
+	if (!page)
+		return NULL;
 
-		execmem_make_temp_rw(page, PAGE_SIZE);
-	}
-#endif /* CONFIG_MODULES */
+	execmem_make_temp_rw(page, PAGE_SIZE);
+	if (pages == &its_pages)
+		set_memory_x((unsigned long)page, 1);
 
-	return no_free_ptr(page);
+	return page;
 }
 
 static void *its_allocate_thunk(int reg)
@@ -268,7 +295,9 @@ u8 *its_static_thunk(int reg)
 	return thunk;
 }
 
-#endif
+#else
+static inline void its_fini_core(void) {}
+#endif /* CONFIG_MITIGATION_ITS */
 
 /*
  * Nomenclature for variable names to simplify and clarify this code and ease
@@ -2338,6 +2367,8 @@ void __init alternative_instructions(void)
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
 	apply_returns(__return_sites, __return_sites_end);
 
+	its_fini_core();
+
 	/*
 	 * Adjust all CALL instructions to point to func()-10, including
 	 * those in .altinstr_replacement.
@@ -3107,6 +3138,6 @@ void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, c
  */
 void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate)
 {
-	__smp_text_poke_batch_add(addr, opcode, len, emulate);
+	smp_text_poke_batch_add(addr, opcode, len, emulate);
 	smp_text_poke_batch_finish();
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..b2ad8d13211a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -31,7 +31,7 @@
 
 #include "cpu.h"
 
-u16 invlpgb_count_max __ro_after_init;
+u16 invlpgb_count_max __ro_after_init = 1;
 
 static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
 {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8feb8fd2957a..27125e009847 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2243,20 +2243,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
 
-/*
- * Clear all 6 debug registers:
- */
-static void clear_all_debug_regs(void)
+static void initialize_debug_regs(void)
 {
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		/* Ignore db4, db5 */
-		if ((i == 4) || (i == 5))
-			continue;
-
-		set_debugreg(0, i);
-	}
+	/* Control register first -- to make sure everything is disabled. */
+	set_debugreg(DR7_FIXED_1, 7);
+	set_debugreg(DR6_RESERVED, 6);
+	/* dr5 and dr4 don't exist */
+	set_debugreg(0, 3);
+	set_debugreg(0, 2);
+	set_debugreg(0, 1);
+	set_debugreg(0, 0);
 }
 
 #ifdef CONFIG_KGDB
@@ -2417,7 +2413,7 @@ void cpu_init(void)
 
 	load_mm_ldt(&init_mm);
 
-	clear_all_debug_regs();
+	initialize_debug_regs();
 	dbg_restore_debug_regs();
 
 	doublefault_init_cpu_tss();
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 7109cbfcad4f..187d527ef73b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	struct rdt_hw_mon_domain *hw_dom;
 	struct rdt_domain_hdr *hdr;
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	int err;
 
 	lockdep_assert_held(&domain_list_lock);
@@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
-	d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!d->ci) {
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
 		mon_domain_free(hw_dom);
 		return;
 	}
+	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	arch_mon_domain_online(r, d);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 102641fd2172..8b1a9733d13e 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs)
 	struct perf_event *bp;
 
 	/* Disable hardware debugging while we are in kgdb: */
-	set_debugreg(0UL, 7);
+	set_debugreg(DR7_FIXED_1, 7);
 	for (i = 0; i < HBP_NUM; i++) {
 		if (!breakinfo[i].enabled)
 			continue;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a10e180cbf23..3ef15c2f152f 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 
 	/* Only print out debug registers if they are in their non-default state. */
 	if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
-	    (d6 == DR6_RESERVED) && (d7 == 0x400))
+	    (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))
 		return;
 
 	printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8d6cf25127aa..b972bf72fb8b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -133,7 +133,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 
 	/* Only print out debug registers if they are in their non-default state. */
 	if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
-	    (d6 == DR6_RESERVED) && (d7 == 0x400))) {
+	    (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) {
 		printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n",
 		       log_lvl, d0, d1, d2);
 		printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n",
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 98123ff10506..42bbc42bd350 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -152,6 +152,8 @@ SYSCALL32_DEFINE0(sigreturn)
 	struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
 	sigset_t set;
 
+	prevent_single_step_upon_eretu(regs);
+
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
 	if (__get_user(set.sig[0], &frame->sc.oldmask)
@@ -175,6 +177,8 @@ SYSCALL32_DEFINE0(rt_sigreturn)
 	struct rt_sigframe_ia32 __user *frame;
 	sigset_t set;
 
+	prevent_single_step_upon_eretu(regs);
+
 	frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
 
 	if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index ee9453891901..d483b585c6c6 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -250,6 +250,8 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	sigset_t set;
 	unsigned long uc_flags;
 
+	prevent_single_step_upon_eretu(regs);
+
 	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
@@ -366,6 +368,8 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
 	sigset_t set;
 	unsigned long uc_flags;
 
+	prevent_single_step_upon_eretu(regs);
+
 	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 
 	if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 18266cc3d98c..b014e6d229f9 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -299,3 +299,27 @@ struct smp_ops smp_ops = {
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+	enum cpuhp_smt_control old = cpu_smt_control;
+	int ret;
+
+	/*
+	 * If SMT has been disabled and SMT siblings are in HLT, bring them back
+	 * online and offline them again so that they end up in MWAIT proper.
+	 *
+	 * Called with hotplug enabled.
+	 */
+	if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+		return 0;
+
+	ret = cpuhp_smt_enable();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_smt_disable(old);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fc78c2325fd2..58ede3fa6a75 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1244,6 +1244,10 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
 void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
@@ -1290,50 +1294,6 @@ void __noreturn mwait_play_dead(unsigned int eax_hint)
 }
 
 /*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead_cpuid_hint(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
-
-	mwait_play_dead(eax);
-}
-
-/*
  * Kick all "offline" CPUs out of mwait on kexec(). See comment in
  * mwait_play_dead().
  */
@@ -1383,9 +1343,9 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead_cpuid_hint();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c5c897a86418..36354b470590 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1022,24 +1022,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs)
 #endif
 }
 
-static __always_inline unsigned long debug_read_clear_dr6(void)
+static __always_inline unsigned long debug_read_reset_dr6(void)
 {
 	unsigned long dr6;
 
+	get_debugreg(dr6, 6);
+	dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
+
 	/*
 	 * The Intel SDM says:
 	 *
-	 *   Certain debug exceptions may clear bits 0-3. The remaining
-	 *   contents of the DR6 register are never cleared by the
-	 *   processor. To avoid confusion in identifying debug
-	 *   exceptions, debug handlers should clear the register before
-	 *   returning to the interrupted task.
+	 *   Certain debug exceptions may clear bits 0-3 of DR6.
+	 *
+	 *   BLD induced #DB clears DR6.BLD and any other debug
+	 *   exception doesn't modify DR6.BLD.
 	 *
-	 * Keep it simple: clear DR6 immediately.
+	 *   RTM induced #DB clears DR6.RTM and any other debug
+	 *   exception sets DR6.RTM.
+	 *
+	 *   To avoid confusion in identifying debug exceptions,
+	 *   debug handlers should set DR6.BLD and DR6.RTM, and
+	 *   clear other DR6 bits before returning.
+	 *
+	 * Keep it simple: write DR6 with its architectural reset
+	 * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately.
 	 */
-	get_debugreg(dr6, 6);
 	set_debugreg(DR6_RESERVED, 6);
-	dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
 
 	return dr6;
 }
@@ -1239,13 +1247,13 @@ out:
 /* IST stack entry */
 DEFINE_IDTENTRY_DEBUG(exc_debug)
 {
-	exc_debug_kernel(regs, debug_read_clear_dr6());
+	exc_debug_kernel(regs, debug_read_reset_dr6());
 }
 
 /* User entry, runs on regular task stack */
 DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
-	exc_debug_user(regs, debug_read_clear_dr6());
+	exc_debug_user(regs, debug_read_reset_dr6());
 }
 
 #ifdef CONFIG_X86_FRED
@@ -1264,7 +1272,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
 {
 	/*
 	 * FRED #DB stores DR6 on the stack in the format which
-	 * debug_read_clear_dr6() returns for the IDT entry points.
+	 * debug_read_reset_dr6() returns for the IDT entry points.
 	 */
 	unsigned long dr6 = fred_event_data(regs);
 
@@ -1279,7 +1287,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
 {
-	unsigned long dr6 = debug_read_clear_dr6();
+	unsigned long dr6 = debug_read_reset_dr6();
 
 	if (user_mode(regs))
 		exc_debug_user(regs, dr6);