diff options
Diffstat (limited to 'arch/s390/pci')
| -rw-r--r-- | arch/s390/pci/Makefile | 5 | ||||
| -rw-r--r-- | arch/s390/pci/pci.c | 365 | ||||
| -rw-r--r-- | arch/s390/pci/pci_bus.c | 123 | ||||
| -rw-r--r-- | arch/s390/pci/pci_bus.h | 15 | ||||
| -rw-r--r-- | arch/s390/pci/pci_clp.c | 68 | ||||
| -rw-r--r-- | arch/s390/pci/pci_debug.c | 29 | ||||
| -rw-r--r-- | arch/s390/pci/pci_dma.c | 732 | ||||
| -rw-r--r-- | arch/s390/pci/pci_event.c | 180 | ||||
| -rw-r--r-- | arch/s390/pci/pci_fixup.c | 23 | ||||
| -rw-r--r-- | arch/s390/pci/pci_insn.c | 122 | ||||
| -rw-r--r-- | arch/s390/pci/pci_iov.c | 59 | ||||
| -rw-r--r-- | arch/s390/pci/pci_iov.h | 9 | ||||
| -rw-r--r-- | arch/s390/pci/pci_irq.c | 130 | ||||
| -rw-r--r-- | arch/s390/pci/pci_kvm_hook.c | 2 | ||||
| -rw-r--r-- | arch/s390/pci/pci_mmio.c | 160 | ||||
| -rw-r--r-- | arch/s390/pci/pci_report.c | 157 | ||||
| -rw-r--r-- | arch/s390/pci/pci_report.h | 16 | ||||
| -rw-r--r-- | arch/s390/pci/pci_sysfs.c | 122 |
18 files changed, 1036 insertions, 1281 deletions
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index 5ae31ca9dd44..1810e0944a4e 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -3,7 +3,8 @@ # Makefile for the s390 PCI subsystem. # -obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \ +obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_clp.o \ pci_event.o pci_debug.o pci_insn.o pci_mmio.o \ - pci_bus.o pci_kvm_hook.o + pci_bus.o pci_kvm_hook.o pci_report.o pci_fixup.o obj-$(CONFIG_PCI_IOV) += pci_iov.o +obj-$(CONFIG_SYSFS) += pci_sysfs.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index ef38b1514c77..93d2c9c780fc 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -16,8 +16,7 @@ * Thomas Klein */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/slab.h> @@ -28,7 +27,10 @@ #include <linux/jump_label.h> #include <linux/pci.h> #include <linux/printk.h> +#include <linux/lockdep.h> +#include <linux/list_sort.h> +#include <asm/machine.h> #include <asm/isc.h> #include <asm/airq.h> #include <asm/facility.h> @@ -42,6 +44,7 @@ /* list of all detected zpci devices */ static LIST_HEAD(zpci_list); static DEFINE_SPINLOCK(zpci_list_lock); +static DEFINE_MUTEX(zpci_add_remove_lock); static DECLARE_BITMAP(zpci_domain, ZPCI_DOMAIN_BITMAP_SIZE); static DEFINE_SPINLOCK(zpci_domain_lock); @@ -67,6 +70,15 @@ EXPORT_SYMBOL_GPL(zpci_aipb); struct airq_iv *zpci_aif_sbv; EXPORT_SYMBOL_GPL(zpci_aif_sbv); +void zpci_zdev_put(struct zpci_dev *zdev) +{ + if (!zdev) + return; + mutex_lock(&zpci_add_remove_lock); + kref_put_lock(&zdev->kref, zpci_release_device, &zpci_list_lock); + mutex_unlock(&zpci_add_remove_lock); +} + struct zpci_dev *get_zdev_by_fid(u32 fid) { struct zpci_dev *tmp, *zdev = NULL; @@ -122,10 +134,13 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas, struct zpci_fib fib = {0}; u8 cc; - WARN_ON_ONCE(iota & 0x3fff); fib.pba = base; - fib.pal = limit; - fib.iota = iota | ZPCI_IOTA_RTTO_FLAG; + /* Work around off by one in ISM virt device */ + if (zdev->pft == PCI_FUNC_TYPE_ISM && limit > base) + fib.pal = limit + (1 << 12); + else + fib.pal = limit; + fib.iota = iota; fib.gd = zdev->gisa; cc = zpci_mod_fc(req, &fib, status); if (cc) @@ -153,7 +168,9 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) int zpci_fmb_enable_device(struct zpci_dev *zdev) { u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE); + struct zpci_iommu_ctrs *ctrs; struct zpci_fib fib = {0}; + unsigned long flags; u8 cc, status; if (zdev->fmb || sizeof(*zdev->fmb) < zdev->fmb_length) @@ -165,9 +182,17 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) WARN_ON((u64) zdev->fmb & 0xf); /* reset software counters */ - atomic64_set(&zdev->allocated_pages, 0); - atomic64_set(&zdev->mapped_pages, 0); - atomic64_set(&zdev->unmapped_pages, 0); + spin_lock_irqsave(&zdev->dom_lock, flags); + ctrs = zpci_get_iommu_ctrs(zdev); + if (ctrs) { + atomic64_set(&ctrs->mapped_pages, 0); + atomic64_set(&ctrs->unmapped_pages, 0); + atomic64_set(&ctrs->global_rpcits, 0); + atomic64_set(&ctrs->sync_map_rpcits, 0); + atomic64_set(&ctrs->sync_rpcits, 0); + } + spin_unlock_irqrestore(&zdev->dom_lock, flags); + fib.fmb_addr = virt_to_phys(zdev->fmb); fib.gd = zdev->gisa; @@ -238,68 +263,25 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, return 0; } -/* combine single writes by using store-block insn */ -void __iowrite64_copy(void __iomem *to, const void *from, size_t count) -{ - zpci_memcpy_toio(to, from, count); -} - -static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + pgprot_t prot) { - unsigned long offset, vaddr; - struct vm_struct *area; - phys_addr_t last_addr; - - last_addr = addr + size - 1; - if (!size || last_addr < addr) - return NULL; - + /* + * When PCI MIO instructions are unavailable the "physical" address + * encodes a hint for accessing the PCI memory space it represents. + * Just pass it unchanged such that ioread/iowrite can decode it. + */ if (!static_branch_unlikely(&have_mio)) - return (void __iomem *) addr; - - offset = addr & ~PAGE_MASK; - addr &= PAGE_MASK; - size = PAGE_ALIGN(size + offset); - area = get_vm_area(size, VM_IOREMAP); - if (!area) - return NULL; + return (void __iomem *)phys_addr; - vaddr = (unsigned long) area->addr; - if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) { - free_vm_area(area); - return NULL; - } - return (void __iomem *) ((unsigned long) area->addr + offset); -} - -void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot) -{ - return __ioremap(addr, size, __pgprot(prot)); + return generic_ioremap_prot(phys_addr, size, prot); } EXPORT_SYMBOL(ioremap_prot); -void __iomem *ioremap(phys_addr_t addr, size_t size) -{ - return __ioremap(addr, size, PAGE_KERNEL); -} -EXPORT_SYMBOL(ioremap); - -void __iomem *ioremap_wc(phys_addr_t addr, size_t size) -{ - return __ioremap(addr, size, pgprot_writecombine(PAGE_KERNEL)); -} -EXPORT_SYMBOL(ioremap_wc); - -void __iomem *ioremap_wt(phys_addr_t addr, size_t size) -{ - return __ioremap(addr, size, pgprot_writethrough(PAGE_KERNEL)); -} -EXPORT_SYMBOL(ioremap_wt); - void iounmap(volatile void __iomem *addr) { if (static_branch_likely(&have_mio)) - vunmap((__force void *) ((unsigned long) addr & PAGE_MASK)); + generic_iounmap(addr); } EXPORT_SYMBOL(iounmap); @@ -544,8 +526,7 @@ static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, return r; } -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources) +int zpci_setup_bus_resources(struct zpci_dev *zdev) { unsigned long addr, size, flags; struct resource *res; @@ -581,7 +562,6 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, return -ENOMEM; } zdev->bars[i].res = res; - pci_add_resource(resources, res); } zdev->has_resources = 1; @@ -590,17 +570,23 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { + struct resource *res; int i; + pci_lock_rescan_remove(); for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (!zdev->bars[i].size || !zdev->bars[i].res) + res = zdev->bars[i].res; + if (!res) continue; + release_resource(res); + pci_bus_remove_resource(zdev->zbus->bus, res); zpci_free_iomap(zdev, zdev->bars[i].map_idx); - release_resource(zdev->bars[i].res); - kfree(zdev->bars[i].res); + zdev->bars[i].res = NULL; + kfree(res); } zdev->has_resources = 0; + pci_unlock_rescan_remove(); } int pcibios_device_add(struct pci_dev *pdev) @@ -614,8 +600,6 @@ int pcibios_device_add(struct pci_dev *pdev) if (pdev->is_physfn) pdev->no_vf_scan = 1; - pdev->dev.groups = zpci_attr_groups; - pdev->dev.dma_ops = &s390_pci_dma_ops; zpci_map_resources(pdev); for (i = 0; i < PCI_STD_NUM_BARS; i++) { @@ -715,6 +699,23 @@ int zpci_enable_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_enable_device); +int zpci_reenable_device(struct zpci_dev *zdev) +{ + u8 status; + int rc; + + rc = zpci_enable_device(zdev); + if (rc) + return rc; + + rc = zpci_iommu_register_ioat(zdev, &status); + if (rc) + zpci_disable_device(zdev); + + return rc; +} +EXPORT_SYMBOL_GPL(zpci_reenable_device); + int zpci_disable_device(struct zpci_dev *zdev) { u32 fh = zdev->fh; @@ -753,20 +754,20 @@ 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 */ 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) */ @@ -782,21 +783,9 @@ int zpci_hot_reset_device(struct zpci_dev *zdev) return rc; } - rc = zpci_enable_device(zdev); - if (rc) - return rc; + rc = zpci_reenable_device(zdev); - if (zdev->dma_table) - rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, - virt_to_phys(zdev->dma_table), &status); - else - rc = zpci_dma_init_device(zdev); - if (rc) { - zpci_disable_device(zdev); - return rc; - } - - return 0; + return rc; } /** @@ -805,8 +794,9 @@ int zpci_hot_reset_device(struct zpci_dev *zdev) * @fh: Current Function Handle of the device to be created * @state: Initial state after creation either Standby or Configured * - * Creates a new zpci device and adds it to its, possibly newly created, zbus - * as well as zpci_list. + * Allocates a new struct zpci_dev and queries the platform for its details. + * If successful the device can subsequently be added to the zPCI subsystem + * using zpci_add_device(). * * Returns: the zdev on success or an error pointer otherwise */ @@ -815,7 +805,6 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state) struct zpci_dev *zdev; int rc; - zpci_dbg(1, "add fid:%x, fh:%x, c:%d\n", fid, fh, state); zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); if (!zdev) return ERR_PTR(-ENOMEM); @@ -830,10 +819,35 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state) goto error; 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); + return zdev; + +error: + zpci_dbg(0, "crt fid:%x, rc:%d\n", fid, rc); + kfree(zdev); + return ERR_PTR(rc); +} + +/** + * zpci_add_device() - Add a previously created zPCI device to the zPCI subsystem + * @zdev: The zPCI device to be added + * + * A struct zpci_dev is added to the zPCI subsystem and to a virtual PCI bus creating + * a new one as necessary. A hotplug slot is created and events start to be handled. + * If successful from this point on zpci_zdev_get() and zpci_zdev_put() must be used. + * If adding the struct zpci_dev fails the device was not added and should be freed. + * + * Return: 0 on success, or an error code otherwise + */ +int zpci_add_device(struct zpci_dev *zdev) +{ + int rc; + + mutex_lock(&zpci_add_remove_lock); + zpci_dbg(1, "add fid:%x, fh:%x, c:%d\n", zdev->fid, zdev->fh, zdev->state); rc = zpci_init_iommu(zdev); if (rc) goto error; @@ -842,18 +856,19 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state) if (rc) goto error_destroy_iommu; + kref_init(&zdev->kref); spin_lock(&zpci_list_lock); list_add_tail(&zdev->entry, &zpci_list); spin_unlock(&zpci_list_lock); - - return zdev; + mutex_unlock(&zpci_add_remove_lock); + return 0; error_destroy_iommu: zpci_destroy_iommu(zdev); error: - zpci_dbg(0, "add fid:%x, rc:%d\n", fid, rc); - kfree(zdev); - return ERR_PTR(rc); + zpci_dbg(0, "add fid:%x, rc:%d\n", zdev->fid, rc); + mutex_unlock(&zpci_add_remove_lock); + return rc; } bool zpci_is_device_configured(struct zpci_dev *zdev) @@ -870,32 +885,15 @@ bool zpci_is_device_configured(struct zpci_dev *zdev) * @fh: The general function handle supplied by the platform * * Given a device in the configuration state Configured, enables, scans and - * adds it to the common code PCI subsystem if possible. If the PCI device is - * parked because we can not yet create a PCI bus because we have not seen - * function 0, it is ignored but will be scanned once function 0 appears. - * If any failure occurs, the zpci_dev is left disabled. + * adds it to the common code PCI subsystem if possible. If any failure occurs, + * the zpci_dev is left disabled. * * Return: 0 on success, or an error code otherwise */ int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh) { - int rc; - zpci_update_fh(zdev, fh); - /* the PCI function will be scanned once function 0 appears */ - if (!zdev->zbus->bus) - return 0; - - /* For function 0 on a multi-function bus scan whole bus as we might - * have to pick up existing functions waiting for it to allow creating - * the PCI bus - */ - if (zdev->devfn == 0 && zdev->zbus->multifunction) - rc = zpci_bus_scan_bus(zdev->zbus); - else - rc = zpci_bus_scan_device(zdev); - - return rc; + return zpci_bus_scan_device(zdev); } /** @@ -912,14 +910,13 @@ 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); - if (zdev->dma_table) { - rc = zpci_dma_exit_device(zdev); - if (rc) - return rc; - } if (zdev_enabled(zdev)) { rc = zpci_disable_device(zdev); if (rc) @@ -936,65 +933,48 @@ 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. - * After a call to this function the zpci_dev can not be found via - * get_zdev_by_fid() anymore but may still be accessible via existing - * references though it will not be functional anymore. */ 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. - */ - spin_lock(&zpci_list_lock); - list_del(&zdev->entry); - spin_unlock(&zpci_list_lock); + lockdep_assert_held(&zdev->state_lock); + /* We may declare the device reserved multiple times */ + if (zdev->state == ZPCI_FN_STATE_RESERVED) + return; zdev->state = ZPCI_FN_STATE_RESERVED; zpci_dbg(3, "rsv fid:%x\n", zdev->fid); + /* + * The underlying device is gone. Allow the zdev to be freed + * as soon as all other references are gone by accounting for + * the removal as a dropped reference. + */ zpci_zdev_put(zdev); } void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); - int ret; - if (zdev->zbus->bus) - zpci_bus_remove_device(zdev, false); + lockdep_assert_held(&zpci_add_remove_lock); + WARN_ON(zdev->state != ZPCI_FN_STATE_RESERVED); + /* + * We already hold zpci_list_lock thanks to kref_put_lock(). + * This makes sure no new reference can be taken from the list. + */ + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); - if (zdev->dma_table) - zpci_dma_exit_device(zdev); - if (zdev_enabled(zdev)) - zpci_disable_device(zdev); + if (zdev->has_hp_slot) + zpci_exit_slot(zdev); - switch (zdev->state) { - case ZPCI_FN_STATE_CONFIGURED: - ret = sclp_pci_deconfigure(zdev->fid); - zpci_dbg(3, "deconf fid:%x, rc:%d\n", zdev->fid, ret); - fallthrough; - case ZPCI_FN_STATE_STANDBY: - if (zdev->has_hp_slot) - zpci_exit_slot(zdev); - spin_lock(&zpci_list_lock); - list_del(&zdev->entry); - spin_unlock(&zpci_list_lock); - zpci_dbg(3, "rsv fid:%x\n", zdev->fid); - fallthrough; - case ZPCI_FN_STATE_RESERVED: - if (zdev->has_resources) - zpci_cleanup_bus_resources(zdev); - zpci_bus_device_unregister(zdev); - zpci_destroy_iommu(zdev); - fallthrough; - default: - break; - } + if (zdev->has_resources) + zpci_cleanup_bus_resources(zdev); + + zpci_bus_device_unregister(zdev); + zpci_destroy_iommu(zdev); zpci_dbg(3, "rem fid:%x\n", zdev->fid); kfree_rcu(zdev, rcu); } @@ -1111,7 +1091,7 @@ char * __init pcibios_setup(char *str) return NULL; } if (!strcmp(str, "nomio")) { - S390_lowcore.machine_flags &= ~MACHINE_FLAG_PCI_MIO; + clear_machine_feature(MFEATURE_PCI_MIO); return NULL; } if (!strcmp(str, "force_floating")) { @@ -1130,6 +1110,50 @@ bool zpci_is_enabled(void) return s390_pci_initialized; } +static int zpci_cmp_rid(void *priv, const struct list_head *a, + const struct list_head *b) +{ + struct zpci_dev *za = container_of(a, struct zpci_dev, entry); + struct zpci_dev *zb = container_of(b, struct zpci_dev, entry); + + /* + * PCI functions without RID available maintain original order + * between themselves but sort before those with RID. + */ + if (za->rid == zb->rid) + return za->rid_available > zb->rid_available; + /* + * PCI functions with RID sort by RID ascending. + */ + return za->rid > zb->rid; +} + +static void zpci_add_devices(struct list_head *scan_list) +{ + struct zpci_dev *zdev, *tmp; + + list_sort(NULL, scan_list, &zpci_cmp_rid); + list_for_each_entry_safe(zdev, tmp, scan_list, entry) { + list_del_init(&zdev->entry); + if (zpci_add_device(zdev)) + kfree(zdev); + } +} + +int zpci_scan_devices(void) +{ + LIST_HEAD(scan_list); + int rc; + + rc = clp_scan_pci_devices(&scan_list); + if (rc) + return rc; + + zpci_add_devices(&scan_list); + zpci_bus_scan_busses(); + return 0; +} + static int __init pci_base_init(void) { int rc; @@ -1142,9 +1166,9 @@ static int __init pci_base_init(void) return 0; } - if (MACHINE_HAS_PCI_MIO) { + if (test_machine_feature(MFEATURE_PCI_MIO)) { static_branch_enable(&have_mio); - ctl_set_bit(2, 5); + system_ctl_set_bit(2, CR2_MIO_ADDRESSING_BIT); } rc = zpci_debug_init(); @@ -1159,21 +1183,18 @@ static int __init pci_base_init(void) if (rc) goto out_irq; - rc = zpci_dma_init(); + rc = zpci_scan_devices(); if (rc) - goto out_dma; + goto out_find; - rc = clp_scan_pci_devices(); + rc = zpci_fw_sysfs_init(); if (rc) goto out_find; - zpci_bus_scan_busses(); s390_pci_initialized = 1; return 0; out_find: - zpci_dma_exit(); -out_dma: zpci_irq_exit(); out_irq: zpci_mem_exit(); diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 6a8da1b742ae..72adc8f6e94f 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -7,18 +7,17 @@ * */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/slab.h> #include <linux/err.h> -#include <linux/export.h> #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/jump_label.h> #include <linux/pci.h> #include <linux/printk.h> +#include <linux/dma-direct.h> #include <asm/pci_clp.h> #include <asm/pci_dma.h> @@ -41,26 +40,21 @@ static int zpci_nb_devices; */ static int zpci_bus_prepare_device(struct zpci_dev *zdev) { - struct resource_entry *window, *n; - struct resource *res; - int rc; + int rc, i; if (!zdev_enabled(zdev)) { rc = zpci_enable_device(zdev); - if (rc) - return rc; - rc = zpci_dma_init_device(zdev); if (rc) { - zpci_disable_device(zdev); + pr_err("Enabling PCI function %08x failed\n", zdev->fid); return rc; } } if (!zdev->has_resources) { - zpci_setup_bus_resources(zdev, &zdev->zbus->resources); - resource_list_for_each_entry_safe(window, n, &zdev->zbus->resources) { - res = window->res; - pci_bus_add_resource(zdev->zbus->bus, res, 0); + zpci_setup_bus_resources(zdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (zdev->bars[i].res) + pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res); } } @@ -87,9 +81,8 @@ int zpci_bus_scan_device(struct zpci_dev *zdev) if (!pdev) return -ENODEV; - pci_bus_add_device(pdev); pci_lock_rescan_remove(); - pci_bus_add_devices(zdev->zbus->bus); + pci_bus_add_device(pdev); pci_unlock_rescan_remove(); return 0; @@ -132,11 +125,8 @@ void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error) * @zbus: the zbus to be scanned * * Enables and scans all PCI functions on the bus making them available to the - * common PCI code. If there is no function 0 on the zbus nothing is scanned. If - * a function does not have a slot yet because it was added to the zbus before - * function 0 the slot is created. If a PCI function fails to be initialized - * an error will be returned but attempts will still be made for all other - * functions on the bus. + * common PCI code. If a PCI function fails to be initialized an error will be + * returned but attempts will still be made for all other functions on the bus. * * Return: 0 on success, an error value otherwise */ @@ -179,9 +169,15 @@ void zpci_bus_scan_busses(void) mutex_unlock(&zbus_list_lock); } +static bool zpci_bus_is_multifunction_root(struct zpci_dev *zdev) +{ + return !s390_pci_no_rid && zdev->rid_available && + !zdev->vfn; +} + /* zpci_bus_create_pci_bus - Create the PCI bus associated with this zbus * @zbus: the zbus holding the zdevices - * @fr: PCI root function that will determine the bus's domain, and bus speeed + * @fr: PCI root function that will determine the bus's domain, and bus speed * @ops: the pci operations * * The PCI function @fr determines the domain (its UID), multifunction property @@ -199,7 +195,7 @@ static int zpci_bus_create_pci_bus(struct zpci_bus *zbus, struct zpci_dev *fr, s return domain; zbus->domain_nr = domain; - zbus->multifunction = fr->rid_available; + zbus->multifunction = zpci_bus_is_multifunction_root(fr); zbus->max_bus_speed = fr->max_bus_speed; /* @@ -213,7 +209,6 @@ static int zpci_bus_create_pci_bus(struct zpci_bus *zbus, struct zpci_dev *fr, s } zbus->bus = bus; - pci_bus_add_devices(bus); return 0; } @@ -244,13 +239,15 @@ static void zpci_bus_put(struct zpci_bus *zbus) kref_put(&zbus->kref, zpci_bus_release); } -static struct zpci_bus *zpci_bus_get(int pchid) +static struct zpci_bus *zpci_bus_get(int topo, bool topo_is_tid) { struct zpci_bus *zbus; mutex_lock(&zbus_list_lock); list_for_each_entry(zbus, &zbus_list, bus_next) { - if (pchid == zbus->pchid) { + if (!zbus->multifunction) + continue; + if (topo_is_tid == zbus->topo_is_tid && topo == zbus->topo) { kref_get(&zbus->kref); goto out_unlock; } @@ -261,7 +258,7 @@ out_unlock: return zbus; } -static struct zpci_bus *zpci_bus_alloc(int pchid) +static struct zpci_bus *zpci_bus_alloc(int topo, bool topo_is_tid) { struct zpci_bus *zbus; @@ -269,7 +266,8 @@ static struct zpci_bus *zpci_bus_alloc(int pchid) if (!zbus) return NULL; - zbus->pchid = pchid; + zbus->topo = topo; + zbus->topo_is_tid = topo_is_tid; INIT_LIST_HEAD(&zbus->bus_next); mutex_lock(&zbus_list_lock); list_add_tail(&zbus->bus_next, &zbus_list); @@ -286,10 +284,32 @@ static struct zpci_bus *zpci_bus_alloc(int pchid) return zbus; } +static void pci_dma_range_setup(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + u64 aligned_end, size; + dma_addr_t dma_start; + int ret; + + dma_start = PAGE_ALIGN(zdev->start_dma); + aligned_end = PAGE_ALIGN_DOWN(zdev->end_dma + 1); + if (aligned_end >= dma_start) + size = aligned_end - dma_start; + else + size = 0; + WARN_ON_ONCE(size == 0); + + ret = dma_direct_set_offset(&pdev->dev, 0, dma_start, size); + if (ret) + pr_err("Failed to allocate DMA range map for %s\n", pci_name(pdev)); +} + void pcibios_bus_add_device(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); + pci_dma_range_setup(pdev); + /* * With pdev->no_vf_scan the common PCI probing code does not * perform PF/VF linking. @@ -304,19 +324,22 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) { int rc = -EINVAL; + if (zbus->multifunction) { + if (!zdev->rid_available) { + WARN_ONCE(1, "rid_available not set for multifunction\n"); + return rc; + } + zdev->devfn = zdev->rid & ZPCI_RID_MASK_DEVFN; + } + if (zbus->function[zdev->devfn]) { pr_err("devfn %04x is already assigned\n", zdev->devfn); return rc; } - zdev->zbus = zbus; zbus->function[zdev->devfn] = zdev; zpci_nb_devices++; - if (zbus->multifunction && !zdev->rid_available) { - WARN_ONCE(1, "rid_available not set for multifunction\n"); - goto error; - } rc = zpci_init_slot(zdev); if (rc) goto error; @@ -331,10 +354,25 @@ error: return rc; } +static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + struct pci_dev *pdev; + + if (!zdev->vfn) + return false; + + pdev = zpci_iov_find_parent_pf(zbus, zdev); + if (!pdev) + return true; + pci_dev_put(pdev); + return false; +} + int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) { + bool topo_is_tid = zdev->tid_avail; struct zpci_bus *zbus = NULL; - int rc = -EBADF; + int topo, rc = -EBADF; if (zpci_nb_devices == ZPCI_NR_DEVICES) { pr_warn("Adding PCI function %08x failed because the configured limit of %d is reached\n", @@ -342,14 +380,19 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) return -ENOSPC; } - if (zdev->devfn >= ZPCI_FUNCTIONS_PER_BUS) - return -EINVAL; - - if (!s390_pci_no_rid && zdev->rid_available) - zbus = zpci_bus_get(zdev->pchid); + topo = topo_is_tid ? zdev->tid : zdev->pchid; + zbus = zpci_bus_get(topo, topo_is_tid); + /* + * An isolated VF gets its own domain/bus even if there exists + * a matching domain/bus already + */ + if (zbus && zpci_bus_is_isolated_vf(zbus, zdev)) { + zpci_bus_put(zbus); + zbus = NULL; + } if (!zbus) { - zbus = zpci_bus_alloc(zdev->pchid); + zbus = zpci_bus_alloc(topo, topo_is_tid); if (!zbus) return -ENOMEM; } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e96c9860e064..ae3d7a9159bd 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -6,6 +6,10 @@ * Pierre Morel <pmorel@linux.ibm.com> * */ +#ifndef __S390_PCI_BUS_H +#define __S390_PCI_BUS_H + +#include <linux/pci.h> int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops); void zpci_bus_device_unregister(struct zpci_dev *zdev); @@ -17,11 +21,8 @@ int zpci_bus_scan_device(struct zpci_dev *zdev); void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error); void zpci_release_device(struct kref *kref); -static inline void zpci_zdev_put(struct zpci_dev *zdev) -{ - if (zdev) - kref_put(&zdev->kref, zpci_release_device); -} + +void zpci_zdev_put(struct zpci_dev *zdev); static inline void zpci_zdev_get(struct zpci_dev *zdev) { @@ -30,8 +31,7 @@ static inline void zpci_zdev_get(struct zpci_dev *zdev) int zpci_alloc_domain(int domain); void zpci_free_domain(int domain); -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources); +int zpci_setup_bus_resources(struct zpci_dev *zdev); static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, unsigned int devfn) @@ -41,3 +41,4 @@ static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn]; } +#endif /* __S390_PCI_BUS_H */ diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index ee367798e388..177aa0214547 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -6,10 +6,8 @@ * Jan Glauber <jang@linux.vnet.ibm.com> */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt -#include <linux/compat.h> #include <linux/kernel.h> #include <linux/miscdevice.h> #include <linux/slab.h> @@ -20,6 +18,7 @@ #include <asm/asm-extable.h> #include <asm/pci_debug.h> #include <asm/pci_clp.h> +#include <asm/asm.h> #include <asm/clp.h> #include <uapi/asm/clp.h> @@ -52,18 +51,20 @@ static inline void zpci_err_clp(unsigned int rsp, int rc) static inline int clp_get_ilp(unsigned long *ilp) { unsigned long mask; - int cc = 3; + int cc, exception; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rrf,0xb9a00000,%[mask],%[cmd],8,0\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [mask] "=d" (mask) : [cmd] "a" (1) - : "cc"); + : CC_OUT(cc, cc), [mask] "=d" (mask), [exc] "+d" (exception) + : [cmd] "a" (1) + : CC_CLOBBER); *ilp = mask; - return cc; + return exception ? 3 : CC_TRANSFORM(cc); } /* @@ -72,19 +73,20 @@ static inline int clp_get_ilp(unsigned long *ilp) static __always_inline int clp_req(void *data, unsigned int lps) { struct { u8 _[CLP_BLK_SIZE]; } *req = data; + int cc, exception; u64 ignored; - int cc = 3; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rrf,0xb9a00000,%[ign],%[req],0,%[lps]\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [ign] "=d" (ignored), "+m" (*req) + : CC_OUT(cc, cc), [ign] "=d" (ignored), "+m" (*req), [exc] "+d" (exception) : [req] "a" (req), [lps] "i" (lps) - : "cc"); - return cc; + : CC_CLOBBER); + return exception ? 3 : CC_TRANSFORM(cc); } static void *clp_alloc_block(gfp_t gfp_mask) @@ -108,6 +110,7 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev, zdev->version = response->version; zdev->maxstbl = response->maxstbl; zdev->dtsm = response->dtsm; + zdev->rtr_avail = response->rtr; switch (response->version) { case 1: @@ -162,12 +165,16 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, zdev->pft = response->pft; zdev->vfn = response->vfn; zdev->port = response->port; + zdev->fidparm = response->fidparm; zdev->uid = response->uid; zdev->fmb_length = sizeof(u32) * response->fmb_len; - zdev->rid_available = response->rid_avail; zdev->is_physfn = response->is_physfn; - if (!s390_pci_no_rid && zdev->rid_available) - zdev->devfn = response->rid & ZPCI_RID_MASK_DEVFN; + zdev->rid_available = response->rid_avail; + if (zdev->rid_available) + zdev->rid = response->rid; + zdev->tid_avail = response->tid_avail; + if (zdev->tid_avail) + zdev->tid = response->tid; memcpy(zdev->pfip, response->pfip, sizeof(zdev->pfip)); if (response->util_str_avail) { @@ -407,6 +414,7 @@ static int clp_find_pci(struct clp_req_rsp_list_pci *rrb, u32 fid, static void __clp_add(struct clp_fh_list_entry *entry, void *data) { + struct list_head *scan_list = data; struct zpci_dev *zdev; if (!entry->vendor_id) @@ -417,10 +425,13 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data) zpci_zdev_put(zdev); return; } - zpci_create_device(entry->fid, entry->fh, entry->config_state); + zdev = zpci_create_device(entry->fid, entry->fh, entry->config_state); + if (IS_ERR(zdev)) + return; + list_add_tail(&zdev->entry, scan_list); } -int clp_scan_pci_devices(void) +int clp_scan_pci_devices(struct list_head *scan_list) { struct clp_req_rsp_list_pci *rrb; int rc; @@ -429,7 +440,7 @@ int clp_scan_pci_devices(void) if (!rrb) return -ENOMEM; - rc = clp_list_pci(rrb, NULL, __clp_add); + rc = clp_list_pci(rrb, scan_list, __clp_add); clp_free_block(rrb); return rc; @@ -638,7 +649,7 @@ static long clp_misc_ioctl(struct file *filp, unsigned int cmd, if (cmd != CLP_SYNC) return -EINVAL; - argp = is_compat_task() ? compat_ptr(arg) : (void __user *) arg; + argp = (void __user *)arg; if (copy_from_user(&req, argp, sizeof(req))) return -EFAULT; if (req.r != 0) @@ -656,8 +667,6 @@ static const struct file_operations clp_misc_fops = { .open = nonseekable_open, .release = clp_misc_release, .unlocked_ioctl = clp_misc_ioctl, - .compat_ioctl = clp_misc_ioctl, - .llseek = no_llseek, }; static struct miscdevice clp_misc_device = { @@ -666,9 +675,4 @@ static struct miscdevice clp_misc_device = { .fops = &clp_misc_fops, }; -static int __init clp_misc_init(void) -{ - return misc_register(&clp_misc_device); -} - -device_initcall(clp_misc_init); +builtin_misc_device(clp_misc_device); diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index ca6bd98eec13..c7ed7bf254b5 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -6,8 +6,7 @@ * Jan Glauber <jang@linux.vnet.ibm.com> */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/seq_file.h> @@ -53,9 +52,11 @@ static char *pci_fmt3_names[] = { }; static char *pci_sw_names[] = { - "Allocated pages", "Mapped pages", "Unmapped pages", + "Global RPCITs", + "Sync Map RPCITs", + "Sync RPCITs", }; static void pci_fmb_show(struct seq_file *m, char *name[], int length, @@ -70,12 +71,22 @@ static void pci_fmb_show(struct seq_file *m, char *name[], int length, static void pci_sw_counter_show(struct seq_file *m) { struct zpci_dev *zdev = m->private; - atomic64_t *counter = &zdev->allocated_pages; + struct zpci_iommu_ctrs *ctrs; + atomic64_t *counter; + unsigned long flags; int i; + spin_lock_irqsave(&zdev->dom_lock, flags); + ctrs = zpci_get_iommu_ctrs(m->private); + if (!ctrs) + goto unlock; + + counter = &ctrs->mapped_pages; for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++) seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i], atomic64_read(counter)); +unlock: + spin_unlock_irqrestore(&zdev->dom_lock, flags); } static int pci_perf_show(struct seq_file *m, void *v) @@ -85,9 +96,9 @@ 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; } @@ -124,7 +135,7 @@ 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; } @@ -142,7 +153,7 @@ 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); @@ -151,7 +162,7 @@ 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_dma.c b/arch/s390/pci/pci_dma.c deleted file mode 100644 index ea478d11fbd1..000000000000 --- a/arch/s390/pci/pci_dma.c +++ /dev/null @@ -1,732 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright IBM Corp. 2012 - * - * Author(s): - * Jan Glauber <jang@linux.vnet.ibm.com> - */ - -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/export.h> -#include <linux/iommu-helper.h> -#include <linux/dma-map-ops.h> -#include <linux/vmalloc.h> -#include <linux/pci.h> -#include <asm/pci_dma.h> - -static struct kmem_cache *dma_region_table_cache; -static struct kmem_cache *dma_page_table_cache; -static int s390_iommu_strict; -static u64 s390_iommu_aperture; -static u32 s390_iommu_aperture_factor = 1; - -static int zpci_refresh_global(struct zpci_dev *zdev) -{ - return zpci_refresh_trans((u64) zdev->fh << 32, zdev->start_dma, - zdev->iommu_pages * PAGE_SIZE); -} - -unsigned long *dma_alloc_cpu_table(void) -{ - unsigned long *table, *entry; - - table = kmem_cache_alloc(dma_region_table_cache, GFP_ATOMIC); - if (!table) - return NULL; - - for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++) - *entry = ZPCI_TABLE_INVALID; - return table; -} - -static void dma_free_cpu_table(void *table) -{ - kmem_cache_free(dma_region_table_cache, table); -} - -static unsigned long *dma_alloc_page_table(void) -{ - unsigned long *table, *entry; - - table = kmem_cache_alloc(dma_page_table_cache, GFP_ATOMIC); - if (!table) - return NULL; - - for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++) - *entry = ZPCI_PTE_INVALID; - return table; -} - -static void dma_free_page_table(void *table) -{ - kmem_cache_free(dma_page_table_cache, table); -} - -static unsigned long *dma_get_seg_table_origin(unsigned long *rtep) -{ - unsigned long old_rte, rte; - unsigned long *sto; - - rte = READ_ONCE(*rtep); - if (reg_entry_isvalid(rte)) { - sto = get_rt_sto(rte); - } else { - sto = dma_alloc_cpu_table(); - if (!sto) - return NULL; - - set_rt_sto(&rte, virt_to_phys(sto)); - validate_rt_entry(&rte); - entry_clr_protected(&rte); - - old_rte = cmpxchg(rtep, ZPCI_TABLE_INVALID, rte); - if (old_rte != ZPCI_TABLE_INVALID) { - /* Somone else was faster, use theirs */ - dma_free_cpu_table(sto); - sto = get_rt_sto(old_rte); - } - } - return sto; -} - -static unsigned long *dma_get_page_table_origin(unsigned long *step) -{ - unsigned long old_ste, ste; - unsigned long *pto; - - ste = READ_ONCE(*step); - if (reg_entry_isvalid(ste)) { - pto = get_st_pto(ste); - } else { - pto = dma_alloc_page_table(); - if (!pto) - return NULL; - set_st_pto(&ste, virt_to_phys(pto)); - validate_st_entry(&ste); - entry_clr_protected(&ste); - - old_ste = cmpxchg(step, ZPCI_TABLE_INVALID, ste); - if (old_ste != ZPCI_TABLE_INVALID) { - /* Somone else was faster, use theirs */ - dma_free_page_table(pto); - pto = get_st_pto(old_ste); - } - } - return pto; -} - -unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr) -{ - unsigned long *sto, *pto; - unsigned int rtx, sx, px; - - rtx = calc_rtx(dma_addr); - sto = dma_get_seg_table_origin(&rto[rtx]); - if (!sto) - return NULL; - - sx = calc_sx(dma_addr); - pto = dma_get_page_table_origin(&sto[sx]); - if (!pto) - return NULL; - - px = calc_px(dma_addr); - return &pto[px]; -} - -void dma_update_cpu_trans(unsigned long *ptep, phys_addr_t page_addr, int flags) -{ - unsigned long pte; - - pte = READ_ONCE(*ptep); - if (flags & ZPCI_PTE_INVALID) { - invalidate_pt_entry(&pte); - } else { - set_pt_pfaa(&pte, page_addr); - validate_pt_entry(&pte); - } - - if (flags & ZPCI_TABLE_PROTECTED) - entry_set_protected(&pte); - else - entry_clr_protected(&pte); - - xchg(ptep, pte); -} - -static int __dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa, - dma_addr_t dma_addr, size_t size, int flags) -{ - unsigned int nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - phys_addr_t page_addr = (pa & PAGE_MASK); - unsigned long *entry; - int i, rc = 0; - - if (!nr_pages) - return -EINVAL; - - if (!zdev->dma_table) - return -EINVAL; - - for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); - if (!entry) { - rc = -ENOMEM; - goto undo_cpu_trans; - } - dma_update_cpu_trans(entry, page_addr, flags); - page_addr += PAGE_SIZE; - dma_addr += PAGE_SIZE; - } - -undo_cpu_trans: - if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) { - flags = ZPCI_PTE_INVALID; - while (i-- > 0) { - page_addr -= PAGE_SIZE; - dma_addr -= PAGE_SIZE; - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); - if (!entry) - break; - dma_update_cpu_trans(entry, page_addr, flags); - } - } - return rc; -} - -static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr, - size_t size, int flags) -{ - unsigned long irqflags; - int ret; - - /* - * With zdev->tlb_refresh == 0, rpcit is not required to establish new - * translations when previously invalid translation-table entries are - * validated. With lazy unmap, rpcit is skipped for previously valid - * entries, but a global rpcit is then required before any address can - * be re-used, i.e. after each iommu bitmap wrap-around. - */ - if ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID) { - if (!zdev->tlb_refresh) - return 0; - } else { - if (!s390_iommu_strict) - return 0; - } - - ret = zpci_refresh_trans((u64) zdev->fh << 32, dma_addr, - PAGE_ALIGN(size)); - if (ret == -ENOMEM && !s390_iommu_strict) { - /* enable the hypervisor to free some resources */ - if (zpci_refresh_global(zdev)) - goto out; - - spin_lock_irqsave(&zdev->iommu_bitmap_lock, irqflags); - bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap, - zdev->lazy_bitmap, zdev->iommu_pages); - bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages); - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, irqflags); - ret = 0; - } -out: - return ret; -} - -static int dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa, - dma_addr_t dma_addr, size_t size, int flags) -{ - int rc; - - rc = __dma_update_trans(zdev, pa, dma_addr, size, flags); - if (rc) - return rc; - - rc = __dma_purge_tlb(zdev, dma_addr, size, flags); - if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) - __dma_update_trans(zdev, pa, dma_addr, size, ZPCI_PTE_INVALID); - - return rc; -} - -void dma_free_seg_table(unsigned long entry) -{ - unsigned long *sto = get_rt_sto(entry); - int sx; - - for (sx = 0; sx < ZPCI_TABLE_ENTRIES; sx++) - if (reg_entry_isvalid(sto[sx])) - dma_free_page_table(get_st_pto(sto[sx])); - - dma_free_cpu_table(sto); -} - -void dma_cleanup_tables(unsigned long *table) -{ - int rtx; - - if (!table) - return; - - for (rtx = 0; rtx < ZPCI_TABLE_ENTRIES; rtx++) - if (reg_entry_isvalid(table[rtx])) - dma_free_seg_table(table[rtx]); - - dma_free_cpu_table(table); -} - -static unsigned long __dma_alloc_iommu(struct device *dev, - unsigned long start, int size) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - - return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages, - start, size, zdev->start_dma >> PAGE_SHIFT, - dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT), - 0); -} - -static dma_addr_t dma_alloc_address(struct device *dev, int size) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long offset, flags; - - spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags); - offset = __dma_alloc_iommu(dev, zdev->next_bit, size); - if (offset == -1) { - if (!s390_iommu_strict) { - /* global flush before DMA addresses are reused */ - if (zpci_refresh_global(zdev)) - goto out_error; - - bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap, - zdev->lazy_bitmap, zdev->iommu_pages); - bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages); - } - /* wrap-around */ - offset = __dma_alloc_iommu(dev, 0, size); - if (offset == -1) - goto out_error; - } - zdev->next_bit = offset + size; - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); - - return zdev->start_dma + offset * PAGE_SIZE; - -out_error: - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); - return DMA_MAPPING_ERROR; -} - -static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long flags, offset; - - offset = (dma_addr - zdev->start_dma) >> PAGE_SHIFT; - - spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags); - if (!zdev->iommu_bitmap) - goto out; - - if (s390_iommu_strict) - bitmap_clear(zdev->iommu_bitmap, offset, size); - else - bitmap_set(zdev->lazy_bitmap, offset, size); - -out: - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); -} - -static inline void zpci_err_dma(unsigned long rc, unsigned long addr) -{ - struct { - unsigned long rc; - unsigned long addr; - } __packed data = {rc, addr}; - - zpci_err_hex(&data, sizeof(data)); -} - -static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long pa = page_to_phys(page) + offset; - int flags = ZPCI_PTE_VALID; - unsigned long nr_pages; - dma_addr_t dma_addr; - int ret; - - /* This rounds up number of pages based on size and offset */ - nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); - dma_addr = dma_alloc_address(dev, nr_pages); - if (dma_addr == DMA_MAPPING_ERROR) { - ret = -ENOSPC; - goto out_err; - } - - /* Use rounded up size */ - size = nr_pages * PAGE_SIZE; - - if (direction == DMA_NONE || direction == DMA_TO_DEVICE) - flags |= ZPCI_TABLE_PROTECTED; - - ret = dma_update_trans(zdev, pa, dma_addr, size, flags); - if (ret) - goto out_free; - - atomic64_add(nr_pages, &zdev->mapped_pages); - return dma_addr + (offset & ~PAGE_MASK); - -out_free: - dma_free_address(dev, dma_addr, nr_pages); -out_err: - zpci_err("map error:\n"); - zpci_err_dma(ret, pa); - return DMA_MAPPING_ERROR; -} - -static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - int npages, ret; - - npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); - dma_addr = dma_addr & PAGE_MASK; - ret = dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE, - ZPCI_PTE_INVALID); - if (ret) { - zpci_err("unmap error:\n"); - zpci_err_dma(ret, dma_addr); - return; - } - - atomic64_add(npages, &zdev->unmapped_pages); - dma_free_address(dev, dma_addr, npages); -} - -static void *s390_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - struct page *page; - phys_addr_t pa; - dma_addr_t map; - - size = PAGE_ALIGN(size); - page = alloc_pages(flag | __GFP_ZERO, get_order(size)); - if (!page) - return NULL; - - pa = page_to_phys(page); - map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, 0); - if (dma_mapping_error(dev, map)) { - __free_pages(page, get_order(size)); - return NULL; - } - - atomic64_add(size / PAGE_SIZE, &zdev->allocated_pages); - if (dma_handle) - *dma_handle = map; - return phys_to_virt(pa); -} - -static void s390_dma_free(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - - size = PAGE_ALIGN(size); - atomic64_sub(size / PAGE_SIZE, &zdev->allocated_pages); - s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, 0); - free_pages((unsigned long)vaddr, get_order(size)); -} - -/* Map a segment into a contiguous dma address area */ -static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg, - size_t size, dma_addr_t *handle, - enum dma_data_direction dir) -{ - unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - dma_addr_t dma_addr_base, dma_addr; - int flags = ZPCI_PTE_VALID; - struct scatterlist *s; - phys_addr_t pa = 0; - int ret; - - dma_addr_base = dma_alloc_address(dev, nr_pages); - if (dma_addr_base == DMA_MAPPING_ERROR) - return -ENOMEM; - - dma_addr = dma_addr_base; - if (dir == DMA_NONE || dir == DMA_TO_DEVICE) - flags |= ZPCI_TABLE_PROTECTED; - - for (s = sg; dma_addr < dma_addr_base + size; s = sg_next(s)) { - pa = page_to_phys(sg_page(s)); - ret = __dma_update_trans(zdev, pa, dma_addr, - s->offset + s->length, flags); - if (ret) - goto unmap; - - dma_addr += s->offset + s->length; - } - ret = __dma_purge_tlb(zdev, dma_addr_base, size, flags); - if (ret) - goto unmap; - - *handle = dma_addr_base; - atomic64_add(nr_pages, &zdev->mapped_pages); - - return ret; - -unmap: - dma_update_trans(zdev, 0, dma_addr_base, dma_addr - dma_addr_base, - ZPCI_PTE_INVALID); - dma_free_address(dev, dma_addr_base, nr_pages); - zpci_err("map error:\n"); - zpci_err_dma(ret, pa); - return ret; -} - -static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nr_elements, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s = sg, *start = sg, *dma = sg; - unsigned int max = dma_get_max_seg_size(dev); - unsigned int size = s->offset + s->length; - unsigned int offset = s->offset; - int count = 0, i, ret; - - for (i = 1; i < nr_elements; i++) { - s = sg_next(s); - - s->dma_length = 0; - - if (s->offset || (size & ~PAGE_MASK) || - size + s->length > max) { - ret = __s390_dma_map_sg(dev, start, size, - &dma->dma_address, dir); - if (ret) - goto unmap; - - dma->dma_address += offset; - dma->dma_length = size - offset; - - size = offset = s->offset; - start = s; - dma = sg_next(dma); - count++; - } - size += s->length; - } - ret = __s390_dma_map_sg(dev, start, size, &dma->dma_address, dir); - if (ret) - goto unmap; - - dma->dma_address += offset; - dma->dma_length = size - offset; - - return count + 1; -unmap: - for_each_sg(sg, s, count, i) - s390_dma_unmap_pages(dev, sg_dma_address(s), sg_dma_len(s), - dir, attrs); - - return ret; -} - -static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, - int nr_elements, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nr_elements, i) { - if (s->dma_length) - s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, - dir, attrs); - s->dma_address = 0; - s->dma_length = 0; - } -} - -int zpci_dma_init_device(struct zpci_dev *zdev) -{ - u8 status; - int rc; - - /* - * At this point, if the device is part of an IOMMU domain, this would - * be a strong hint towards a bug in the IOMMU API (common) code and/or - * simultaneous access via IOMMU and DMA API. So let's issue a warning. - */ - WARN_ON(zdev->s390_domain); - - spin_lock_init(&zdev->iommu_bitmap_lock); - - zdev->dma_table = dma_alloc_cpu_table(); - if (!zdev->dma_table) { - rc = -ENOMEM; - goto out; - } - - /* - * Restrict the iommu bitmap size to the minimum of the following: - * - s390_iommu_aperture which defaults to high_memory - * - 3-level pagetable address limit minus start_dma offset - * - DMA address range allowed by the hardware (clp query pci fn) - * - * Also set zdev->end_dma to the actual end address of the usable - * range, instead of the theoretical maximum as reported by hardware. - * - * This limits the number of concurrently usable DMA mappings since - * for each DMA mapped memory address we need a DMA address including - * extra DMA addresses for multiple mappings of the same memory address. - */ - zdev->start_dma = PAGE_ALIGN(zdev->start_dma); - zdev->iommu_size = min3(s390_iommu_aperture, - ZPCI_TABLE_SIZE_RT - zdev->start_dma, - zdev->end_dma - zdev->start_dma + 1); - zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1; - zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT; - zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); - if (!zdev->iommu_bitmap) { - rc = -ENOMEM; - goto free_dma_table; - } - if (!s390_iommu_strict) { - zdev->lazy_bitmap = vzalloc(zdev->iommu_pages / 8); - if (!zdev->lazy_bitmap) { - rc = -ENOMEM; - goto free_bitmap; - } - - } - if (zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, - virt_to_phys(zdev->dma_table), &status)) { - rc = -EIO; - goto free_bitmap; - } - - return 0; -free_bitmap: - vfree(zdev->iommu_bitmap); - zdev->iommu_bitmap = NULL; - vfree(zdev->lazy_bitmap); - zdev->lazy_bitmap = NULL; -free_dma_table: - dma_free_cpu_table(zdev->dma_table); - zdev->dma_table = NULL; -out: - return rc; -} - -int zpci_dma_exit_device(struct zpci_dev *zdev) -{ - int cc = 0; - - /* - * At this point, if the device is part of an IOMMU domain, this would - * be a strong hint towards a bug in the IOMMU API (common) code and/or - * simultaneous access via IOMMU and DMA API. So let's issue a warning. - */ - WARN_ON(zdev->s390_domain); - if (zdev_enabled(zdev)) - cc = zpci_unregister_ioat(zdev, 0); - /* - * cc == 3 indicates the function is gone already. This can happen - * if the function was deconfigured/disabled suddenly and we have not - * received a new handle yet. - */ - if (cc && cc != 3) - return -EIO; - - dma_cleanup_tables(zdev->dma_table); - zdev->dma_table = NULL; - vfree(zdev->iommu_bitmap); - zdev->iommu_bitmap = NULL; - vfree(zdev->lazy_bitmap); - zdev->lazy_bitmap = NULL; - zdev->next_bit = 0; - return 0; -} - -static int __init dma_alloc_cpu_table_caches(void) -{ - dma_region_table_cache = kmem_cache_create("PCI_DMA_region_tables", - ZPCI_TABLE_SIZE, ZPCI_TABLE_ALIGN, - 0, NULL); - if (!dma_region_table_cache) - return -ENOMEM; - - dma_page_table_cache = kmem_cache_create("PCI_DMA_page_tables", - ZPCI_PT_SIZE, ZPCI_PT_ALIGN, - 0, NULL); - if (!dma_page_table_cache) { - kmem_cache_destroy(dma_region_table_cache); - return -ENOMEM; - } - return 0; -} - -int __init zpci_dma_init(void) -{ - s390_iommu_aperture = (u64)virt_to_phys(high_memory); - if (!s390_iommu_aperture_factor) - s390_iommu_aperture = ULONG_MAX; - else - s390_iommu_aperture *= s390_iommu_aperture_factor; - - return dma_alloc_cpu_table_caches(); -} - -void zpci_dma_exit(void) -{ - kmem_cache_destroy(dma_page_table_cache); - kmem_cache_destroy(dma_region_table_cache); -} - -const struct dma_map_ops s390_pci_dma_ops = { - .alloc = s390_dma_alloc, - .free = s390_dma_free, - .map_sg = s390_dma_map_sg, - .unmap_sg = s390_dma_unmap_sg, - .map_page = s390_dma_map_pages, - .unmap_page = s390_dma_unmap_pages, - .mmap = dma_common_mmap, - .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, - .free_pages = dma_common_free_pages, - /* dma_supported is unconditionally true without a callback */ -}; -EXPORT_SYMBOL_GPL(s390_pci_dma_ops); - -static int __init s390_iommu_setup(char *str) -{ - if (!strcmp(str, "strict")) - s390_iommu_strict = 1; - return 1; -} - -__setup("s390_iommu=", s390_iommu_setup); - -static int __init s390_iommu_aperture_setup(char *str) -{ - if (kstrtou32(str, 10, &s390_iommu_aperture_factor)) - s390_iommu_aperture_factor = 1; - return 1; -} - -__setup("s390_iommu_aperture=", s390_iommu_aperture_setup); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index b9324ca2eb94..839bd91c056e 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -6,8 +6,7 @@ * Jan Glauber <jang@linux.vnet.ibm.com> */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/pci.h> @@ -16,6 +15,7 @@ #include <asm/sclp.h> #include "pci_bus.h" +#include "pci_report.h" /* Content Code Description for PCI Function Error */ struct zpci_ccdf_err { @@ -53,15 +53,23 @@ static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res) case PCI_ERS_RESULT_CAN_RECOVER: case PCI_ERS_RESULT_RECOVERED: case PCI_ERS_RESULT_NEED_RESET: + case PCI_ERS_RESULT_NONE: return false; default: return true; } } -static bool is_passed_through(struct zpci_dev *zdev) +static bool is_passed_through(struct pci_dev *pdev) { - return zdev->s390_domain; + struct zpci_dev *zdev = to_zpci(pdev); + bool ret; + + mutex_lock(&zdev->kzdev_lock); + ret = !!zdev->kzdev; + mutex_unlock(&zdev->kzdev_lock); + + return ret; } static bool is_driver_supported(struct pci_driver *driver) @@ -70,10 +78,6 @@ static bool is_driver_supported(struct pci_driver *driver) 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; } @@ -83,6 +87,7 @@ static pci_ers_result_t zpci_event_notify_error_detected(struct pci_dev *pdev, pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; ers_res = driver->err_handler->error_detected(pdev, pdev->error_state); + pci_uevent_ers(pdev, ers_res); 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) @@ -98,6 +103,10 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, struct zpci_dev *zdev = to_zpci(pdev); int rc; + /* The underlying device may have been disabled by the event */ + if (!zdev_enabled(zdev)) + return PCI_ERS_RESULT_NEED_RESET; + pr_info("%s: Unblocking device access for examination\n", pci_name(pdev)); rc = zpci_reset_load_store_blocked(zdev); if (rc) { @@ -106,16 +115,18 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, return PCI_ERS_RESULT_NEED_RESET; } - if (driver->err_handler->mmio_enabled) { + 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; - } + else + ers_res = PCI_ERS_RESULT_NONE; + + 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)); @@ -142,7 +153,12 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, return ers_res; } pdev->error_state = pci_channel_io_normal; - ers_res = driver->err_handler->slot_reset(pdev); + + if (driver->err_handler->slot_reset) + ers_res = driver->err_handler->slot_reset(pdev); + else + ers_res = PCI_ERS_RESULT_NONE; + if (ers_result_indicates_abort(ers_res)) { pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev)); return ers_res; @@ -162,6 +178,8 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, 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 zpci_dev *zdev = to_zpci(pdev); + char *status_str = "success"; struct pci_driver *driver; /* @@ -169,55 +187,77 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) * is unbound or probed and that userspace can't access its * configuration space while we perform recovery. */ - pci_dev_lock(pdev); + device_lock(&pdev->dev); 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))) { + if (is_passed_through(pdev)) { pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n", pci_name(pdev)); + status_str = "failed (pass-through)"; goto out_unlock; } driver = to_pci_driver(pdev->dev.driver); if (!is_driver_supported(driver)) { - if (!driver) + if (!driver) { pr_info("%s: Cannot be recovered because no driver is bound to the device\n", pci_name(pdev)); - else + status_str = "failed (no driver)"; + } else { pr_info("%s: The %s driver bound to the device does not support error recovery\n", pci_name(pdev), driver->name); + status_str = "failed (no driver support)"; + } goto out_unlock; } ers_res = zpci_event_notify_error_detected(pdev, driver); - if (ers_result_indicates_abort(ers_res)) + if (ers_result_indicates_abort(ers_res)) { + status_str = "failed (abort on detection)"; goto out_unlock; + } - if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) { + if (ers_res != PCI_ERS_RESULT_NEED_RESET) { ers_res = zpci_event_do_error_state_clear(pdev, driver); - if (ers_result_indicates_abort(ers_res)) + if (ers_result_indicates_abort(ers_res)) { + status_str = "failed (abort on MMIO enable)"; goto out_unlock; + } } if (ers_res == PCI_ERS_RESULT_NEED_RESET) ers_res = zpci_event_do_reset(pdev, driver); + /* + * ers_res can be PCI_ERS_RESULT_NONE either because the driver + * decided to return it, indicating that it abstains from voting + * on how to recover, or because it didn't implement the callback. + * Both cases assume, that if there is nothing else causing a + * disconnect, we recovered successfully. + */ + if (ers_res == PCI_ERS_RESULT_NONE) + ers_res = PCI_ERS_RESULT_RECOVERED; + if (ers_res != PCI_ERS_RESULT_RECOVERED) { + pci_uevent_ers(pdev, PCI_ERS_RESULT_DISCONNECT); pr_err("%s: Automatic recovery failed; operator intervention is required\n", pci_name(pdev)); + status_str = "failed (driver can't recover)"; 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); + pci_uevent_ers(pdev, PCI_ERS_RESULT_RECOVERED); out_unlock: - pci_dev_unlock(pdev); + device_unlock(&pdev->dev); + zpci_report_status(zdev, "recovery", status_str); return ers_res; } @@ -239,7 +279,7 @@ static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es) * we will inject the error event and let the guest recover the device * itself. */ - if (is_passed_through(to_zpci(pdev))) + if (is_passed_through(pdev)) goto out; driver = to_pci_driver(pdev->dev.driver); if (driver && driver->err_handler && driver->err_handler->error_detected) @@ -253,6 +293,8 @@ 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; + u32 fh = 0; + int rc; zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); @@ -260,6 +302,16 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) zpci_err_hex(ccdf, sizeof(*ccdf)); if (zdev) { + mutex_lock(&zdev->state_lock); + rc = clp_refresh_fh(zdev->fid, &fh); + if (rc) + goto no_pdev; + if (!fh || ccdf->fh != fh) { + /* Ignore events with stale handles */ + zpci_dbg(3, "err fid:%x, fh:%x (stale %x)\n", + ccdf->fid, fh, ccdf->fh); + goto no_pdev; + } zpci_update_fh(zdev, ccdf->fh); if (zdev->zbus->bus) pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); @@ -272,21 +324,24 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) goto no_pdev; switch (ccdf->pec) { - case 0x003a: /* Service Action or Error Recovery Successful */ + case 0x002a: /* Error event concerns FMB */ + case 0x002b: + case 0x002c: + break; + case 0x0040: /* Service Action or Error Recovery Failed */ + case 0x003b: + zpci_event_io_failure(pdev, pci_channel_io_perm_failure); + break; + default: /* PCI function left in the error state attempt to recover */ 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); no_pdev: + if (zdev) + mutex_unlock(&zdev->state_lock); zpci_zdev_put(zdev); } @@ -306,13 +361,27 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) /* Even though the device is already gone we still * need to free zPCI resources as part of the disable. */ - if (zdev->dma_table) - zpci_dma_exit_device(zdev); if (zdev_enabled(zdev)) zpci_disable_device(zdev); zdev->state = ZPCI_FN_STATE_STANDBY; } +static void zpci_event_reappear(struct zpci_dev *zdev) +{ + lockdep_assert_held(&zdev->state_lock); + /* + * The zdev is in the reserved state. This means that it was presumed to + * go away but there are still undropped references. Now, the platform + * announced its availability again. Bring back the lingering zdev + * to standby. This is safe because we hold a temporary reference + * now so that it won't go away. Account for the re-appearance of the + * underlying device by incrementing the reference count. + */ + zdev->state = ZPCI_FN_STATE_STANDBY; + zpci_zdev_get(zdev); + zpci_dbg(1, "rea fid:%x, fh:%x\n", zdev->fid, zdev->fh); +} + static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); @@ -321,29 +390,48 @@ 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) { zdev = zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_CONFIGURED); if (IS_ERR(zdev)) break; + if (zpci_add_device(zdev)) { + kfree(zdev); + break; + } } else { + if (zdev->state == ZPCI_FN_STATE_RESERVED) + zpci_event_reappear(zdev); /* the configuration request may be stale */ - if (zdev->state != ZPCI_FN_STATE_STANDBY) + else if (zdev->state != ZPCI_FN_STATE_STANDBY) break; zdev->state = ZPCI_FN_STATE_CONFIGURED; } zpci_scan_configured_device(zdev, ccdf->fh); break; case 0x0302: /* Reserved -> Standby */ - if (!zdev) - zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY); - else + if (!zdev) { + zdev = zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY); + if (IS_ERR(zdev)) + break; + if (zpci_add_device(zdev)) { + kfree(zdev); + break; + } + } else { + if (zdev->state == ZPCI_FN_STATE_RESERVED) + zpci_event_reappear(zdev); zpci_update_fh(zdev, ccdf->fh); + } 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) @@ -354,7 +442,7 @@ 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) @@ -368,7 +456,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) break; case 0x0306: /* 0x308 or 0x302 for multiple devices */ zpci_remove_reserved_devices(); - clp_scan_pci_devices(); + zpci_scan_devices(); break; case 0x0308: /* Standby -> Reserved */ if (!zdev) @@ -378,8 +466,10 @@ 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_fixup.c b/arch/s390/pci/pci_fixup.c new file mode 100644 index 000000000000..35688b645098 --- /dev/null +++ b/arch/s390/pci/pci_fixup.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Exceptions for specific devices, + * + * Copyright IBM Corp. 2025 + * + * Author(s): + * Niklas Schnelle <schnelle@linux.ibm.com> + */ +#include <linux/pci.h> + +static void zpci_ism_bar_no_mmap(struct pci_dev *pdev) +{ + /* + * ISM's BAR is special. Drivers written for ISM know + * how to handle this but others need to be aware of their + * special nature e.g. to prevent attempts to mmap() it. + */ + pdev->non_mappable_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, + PCI_DEVICE_ID_IBM_ISM, + zpci_ism_bar_no_mmap); diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 56480be48244..35ceb1bea1c6 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -15,6 +15,7 @@ #include <asm/pci_debug.h> #include <asm/pci_io.h> #include <asm/processor.h> +#include <asm/asm.h> #define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ @@ -57,16 +58,16 @@ static inline void zpci_err_insn_addr(int lvl, u8 insn, u8 cc, u8 status, /* Modify PCI Function Controls */ static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) { - u8 cc; + int cc; asm volatile ( " .insn rxy,0xe300000000d0,%[req],%[fib]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib) - : : "cc"); + CC_IPM(cc) + : CC_OUT(cc, cc), [req] "+d" (req), [fib] "+Q" (*fib) + : + : CC_CLOBBER); *status = req >> 24 & 0xff; - return cc; + return CC_TRANSFORM(cc); } u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status) @@ -98,17 +99,16 @@ EXPORT_SYMBOL_GPL(zpci_mod_fc); static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) { union register_pair addr_range = {.even = addr, .odd = range}; - u8 cc; + int cc; asm volatile ( " .insn rre,0xb9d30000,%[fn],%[addr_range]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [fn] "+d" (fn) + CC_IPM(cc) + : CC_OUT(cc, cc), [fn] "+d" (fn) : [addr_range] "d" (addr_range.pair) - : "cc"); + : CC_CLOBBER); *status = fn >> 24 & 0xff; - return cc; + return CC_TRANSFORM(cc); } int zpci_refresh_trans(u64 fn, u64 addr, u64 range) @@ -145,7 +145,7 @@ int zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib) return -EIO; asm volatile( - ".insn rsy,0xeb00000000d1,%[ctl],%[isc],%[iib]\n" + ".insn rsy,0xeb00000000d1,%[ctl],%[isc],%[iib]" : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [iib] "Q" (*iib)); return 0; @@ -156,20 +156,23 @@ EXPORT_SYMBOL_GPL(zpci_set_irq_ctrl); static inline int ____pcilg(u64 *data, u64 req, u64 offset, u8 *status) { union register_pair req_off = {.even = req, .odd = offset}; - int cc = -ENXIO; + int cc, exception; u64 __data; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rre,0xb9d20000,%[data],%[req_off]\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [data] "=d" (__data), - [req_off] "+&d" (req_off.pair) :: "cc"); + : CC_OUT(cc, cc), [data] "=d" (__data), + [req_off] "+d" (req_off.pair), [exc] "+d" (exception) + : + : CC_CLOBBER); *status = req_off.even >> 24 & 0xff; *data = __data; - return cc; + return exception ? -ENXIO : CC_TRANSFORM(cc); } static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status) @@ -222,20 +225,23 @@ static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr, static inline int __pcilg_mio(u64 *data, u64 ioaddr, u64 len, u8 *status) { union register_pair ioaddr_len = {.even = ioaddr, .odd = len}; - int cc = -ENXIO; + int cc, exception; u64 __data; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rre,0xb9d60000,%[data],%[ioaddr_len]\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [data] "=d" (__data), - [ioaddr_len] "+&d" (ioaddr_len.pair) :: "cc"); + : CC_OUT(cc, cc), [data] "=d" (__data), + [ioaddr_len] "+d" (ioaddr_len.pair), [exc] "+d" (exception) + : + : CC_CLOBBER); *status = ioaddr_len.odd >> 24 & 0xff; *data = __data; - return cc; + return exception ? -ENXIO : CC_TRANSFORM(cc); } int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len) @@ -258,19 +264,20 @@ EXPORT_SYMBOL_GPL(zpci_load); static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status) { union register_pair req_off = {.even = req, .odd = offset}; - int cc = -ENXIO; + int cc, exception; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rre,0xb9d00000,%[data],%[req_off]\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [req_off] "+&d" (req_off.pair) + : CC_OUT(cc, cc), [req_off] "+d" (req_off.pair), [exc] "+d" (exception) : [data] "d" (data) - : "cc"); + : CC_CLOBBER); *status = req_off.even >> 24 & 0xff; - return cc; + return exception ? -ENXIO : CC_TRANSFORM(cc); } int __zpci_store(u64 data, u64 req, u64 offset) @@ -311,19 +318,20 @@ static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data, static inline int __pcistg_mio(u64 data, u64 ioaddr, u64 len, u8 *status) { union register_pair ioaddr_len = {.even = ioaddr, .odd = len}; - int cc = -ENXIO; + int cc, exception; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rre,0xb9d40000,%[data],%[ioaddr_len]\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [ioaddr_len] "+&d" (ioaddr_len.pair) + : CC_OUT(cc, cc), [ioaddr_len] "+d" (ioaddr_len.pair), [exc] "+d" (exception) : [data] "d" (data) - : "cc", "memory"); + : CC_CLOBBER_LIST("memory")); *status = ioaddr_len.odd >> 24 & 0xff; - return cc; + return exception ? -ENXIO : CC_TRANSFORM(cc); } int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len) @@ -345,19 +353,20 @@ EXPORT_SYMBOL_GPL(zpci_store); /* PCI Store Block */ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) { - int cc = -ENXIO; + int cc, exception; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rsy,0xeb00000000d0,%[req],%[offset],%[data]\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [req] "+d" (req) + : CC_OUT(cc, cc), [req] "+d" (req), [exc] "+d" (exception) : [offset] "d" (offset), [data] "Q" (*data) - : "cc"); + : CC_CLOBBER); *status = req >> 24 & 0xff; - return cc; + return exception ? -ENXIO : CC_TRANSFORM(cc); } int __zpci_store_block(const u64 *data, u64 req, u64 offset) @@ -398,19 +407,20 @@ static inline int zpci_write_block_fh(volatile void __iomem *dst, static inline int __pcistb_mio(const u64 *data, u64 ioaddr, u64 len, u8 *status) { - int cc = -ENXIO; + int cc, exception; - asm volatile ( + exception = 1; + asm_inline volatile ( " .insn rsy,0xeb00000000d4,%[len],%[ioaddr],%[data]\n" - "0: ipm %[cc]\n" - " srl %[cc],28\n" + "0: lhi %[exc],0\n" "1:\n" + CC_IPM(cc) EX_TABLE(0b, 1b) - : [cc] "+d" (cc), [len] "+d" (len) + : CC_OUT(cc, cc), [len] "+d" (len), [exc] "+d" (exception) : [ioaddr] "d" (ioaddr), [data] "Q" (*data) - : "cc"); + : CC_CLOBBER); *status = len >> 24 & 0xff; - return cc; + return exception ? -ENXIO : CC_TRANSFORM(cc); } int zpci_write_block(volatile void __iomem *dst, @@ -432,7 +442,7 @@ EXPORT_SYMBOL_GPL(zpci_write_block); static inline void __pciwb_mio(void) { - asm volatile (".insn rre,0xb9d50000,0,0\n"); + asm volatile (".insn rre,0xb9d50000,0,0"); } void zpci_barrier(void) diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c index ead062bf2b41..13050ce5c3e9 100644 --- a/arch/s390/pci/pci_iov.c +++ b/arch/s390/pci/pci_iov.c @@ -7,8 +7,7 @@ * */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/pci.h> @@ -60,18 +59,35 @@ static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, in return 0; } -int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +/** + * zpci_iov_find_parent_pf - Find the parent PF, if any, of the given function + * @zbus: The bus that the PCI function is on, or would be added on + * @zdev: The PCI function + * + * Finds the parent PF, if it exists and is configured, of the given PCI function + * and increments its refcount. Th PF is searched for on the provided bus so the + * caller has to ensure that this is the correct bus to search. This function may + * be used before adding the PCI function to a zbus. + * + * Return: Pointer to the struct pci_dev of the parent PF or NULL if it not + * found. If the function is not a VF or has no RequesterID information, + * NULL is returned as well. + */ +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) { - int i, cand_devfn; - struct zpci_dev *zdev; + int i, vfid, devfn, cand_devfn; struct pci_dev *pdev; - int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ - int rc = 0; if (!zbus->multifunction) - return 0; - - /* If the parent PF for the given VF is also configured in the + return NULL; + /* Non-VFs and VFs without RID available don't have a parent */ + if (!zdev->vfn || !zdev->rid_available) + return NULL; + /* Linux vfid starts at 0 vfn at 1 */ + vfid = zdev->vfn - 1; + devfn = zdev->rid & ZPCI_RID_MASK_DEVFN; + /* + * If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what * devfn the VF would have if it belonged to that PF using the PF's @@ -85,15 +101,26 @@ int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn if (!pdev) continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); - if (cand_devfn == virtfn->devfn) { - rc = zpci_iov_link_virtfn(pdev, virtfn, vfid); - /* balance pci_get_slot() */ - pci_dev_put(pdev); - break; - } + if (cand_devfn == devfn) + return pdev; /* balance pci_get_slot() */ pci_dev_put(pdev); } } + return NULL; +} + +int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +{ + struct zpci_dev *zdev = to_zpci(virtfn); + struct pci_dev *pdev_pf; + int rc = 0; + + pdev_pf = zpci_iov_find_parent_pf(zbus, zdev); + if (pdev_pf) { + /* Linux' vfids start at 0 while zdev->vfn starts at 1 */ + rc = zpci_iov_link_virtfn(pdev_pf, virtfn, zdev->vfn - 1); + pci_dev_put(pdev_pf); + } return rc; } diff --git a/arch/s390/pci/pci_iov.h b/arch/s390/pci/pci_iov.h index b2c828003bad..d2c2793eb0f3 100644 --- a/arch/s390/pci/pci_iov.h +++ b/arch/s390/pci/pci_iov.h @@ -10,6 +10,8 @@ #ifndef __S390_PCI_IOV_H #define __S390_PCI_IOV_H +#include <linux/pci.h> + #ifdef CONFIG_PCI_IOV void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn); @@ -17,6 +19,8 @@ void zpci_iov_map_resources(struct pci_dev *pdev); int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn); +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev); + #else /* CONFIG_PCI_IOV */ static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {} @@ -26,5 +30,10 @@ static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *v { return 0; } + +static inline struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + return NULL; +} #endif /* CONFIG_PCI_IOV */ #endif /* __S390_PCI_IOV_h */ diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 4ab0cf829999..2a06df8c2498 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/irq.h> @@ -107,9 +106,6 @@ static int zpci_set_irq(struct zpci_dev *zdev) else rc = zpci_set_airq(zdev); - if (!rc) - zdev->irqs_registered = 1; - return rc; } @@ -123,9 +119,6 @@ static int zpci_clear_irq(struct zpci_dev *zdev) else rc = zpci_clear_airq(zdev); - if (!rc) - zdev->irqs_registered = 0; - return rc; } @@ -163,7 +156,7 @@ static void zpci_handle_cpu_local_irq(bool rescan) if (!rescan || irqs_on++) /* End of second scan with interrupts on. */ break; - /* First scan complete, reenable interrupts. */ + /* First scan complete, re-enable interrupts. */ if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &iib)) break; bit = 0; @@ -202,7 +195,7 @@ static void zpci_handle_fallback_irq(void) if (irqs_on++) /* End of second scan with interrupts on. */ break; - /* First scan complete, reenable interrupts. */ + /* First scan complete, re-enable interrupts. */ if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib)) break; cpu = 0; @@ -247,7 +240,7 @@ static void zpci_floating_irq_handler(struct airq_struct *airq, if (irqs_on++) /* End of second scan with interrupts on. */ break; - /* First scan complete, reenable interrupts. */ + /* First scan complete, re-enable interrupts. */ if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib)) break; si = 0; @@ -268,33 +261,20 @@ static void zpci_floating_irq_handler(struct airq_struct *airq, } } -int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +static int __alloc_airq(struct zpci_dev *zdev, int msi_vecs, + unsigned long *bit) { - struct zpci_dev *zdev = to_zpci(pdev); - unsigned int hwirq, msi_vecs, cpu; - unsigned long bit; - struct msi_desc *msi; - struct msi_msg msg; - int cpu_addr; - int rc, irq; - - zdev->aisb = -1UL; - zdev->msi_first_bit = -1U; - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; - msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); - if (irq_delivery == DIRECTED) { /* Allocate cpu vector bits */ - bit = airq_iv_alloc(zpci_ibv[0], msi_vecs); - if (bit == -1UL) + *bit = airq_iv_alloc(zpci_ibv[0], msi_vecs); + if (*bit == -1UL) return -EIO; } else { /* Allocate adapter summary indicator bit */ - bit = airq_iv_alloc_bit(zpci_sbv); - if (bit == -1UL) + *bit = airq_iv_alloc_bit(zpci_sbv); + if (*bit == -1UL) return -EIO; - zdev->aisb = bit; + zdev->aisb = *bit; /* Create adapter interrupt vector */ zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL); @@ -302,27 +282,66 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return -ENOMEM; /* Wire up shortcut pointer */ - zpci_ibv[bit] = zdev->aibv; + zpci_ibv[*bit] = zdev->aibv; /* Each function has its own interrupt vector */ - bit = 0; + *bit = 0; } + return 0; +} - /* Request MSI interrupts */ +int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +{ + unsigned int hwirq, msi_vecs, irqs_per_msi, i, cpu; + struct zpci_dev *zdev = to_zpci(pdev); + struct msi_desc *msi; + struct msi_msg msg; + unsigned long bit; + int cpu_addr; + int rc, irq; + + zdev->aisb = -1UL; + zdev->msi_first_bit = -1U; + + msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); + if (msi_vecs < nvec) { + pr_info("%s requested %d irqs, allocate system limit of %d", + pci_name(pdev), nvec, zdev->max_msi); + } + + rc = __alloc_airq(zdev, msi_vecs, &bit); + if (rc < 0) + return rc; + + /* + * Request MSI interrupts: + * When using MSI, nvec_used interrupt sources and their irq + * descriptors are controlled through one msi descriptor. + * Thus the outer loop over msi descriptors shall run only once, + * while two inner loops iterate over the interrupt vectors. + * When using MSI-X, each interrupt vector/irq descriptor + * is bound to exactly one msi descriptor (nvec_used is one). + * So the inner loops are executed once, while the outer iterates + * over the MSI-X descriptors. + */ hwirq = bit; msi_for_each_desc(msi, &pdev->dev, MSI_DESC_NOTASSOCIATED) { - rc = -EIO; if (hwirq - bit >= msi_vecs) break; - irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, - (irq_delivery == DIRECTED) ? - msi->affinity : NULL); + irqs_per_msi = min_t(unsigned int, msi_vecs, msi->nvec_used); + irq = __irq_alloc_descs(-1, 0, irqs_per_msi, 0, THIS_MODULE, + (irq_delivery == DIRECTED) ? + msi->affinity : NULL); if (irq < 0) return -ENOMEM; - rc = irq_set_msi_desc(irq, msi); - if (rc) - return rc; - irq_set_chip_and_handler(irq, &zpci_irq_chip, - handle_percpu_irq); + + for (i = 0; i < irqs_per_msi; i++) { + rc = irq_set_msi_desc_off(irq, i, msi); + if (rc) + return rc; + irq_set_chip_and_handler(irq + i, &zpci_irq_chip, + handle_percpu_irq); + } + msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { if (msi->affinity) @@ -335,31 +354,35 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) msg.address_lo |= (cpu_addr << 8); for_each_possible_cpu(cpu) { - airq_iv_set_data(zpci_ibv[cpu], hwirq, irq); + for (i = 0; i < irqs_per_msi; i++) + airq_iv_set_data(zpci_ibv[cpu], + hwirq + i, irq + i); } } else { msg.address_lo = zdev->msi_addr & 0xffffffff; - airq_iv_set_data(zdev->aibv, hwirq, irq); + for (i = 0; i < irqs_per_msi; i++) + airq_iv_set_data(zdev->aibv, hwirq + i, irq + i); } msg.address_hi = zdev->msi_addr >> 32; pci_write_msi_msg(irq, &msg); - hwirq++; + hwirq += irqs_per_msi; } zdev->msi_first_bit = bit; - zdev->msi_nr_irqs = msi_vecs; + zdev->msi_nr_irqs = hwirq - bit; rc = zpci_set_irq(zdev); if (rc) return rc; - return (msi_vecs == nvec) ? 0 : msi_vecs; + return (zdev->msi_nr_irqs == nvec) ? 0 : zdev->msi_nr_irqs; } void arch_teardown_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); struct msi_desc *msi; + unsigned int i; int rc; /* Disable interrupts */ @@ -369,8 +392,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) /* Release MSI interrupts */ msi_for_each_desc(msi, &pdev->dev, MSI_DESC_ASSOCIATED) { - irq_set_msi_desc(msi->irq, NULL); - irq_free_desc(msi->irq); + for (i = 0; i < msi->nvec_used; i++) { + irq_set_msi_desc(msi->irq + i, NULL); + irq_free_desc(msi->irq + i); + } msi->msg.address_lo = 0; msi->msg.address_hi = 0; msi->msg.data = 0; @@ -395,8 +420,7 @@ bool arch_restore_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); - if (!zdev->irqs_registered) - zpci_set_irq(zdev); + zpci_set_irq(zdev); return true; } @@ -410,7 +434,7 @@ static void __init cpu_enable_directed_irq(void *unused) union zpci_sic_iib iib = {{0}}; union zpci_sic_iib ziib = {{0}}; - iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector; + iib.cdiib.dibv_addr = virt_to_phys(zpci_ibv[smp_processor_id()]->vector); zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib); zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib); diff --git a/arch/s390/pci/pci_kvm_hook.c b/arch/s390/pci/pci_kvm_hook.c index ff34baf50a3e..df5b25dbe9ca 100644 --- a/arch/s390/pci/pci_kvm_hook.c +++ b/arch/s390/pci/pci_kvm_hook.c @@ -5,7 +5,9 @@ * Copyright (C) IBM Corp. 2022. All rights reserved. * Author(s): Pierre Morel <pmorel@linux.ibm.com> */ + #include <linux/kvm_host.h> +#include <linux/export.h> struct zpci_kvm_hook zpci_kvm_hook; EXPORT_SYMBOL_GPL(zpci_kvm_hook); diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 588089332931..51e7a28af899 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -14,6 +14,7 @@ #include <asm/asm-extable.h> #include <asm/pci_io.h> #include <asm/pci_debug.h> +#include <asm/asm.h> static inline void zpci_err_mmio(u8 cc, u8 status, u64 offset) { @@ -30,20 +31,24 @@ static inline int __pcistb_mio_inuser( void __iomem *ioaddr, const void __user *src, u64 len, u8 *status) { - int cc = -ENXIO; - - asm volatile ( - " sacf 256\n" - "0: .insn rsy,0xeb00000000d4,%[len],%[ioaddr],%[src]\n" - "1: ipm %[cc]\n" - " srl %[cc],28\n" - "2: sacf 768\n" + int cc, exception; + bool sacf_flag; + + exception = 1; + sacf_flag = enable_sacf_uaccess(); + asm_inline volatile ( + " sacf 256\n" + "0: .insn rsy,0xeb00000000d4,%[len],%[ioaddr],%[src]\n" + "1: lhi %[exc],0\n" + "2: sacf 768\n" + CC_IPM(cc) EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) - : [cc] "+d" (cc), [len] "+d" (len) + : CC_OUT(cc, cc), [len] "+d" (len), [exc] "+d" (exception) : [ioaddr] "a" (ioaddr), [src] "Q" (*((u8 __force *)src)) - : "cc", "memory"); + : CC_CLOBBER_LIST("memory")); + disable_sacf_uaccess(sacf_flag); *status = len >> 24 & 0xff; - return cc; + return exception ? -ENXIO : CC_TRANSFORM(cc); } static inline int __pcistg_mio_inuser( @@ -51,7 +56,8 @@ static inline int __pcistg_mio_inuser( u64 ulen, u8 *status) { union register_pair ioaddr_len = {.even = (u64 __force)ioaddr, .odd = ulen}; - int cc = -ENXIO; + int cc, exception; + bool sacf_flag; u64 val = 0; u64 cnt = ulen; u8 tmp; @@ -61,25 +67,29 @@ static inline int __pcistg_mio_inuser( * a register, then store it to PCI at @ioaddr while in secondary * address space. pcistg then uses the user mappings. */ - asm volatile ( - " sacf 256\n" - "0: llgc %[tmp],0(%[src])\n" + exception = 1; + sacf_flag = enable_sacf_uaccess(); + asm_inline volatile ( + " sacf 256\n" + "0: llgc %[tmp],0(%[src])\n" "4: sllg %[val],%[val],8\n" - " aghi %[src],1\n" - " ogr %[val],%[tmp]\n" - " brctg %[cnt],0b\n" - "1: .insn rre,0xb9d40000,%[val],%[ioaddr_len]\n" - "2: ipm %[cc]\n" - " srl %[cc],28\n" - "3: sacf 768\n" + " aghi %[src],1\n" + " ogr %[val],%[tmp]\n" + " brctg %[cnt],0b\n" + "1: .insn rre,0xb9d40000,%[val],%[ioaddr_len]\n" + "2: lhi %[exc],0\n" + "3: sacf 768\n" + CC_IPM(cc) EX_TABLE(0b, 3b) EX_TABLE(4b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b) + : [src] "+a" (src), [cnt] "+d" (cnt), + [val] "+d" (val), [tmp] "=d" (tmp), [exc] "+d" (exception), + CC_OUT(cc, cc), [ioaddr_len] "+&d" (ioaddr_len.pair) : - [src] "+a" (src), [cnt] "+d" (cnt), - [val] "+d" (val), [tmp] "=d" (tmp), - [cc] "+d" (cc), [ioaddr_len] "+&d" (ioaddr_len.pair) - :: "cc", "memory"); + : CC_CLOBBER_LIST("memory")); + disable_sacf_uaccess(sacf_flag); *status = ioaddr_len.odd >> 24 & 0xff; + cc = exception ? -ENXIO : CC_TRANSFORM(cc); /* did we read everything from user memory? */ if (!cc && cnt != 0) cc = -EFAULT; @@ -97,9 +107,9 @@ static inline int __memcpy_toio_inuser(void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) dst, - (u64 __force) src, n, - ZPCI_MAX_WRITE_SIZE); + size = zpci_get_max_io_size((u64 __force) dst, + (u64 __force) src, n, + ZPCI_MAX_WRITE_SIZE); if (size > 8) /* main path */ rc = __pcistb_mio_inuser(dst, src, size, &status); else @@ -118,12 +128,11 @@ static inline int __memcpy_toio_inuser(void __iomem *dst, SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, const void __user *, user_buffer, size_t, length) { + struct follow_pfnmap_args args = { }; u8 local_buf[64]; void __iomem *io_addr; void *buf; struct vm_area_struct *vma; - pte_t *ptep; - spinlock_t *ptl; long ret; if (!zpci_is_enabled()) @@ -169,11 +178,17 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, if (!(vma->vm_flags & VM_WRITE)) goto out_unlock_mmap; - ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl); - if (ret) - goto out_unlock_mmap; + args.address = mmio_addr; + args.vma = vma; + ret = follow_pfnmap_start(&args); + if (ret) { + fixup_user_fault(current->mm, mmio_addr, FAULT_FLAG_WRITE, NULL); + ret = follow_pfnmap_start(&args); + if (ret) + goto out_unlock_mmap; + } - io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) | + io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) @@ -181,7 +196,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, ret = zpci_memcpy_toio(io_addr, buf, length); out_unlock_pt: - pte_unmap_unlock(ptep, ptl); + follow_pfnmap_end(&args); out_unlock_mmap: mmap_read_unlock(current->mm); out_free: @@ -195,9 +210,10 @@ static inline int __pcilg_mio_inuser( u64 ulen, u8 *status) { union register_pair ioaddr_len = {.even = (u64 __force)ioaddr, .odd = ulen}; + bool sacf_flag; u64 cnt = ulen; int shift = ulen * 8; - int cc = -ENXIO; + int cc, exception; u64 val, tmp; /* @@ -205,27 +221,34 @@ static inline int __pcilg_mio_inuser( * user space) into a register using pcilg then store these bytes at * user address @dst */ - asm volatile ( - " sacf 256\n" - "0: .insn rre,0xb9d60000,%[val],%[ioaddr_len]\n" - "1: ipm %[cc]\n" - " srl %[cc],28\n" - " ltr %[cc],%[cc]\n" - " jne 4f\n" - "2: ahi %[shift],-8\n" - " srlg %[tmp],%[val],0(%[shift])\n" - "3: stc %[tmp],0(%[dst])\n" + exception = 1; + sacf_flag = enable_sacf_uaccess(); + asm_inline volatile ( + " sacf 256\n" + "0: .insn rre,0xb9d60000,%[val],%[ioaddr_len]\n" + "1: lhi %[exc],0\n" + " jne 4f\n" + "2: ahi %[shift],-8\n" + " srlg %[tmp],%[val],0(%[shift])\n" + "3: stc %[tmp],0(%[dst])\n" "5: aghi %[dst],1\n" - " brctg %[cnt],2b\n" - "4: sacf 768\n" + " brctg %[cnt],2b\n" + /* + * Use xr to clear exc and set condition code to zero + * to ensure flag output is correct for this branch. + */ + " xr %[exc],%[exc]\n" + "4: sacf 768\n" + CC_IPM(cc) EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) EX_TABLE(5b, 4b) + : [ioaddr_len] "+&d" (ioaddr_len.pair), [exc] "+d" (exception), + CC_OUT(cc, cc), [val] "=d" (val), + [dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp), + [shift] "+a" (shift) : - [ioaddr_len] "+&d" (ioaddr_len.pair), - [cc] "+d" (cc), [val] "=d" (val), - [dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp), - [shift] "+d" (shift) - :: "cc", "memory"); - + : CC_CLOBBER_LIST("memory")); + disable_sacf_uaccess(sacf_flag); + cc = exception ? -ENXIO : CC_TRANSFORM(cc); /* did we write everything to the user space buffer? */ if (!cc && cnt != 0) cc = -EFAULT; @@ -242,9 +265,9 @@ static inline int __memcpy_fromio_inuser(void __user *dst, u8 status; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) src, - (u64 __force) dst, n, - ZPCI_MAX_READ_SIZE); + size = zpci_get_max_io_size((u64 __force) src, + (u64 __force) dst, n, + ZPCI_MAX_READ_SIZE); rc = __pcilg_mio_inuser(dst, src, size, &status); if (rc) break; @@ -260,12 +283,11 @@ static inline int __memcpy_fromio_inuser(void __user *dst, SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, void __user *, user_buffer, size_t, length) { + struct follow_pfnmap_args args = { }; u8 local_buf[64]; void __iomem *io_addr; void *buf; struct vm_area_struct *vma; - pte_t *ptep; - spinlock_t *ptl; long ret; if (!zpci_is_enabled()) @@ -305,14 +327,20 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out_unlock_mmap; ret = -EACCES; - if (!(vma->vm_flags & VM_WRITE)) + if (!(vma->vm_flags & VM_READ)) goto out_unlock_mmap; - ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl); - if (ret) - goto out_unlock_mmap; + args.vma = vma; + args.address = mmio_addr; + ret = follow_pfnmap_start(&args); + if (ret) { + fixup_user_fault(current->mm, mmio_addr, 0, NULL); + ret = follow_pfnmap_start(&args); + if (ret) + goto out_unlock_mmap; + } - io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) | + io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) { @@ -322,7 +350,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, ret = zpci_memcpy_fromio(buf, io_addr, length); out_unlock_pt: - pte_unmap_unlock(ptep, ptl); + follow_pfnmap_end(&args); out_unlock_mmap: mmap_read_unlock(current->mm); diff --git a/arch/s390/pci/pci_report.c b/arch/s390/pci/pci_report.c new file mode 100644 index 000000000000..7030f7052926 --- /dev/null +++ b/arch/s390/pci/pci_report.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2024 + * + * Author(s): + * Niklas Schnelle <schnelle@linux.ibm.com> + * + */ + +#define pr_fmt(fmt) "zpci: " fmt + +#include <linux/kernel.h> +#include <linux/sprintf.h> +#include <linux/pci.h> + +#include <asm/sclp.h> +#include <asm/debug.h> +#include <asm/pci_debug.h> + +#include "pci_report.h" + +#define ZPCI_ERR_LOG_ID_KERNEL_REPORT 0x4714 + +struct zpci_report_error_data { + u64 timestamp; + u64 err_log_id; + char log_data[]; +} __packed; + +#define ZPCI_REPORT_SIZE (PAGE_SIZE - sizeof(struct err_notify_sccb)) +#define ZPCI_REPORT_DATA_SIZE (ZPCI_REPORT_SIZE - sizeof(struct zpci_report_error_data)) + +struct zpci_report_error { + struct zpci_report_error_header header; + struct zpci_report_error_data data; +} __packed; + +static const char *zpci_state_str(pci_channel_state_t state) +{ + switch (state) { + case pci_channel_io_normal: + return "normal"; + case pci_channel_io_frozen: + return "frozen"; + case pci_channel_io_perm_failure: + return "permanent-failure"; + default: + return "invalid"; + }; +} + +static int debug_log_header_fn(debug_info_t *id, struct debug_view *view, + int area, debug_entry_t *entry, char *out_buf, + size_t out_buf_size) +{ + unsigned long sec, usec; + unsigned int level; + char *except_str; + int rc = 0; + + level = entry->level; + sec = entry->clock; + usec = do_div(sec, USEC_PER_SEC); + + if (entry->exception) + except_str = "*"; + else + except_str = "-"; + rc += scnprintf(out_buf, out_buf_size, "%011ld:%06lu %1u %1s %04u ", + sec, usec, level, except_str, + entry->cpu); + return rc; +} + +static int debug_prolog_header(debug_info_t *id, struct debug_view *view, + char *out_buf, size_t out_buf_size) +{ + return scnprintf(out_buf, out_buf_size, "sec:usec level except cpu msg\n"); +} + +static struct debug_view debug_log_view = { + "pci_msg_log", + &debug_prolog_header, + &debug_log_header_fn, + &debug_sprintf_format_fn, + NULL, + NULL +}; + +/** + * zpci_report_status - Report the status of operations on a PCI device + * @zdev: The PCI device for which to report status + * @operation: A string representing the operation reported + * @status: A string representing the status of the operation + * + * This function creates a human readable report about an operation such as + * PCI device recovery and forwards this to the platform using the SCLP Write + * Event Data mechanism. Besides the operation and status strings the report + * also contains additional information about the device deemed useful for + * debug such as the currently bound device driver, if any, and error state. + * Additionally a string representation of pci_debug_msg_id, or as much as fits, + * is also included. + * + * Return: 0 on success an error code < 0 otherwise. + */ +int zpci_report_status(struct zpci_dev *zdev, const char *operation, const char *status) +{ + struct zpci_report_error *report; + struct pci_driver *driver = NULL; + struct pci_dev *pdev = NULL; + char *buf, *end; + int ret; + + if (!zdev || !zdev->zbus) + return -ENODEV; + + /* Protected virtualization hosts get nothing from us */ + if (prot_virt_guest) + return -ENODATA; + + report = (void *)get_zeroed_page(GFP_KERNEL); + if (!report) + return -ENOMEM; + if (zdev->zbus->bus) + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (pdev) + driver = to_pci_driver(pdev->dev.driver); + + buf = report->data.log_data; + end = report->data.log_data + ZPCI_REPORT_DATA_SIZE; + buf += scnprintf(buf, end - buf, "report: %s\n", operation); + buf += scnprintf(buf, end - buf, "status: %s\n", status); + buf += scnprintf(buf, end - buf, "state: %s\n", + (pdev) ? zpci_state_str(pdev->error_state) : "n/a"); + buf += scnprintf(buf, end - buf, "driver: %s\n", (driver) ? driver->name : "n/a"); + ret = debug_dump(pci_debug_msg_id, &debug_log_view, buf, end - buf, true); + if (ret < 0) + pr_err("Reading PCI debug messages failed with code %d\n", ret); + else + buf += ret; + + report->header.version = 1; + report->header.action = SCLP_ERRNOTIFY_AQ_INFO_LOG; + report->header.length = buf - (char *)&report->data; + report->data.timestamp = ktime_get_clocktai_seconds(); + report->data.err_log_id = ZPCI_ERR_LOG_ID_KERNEL_REPORT; + + ret = sclp_pci_report(&report->header, zdev->fh, zdev->fid); + if (ret) + pr_err("Reporting PCI status failed with code %d\n", ret); + else + pr_info("Reported PCI device status\n"); + + free_page((unsigned long)report); + + return ret; +} diff --git a/arch/s390/pci/pci_report.h b/arch/s390/pci/pci_report.h new file mode 100644 index 000000000000..e08003d51a97 --- /dev/null +++ b/arch/s390/pci/pci_report.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 2024 + * + * Author(s): + * Niklas Schnelle <schnelle@linux.ibm.com> + * + */ +#ifndef __S390_PCI_REPORT_H +#define __S390_PCI_REPORT_H + +struct zpci_dev; + +int zpci_report_status(struct zpci_dev *zdev, const char *operation, const char *status); + +#endif /* __S390_PCI_REPORT_H */ diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index cae280e5c047..c2444a23e26c 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -6,8 +6,7 @@ * Jan Glauber <jang@linux.vnet.ibm.com> */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/stat.h> @@ -23,7 +22,7 @@ static ssize_t name##_show(struct device *dev, \ { \ struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); \ \ - return sprintf(buf, fmt, zdev->member); \ + return sysfs_emit(buf, fmt, zdev->member); \ } \ static DEVICE_ATTR_RO(name) @@ -34,21 +33,49 @@ zpci_attr(pfgid, "0x%02x\n", pfgid); zpci_attr(vfn, "0x%04x\n", vfn); zpci_attr(pft, "0x%02x\n", pft); zpci_attr(port, "%d\n", port); +zpci_attr(fidparm, "0x%02x\n", fidparm); zpci_attr(uid, "0x%x\n", uid); zpci_attr(segment0, "0x%02x\n", pfip[0]); zpci_attr(segment1, "0x%02x\n", pfip[1]); zpci_attr(segment2, "0x%02x\n", pfip[2]); zpci_attr(segment3, "0x%02x\n", pfip[3]); +#define ZPCI_FW_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + static ssize_t mio_enabled_show(struct device *dev, struct device_attribute *attr, char *buf) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - return sprintf(buf, zpci_use_mio(zdev) ? "1\n" : "0\n"); + return sysfs_emit(buf, zpci_use_mio(zdev) ? "1\n" : "0\n"); } static DEVICE_ATTR_RO(mio_enabled); +static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev) +{ + 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_reenable_device(zdev); + + return ret; +} + static ssize_t recover_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -69,6 +96,12 @@ 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 */ @@ -81,39 +114,13 @@ 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->dma_table) { - ret = zpci_dma_exit_device(zdev); - if (ret) - goto out; - } - - 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; - ret = zpci_dma_init_device(zdev); - if (ret) { - zpci_disable_device(zdev); - goto out; - } - pci_rescan_bus(zdev->zbus->bus); + 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; @@ -121,7 +128,7 @@ out: static DEVICE_ATTR_WO(recover); static ssize_t util_string_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -131,10 +138,10 @@ static ssize_t util_string_read(struct file *filp, struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, zdev->util_str, sizeof(zdev->util_str)); } -static BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN); +static const BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN); static ssize_t report_error_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct zpci_report_error_header *report = (void *) buf; @@ -150,7 +157,7 @@ static ssize_t report_error_write(struct file *filp, struct kobject *kobj, return ret ? ret : count; } -static BIN_ATTR(report_error, S_IWUSR, NULL, report_error_write, PAGE_SIZE); +static const BIN_ATTR(report_error, S_IWUSR, NULL, report_error_write, PAGE_SIZE); static ssize_t uid_is_unique_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -159,7 +166,13 @@ static ssize_t uid_is_unique_show(struct device *dev, } static DEVICE_ATTR_RO(uid_is_unique); -#ifndef CONFIG_DMI +static ssize_t uid_checking_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%d\n", zpci_unique_uid ? 1 : 0); +} +ZPCI_FW_ATTR_RO(uid_checking); + /* analogous to smbios index */ static ssize_t index_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -185,13 +198,12 @@ static struct attribute *zpci_ident_attrs[] = { NULL, }; -static struct attribute_group zpci_ident_attr_group = { +const struct attribute_group zpci_ident_attr_group = { .attrs = zpci_ident_attrs, .is_visible = zpci_index_is_visible, }; -#endif -static struct bin_attribute *zpci_bin_attrs[] = { +static const struct bin_attribute *const zpci_bin_attrs[] = { &bin_attr_util_string, &bin_attr_report_error, NULL, @@ -204,6 +216,7 @@ static struct attribute *zpci_dev_attrs[] = { &dev_attr_pfgid.attr, &dev_attr_pft.attr, &dev_attr_port.attr, + &dev_attr_fidparm.attr, &dev_attr_vfn.attr, &dev_attr_uid.attr, &dev_attr_recover.attr, @@ -212,7 +225,7 @@ static struct attribute *zpci_dev_attrs[] = { NULL, }; -static struct attribute_group zpci_attr_group = { +const struct attribute_group zpci_attr_group = { .attrs = zpci_dev_attrs, .bin_attrs = zpci_bin_attrs, }; @@ -224,16 +237,23 @@ static struct attribute *pfip_attrs[] = { &dev_attr_segment3.attr, NULL, }; -static struct attribute_group pfip_attr_group = { + +const struct attribute_group pfip_attr_group = { .name = "pfip", .attrs = pfip_attrs, }; -const struct attribute_group *zpci_attr_groups[] = { - &zpci_attr_group, - &pfip_attr_group, -#ifndef CONFIG_DMI - &zpci_ident_attr_group, -#endif +static struct attribute *clp_fw_attrs[] = { + &uid_checking_attr.attr, NULL, }; + +static struct attribute_group clp_fw_attr_group = { + .name = "clp", + .attrs = clp_fw_attrs, +}; + +int __init __zpci_fw_sysfs_init(void) +{ + return sysfs_create_group(firmware_kobj, &clp_fw_attr_group); +} |