Merge 'x86/cpu' to pick up dependent bits

Pick up work happening in parallel to avoid nasty merge conflicts later.

Signed-off-by: Borislav Petkov <bp@suse.de>

arch/x86/include/asm/cpufeatures.h

@@ -368,6 +368,7 @@
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
+#define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */

arch/x86/include/asm/fpu/internal.h

@@ -602,9 +602,7 @@ static inline u64 xgetbv(u32 index)
 {
 	u32 eax, edx;
 
-	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
-		     : "=a" (eax), "=d" (edx)
-		     : "c" (index));
+	asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index));
 	return eax + ((u64)edx << 32);
 }
 
@@ -613,8 +611,7 @@ static inline void xsetbv(u32 index, u64 value)
 	u32 eax = value;
 	u32 edx = value >> 32;
 
-	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
-		     : : "a" (eax), "d" (edx), "c" (index));
+	asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
 }
 
 #endif /* _ASM_X86_FPU_INTERNAL_H */

arch/x86/include/asm/special_insns.h

@@ -234,6 +234,12 @@ static inline void clwb(volatile void *__p)
 
 #define nop() asm volatile ("nop")
 
+static inline void serialize(void)
+{
+	/* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */
+	asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory");
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */

arch/x86/include/asm/sync_core.h

@@ -5,6 +5,7 @@
 #include <linux/preempt.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_X86_32
 static inline void iret_to_self(void)
@@ -46,22 +47,34 @@ static inline void iret_to_self(void)
  *
  *  b) Text was modified on a different CPU, may subsequently be
  *     executed on this CPU, and you want to make sure the new version
- *     gets executed.  This generally means you're calling this in a IPI.
+ *     gets executed.  This generally means you're calling this in an IPI.
  *
  * If you're calling this for a different reason, you're probably doing
  * it wrong.
+ *
+ * Like all of Linux's memory ordering operations, this is a
+ * compiler barrier as well.
  */
 static inline void sync_core(void)
 {
 	/*
-	 * There are quite a few ways to do this.  IRET-to-self is nice
-	 * because it works on every CPU, at any CPL (so it's compatible
-	 * with paravirtualization), and it never exits to a hypervisor.
-	 * The only down sides are that it's a bit slow (it seems to be
-	 * a bit more than 2x slower than the fastest options) and that
-	 * it unmasks NMIs.  The "push %cs" is needed because, in
-	 * paravirtual environments, __KERNEL_CS may not be a valid CS
-	 * value when we do IRET directly.
+	 * The SERIALIZE instruction is the most straightforward way to
+	 * do this, but it is not universally available.
+	 */
+	if (static_cpu_has(X86_FEATURE_SERIALIZE)) {
+		serialize();
+		return;
+	}
+
+	/*
+	 * For all other processors, there are quite a few ways to do this.
+	 * IRET-to-self is nice because it works on every CPU, at any CPL
+	 * (so it's compatible with paravirtualization), and it never exits
+	 * to a hypervisor.  The only downsides are that it's a bit slow
+	 * (it seems to be a bit more than 2x slower than the fastest
+	 * options) and that it unmasks NMIs.  The "push %cs" is needed,
+	 * because in paravirtual environments __KERNEL_CS may not be a
+	 * valid CS value when we do IRET directly.
 	 *
 	 * In case NMI unmasking or performance ever becomes a problem,
 	 * the next best option appears to be MOV-to-CR2 and an
@@ -71,9 +84,6 @@ static inline void sync_core(void)
 	 * CPUID is the conventional way, but it's nasty: it doesn't
 	 * exist on some 486-like CPUs, and it usually exits to a
 	 * hypervisor.
-	 *
-	 * Like all of Linux's memory ordering operations, this is a
-	 * compiler barrier as well.
 	 */
 	iret_to_self();
 }

arch/x86/kernel/umip.c

@@ -45,11 +45,12 @@
  * value that, lies close to the top of the kernel memory. The limit for the GDT
  * and the IDT are set to zero.
  *
- * Given that SLDT and STR are not commonly used in programs that run on WineHQ
- * or DOSEMU2, they are not emulated.
- *
- * The instruction smsw is emulated to return the value that the register CR0
+ * The instruction SMSW is emulated to return the value that the register CR0
  * has at boot time as set in the head_32.
+ * SLDT and STR are emulated to return the values that the kernel programmatically
+ * assigns:
+ * - SLDT returns (GDT_ENTRY_LDT * 8) if an LDT has been set, 0 if not.
+ * - STR returns (GDT_ENTRY_TSS * 8).
  *
  * Emulation is provided for both 32-bit and 64-bit processes.
  *
@@ -244,16 +245,34 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
 		*data_size += UMIP_GDT_IDT_LIMIT_SIZE;
 		memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE);
 
-	} else if (umip_inst == UMIP_INST_SMSW) {
-		unsigned long dummy_value = CR0_STATE;
+	} else if (umip_inst == UMIP_INST_SMSW || umip_inst == UMIP_INST_SLDT ||
+		   umip_inst == UMIP_INST_STR) {
+		unsigned long dummy_value;
+
+		if (umip_inst == UMIP_INST_SMSW) {
+			dummy_value = CR0_STATE;
+		} else if (umip_inst == UMIP_INST_STR) {
+			dummy_value = GDT_ENTRY_TSS * 8;
+		} else if (umip_inst == UMIP_INST_SLDT) {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+			down_read(&current->mm->context.ldt_usr_sem);
+			if (current->mm->context.ldt)
+				dummy_value = GDT_ENTRY_LDT * 8;
+			else
+				dummy_value = 0;
+			up_read(&current->mm->context.ldt_usr_sem);
+#else
+			dummy_value = 0;
+#endif
+		}
 
 		/*
-		 * Even though the CR0 register has 4 bytes, the number
+		 * For these 3 instructions, the number
 		 * of bytes to be copied in the result buffer is determined
 		 * by whether the operand is a register or a memory location.
 		 * If operand is a register, return as many bytes as the operand
 		 * size. If operand is memory, return only the two least
-		 * siginificant bytes of CR0.
+		 * siginificant bytes.
 		 */
 		if (X86_MODRM_MOD(insn->modrm.value) == 3)
 			*data_size = insn->opnd_bytes;
@@ -261,7 +280,6 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
 			*data_size = 2;
 
 		memcpy(data, &dummy_value, *data_size);
-	/* STR and SLDT  are not emulated */
 	} else {
 		return -EINVAL;
 	}
@@ -383,10 +401,6 @@ bool fixup_umip_exception(struct pt_regs *regs)
 	umip_pr_warn(regs, "%s instruction cannot be used by applications.\n",
 			umip_insns[umip_inst]);
 
-	/* Do not emulate (spoof) SLDT or STR. */
-	if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT)
-		return false;
-
 	umip_pr_warn(regs, "For now, expensive software emulation returns the result.\n");
 
 	if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size,

arch/x86/kvm/cpuid.c

@@ -371,7 +371,7 @@ void kvm_set_cpu_caps(void)
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
 		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
 		F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) |
-		F(SERIALIZE)
+		F(SERIALIZE) | F(TSXLDTRK)
 	);
 
 	/* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */