[pull] master from torvalds:master

Documentation/dev-tools/kcsan.rst

@@ -114,12 +114,6 @@ the below options are available:
   To dynamically limit for which functions to generate reports, see the
   `DebugFS interface`_ blacklist/whitelist feature.
 
-  For ``__always_inline`` functions, replace ``__always_inline`` with
-  ``__no_kcsan_or_inline`` (which implies ``__always_inline``)::
-
-    static __no_kcsan_or_inline void foo(void) {
-        ...
-
 * To disable data race detection for a particular compilation unit, add to the
   ``Makefile``::
 

arch/x86/Kconfig

@@ -67,7 +67,7 @@ config X86
 	select ARCH_HAS_FILTER_PGPROT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_KCOV			if X86_64
+	select ARCH_HAS_KCOV			if X86_64 && STACK_VALIDATION
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE

arch/x86/include/asm/bitops.h

@@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr)
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
-static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-	/*
-	 * Because this is a plain access, we need to disable KCSAN here to
-	 * avoid double instrumentation via instrumented bitops.
-	 */
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }

arch/x86/include/asm/bug.h

@@ -75,6 +75,12 @@ do {								\
 	unreachable();						\
 } while (0)
 
+/*
+ * This instrumentation_begin() is strictly speaking incorrect; but it
+ * suppresses the complaints from WARN()s in noinstr code. If such a WARN()
+ * were to trigger, we'd rather wreck the machine in an attempt to get the
+ * message out than not know about it.
+ */
 #define __WARN_FLAGS(flags)					\
 do {								\
 	instrumentation_begin();				\

arch/x86/include/asm/cpu.h

@@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip)
 	return false;
 }
 #endif
+#ifdef CONFIG_IA32_FEAT_CTL
+void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
+#else
+static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
+#endif
 #endif /* _ASM_X86_CPU_H */

arch/x86/include/asm/cpumask.h

@@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask;
 
 extern void setup_cpu_local_masks(void);
 
+/*
+ * NMI and MCE exceptions need cpu_is_offline() _really_ early,
+ * provide an arch_ special for them to avoid instrumentation.
+ */
+#if NR_CPUS > 1
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
+}
+#else
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return cpu == 0;
+}
+#endif
+
+#define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */

arch/x86/include/asm/processor.h

@@ -370,7 +370,7 @@ struct x86_hw_tss {
 #define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
 
 struct entry_stack {
-	unsigned long		words[64];
+	char	stack[PAGE_SIZE];
 };
 
 struct entry_stack_page {

arch/x86/kernel/cpu/centaur.c

@@ -3,6 +3,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/e820/api.h>
 #include <asm/mtrr.h>

arch/x86/kernel/cpu/common.c

@@ -347,6 +347,9 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+/* These bits should not change their value after CPU init is finished. */
+static const unsigned long cr4_pinned_mask =
+	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
@@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0);
 
 void native_write_cr4(unsigned long val)
 {
-	unsigned long bits_missing = 0;
+	unsigned long bits_changed = 0;
 
 set_register:
 	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
 
 	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
-			bits_missing = ~val & cr4_pinned_bits;
-			val |= bits_missing;
+		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {
+			bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits;
+			val = (val & ~cr4_pinned_mask) | cr4_pinned_bits;
 			goto set_register;
 		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
-			  bits_missing);
+		/* Warn after we've corrected the changed bits. */
+		WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n",
+			  bits_changed);
 	}
 }
 #if IS_MODULE(CONFIG_LKDTM)
@@ -419,7 +422,7 @@ void cr4_init(void)
 	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4 |= X86_CR4_PCIDE;
 	if (static_branch_likely(&cr_pinning))
-		cr4 |= cr4_pinned_bits;
+		cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;
 
 	__write_cr4(cr4);
 
@@ -434,10 +437,7 @@ void cr4_init(void)
  */
 static void __init setup_cr_pinning(void)
 {
-	unsigned long mask;
-
-	mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP);
-	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask;
+	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask;
 	static_key_enable(&cr_pinning.key);
 }
 

arch/x86/kernel/cpu/cpu.h

@@ -81,8 +81,4 @@ extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
-#ifdef CONFIG_IA32_FEAT_CTL
-void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
-#endif
-
 #endif /* ARCH_X86_CPU_H */

arch/x86/kernel/cpu/mce/core.c

@@ -1083,7 +1083,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 {
 	unsigned int cpu = smp_processor_id();
 
-	if (cpu_is_offline(cpu) ||
+	if (arch_cpu_is_offline(cpu) ||
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 

arch/x86/kernel/cpu/resctrl/core.c

@@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 
 		c->x86_cache_max_rmid  = ecx;
 		c->x86_cache_occ_scale = ebx;
-		if (c->x86_vendor == X86_VENDOR_INTEL)
-			c->x86_cache_mbm_width_offset = eax & 0xff;
-		else
-			c->x86_cache_mbm_width_offset = -1;
+		c->x86_cache_mbm_width_offset = eax & 0xff;
+
+		if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset)
+			c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD;
 	}
 }
 

arch/x86/kernel/cpu/resctrl/internal.h

@@ -37,6 +37,7 @@
 #define MBA_IS_LINEAR			0x4
 #define MBA_MAX_MBPS			U32_MAX
 #define MAX_MBA_BW_AMD			0x800
+#define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
 	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
+		_d_cdp = NULL;
 		ret = -EINVAL;
 	}
 

arch/x86/kernel/cpu/zhaoxin.c

@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 
 #include "cpu.h"

arch/x86/kernel/nmi.c

@@ -478,7 +478,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);
 
 DEFINE_IDTENTRY_RAW(exc_nmi)
 {
-	if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id()))
+	if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
 		return;
 
 	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {

arch/x86/kernel/traps.c

@@ -84,17 +84,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
 		local_irq_disable();
 }
 
-int is_valid_bugaddr(unsigned long addr)
+__always_inline int is_valid_bugaddr(unsigned long addr)
 {
-	unsigned short ud;
-
 	if (addr < TASK_SIZE_MAX)
 		return 0;
 
-	if (get_kernel_nofault(ud, (unsigned short *)addr))
-		return 0;
-
-	return ud == INSN_UD0 || ud == INSN_UD2;
+	/*
+	 * We got #UD, if the text isn't readable we'd have gotten
+	 * a different exception.
+	 */
+	return *(unsigned short *)addr == INSN_UD2;
 }
 
 static nokprobe_inline int
@@ -216,40 +215,45 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 		      ILL_ILLOPN, error_get_trap_addr(regs));
 }
 
-DEFINE_IDTENTRY_RAW(exc_invalid_op)
+static noinstr bool handle_bug(struct pt_regs *regs)
 {
-	bool rcu_exit;
+	bool handled = false;
+
+	if (!is_valid_bugaddr(regs->ip))
+		return handled;
 
 	/*
-	 * Handle BUG/WARN like NMIs instead of like normal idtentries:
-	 * if we bugged/warned in a bad RCU context, for example, the last
-	 * thing we want is to BUG/WARN again in the idtentry code, ad
-	 * infinitum.
+	 * All lies, just get the WARN/BUG out.
 	 */
-	if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) {
-		enum bug_trap_type type;
+	instrumentation_begin();
+	/*
+	 * Since we're emulating a CALL with exceptions, restore the interrupt
+	 * state to what it was at the exception site.
+	 */
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_enable();
+	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+		regs->ip += LEN_UD2;
+		handled = true;
+	}
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_disable();
+	instrumentation_end();
 
-		nmi_enter();
-		instrumentation_begin();
-		trace_hardirqs_off_finish();
-		type = report_bug(regs->ip, regs);
-		if (regs->flags & X86_EFLAGS_IF)
-			trace_hardirqs_on_prepare();
-		instrumentation_end();
-		nmi_exit();
+	return handled;
+}
 
-		if (type == BUG_TRAP_TYPE_WARN) {
-			/* Skip the ud2. */
-			regs->ip += LEN_UD2;
-			return;
-		}
+DEFINE_IDTENTRY_RAW(exc_invalid_op)
+{
+	bool rcu_exit;
 
-		/*
-		 * Else, if this was a BUG and report_bug returns or if this
-		 * was just a normal #UD, we want to continue onward and
-		 * crash.
-		 */
-	}
+	/*
+	 * We use UD2 as a short encoding for 'CALL __WARN', as such
+	 * handle it before exception entry to avoid recursive WARN
+	 * in case exception entry is the one triggering WARNs.
+	 */
+	if (!user_mode(regs) && handle_bug(regs))
+		return;
 
 	rcu_exit = idtentry_enter_cond_rcu(regs);
 	instrumentation_begin();
@@ -691,13 +695,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 		(struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the temporary storage. */
-	memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
 
 	/* Update the entry stack */
-	memcpy(new_stack, &tmp, sizeof(tmp));
+	__memcpy(new_stack, &tmp, sizeof(tmp));
 
 	BUG_ON(!user_mode(&new_stack->regs));
 	return new_stack;

arch/x86/lib/memcpy_64.S

@@ -8,6 +8,8 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
+.pushsection .noinstr.text, "ax"
+
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
  * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
@@ -184,6 +186,8 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	retq
 SYM_FUNC_END(memcpy_orig)
 
+.popsection
+
 #ifndef CONFIG_UML
 
 MCSAFE_TEST_CTL

arch/x86/lib/usercopy_64.c

@@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 	asm volatile(
 		"	testq  %[size8],%[size8]\n"
 		"	jz     4f\n"
+		"	.align 16\n"
 		"0:	movq $0,(%[dst])\n"
 		"	addq   $8,%[dst]\n"
 		"	decl %%ecx ; jnz   0b\n"

arch/x86/power/cpu.c

@@ -193,6 +193,8 @@ static void fix_processor_context(void)
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
+	struct cpuinfo_x86 *c;
+
 	if (ctxt->misc_enable_saved)
 		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
 	/*
@@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	mtrr_bp_restore();
 	perf_restore_debug_store();
 	msr_restore_context(ctxt);
+
+	c = &cpu_data(smp_processor_id());
+	if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL))
+		init_ia32_feat_ctl(c);
 }
 
 /* Needed by apm.c */