Merge tag 'x86_urgent_for_v5.11_rc7' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:
 "I hope this is the last batch of x86/urgent updates for this round:

   - Remove superfluous EFI PGD range checks which lead to those
     assertions failing with certain kernel configs and LLVM.

   - Disable setting breakpoints on facilities involved in #DB exception
     handling to avoid infinite loops.

   - Add extra serialization to non-serializing MSRs (IA32_TSC_DEADLINE
     and x2 APIC MSRs) to adhere to SDM's recommendation and avoid any
     theoretical issues.

   - Re-add the EPB MSR reading on turbostat so that it works on older
     kernels which don't have the corresponding EPB sysfs file.

   - Add Alder Lake to the list of CPUs which support split lock.

   - Fix %dr6 register handling in order to be able to set watchpoints
     with gdb again.

   - Disable CET instrumentation in the kernel so that gcc doesn't add
     ENDBR64 to kernel code and thus confuse tracing"

* tag 'x86_urgent_for_v5.11_rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/efi: Remove EFI PGD build time checks
  x86/debug: Prevent data breakpoints on cpu_dr7
  x86/debug: Prevent data breakpoints on __per_cpu_offset
  x86/apic: Add extra serialization for non-serializing MSRs
  tools/power/turbostat: Fallback to an MSR read for EPB
  x86/split_lock: Enable the split lock feature on another Alder Lake CPU
  x86/debug: Fix DR6 handling
  x86/build: Disable CET instrumentation in the kernel

Makefile

@@ -949,12 +949,6 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=designated-init)
 # change __FILE__ to the relative path from the srctree
 KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 
-# ensure -fcf-protection is disabled when using retpoline as it is
-# incompatible with -mindirect-branch=thunk-extern
-ifdef CONFIG_RETPOLINE
-KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
-endif
-
 # include additional Makefiles when needed
 include-y			:= scripts/Makefile.extrawarn
 include-$(CONFIG_KASAN)		+= scripts/Makefile.kasan

arch/x86/Makefile

@@ -120,6 +120,9 @@ else
 
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel
+
+	# Intel CET isn't enabled in the kernel
+	KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
 endif
 
 ifdef CONFIG_X86_X32

arch/x86/include/asm/apic.h

@@ -197,16 +197,6 @@ static inline bool apic_needs_pit(void) { return true; }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_X2APIC
-/*
- * Make previous memory operations globally visible before
- * sending the IPI through x2apic wrmsr. We need a serializing instruction or
- * mfence for this.
- */
-static inline void x2apic_wrmsr_fence(void)
-{
-	asm volatile("mfence" : : : "memory");
-}
-
 static inline void native_apic_msr_write(u32 reg, u32 v)
 {
 	if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||

arch/x86/include/asm/barrier.h

@@ -84,4 +84,22 @@ do {									\
 
 #include <asm-generic/barrier.h>
 
+/*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions.  WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE.  The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier.  This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+static inline void weak_wrmsr_fence(void)
+{
+	asm volatile("mfence; lfence" : : : "memory");
+}
+
 #endif /* _ASM_X86_BARRIER_H */

arch/x86/kernel/apic/apic.c

@@ -41,6 +41,7 @@
 #include <asm/perf_event.h>
 #include <asm/x86_init.h>
 #include <linux/atomic.h>
+#include <asm/barrier.h>
 #include <asm/mpspec.h>
 #include <asm/i8259.h>
 #include <asm/proto.h>
@@ -477,6 +478,9 @@ static int lapic_next_deadline(unsigned long delta,
 {
 	u64 tsc;
 
+	/* This MSR is special and need a special fence: */
+	weak_wrmsr_fence();
+
 	tsc = rdtsc();
 	wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
 	return 0;

arch/x86/kernel/apic/x2apic_cluster.c

@@ -29,7 +29,8 @@ static void x2apic_send_IPI(int cpu, int vector)
 {
 	u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	__x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL);
 }
 
@@ -41,7 +42,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	unsigned long flags;
 	u32 dest;
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	local_irq_save(flags);
 
 	tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask);

arch/x86/kernel/apic/x2apic_phys.c

@@ -43,7 +43,8 @@ static void x2apic_send_IPI(int cpu, int vector)
 {
 	u32 dest = per_cpu(x86_cpu_to_apicid, cpu);
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	__x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL);
 }
 
@@ -54,7 +55,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	unsigned long this_cpu;
 	unsigned long flags;
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 
 	local_irq_save(flags);
 
@@ -125,7 +127,8 @@ void __x2apic_send_IPI_shorthand(int vector, u32 which)
 {
 	unsigned long cfg = __prepare_ICR(which, vector, 0);
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	native_x2apic_icr_write(cfg, 0);
 }
 

arch/x86/kernel/cpu/intel.c

@@ -1159,6 +1159,7 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		1),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	1),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		1),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		1),
 	{}
 };
 

arch/x86/kernel/hw_breakpoint.c

@@ -269,6 +269,20 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end)
 			CPU_ENTRY_AREA_TOTAL_SIZE))
 		return true;
 
+	/*
+	 * When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU
+	 * GSBASE value via __per_cpu_offset or pcpu_unit_offsets.
+	 */
+#ifdef CONFIG_SMP
+	if (within_area(addr, end, (unsigned long)__per_cpu_offset,
+			sizeof(unsigned long) * nr_cpu_ids))
+		return true;
+#else
+	if (within_area(addr, end, (unsigned long)&pcpu_unit_offsets,
+			sizeof(pcpu_unit_offsets)))
+		return true;
+#endif
+
 	for_each_possible_cpu(cpu) {
 		/* The original rw GDT is being used after load_direct_gdt() */
 		if (within_area(addr, end, (unsigned long)get_cpu_gdt_rw(cpu),
@@ -293,6 +307,14 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end)
 				(unsigned long)&per_cpu(cpu_tlbstate, cpu),
 				sizeof(struct tlb_state)))
 			return true;
+
+		/*
+		 * When in guest (X86_FEATURE_HYPERVISOR), local_db_save()
+		 * will read per-cpu cpu_dr7 before clear dr7 register.
+		 */
+		if (within_area(addr, end, (unsigned long)&per_cpu(cpu_dr7, cpu),
+				sizeof(cpu_dr7)))
+			return true;
 	}
 
 	return false;
@@ -491,15 +513,12 @@ static int hw_breakpoint_handler(struct die_args *args)
 	struct perf_event *bp;
 	unsigned long *dr6_p;
 	unsigned long dr6;
+	bool bpx;
 
 	/* The DR6 value is pointed by args->err */
 	dr6_p = (unsigned long *)ERR_PTR(args->err);
 	dr6 = *dr6_p;
 
-	/* If it's a single step, TRAP bits are random */
-	if (dr6 & DR_STEP)
-		return NOTIFY_DONE;
-
 	/* Do an early return if no trap bits are set in DR6 */
 	if ((dr6 & DR_TRAP_BITS) == 0)
 		return NOTIFY_DONE;
@@ -509,40 +528,40 @@ static int hw_breakpoint_handler(struct die_args *args)
 		if (likely(!(dr6 & (DR_TRAP0 << i))))
 			continue;
 
+		bp = this_cpu_read(bp_per_reg[i]);
+		if (!bp)
+			continue;
+
+		bpx = bp->hw.info.type == X86_BREAKPOINT_EXECUTE;
+
 		/*
-		 * The counter may be concurrently released but that can only
-		 * occur from a call_rcu() path. We can then safely fetch
-		 * the breakpoint, use its callback, touch its counter
-		 * while we are in an rcu_read_lock() path.
+		 * TF and data breakpoints are traps and can be merged, however
+		 * instruction breakpoints are faults and will be raised
+		 * separately.
+		 *
+		 * However DR6 can indicate both TF and instruction
+		 * breakpoints. In that case take TF as that has precedence and
+		 * delay the instruction breakpoint for the next exception.
 		 */
-		rcu_read_lock();
+		if (bpx && (dr6 & DR_STEP))
+			continue;
 
-		bp = this_cpu_read(bp_per_reg[i]);
 		/*
 		 * Reset the 'i'th TRAP bit in dr6 to denote completion of
 		 * exception handling
 		 */
 		(*dr6_p) &= ~(DR_TRAP0 << i);
-		/*
-		 * bp can be NULL due to lazy debug register switching
-		 * or due to concurrent perf counter removing.
-		 */
-		if (!bp) {
-			rcu_read_unlock();
-			break;
-		}
 
 		perf_bp_event(bp, args->regs);
 
 		/*
 		 * Set up resume flag to avoid breakpoint recursion when
 		 * returning back to origin.
 		 */
-		if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE)
+		if (bpx)
 			args->regs->flags |= X86_EFLAGS_RF;
-
-		rcu_read_unlock();
 	}
+
 	/*
 	 * Further processing in do_debug() is needed for a) user-space
 	 * breakpoints (to generate signals) and b) when the system has

arch/x86/platform/efi/efi_64.c

@@ -115,31 +115,12 @@ void efi_sync_low_kernel_mappings(void)
 	pud_t *pud_k, *pud_efi;
 	pgd_t *efi_pgd = efi_mm.pgd;
 
-	/*
-	 * We can share all PGD entries apart from the one entry that
-	 * covers the EFI runtime mapping space.
-	 *
-	 * Make sure the EFI runtime region mappings are guaranteed to
-	 * only span a single PGD entry and that the entry also maps
-	 * other important kernel regions.
-	 */
-	MAYBE_BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END));
-	MAYBE_BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) !=
-			(EFI_VA_END & PGDIR_MASK));
-
 	pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET);
 	pgd_k = pgd_offset_k(PAGE_OFFSET);
 
 	num_entries = pgd_index(EFI_VA_END) - pgd_index(PAGE_OFFSET);
 	memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries);
 
-	/*
-	 * As with PGDs, we share all P4D entries apart from the one entry
-	 * that covers the EFI runtime mapping space.
-	 */
-	BUILD_BUG_ON(p4d_index(EFI_VA_END) != p4d_index(MODULES_END));
-	BUILD_BUG_ON((EFI_VA_START & P4D_MASK) != (EFI_VA_END & P4D_MASK));
-
 	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
 	pgd_k = pgd_offset_k(EFI_VA_END);
 	p4d_efi = p4d_offset(pgd_efi, 0);

tools/power/x86/turbostat/turbostat.c

@@ -1834,12 +1834,15 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
 int get_epb(int cpu)
 {
 	char path[128 + PATH_BYTES];
+	unsigned long long msr;
 	int ret, epb = -1;
 	FILE *fp;
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/power/energy_perf_bias", cpu);
 
-	fp = fopen_or_die(path, "r");
+	fp = fopen(path, "r");
+	if (!fp)
+		goto msr_fallback;
 
 	ret = fscanf(fp, "%d", &epb);
 	if (ret != 1)
@@ -1848,6 +1851,11 @@ int get_epb(int cpu)
 	fclose(fp);
 
 	return epb;
+
+msr_fallback:
+	get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr);
+
+	return msr & 0xf;
 }
 
 void get_apic_id(struct thread_data *t)