13 files changed, 102 insertions, 94 deletions

diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 19de7537e7d3..d1ce8e2f98b9 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -29,6 +29,11 @@
 #include <asm/cpu_ops.h>
 #include <asm/smp_plat.h>
 
+#ifdef CONFIG_ACPI_APEI
+# include <linux/efi.h>
+# include <asm/pgtable.h>
+#endif
+
 int acpi_noirq = 1;		/* skip ACPI IRQ initialization */
 int acpi_disabled = 1;
 EXPORT_SYMBOL(acpi_disabled);
@@ -206,27 +211,26 @@ void __init acpi_boot_table_init(void)
 	}
 }
 
-void __init acpi_gic_init(void)
+#ifdef CONFIG_ACPI_APEI
+pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
 {
-	struct acpi_table_header *table;
-	acpi_status status;
-	acpi_size tbl_size;
-	int err;
-
-	if (acpi_disabled)
-		return;
-
-	status = acpi_get_table_with_size(ACPI_SIG_MADT, 0, &table, &tbl_size);
-	if (ACPI_FAILURE(status)) {
-		const char *msg = acpi_format_exception(status);
-
-		pr_err("Failed to get MADT table, %s\n", msg);
-		return;
-	}
+	/*
+	 * According to "Table 8 Map: EFI memory types to AArch64 memory
+	 * types" of UEFI 2.5 section 2.3.6.1, each EFI memory type is
+	 * mapped to a corresponding MAIR attribute encoding.
+	 * The EFI memory attribute advises all possible capabilities
+	 * of a memory region. We use the most efficient capability.
+	 */
 
-	err = gic_v2_acpi_init(table);
-	if (err)
-		pr_err("Failed to initialize GIC IRQ controller");
+	u64 attr;
 
-	early_acpi_os_unmap_memory((char *)table, tbl_size);
+	attr = efi_mem_attributes(addr);
+	if (attr & EFI_MEMORY_WB)
+		return PAGE_KERNEL;
+	if (attr & EFI_MEMORY_WT)
+		return __pgprot(PROT_NORMAL_WT);
+	if (attr & EFI_MEMORY_WC)
+		return __pgprot(PROT_NORMAL_NC);
+	return __pgprot(PROT_DEVICE_nGnRnE);
 }
+#endif
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index bcee7abac68e..937f5e58a4d3 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -284,21 +284,23 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
 	__asm__ __volatile__(					\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
 		    CONFIG_ARM64_PAN)				\
-	"	mov		%w2, %w1\n"			\
-	"0:	ldxr"B"		%w1, [%3]\n"			\
-	"1:	stxr"B"		%w0, %w2, [%3]\n"		\
+	"0:	ldxr"B"		%w2, [%3]\n"			\
+	"1:	stxr"B"		%w0, %w1, [%3]\n"		\
 	"	cbz		%w0, 2f\n"			\
 	"	mov		%w0, %w4\n"			\
+	"	b		3f\n"				\
 	"2:\n"							\
+	"	mov		%w1, %w2\n"			\
+	"3:\n"							\
 	"	.pushsection	 .fixup,\"ax\"\n"		\
 	"	.align		2\n"				\
-	"3:	mov		%w0, %w5\n"			\
-	"	b		2b\n"				\
+	"4:	mov		%w0, %w5\n"			\
+	"	b		3b\n"				\
 	"	.popsection"					\
 	"	.pushsection	 __ex_table,\"a\"\n"		\
 	"	.align		3\n"				\
-	"	.quad		0b, 3b\n"			\
-	"	.quad		1b, 3b\n"			\
+	"	.quad		0b, 4b\n"			\
+	"	.quad		1b, 4b\n"			\
 	"	.popsection\n"					\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
 		CONFIG_ARM64_PAN)				\
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 09eab326ef93..24926f2504f7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -23,6 +23,7 @@
 
 #define MIDR_CORTEX_A53 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_THUNDERX	MIDR_CPU_PART(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 
 #define CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \
 			MIDR_ARCHITECTURE_MASK)
@@ -82,6 +83,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x04),
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23154
+	{
+	/* Cavium ThunderX, pass 1.x */
+		.desc = "Cavium erratum 23154",
+		.capability = ARM64_WORKAROUND_CAVIUM_23154,
+		MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 6ecb82481790..c8cf89223b5a 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -578,6 +578,8 @@ u64 read_system_reg(u32 id)
 	return regp->sys_val;
 }
 
+#include <linux/irqchip/arm-gic-v3.h>
+
 static bool
 feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
 {
@@ -595,11 +597,26 @@ has_cpuid_feature(const struct arm64_cpu_capabilities *entry)
 	return feature_matches(val, entry);
 }
 
+static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry)
+{
+	bool has_sre;
+
+	if (!has_cpuid_feature(entry))
+		return false;
+
+	has_sre = gic_enable_sre();
+	if (!has_sre)
+		pr_warn_once("%s present but disabled by higher exception level\n",
+			     entry->desc);
+
+	return has_sre;
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
 		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
-		.matches = has_cpuid_feature,
+		.matches = has_useable_gicv3_cpuif,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.field_pos = ID_AA64PFR0_GIC_SHIFT,
 		.min_field_value = 1,
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 1429044b143c..8aee3aeec3e6 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -60,7 +60,7 @@ static u32 mdscr_read(void)
  * Allow root to disable self-hosted debug from userspace.
  * This is useful if you want to connect an external JTAG debugger.
  */
-static u32 debug_enabled = 1;
+static bool debug_enabled = true;
 
 static int create_debug_debugfs_entry(void)
 {
@@ -71,7 +71,7 @@ fs_initcall(create_debug_debugfs_entry);
 
 static int __init early_debug_disable(char *buf)
 {
-	debug_enabled = 0;
+	debug_enabled = false;
 	return 0;
 }
 
@@ -273,20 +273,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
  * Use reader/writer locks instead of plain spinlock.
  */
 static LIST_HEAD(break_hook);
-static DEFINE_RWLOCK(break_hook_lock);
+static DEFINE_SPINLOCK(break_hook_lock);
 
 void register_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_add(&hook->node, &break_hook);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_add_rcu(&hook->node, &break_hook);
+	spin_unlock(&break_hook_lock);
 }
 
 void unregister_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&break_hook_lock);
+	synchronize_rcu();
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
@@ -294,11 +295,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 	struct break_hook *hook;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
-	read_lock(&break_hook_lock);
-	list_for_each_entry(hook, &break_hook, node)
+	rcu_read_lock();
+	list_for_each_entry_rcu(hook, &break_hook, node)
 		if ((esr & hook->esr_mask) == hook->esr_val)
 			fn = hook->fn;
-	read_unlock(&break_hook_lock);
+	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index a48d1f477b2e..de46b50f4cdf 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -50,15 +50,6 @@ static struct mm_struct efi_mm = {
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
 };
 
-static int uefi_debug __initdata;
-static int __init uefi_debug_setup(char *str)
-{
-	uefi_debug = 1;
-
-	return 0;
-}
-early_param("uefi_debug", uefi_debug_setup);
-
 static int __init is_normal_ram(efi_memory_desc_t *md)
 {
 	if (md->attribute & EFI_MEMORY_WB)
@@ -170,14 +161,14 @@ static __init void reserve_regions(void)
 	efi_memory_desc_t *md;
 	u64 paddr, npages, size;
 
-	if (uefi_debug)
+	if (efi_enabled(EFI_DBG))
 		pr_info("Processing EFI memory map:\n");
 
 	for_each_efi_memory_desc(&memmap, md) {
 		paddr = md->phys_addr;
 		npages = md->num_pages;
 
-		if (uefi_debug) {
+		if (efi_enabled(EFI_DBG)) {
 			char buf[64];
 
 			pr_info("  0x%012llx-0x%012llx %s",
@@ -193,11 +184,11 @@ static __init void reserve_regions(void)
 
 		if (is_reserve_region(md)) {
 			memblock_reserve(paddr, size);
-			if (uefi_debug)
+			if (efi_enabled(EFI_DBG))
 				pr_cont("*");
 		}
 
-		if (uefi_debug)
+		if (efi_enabled(EFI_DBG))
 			pr_cont("\n");
 	}
 
@@ -209,14 +200,14 @@ void __init efi_init(void)
 	struct efi_fdt_params params;
 
 	/* Grab UEFI information placed in FDT by stub */
-	if (!efi_get_fdt_params(&params, uefi_debug))
+	if (!efi_get_fdt_params(&params))
 		return;
 
 	efi_system_table = params.system_table;
 
 	memblock_reserve(params.mmap & PAGE_MASK,
 			 PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
-	memmap.phys_map = (void *)params.mmap;
+	memmap.phys_map = params.mmap;
 	memmap.map = early_memremap(params.mmap, params.mmap_size);
 	memmap.map_end = memmap.map + params.mmap_size;
 	memmap.desc_size = params.desc_size;
@@ -290,7 +281,7 @@ static int __init arm64_enable_runtime_services(void)
 	pr_info("Remapping and enabling EFI services.\n");
 
 	mapsize = memmap.map_end - memmap.map;
-	memmap.map = (__force void *)ioremap_cache((phys_addr_t)memmap.phys_map,
+	memmap.map = (__force void *)ioremap_cache(memmap.phys_map,
 						   mapsize);
 	if (!memmap.map) {
 		pr_err("Failed to remap EFI memory map\n");
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 514c1cc9fdc5..23cfc08fc8ba 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -484,6 +484,8 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
 	msr_s	ICC_SRE_EL2, x0
 	isb					// Make sure SRE is now set
+	mrs_s	x0, ICC_SRE_EL2			// Read SRE back,
+	tbz	x0, #0, 3f			// and check that it sticks
 	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
 
 3:
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index f341866aa810..c08b9ad6f429 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -85,7 +85,7 @@ bool aarch64_insn_is_branch_imm(u32 insn)
 		aarch64_insn_is_bcond(insn));
 }
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
@@ -131,13 +131,13 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn)
 	unsigned long flags = 0;
 	int ret;
 
-	spin_lock_irqsave(&patch_lock, flags);
+	raw_spin_lock_irqsave(&patch_lock, flags);
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
 	ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE);
 
 	patch_unmap(FIX_TEXT_POKE0);
-	spin_unlock_irqrestore(&patch_lock, flags);
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index aa94a88f6279..f67f35b6edb1 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -30,20 +30,6 @@
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 
-static bool psci_power_state_loses_context(u32 state)
-{
-	return state & PSCI_0_2_POWER_STATE_TYPE_MASK;
-}
-
-static bool psci_power_state_is_valid(u32 state)
-{
-	const u32 valid_mask = PSCI_0_2_POWER_STATE_ID_MASK |
-			       PSCI_0_2_POWER_STATE_TYPE_MASK |
-			       PSCI_0_2_POWER_STATE_AFFL_MASK;
-
-	return !(state & ~valid_mask);
-}
-
 static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
 
 static int __maybe_unused cpu_psci_cpu_init_idle(unsigned int cpu)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 556301fbeeef..8119479147db 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -248,6 +248,8 @@ static void __init relocate_initrd(void)
 		to_free = ram_end - orig_start;
 
 	size = orig_end - orig_start;
+	if (!size)
+		return;
 
 	/* initrd needs to be relocated completely inside linear mapping */
 	new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn),
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 407991bf79f5..ccb6078ed9f2 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,11 +48,7 @@ int notrace unwind_frame(struct stackframe *frame)
 
 	frame->sp = fp + 0x10;
 	frame->fp = *(unsigned long *)(fp);
-	/*
-	 * -4 here because we care about the PC at time of bl,
-	 * not where the return will go.
-	 */
-	frame->pc = *(unsigned long *)(fp + 8) - 4;
+	frame->pc = *(unsigned long *)(fp + 8);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index d87403e8ba1d..fce95e17cf7f 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -80,17 +80,21 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	if (ret == 0) {
 		/*
 		 * We are resuming from reset with TTBR0_EL1 set to the
-		 * idmap to enable the MMU; restore the active_mm mappings in
-		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
-		 * the thread entered cpu_suspend with TTBR0_EL1 set to
-		 * reserved TTBR0 page tables and should be restored as such.
+		 * idmap to enable the MMU; set the TTBR0 to the reserved
+		 * page tables to prevent speculative TLB allocations, flush
+		 * the local tlb and set the default tcr_el1.t0sz so that
+		 * the TTBR0 address space set-up is properly restored.
+		 * If the current active_mm != &init_mm we entered cpu_suspend
+		 * with mappings in TTBR0 that must be restored, so we switch
+		 * them back to complete the address space configuration
+		 * restoration before returning.
 		 */
-		if (mm == &init_mm)
-			cpu_set_reserved_ttbr0();
-		else
-			cpu_switch_mm(mm->pgd, mm);
-
+		cpu_set_reserved_ttbr0();
 		local_flush_tlb_all();
+		cpu_set_default_tcr_t0sz();
+
+		if (mm != &init_mm)
+			cpu_switch_mm(mm->pgd, mm);
 
 		/*
 		 * Restore per-cpu offset before any kernel
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 149151fb42bb..13339b6ffc1a 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -67,16 +67,10 @@ void __init time_init(void)
 	u32 arch_timer_rate;
 
 	of_clk_init(NULL);
-	clocksource_of_init();
+	clocksource_probe();
 
 	tick_setup_hrtimer_broadcast();
 
-	/*
-	 * Since ACPI or FDT will only one be available in the system,
-	 * we can use acpi_generic_timer_init() here safely
-	 */
-	acpi_generic_timer_init();
-
 	arch_timer_rate = arch_timer_get_rate();
 	if (!arch_timer_rate)
 		panic("Unable to initialise architected timer.\n");