19 files changed, 467 insertions, 102 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8857ec3b97eb..2a5bb4f29cfe 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -47,7 +47,7 @@ config ARCH_SUPPORTS_UPROBES
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
-	default 0x18000000000000
+	default 0x1C000000000000
 
 config S390
 	def_bool y
@@ -194,6 +194,7 @@ config S390
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_RSEQ
 	select HAVE_SAMPLE_FTRACE_DIRECT
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 69c45f600273..609e3697324b 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -77,10 +77,12 @@ KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y)
 KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y)
 
 ifneq ($(call cc-option,-mstack-size=8192 -mstack-guard=128),)
-cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE)
-ifeq ($(call cc-option,-mstack-size=8192),)
-cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
-endif
+  CC_FLAGS_CHECK_STACK := -mstack-size=$(STACK_SIZE)
+  ifeq ($(call cc-option,-mstack-size=8192),)
+    CC_FLAGS_CHECK_STACK += -mstack-guard=$(CONFIG_STACK_GUARD)
+  endif
+  export CC_FLAGS_CHECK_STACK
+  cflags-$(CONFIG_CHECK_STACK) += $(CC_FLAGS_CHECK_STACK)
 endif
 
 ifdef CONFIG_EXPOLINE
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 7571dee72a0c..1aa11a8f57dd 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -149,82 +149,56 @@ static void setup_ident_map_size(unsigned long max_physmem_end)
 
 static void setup_kernel_memory_layout(void)
 {
-	bool vmalloc_size_verified = false;
-	unsigned long vmemmap_off;
-	unsigned long vspace_left;
+	unsigned long vmemmap_start;
 	unsigned long rte_size;
 	unsigned long pages;
-	unsigned long vmax;
 
 	pages = ident_map_size / PAGE_SIZE;
 	/* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */
 	vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);
 
 	/* choose kernel address space layout: 4 or 3 levels. */
-	vmemmap_off = round_up(ident_map_size, _REGION3_SIZE);
+	vmemmap_start = round_up(ident_map_size, _REGION3_SIZE);
 	if (IS_ENABLED(CONFIG_KASAN) ||
 	    vmalloc_size > _REGION2_SIZE ||
-	    vmemmap_off + vmemmap_size + vmalloc_size + MODULES_LEN > _REGION2_SIZE)
-		vmax = _REGION1_SIZE;
-	else
-		vmax = _REGION2_SIZE;
-
-	/* keep vmemmap_off aligned to a top level region table entry */
-	rte_size = vmax == _REGION1_SIZE ? _REGION2_SIZE : _REGION3_SIZE;
-	MODULES_END = vmax;
-	if (is_prot_virt_host()) {
-		/*
-		 * forcing modules and vmalloc area under the ultravisor
-		 * secure storage limit, so that any vmalloc allocation
-		 * we do could be used to back secure guest storage.
-		 */
-		adjust_to_uv_max(&MODULES_END);
-	}
-
-#ifdef CONFIG_KASAN
-	if (MODULES_END < vmax) {
-		/* force vmalloc and modules below kasan shadow */
-		MODULES_END = min(MODULES_END, KASAN_SHADOW_START);
+	    vmemmap_start + vmemmap_size + vmalloc_size + MODULES_LEN >
+		    _REGION2_SIZE) {
+		MODULES_END = _REGION1_SIZE;
+		rte_size = _REGION2_SIZE;
 	} else {
-		/*
-		 * leave vmalloc and modules above kasan shadow but make
-		 * sure they don't overlap with it
-		 */
-		vmalloc_size = min(vmalloc_size, vmax - KASAN_SHADOW_END - MODULES_LEN);
-		vmalloc_size_verified = true;
-		vspace_left = KASAN_SHADOW_START;
+		MODULES_END = _REGION2_SIZE;
+		rte_size = _REGION3_SIZE;
 	}
+	/*
+	 * forcing modules and vmalloc area under the ultravisor
+	 * secure storage limit, so that any vmalloc allocation
+	 * we do could be used to back secure guest storage.
+	 */
+	adjust_to_uv_max(&MODULES_END);
+#ifdef CONFIG_KASAN
+	/* force vmalloc and modules below kasan shadow */
+	MODULES_END = min(MODULES_END, KASAN_SHADOW_START);
 #endif
 	MODULES_VADDR = MODULES_END - MODULES_LEN;
 	VMALLOC_END = MODULES_VADDR;
 
-	if (vmalloc_size_verified) {
-		VMALLOC_START = VMALLOC_END - vmalloc_size;
-	} else {
-		vmemmap_off = round_up(ident_map_size, rte_size);
-
-		if (vmemmap_off + vmemmap_size > VMALLOC_END ||
-		    vmalloc_size > VMALLOC_END - vmemmap_off - vmemmap_size) {
-			/*
-			 * allow vmalloc area to occupy up to 1/2 of
-			 * the rest virtual space left.
-			 */
-			vmalloc_size = min(vmalloc_size, VMALLOC_END / 2);
-		}
-		VMALLOC_START = VMALLOC_END - vmalloc_size;
-		vspace_left = VMALLOC_START;
-	}
+	/* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */
+	vmalloc_size = min(vmalloc_size, round_down(VMALLOC_END / 2, _REGION3_SIZE));
+	VMALLOC_START = VMALLOC_END - vmalloc_size;
 
-	pages = vspace_left / (PAGE_SIZE + sizeof(struct page));
+	/* split remaining virtual space between 1:1 mapping & vmemmap array */
+	pages = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
 	pages = SECTION_ALIGN_UP(pages);
-	vmemmap_off = round_up(vspace_left - pages * sizeof(struct page), rte_size);
-	/* keep vmemmap left most starting from a fresh region table entry */
-	vmemmap_off = min(vmemmap_off, round_up(ident_map_size, rte_size));
-	/* take care that identity map is lower then vmemmap */
-	ident_map_size = min(ident_map_size, vmemmap_off);
+	/* keep vmemmap_start aligned to a top level region table entry */
+	vmemmap_start = round_down(VMALLOC_START - pages * sizeof(struct page), rte_size);
+	/* vmemmap_start is the future VMEM_MAX_PHYS, make sure it is within MAX_PHYSMEM */
+	vmemmap_start = min(vmemmap_start, 1UL << MAX_PHYSMEM_BITS);
+	/* make sure identity map doesn't overlay with vmemmap */
+	ident_map_size = min(ident_map_size, vmemmap_start);
 	vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page);
-	VMALLOC_START = max(vmemmap_off + vmemmap_size, VMALLOC_START);
-	vmemmap = (struct page *)vmemmap_off;
+	/* make sure vmemmap doesn't overlay with vmalloc area */
+	VMALLOC_START = max(vmemmap_start + vmemmap_size, VMALLOC_START);
+	vmemmap = (struct page *)vmemmap_start;
 }
 
 /*
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index ea398a05f643..7f3c9ac34bd8 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -74,6 +74,12 @@ void *kexec_file_add_components(struct kimage *image,
 int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
 			 unsigned long addr);
 
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	void *ipl_buf;
+};
+
 extern const struct kexec_file_ops s390_kexec_image_ops;
 extern const struct kexec_file_ops s390_kexec_elf_ops;
 
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 6b3c366af78e..90824be5ce9a 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -210,9 +210,11 @@ int zpci_deconfigure_device(struct zpci_dev *zdev);
 void zpci_device_reserved(struct zpci_dev *zdev);
 bool zpci_is_device_configured(struct zpci_dev *zdev);
 
+int zpci_hot_reset_device(struct zpci_dev *zdev);
 int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
 int zpci_unregister_ioat(struct zpci_dev *, u8);
 void zpci_remove_reserved_devices(void);
+void zpci_update_fh(struct zpci_dev *zdev, u32 fh);
 
 /* CLP */
 int clp_setup_writeback_mio(void);
@@ -294,8 +296,10 @@ void zpci_debug_exit(void);
 void zpci_debug_init_device(struct zpci_dev *, const char *);
 void zpci_debug_exit_device(struct zpci_dev *);
 
-/* Error reporting */
+/* Error handling */
 int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *);
+int zpci_clear_error_state(struct zpci_dev *zdev);
+int zpci_reset_load_store_blocked(struct zpci_dev *zdev);
 
 #ifdef CONFIG_NUMA
 
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d72a6df058d7..785d54c9350c 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -191,8 +191,8 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count)
 				return rc;
 		} else {
 			/* Check for swapped kdump oldmem areas */
-			if (oldmem_data.start && from - oldmem_data.size < oldmem_data.size) {
-				from -= oldmem_data.size;
+			if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) {
+				from -= oldmem_data.start;
 				len = min(count, oldmem_data.size - from);
 			} else if (oldmem_data.start && from < oldmem_data.size) {
 				len = min(count, oldmem_data.size - from);
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index e2cc35775b99..5ad1dde23dc5 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2156,7 +2156,7 @@ void *ipl_report_finish(struct ipl_report *report)
 
 	buf = vzalloc(report->size);
 	if (!buf)
-		return ERR_PTR(-ENOMEM);
+		goto out;
 	ptr = buf;
 
 	memcpy(ptr, report->ipib, report->ipib->hdr.len);
@@ -2195,6 +2195,7 @@ void *ipl_report_finish(struct ipl_report *report)
 	}
 
 	BUG_ON(ptr > buf + report->size);
+out:
 	return buf;
 }
 
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 528edff085d9..9975ad200d74 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -12,6 +12,7 @@
 #include <linux/kexec.h>
 #include <linux/module_signature.h>
 #include <linux/verification.h>
+#include <linux/vmalloc.h>
 #include <asm/boot_data.h>
 #include <asm/ipl.h>
 #include <asm/setup.h>
@@ -170,6 +171,7 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 	struct kexec_buf buf;
 	unsigned long addr;
 	void *ptr, *end;
+	int ret;
 
 	buf.image = image;
 
@@ -199,9 +201,13 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 		ptr += len;
 	}
 
+	ret = -ENOMEM;
 	buf.buffer = ipl_report_finish(data->report);
+	if (!buf.buffer)
+		goto out;
 	buf.bufsz = data->report->size;
 	buf.memsz = buf.bufsz;
+	image->arch.ipl_buf = buf.buffer;
 
 	data->memsz += buf.memsz;
 
@@ -209,7 +215,9 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 		data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
 	*lc_ipl_parmblock_ptr = (__u32)buf.mem;
 
-	return kexec_add_buffer(&buf);
+	ret = kexec_add_buffer(&buf);
+out:
+	return ret;
 }
 
 void *kexec_file_add_components(struct kimage *image,
@@ -322,3 +330,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 	}
 	return 0;
 }
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	vfree(image->arch.ipl_buf);
+	image->arch.ipl_buf = NULL;
+
+	return kexec_image_post_load_cleanup_default(image);
+}
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 6f431fa9e4d7..ee8707abdb6a 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -687,8 +687,10 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags)
 						      false);
 			if (cfdiag_diffctr(cpuhw, event->hw.config_base))
 				cfdiag_push_sample(event, cpuhw);
-		} else
+		} else if (cpuhw->flags & PMU_F_RESERVED) {
+			/* Only update when PMU not hotplugged off */
 			hw_perf_event_update(event);
+		}
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 }
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 40405f2304f1..225ab2d0a4c6 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -606,7 +606,7 @@ static void __init setup_resources(void)
 
 static void __init setup_memory_end(void)
 {
-	memblock_remove(ident_map_size, ULONG_MAX);
+	memblock_remove(ident_map_size, PHYS_ADDR_MAX - ident_map_size);
 	max_pfn = max_low_pfn = PFN_DOWN(ident_map_size);
 	pr_notice("The maximum memory size is %luMB\n", ident_map_size >> 20);
 }
@@ -638,14 +638,6 @@ static struct notifier_block kdump_mem_nb = {
 #endif
 
 /*
- * Make sure that the area above identity mapping is protected
- */
-static void __init reserve_above_ident_map(void)
-{
-	memblock_reserve(ident_map_size, ULONG_MAX);
-}
-
-/*
  * Reserve memory for kdump kernel to be loaded with kexec
  */
 static void __init reserve_crashkernel(void)
@@ -785,7 +777,6 @@ static void __init memblock_add_mem_detect_info(void)
 	}
 	memblock_set_bottom_up(false);
 	memblock_set_node(0, ULONG_MAX, &memblock.memory, 0);
-	memblock_dump_all();
 }
 
 /*
@@ -826,9 +817,6 @@ static void __init setup_memory(void)
 		storage_key_init_range(start, end);
 
 	psw_set_key(PAGE_DEFAULT_KEY);
-
-	/* Only cosmetics */
-	memblock_enforce_memory_limit(memblock_end_of_DRAM());
 }
 
 static void __init relocate_amode31_section(void)
@@ -999,24 +987,24 @@ void __init setup_arch(char **cmdline_p)
 	setup_control_program_code();
 
 	/* Do some memory reservations *before* memory is added to memblock */
-	reserve_above_ident_map();
 	reserve_kernel();
 	reserve_initrd();
 	reserve_certificate_list();
 	reserve_mem_detect_info();
+	memblock_set_current_limit(ident_map_size);
 	memblock_allow_resize();
 
 	/* Get information about *all* installed memory */
 	memblock_add_mem_detect_info();
 
 	free_mem_detect_info();
+	setup_memory_end();
+	memblock_dump_all();
+	setup_memory();
 
 	relocate_amode31_section();
 	setup_cr();
-
 	setup_uv();
-	setup_memory_end();
-	setup_memory();
 	dma_contiguous_reserve(ident_map_size);
 	vmcp_cma_reserve();
 	if (MACHINE_HAS_EDAT2)
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index df5261e5cfe1..ed9c5c2eafad 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
+449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 035705c9f23e..2b780786fc68 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -84,7 +84,7 @@ static void default_trap_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		report_user_fault(regs, SIGSEGV, 0);
-		force_fatal_sig(SIGSEGV);
+		force_exit_sig(SIGSEGV);
 	} else
 		die(regs, "Unknown program exception");
 }
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index e3e6ac5686df..245bddfe9bc0 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -22,7 +22,7 @@ KBUILD_AFLAGS_32 += -m31 -s
 KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin
 
-LDFLAGS_vdso32.so.dbg += -fPIC -shared -nostdlib -soname=linux-vdso32.so.1 \
+LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \
 	--hash-style=both --build-id=sha1 -melf_s390 -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 6568de236701..9e2b95a222a9 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -8,8 +8,9 @@ ARCH_REL_TYPE_ABS += R_390_GOT|R_390_PLT
 include $(srctree)/lib/vdso/Makefile
 obj-vdso64 = vdso_user_wrapper.o note.o
 obj-cvdso64 = vdso64_generic.o getcpu.o
-CFLAGS_REMOVE_getcpu.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
-CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
+VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK)
+CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE)
+CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE)
 
 # Build rules
 
@@ -25,7 +26,7 @@ KBUILD_AFLAGS_64 += -m64 -s
 
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
-ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \
+ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \
 	     --hash-style=both --build-id=sha1 -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c6257f625929..14a18ba5ff2c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -585,6 +585,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r = KVM_MAX_VCPUS;
 		else if (sclp.has_esca && sclp.has_64bscao)
 			r = KVM_S390_ESCA_CPU_SLOTS;
+		if (ext == KVM_CAP_NR_VCPUS)
+			r = min_t(unsigned int, num_online_cpus(), r);
 		break;
 	case KVM_CAP_S390_COW:
 		r = MACHINE_HAS_ESOP;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 872d772b73d2..2f9b78fa82a5 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -481,6 +481,34 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
 	spin_unlock(&zpci_iomap_lock);
 }
 
+static void zpci_do_update_iomap_fh(struct zpci_dev *zdev, u32 fh)
+{
+	int bar, idx;
+
+	spin_lock(&zpci_iomap_lock);
+	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
+		if (!zdev->bars[bar].size)
+			continue;
+		idx = zdev->bars[bar].map_idx;
+		if (!zpci_iomap_start[idx].count)
+			continue;
+		WRITE_ONCE(zpci_iomap_start[idx].fh, zdev->fh);
+	}
+	spin_unlock(&zpci_iomap_lock);
+}
+
+void zpci_update_fh(struct zpci_dev *zdev, u32 fh)
+{
+	if (!fh || zdev->fh == fh)
+		return;
+
+	zdev->fh = fh;
+	if (zpci_use_mio(zdev))
+		return;
+	if (zdev->has_resources && zdev_enabled(zdev))
+		zpci_do_update_iomap_fh(zdev, fh);
+}
+
 static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start,
 				    unsigned long size, unsigned long flags)
 {
@@ -668,7 +696,7 @@ int zpci_enable_device(struct zpci_dev *zdev)
 	if (clp_enable_fh(zdev, &fh, ZPCI_NR_DMA_SPACES))
 		rc = -EIO;
 	else
-		zdev->fh = fh;
+		zpci_update_fh(zdev, fh);
 	return rc;
 }
 
@@ -679,14 +707,14 @@ int zpci_disable_device(struct zpci_dev *zdev)
 
 	cc = clp_disable_fh(zdev, &fh);
 	if (!cc) {
-		zdev->fh = fh;
+		zpci_update_fh(zdev, fh);
 	} else if (cc == CLP_RC_SETPCIFN_ALRDY) {
 		pr_info("Disabling PCI function %08x had no effect as it was already disabled\n",
 			zdev->fid);
 		/* Function is already disabled - update handle */
 		rc = clp_refresh_fh(zdev->fid, &fh);
 		if (!rc) {
-			zdev->fh = fh;
+			zpci_update_fh(zdev, fh);
 			rc = -EINVAL;
 		}
 	} else {
@@ -696,6 +724,65 @@ int zpci_disable_device(struct zpci_dev *zdev)
 }
 
 /**
+ * zpci_hot_reset_device - perform a reset of the given zPCI function
+ * @zdev: the slot which should be reset
+ *
+ * Performs a low level reset of the zPCI function. The reset is low level in
+ * the sense that the zPCI function can be reset without detaching it from the
+ * common PCI subsystem. The reset may be performed while under control of
+ * either DMA or IOMMU APIs in which case the existing DMA/IOMMU translation
+ * table is reinstated at the end of the reset.
+ *
+ * After the reset the functions internal state is reset to an initial state
+ * equivalent to its state during boot when first probing a driver.
+ * Consequently after reset the PCI function requires re-initialization via the
+ * common PCI code including re-enabling IRQs via pci_alloc_irq_vectors()
+ * and enabling the function via e.g.pci_enablde_device_flags().The caller
+ * must guard against concurrent reset attempts.
+ *
+ * In most cases this function should not be called directly but through
+ * pci_reset_function() or pci_reset_bus() which handle the save/restore and
+ * locking.
+ *
+ * Return: 0 on success and an error value otherwise
+ */
+int zpci_hot_reset_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	zpci_dbg(3, "rst fid:%x, fh:%x\n", zdev->fid, zdev->fh);
+	if (zdev_enabled(zdev)) {
+		/* Disables device access, DMAs and IRQs (reset state) */
+		rc = zpci_disable_device(zdev);
+		/*
+		 * Due to a z/VM vs LPAR inconsistency in the error state the
+		 * FH may indicate an enabled device but disable says the
+		 * device is already disabled don't treat it as an error here.
+		 */
+		if (rc == -EINVAL)
+			rc = 0;
+		if (rc)
+			return rc;
+	}
+
+	rc = zpci_enable_device(zdev);
+	if (rc)
+		return rc;
+
+	if (zdev->dma_table)
+		rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+					(u64)zdev->dma_table);
+	else
+		rc = zpci_dma_init_device(zdev);
+	if (rc) {
+		zpci_disable_device(zdev);
+		return rc;
+	}
+
+	return 0;
+}
+
+/**
  * zpci_create_device() - Create a new zpci_dev and add it to the zbus
  * @fid: Function ID of the device to be created
  * @fh: Current Function Handle of the device to be created
@@ -776,7 +863,7 @@ int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh)
 {
 	int rc;
 
-	zdev->fh = fh;
+	zpci_update_fh(zdev, fh);
 	/* the PCI function will be scanned once function 0 appears */
 	if (!zdev->zbus->bus)
 		return 0;
@@ -903,6 +990,59 @@ int zpci_report_error(struct pci_dev *pdev,
 }
 EXPORT_SYMBOL(zpci_report_error);
 
+/**
+ * zpci_clear_error_state() - Clears the zPCI error state of the device
+ * @zdev: The zdev for which the zPCI error state should be reset
+ *
+ * Clear the zPCI error state of the device. If clearing the zPCI error state
+ * fails the device is left in the error state. In this case it may make sense
+ * to call zpci_io_perm_failure() on the associated pdev if it exists.
+ *
+ * Returns: 0 on success, -EIO otherwise
+ */
+int zpci_clear_error_state(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_ERROR);
+	struct zpci_fib fib = {0};
+	u8 status;
+	int cc;
+
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc) {
+		zpci_dbg(3, "ces fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * zpci_reset_load_store_blocked() - Re-enables L/S from error state
+ * @zdev: The zdev for which to unblock load/store access
+ *
+ * Re-enables load/store access for a PCI function in the error state while
+ * keeping DMA blocked. In this state drivers can poke MMIO space to determine
+ * if error recovery is possible while catching any rogue DMA access from the
+ * device.
+ *
+ * Returns: 0 on success, -EIO otherwise
+ */
+int zpci_reset_load_store_blocked(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_BLOCK);
+	struct zpci_fib fib = {0};
+	u8 status;
+	int cc;
+
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc) {
+		zpci_dbg(3, "rls fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int zpci_mem_init(void)
 {
 	BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) ||
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 6a5bfa9dc1f2..2e3e5b278925 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -47,18 +47,223 @@ struct zpci_ccdf_avail {
 	u16 pec;			/* PCI event code */
 } __packed;
 
+static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res)
+{
+	switch (ers_res) {
+	case PCI_ERS_RESULT_CAN_RECOVER:
+	case PCI_ERS_RESULT_RECOVERED:
+	case PCI_ERS_RESULT_NEED_RESET:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static bool is_passed_through(struct zpci_dev *zdev)
+{
+	return zdev->s390_domain;
+}
+
+static bool is_driver_supported(struct pci_driver *driver)
+{
+	if (!driver || !driver->err_handler)
+		return false;
+	if (!driver->err_handler->error_detected)
+		return false;
+	if (!driver->err_handler->slot_reset)
+		return false;
+	if (!driver->err_handler->resume)
+		return false;
+	return true;
+}
+
+static pci_ers_result_t zpci_event_notify_error_detected(struct pci_dev *pdev,
+							 struct pci_driver *driver)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+
+	ers_res = driver->err_handler->error_detected(pdev,  pdev->error_state);
+	if (ers_result_indicates_abort(ers_res))
+		pr_info("%s: Automatic recovery failed after initial reporting\n", pci_name(pdev));
+	else if (ers_res == PCI_ERS_RESULT_NEED_RESET)
+		pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
+
+	return ers_res;
+}
+
+static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev,
+							struct pci_driver *driver)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+	struct zpci_dev *zdev = to_zpci(pdev);
+	int rc;
+
+	pr_info("%s: Unblocking device access for examination\n", pci_name(pdev));
+	rc = zpci_reset_load_store_blocked(zdev);
+	if (rc) {
+		pr_err("%s: Unblocking device access failed\n", pci_name(pdev));
+		/* Let's try a full reset instead */
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+
+	if (driver->err_handler->mmio_enabled) {
+		ers_res = driver->err_handler->mmio_enabled(pdev);
+		if (ers_result_indicates_abort(ers_res)) {
+			pr_info("%s: Automatic recovery failed after MMIO re-enable\n",
+				pci_name(pdev));
+			return ers_res;
+		} else if (ers_res == PCI_ERS_RESULT_NEED_RESET) {
+			pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
+			return ers_res;
+		}
+	}
+
+	pr_debug("%s: Unblocking DMA\n", pci_name(pdev));
+	rc = zpci_clear_error_state(zdev);
+	if (!rc) {
+		pdev->error_state = pci_channel_io_normal;
+	} else {
+		pr_err("%s: Unblocking DMA failed\n", pci_name(pdev));
+		/* Let's try a full reset instead */
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+
+	return ers_res;
+}
+
+static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev,
+					    struct pci_driver *driver)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+
+	pr_info("%s: Initiating reset\n", pci_name(pdev));
+	if (zpci_hot_reset_device(to_zpci(pdev))) {
+		pr_err("%s: The reset request failed\n", pci_name(pdev));
+		return ers_res;
+	}
+	pdev->error_state = pci_channel_io_normal;
+	ers_res = driver->err_handler->slot_reset(pdev);
+	if (ers_result_indicates_abort(ers_res)) {
+		pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev));
+		return ers_res;
+	}
+
+	return ers_res;
+}
+
+/* zpci_event_attempt_error_recovery - Try to recover the given PCI function
+ * @pdev: PCI function to recover currently in the error state
+ *
+ * We follow the scheme outlined in Documentation/PCI/pci-error-recovery.rst.
+ * With the simplification that recovery always happens per function
+ * and the platform determines which functions are affected for
+ * multi-function devices.
+ */
+static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+	struct pci_driver *driver;
+
+	/*
+	 * Ensure that the PCI function is not removed concurrently, no driver
+	 * is unbound or probed and that userspace can't access its
+	 * configuration space while we perform recovery.
+	 */
+	pci_dev_lock(pdev);
+	if (pdev->error_state == pci_channel_io_perm_failure) {
+		ers_res = PCI_ERS_RESULT_DISCONNECT;
+		goto out_unlock;
+	}
+	pdev->error_state = pci_channel_io_frozen;
+
+	if (is_passed_through(to_zpci(pdev))) {
+		pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n",
+			pci_name(pdev));
+		goto out_unlock;
+	}
+
+	driver = to_pci_driver(pdev->dev.driver);
+	if (!is_driver_supported(driver)) {
+		if (!driver)
+			pr_info("%s: Cannot be recovered because no driver is bound to the device\n",
+				pci_name(pdev));
+		else
+			pr_info("%s: The %s driver bound to the device does not support error recovery\n",
+				pci_name(pdev),
+				driver->name);
+		goto out_unlock;
+	}
+
+	ers_res = zpci_event_notify_error_detected(pdev, driver);
+	if (ers_result_indicates_abort(ers_res))
+		goto out_unlock;
+
+	if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) {
+		ers_res = zpci_event_do_error_state_clear(pdev, driver);
+		if (ers_result_indicates_abort(ers_res))
+			goto out_unlock;
+	}
+
+	if (ers_res == PCI_ERS_RESULT_NEED_RESET)
+		ers_res = zpci_event_do_reset(pdev, driver);
+
+	if (ers_res != PCI_ERS_RESULT_RECOVERED) {
+		pr_err("%s: Automatic recovery failed; operator intervention is required\n",
+		       pci_name(pdev));
+		goto out_unlock;
+	}
+
+	pr_info("%s: The device is ready to resume operations\n", pci_name(pdev));
+	if (driver->err_handler->resume)
+		driver->err_handler->resume(pdev);
+out_unlock:
+	pci_dev_unlock(pdev);
+
+	return ers_res;
+}
+
+/* zpci_event_io_failure - Report PCI channel failure state to driver
+ * @pdev: PCI function for which to report
+ * @es: PCI channel failure state to report
+ */
+static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es)
+{
+	struct pci_driver *driver;
+
+	pci_dev_lock(pdev);
+	pdev->error_state = es;
+	/**
+	 * While vfio-pci's error_detected callback notifies user-space QEMU
+	 * reacts to this by freezing the guest. In an s390 environment PCI
+	 * errors are rarely fatal so this is overkill. Instead in the future
+	 * we will inject the error event and let the guest recover the device
+	 * itself.
+	 */
+	if (is_passed_through(to_zpci(pdev)))
+		goto out;
+	driver = to_pci_driver(pdev->dev.driver);
+	if (driver && driver->err_handler && driver->err_handler->error_detected)
+		driver->err_handler->error_detected(pdev, pdev->error_state);
+out:
+	pci_dev_unlock(pdev);
+}
+
 static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
 	struct pci_dev *pdev = NULL;
+	pci_ers_result_t ers_res;
 
 	zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n",
 		 ccdf->fid, ccdf->fh, ccdf->pec);
 	zpci_err("error CCDF:\n");
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
-	if (zdev)
-		pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
+	if (zdev) {
+		zpci_update_fh(zdev, ccdf->fh);
+		if (zdev->zbus->bus)
+			pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
+	}
 
 	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
 	       pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
@@ -66,7 +271,20 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	if (!pdev)
 		return;
 
-	pdev->error_state = pci_channel_io_perm_failure;
+	switch (ccdf->pec) {
+	case 0x003a: /* Service Action or Error Recovery Successful */
+		ers_res = zpci_event_attempt_error_recovery(pdev);
+		if (ers_res != PCI_ERS_RESULT_RECOVERED)
+			zpci_event_io_failure(pdev, pci_channel_io_perm_failure);
+		break;
+	default:
+		/*
+		 * Mark as frozen not permanently failed because the device
+		 * could be subsequently recovered by the platform.
+		 */
+		zpci_event_io_failure(pdev, pci_channel_io_frozen);
+		break;
+	}
 	pci_dev_put(pdev);
 }
 
@@ -78,7 +296,7 @@ void zpci_event_error(void *data)
 
 static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
 {
-	zdev->fh = fh;
+	zpci_update_fh(zdev, fh);
 	/* Give the driver a hint that the function is
 	 * already unusable.
 	 */
@@ -121,7 +339,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		if (!zdev)
 			zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY);
 		else
-			zdev->fh = ccdf->fh;
+			zpci_update_fh(zdev, ccdf->fh);
 		break;
 	case 0x0303: /* Deconfiguration requested */
 		if (zdev) {
@@ -130,7 +348,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			 */
 			if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
 				break;
-			zdev->fh = ccdf->fh;
+			zpci_update_fh(zdev, ccdf->fh);
 			zpci_deconfigure_device(zdev);
 		}
 		break;
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 2e43996159f0..28d863aaafea 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -163,7 +163,7 @@ static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr,
 			       unsigned long len)
 {
 	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+	u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len);
 
 	return __zpci_load(data, req, ZPCI_OFFSET(addr));
 }
@@ -244,7 +244,7 @@ static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data,
 				unsigned long len)
 {
 	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+	u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len);
 
 	return __zpci_store(data, req, ZPCI_OFFSET(addr));
 }
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 3823e159bf74..954bb7a83124 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -387,6 +387,15 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 		airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs);
 }
 
+void arch_restore_msi_irqs(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+
+	if (!zdev->irqs_registered)
+		zpci_set_irq(zdev);
+	default_restore_msi_irqs(pdev);
+}
+
 static struct airq_struct zpci_airq = {
 	.handler = zpci_floating_irq_handler,
 	.isc = PCI_ISC,