Merge tag 's390-6.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Alexander Gordeev:

 - Store AP Query Configuration Information in a static buffer

 - Rework the AP initialization and add missing cleanups to the error
   path

 - Swap IRQ and AP bus/device registration to avoid race conditions

 - Export prot_virt_guest symbol

 - Introduce AP configuration changes notifier interface to facilitate
   modularization of the AP bus

 - Add CONFIG_AP kernel configuration option to allow modularization of
   the AP bus

 - Rework CONFIG_ZCRYPT_DEBUG kernel configuration option description
   and dependency and rename it to CONFIG_AP_DEBUG

 - Convert sprintf() and snprintf() to sysfs_emit() in CIO code

 - Adjust indentation of RELOCS command build step

 - Make crypto performance counters upward compatible

 - Convert make_page_secure() and gmap_make_secure() to use folio

 - Rework channel-utilization-block (CUB) handling in preparation of
   introducing additional CUBs

 - Use attribute groups to simplify registration, removal and extension
   of measurement-related channel-path sysfs attributes

 - Add a per-channel-path binary "ext_measurement" sysfs attribute that
   provides access to extended channel-path measurement data

 - Export measurement data for all channel-measurement-groups (CMG), not
   only for a specific ones. This enables support of new CMG data
   formats in userspace without the need for kernel changes

 - Add a per-channel-path sysfs attribute "speed_bps" that provides the
   operating speed in bits per second or 0 if the operating speed is not
   available

 - The CIO tracepoint subchannel-type field "st" is incorrectly set to
   the value of subchannel-enabled SCHIB "ena" field. Fix that

 - Do not forcefully limit vmemmap starting address to MAX_PHYSMEM_BITS

 - Consider the maximum physical address available to a DCSS segment
   (512GB) when memory layout is set up

 - Simplify the virtual memory layout setup by reducing the size of
   identity mapping vs vmemmap overlap

 - Swap vmalloc and Lowcore/Real Memory Copy areas in virtual memory.
   This will allow to place the kernel image next to kernel modules

 - Move everyting KASLR related from <asm/setup.h> to <asm/page.h>

 - Put virtual memory layout information into a structure to improve
   code generation

 - Currently __kaslr_offset is the kernel offset in both physical and
   virtual memory spaces. Uncouple these offsets to allow uncoupling of
   the addresses spaces

 - Currently the identity mapping base address is implicit and is always
   set to zero. Make it explicit by putting into __identity_base
   persistent boot variable and use it in proper context

 - Introduce .amode31 section start and end macros AMODE31_START and
   AMODE31_END

 - Introduce OS_INFO entries that do not reference any data in memory,
   but rather provide only values

 - Store virtual memory layout in OS_INFO. It is read out by
   makedumpfile, crash and other tools

 - Store virtual memory layout in VMCORE_INFO. It is read out by crash
   and other tools when /proc/kcore device is used

 - Create additional PT_LOAD ELF program header that covers kernel image
   only, so that vmcore tools could locate kernel text and data when
   virtual and physical memory spaces are uncoupled

 - Uncouple physical and virtual address spaces

 - Map kernel at fixed location when KASLR mode is disabled. The
   location is defined by CONFIG_KERNEL_IMAGE_BASE kernel configuration
   value.

 - Rework deployment of kernel image for both compressed and
   uncompressed variants as defined by CONFIG_KERNEL_UNCOMPRESSED kernel
   configuration value

 - Move .vmlinux.relocs section in front of the compressed kernel. The
   interim section rescue step is avoided as result

 - Correct modules thunk offset calculation when branch target is more
   than 2GB away

 - Kernel modules contain their own set of expoline thunks. Now that the
   kernel modules area is less than 4GB away from kernel expoline
   thunks, make modules use kernel expolines. Also make EXPOLINE_EXTERN
   the default if the compiler supports it

 - userfaultfd can insert shared zeropages into processes running VMs,
   but that is not allowed for s390. Fallback to allocating a fresh
   zeroed anonymous folio and insert that instead

 - Re-enable shared zeropages for non-PV and non-skeys KVM guests

 - Rename hex2bitmap() to ap_hex2bitmap() and export it for external use

 - Add ap_config sysfs attribute to provide the means for setting or
   displaying adapters, domains and control domains assigned to a
   vfio-ap mediated device in a single operation

 - Make vfio_ap_mdev_link_queue() ignore duplicate link requests

 - Add write support to ap_config sysfs attribute to allow atomic update
   a vfio-ap mediated device state

 - Document ap_config sysfs attribute

 - Function os_info_old_init() is expected to be called only from a
   regular kdump kernel. Enable it to be called from a stand-alone dump
   kernel

 - Address gcc -Warray-bounds warning and fix array size in struct
   os_info

 - s390 does not support SMBIOS, so drop unneeded CONFIG_DMI checks

 - Use unwinder instead of __builtin_return_address() with ftrace to
   prevent returning of undefined values

 - Sections .hash and .gnu.hash are only created when CONFIG_PIE_BUILD
   kernel is enabled. Drop these for the case CONFIG_PIE_BUILD is
   disabled

 - Compile kernel with -fPIC and link with -no-pie to allow kpatch
   feature always succeed and drop the whole CONFIG_PIE_BUILD
   option-enabled code

 - Add missing virt_to_phys() converter for VSIE facility and crypto
   control blocks

* tag 's390-6.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (54 commits)
  Revert "s390: Relocate vmlinux ELF data to virtual address space"
  KVM: s390: vsie: Use virt_to_phys for crypto control block
  s390: Relocate vmlinux ELF data to virtual address space
  s390: Compile kernel with -fPIC and link with -no-pie
  s390: vmlinux.lds.S: Drop .hash and .gnu.hash for !CONFIG_PIE_BUILD
  s390/ftrace: Use unwinder instead of __builtin_return_address()
  s390/pci: Drop unneeded reference to CONFIG_DMI
  s390/os_info: Fix array size in struct os_info
  s390/os_info: Initialize old os_info in standalone dump kernel
  docs: Update s390 vfio-ap doc for ap_config sysfs attribute
  s390/vfio-ap: Add write support to sysfs attr ap_config
  s390/vfio-ap: Ignore duplicate link requests in vfio_ap_mdev_link_queue
  s390/vfio-ap: Add sysfs attr, ap_config, to export mdev state
  s390/ap: Externalize AP bus specific bitmap reading function
  s390/mm: Re-enable the shared zeropage for !PV and !skeys KVM guests
  mm/userfaultfd: Do not place zeropages when zeropages are disallowed
  s390/expoline: Make modules use kernel expolines
  s390/nospec: Correct modules thunk offset calculation
  s390/boot: Do not rescue .vmlinux.relocs section
  s390/boot: Rework deployment of the kernel image
  ...

1 files changed, 137 insertions, 101 deletions

diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index cce0bafd4c92..c20b45092079 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -39,13 +39,15 @@
 #include <linux/ctype.h>
 #include <linux/module.h>
 #include <asm/uv.h>
+#include <asm/chsc.h>
 
 #include "ap_bus.h"
 #include "ap_debug.h"
 
-/*
- * Module parameters; note though this file itself isn't modular.
- */
+MODULE_AUTHOR("IBM Corporation");
+MODULE_DESCRIPTION("Adjunct Processor Bus driver");
+MODULE_LICENSE("GPL");
+
 int ap_domain_index = -1;	/* Adjunct Processor Domain Index */
 static DEFINE_SPINLOCK(ap_domain_lock);
 module_param_named(domain, ap_domain_index, int, 0440);
@@ -90,8 +92,9 @@ static atomic64_t ap_bindings_complete_count = ATOMIC64_INIT(0);
 /* completion for APQN bindings complete */
 static DECLARE_COMPLETION(ap_apqn_bindings_complete);
 
-static struct ap_config_info *ap_qci_info;
-static struct ap_config_info *ap_qci_info_old;
+static struct ap_config_info qci[2];
+static struct ap_config_info *const ap_qci_info = &qci[0];
+static struct ap_config_info *const ap_qci_info_old = &qci[1];
 
 /*
  * AP bus related debug feature things.
@@ -203,9 +206,7 @@ static int ap_apft_available(void)
  */
 static inline int ap_qact_available(void)
 {
-	if (ap_qci_info)
-		return ap_qci_info->qact;
-	return 0;
+	return ap_qci_info->qact;
 }
 
 /*
@@ -215,9 +216,7 @@ static inline int ap_qact_available(void)
  */
 int ap_sb_available(void)
 {
-	if (ap_qci_info)
-		return ap_qci_info->apsb;
-	return 0;
+	return ap_qci_info->apsb;
 }
 
 /*
@@ -229,23 +228,6 @@ bool ap_is_se_guest(void)
 }
 EXPORT_SYMBOL(ap_is_se_guest);
 
-/*
- * ap_fetch_qci_info(): Fetch cryptographic config info
- *
- * Returns the ap configuration info fetched via PQAP(QCI).
- * On success 0 is returned, on failure a negative errno
- * is returned, e.g. if the PQAP(QCI) instruction is not
- * available, the return value will be -EOPNOTSUPP.
- */
-static inline int ap_fetch_qci_info(struct ap_config_info *info)
-{
-	if (!ap_qci_available())
-		return -EOPNOTSUPP;
-	if (!info)
-		return -EINVAL;
-	return ap_qci(info);
-}
-
 /**
  * ap_init_qci_info(): Allocate and query qci config info.
  * Does also update the static variables ap_max_domain_id
@@ -253,27 +235,12 @@ static inline int ap_fetch_qci_info(struct ap_config_info *info)
  */
 static void __init ap_init_qci_info(void)
 {
-	if (!ap_qci_available()) {
+	if (!ap_qci_available() ||
+	    ap_qci(ap_qci_info)) {
 		AP_DBF_INFO("%s QCI not supported\n", __func__);
 		return;
 	}
-
-	ap_qci_info = kzalloc(sizeof(*ap_qci_info), GFP_KERNEL);
-	if (!ap_qci_info)
-		return;
-	ap_qci_info_old = kzalloc(sizeof(*ap_qci_info_old), GFP_KERNEL);
-	if (!ap_qci_info_old) {
-		kfree(ap_qci_info);
-		ap_qci_info = NULL;
-		return;
-	}
-	if (ap_fetch_qci_info(ap_qci_info) != 0) {
-		kfree(ap_qci_info);
-		kfree(ap_qci_info_old);
-		ap_qci_info = NULL;
-		ap_qci_info_old = NULL;
-		return;
-	}
+	memcpy(ap_qci_info_old, ap_qci_info, sizeof(*ap_qci_info));
 	AP_DBF_INFO("%s successful fetched initial qci info\n", __func__);
 
 	if (ap_qci_info->apxa) {
@@ -288,8 +255,6 @@ static void __init ap_init_qci_info(void)
 				    __func__, ap_max_domain_id);
 		}
 	}
-
-	memcpy(ap_qci_info_old, ap_qci_info, sizeof(*ap_qci_info));
 }
 
 /*
@@ -312,7 +277,7 @@ static inline int ap_test_config_card_id(unsigned int id)
 {
 	if (id > ap_max_adapter_id)
 		return 0;
-	if (ap_qci_info)
+	if (ap_qci_info->flags)
 		return ap_test_config(ap_qci_info->apm, id);
 	return 1;
 }
@@ -329,7 +294,7 @@ int ap_test_config_usage_domain(unsigned int domain)
 {
 	if (domain > ap_max_domain_id)
 		return 0;
-	if (ap_qci_info)
+	if (ap_qci_info->flags)
 		return ap_test_config(ap_qci_info->aqm, domain);
 	return 1;
 }
@@ -1061,22 +1026,24 @@ EXPORT_SYMBOL(ap_bus_force_rescan);
 /*
  * A config change has happened, force an ap bus rescan.
  */
-void ap_bus_cfg_chg(void)
+static int ap_bus_cfg_chg(struct notifier_block *nb,
+			  unsigned long action, void *data)
 {
+	if (action != CHSC_NOTIFY_AP_CFG)
+		return NOTIFY_DONE;
+
 	pr_debug("%s config change, forcing bus rescan\n", __func__);
 
 	ap_bus_force_rescan();
+
+	return NOTIFY_OK;
 }
 
-/*
- * hex2bitmap() - parse hex mask string and set bitmap.
- * Valid strings are "0x012345678" with at least one valid hex number.
- * Rest of the bitmap to the right is padded with 0. No spaces allowed
- * within the string, the leading 0x may be omitted.
- * Returns the bitmask with exactly the bits set as given by the hex
- * string (both in big endian order).
- */
-static int hex2bitmap(const char *str, unsigned long *bitmap, int bits)
+static struct notifier_block ap_bus_nb = {
+	.notifier_call = ap_bus_cfg_chg,
+};
+
+int ap_hex2bitmap(const char *str, unsigned long *bitmap, int bits)
 {
 	int i, n, b;
 
@@ -1103,6 +1070,7 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits)
 		return -EINVAL;
 	return 0;
 }
+EXPORT_SYMBOL(ap_hex2bitmap);
 
 /*
  * modify_bitmap() - parse bitmask argument and modify an existing
@@ -1168,7 +1136,7 @@ static int ap_parse_bitmap_str(const char *str, unsigned long *bitmap, int bits,
 		rc = modify_bitmap(str, newmap, bits);
 	} else {
 		memset(newmap, 0, size);
-		rc = hex2bitmap(str, newmap, bits);
+		rc = ap_hex2bitmap(str, newmap, bits);
 	}
 	return rc;
 }
@@ -1234,7 +1202,7 @@ static BUS_ATTR_RW(ap_domain);
 
 static ssize_t ap_control_domain_mask_show(const struct bus_type *bus, char *buf)
 {
-	if (!ap_qci_info)	/* QCI not supported */
+	if (!ap_qci_info->flags)	/* QCI not supported */
 		return sysfs_emit(buf, "not supported\n");
 
 	return sysfs_emit(buf, "0x%08x%08x%08x%08x%08x%08x%08x%08x\n",
@@ -1248,7 +1216,7 @@ static BUS_ATTR_RO(ap_control_domain_mask);
 
 static ssize_t ap_usage_domain_mask_show(const struct bus_type *bus, char *buf)
 {
-	if (!ap_qci_info)	/* QCI not supported */
+	if (!ap_qci_info->flags)	/* QCI not supported */
 		return sysfs_emit(buf, "not supported\n");
 
 	return sysfs_emit(buf, "0x%08x%08x%08x%08x%08x%08x%08x%08x\n",
@@ -1262,7 +1230,7 @@ static BUS_ATTR_RO(ap_usage_domain_mask);
 
 static ssize_t ap_adapter_mask_show(const struct bus_type *bus, char *buf)
 {
-	if (!ap_qci_info)	/* QCI not supported */
+	if (!ap_qci_info->flags)	/* QCI not supported */
 		return sysfs_emit(buf, "not supported\n");
 
 	return sysfs_emit(buf, "0x%08x%08x%08x%08x%08x%08x%08x%08x\n",
@@ -1595,7 +1563,7 @@ static ssize_t features_show(const struct bus_type *bus, char *buf)
 {
 	int n = 0;
 
-	if (!ap_qci_info)	/* QCI not supported */
+	if (!ap_qci_info->flags)	/* QCI not supported */
 		return sysfs_emit(buf, "-\n");
 
 	if (ap_qci_info->apsc)
@@ -2158,11 +2126,11 @@ static inline void ap_scan_adapter(int ap)
  */
 static bool ap_get_configuration(void)
 {
-	if (!ap_qci_info)	/* QCI not supported */
+	if (!ap_qci_info->flags)	/* QCI not supported */
 		return false;
 
 	memcpy(ap_qci_info_old, ap_qci_info, sizeof(*ap_qci_info));
-	ap_fetch_qci_info(ap_qci_info);
+	ap_qci(ap_qci_info);
 
 	return memcmp(ap_qci_info, ap_qci_info_old,
 		      sizeof(struct ap_config_info)) != 0;
@@ -2179,7 +2147,7 @@ static bool ap_config_has_new_aps(void)
 
 	unsigned long m[BITS_TO_LONGS(AP_DEVICES)];
 
-	if (!ap_qci_info)
+	if (!ap_qci_info->flags)
 		return false;
 
 	bitmap_andnot(m, (unsigned long *)ap_qci_info->apm,
@@ -2200,7 +2168,7 @@ static bool ap_config_has_new_doms(void)
 {
 	unsigned long m[BITS_TO_LONGS(AP_DOMAINS)];
 
-	if (!ap_qci_info)
+	if (!ap_qci_info->flags)
 		return false;
 
 	bitmap_andnot(m, (unsigned long *)ap_qci_info->aqm,
@@ -2310,7 +2278,82 @@ static void ap_scan_bus_wq_callback(struct work_struct *unused)
 	}
 }
 
-static int __init ap_debug_init(void)
+static inline void __exit ap_async_exit(void)
+{
+	if (ap_thread_flag)
+		ap_poll_thread_stop();
+	chsc_notifier_unregister(&ap_bus_nb);
+	cancel_work(&ap_scan_bus_work);
+	hrtimer_cancel(&ap_poll_timer);
+	timer_delete(&ap_scan_bus_timer);
+}
+
+static inline int __init ap_async_init(void)
+{
+	int rc;
+
+	/* Setup the AP bus rescan timer. */
+	timer_setup(&ap_scan_bus_timer, ap_scan_bus_timer_callback, 0);
+
+	/*
+	 * Setup the high resolution poll timer.
+	 * If we are running under z/VM adjust polling to z/VM polling rate.
+	 */
+	if (MACHINE_IS_VM)
+		poll_high_timeout = 1500000;
+	hrtimer_init(&ap_poll_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	ap_poll_timer.function = ap_poll_timeout;
+
+	queue_work(system_long_wq, &ap_scan_bus_work);
+
+	rc = chsc_notifier_register(&ap_bus_nb);
+	if (rc)
+		goto out;
+
+	/* Start the low priority AP bus poll thread. */
+	if (!ap_thread_flag)
+		return 0;
+
+	rc = ap_poll_thread_start();
+	if (rc)
+		goto out_notifier;
+
+	return 0;
+
+out_notifier:
+	chsc_notifier_unregister(&ap_bus_nb);
+out:
+	cancel_work(&ap_scan_bus_work);
+	hrtimer_cancel(&ap_poll_timer);
+	timer_delete(&ap_scan_bus_timer);
+	return rc;
+}
+
+static inline void ap_irq_exit(void)
+{
+	if (ap_irq_flag)
+		unregister_adapter_interrupt(&ap_airq);
+}
+
+static inline int __init ap_irq_init(void)
+{
+	int rc;
+
+	if (!ap_interrupts_available() || !ap_useirq)
+		return 0;
+
+	rc = register_adapter_interrupt(&ap_airq);
+	ap_irq_flag = (rc == 0);
+
+	return rc;
+}
+
+static inline void ap_debug_exit(void)
+{
+	debug_unregister(ap_dbf_info);
+}
+
+static inline int __init ap_debug_init(void)
 {
 	ap_dbf_info = debug_register("ap", 2, 1,
 				     AP_DBF_MAX_SPRINTF_ARGS * sizeof(long));
@@ -2378,12 +2421,6 @@ static int __init ap_module_init(void)
 		ap_domain_index = -1;
 	}
 
-	/* enable interrupts if available */
-	if (ap_interrupts_available() && ap_useirq) {
-		rc = register_adapter_interrupt(&ap_airq);
-		ap_irq_flag = (rc == 0);
-	}
-
 	/* Create /sys/bus/ap. */
 	rc = bus_register(&ap_bus_type);
 	if (rc)
@@ -2396,38 +2433,37 @@ static int __init ap_module_init(void)
 		goto out_bus;
 	ap_root_device->bus = &ap_bus_type;
 
-	/* Setup the AP bus rescan timer. */
-	timer_setup(&ap_scan_bus_timer, ap_scan_bus_timer_callback, 0);
-
-	/*
-	 * Setup the high resolution poll timer.
-	 * If we are running under z/VM adjust polling to z/VM polling rate.
-	 */
-	if (MACHINE_IS_VM)
-		poll_high_timeout = 1500000;
-	hrtimer_init(&ap_poll_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	ap_poll_timer.function = ap_poll_timeout;
-
-	/* Start the low priority AP bus poll thread. */
-	if (ap_thread_flag) {
-		rc = ap_poll_thread_start();
-		if (rc)
-			goto out_work;
-	}
+	/* enable interrupts if available */
+	rc = ap_irq_init();
+	if (rc)
+		goto out_device;
 
-	queue_work(system_long_wq, &ap_scan_bus_work);
+	/* Setup asynchronous work (timers, workqueue, etc). */
+	rc = ap_async_init();
+	if (rc)
+		goto out_irq;
 
 	return 0;
 
-out_work:
-	hrtimer_cancel(&ap_poll_timer);
+out_irq:
+	ap_irq_exit();
+out_device:
 	root_device_unregister(ap_root_device);
 out_bus:
 	bus_unregister(&ap_bus_type);
 out:
-	if (ap_irq_flag)
-		unregister_adapter_interrupt(&ap_airq);
-	kfree(ap_qci_info);
+	ap_debug_exit();
 	return rc;
 }
-device_initcall(ap_module_init);
+
+static void __exit ap_module_exit(void)
+{
+	ap_async_exit();
+	ap_irq_exit();
+	root_device_unregister(ap_root_device);
+	bus_unregister(&ap_bus_type);
+	ap_debug_exit();
+}
+
+module_init(ap_module_init);
+module_exit(ap_module_exit);