Merge tag 's390-6.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:

 - Add vfio-ap support to pass-through crypto devices to secure
   execution guests

 - Add API ordinal 6 support to zcrypt_ep11misc device drive, which is
   required to handle key generate and key derive (e.g. secure key to
   protected key) correctly

 - Add missing secure/has_secure sysfs files for the case where it is
   not possible to figure where a system has been booted from. Existing
   user space relies on that these files are always present

 - Fix DCSS block device driver list corruption, caused by incorrect
   error handling

 - Convert virt_to_pfn() and pfn_to_virt() from defines to static inline
   functions to enforce type checking

 - Cleanups, improvements, and minor fixes to the kernel mapping setup

 - Fix various virtual vs physical address confusions

 - Move pfault code to separate file, since it has nothing to do with
   regular fault handling

 - Move s390 documentation to Documentation/arch/ like it has been done
   for other architectures already

 - Add HAVE_FUNCTION_GRAPH_RETVAL support

 - Factor out the s390_hypfs filesystem and add a new config option for
   it. The filesystem is deprecated and as soon as all users are gone it
   can be removed some time in the not so near future

 - Remove support for old CEX2 and CEX3 crypto cards from zcrypt device
   driver

 - Add support for user-defined certificates: receive user-defined
   certificates with a diagnose call and provide them via 'cert_store'
   keyring to user space

 - Couple of other small fixes and improvements all over the place

* tag 's390-6.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (66 commits)
  s390/pci: use builtin_misc_device macro to simplify the code
  s390/vfio-ap: make sure nib is shared
  KVM: s390: export kvm_s390_pv*_is_protected functions
  s390/uv: export uv_pin_shared for direct usage
  s390/vfio-ap: check for TAPQ response codes 0x35 and 0x36
  s390/vfio-ap: handle queue state change in progress on reset
  s390/vfio-ap: use work struct to verify queue reset
  s390/vfio-ap: store entire AP queue status word with the queue object
  s390/vfio-ap: remove upper limit on wait for queue reset to complete
  s390/vfio-ap: allow deconfigured queue to be passed through to a guest
  s390/vfio-ap: wait for response code 05 to clear on queue reset
  s390/vfio-ap: clean up irq resources if possible
  s390/vfio-ap: no need to check the 'E' and 'I' bits in APQSW after TAPQ
  s390/ipl: refactor deprecated strncpy
  s390/ipl: fix virtual vs physical address confusion
  s390/zcrypt_ep11misc: support API ordinal 6 with empty pin-blob
  s390/paes: fix PKEY_TYPE_EP11_AES handling for secure keyblobs
  s390/pkey: fix PKEY_TYPE_EP11_AES handling for sysfs attributes
  s390/pkey: fix PKEY_TYPE_EP11_AES handling in PKEY_VERIFYKEY2 IOCTL
  s390/pkey: fix PKEY_TYPE_EP11_AES handling in PKEY_KBLOB2PROTK[23]
  ...

1 files changed, 248 insertions, 0 deletions

diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
new file mode 100644
index 000000000000..1aac13bb8f53
--- /dev/null
+++ b/arch/s390/mm/pfault.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 1999, 2023
+ */
+
+#include <linux/cpuhotplug.h>
+#include <linux/sched/task.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <asm/asm-extable.h>
+#include <asm/pfault.h>
+#include <asm/diag.h>
+
+#define __SUBCODE_MASK 0x0600
+#define __PF_RES_FIELD 0x8000000000000000UL
+
+/*
+ * 'pfault' pseudo page faults routines.
+ */
+static int pfault_disable;
+
+static int __init nopfault(char *str)
+{
+	pfault_disable = 1;
+	return 1;
+}
+early_param("nopfault", nopfault);
+
+struct pfault_refbk {
+	u16 refdiagc;
+	u16 reffcode;
+	u16 refdwlen;
+	u16 refversn;
+	u64 refgaddr;
+	u64 refselmk;
+	u64 refcmpmk;
+	u64 reserved;
+};
+
+static struct pfault_refbk pfault_init_refbk = {
+	.refdiagc = 0x258,
+	.reffcode = 0,
+	.refdwlen = 5,
+	.refversn = 2,
+	.refgaddr = __LC_LPP,
+	.refselmk = 1UL << 48,
+	.refcmpmk = 1UL << 48,
+	.reserved = __PF_RES_FIELD
+};
+
+int __pfault_init(void)
+{
+	int rc = -EOPNOTSUPP;
+
+	if (pfault_disable)
+		return rc;
+	diag_stat_inc(DIAG_STAT_X258);
+	asm volatile(
+		"	diag	%[refbk],%[rc],0x258\n"
+		"0:	nopr	%%r7\n"
+		EX_TABLE(0b, 0b)
+		: [rc] "+d" (rc)
+		: [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk)
+		: "cc");
+	return rc;
+}
+
+static struct pfault_refbk pfault_fini_refbk = {
+	.refdiagc = 0x258,
+	.reffcode = 1,
+	.refdwlen = 5,
+	.refversn = 2,
+};
+
+void __pfault_fini(void)
+{
+	if (pfault_disable)
+		return;
+	diag_stat_inc(DIAG_STAT_X258);
+	asm volatile(
+		"	diag	%[refbk],0,0x258\n"
+		"0:	nopr	%%r7\n"
+		EX_TABLE(0b, 0b)
+		:
+		: [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk)
+		: "cc");
+}
+
+static DEFINE_SPINLOCK(pfault_lock);
+static LIST_HEAD(pfault_list);
+
+#define PF_COMPLETE	0x0080
+
+/*
+ * The mechanism of our pfault code: if Linux is running as guest, runs a user
+ * space process and the user space process accesses a page that the host has
+ * paged out we get a pfault interrupt.
+ *
+ * This allows us, within the guest, to schedule a different process. Without
+ * this mechanism the host would have to suspend the whole virtual cpu until
+ * the page has been paged in.
+ *
+ * So when we get such an interrupt then we set the state of the current task
+ * to uninterruptible and also set the need_resched flag. Both happens within
+ * interrupt context(!). If we later on want to return to user space we
+ * recognize the need_resched flag and then call schedule().  It's not very
+ * obvious how this works...
+ *
+ * Of course we have a lot of additional fun with the completion interrupt (->
+ * host signals that a page of a process has been paged in and the process can
+ * continue to run). This interrupt can arrive on any cpu and, since we have
+ * virtual cpus, actually appear before the interrupt that signals that a page
+ * is missing.
+ */
+static void pfault_interrupt(struct ext_code ext_code,
+			     unsigned int param32, unsigned long param64)
+{
+	struct task_struct *tsk;
+	__u16 subcode;
+	pid_t pid;
+
+	/*
+	 * Get the external interruption subcode & pfault initial/completion
+	 * signal bit. VM stores this in the 'cpu address' field associated
+	 * with the external interrupt.
+	 */
+	subcode = ext_code.subcode;
+	if ((subcode & 0xff00) != __SUBCODE_MASK)
+		return;
+	inc_irq_stat(IRQEXT_PFL);
+	/* Get the token (= pid of the affected task). */
+	pid = param64 & LPP_PID_MASK;
+	rcu_read_lock();
+	tsk = find_task_by_pid_ns(pid, &init_pid_ns);
+	if (tsk)
+		get_task_struct(tsk);
+	rcu_read_unlock();
+	if (!tsk)
+		return;
+	spin_lock(&pfault_lock);
+	if (subcode & PF_COMPLETE) {
+		/* signal bit is set -> a page has been swapped in by VM */
+		if (tsk->thread.pfault_wait == 1) {
+			/*
+			 * Initial interrupt was faster than the completion
+			 * interrupt. pfault_wait is valid. Set pfault_wait
+			 * back to zero and wake up the process. This can
+			 * safely be done because the task is still sleeping
+			 * and can't produce new pfaults.
+			 */
+			tsk->thread.pfault_wait = 0;
+			list_del(&tsk->thread.list);
+			wake_up_process(tsk);
+			put_task_struct(tsk);
+		} else {
+			/*
+			 * Completion interrupt was faster than initial
+			 * interrupt. Set pfault_wait to -1 so the initial
+			 * interrupt doesn't put the task to sleep.
+			 * If the task is not running, ignore the completion
+			 * interrupt since it must be a leftover of a PFAULT
+			 * CANCEL operation which didn't remove all pending
+			 * completion interrupts.
+			 */
+			if (task_is_running(tsk))
+				tsk->thread.pfault_wait = -1;
+		}
+	} else {
+		/* signal bit not set -> a real page is missing. */
+		if (WARN_ON_ONCE(tsk != current))
+			goto out;
+		if (tsk->thread.pfault_wait == 1) {
+			/* Already on the list with a reference: put to sleep */
+			goto block;
+		} else if (tsk->thread.pfault_wait == -1) {
+			/*
+			 * Completion interrupt was faster than the initial
+			 * interrupt (pfault_wait == -1). Set pfault_wait
+			 * back to zero and exit.
+			 */
+			tsk->thread.pfault_wait = 0;
+		} else {
+			/*
+			 * Initial interrupt arrived before completion
+			 * interrupt. Let the task sleep.
+			 * An extra task reference is needed since a different
+			 * cpu may set the task state to TASK_RUNNING again
+			 * before the scheduler is reached.
+			 */
+			get_task_struct(tsk);
+			tsk->thread.pfault_wait = 1;
+			list_add(&tsk->thread.list, &pfault_list);
+block:
+			/*
+			 * Since this must be a userspace fault, there
+			 * is no kernel task state to trample. Rely on the
+			 * return to userspace schedule() to block.
+			 */
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			set_tsk_need_resched(tsk);
+			set_preempt_need_resched();
+		}
+	}
+out:
+	spin_unlock(&pfault_lock);
+	put_task_struct(tsk);
+}
+
+static int pfault_cpu_dead(unsigned int cpu)
+{
+	struct thread_struct *thread, *next;
+	struct task_struct *tsk;
+
+	spin_lock_irq(&pfault_lock);
+	list_for_each_entry_safe(thread, next, &pfault_list, list) {
+		thread->pfault_wait = 0;
+		list_del(&thread->list);
+		tsk = container_of(thread, struct task_struct, thread);
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+	}
+	spin_unlock_irq(&pfault_lock);
+	return 0;
+}
+
+static int __init pfault_irq_init(void)
+{
+	int rc;
+
+	rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
+	if (rc)
+		goto out_extint;
+	rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
+	if (rc)
+		goto out_pfault;
+	irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
+	cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead",
+				  NULL, pfault_cpu_dead);
+	return 0;
+
+out_pfault:
+	unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
+out_extint:
+	pfault_disable = 1;
+	return rc;
+}
+early_initcall(pfault_irq_init);