Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 68d362f..c72c179 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -27,6 +27,7 @@
 
 extern char ftrace_graph_caller_end;
 extern unsigned long ftrace_plt;
+extern void *ftrace_func;
 
 struct dyn_arch_ftrace { };
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index abe6026..4d59d11 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -31,12 +31,12 @@
 #define KVM_USER_MEM_SLOTS 32
 
 /*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
  */
 #define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
 #define KVM_HALT_POLL_NS_DEFAULT 50000
 
 /* s390-specific vcpu->requests bit members */
@@ -873,6 +873,7 @@
 	atomic64_t cmma_dirty_pages;
 	/* subset of available cpu features enabled by user space */
 	DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
+	/* indexed by vcpu_idx */
 	DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS);
 	struct kvm_s390_gisa_interrupt gisa_int;
 };
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 237ee0c..612ed3c 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -141,7 +141,9 @@
 
 	/* br %r1 trampoline */
 	__u16	br_r1_trampoline;		/* 0x0400 */
-	__u8	pad_0x0402[0x0e00-0x0402];	/* 0x0402 */
+	__u32	return_lpswe;			/* 0x0402 */
+	__u32	return_mcck_lpswe;		/* 0x0406 */
+	__u8	pad_0x040a[0x0e00-0x040a];	/* 0x040a */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h
index 35f8cbe..c759dcf 100644
--- a/arch/s390/include/asm/numa.h
+++ b/arch/s390/include/asm/numa.h
@@ -17,7 +17,6 @@
 
 void numa_setup(void);
 int numa_pfn_to_nid(unsigned long pfn);
-int __node_distance(int a, int b);
 void numa_update_cpu_topology(void);
 
 extern cpumask_t node_to_cpumask_map[MAX_NUMNODES];
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 823578c..e399102 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -33,6 +33,8 @@
 #define ARCH_HAS_PREPARE_HUGEPAGE
 #define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH
 
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+
 #include <asm/setup.h>
 #ifndef __ASSEMBLY__
 
@@ -40,7 +42,7 @@
 
 static inline void storage_key_init_range(unsigned long start, unsigned long end)
 {
-	if (PAGE_DEFAULT_KEY)
+	if (PAGE_DEFAULT_KEY != 0)
 		__storage_key_init_range(start, end);
 }
 
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index a2399ef..6087a4e 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -183,7 +183,7 @@
 /* CLP */
 int clp_scan_pci_devices(void);
 int clp_rescan_pci_devices(void);
-int clp_rescan_pci_devices_simple(void);
+int clp_rescan_pci_devices_simple(u32 *fid);
 int clp_add_pci_device(u32, u32, int);
 int clp_enable_fh(struct zpci_dev *, u8);
 int clp_disable_fh(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cd060b5..e4dc64c 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -8,6 +8,10 @@
 #include <linux/slab.h>
 #include <asm/pci_insn.h>
 
+/* I/O size constraints */
+#define ZPCI_MAX_READ_SIZE	8
+#define ZPCI_MAX_WRITE_SIZE	128
+
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
 #define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
@@ -140,7 +144,8 @@
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64) dst, n, 8);
+					       (u64) dst, n,
+					       ZPCI_MAX_READ_SIZE);
 		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
@@ -161,7 +166,8 @@
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64) src, n, 128);
+					       (u64) src, n,
+					       ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = zpci_write_block(dst, src, size);
 		else
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 50b4ce8..918f0ba 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -29,7 +29,7 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\
@@ -37,7 +37,7 @@
 		new__ = old__ op (val);					\
 		prev__ = cmpxchg(ptr__, old__, new__);			\
 	} while (prev__ != old__);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	new__;								\
 })
 
@@ -68,7 +68,7 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
@@ -84,7 +84,7 @@
 			: [val__] "d" (val__)				\
 			: "cc");					\
 	}								\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)
@@ -95,14 +95,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();						\
 	old__ + val__;							\
 })
 
@@ -114,14 +114,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_and_4(pcp, val)	arch_this_cpu_to_op(pcp, val, "lan")
@@ -136,10 +136,10 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
@@ -152,10 +152,10 @@
 ({									\
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
@@ -171,11 +171,11 @@
 	typeof(pcp1) *p1__;						\
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	p1__ = raw_cpu_ptr(&(pcp1));					\
 	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index bccb8f4..77606c4 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -56,7 +56,12 @@
 		crst_table_init(table, _REGION2_ENTRY_EMPTY);
 	return (p4d_t *) table;
 }
-#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!mm_p4d_folded(mm))
+		crst_table_free(mm, (unsigned long *) p4d);
+}
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
@@ -65,7 +70,12 @@
 		crst_table_init(table, _REGION3_ENTRY_EMPTY);
 	return (pud_t *) table;
 }
-#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (!mm_pud_folded(mm))
+		crst_table_free(mm, (unsigned long *) pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
@@ -83,6 +93,8 @@
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	crst_table_free(mm, (unsigned long *) pmd);
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ff98d7..5ce5869 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -756,6 +756,12 @@
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
 static inline int pmd_dirty(pmd_t pmd)
 {
 	int dirty = 1;
@@ -1173,8 +1179,6 @@
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t entry)
 {
-	if (!MACHINE_HAS_NX)
-		pte_val(entry) &= ~_PAGE_NOEXEC;
 	if (pte_present(entry))
 		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm))
@@ -1191,6 +1195,8 @@
 {
 	pte_t __pte;
 	pte_val(__pte) = physpage + pgprot_val(pgprot);
+	if (!MACHINE_HAS_NX)
+		pte_val(__pte) &= ~_PAGE_NOEXEC;
 	return pte_mkyoung(__pte);
 }
 
@@ -1241,26 +1247,46 @@
 #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address)
 {
-	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
-		return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
-	return (p4d_t *) pgd;
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+		return (p4d_t *) pgd_deref(pgd) + p4d_index(address);
+	return (p4d_t *) pgdp;
+}
+#define p4d_offset_lockless p4d_offset_lockless
+
+static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address)
+{
+	return p4d_offset_lockless(pgdp, *pgdp, address);
 }
 
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address)
 {
-	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
-		return (pud_t *) p4d_deref(*p4d) + pud_index(address);
-	return (pud_t *) p4d;
+	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+		return (pud_t *) p4d_deref(p4d) + pud_index(address);
+	return (pud_t *) p4dp;
 }
+#define pud_offset_lockless pud_offset_lockless
 
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address)
 {
-	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
-		return (pmd_t *) pud_deref(*pud) + pmd_index(address);
-	return (pmd_t *) pud;
+	return pud_offset_lockless(p4dp, *p4dp, address);
 }
+#define pud_offset pud_offset
+
+static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address)
+{
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+		return (pmd_t *) pud_deref(pud) + pmd_index(address);
+	return (pmd_t *) pudp;
+}
+#define pmd_offset_lockless pmd_offset_lockless
+
+static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address)
+{
+	return pmd_offset_lockless(pudp, *pudp, address);
+}
+#define pmd_offset pmd_offset
 
 static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
 {
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 51a0e4a..48d6ccd 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -162,6 +162,7 @@
 #define INIT_THREAD {							\
 	.ksp = sizeof(init_stack) + (unsigned long) &init_stack,	\
 	.fpu.regs = (void *) init_task.thread.fpu.fprs,			\
+	.last_break = 1,						\
 }
 
 /*
@@ -214,7 +215,7 @@
 	return sp;
 }
 
-static __no_kasan_or_inline unsigned short stap(void)
+static __always_inline unsigned short stap(void)
 {
 	unsigned short cpu_address;
 
@@ -253,7 +254,7 @@
  * Set PSW mask to specified value, while leaving the
  * PSW addr pointing to the next instruction.
  */
-static __no_kasan_or_inline void __load_psw_mask(unsigned long mask)
+static __always_inline void __load_psw_mask(unsigned long mask)
 {
 	unsigned long addr;
 	psw_t psw;
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index e3f238e..4f35b10 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -227,7 +227,7 @@
  * @sbal: absolute SBAL address
  */
 struct sl_element {
-	unsigned long sbal;
+	u64 sbal;
 } __attribute__ ((packed));
 
 /**
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 6dc6c4f..e6a5007 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -8,6 +8,7 @@
 
 #include <linux/bits.h>
 #include <uapi/asm/setup.h>
+#include <linux/build_bug.h>
 
 #define EP_OFFSET		0x10008
 #define EP_STRING		"S390EP"
@@ -38,6 +39,7 @@
 #define MACHINE_FLAG_NX		BIT(15)
 #define MACHINE_FLAG_GS		BIT(16)
 #define MACHINE_FLAG_SCC	BIT(17)
+#define MACHINE_FLAG_PCI_MIO	BIT(18)
 
 #define LPP_MAGIC		BIT(31)
 #define LPP_PID_MASK		_AC(0xffffffff, UL)
@@ -105,6 +107,7 @@
 #define MACHINE_HAS_NX		(S390_lowcore.machine_flags & MACHINE_FLAG_NX)
 #define MACHINE_HAS_GS		(S390_lowcore.machine_flags & MACHINE_FLAG_GS)
 #define MACHINE_HAS_SCC		(S390_lowcore.machine_flags & MACHINE_FLAG_SCC)
+#define MACHINE_HAS_PCI_MIO	(S390_lowcore.machine_flags & MACHINE_FLAG_PCI_MIO)
 
 /*
  * Console mode. Override with conmode=
@@ -157,6 +160,12 @@
 	return __kaslr_offset;
 }
 
+static inline u32 gen_lpswe(unsigned long addr)
+{
+	BUILD_BUG_ON(addr > 0xfff);
+	return 0xb2b20000 | addr;
+}
+
 #else /* __ASSEMBLY__ */
 
 #define IPL_DEVICE	(IPL_DEVICE_OFFSET)
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 0ae4bbf..e192681 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -79,12 +79,16 @@
 	CALL_ARGS_4(arg1, arg2, arg3, arg4);				\
 	register unsigned long r4 asm("6") = (unsigned long)(arg5)
 
-#define CALL_FMT_0 "=&d" (r2) :
-#define CALL_FMT_1 "+&d" (r2) :
-#define CALL_FMT_2 CALL_FMT_1 "d" (r3),
-#define CALL_FMT_3 CALL_FMT_2 "d" (r4),
-#define CALL_FMT_4 CALL_FMT_3 "d" (r5),
-#define CALL_FMT_5 CALL_FMT_4 "d" (r6),
+/*
+ * To keep this simple mark register 2-6 as being changed (volatile)
+ * by the called function, even though register 6 is saved/nonvolatile.
+ */
+#define CALL_FMT_0 "=&d" (r2)
+#define CALL_FMT_1 "+&d" (r2)
+#define CALL_FMT_2 CALL_FMT_1, "+&d" (r3)
+#define CALL_FMT_3 CALL_FMT_2, "+&d" (r4)
+#define CALL_FMT_4 CALL_FMT_3, "+&d" (r5)
+#define CALL_FMT_5 CALL_FMT_4, "+&d" (r6)
 
 #define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
 #define CALL_CLOBBER_4 CALL_CLOBBER_5
@@ -105,10 +109,118 @@
 		"	brasl	14,%[_fn]\n"				\
 		"	la	15,0(%[_prev])\n"			\
 		: [_prev] "=&a" (prev), CALL_FMT_##nr			\
-		  [_stack] "a" (stack),					\
+		: [_stack] "a" (stack),					\
 		  [_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
 		  [_fn] "X" (fn) : CALL_CLOBBER_##nr);			\
 	r2;								\
 })
 
+#define CALL_LARGS_0(...)						\
+	long dummy = 0
+#define CALL_LARGS_1(t1, a1)						\
+	long arg1  = (long)(t1)(a1)
+#define CALL_LARGS_2(t1, a1, t2, a2)					\
+	CALL_LARGS_1(t1, a1);						\
+	long arg2 = (long)(t2)(a2)
+#define CALL_LARGS_3(t1, a1, t2, a2, t3, a3)				\
+	CALL_LARGS_2(t1, a1, t2, a2);					\
+	long arg3 = (long)(t3)(a3)
+#define CALL_LARGS_4(t1, a1, t2, a2, t3, a3, t4, a4)			\
+	CALL_LARGS_3(t1, a1, t2, a2, t3, a3);				\
+	long arg4  = (long)(t4)(a4)
+#define CALL_LARGS_5(t1, a1, t2, a2, t3, a3, t4, a4, t5, a5)		\
+	CALL_LARGS_4(t1, a1, t2, a2, t3, a3, t4, a4);			\
+	long arg5 = (long)(t5)(a5)
+
+#define CALL_REGS_0							\
+	register long r2 asm("2") = dummy
+#define CALL_REGS_1							\
+	register long r2 asm("2") = arg1
+#define CALL_REGS_2							\
+	CALL_REGS_1;							\
+	register long r3 asm("3") = arg2
+#define CALL_REGS_3							\
+	CALL_REGS_2;							\
+	register long r4 asm("4") = arg3
+#define CALL_REGS_4							\
+	CALL_REGS_3;							\
+	register long r5 asm("5") = arg4
+#define CALL_REGS_5							\
+	CALL_REGS_4;							\
+	register long r6 asm("6") = arg5
+
+#define CALL_TYPECHECK_0(...)
+#define CALL_TYPECHECK_1(t, a, ...)					\
+	typecheck(t, a)
+#define CALL_TYPECHECK_2(t, a, ...)					\
+	CALL_TYPECHECK_1(__VA_ARGS__);					\
+	typecheck(t, a)
+#define CALL_TYPECHECK_3(t, a, ...)					\
+	CALL_TYPECHECK_2(__VA_ARGS__);					\
+	typecheck(t, a)
+#define CALL_TYPECHECK_4(t, a, ...)					\
+	CALL_TYPECHECK_3(__VA_ARGS__);					\
+	typecheck(t, a)
+#define CALL_TYPECHECK_5(t, a, ...)					\
+	CALL_TYPECHECK_4(__VA_ARGS__);					\
+	typecheck(t, a)
+
+#define CALL_PARM_0(...) void
+#define CALL_PARM_1(t, a, ...) t
+#define CALL_PARM_2(t, a, ...) t, CALL_PARM_1(__VA_ARGS__)
+#define CALL_PARM_3(t, a, ...) t, CALL_PARM_2(__VA_ARGS__)
+#define CALL_PARM_4(t, a, ...) t, CALL_PARM_3(__VA_ARGS__)
+#define CALL_PARM_5(t, a, ...) t, CALL_PARM_4(__VA_ARGS__)
+#define CALL_PARM_6(t, a, ...) t, CALL_PARM_5(__VA_ARGS__)
+
+/*
+ * Use call_on_stack() to call a function switching to a specified
+ * stack. Proper sign and zero extension of function arguments is
+ * done. Usage:
+ *
+ * rc = call_on_stack(nr, stack, rettype, fn, t1, a1, t2, a2, ...)
+ *
+ * - nr specifies the number of function arguments of fn.
+ * - stack specifies the stack to be used.
+ * - fn is the function to be called.
+ * - rettype is the return type of fn.
+ * - t1, a1, ... are pairs, where t1 must match the type of the first
+ *   argument of fn, t2 the second, etc. a1 is the corresponding
+ *   first function argument (not name), etc.
+ */
+#define call_on_stack(nr, stack, rettype, fn, ...)			\
+({									\
+	rettype (*__fn)(CALL_PARM_##nr(__VA_ARGS__)) = fn;		\
+	unsigned long frame = current_frame_address();			\
+	unsigned long __stack = stack;					\
+	unsigned long prev;						\
+	CALL_LARGS_##nr(__VA_ARGS__);					\
+	CALL_REGS_##nr;							\
+									\
+	CALL_TYPECHECK_##nr(__VA_ARGS__);				\
+	asm volatile(							\
+		"	lgr	%[_prev],15\n"				\
+		"	lg	15,%[_stack]\n"				\
+		"	stg	%[_frame],%[_bc](15)\n"			\
+		"	brasl	14,%[_fn]\n"				\
+		"	lgr	15,%[_prev]\n"				\
+		: [_prev] "=&d" (prev), CALL_FMT_##nr			\
+		: [_stack] "R" (__stack),				\
+		  [_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
+		  [_frame] "d" (frame),					\
+		  [_fn] "X" (__fn) : CALL_CLOBBER_##nr);		\
+	(rettype)r2;							\
+})
+
+#define CALL_ON_STACK_NORETURN(fn, stack)				\
+({									\
+	asm volatile(							\
+		"	la	15,0(%[_stack])\n"			\
+		"	xc	%[_bc](8,15),%[_bc](15)\n"		\
+		"	brasl	14,%[_fn]\n"				\
+		::[_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
+		  [_stack] "a" (stack), [_fn] "X" (fn));		\
+	BUG();								\
+})
+
 #endif /* _ASM_S390_STACKTRACE_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index f073292..d9d5de0 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -33,7 +33,17 @@
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0;
+	unsigned long error = regs->gprs[2];
+#ifdef CONFIG_COMPAT
+	if (test_tsk_thread_flag(task, TIF_31BIT)) {
+		/*
+		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+		 * and will match correctly in comparisons.
+		 */
+		error = (long)(int)error;
+	}
+#endif
+	return IS_ERR_VALUE(error) ? error : 0;
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 64539c2..b6a4ce9 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,8 +10,9 @@
 #ifndef _ASM_S390_TIMEX_H
 #define _ASM_S390_TIMEX_H
 
-#include <asm/lowcore.h>
+#include <linux/preempt.h>
 #include <linux/time64.h>
+#include <asm/lowcore.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -154,7 +155,7 @@
 
 static inline unsigned long long get_tod_clock(void)
 {
-	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+	char clk[STORE_CLOCK_EXT_SIZE];
 
 	get_tod_clock_ext(clk);
 	return *((unsigned long long *)&clk[1]);
@@ -186,15 +187,18 @@
 /**
  * get_clock_monotonic - returns current time in clock rate units
  *
- * The caller must ensure that preemption is disabled.
  * The clock and tod_clock_base get changed via stop_machine.
- * Therefore preemption must be disabled when calling this
- * function, otherwise the returned value is not guaranteed to
- * be monotonic.
+ * Therefore preemption must be disabled, otherwise the returned
+ * value is not guaranteed to be monotonic.
  */
 static inline unsigned long long get_tod_clock_monotonic(void)
 {
-	return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	unsigned long long tod;
+
+	preempt_disable_notrace();
+	tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	preempt_enable_notrace();
+	return tod;
 }
 
 /**
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index cca406f..ef9dd25 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -83,8 +83,6 @@
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 
-#define node_distance(a, b) __node_distance(a, b)
-
 #else /* !CONFIG_NUMA */
 
 #define numa_node_id numa_node_id
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index a470f1f..3244388 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -276,6 +276,6 @@
 }
 
 int copy_to_user_real(void __user *dest, void *src, unsigned long count);
-void s390_kernel_write(void *dst, const void *src, size_t size);
+void *s390_kernel_write(void *dst, const void *src, size_t size);
 
 #endif /* __S390_UACCESS_H */
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 169d760..f3ba84f 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -36,6 +36,7 @@
 	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
 	__u32 ts_dir;			/* TOD steering direction	0x64 */
 	__u64 ts_end;			/* TOD steering end		0x68 */
+	__u32 hrtimer_res;		/* hrtimer resolution		0x70 */
 };
 
 struct vdso_per_cpu_data {