Merge tag 'x86-cleanups-2024-01-08' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull x86 cleanups from Ingo Molnar:

 - Change global variables to local

 - Add missing kernel-doc function parameter descriptions

 - Remove unused parameter from a macro

 - Remove obsolete Kconfig entry

 - Fix comments

 - Fix typos, mostly scripted, manually reviewed

and a micro-optimization got misplaced as a cleanup:

 - Micro-optimize the asm code in secondary_startup_64_no_verify()

* tag 'x86-cleanups-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  arch/x86: Fix typos
  x86/head_64: Use TESTB instead of TESTL in secondary_startup_64_no_verify()
  x86/docs: Remove reference to syscall trampoline in PTI
  x86/Kconfig: Remove obsolete config X86_32_SMP
  x86/io: Remove the unused 'bw' parameter from the BUILDIO() macro
  x86/mtrr: Document missing function parameters in kernel-doc
  x86/setup: Make relocated_ramdisk a local variable of relocate_initrd()

Documentation/arch/x86/pti.rst

@@ -81,11 +81,9 @@ this protection comes at a cost:
      and exit (it can be skipped when the kernel is interrupted,
      though.)  Moves to CR3 are on the order of a hundred
      cycles, and are required at every entry and exit.
-  b. A "trampoline" must be used for SYSCALL entry.  This
-     trampoline depends on a smaller set of resources than the
-     non-PTI SYSCALL entry code, so requires mapping fewer
-     things into the userspace page tables.  The downside is
-     that stacks must be switched at entry time.
+  b. Percpu TSS is mapped into the user page tables to allow SYSCALL64 path
+     to work under PTI. This doesn't have a direct runtime cost but it can
+     be argued it opens certain timing attack scenarios.
   c. Global pages are disabled for all kernel structures not
      mapped into both kernel and userspace page tables.  This
      feature of the MMU allows different processes to share TLB
@@ -167,7 +165,7 @@ that are worth noting here.
  * Failures of the selftests/x86 code.  Usually a bug in one of the
    more obscure corners of entry_64.S
  * Crashes in early boot, especially around CPU bringup.  Bugs
-   in the trampoline code or mappings cause these.
+   in the mappings cause these.
  * Crashes at the first interrupt.  Caused by bugs in entry_64.S,
    like screwing up a page table switch.  Also caused by
    incorrectly mapping the IRQ handler entry code.

arch/x86/Kconfig

@@ -384,10 +384,6 @@ config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
 
-config X86_32_SMP
-	def_bool y
-	depends on X86_32 && SMP
-
 config X86_64_SMP
 	def_bool y
 	depends on X86_64 && SMP

arch/x86/boot/compressed/Makefile

@@ -53,7 +53,7 @@ KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(call cc-option,-Wa$(comma)-mrelax-relocations=no)
 KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 
-# sev.c indirectly inludes inat-table.h which is generated during
+# sev.c indirectly includes inat-table.h which is generated during
 # compilation and stored in $(objtree). Add the directory to the includes so
 # that the compiler finds it even with out-of-tree builds (make O=/some/path).
 CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/

arch/x86/boot/compressed/mem.c

@@ -8,7 +8,7 @@
 
 /*
  * accept_memory() and process_unaccepted_memory() called from EFI stub which
- * runs before decompresser and its early_tdx_detect().
+ * runs before decompressor and its early_tdx_detect().
  *
  * Enumerate TDX directly from the early users.
  */

arch/x86/coco/tdx/tdx.c

@@ -887,7 +887,7 @@ void __init tdx_early_init(void)
 	 * there.
 	 *
 	 * Intel-TDX has a secure RDMSR hypercall, but that needs to be
-	 * implemented seperately in the low level startup ASM code.
+	 * implemented separately in the low level startup ASM code.
 	 * Until that is in place, disable parallel bringup for TDX.
 	 */
 	x86_cpuinit.parallel_bringup = false;

arch/x86/crypto/aesni-intel_asm.S

@@ -666,7 +666,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 
 .ifc \operation, dec
 	movdqa	%xmm1, %xmm3
-	pxor	%xmm1, %xmm9		# Cyphertext XOR E(K, Yn)
+	pxor	%xmm1, %xmm9		# Ciphertext XOR E(K, Yn)
 
 	mov	\PLAIN_CYPH_LEN, %r10
 	add	%r13, %r10

arch/x86/crypto/aesni-intel_avx-x86_64.S

@@ -747,7 +747,7 @@ VARIABLE_OFFSET = 16*8
 
 .if  \ENC_DEC ==  DEC
         vmovdqa	%xmm1, %xmm3
-        pxor	%xmm1, %xmm9		# Cyphertext XOR E(K, Yn)
+        pxor	%xmm1, %xmm9		# Ciphertext XOR E(K, Yn)
 
         mov	\PLAIN_CYPH_LEN, %r10
         add	%r13, %r10

arch/x86/crypto/crc32c-pcl-intel-asm_64.S

@@ -184,7 +184,7 @@ SYM_FUNC_START(crc_pcl)
 	xor     crc1,crc1
 	xor     crc2,crc2
 
-	# Fall thruogh into top of crc array (crc_128)
+	# Fall through into top of crc array (crc_128)
 
 	################################################################
 	## 3) CRC Array:

arch/x86/crypto/sha512-avx-asm.S

@@ -84,7 +84,7 @@ frame_size = frame_WK + WK_SIZE
 
 # Useful QWORD "arrays" for simpler memory references
 # MSG, DIGEST, K_t, W_t are arrays
-# WK_2(t) points to 1 of 2 qwords at frame.WK depdending on t being odd/even
+# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even
 
 # Input message (arg1)
 #define MSG(i)    8*i(msg)

arch/x86/crypto/sha512-ssse3-asm.S

@@ -82,7 +82,7 @@ frame_size = frame_WK + WK_SIZE
 
 # Useful QWORD "arrays" for simpler memory references
 # MSG, DIGEST, K_t, W_t are arrays
-# WK_2(t) points to 1 of 2 qwords at frame.WK depdending on t being odd/even
+# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even
 
 # Input message (arg1)
 #define MSG(i)    8*i(msg)

arch/x86/events/amd/brs.c

@@ -125,7 +125,7 @@ int amd_brs_hw_config(struct perf_event *event)
 	 * Where X is the number of taken branches due to interrupt
 	 * skid. Skid is large.
 	 *
-	 * Where Y is the occurences of the event while BRS is
+	 * Where Y is the occurrences of the event while BRS is
 	 * capturing the lbr_nr entries.
 	 *
 	 * By using retired taken branches, we limit the impact on the

arch/x86/events/amd/core.c

@@ -1184,7 +1184,7 @@ static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc,
  * period of each one and given that the BRS saturates, it would not be possible
  * to guarantee correlated content for all events. Therefore, in situations
  * where multiple events want to use BRS, the kernel enforces mutual exclusion.
- * Exclusion is enforced by chosing only one counter for events using BRS.
+ * Exclusion is enforced by choosing only one counter for events using BRS.
  * The event scheduling logic will then automatically multiplex the
  * events and ensure that at most one event is actively using BRS.
  *

arch/x86/events/intel/core.c

@@ -4027,7 +4027,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 
 /*
  * Currently, the only caller of this function is the atomic_switch_perf_msrs().
- * The host perf conext helps to prepare the values of the real hardware for
+ * The host perf context helps to prepare the values of the real hardware for
  * a set of msrs that need to be switched atomically in a vmx transaction.
  *
  * For example, the pseudocode needed to add a new msr should look like:

arch/x86/hyperv/hv_apic.c

@@ -209,7 +209,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector,
 
 		/*
 		 * This particular version of the IPI hypercall can
-		 * only target upto 64 CPUs.
+		 * only target up to 64 CPUs.
 		 */
 		if (vcpu >= 64)
 			goto do_ex_hypercall;

arch/x86/hyperv/irqdomain.c

@@ -212,7 +212,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		 * This interrupt is already mapped. Let's unmap first.
 		 *
 		 * We don't use retarget interrupt hypercalls here because
-		 * Microsoft Hypervisor doens't allow root to change the vector
+		 * Microsoft Hypervisor doesn't allow root to change the vector
 		 * or specify VPs outside of the set that is initially used
 		 * during mapping.
 		 */

arch/x86/hyperv/ivm.c

@@ -144,7 +144,7 @@ void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason)
 	/* Tell the hypervisor what went wrong. */
 	val |= GHCB_SEV_TERM_REASON(set, reason);
 
-	/* Request Guest Termination from Hypvervisor */
+	/* Request Guest Termination from Hypervisor */
 	wr_ghcb_msr(val);
 	VMGEXIT();
 

arch/x86/include/asm/amd_nb.h

@@ -104,7 +104,7 @@ static inline bool amd_gart_present(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return false;
 
-	/* GART present only on Fam15h, upto model 0fh */
+	/* GART present only on Fam15h, up to model 0fh */
 	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
 	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
 		return true;

arch/x86/include/asm/extable_fixup_types.h

@@ -4,7 +4,7 @@
 
 /*
  * Our IMM is signed, as such it must live at the top end of the word. Also,
- * since C99 hex constants are of ambigious type, force cast the mask to 'int'
+ * since C99 hex constants are of ambiguous type, force cast the mask to 'int'
  * so that FIELD_GET() will DTRT and sign extend the value when it extracts it.
  */
 #define EX_DATA_TYPE_MASK		((int)0x000000FF)

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

@@ -415,7 +415,7 @@ struct fpu_state_perm {
 	 *
 	 * This master permission field is only to be used when
 	 * task.fpu.fpstate based checks fail to validate whether the task
-	 * is allowed to expand it's xfeatures set which requires to
+	 * is allowed to expand its xfeatures set which requires to
 	 * allocate a larger sized fpstate buffer.
 	 *
 	 * Do not access this field directly.  Use the provided helper

arch/x86/include/asm/io.h

@@ -242,7 +242,7 @@ static inline void slow_down_io(void)
 
 #endif
 
-#define BUILDIO(bwl, bw, type)						\
+#define BUILDIO(bwl, type)						\
 static inline void out##bwl##_p(type value, u16 port)			\
 {									\
 	out##bwl(value, port);						\
@@ -288,9 +288,9 @@ static inline void ins##bwl(u16 port, void *addr, unsigned long count)	\
 	}								\
 }
 
-BUILDIO(b, b, u8)
-BUILDIO(w, w, u16)
-BUILDIO(l,  , u32)
+BUILDIO(b, u8)
+BUILDIO(w, u16)
+BUILDIO(l, u32)
 #undef BUILDIO
 
 #define inb_p inb_p

arch/x86/include/asm/iosf_mbi.h

@@ -111,7 +111,7 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask);
  * This function will block all kernel access to the PMIC I2C bus, so that the
  * P-Unit can safely access the PMIC over the shared I2C bus.
  *
- * Note on these systems the i2c-bus driver will request a sempahore from the
+ * Note on these systems the i2c-bus driver will request a semaphore from the
  * P-Unit for exclusive access to the PMIC bus when i2c drivers are accessing
  * it, but this does not appear to be sufficient, we still need to avoid making
  * certain P-Unit requests during the access window to avoid problems.

arch/x86/include/asm/kvm_host.h

@@ -1652,7 +1652,7 @@ struct kvm_x86_ops {
 	/* Whether or not a virtual NMI is pending in hardware. */
 	bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu);
 	/*
-	 * Attempt to pend a virtual NMI in harware.  Returns %true on success
+	 * Attempt to pend a virtual NMI in hardware.  Returns %true on success
 	 * to allow using static_call_ret0 as the fallback.
 	 */
 	bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu);

arch/x86/include/asm/nospec-branch.h

@@ -49,7 +49,7 @@
  * but there is still a cushion vs. the RSB depth. The algorithm does not
  * claim to be perfect and it can be speculated around by the CPU, but it
  * is considered that it obfuscates the problem enough to make exploitation
- * extremly difficult.
+ * extremely difficult.
  */
 #define RET_DEPTH_SHIFT			5
 #define RSB_RET_STUFF_LOOPS		16
@@ -208,7 +208,7 @@
 
 /*
  * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should
- * eventually turn into it's own annotation.
+ * eventually turn into its own annotation.
  */
 .macro VALIDATE_UNRET_END
 #if defined(CONFIG_NOINSTR_VALIDATION) && \

arch/x86/include/asm/pgtable_64.h

@@ -203,7 +203,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
  * F (2) in swp entry is used to record when a pagetable is
  * writeprotected by userfaultfd WP support.
  *
- * E (3) in swp entry is used to rememeber PG_anon_exclusive.
+ * E (3) in swp entry is used to remember PG_anon_exclusive.
  *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.

arch/x86/include/asm/setup.h

@@ -31,8 +31,6 @@
 #include <asm/bootparam.h>
 #include <asm/x86_init.h>
 
-extern u64 relocated_ramdisk;
-
 /* Interrupt control for vSMPowered x86_64 systems */
 #ifdef CONFIG_X86_64
 void vsmp_init(void);

arch/x86/include/asm/uv/uv_hub.h

@@ -653,7 +653,7 @@ static inline int uv_blade_to_node(int blade)
 	return uv_socket_to_node(blade);
 }
 
-/* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
+/* Blade number of current cpu. Numbered 0 .. <#blades -1> */
 static inline int uv_numa_blade_id(void)
 {
 	return uv_hub_info->numa_blade_id;

arch/x86/include/asm/vdso/gettimeofday.h

@@ -321,7 +321,7 @@ static __always_inline
 u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
 {
 	/*
-	 * Due to the MSB/Sign-bit being used as invald marker (see
+	 * Due to the MSB/Sign-bit being used as invalid marker (see
 	 * arch_vdso_cycles_valid() above), the effective mask is S64_MAX.
 	 */
 	u64 delta = (cycles - last) & S64_MAX;

arch/x86/include/asm/xen/interface_64.h

@@ -61,7 +61,7 @@
  *   RING1 -> RING3 kernel mode.
  *   RING2 -> RING3 kernel mode.
  *   RING3 -> RING3 user mode.
- * However RING0 indicates that the guest kernel should return to iteself
+ * However RING0 indicates that the guest kernel should return to itself
  * directly with
  *      orb   $3,1*8(%rsp)
  *      iretq

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

@@ -238,7 +238,7 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] = {
 	/*
 	 * HSMP_GET_DIMM_THERMAL, num_args = 1, response_sz = 1
 	 * input: args[0] = DIMM address[7:0]
-	 * output: args[0] = temperature in degree celcius[31:21] + update rate in ms[16:8] +
+	 * output: args[0] = temperature in degree celsius[31:21] + update rate in ms[16:8] +
 	 * DIMM address[7:0]
 	 */
 	{1, 1, HSMP_GET},

arch/x86/kernel/alternative.c

@@ -1906,7 +1906,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
  * Note that the caller must ensure that if the modified code is part of a
  * module, the module would not be removed during poking. This can be achieved
  * by registering a module notifier, and ordering module removal and patching
- * trough a mutex.
+ * through a mutex.
  */
 void *text_poke(void *addr, const void *opcode, size_t len)
 {

arch/x86/kernel/amd_gart_64.c

@@ -776,7 +776,7 @@ int __init gart_iommu_init(void)
 				iommu_size >> PAGE_SHIFT);
 	/*
 	 * Tricky. The GART table remaps the physical memory range,
-	 * so the CPU wont notice potential aliases and if the memory
+	 * so the CPU won't notice potential aliases and if the memory
 	 * is remapped to UC later on, we might surprise the PCI devices
 	 * with a stray writeout of a cacheline. So play it sure and
 	 * do an explicit, full-scale wbinvd() _after_ having marked all

arch/x86/kernel/apic/Makefile

@@ -4,7 +4,7 @@
 #
 
 # Leads to non-deterministic coverage that is not a function of syscall inputs.
-# In particualr, smp_apic_timer_interrupt() is called in random places.
+# In particular, smp_apic_timer_interrupt() is called in random places.
 KCOV_INSTRUMENT		:= n
 
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_common.o apic_noop.o ipi.o vector.o init.o

arch/x86/kernel/apic/apic.c

@@ -782,7 +782,7 @@ bool __init apic_needs_pit(void)
 
 	/*
 	 * If interrupt delivery mode is legacy PIC or virtual wire without
-	 * configuration, the local APIC timer wont be set up. Make sure
+	 * configuration, the local APIC timer won't be set up. Make sure
 	 * that the PIT is initialized.
 	 */
 	if (apic_intr_mode == APIC_PIC ||

arch/x86/kernel/apic/vector.c

@@ -738,8 +738,8 @@ int __init arch_probe_nr_irqs(void)
 void lapic_assign_legacy_vector(unsigned int irq, bool replace)
 {
 	/*
-	 * Use assign system here so it wont get accounted as allocated
-	 * and moveable in the cpu hotplug check and it prevents managed
+	 * Use assign system here so it won't get accounted as allocated
+	 * and movable in the cpu hotplug check and it prevents managed
 	 * irq reservation from touching it.
 	 */
 	irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace);

arch/x86/kernel/cpu/mtrr/generic.c

@@ -428,6 +428,10 @@ void __init mtrr_copy_map(void)
  * from the x86_init.hyper.init_platform() hook.  It can be called only once.
  * The MTRR state can't be changed afterwards.  To ensure that, X86_FEATURE_MTRR
  * is cleared.
+ *
+ * @var: MTRR variable range array to use
+ * @num_var: length of the @var array
+ * @def_type: default caching type
  */
 void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var,
 			  mtrr_type def_type)
@@ -492,13 +496,15 @@ static u8 type_merge(u8 type, u8 new_type, u8 *uniform)
 /**
  * mtrr_type_lookup - look up memory type in MTRR
  *
+ * @start: Begin of the physical address range
+ * @end: End of the physical address range
+ * @uniform: output argument:
+ *  - 1: the returned MTRR type is valid for the whole region
+ *  - 0: otherwise
+ *
  * Return Values:
  * MTRR_TYPE_(type)  - The effective MTRR type for the region
  * MTRR_TYPE_INVALID - MTRR is disabled
- *
- * Output Argument:
- * uniform - Set to 1 when the returned MTRR type is valid for the whole
- *	     region, set to 0 else.
  */
 u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 {

arch/x86/kernel/cpu/sgx/ioctl.c

@@ -581,7 +581,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct,
  *
  * Flush any outstanding enqueued EADD operations and perform EINIT.  The
  * Launch Enclave Public Key Hash MSRs are rewritten as necessary to match
- * the enclave's MRSIGNER, which is caculated from the provided sigstruct.
+ * the enclave's MRSIGNER, which is calculated from the provided sigstruct.
  *
  * Return:
  * - 0:		Success.

arch/x86/kernel/fpu/core.c

@@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
  * Must be invoked from KVM after a VMEXIT before enabling interrupts when
  * XFD write emulation is disabled. This is required because the guest can
  * freely modify XFD and the state at VMEXIT is not guaranteed to be the
- * same as the state on VMENTER. So software state has to be udpated before
+ * same as the state on VMENTER. So software state has to be updated before
  * any operation which depends on it can take place.
  *
  * Note: It can be invoked unconditionally even when write emulation is