Import Upstream version 5.4.8

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1117,7 +1117,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r7, VCPU_GPR(R7)(r4)
 	bne	ret_to_ultra
 
-	lwz	r0, VCPU_CR(r4)
+	ld	r0, VCPU_CR(r4)
 	mtcr	r0
 
 	ld	r0, VCPU_GPR(R0)(r4)
@@ -1137,7 +1137,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
  *   R3 = UV_RETURN
  */
 ret_to_ultra:
-	lwz	r0, VCPU_CR(r4)
+	ld	r0, VCPU_CR(r4)
 	mtcr	r0
 
 	ld	r0, VCPU_GPR(R3)(r4)

arch/powerpc/lib/string_32.S

@@ -17,7 +17,7 @@ CACHELINE_BYTES = L1_CACHE_BYTES
 LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
-_GLOBAL(__clear_user)
+_GLOBAL(__arch_clear_user)
 /*
  * Use dcbz on the complete cache lines in the destination
  * to set them to zero.  This requires that the destination
@@ -87,4 +87,4 @@ _GLOBAL(__clear_user)
 	EX_TABLE(8b, 91b)
 	EX_TABLE(9b, 91b)
 
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)

arch/powerpc/lib/string_64.S

@@ -17,7 +17,7 @@ PPC64_CACHES:
 	.section	".text"
 
 /**
- * __clear_user: - Zero a block of memory in user space, with less checking.
+ * __arch_clear_user: - Zero a block of memory in user space, with less checking.
  * @to:   Destination address, in user space.
  * @n:    Number of bytes to zero.
  *
@@ -58,7 +58,7 @@ err3;	stb	r0,0(r3)
 	mr	r3,r4
 	blr
 
-_GLOBAL_TOC(__clear_user)
+_GLOBAL_TOC(__arch_clear_user)
 	cmpdi	r4,32
 	neg	r6,r3
 	li	r0,0
@@ -181,4 +181,4 @@ err1;	dcbz	0,r3
 	cmpdi	r4,32
 	blt	.Lshort_clear
 	b	.Lmedium_clear
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)

arch/powerpc/mm/book3s64/hash_utils.c

@@ -294,10 +294,18 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
 					       HPTE_V_BOLTED, psize, psize,
 					       ssize);
-
+		if (ret == -1) {
+			/* Try to remove a non bolted entry */
+			ret = mmu_hash_ops.hpte_remove(hpteg);
+			if (ret != -1)
+				ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
+							       HPTE_V_BOLTED, psize, psize,
+							       ssize);
+		}
 		if (ret < 0)
 			break;
 
+		cond_resched();
 #ifdef CONFIG_DEBUG_PAGEALLOC
 		if (debug_pagealloc_enabled() &&
 			(paddr >> PAGE_SHIFT) < linear_map_hash_count)

arch/powerpc/platforms/pseries/cmm.c

@@ -411,6 +411,10 @@ static struct bus_type cmm_subsys = {
 	.dev_name = "cmm",
 };
 
+static void cmm_release_device(struct device *dev)
+{
+}
+
 /**
  * cmm_sysfs_register - Register with sysfs
  *
@@ -426,6 +430,7 @@ static int cmm_sysfs_register(struct device *dev)
 
 	dev->id = 0;
 	dev->bus = &cmm_subsys;
+	dev->release = cmm_release_device;
 
 	if ((rc = device_register(dev)))
 		goto subsys_unregister;

arch/powerpc/platforms/pseries/papr_scm.c

@@ -152,7 +152,7 @@ static int papr_scm_meta_get(struct papr_scm_priv *p,
 	int len, read;
 	int64_t ret;
 
-	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
 		return -EINVAL;
 
 	for (len = hdr->in_length; len; len -= read) {
@@ -206,7 +206,7 @@ static int papr_scm_meta_set(struct papr_scm_priv *p,
 	__be64 data_be;
 	int64_t ret;
 
-	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
 		return -EINVAL;
 
 	for (len = hdr->in_length; len; len -= wrote) {

arch/powerpc/tools/relocs_check.sh

@@ -20,7 +20,7 @@ objdump="$1"
 vmlinux="$2"
 
 bad_relocs=$(
-"$objdump" -R "$vmlinux" |
+$objdump -R "$vmlinux" |
 	# Only look at relocation lines.
 	grep -E '\<R_' |
 	# These relocations are okay

arch/powerpc/tools/unrel_branch_check.sh

@@ -18,14 +18,14 @@ vmlinux="$2"
 #__end_interrupts should be located within the first 64K
 
 end_intr=0x$(
-"$objdump" -R "$vmlinux" -d --start-address=0xc000000000000000		\
+$objdump -R "$vmlinux" -d --start-address=0xc000000000000000           \
 		 --stop-address=0xc000000000010000 |
 grep '\<__end_interrupts>:' |
 awk '{print $1}'
 )
 
 BRANCHES=$(
-"$objdump" -R "$vmlinux" -D --start-address=0xc000000000000000		\
+$objdump -R "$vmlinux" -D --start-address=0xc000000000000000           \
 		--stop-address=${end_intr} |
 grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" |
 grep -v '\<__start_initialization_multiplatform>' |

arch/s390/crypto/sha_common.c

@@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bsize = crypto_shash_blocksize(desc->tfm);
 	u64 bits;
-	unsigned int n, mbl_offset;
+	unsigned int n;
+	int mbl_offset;
 
 	n = ctx->count % bsize;
 	bits = ctx->count * 8;
-	mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32);
+	mbl_offset = s390_crypto_shash_parmsize(ctx->func);
 	if (mbl_offset < 0)
 		return -EINVAL;
 
+	mbl_offset = mbl_offset / sizeof(u32);
+
 	/* set total msg bit length (mbl) in CPACF parmblock */
 	switch (ctx->func) {
 	case CPACF_KLMD_SHA_1:

arch/s390/include/asm/pgalloc.h

@@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
 		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 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 		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 pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 
 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);
 }

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
@@ -186,15 +187,18 @@ extern unsigned char tod_clock_base[16] __aligned(8);
 /**
  * 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;
 }
 
 /**

arch/s390/kernel/dis.c

@@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 				ptr += sprintf(ptr, "%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
 				ptr += sprintf(ptr, "%%v%i", value);
-			else if (operand->flags & OPERAND_PCREL)
-				ptr += sprintf(ptr, "%lx", (signed int) value
-								      + addr);
-			else if (operand->flags & OPERAND_SIGNED)
+			else if (operand->flags & OPERAND_PCREL) {
+				void *pcrel = (void *)((int)value + addr);
+
+				ptr += sprintf(ptr, "%px", pcrel);
+			} else if (operand->flags & OPERAND_SIGNED)
 				ptr += sprintf(ptr, "%i", value);
 			else
 				ptr += sprintf(ptr, "%u", value);
@@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs)
 		else
 			*ptr++ = ' ';
 		addr = regs->psw.addr + start - 32;
-		ptr += sprintf(ptr, "%016lx: ", addr);
+		ptr += sprintf(ptr, "%px: ", (void *)addr);
 		if (start + opsize >= end)
 			break;
 		for (i = 0; i < opsize; i++)
@@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len)
 		opsize = insn_length(*code);
 		if (opsize > len)
 			break;
-		ptr += sprintf(ptr, "%p: ", code);
+		ptr += sprintf(ptr, "%px: ", code);
 		for (i = 0; i < opsize; i++)
 			ptr += sprintf(ptr, "%02x", code[i]);
 		*ptr++ = '\t';

arch/s390/kernel/machine_kexec.c

@@ -164,7 +164,9 @@ static bool kdump_csum_valid(struct kimage *image)
 #ifdef CONFIG_CRASH_DUMP
 	int rc;
 
+	preempt_disable();
 	rc = CALL_ON_STACK(do_start_kdump, S390_lowcore.nodat_stack, 1, image);
+	preempt_enable();
 	return rc == 0;
 #else
 	return false;

arch/s390/kernel/perf_cpum_cf.c

@@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = {
 	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
 };
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct hw_perf_event *hwc = &event->hw;
@@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	int err = 0;
 	u64 ev;
 
-	switch (attr->type) {
+	switch (type) {
 	case PERF_TYPE_RAW:
 		/* Raw events are used to access counters directly,
 		 * hence do not permit excludes */
@@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static int cpumf_pmu_event_init(struct perf_event *event)
 {
+	unsigned int type = event->attr.type;
 	int err;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-	case PERF_TYPE_RAW:
-		err = __hw_perf_event_init(event);
-		break;
-	default:
+	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
+		err = __hw_perf_event_init(event, type);
+	else if (event->pmu->type == type)
+		/* Registered as unknown PMU */
+		err = __hw_perf_event_init(event, PERF_TYPE_RAW);
+	else
 		return -ENOENT;
-	}
 
 	if (unlikely(err) && event->destroy)
 		event->destroy(event);
@@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void)
 		return -ENODEV;
 
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
-	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1);
 	if (rc)
 		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
 	return rc;

arch/s390/kernel/perf_cpum_cf_diag.c

@@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event)
 	int err = -ENOENT;
 
 	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d config %#llx "
+			    "%s event %p cpu %d config %#llx type:%u "
 			    "sample_type %#llx cf_diag_events %d\n", __func__,
-			    event, event->cpu, attr->config, attr->sample_type,
-			    atomic_read(&cf_diag_events));
+			    event, event->cpu, attr->config, event->pmu->type,
+			    attr->sample_type, atomic_read(&cf_diag_events));
 
 	if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
-	    event->attr.type != PERF_TYPE_RAW)
+	    event->attr.type != event->pmu->type)
 		goto out;
 
 	/* Raw events are used to access counters directly,
@@ -693,7 +693,7 @@ static int __init cf_diag_init(void)
 	}
 	debug_register_view(cf_diag_dbg, &debug_sprintf_view);
 
-	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1);
 	if (rc) {
 		debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
 		debug_unregister(cf_diag_dbg);

arch/s390/kernel/perf_cpum_sf.c

@@ -193,7 +193,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 				   unsigned long num_sdb, gfp_t gfp_flags)
 {
 	int i, rc;
-	unsigned long *new, *tail;
+	unsigned long *new, *tail, *tail_prev = NULL;
 
 	if (!sfb->sdbt || !sfb->tail)
 		return -EINVAL;
@@ -232,6 +232,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 			sfb->num_sdbt++;
 			/* Link current page to tail of chain */
 			*tail = (unsigned long)(void *) new + 1;
+			tail_prev = tail;
 			tail = new;
 		}
 
@@ -241,10 +242,22 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 		 * issue, a new realloc call (if required) might succeed.
 		 */
 		rc = alloc_sample_data_block(tail, gfp_flags);
-		if (rc)
+		if (rc) {
+			/* Undo last SDBT. An SDBT with no SDB at its first
+			 * entry but with an SDBT entry instead can not be
+			 * handled by the interrupt handler code.
+			 * Avoid this situation.
+			 */
+			if (tail_prev) {
+				sfb->num_sdbt--;
+				free_page((unsigned long) new);
+				tail = tail_prev;
+			}
 			break;
+		}
 		sfb->num_sdb++;
 		tail++;
+		tail_prev = new = NULL;	/* Allocated at least one SBD */
 	}
 
 	/* Link sampling buffer to its origin */

arch/s390/kernel/perf_event.c

@@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	struct unwind_state state;
+	unsigned long addr;
 
-	unwind_for_each_frame(&state, current, regs, 0)
-		perf_callchain_store(entry, state.ip);
+	unwind_for_each_frame(&state, current, regs, 0) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
 }
 
 /* Perf definitions for PMU event attributes in sysfs */

arch/s390/kernel/unwind_bc.c

@@ -60,6 +60,11 @@ bool unwind_next_frame(struct unwind_state *state)
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 		reliable = false;
 		regs = NULL;
+		if (!__kernel_text_address(ip)) {
+			/* skip bogus %r14 */
+			state->regs = NULL;
+			return unwind_next_frame(state);
+		}
 	} else {
 		sf = (struct stack_frame *) state->sp;
 		sp = READ_ONCE_NOCHECK(sf->back_chain);

arch/s390/mm/maccess.c

@@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size)
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
 }
 
-static int __memcpy_real(void *dest, void *src, size_t count)
+static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
 {
 	register unsigned long _dest asm("2") = (unsigned long) dest;
 	register unsigned long _len1 asm("3") = (unsigned long) count;
@@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count)
 	return rc;
 }
 
-static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
-				  unsigned long count)
+static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest,
+							unsigned long src,
+							unsigned long count)
 {
 	int irqs_disabled, rc;
 	unsigned long flags;
 
 	if (!count)
 		return 0;
-	flags = __arch_local_irq_stnsm(0xf8UL);
+	flags = arch_local_irq_save();
 	irqs_disabled = arch_irqs_disabled_flags(flags);
 	if (!irqs_disabled)
 		trace_hardirqs_off();
+	__arch_local_irq_stnsm(0xf8); // disable DAT
 	rc = __memcpy_real((void *) dest, (void *) src, (size_t) count);
+	if (flags & PSW_MASK_DAT)
+		__arch_local_irq_stosm(0x04); // enable DAT
 	if (!irqs_disabled)
 		trace_hardirqs_on();
 	__arch_local_irq_ssm(flags);
@@ -115,9 +119,15 @@ static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
  */
 int memcpy_real(void *dest, void *src, size_t count)
 {
-	if (S390_lowcore.nodat_stack != 0)
-		return CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack,
-				     3, dest, src, count);
+	int rc;
+
+	if (S390_lowcore.nodat_stack != 0) {
+		preempt_disable();
+		rc = CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack, 3,
+				   dest, src, count);
+		preempt_enable();
+		return rc;
+	}
 	/*
 	 * This is a really early memcpy_real call, the stacks are
 	 * not set up yet. Just call _memcpy_real on the early boot

arch/s390/net/bpf_jit_comp.c

@@ -23,6 +23,7 @@
 #include <linux/filter.h>
 #include <linux/init.h>
 #include <linux/bpf.h>
+#include <linux/mm.h>
 #include <asm/cacheflush.h>
 #include <asm/dis.h>
 #include <asm/facility.h>
@@ -1369,7 +1370,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 
 	memset(&jit, 0, sizeof(jit));
-	jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
+	jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
 	if (jit.addrs == NULL) {
 		fp = orig_fp;
 		goto out;
@@ -1422,7 +1423,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	if (!fp->is_func || extra_pass) {
 		bpf_prog_fill_jited_linfo(fp, jit.addrs + 1);
 free_addrs:
-		kfree(jit.addrs);
+		kvfree(jit.addrs);
 		kfree(jit_data);
 		fp->aux->jit_data = NULL;
 	}