Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Catalin Marinas:

 - support for nr_cpus= command line argument (maxcpus was previously
   changed to allow secondary CPUs to be hot-plugged)

 - ARM PMU interrupt handling fix

 - fix potential TLB conflict in the hibernate code

 - improved handling of EL1 instruction aborts (better error reporting)

 - removal of useless jprobes code for stack saving/restoring

 - defconfig updates

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: defconfig: enable CONFIG_LOCALVERSION_AUTO
  arm64: defconfig: add options for virtualization and containers
  arm64: hibernate: handle allocation failures
  arm64: hibernate: avoid potential TLB conflict
  arm64: Handle el1 synchronous instruction aborts cleanly
  arm64: Remove stack duplicating code from jprobes
  drivers/perf: arm-pmu: Fix handling of SPI lacking "interrupt-affinity" property
  drivers/perf: arm-pmu: convert arm_pmu_mutex to spinlock
  arm64: Support hard limit of cpu count by nr_cpus

8 files changed, 136 insertions, 86 deletions

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 0555b7c..eadf485 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1,4 +1,3 @@
-# CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
@@ -15,10 +14,14 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_HUGETLB=y
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_NET_NS is not set
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_USER_NS=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
@@ -71,6 +74,7 @@ CONFIG_PREEMPT=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
+CONFIG_SECCOMP=y
 CONFIG_XEN=y
 CONFIG_KEXEC=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
@@ -84,10 +88,37 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
+CONFIG_IPV6=m
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NETFILTER_XT_TARGET_LOG=m
+CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_TARGET_MASQUERADE=m
+CONFIG_BRIDGE=m
+CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_VLAN_8021Q=m
+CONFIG_VLAN_8021Q_GVRP=y
+CONFIG_VLAN_8021Q_MVRP=y
 CONFIG_BPF_JIT=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
@@ -103,6 +134,7 @@ CONFIG_MTD=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=m
 CONFIG_VIRTIO_BLK=y
 CONFIG_SRAM=y
 # CONFIG_SCSI_PROC_FS is not set
@@ -120,7 +152,10 @@ CONFIG_SATA_SIL24=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
+CONFIG_MACVLAN=m
+CONFIG_MACVTAP=m
 CONFIG_TUN=y
+CONFIG_VETH=m
 CONFIG_VIRTIO_NET=y
 CONFIG_AMD_XGBE=y
 CONFIG_NET_XGENE=y
@@ -350,12 +385,16 @@ CONFIG_EXYNOS_ADC=y
 CONFIG_PWM_SAMSUNG=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_BTRFS_FS=m
+CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
 CONFIG_AUTOFS4_FS=y
-CONFIG_FUSE_FS=y
-CONFIG_CUSE=y
+CONFIG_FUSE_FS=m
+CONFIG_CUSE=m
+CONFIG_OVERLAY_FS=m
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 61b4915..1737aec 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -22,7 +22,6 @@
 
 #define __ARCH_WANT_KPROBES_INSN_SLOT
 #define MAX_INSN_SIZE			1
-#define MAX_STACK_SIZE			128
 
 #define flush_insn_slot(p)		do { } while (0)
 #define kretprobe_blacklist_size	0
@@ -47,7 +46,6 @@ struct kprobe_ctlblk {
 	struct prev_kprobe prev_kprobe;
 	struct kprobe_step_ctx ss_ctx;
 	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 96e4a2b..441420c 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -353,6 +353,8 @@ el1_sync:
 	lsr	x24, x1, #ESR_ELx_EC_SHIFT	// exception class
 	cmp	x24, #ESR_ELx_EC_DABT_CUR	// data abort in EL1
 	b.eq	el1_da
+	cmp	x24, #ESR_ELx_EC_IABT_CUR	// instruction abort in EL1
+	b.eq	el1_ia
 	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
 	b.eq	el1_undef
 	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
@@ -364,6 +366,11 @@ el1_sync:
 	cmp	x24, #ESR_ELx_EC_BREAKPT_CUR	// debug exception in EL1
 	b.ge	el1_dbg
 	b	el1_inv
+
+el1_ia:
+	/*
+	 * Fall through to the Data abort case
+	 */
 el1_da:
 	/*
 	 * Data abort handling
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 21ab5df..65d81f9 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -35,6 +35,7 @@
 #include <asm/sections.h>
 #include <asm/smp.h>
 #include <asm/suspend.h>
+#include <asm/sysreg.h>
 #include <asm/virt.h>
 
 /*
@@ -217,12 +218,22 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	set_pte(pte, __pte(virt_to_phys((void *)dst) |
 			 pgprot_val(PAGE_KERNEL_EXEC)));
 
-	/* Load our new page tables */
-	asm volatile("msr	ttbr0_el1, %0;"
-		     "isb;"
-		     "tlbi	vmalle1is;"
-		     "dsb	ish;"
-		     "isb" : : "r"(virt_to_phys(pgd)));
+	/*
+	 * Load our new page tables. A strict BBM approach requires that we
+	 * ensure that TLBs are free of any entries that may overlap with the
+	 * global mappings we are about to install.
+	 *
+	 * For a real hibernate/resume cycle TTBR0 currently points to a zero
+	 * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI
+	 * runtime services), while for a userspace-driven test_resume cycle it
+	 * points to userspace page tables (and we must point it at a zero page
+	 * ourselves). Elsewhere we only (un)install the idmap with preemption
+	 * disabled, so T0SZ should be as required regardless.
+	 */
+	cpu_set_reserved_ttbr0();
+	local_flush_tlb_all();
+	write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+	isb();
 
 	*phys_dst_addr = virt_to_phys((void *)dst);
 
@@ -394,6 +405,38 @@ int swsusp_arch_resume(void)
 					  void *, phys_addr_t, phys_addr_t);
 
 	/*
+	 * Restoring the memory image will overwrite the ttbr1 page tables.
+	 * Create a second copy of just the linear map, and use this when
+	 * restoring.
+	 */
+	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	if (!tmp_pg_dir) {
+		pr_err("Failed to allocate memory for temporary page tables.");
+		rc = -ENOMEM;
+		goto out;
+	}
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+	if (rc)
+		goto out;
+
+	/*
+	 * Since we only copied the linear map, we need to find restore_pblist's
+	 * linear map address.
+	 */
+	lm_restore_pblist = LMADDR(restore_pblist);
+
+	/*
+	 * We need a zero page that is zero before & after resume in order to
+	 * to break before make on the ttbr1 page tables.
+	 */
+	zero_page = (void *)get_safe_page(GFP_ATOMIC);
+	if (!zero_page) {
+		pr_err("Failed to allocate zero page.");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/*
 	 * Locate the exit code in the bottom-but-one page, so that *NULL
 	 * still has disastrous affects.
 	 */
@@ -419,27 +462,6 @@ int swsusp_arch_resume(void)
 	__flush_dcache_area(hibernate_exit, exit_size);
 
 	/*
-	 * Restoring the memory image will overwrite the ttbr1 page tables.
-	 * Create a second copy of just the linear map, and use this when
-	 * restoring.
-	 */
-	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
-	if (!tmp_pg_dir) {
-		pr_err("Failed to allocate memory for temporary page tables.");
-		rc = -ENOMEM;
-		goto out;
-	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
-	if (rc)
-		goto out;
-
-	/*
-	 * Since we only copied the linear map, we need to find restore_pblist's
-	 * linear map address.
-	 */
-	lm_restore_pblist = LMADDR(restore_pblist);
-
-	/*
 	 * KASLR will cause the el2 vectors to be in a different location in
 	 * the resumed kernel. Load hibernate's temporary copy into el2.
 	 *
@@ -453,12 +475,6 @@ int swsusp_arch_resume(void)
 		__hyp_set_vectors(el2_vectors);
 	}
 
-	/*
-	 * We need a zero page that is zero before & after resume in order to
-	 * to break before make on the ttbr1 page tables.
-	 */
-	zero_page = (void *)get_safe_page(GFP_ATOMIC);
-
 	hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1,
 		       resume_hdr.reenter_kernel, lm_restore_pblist,
 		       resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index bf97685..c6b0f40 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -41,18 +41,6 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 static void __kprobes
 post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
 
-static inline unsigned long min_stack_size(unsigned long addr)
-{
-	unsigned long size;
-
-	if (on_irq_stack(addr, raw_smp_processor_id()))
-		size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr;
-	else
-		size = (unsigned long)current_thread_info() + THREAD_START_SP - addr;
-
-	return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack));
-}
-
 static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
 {
 	/* prepare insn slot */
@@ -489,20 +477,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_ptr = kernel_stack_pointer(regs);
 
 	kcb->jprobe_saved_regs = *regs;
 	/*
-	 * As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
+	 * Since we can't be sure where in the stack frame "stacked"
+	 * pass-by-value arguments are stored we just don't try to
+	 * duplicate any of the stack. Do not use jprobes on functions that
+	 * use more than 64 bytes (after padding each to an 8 byte boundary)
+	 * of arguments, or pass individual arguments larger than 16 bytes.
 	 */
-	kasan_disable_current();
-	memcpy(kcb->jprobes_stack, (void *)stack_ptr,
-	       min_stack_size(stack_ptr));
-	kasan_enable_current();
 
 	instruction_pointer_set(regs, (unsigned long) jp->entry);
 	preempt_disable();
@@ -554,10 +537,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 	unpause_graph_tracing();
 	*regs = kcb->jprobe_saved_regs;
-	kasan_disable_current();
-	memcpy((void *)stack_addr, kcb->jprobes_stack,
-	       min_stack_size(stack_addr));
-	kasan_enable_current();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 76a6d92..d93d433 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -661,9 +661,9 @@ void __init smp_init_cpus(void)
 		acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
 				      acpi_parse_gic_cpu_interface, 0);
 
-	if (cpu_count > NR_CPUS)
-		pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",
-			cpu_count, NR_CPUS);
+	if (cpu_count > nr_cpu_ids)
+		pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n",
+			cpu_count, nr_cpu_ids);
 
 	if (!bootcpu_valid) {
 		pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
@@ -677,7 +677,7 @@ void __init smp_init_cpus(void)
 	 * with entries in cpu_logical_map while initializing the cpus.
 	 * If the cpu set-up fails, invalidate the cpu_logical_map entry.
 	 */
-	for (i = 1; i < NR_CPUS; i++) {
+	for (i = 1; i < nr_cpu_ids; i++) {
 		if (cpu_logical_map(i) != INVALID_HWID) {
 			if (smp_cpu_setup(i))
 				cpu_logical_map(i) = INVALID_HWID;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c8beaa0..05d2bd7 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -153,6 +153,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 }
 #endif
 
+static bool is_el1_instruction_abort(unsigned int esr)
+{
+	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
+}
+
 /*
  * The kernel tried to access some page that wasn't present.
  */
@@ -161,8 +166,9 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
 {
 	/*
 	 * Are we prepared to handle this kernel fault?
+	 * We are almost certainly not prepared to handle instruction faults.
 	 */
-	if (fixup_exception(regs))
+	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
 		return;
 
 	/*
@@ -267,7 +273,8 @@ static inline bool is_permission_fault(unsigned int esr)
 	unsigned int ec       = ESR_ELx_EC(esr);
 	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
 
-	return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
+	return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) ||
+	       (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -312,6 +319,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
 
+		if (is_el1_instruction_abort(esr))
+			die("Attempting to execute userspace memory", regs, esr);
+
 		if (!search_exception_tables(regs->pc))
 			die("Accessing user space memory outside uaccess.h routines", regs, esr);
 	}
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 6ccb994..c494613 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -688,7 +688,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 	return 0;
 }
 
-static DEFINE_MUTEX(arm_pmu_mutex);
+static DEFINE_SPINLOCK(arm_pmu_lock);
 static LIST_HEAD(arm_pmu_list);
 
 /*
@@ -701,7 +701,7 @@ static int arm_perf_starting_cpu(unsigned int cpu)
 {
 	struct arm_pmu *pmu;
 
-	mutex_lock(&arm_pmu_mutex);
+	spin_lock(&arm_pmu_lock);
 	list_for_each_entry(pmu, &arm_pmu_list, entry) {
 
 		if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
@@ -709,7 +709,7 @@ static int arm_perf_starting_cpu(unsigned int cpu)
 		if (pmu->reset)
 			pmu->reset(pmu);
 	}
-	mutex_unlock(&arm_pmu_mutex);
+	spin_unlock(&arm_pmu_lock);
 	return 0;
 }
 
@@ -821,9 +821,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	if (!cpu_hw_events)
 		return -ENOMEM;
 
-	mutex_lock(&arm_pmu_mutex);
+	spin_lock(&arm_pmu_lock);
 	list_add_tail(&cpu_pmu->entry, &arm_pmu_list);
-	mutex_unlock(&arm_pmu_mutex);
+	spin_unlock(&arm_pmu_lock);
 
 	err = cpu_pm_pmu_register(cpu_pmu);
 	if (err)
@@ -859,9 +859,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	return 0;
 
 out_unregister:
-	mutex_lock(&arm_pmu_mutex);
+	spin_lock(&arm_pmu_lock);
 	list_del(&cpu_pmu->entry);
-	mutex_unlock(&arm_pmu_mutex);
+	spin_unlock(&arm_pmu_lock);
 	free_percpu(cpu_hw_events);
 	return err;
 }
@@ -869,9 +869,9 @@ out_unregister:
 static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
 {
 	cpu_pm_pmu_unregister(cpu_pmu);
-	mutex_lock(&arm_pmu_mutex);
+	spin_lock(&arm_pmu_lock);
 	list_del(&cpu_pmu->entry);
-	mutex_unlock(&arm_pmu_mutex);
+	spin_unlock(&arm_pmu_lock);
 	free_percpu(cpu_pmu->hw_events);
 }
 
@@ -967,11 +967,12 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 
 	/* If we didn't manage to parse anything, try the interrupt affinity */
 	if (cpumask_weight(&pmu->supported_cpus) == 0) {
-		if (!using_spi) {
+		int irq = platform_get_irq(pdev, 0);
+
+		if (irq_is_percpu(irq)) {
 			/* If using PPIs, check the affinity of the partition */
-			int ret, irq;
+			int ret;
 
-			irq = platform_get_irq(pdev, 0);
 			ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus);
 			if (ret) {
 				kfree(irqs);