Import Upstream version 5.4.13

arch/parisc/Kconfig

@@ -62,6 +62,7 @@ config PARISC
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_COPY_THREAD_TLS
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used

arch/parisc/include/asm/cmpxchg.h

@@ -44,8 +44,14 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
 **		if (((unsigned long)p & 0xf) == 0)
 **			return __ldcw(p);
 */
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+#define xchg(ptr, x)							\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	__ret = (__typeof__(*(ptr)))					\
+		__xchg((unsigned long)_x_, (ptr), sizeof(*(ptr)));	\
+	__ret;								\
+})
 
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);

arch/parisc/include/asm/kexec.h

@@ -2,8 +2,6 @@
 #ifndef _ASM_PARISC_KEXEC_H
 #define _ASM_PARISC_KEXEC_H
 
-#ifdef CONFIG_KEXEC
-
 /* Maximum physical address we can use pages from */
 #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
 /* Maximum address we can reach in physical address mode */
@@ -32,6 +30,4 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* CONFIG_KEXEC */
-
 #endif /* _ASM_PARISC_KEXEC_H */

arch/parisc/kernel/Makefile

@@ -37,5 +37,5 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 obj-$(CONFIG_KGDB)			+= kgdb.o
 obj-$(CONFIG_KPROBES)			+= kprobes.o
-obj-$(CONFIG_KEXEC)			+= kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)		+= kexec.o relocate_kernel.o
 obj-$(CONFIG_KEXEC_FILE)		+= kexec_file.o

arch/parisc/kernel/drivers.c

@@ -810,7 +810,7 @@ EXPORT_SYMBOL(device_to_hwpath);
 static void walk_native_bus(unsigned long io_io_low, unsigned long io_io_high,
                             struct device *parent);
 
-static void walk_lower_bus(struct parisc_device *dev)
+static void __init walk_lower_bus(struct parisc_device *dev)
 {
 	unsigned long io_io_low, io_io_high;
 

arch/parisc/kernel/process.c

@@ -208,8 +208,8 @@ arch_initcall(parisc_idle_init);
  * Copy architecture-specific thread state
  */
 int
-copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long kthread_arg, struct task_struct *p)
+copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+	    unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *cregs = &(p->thread.regs);
 	void *stack = task_stack_page(p);
@@ -254,9 +254,9 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 		cregs->ksp = (unsigned long)stack + THREAD_SZ_ALGN + FRAME_SIZE;
 		cregs->kpc = (unsigned long) &child_return;
 
-		/* Setup thread TLS area from the 4th parameter in clone */
+		/* Setup thread TLS area */
 		if (clone_flags & CLONE_SETTLS)
-			cregs->cr27 = cregs->gr[23];
+			cregs->cr27 = tls;
 	}
 
 	return 0;

arch/powerpc/include/asm/spinlock.h

@@ -15,6 +15,7 @@
  *
  * (the type definitions are in asm/spinlock_types.h)
  */
+#include <linux/jump_label.h>
 #include <linux/irqflags.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -36,10 +37,12 @@
 #endif
 
 #ifdef CONFIG_PPC_PSERIES
+DECLARE_STATIC_KEY_FALSE(shared_processor);
+
 #define vcpu_is_preempted vcpu_is_preempted
 static inline bool vcpu_is_preempted(int cpu)
 {
-	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+	if (!static_branch_unlikely(&shared_processor))
 		return false;
 	return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
 }

arch/powerpc/mm/mem.c

@@ -104,6 +104,27 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end)
 	return -ENODEV;
 }
 
+#define FLUSH_CHUNK_SIZE SZ_1G
+/**
+ * flush_dcache_range_chunked(): Write any modified data cache blocks out to
+ * memory and invalidate them, in chunks of up to FLUSH_CHUNK_SIZE
+ * Does not invalidate the corresponding instruction cache blocks.
+ *
+ * @start: the start address
+ * @stop: the stop address (exclusive)
+ * @chunk: the max size of the chunks
+ */
+static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
+				       unsigned long chunk)
+{
+	unsigned long i;
+
+	for (i = start; i < stop; i += chunk) {
+		flush_dcache_range(i, min(stop, i + chunk));
+		cond_resched();
+	}
+}
+
 int __ref arch_add_memory(int nid, u64 start, u64 size,
 			struct mhp_restrictions *restrictions)
 {
@@ -120,7 +141,8 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
 			start, start + size, rc);
 		return -EFAULT;
 	}
-	flush_dcache_range(start, start + size);
+
+	flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE);
 
 	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
@@ -130,14 +152,14 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
 	int ret;
 
-	__remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
-	flush_dcache_range(start, start + size);
+	flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE);
+
 	ret = remove_section_mapping(start, start + size);
 	WARN_ON_ONCE(ret);
 
@@ -260,6 +282,14 @@ void __init mem_init(void)
 	BUILD_BUG_ON(MMU_PAGE_COUNT > 16);
 
 #ifdef CONFIG_SWIOTLB
+	/*
+	 * Some platforms (e.g. 85xx) limit DMA-able memory way below
+	 * 4G. We force memblock to bottom-up mode to ensure that the
+	 * memory allocated in swiotlb_init() is DMA-able.
+	 * As it's the last memblock allocation, no need to reset it
+	 * back to to-down.
+	 */
+	memblock_set_bottom_up(true);
 	swiotlb_init(0);
 #endif
 

arch/powerpc/mm/slice.c

@@ -50,7 +50,7 @@ static void slice_print_mask(const char *label, const struct slice_mask *mask) {
 
 #endif
 
-static inline bool slice_addr_is_low(unsigned long addr)
+static inline notrace bool slice_addr_is_low(unsigned long addr)
 {
 	u64 tmp = (u64)addr;
 
@@ -659,7 +659,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 				       mm_ctx_user_psize(&current->mm->context), 1);
 }
 
-unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
+unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned char *psizes;
 	int index, mask_index;

arch/powerpc/platforms/powernv/pci.c

@@ -945,6 +945,23 @@ void __init pnv_pci_init(void)
 	if (!firmware_has_feature(FW_FEATURE_OPAL))
 		return;
 
+#ifdef CONFIG_PCIEPORTBUS
+	/*
+	 * On PowerNV PCIe devices are (currently) managed in cooperation
+	 * with firmware. This isn't *strictly* required, but there's enough
+	 * assumptions baked into both firmware and the platform code that
+	 * it's unwise to allow the portbus services to be used.
+	 *
+	 * We need to fix this eventually, but for now set this flag to disable
+	 * the portbus driver. The AER service isn't required since that AER
+	 * events are handled via EEH. The pciehp hotplug driver can't work
+	 * without kernel changes (and portbus binding breaks pnv_php). The
+	 * other services also require some thinking about how we're going
+	 * to integrate them.
+	 */
+	pcie_ports_disabled = true;
+#endif
+
 	/* Look for IODA IO-Hubs. */
 	for_each_compatible_node(np, NULL, "ibm,ioda-hub") {
 		pnv_pci_init_ioda_hub(np);

arch/powerpc/platforms/pseries/setup.c

@@ -74,6 +74,9 @@
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
 
+DEFINE_STATIC_KEY_FALSE(shared_processor);
+EXPORT_SYMBOL_GPL(shared_processor);
+
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
 unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K);
@@ -758,6 +761,10 @@ static void __init pSeries_setup_arch(void)
 
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
+
+		if (lppaca_shared_proc(get_lppaca()))
+			static_branch_enable(&shared_processor);
+
 		ppc_md.power_save = pseries_lpar_idle;
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
 #ifdef CONFIG_PCI_IOV

arch/riscv/Kconfig

@@ -61,6 +61,7 @@ config RISCV
 	select SPARSEMEM_STATIC if 32BIT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select HAVE_ARCH_MMAP_RND_BITS
+	select HAVE_COPY_THREAD_TLS
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT

arch/riscv/kernel/ftrace.c

@@ -142,7 +142,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	 */
 	old = *parent;
 
-	if (function_graph_enter(old, self_addr, frame_pointer, parent))
+	if (!function_graph_enter(old, self_addr, frame_pointer, parent))
 		*parent = return_hooker;
 }
 

arch/riscv/kernel/process.c

@@ -99,8 +99,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-	unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+	unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -120,7 +120,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		if (usp) /* User fork */
 			childregs->sp = usp;
 		if (clone_flags & CLONE_SETTLS)
-			childregs->tp = childregs->a5;
+			childregs->tp = tls;
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.ra = (unsigned long)ret_from_fork;
 	}

arch/riscv/mm/cacheflush.c

@@ -14,6 +14,7 @@ void flush_icache_all(void)
 {
 	sbi_remote_fence_i(NULL);
 }
+EXPORT_SYMBOL(flush_icache_all);
 
 /*
  * Performs an icache flush for the given MM context.  RISC-V has no direct

arch/riscv/net/bpf_jit_comp.c

@@ -631,14 +631,14 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 		return -1;
 	emit(rv_bgeu(RV_REG_A2, RV_REG_T1, off >> 1), ctx);
 
-	/* if (--TCC < 0)
+	/* if (TCC-- < 0)
 	 *     goto out;
 	 */
 	emit(rv_addi(RV_REG_T1, tcc, -1), ctx);
 	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
 	if (is_13b_check(off, insn))
 		return -1;
-	emit(rv_blt(RV_REG_T1, RV_REG_ZERO, off >> 1), ctx);
+	emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx);
 
 	/* prog = array->ptrs[index];
 	 * if (!prog)

arch/s390/kernel/perf_cpum_sf.c

@@ -1313,18 +1313,28 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		 */
 		if (flush_all && done)
 			break;
-
-		/* If an event overflow happened, discard samples by
-		 * processing any remaining sample-data-blocks.
-		 */
-		if (event_overflow)
-			flush_all = 1;
 	}
 
 	/* Account sample overflows in the event hardware structure */
 	if (sampl_overflow)
 		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
 						 sampl_overflow, 1 + num_sdb);
+
+	/* Perf_event_overflow() and perf_event_account_interrupt() limit
+	 * the interrupt rate to an upper limit. Roughly 1000 samples per
+	 * task tick.
+	 * Hitting this limit results in a large number
+	 * of throttled REF_REPORT_THROTTLE entries and the samples
+	 * are dropped.
+	 * Slightly increase the interval to avoid hitting this limit.
+	 */
+	if (event_overflow) {
+		SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10);
+		debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n",
+				    __func__,
+				    DIV_ROUND_UP(SAMPL_RATE(hwc), 10));
+	}
+
 	if (sampl_overflow || event_overflow)
 		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
 				    "overflow stats: sample=%llu event=%llu\n",

arch/s390/kernel/smp.c

@@ -727,39 +727,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
 
 static int smp_add_present_cpu(int cpu);
 
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+			bool configured, bool early)
 {
 	struct pcpu *pcpu;
-	cpumask_t avail;
-	int cpu, nr, i, j;
+	int cpu, nr, i;
 	u16 address;
 
 	nr = 0;
-	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
-	cpu = cpumask_first(&avail);
-	for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
-		if (sclp.has_core_type && info->core[i].type != boot_core_type)
+	if (sclp.has_core_type && core->type != boot_core_type)
+		return nr;
+	cpu = cpumask_first(avail);
+	address = core->core_id << smp_cpu_mt_shift;
+	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+		if (pcpu_find_address(cpu_present_mask, address + i))
 			continue;
-		address = info->core[i].core_id << smp_cpu_mt_shift;
-		for (j = 0; j <= smp_cpu_mtid; j++) {
-			if (pcpu_find_address(cpu_present_mask, address + j))
-				continue;
-			pcpu = pcpu_devices + cpu;
-			pcpu->address = address + j;
-			pcpu->state =
-				(cpu >= info->configured*(smp_cpu_mtid + 1)) ?
-				CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
-			smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-			set_cpu_present(cpu, true);
-			if (sysfs_add && smp_add_present_cpu(cpu) != 0)
-				set_cpu_present(cpu, false);
-			else
-				nr++;
-			cpu = cpumask_next(cpu, &avail);
-			if (cpu >= nr_cpu_ids)
+		pcpu = pcpu_devices + cpu;
+		pcpu->address = address + i;
+		if (configured)
+			pcpu->state = CPU_STATE_CONFIGURED;
+		else
+			pcpu->state = CPU_STATE_STANDBY;
+		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		set_cpu_present(cpu, true);
+		if (!early && smp_add_present_cpu(cpu) != 0)
+			set_cpu_present(cpu, false);
+		else
+			nr++;
+		cpumask_clear_cpu(cpu, avail);
+		cpu = cpumask_next(cpu, avail);
+	}
+	return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+	struct sclp_core_entry *core;
+	cpumask_t avail;
+	bool configured;
+	u16 core_id;
+	int nr, i;
+
+	nr = 0;
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+	/*
+	 * Add IPL core first (which got logical CPU number 0) to make sure
+	 * that all SMT threads get subsequent logical CPU numbers.
+	 */
+	if (early) {
+		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+		for (i = 0; i < info->configured; i++) {
+			core = &info->core[i];
+			if (core->core_id == core_id) {
+				nr += smp_add_core(core, &avail, true, early);
 				break;
+			}
 		}
 	}
+	for (i = 0; i < info->combined; i++) {
+		configured = i < info->configured;
+		nr += smp_add_core(&info->core[i], &avail, configured, early);
+	}
 	return nr;
 }
 
@@ -808,7 +836,7 @@ void __init smp_detect_cpus(void)
 
 	/* Add CPUs present at boot */
 	get_online_cpus();
-	__smp_rescan_cpus(info, 0);
+	__smp_rescan_cpus(info, true);
 	put_online_cpus();
 	memblock_free_early((unsigned long)info, sizeof(*info));
 }
@@ -1153,7 +1181,7 @@ int __ref smp_rescan_cpus(void)
 	smp_get_core_info(info, 0);
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	nr = __smp_rescan_cpus(info, 1);
+	nr = __smp_rescan_cpus(info, false);
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
 	kfree(info);

arch/s390/mm/init.c

@@ -291,10 +291,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 	vmem_remove_mapping(start, size);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/s390/purgatory/Makefile

@@ -15,8 +15,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
 
-$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
-	$(call if_changed_rule,cc_o_c)
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
 
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare