Update 5.4-1.0.0-imx to v5.4.38 from stable

Documentation/admin-guide/kernel-parameters.txt

@@ -5005,8 +5005,7 @@
 
 	usbcore.old_scheme_first=
 			[USB] Start with the old device initialization
-			scheme,  applies only to low and full-speed devices
-			 (default 0 = off).
+			scheme (default 0 = off).
 
 	usbcore.usbfs_memory_mb=
 			[USB] Memory limit (in MB) for buffers allocated by

Documentation/arm64/silicon-errata.rst

@@ -88,6 +88,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 35
+SUBLEVEL = 38
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 

arch/arm/boot/dts/bcm283x.dtsi

@@ -488,6 +488,7 @@
 					     "dsi0_ddr2",
 					     "dsi0_ddr";
 
+			status = "disabled";
 		};
 
 		thermal: thermal@7e212000 {

arch/arm/mach-imx/Makefile

@@ -118,8 +118,10 @@ obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o
 obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o
 obj-$(CONFIG_SOC_IMX7ULP) += suspend-imx7ulp.o
 endif
+ifeq ($(CONFIG_ARM_CPU_SUSPEND),y)
 AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += resume-imx6.o
+endif
 obj-$(CONFIG_SOC_IMX6) += pm-imx6.o
 
 obj-$(CONFIG_SOC_IMX1) += mach-imx1.o

arch/arm64/Kconfig

@@ -559,6 +559,22 @@ config ARM64_ERRATUM_1463225
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1542419
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
+	default y
+	help
+	  This option adds a workaround for ARM Neoverse-N1 erratum
+	  1542419.
+
+	  Affected Neoverse-N1 cores could execute a stale instruction when
+	  modified by another CPU. The workaround depends on a firmware
+	  counterpart.
+
+	  Workaround the issue by hiding the DIC feature from EL0. This
+	  forces user-space to perform cache maintenance.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

arch/arm64/include/asm/cache.h

@@ -11,14 +11,15 @@
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
 #define CTR_IMINLINE_SHIFT	0
+#define CTR_IMINLINE_MASK	0xf
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
 #define CTR_IDC_SHIFT		28
 #define CTR_DIC_SHIFT		29
 
 #define CTR_CACHE_MINLINE_MASK	\
-	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+	(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 

arch/arm64/include/asm/compat.h

@@ -4,6 +4,9 @@
  */
 #ifndef __ASM_COMPAT_H
 #define __ASM_COMPAT_H
+
+#include <asm-generic/compat.h>
+
 #ifdef CONFIG_COMPAT
 
 /*
@@ -13,8 +16,6 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 
-#include <asm-generic/compat.h>
-
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
 #define COMPAT_UTS_MACHINE	"armv8b\0\0"

arch/arm64/include/asm/cpucaps.h

@@ -54,7 +54,8 @@
 #define ARM64_WORKAROUND_1463225		44
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
+#define ARM64_WORKAROUND_1542419		47
 
-#define ARM64_NCAPS				47
+#define ARM64_NCAPS				48
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/sysreg.h

@@ -49,7 +49,9 @@
 #ifndef CONFIG_BROKEN_GAS_INST
 
 #ifdef __ASSEMBLY__
-#define __emit_inst(x)			.inst (x)
+// The space separator is omitted so that __emit_inst(x) can be parsed as
+// either an assembler directive or an assembler macro argument.
+#define __emit_inst(x)			.inst(x)
 #else
 #define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
 #endif

arch/arm64/kernel/cpu_errata.c

@@ -88,13 +88,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 }
 
 static void
-cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
+cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
 	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	bool enable_uct_trap = false;
 
 	/* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
 	if ((read_cpuid_cachetype() & mask) !=
 	    (arm64_ftr_reg_ctrel0.sys_val & mask))
+		enable_uct_trap = true;
+
+	/* ... or if the system is affected by an erratum */
+	if (cap->capability == ARM64_WORKAROUND_1542419)
+		enable_uct_trap = true;
+
+	if (enable_uct_trap)
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
@@ -651,6 +659,18 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
 	return false;
 }
 
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
+
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
 static const struct midr_range arm64_harden_el2_vectors[] = {
@@ -927,6 +947,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM,
 		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
 	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
 #endif
 	{
 	}

arch/arm64/kernel/sys_compat.c

@@ -8,6 +8,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -17,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;

arch/arm64/kernel/traps.c

@@ -501,6 +501,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);

arch/powerpc/kernel/entry_32.S

@@ -705,7 +705,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE)
 	stw	r10,_CCR(r1)
 	stw	r1,KSP(r3)	/* Set old stack pointer */
 
-	kuap_check r2, r4
+	kuap_check r2, r0
 #ifdef CONFIG_SMP
 	/* We need a sync somewhere here to make sure that if the
 	 * previous task gets rescheduled on another CPU, it sees all

arch/powerpc/kernel/setup_64.c

@@ -541,6 +541,8 @@ static bool __init parse_cache_info(struct device_node *np,
 	lsizep = of_get_property(np, propnames[3], NULL);
 	if (bsizep == NULL)
 		bsizep = lsizep;
+	if (lsizep == NULL)
+		lsizep = bsizep;
 	if (lsizep != NULL)
 		lsize = be32_to_cpu(*lsizep);
 	if (bsizep != NULL)

arch/powerpc/kernel/time.c

@@ -522,35 +522,6 @@ static inline void clear_irq_work_pending(void)
 		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
-void arch_irq_work_raise(void)
-{
-	preempt_disable();
-	set_irq_work_pending_flag();
-	/*
-	 * Non-nmi code running with interrupts disabled will replay
-	 * irq_happened before it re-enables interrupts, so setthe
-	 * decrementer there instead of causing a hardware exception
-	 * which would immediately hit the masked interrupt handler
-	 * and have the net effect of setting the decrementer in
-	 * irq_happened.
-	 *
-	 * NMI interrupts can not check this when they return, so the
-	 * decrementer hardware exception is raised, which will fire
-	 * when interrupts are next enabled.
-	 *
-	 * BookE does not support this yet, it must audit all NMI
-	 * interrupt handlers to ensure they call nmi_enter() so this
-	 * check would be correct.
-	 */
-	if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) {
-		set_dec(1);
-	} else {
-		hard_irq_disable();
-		local_paca->irq_happened |= PACA_IRQ_DEC;
-	}
-	preempt_enable();
-}
-
 #else /* 32-bit */
 
 DEFINE_PER_CPU(u8, irq_work_pending);
@@ -559,16 +530,27 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 #define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
 #define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
+#endif /* 32 vs 64 bit */
+
 void arch_irq_work_raise(void)
 {
+	/*
+	 * 64-bit code that uses irq soft-mask can just cause an immediate
+	 * interrupt here that gets soft masked, if this is called under
+	 * local_irq_disable(). It might be possible to prevent that happening
+	 * by noticing interrupts are disabled and setting decrementer pending
+	 * to be replayed when irqs are enabled. The problem there is that
+	 * tracing can call irq_work_raise, including in code that does low
+	 * level manipulations of irq soft-mask state (e.g., trace_hardirqs_on)
+	 * which could get tangled up if we're messing with the same state
+	 * here.
+	 */
 	preempt_disable();
 	set_irq_work_pending_flag();
 	set_dec(1);
 	preempt_enable();
 }
 
-#endif /* 32 vs 64 bit */
-
 #else  /* CONFIG_IRQ_WORK */
 
 #define test_irq_work_pending()	0

arch/powerpc/platforms/Kconfig.cputype

@@ -389,7 +389,7 @@ config PPC_KUAP
 
 config PPC_KUAP_DEBUG
 	bool "Extra debugging for Kernel Userspace Access Protection"
-	depends on PPC_HAVE_KUAP && (PPC_RADIX_MMU || PPC_32)
+	depends on PPC_KUAP && (PPC_RADIX_MMU || PPC32)
 	help
 	  Add extra debugging for Kernel Userspace Access Protection (KUAP)
 	  If you're unsure, say N.

arch/powerpc/platforms/pseries/ras.c

@@ -683,6 +683,17 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp)
 #endif
 
 out:
+	/*
+	 * Enable translation as we will be accessing per-cpu variables
+	 * in save_mce_event() which may fall outside RMO region, also
+	 * leave it enabled because subsequently we will be queuing work
+	 * to workqueues where again per-cpu variables accessed, besides
+	 * fwnmi_release_errinfo() crashes when called in realmode on
+	 * pseries.
+	 * Note: All the realmode handling like flushing SLB entries for
+	 *       SLB multihit is done by now.
+	 */
+	mtmsr(mfmsr() | MSR_IR | MSR_DR);
 	save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED,
 			&mce_err, regs->nip, eaddr, paddr);
 

arch/s390/kernel/diag.c

@@ -133,7 +133,7 @@ void diag_stat_inc(enum diag_stat_enum nr)
 }
 EXPORT_SYMBOL(diag_stat_inc);
 
-void diag_stat_inc_norecursion(enum diag_stat_enum nr)
+void notrace diag_stat_inc_norecursion(enum diag_stat_enum nr)
 {
 	this_cpu_inc(diag_stat.counter[nr]);
 	trace_s390_diagnose_norecursion(diag_map[nr].code);

arch/s390/kernel/smp.c

@@ -403,7 +403,7 @@ int smp_find_processor_id(u16 address)
 	return -1;
 }
 
-bool arch_vcpu_is_preempted(int cpu)
+bool notrace arch_vcpu_is_preempted(int cpu)
 {
 	if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
 		return false;
@@ -413,7 +413,7 @@ bool arch_vcpu_is_preempted(int cpu)
 }
 EXPORT_SYMBOL(arch_vcpu_is_preempted);
 
-void smp_yield_cpu(int cpu)
+void notrace smp_yield_cpu(int cpu)
 {
 	if (MACHINE_HAS_DIAG9C) {
 		diag_stat_inc_norecursion(DIAG_STAT_X09C);

arch/s390/kernel/trace.c

@@ -14,7 +14,7 @@ EXPORT_TRACEPOINT_SYMBOL(s390_diagnose);
 
 static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth);
 
-void trace_s390_diagnose_norecursion(int diag_nr)
+void notrace trace_s390_diagnose_norecursion(int diag_nr)
 {
 	unsigned long flags;
 	unsigned int *depth;

arch/s390/kvm/kvm-s390.c

@@ -1932,6 +1932,9 @@ static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn)
 			start = slot + 1;
 	}
 
+	if (start >= slots->used_slots)
+		return slots->used_slots - 1;
+
 	if (gfn >= memslots[start].base_gfn &&
 	    gfn < memslots[start].base_gfn + memslots[start].npages) {
 		atomic_set(&slots->lru_slot, start);