Merge tag 's390-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:

 - Various virtual vs physical address usage fixes

 - Fix error handling in Processor Activity Instrumentation device
   driver, and export number of counters with a sysfs file

 - Allow for multiple events when Processor Activity Instrumentation
   counters are monitored in system wide sampling

 - Change multiplier and shift values of the Time-of-Day clock source to
   improve steering precision

 - Remove a couple of unneeded GFP_DMA flags from allocations

 - Disable mmap alignment if randomize_va_space is also disabled, to
   avoid a too small heap

 - Various changes to allow s390 to be compiled with LLVM=1, since
   ld.lld and llvm-objcopy will have proper s390 support witch clang 19

 - Add __uninitialized macro to Compiler Attributes. This is helpful
   with s390's FPU code where some users have up to 520 byte stack
   frames. Clearing such stack frames (if INIT_STACK_ALL_PATTERN or
   INIT_STACK_ALL_ZERO is enabled) before they are used contradicts the
   intention (performance improvement) of such code sections.

 - Convert switch_to() to an out-of-line function, and use the generic
   switch_to header file

 - Replace the usage of s390's debug feature with pr_debug() calls
   within the zcrypt device driver

 - Improve hotplug support of the Adjunct Processor device driver

 - Improve retry handling in the zcrypt device driver

 - Various changes to the in-kernel FPU code:

     - Make in-kernel FPU sections preemptible

     - Convert various larger inline assemblies and assembler files to
       C, mainly by using singe instruction inline assemblies. This
       increases readability, but also allows makes it easier to add
       proper instrumentation hooks

     - Cleanup of the header files

 - Provide fast variants of csum_partial() and
   csum_partial_copy_nocheck() based on vector instructions

 - Introduce and use a lock to synchronize accesses to zpci device data
   structures to avoid inconsistent states caused by concurrent accesses

 - Compile the kernel without -fPIE. This addresses the following
   problems if the kernel is compiled with -fPIE:

     - It uses dynamic symbols (.dynsym), for which the linker refuses
       to allow more than 64k sections. This can break features which
       use '-ffunction-sections' and '-fdata-sections', including
       kpatch-build and function granular KASLR

     - It unnecessarily uses GOT relocations, adding an extra layer of
       indirection for many memory accesses

 - Fix shared_cpu_list for CPU private L2 caches, which incorrectly were
   reported as globally shared

* tag 's390-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (117 commits)
  s390/tools: handle rela R_390_GOTPCDBL/R_390_GOTOFF64
  s390/cache: prevent rebuild of shared_cpu_list
  s390/crypto: remove retry loop with sleep from PAES pkey invocation
  s390/pkey: improve pkey retry behavior
  s390/zcrypt: improve zcrypt retry behavior
  s390/zcrypt: introduce retries on in-kernel send CPRB functions
  s390/ap: introduce mutex to lock the AP bus scan
  s390/ap: rework ap_scan_bus() to return true on config change
  s390/ap: clarify AP scan bus related functions and variables
  s390/ap: rearm APQNs bindings complete completion
  s390/configs: increase number of LOCKDEP_BITS
  s390/vfio-ap: handle hardware checkstop state on queue reset operation
  s390/pai: change sampling event assignment for PMU device driver
  s390/boot: fix minor comment style damages
  s390/boot: do not check for zero-termination relocation entry
  s390/boot: make type of __vmlinux_relocs_64_start|end consistent
  s390/boot: sanitize kaslr_adjust_relocs() function prototype
  s390/boot: simplify GOT handling
  s390: vmlinux.lds.S: fix .got.plt assertion
  s390/boot: workaround current 'llvm-objdump -t -j ...' behavior
  ...

4 files changed, 74 insertions, 41 deletions

diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 52a44e353796..26afde0d1ed3 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -28,6 +28,7 @@
 #include <linux/jump_label.h>
 #include <linux/pci.h>
 #include <linux/printk.h>
+#include <linux/lockdep.h>
 
 #include <asm/isc.h>
 #include <asm/airq.h>
@@ -730,12 +731,12 @@ EXPORT_SYMBOL_GPL(zpci_disable_device);
  * 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
+ * and enabling the function via e.g. pci_enable_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.
+ * locking - asserted by lockdep.
  *
  * Return: 0 on success and an error value otherwise
  */
@@ -744,6 +745,7 @@ int zpci_hot_reset_device(struct zpci_dev *zdev)
 	u8 status;
 	int rc;
 
+	lockdep_assert_held(&zdev->state_lock);
 	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) */
@@ -806,7 +808,8 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state)
 	zdev->state =  state;
 
 	kref_init(&zdev->kref);
-	mutex_init(&zdev->lock);
+	mutex_init(&zdev->state_lock);
+	mutex_init(&zdev->fmb_lock);
 	mutex_init(&zdev->kzdev_lock);
 
 	rc = zpci_init_iommu(zdev);
@@ -870,6 +873,10 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
 {
 	int rc;
 
+	lockdep_assert_held(&zdev->state_lock);
+	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
+		return 0;
+
 	if (zdev->zbus->bus)
 		zpci_bus_remove_device(zdev, false);
 
@@ -889,7 +896,7 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
 }
 
 /**
- * zpci_device_reserved() - Mark device as resverved
+ * zpci_device_reserved() - Mark device as reserved
  * @zdev: the zpci_dev that was reserved
  *
  * Handle the case that a given zPCI function was reserved by another system.
@@ -899,8 +906,6 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
  */
 void zpci_device_reserved(struct zpci_dev *zdev)
 {
-	if (zdev->has_hp_slot)
-		zpci_exit_slot(zdev);
 	/*
 	 * Remove device from zpci_list as it is going away. This also
 	 * makes sure we ignore subsequent zPCI events for this device.
@@ -918,6 +923,9 @@ void zpci_release_device(struct kref *kref)
 	struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
 	int ret;
 
+	if (zdev->has_hp_slot)
+		zpci_exit_slot(zdev);
+
 	if (zdev->zbus->bus)
 		zpci_bus_remove_device(zdev, false);
 
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 6dde2263c79d..2cb5043a997d 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -91,9 +91,9 @@ static int pci_perf_show(struct seq_file *m, void *v)
 	if (!zdev)
 		return 0;
 
-	mutex_lock(&zdev->lock);
+	mutex_lock(&zdev->fmb_lock);
 	if (!zdev->fmb) {
-		mutex_unlock(&zdev->lock);
+		mutex_unlock(&zdev->fmb_lock);
 		seq_puts(m, "FMB statistics disabled\n");
 		return 0;
 	}
@@ -130,7 +130,7 @@ static int pci_perf_show(struct seq_file *m, void *v)
 	}
 
 	pci_sw_counter_show(m);
-	mutex_unlock(&zdev->lock);
+	mutex_unlock(&zdev->fmb_lock);
 	return 0;
 }
 
@@ -148,7 +148,7 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf,
 	if (rc)
 		return rc;
 
-	mutex_lock(&zdev->lock);
+	mutex_lock(&zdev->fmb_lock);
 	switch (val) {
 	case 0:
 		rc = zpci_fmb_disable_device(zdev);
@@ -157,7 +157,7 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf,
 		rc = zpci_fmb_enable_device(zdev);
 		break;
 	}
-	mutex_unlock(&zdev->lock);
+	mutex_unlock(&zdev->fmb_lock);
 	return rc ? rc : count;
 }
 
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 4d9773ef9e0a..dbe95ec5917e 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -267,6 +267,7 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
 	if (zdev) {
+		mutex_lock(&zdev->state_lock);
 		zpci_update_fh(zdev, ccdf->fh);
 		if (zdev->zbus->bus)
 			pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
@@ -294,6 +295,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	}
 	pci_dev_put(pdev);
 no_pdev:
+	if (zdev)
+		mutex_unlock(&zdev->state_lock);
 	zpci_zdev_put(zdev);
 }
 
@@ -326,6 +329,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 
 	zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n",
 		 ccdf->fid, ccdf->fh, ccdf->pec);
+
+	if (existing_zdev)
+		mutex_lock(&zdev->state_lock);
+
 	switch (ccdf->pec) {
 	case 0x0301: /* Reserved|Standby -> Configured */
 		if (!zdev) {
@@ -348,7 +355,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		break;
 	case 0x0303: /* Deconfiguration requested */
 		if (zdev) {
-			/* The event may have been queued before we confirgured
+			/* The event may have been queued before we configured
 			 * the device.
 			 */
 			if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
@@ -359,7 +366,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		break;
 	case 0x0304: /* Configured -> Standby|Reserved */
 		if (zdev) {
-			/* The event may have been queued before we confirgured
+			/* The event may have been queued before we configured
 			 * the device.:
 			 */
 			if (zdev->state == ZPCI_FN_STATE_CONFIGURED)
@@ -383,8 +390,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	default:
 		break;
 	}
-	if (existing_zdev)
+	if (existing_zdev) {
+		mutex_unlock(&zdev->state_lock);
 		zpci_zdev_put(zdev);
+	}
 }
 
 void zpci_event_availability(void *data)
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index 8a7abac51816..a0b872b74fe3 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -49,6 +49,39 @@ static ssize_t mio_enabled_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(mio_enabled);
 
+static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev)
+{
+	u8 status;
+	int ret;
+
+	pci_stop_and_remove_bus_device(pdev);
+	if (zdev_enabled(zdev)) {
+		ret = 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 (ret == -EINVAL)
+			ret = 0;
+		if (ret)
+			return ret;
+	}
+
+	ret = zpci_enable_device(zdev);
+	if (ret)
+		return ret;
+
+	if (zdev->dma_table) {
+		ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+					 virt_to_phys(zdev->dma_table), &status);
+		if (ret)
+			zpci_disable_device(zdev);
+	}
+	return ret;
+}
+
 static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t count)
 {
@@ -56,7 +89,6 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct zpci_dev *zdev = to_zpci(pdev);
 	int ret = 0;
-	u8 status;
 
 	/* Can't use device_remove_self() here as that would lead us to lock
 	 * the pci_rescan_remove_lock while holding the device' kernfs lock.
@@ -70,6 +102,12 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 	 */
 	kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
 	WARN_ON_ONCE(!kn);
+
+	/* Device needs to be configured and state must not change */
+	mutex_lock(&zdev->state_lock);
+	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
+		goto out;
+
 	/* device_remove_file() serializes concurrent calls ignoring all but
 	 * the first
 	 */
@@ -82,35 +120,13 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 	 */
 	pci_lock_rescan_remove();
 	if (pci_dev_is_added(pdev)) {
-		pci_stop_and_remove_bus_device(pdev);
-		if (zdev_enabled(zdev)) {
-			ret = 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 (ret == -EINVAL)
-				ret = 0;
-			if (ret)
-				goto out;
-		}
-
-		ret = zpci_enable_device(zdev);
-		if (ret)
-			goto out;
-
-		if (zdev->dma_table) {
-			ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-						 virt_to_phys(zdev->dma_table), &status);
-			if (ret)
-				zpci_disable_device(zdev);
-		}
+		ret = _do_recover(pdev, zdev);
 	}
-out:
 	pci_rescan_bus(zdev->zbus->bus);
 	pci_unlock_rescan_remove();
+
+out:
+	mutex_unlock(&zdev->state_lock);
 	if (kn)
 		sysfs_unbreak_active_protection(kn);
 	return ret ? ret : count;