Merge tag 'x86_urgent_for_v6.16_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Make sure DR6 and DR7 are initialized to their architectural values
   and not accidentally cleared, leading to misconfigurations

* tag 'x86_urgent_for_v6.16_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/traps: Initialize DR7 by writing its architectural reset value
  x86/traps: Initialize DR6 by writing its architectural reset value

Author: torvalds

arch/x86/include/asm/debugreg.h

@@ -9,6 +9,14 @@
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
 
+/*
+ * Define bits that are always set to 1 in DR7, only bit 10 is
+ * architecturally reserved to '1'.
+ *
+ * This is also the init/reset value for DR7.
+ */
+#define DR7_FIXED_1	0x00000400
+
 DECLARE_PER_CPU(unsigned long, cpu_dr7);
 
 #ifndef CONFIG_PARAVIRT_XXL
@@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
 
 static inline void hw_breakpoint_disable(void)
 {
-	/* Zero the control register for HW Breakpoint */
-	set_debugreg(0UL, 7);
+	/* Reset the control register for HW Breakpoint */
+	set_debugreg(DR7_FIXED_1, 7);
 
 	/* Zero-out the individual HW breakpoint address registers */
 	set_debugreg(0UL, 0);
@@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void)
 		return 0;
 
 	get_debugreg(dr7, 7);
-	dr7 &= ~0x400; /* architecturally set bit */
+
+	/* Architecturally set bit */
+	dr7 &= ~DR7_FIXED_1;
 	if (dr7)
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
+
 	/*
 	 * Ensure the compiler doesn't lower the above statements into
 	 * the critical section; disabling breakpoints late would not

arch/x86/include/asm/kvm_host.h

@@ -31,6 +31,7 @@
 
 #include <asm/apic.h>
 #include <asm/pvclock-abi.h>
+#include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
@@ -249,7 +250,6 @@ enum x86_intercept_stage;
 #define DR7_BP_EN_MASK	0x000000ff
 #define DR7_GE		(1 << 9)
 #define DR7_GD		(1 << 13)
-#define DR7_FIXED_1	0x00000400
 #define DR7_VOLATILE	0xffff2bff
 
 #define KVM_GUESTDBG_VALID_MASK \

arch/x86/include/uapi/asm/debugreg.h

@@ -15,7 +15,26 @@
    which debugging register was responsible for the trap.  The other bits
    are either reserved or not of interest to us. */
 
-/* Define reserved bits in DR6 which are always set to 1 */
+/*
+ * Define bits in DR6 which are set to 1 by default.
+ *
+ * This is also the DR6 architectural value following Power-up, Reset or INIT.
+ *
+ * Note, with the introduction of Bus Lock Detection (BLD) and Restricted
+ * Transactional Memory (RTM), the DR6 register has been modified:
+ *
+ * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports
+ *    Bus Lock Detection.  The assertion of a bus lock could clear it.
+ *
+ * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports
+ *    restricted transactional memory.  #DB occurred inside an RTM region
+ *    could clear it.
+ *
+ * Apparently, DR6.BLD and DR6.RTM are active low bits.
+ *
+ * As a result, DR6_RESERVED is an incorrect name now, but it is kept for
+ * compatibility.
+ */
 #define DR6_RESERVED	(0xFFFF0FF0)
 
 #define DR_TRAP0	(0x1)		/* db0 */

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();

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;

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",

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",

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 @@ static noinstr void exc_debug_user(struct pt_regs *regs, unsigned long dr6)
 /* 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);

arch/x86/kvm/x86.c

@@ -11035,7 +11035,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	if (unlikely(vcpu->arch.switch_db_regs &&
 		     !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) {
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
 		set_debugreg(vcpu->arch.eff_db[1], 1);
 		set_debugreg(vcpu->arch.eff_db[2], 2);
@@ -11044,7 +11044,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
 			kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
 	} else if (unlikely(hw_breakpoint_active())) {
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
 	}
 
 	vcpu->arch.host_debugctl = get_debugctlmsr();