From 8b0a9d42301e45d501d751074a6f767fded680b1 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 29 Jun 2015 11:16:25 +0200 Subject: virtio_net: document VIRTIO_NET_CTRL_GUEST_OFFLOADS Document VIRTIO_NET_CTRL_GUEST_OFFLOADS and the relevant feature bits. Will allow ethtool control of the offloads down the road. Reported-by: Yan Vugenfirer Signed-off-by: Michael S. Tsirkin diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 7bbee79..ec32293 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -34,6 +34,7 @@ /* The feature bitmap for virtio net */ #define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */ #define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */ +#define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */ #define VIRTIO_NET_F_MAC 5 /* Host has given MAC address. */ #define VIRTIO_NET_F_GUEST_TSO4 7 /* Guest can handle TSOv4 in. */ #define VIRTIO_NET_F_GUEST_TSO6 8 /* Guest can handle TSOv6 in. */ @@ -226,4 +227,19 @@ struct virtio_net_ctrl_mq { #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN 1 #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX 0x8000 +/* + * Control network offloads + * + * Reconfigures the network offloads that Guest can handle. + * + * Available with the VIRTIO_NET_F_CTRL_GUEST_OFFLOADS feature bit. + * + * Command data format matches the feature bit mask exactly. + * + * See VIRTIO_NET_F_GUEST_* for the list of offloads + * that can be enabled/disabled. + */ +#define VIRTIO_NET_CTRL_GUEST_OFFLOADS 5 +#define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET 0 + #endif /* _LINUX_VIRTIO_NET_H */ -- cgit v0.10.2 From bcfeacab45e6d419c6bafc0e57ea4b1125e23231 Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Tue, 16 Jun 2015 18:33:35 +0200 Subject: vhost: use binary search instead of linear in find_region() For default region layouts performance stays the same as linear search i.e. it takes around 210ns average for translate_desc() that inlines find_region(). But it scales better with larger amount of regions, 235ns BS vs 300ns LS with 55 memory regions and it will be about the same values when allowed number of slots is increased to 509 like it has been done in kvm. Signed-off-by: Igor Mammedov Signed-off-by: Michael S. Tsirkin diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 9e8e004..71bb468 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "vhost.h" @@ -663,6 +664,16 @@ int vhost_vq_access_ok(struct vhost_virtqueue *vq) } EXPORT_SYMBOL_GPL(vhost_vq_access_ok); +static int vhost_memory_reg_sort_cmp(const void *p1, const void *p2) +{ + const struct vhost_memory_region *r1 = p1, *r2 = p2; + if (r1->guest_phys_addr < r2->guest_phys_addr) + return 1; + if (r1->guest_phys_addr > r2->guest_phys_addr) + return -1; + return 0; +} + static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) { struct vhost_memory mem, *newmem, *oldmem; @@ -682,9 +693,11 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) memcpy(newmem, &mem, size); if (copy_from_user(newmem->regions, m->regions, mem.nregions * sizeof *m->regions)) { - kfree(newmem); + kvfree(newmem); return -EFAULT; } + sort(newmem->regions, newmem->nregions, sizeof(*newmem->regions), + vhost_memory_reg_sort_cmp, NULL); if (!memory_access_ok(d, newmem, 0)) { kfree(newmem); @@ -992,17 +1005,22 @@ EXPORT_SYMBOL_GPL(vhost_dev_ioctl); static const struct vhost_memory_region *find_region(struct vhost_memory *mem, __u64 addr, __u32 len) { - struct vhost_memory_region *reg; - int i; + const struct vhost_memory_region *reg; + int start = 0, end = mem->nregions; - /* linear search is not brilliant, but we really have on the order of 6 - * regions in practice */ - for (i = 0; i < mem->nregions; ++i) { - reg = mem->regions + i; - if (reg->guest_phys_addr <= addr && - reg->guest_phys_addr + reg->memory_size - 1 >= addr) - return reg; + while (start < end) { + int slot = start + (end - start) / 2; + reg = mem->regions + slot; + if (addr >= reg->guest_phys_addr) + end = slot; + else + start = slot + 1; } + + reg = mem->regions + start; + if (addr >= reg->guest_phys_addr && + reg->guest_phys_addr + reg->memory_size > addr) + return reg; return NULL; } -- cgit v0.10.2 From 908a5544cd29ed60114ed60bded6dbe8cdd56326 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 30 Jun 2015 10:59:04 +1000 Subject: virtio scsi: fix unused variable warning drivers/scsi/virtio_scsi.c: In function 'virtscsi_probe': drivers/scsi/virtio_scsi.c:952:11: warning: unused variable 'host_prot' [-Wunused-variable] int err, host_prot; ^ Signed-off-by: Stephen Rothwell Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index f164f24..55441c7 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -944,7 +944,7 @@ static int virtscsi_probe(struct virtio_device *vdev) { struct Scsi_Host *shost; struct virtio_scsi *vscsi; - int err, host_prot; + int err; u32 sg_elems, num_targets; u32 cmd_per_lun; u32 num_queues; @@ -1003,6 +1003,8 @@ static int virtscsi_probe(struct virtio_device *vdev) shost->nr_hw_queues = num_queues; if (virtio_has_feature(vdev, VIRTIO_SCSI_F_T10_PI)) { + int host_prot; + host_prot = SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION | SHOST_DIF_TYPE3_PROTECTION | SHOST_DIX_TYPE1_PROTECTION | SHOST_DIX_TYPE2_PROTECTION | SHOST_DIX_TYPE3_PROTECTION; -- cgit v0.10.2 From d768f32aec8c0ebb8499ffca89cfed8f5f1a4432 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Thu, 2 Jul 2015 09:21:22 +0200 Subject: virtio: Fix typecast of pointer in vring_init() The virtio_ring.h header is used in userspace programs (ie. QEMU), too. Here we can not assume that sizeof(pointer) is the same as sizeof(long), e.g. when compiling for Windows, so the typecast in vring_init() should be done with (uintptr_t) instead of (unsigned long). Signed-off-by: Thomas Huth Signed-off-by: Michael S. Tsirkin diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 915980a..c072959 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -31,6 +31,9 @@ * SUCH DAMAGE. * * Copyright Rusty Russell IBM Corporation 2007. */ +#ifndef __KERNEL__ +#include +#endif #include #include @@ -143,7 +146,7 @@ static inline void vring_init(struct vring *vr, unsigned int num, void *p, vr->num = num; vr->desc = p; vr->avail = p + num*sizeof(struct vring_desc); - vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__virtio16) + vr->used = (void *)(((uintptr_t)&vr->avail->ring[num] + sizeof(__virtio16) + align-1) & ~(align - 1)); } -- cgit v0.10.2 From 3121bb023e2db4f00ed6678898c09e35ed4b5301 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 2 Jul 2015 10:56:49 +0200 Subject: virtio: define virtio_pci_cfg_cap in header. We already have VIRTIO_PCI_CAP_PCI_CFG, let's define the structure that goes with it. Signed-off-by: Michael S. Tsirkin diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 7530146..90007a1 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -157,6 +157,12 @@ struct virtio_pci_common_cfg { __le32 queue_used_hi; /* read-write */ }; +/* Fields in VIRTIO_PCI_CAP_PCI_CFG: */ +struct virtio_pci_cfg_cap { + struct virtio_pci_cap cap; + __u8 pci_cfg_data[4]; /* Data for BAR access. */ +}; + /* Macro versions of offsets for the Old Timers! */ #define VIRTIO_PCI_CAP_VNDR 0 #define VIRTIO_PCI_CAP_NEXT 1 -- cgit v0.10.2 From f2dbda3b4fc2833f0a6240ac28b0e3a17f09893b Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Wed, 1 Jul 2015 17:15:37 +0200 Subject: MAINTAINERS: separate section for s390 virtio drivers The s390-specific virtio drivers have probably more to do with virtio than with kvm today; let's move them out into a separate section to reflect this and to be able to add relevant mailing lists. CC: Christian Borntraeger Signed-off-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin diff --git a/MAINTAINERS b/MAINTAINERS index af802b3..280a568 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5690,7 +5690,6 @@ S: Supported F: Documentation/s390/kvm.txt F: arch/s390/include/asm/kvm* F: arch/s390/kvm/ -F: drivers/s390/kvm/ KERNEL VIRTUAL MACHINE (KVM) FOR ARM M: Christoffer Dall @@ -10571,6 +10570,15 @@ F: drivers/block/virtio_blk.c F: include/linux/virtio_*.h F: include/uapi/linux/virtio_*.h +VIRTIO DRIVERS FOR S390 +M: Christian Borntraeger +M: Cornelia Huck +L: linux-s390@vger.kernel.org +L: virtualization@lists.linux-foundation.org +L: kvm@vger.kernel.org +S: Supported +F: drivers/s390/kvm/ + VIRTIO HOST (VHOST) M: "Michael S. Tsirkin" L: kvm@vger.kernel.org -- cgit v0.10.2 From 1b568d934eec1c5c99565c41f6c8ca66e9743e96 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Tue, 7 Jul 2015 11:41:01 +0200 Subject: virtio/s390: rename drivers/s390/kvm -> drivers/s390/virtio This more accurately reflects what these drivers actually do. Suggested-by: Paolo Bonzini Acked-by: Christian Borntraeger Signed-off-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin diff --git a/MAINTAINERS b/MAINTAINERS index 280a568..fbef7d0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10577,7 +10577,7 @@ L: linux-s390@vger.kernel.org L: virtualization@lists.linux-foundation.org L: kvm@vger.kernel.org S: Supported -F: drivers/s390/kvm/ +F: drivers/s390/virtio/ VIRTIO HOST (VHOST) M: "Michael S. Tsirkin" diff --git a/drivers/s390/Makefile b/drivers/s390/Makefile index 95bccfd..e5225ad 100644 --- a/drivers/s390/Makefile +++ b/drivers/s390/Makefile @@ -2,7 +2,7 @@ # Makefile for the S/390 specific device drivers # -obj-y += cio/ block/ char/ crypto/ net/ scsi/ kvm/ +obj-y += cio/ block/ char/ crypto/ net/ scsi/ virtio/ drivers-y += drivers/s390/built-in.o diff --git a/drivers/s390/kvm/Makefile b/drivers/s390/kvm/Makefile deleted file mode 100644 index 241891a..0000000 --- a/drivers/s390/kvm/Makefile +++ /dev/null @@ -1,9 +0,0 @@ -# Makefile for kvm guest drivers on s390 -# -# Copyright IBM Corp. 2008 -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License (version 2 only) -# as published by the Free Software Foundation. - -obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c deleted file mode 100644 index dd65c8b..0000000 --- a/drivers/s390/kvm/kvm_virtio.c +++ /dev/null @@ -1,510 +0,0 @@ -/* - * virtio for kvm on s390 - * - * Copyright IBM Corp. 2008 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * - * Author(s): Christian Borntraeger - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define VIRTIO_SUBCODE_64 0x0D00 - -/* - * The pointer to our (page) of device descriptions. - */ -static void *kvm_devices; -static struct work_struct hotplug_work; - -struct kvm_device { - struct virtio_device vdev; - struct kvm_device_desc *desc; -}; - -#define to_kvmdev(vd) container_of(vd, struct kvm_device, vdev) - -/* - * memory layout: - * - kvm_device_descriptor - * struct kvm_device_desc - * - configuration - * struct kvm_vqconfig - * - feature bits - * - config space - */ -static struct kvm_vqconfig *kvm_vq_config(const struct kvm_device_desc *desc) -{ - return (struct kvm_vqconfig *)(desc + 1); -} - -static u8 *kvm_vq_features(const struct kvm_device_desc *desc) -{ - return (u8 *)(kvm_vq_config(desc) + desc->num_vq); -} - -static u8 *kvm_vq_configspace(const struct kvm_device_desc *desc) -{ - return kvm_vq_features(desc) + desc->feature_len * 2; -} - -/* - * The total size of the config page used by this device (incl. desc) - */ -static unsigned desc_size(const struct kvm_device_desc *desc) -{ - return sizeof(*desc) - + desc->num_vq * sizeof(struct kvm_vqconfig) - + desc->feature_len * 2 - + desc->config_len; -} - -/* This gets the device's feature bits. */ -static u64 kvm_get_features(struct virtio_device *vdev) -{ - unsigned int i; - u32 features = 0; - struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; - u8 *in_features = kvm_vq_features(desc); - - for (i = 0; i < min(desc->feature_len * 8, 32); i++) - if (in_features[i / 8] & (1 << (i % 8))) - features |= (1 << i); - return features; -} - -static int kvm_finalize_features(struct virtio_device *vdev) -{ - unsigned int i, bits; - struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; - /* Second half of bitmap is features we accept. */ - u8 *out_features = kvm_vq_features(desc) + desc->feature_len; - - /* Give virtio_ring a chance to accept features. */ - vring_transport_features(vdev); - - /* Make sure we don't have any features > 32 bits! */ - BUG_ON((u32)vdev->features != vdev->features); - - memset(out_features, 0, desc->feature_len); - bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8; - for (i = 0; i < bits; i++) { - if (__virtio_test_bit(vdev, i)) - out_features[i / 8] |= (1 << (i % 8)); - } - - return 0; -} - -/* - * Reading and writing elements in config space - */ -static void kvm_get(struct virtio_device *vdev, unsigned int offset, - void *buf, unsigned len) -{ - struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; - - BUG_ON(offset + len > desc->config_len); - memcpy(buf, kvm_vq_configspace(desc) + offset, len); -} - -static void kvm_set(struct virtio_device *vdev, unsigned int offset, - const void *buf, unsigned len) -{ - struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; - - BUG_ON(offset + len > desc->config_len); - memcpy(kvm_vq_configspace(desc) + offset, buf, len); -} - -/* - * The operations to get and set the status word just access - * the status field of the device descriptor. set_status will also - * make a hypercall to the host, to tell about status changes - */ -static u8 kvm_get_status(struct virtio_device *vdev) -{ - return to_kvmdev(vdev)->desc->status; -} - -static void kvm_set_status(struct virtio_device *vdev, u8 status) -{ - BUG_ON(!status); - to_kvmdev(vdev)->desc->status = status; - kvm_hypercall1(KVM_S390_VIRTIO_SET_STATUS, - (unsigned long) to_kvmdev(vdev)->desc); -} - -/* - * To reset the device, we use the KVM_VIRTIO_RESET hypercall, using the - * descriptor address. The Host will zero the status and all the - * features. - */ -static void kvm_reset(struct virtio_device *vdev) -{ - kvm_hypercall1(KVM_S390_VIRTIO_RESET, - (unsigned long) to_kvmdev(vdev)->desc); -} - -/* - * When the virtio_ring code wants to notify the Host, it calls us here and we - * make a hypercall. We hand the address of the virtqueue so the Host - * knows which virtqueue we're talking about. - */ -static bool kvm_notify(struct virtqueue *vq) -{ - long rc; - struct kvm_vqconfig *config = vq->priv; - - rc = kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address); - if (rc < 0) - return false; - return true; -} - -/* - * This routine finds the first virtqueue described in the configuration of - * this device and sets it up. - */ -static struct virtqueue *kvm_find_vq(struct virtio_device *vdev, - unsigned index, - void (*callback)(struct virtqueue *vq), - const char *name) -{ - struct kvm_device *kdev = to_kvmdev(vdev); - struct kvm_vqconfig *config; - struct virtqueue *vq; - int err; - - if (index >= kdev->desc->num_vq) - return ERR_PTR(-ENOENT); - - if (!name) - return NULL; - - config = kvm_vq_config(kdev->desc)+index; - - err = vmem_add_mapping(config->address, - vring_size(config->num, - KVM_S390_VIRTIO_RING_ALIGN)); - if (err) - goto out; - - vq = vring_new_virtqueue(index, config->num, KVM_S390_VIRTIO_RING_ALIGN, - vdev, true, (void *) config->address, - kvm_notify, callback, name); - if (!vq) { - err = -ENOMEM; - goto unmap; - } - - /* - * register a callback token - * The host will sent this via the external interrupt parameter - */ - config->token = (u64) vq; - - vq->priv = config; - return vq; -unmap: - vmem_remove_mapping(config->address, - vring_size(config->num, - KVM_S390_VIRTIO_RING_ALIGN)); -out: - return ERR_PTR(err); -} - -static void kvm_del_vq(struct virtqueue *vq) -{ - struct kvm_vqconfig *config = vq->priv; - - vring_del_virtqueue(vq); - vmem_remove_mapping(config->address, - vring_size(config->num, - KVM_S390_VIRTIO_RING_ALIGN)); -} - -static void kvm_del_vqs(struct virtio_device *vdev) -{ - struct virtqueue *vq, *n; - - list_for_each_entry_safe(vq, n, &vdev->vqs, list) - kvm_del_vq(vq); -} - -static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char *names[]) -{ - struct kvm_device *kdev = to_kvmdev(vdev); - int i; - - /* We must have this many virtqueues. */ - if (nvqs > kdev->desc->num_vq) - return -ENOENT; - - for (i = 0; i < nvqs; ++i) { - vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i]); - if (IS_ERR(vqs[i])) - goto error; - } - return 0; - -error: - kvm_del_vqs(vdev); - return PTR_ERR(vqs[i]); -} - -static const char *kvm_bus_name(struct virtio_device *vdev) -{ - return ""; -} - -/* - * The config ops structure as defined by virtio config - */ -static const struct virtio_config_ops kvm_vq_configspace_ops = { - .get_features = kvm_get_features, - .finalize_features = kvm_finalize_features, - .get = kvm_get, - .set = kvm_set, - .get_status = kvm_get_status, - .set_status = kvm_set_status, - .reset = kvm_reset, - .find_vqs = kvm_find_vqs, - .del_vqs = kvm_del_vqs, - .bus_name = kvm_bus_name, -}; - -/* - * The root device for the kvm virtio devices. - * This makes them appear as /sys/devices/kvm_s390/0,1,2 not /sys/devices/0,1,2. - */ -static struct device *kvm_root; - -/* - * adds a new device and register it with virtio - * appropriate drivers are loaded by the device model - */ -static void add_kvm_device(struct kvm_device_desc *d, unsigned int offset) -{ - struct kvm_device *kdev; - - kdev = kzalloc(sizeof(*kdev), GFP_KERNEL); - if (!kdev) { - printk(KERN_EMERG "Cannot allocate kvm dev %u type %u\n", - offset, d->type); - return; - } - - kdev->vdev.dev.parent = kvm_root; - kdev->vdev.id.device = d->type; - kdev->vdev.config = &kvm_vq_configspace_ops; - kdev->desc = d; - - if (register_virtio_device(&kdev->vdev) != 0) { - printk(KERN_ERR "Failed to register kvm device %u type %u\n", - offset, d->type); - kfree(kdev); - } -} - -/* - * scan_devices() simply iterates through the device page. - * The type 0 is reserved to mean "end of devices". - */ -static void scan_devices(void) -{ - unsigned int i; - struct kvm_device_desc *d; - - for (i = 0; i < PAGE_SIZE; i += desc_size(d)) { - d = kvm_devices + i; - - if (d->type == 0) - break; - - add_kvm_device(d, i); - } -} - -/* - * match for a kvm device with a specific desc pointer - */ -static int match_desc(struct device *dev, void *data) -{ - struct virtio_device *vdev = dev_to_virtio(dev); - struct kvm_device *kdev = to_kvmdev(vdev); - - return kdev->desc == data; -} - -/* - * hotplug_device tries to find changes in the device page. - */ -static void hotplug_devices(struct work_struct *dummy) -{ - unsigned int i; - struct kvm_device_desc *d; - struct device *dev; - - for (i = 0; i < PAGE_SIZE; i += desc_size(d)) { - d = kvm_devices + i; - - /* end of list */ - if (d->type == 0) - break; - - /* device already exists */ - dev = device_find_child(kvm_root, d, match_desc); - if (dev) { - /* XXX check for hotplug remove */ - put_device(dev); - continue; - } - - /* new device */ - printk(KERN_INFO "Adding new virtio device %p\n", d); - add_kvm_device(d, i); - } -} - -/* - * we emulate the request_irq behaviour on top of s390 extints - */ -static void kvm_extint_handler(struct ext_code ext_code, - unsigned int param32, unsigned long param64) -{ - struct virtqueue *vq; - u32 param; - - if ((ext_code.subcode & 0xff00) != VIRTIO_SUBCODE_64) - return; - inc_irq_stat(IRQEXT_VRT); - - /* The LSB might be overloaded, we have to mask it */ - vq = (struct virtqueue *)(param64 & ~1UL); - - /* We use ext_params to decide what this interrupt means */ - param = param32 & VIRTIO_PARAM_MASK; - - switch (param) { - case VIRTIO_PARAM_CONFIG_CHANGED: - virtio_config_changed(vq->vdev); - break; - case VIRTIO_PARAM_DEV_ADD: - schedule_work(&hotplug_work); - break; - case VIRTIO_PARAM_VRING_INTERRUPT: - default: - vring_interrupt(0, vq); - break; - } -} - -/* - * For s390-virtio, we expect a page above main storage containing - * the virtio configuration. Try to actually load from this area - * in order to figure out if the host provides this page. - */ -static int __init test_devices_support(unsigned long addr) -{ - int ret = -EIO; - - asm volatile( - "0: lura 0,%1\n" - "1: xgr %0,%0\n" - "2:\n" - EX_TABLE(0b,2b) - EX_TABLE(1b,2b) - : "+d" (ret) - : "a" (addr) - : "0", "cc"); - return ret; -} -/* - * Init function for virtio - * devices are in a single page above top of "normal" + standby mem - */ -static int __init kvm_devices_init(void) -{ - int rc; - unsigned long total_memory_size = sclp_get_rzm() * sclp_get_rnmax(); - - if (!MACHINE_IS_KVM) - return -ENODEV; - - if (test_devices_support(total_memory_size) < 0) - return -ENODEV; - - rc = vmem_add_mapping(total_memory_size, PAGE_SIZE); - if (rc) - return rc; - - kvm_devices = (void *) total_memory_size; - - kvm_root = root_device_register("kvm_s390"); - if (IS_ERR(kvm_root)) { - rc = PTR_ERR(kvm_root); - printk(KERN_ERR "Could not register kvm_s390 root device"); - vmem_remove_mapping(total_memory_size, PAGE_SIZE); - return rc; - } - - INIT_WORK(&hotplug_work, hotplug_devices); - - irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); - register_external_irq(EXT_IRQ_CP_SERVICE, kvm_extint_handler); - - scan_devices(); - return 0; -} - -/* code for early console output with virtio_console */ -static __init int early_put_chars(u32 vtermno, const char *buf, int count) -{ - char scratch[17]; - unsigned int len = count; - - if (len > sizeof(scratch) - 1) - len = sizeof(scratch) - 1; - scratch[len] = '\0'; - memcpy(scratch, buf, len); - kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, __pa(scratch)); - return len; -} - -static int __init s390_virtio_console_init(void) -{ - if (sclp_has_vt220() || sclp_has_linemode()) - return -ENODEV; - return virtio_cons_early_init(early_put_chars); -} -console_initcall(s390_virtio_console_init); - - -/* - * We do this after core stuff, but before the drivers. - */ -postcore_initcall(kvm_devices_init); diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c deleted file mode 100644 index 6f1fa17..0000000 --- a/drivers/s390/kvm/virtio_ccw.c +++ /dev/null @@ -1,1380 +0,0 @@ -/* - * ccw based virtio transport - * - * Copyright IBM Corp. 2012, 2014 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * - * Author(s): Cornelia Huck - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * virtio related functions - */ - -struct vq_config_block { - __u16 index; - __u16 num; -} __packed; - -#define VIRTIO_CCW_CONFIG_SIZE 0x100 -/* same as PCI config space size, should be enough for all drivers */ - -struct virtio_ccw_device { - struct virtio_device vdev; - __u8 *status; - __u8 config[VIRTIO_CCW_CONFIG_SIZE]; - struct ccw_device *cdev; - __u32 curr_io; - int err; - unsigned int revision; /* Transport revision */ - wait_queue_head_t wait_q; - spinlock_t lock; - struct list_head virtqueues; - unsigned long indicators; - unsigned long indicators2; - struct vq_config_block *config_block; - bool is_thinint; - bool going_away; - bool device_lost; - void *airq_info; -}; - -struct vq_info_block_legacy { - __u64 queue; - __u32 align; - __u16 index; - __u16 num; -} __packed; - -struct vq_info_block { - __u64 desc; - __u32 res0; - __u16 index; - __u16 num; - __u64 avail; - __u64 used; -} __packed; - -struct virtio_feature_desc { - __u32 features; - __u8 index; -} __packed; - -struct virtio_thinint_area { - unsigned long summary_indicator; - unsigned long indicator; - u64 bit_nr; - u8 isc; -} __packed; - -struct virtio_rev_info { - __u16 revision; - __u16 length; - __u8 data[]; -}; - -/* the highest virtio-ccw revision we support */ -#define VIRTIO_CCW_REV_MAX 1 - -struct virtio_ccw_vq_info { - struct virtqueue *vq; - int num; - void *queue; - union { - struct vq_info_block s; - struct vq_info_block_legacy l; - } *info_block; - int bit_nr; - struct list_head node; - long cookie; -}; - -#define VIRTIO_AIRQ_ISC IO_SCH_ISC /* inherit from subchannel */ - -#define VIRTIO_IV_BITS (L1_CACHE_BYTES * 8) -#define MAX_AIRQ_AREAS 20 - -static int virtio_ccw_use_airq = 1; - -struct airq_info { - rwlock_t lock; - u8 summary_indicator; - struct airq_struct airq; - struct airq_iv *aiv; -}; -static struct airq_info *airq_areas[MAX_AIRQ_AREAS]; - -#define CCW_CMD_SET_VQ 0x13 -#define CCW_CMD_VDEV_RESET 0x33 -#define CCW_CMD_SET_IND 0x43 -#define CCW_CMD_SET_CONF_IND 0x53 -#define CCW_CMD_READ_FEAT 0x12 -#define CCW_CMD_WRITE_FEAT 0x11 -#define CCW_CMD_READ_CONF 0x22 -#define CCW_CMD_WRITE_CONF 0x21 -#define CCW_CMD_WRITE_STATUS 0x31 -#define CCW_CMD_READ_VQ_CONF 0x32 -#define CCW_CMD_SET_IND_ADAPTER 0x73 -#define CCW_CMD_SET_VIRTIO_REV 0x83 - -#define VIRTIO_CCW_DOING_SET_VQ 0x00010000 -#define VIRTIO_CCW_DOING_RESET 0x00040000 -#define VIRTIO_CCW_DOING_READ_FEAT 0x00080000 -#define VIRTIO_CCW_DOING_WRITE_FEAT 0x00100000 -#define VIRTIO_CCW_DOING_READ_CONFIG 0x00200000 -#define VIRTIO_CCW_DOING_WRITE_CONFIG 0x00400000 -#define VIRTIO_CCW_DOING_WRITE_STATUS 0x00800000 -#define VIRTIO_CCW_DOING_SET_IND 0x01000000 -#define VIRTIO_CCW_DOING_READ_VQ_CONF 0x02000000 -#define VIRTIO_CCW_DOING_SET_CONF_IND 0x04000000 -#define VIRTIO_CCW_DOING_SET_IND_ADAPTER 0x08000000 -#define VIRTIO_CCW_DOING_SET_VIRTIO_REV 0x10000000 -#define VIRTIO_CCW_INTPARM_MASK 0xffff0000 - -static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev) -{ - return container_of(vdev, struct virtio_ccw_device, vdev); -} - -static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info) -{ - unsigned long i, flags; - - write_lock_irqsave(&info->lock, flags); - for (i = 0; i < airq_iv_end(info->aiv); i++) { - if (vq == (void *)airq_iv_get_ptr(info->aiv, i)) { - airq_iv_free_bit(info->aiv, i); - airq_iv_set_ptr(info->aiv, i, 0); - break; - } - } - write_unlock_irqrestore(&info->lock, flags); -} - -static void virtio_airq_handler(struct airq_struct *airq) -{ - struct airq_info *info = container_of(airq, struct airq_info, airq); - unsigned long ai; - - inc_irq_stat(IRQIO_VAI); - read_lock(&info->lock); - /* Walk through indicators field, summary indicator active. */ - for (ai = 0;;) { - ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv)); - if (ai == -1UL) - break; - vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai)); - } - info->summary_indicator = 0; - smp_wmb(); - /* Walk through indicators field, summary indicator not active. */ - for (ai = 0;;) { - ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv)); - if (ai == -1UL) - break; - vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai)); - } - read_unlock(&info->lock); -} - -static struct airq_info *new_airq_info(void) -{ - struct airq_info *info; - int rc; - - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - return NULL; - rwlock_init(&info->lock); - info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR); - if (!info->aiv) { - kfree(info); - return NULL; - } - info->airq.handler = virtio_airq_handler; - info->airq.lsi_ptr = &info->summary_indicator; - info->airq.lsi_mask = 0xff; - info->airq.isc = VIRTIO_AIRQ_ISC; - rc = register_adapter_interrupt(&info->airq); - if (rc) { - airq_iv_release(info->aiv); - kfree(info); - return NULL; - } - return info; -} - -static void destroy_airq_info(struct airq_info *info) -{ - if (!info) - return; - - unregister_adapter_interrupt(&info->airq); - airq_iv_release(info->aiv); - kfree(info); -} - -static unsigned long get_airq_indicator(struct virtqueue *vqs[], int nvqs, - u64 *first, void **airq_info) -{ - int i, j; - struct airq_info *info; - unsigned long indicator_addr = 0; - unsigned long bit, flags; - - for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) { - if (!airq_areas[i]) - airq_areas[i] = new_airq_info(); - info = airq_areas[i]; - if (!info) - return 0; - write_lock_irqsave(&info->lock, flags); - bit = airq_iv_alloc(info->aiv, nvqs); - if (bit == -1UL) { - /* Not enough vacancies. */ - write_unlock_irqrestore(&info->lock, flags); - continue; - } - *first = bit; - *airq_info = info; - indicator_addr = (unsigned long)info->aiv->vector; - for (j = 0; j < nvqs; j++) { - airq_iv_set_ptr(info->aiv, bit + j, - (unsigned long)vqs[j]); - } - write_unlock_irqrestore(&info->lock, flags); - } - return indicator_addr; -} - -static void virtio_ccw_drop_indicators(struct virtio_ccw_device *vcdev) -{ - struct virtio_ccw_vq_info *info; - - list_for_each_entry(info, &vcdev->virtqueues, node) - drop_airq_indicator(info->vq, vcdev->airq_info); -} - -static int doing_io(struct virtio_ccw_device *vcdev, __u32 flag) -{ - unsigned long flags; - __u32 ret; - - spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags); - if (vcdev->err) - ret = 0; - else - ret = vcdev->curr_io & flag; - spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags); - return ret; -} - -static int ccw_io_helper(struct virtio_ccw_device *vcdev, - struct ccw1 *ccw, __u32 intparm) -{ - int ret; - unsigned long flags; - int flag = intparm & VIRTIO_CCW_INTPARM_MASK; - - do { - spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags); - ret = ccw_device_start(vcdev->cdev, ccw, intparm, 0, 0); - if (!ret) { - if (!vcdev->curr_io) - vcdev->err = 0; - vcdev->curr_io |= flag; - } - spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags); - cpu_relax(); - } while (ret == -EBUSY); - wait_event(vcdev->wait_q, doing_io(vcdev, flag) == 0); - return ret ? ret : vcdev->err; -} - -static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev, - struct ccw1 *ccw) -{ - int ret; - unsigned long *indicatorp = NULL; - struct virtio_thinint_area *thinint_area = NULL; - struct airq_info *airq_info = vcdev->airq_info; - - if (vcdev->is_thinint) { - thinint_area = kzalloc(sizeof(*thinint_area), - GFP_DMA | GFP_KERNEL); - if (!thinint_area) - return; - thinint_area->summary_indicator = - (unsigned long) &airq_info->summary_indicator; - thinint_area->isc = VIRTIO_AIRQ_ISC; - ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER; - ccw->count = sizeof(*thinint_area); - ccw->cda = (__u32)(unsigned long) thinint_area; - } else { - indicatorp = kmalloc(sizeof(&vcdev->indicators), - GFP_DMA | GFP_KERNEL); - if (!indicatorp) - return; - *indicatorp = 0; - ccw->cmd_code = CCW_CMD_SET_IND; - ccw->count = sizeof(vcdev->indicators); - ccw->cda = (__u32)(unsigned long) indicatorp; - } - /* Deregister indicators from host. */ - vcdev->indicators = 0; - ccw->flags = 0; - ret = ccw_io_helper(vcdev, ccw, - vcdev->is_thinint ? - VIRTIO_CCW_DOING_SET_IND_ADAPTER : - VIRTIO_CCW_DOING_SET_IND); - if (ret && (ret != -ENODEV)) - dev_info(&vcdev->cdev->dev, - "Failed to deregister indicators (%d)\n", ret); - else if (vcdev->is_thinint) - virtio_ccw_drop_indicators(vcdev); - kfree(indicatorp); - kfree(thinint_area); -} - -static inline long do_kvm_notify(struct subchannel_id schid, - unsigned long queue_index, - long cookie) -{ - register unsigned long __nr asm("1") = KVM_S390_VIRTIO_CCW_NOTIFY; - register struct subchannel_id __schid asm("2") = schid; - register unsigned long __index asm("3") = queue_index; - register long __rc asm("2"); - register long __cookie asm("4") = cookie; - - asm volatile ("diag 2,4,0x500\n" - : "=d" (__rc) : "d" (__nr), "d" (__schid), "d" (__index), - "d"(__cookie) - : "memory", "cc"); - return __rc; -} - -static bool virtio_ccw_kvm_notify(struct virtqueue *vq) -{ - struct virtio_ccw_vq_info *info = vq->priv; - struct virtio_ccw_device *vcdev; - struct subchannel_id schid; - - vcdev = to_vc_device(info->vq->vdev); - ccw_device_get_schid(vcdev->cdev, &schid); - info->cookie = do_kvm_notify(schid, vq->index, info->cookie); - if (info->cookie < 0) - return false; - return true; -} - -static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev, - struct ccw1 *ccw, int index) -{ - vcdev->config_block->index = index; - ccw->cmd_code = CCW_CMD_READ_VQ_CONF; - ccw->flags = 0; - ccw->count = sizeof(struct vq_config_block); - ccw->cda = (__u32)(unsigned long)(vcdev->config_block); - ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF); - return vcdev->config_block->num; -} - -static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vq->vdev); - struct virtio_ccw_vq_info *info = vq->priv; - unsigned long flags; - unsigned long size; - int ret; - unsigned int index = vq->index; - - /* Remove from our list. */ - spin_lock_irqsave(&vcdev->lock, flags); - list_del(&info->node); - spin_unlock_irqrestore(&vcdev->lock, flags); - - /* Release from host. */ - if (vcdev->revision == 0) { - info->info_block->l.queue = 0; - info->info_block->l.align = 0; - info->info_block->l.index = index; - info->info_block->l.num = 0; - ccw->count = sizeof(info->info_block->l); - } else { - info->info_block->s.desc = 0; - info->info_block->s.index = index; - info->info_block->s.num = 0; - info->info_block->s.avail = 0; - info->info_block->s.used = 0; - ccw->count = sizeof(info->info_block->s); - } - ccw->cmd_code = CCW_CMD_SET_VQ; - ccw->flags = 0; - ccw->cda = (__u32)(unsigned long)(info->info_block); - ret = ccw_io_helper(vcdev, ccw, - VIRTIO_CCW_DOING_SET_VQ | index); - /* - * -ENODEV isn't considered an error: The device is gone anyway. - * This may happen on device detach. - */ - if (ret && (ret != -ENODEV)) - dev_warn(&vq->vdev->dev, "Error %d while deleting queue %d", - ret, index); - - vring_del_virtqueue(vq); - size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN)); - free_pages_exact(info->queue, size); - kfree(info->info_block); - kfree(info); -} - -static void virtio_ccw_del_vqs(struct virtio_device *vdev) -{ - struct virtqueue *vq, *n; - struct ccw1 *ccw; - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return; - - virtio_ccw_drop_indicator(vcdev, ccw); - - list_for_each_entry_safe(vq, n, &vdev->vqs, list) - virtio_ccw_del_vq(vq, ccw); - - kfree(ccw); -} - -static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, - int i, vq_callback_t *callback, - const char *name, - struct ccw1 *ccw) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - int err; - struct virtqueue *vq = NULL; - struct virtio_ccw_vq_info *info; - unsigned long size = 0; /* silence the compiler */ - unsigned long flags; - - /* Allocate queue. */ - info = kzalloc(sizeof(struct virtio_ccw_vq_info), GFP_KERNEL); - if (!info) { - dev_warn(&vcdev->cdev->dev, "no info\n"); - err = -ENOMEM; - goto out_err; - } - info->info_block = kzalloc(sizeof(*info->info_block), - GFP_DMA | GFP_KERNEL); - if (!info->info_block) { - dev_warn(&vcdev->cdev->dev, "no info block\n"); - err = -ENOMEM; - goto out_err; - } - info->num = virtio_ccw_read_vq_conf(vcdev, ccw, i); - size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN)); - info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); - if (info->queue == NULL) { - dev_warn(&vcdev->cdev->dev, "no queue\n"); - err = -ENOMEM; - goto out_err; - } - - vq = vring_new_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev, - true, info->queue, virtio_ccw_kvm_notify, - callback, name); - if (!vq) { - /* For now, we fail if we can't get the requested size. */ - dev_warn(&vcdev->cdev->dev, "no vq\n"); - err = -ENOMEM; - goto out_err; - } - - /* Register it with the host. */ - if (vcdev->revision == 0) { - info->info_block->l.queue = (__u64)info->queue; - info->info_block->l.align = KVM_VIRTIO_CCW_RING_ALIGN; - info->info_block->l.index = i; - info->info_block->l.num = info->num; - ccw->count = sizeof(info->info_block->l); - } else { - info->info_block->s.desc = (__u64)info->queue; - info->info_block->s.index = i; - info->info_block->s.num = info->num; - info->info_block->s.avail = (__u64)virtqueue_get_avail(vq); - info->info_block->s.used = (__u64)virtqueue_get_used(vq); - ccw->count = sizeof(info->info_block->s); - } - ccw->cmd_code = CCW_CMD_SET_VQ; - ccw->flags = 0; - ccw->cda = (__u32)(unsigned long)(info->info_block); - err = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_VQ | i); - if (err) { - dev_warn(&vcdev->cdev->dev, "SET_VQ failed\n"); - goto out_err; - } - - info->vq = vq; - vq->priv = info; - - /* Save it to our list. */ - spin_lock_irqsave(&vcdev->lock, flags); - list_add(&info->node, &vcdev->virtqueues); - spin_unlock_irqrestore(&vcdev->lock, flags); - - return vq; - -out_err: - if (vq) - vring_del_virtqueue(vq); - if (info) { - if (info->queue) - free_pages_exact(info->queue, size); - kfree(info->info_block); - } - kfree(info); - return ERR_PTR(err); -} - -static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev, - struct virtqueue *vqs[], int nvqs, - struct ccw1 *ccw) -{ - int ret; - struct virtio_thinint_area *thinint_area = NULL; - struct airq_info *info; - - thinint_area = kzalloc(sizeof(*thinint_area), GFP_DMA | GFP_KERNEL); - if (!thinint_area) { - ret = -ENOMEM; - goto out; - } - /* Try to get an indicator. */ - thinint_area->indicator = get_airq_indicator(vqs, nvqs, - &thinint_area->bit_nr, - &vcdev->airq_info); - if (!thinint_area->indicator) { - ret = -ENOSPC; - goto out; - } - info = vcdev->airq_info; - thinint_area->summary_indicator = - (unsigned long) &info->summary_indicator; - thinint_area->isc = VIRTIO_AIRQ_ISC; - ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER; - ccw->flags = CCW_FLAG_SLI; - ccw->count = sizeof(*thinint_area); - ccw->cda = (__u32)(unsigned long)thinint_area; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND_ADAPTER); - if (ret) { - if (ret == -EOPNOTSUPP) { - /* - * The host does not support adapter interrupts - * for virtio-ccw, stop trying. - */ - virtio_ccw_use_airq = 0; - pr_info("Adapter interrupts unsupported on host\n"); - } else - dev_warn(&vcdev->cdev->dev, - "enabling adapter interrupts = %d\n", ret); - virtio_ccw_drop_indicators(vcdev); - } -out: - kfree(thinint_area); - return ret; -} - -static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char *names[]) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - unsigned long *indicatorp = NULL; - int ret, i; - struct ccw1 *ccw; - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return -ENOMEM; - - for (i = 0; i < nvqs; ++i) { - vqs[i] = virtio_ccw_setup_vq(vdev, i, callbacks[i], names[i], - ccw); - if (IS_ERR(vqs[i])) { - ret = PTR_ERR(vqs[i]); - vqs[i] = NULL; - goto out; - } - } - ret = -ENOMEM; - /* We need a data area under 2G to communicate. */ - indicatorp = kmalloc(sizeof(&vcdev->indicators), GFP_DMA | GFP_KERNEL); - if (!indicatorp) - goto out; - *indicatorp = (unsigned long) &vcdev->indicators; - if (vcdev->is_thinint) { - ret = virtio_ccw_register_adapter_ind(vcdev, vqs, nvqs, ccw); - if (ret) - /* no error, just fall back to legacy interrupts */ - vcdev->is_thinint = 0; - } - if (!vcdev->is_thinint) { - /* Register queue indicators with host. */ - vcdev->indicators = 0; - ccw->cmd_code = CCW_CMD_SET_IND; - ccw->flags = 0; - ccw->count = sizeof(vcdev->indicators); - ccw->cda = (__u32)(unsigned long) indicatorp; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND); - if (ret) - goto out; - } - /* Register indicators2 with host for config changes */ - *indicatorp = (unsigned long) &vcdev->indicators2; - vcdev->indicators2 = 0; - ccw->cmd_code = CCW_CMD_SET_CONF_IND; - ccw->flags = 0; - ccw->count = sizeof(vcdev->indicators2); - ccw->cda = (__u32)(unsigned long) indicatorp; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_CONF_IND); - if (ret) - goto out; - - kfree(indicatorp); - kfree(ccw); - return 0; -out: - kfree(indicatorp); - kfree(ccw); - virtio_ccw_del_vqs(vdev); - return ret; -} - -static void virtio_ccw_reset(struct virtio_device *vdev) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - struct ccw1 *ccw; - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return; - - /* Zero status bits. */ - *vcdev->status = 0; - - /* Send a reset ccw on device. */ - ccw->cmd_code = CCW_CMD_VDEV_RESET; - ccw->flags = 0; - ccw->count = 0; - ccw->cda = 0; - ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_RESET); - kfree(ccw); -} - -static u64 virtio_ccw_get_features(struct virtio_device *vdev) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - struct virtio_feature_desc *features; - int ret; - u64 rc; - struct ccw1 *ccw; - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return 0; - - features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL); - if (!features) { - rc = 0; - goto out_free; - } - /* Read the feature bits from the host. */ - features->index = 0; - ccw->cmd_code = CCW_CMD_READ_FEAT; - ccw->flags = 0; - ccw->count = sizeof(*features); - ccw->cda = (__u32)(unsigned long)features; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_FEAT); - if (ret) { - rc = 0; - goto out_free; - } - - rc = le32_to_cpu(features->features); - - if (vcdev->revision == 0) - goto out_free; - - /* Read second half of the feature bits from the host. */ - features->index = 1; - ccw->cmd_code = CCW_CMD_READ_FEAT; - ccw->flags = 0; - ccw->count = sizeof(*features); - ccw->cda = (__u32)(unsigned long)features; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_FEAT); - if (ret == 0) - rc |= (u64)le32_to_cpu(features->features) << 32; - -out_free: - kfree(features); - kfree(ccw); - return rc; -} - -static int virtio_ccw_finalize_features(struct virtio_device *vdev) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - struct virtio_feature_desc *features; - struct ccw1 *ccw; - int ret; - - if (vcdev->revision >= 1 && - !__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) { - dev_err(&vdev->dev, "virtio: device uses revision 1 " - "but does not have VIRTIO_F_VERSION_1\n"); - return -EINVAL; - } - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return -ENOMEM; - - features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL); - if (!features) { - ret = -ENOMEM; - goto out_free; - } - /* Give virtio_ring a chance to accept features. */ - vring_transport_features(vdev); - - features->index = 0; - features->features = cpu_to_le32((u32)vdev->features); - /* Write the first half of the feature bits to the host. */ - ccw->cmd_code = CCW_CMD_WRITE_FEAT; - ccw->flags = 0; - ccw->count = sizeof(*features); - ccw->cda = (__u32)(unsigned long)features; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT); - if (ret) - goto out_free; - - if (vcdev->revision == 0) - goto out_free; - - features->index = 1; - features->features = cpu_to_le32(vdev->features >> 32); - /* Write the second half of the feature bits to the host. */ - ccw->cmd_code = CCW_CMD_WRITE_FEAT; - ccw->flags = 0; - ccw->count = sizeof(*features); - ccw->cda = (__u32)(unsigned long)features; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT); - -out_free: - kfree(features); - kfree(ccw); - - return ret; -} - -static void virtio_ccw_get_config(struct virtio_device *vdev, - unsigned int offset, void *buf, unsigned len) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - int ret; - struct ccw1 *ccw; - void *config_area; - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return; - - config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL); - if (!config_area) - goto out_free; - - /* Read the config area from the host. */ - ccw->cmd_code = CCW_CMD_READ_CONF; - ccw->flags = 0; - ccw->count = offset + len; - ccw->cda = (__u32)(unsigned long)config_area; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_CONFIG); - if (ret) - goto out_free; - - memcpy(vcdev->config, config_area, sizeof(vcdev->config)); - memcpy(buf, &vcdev->config[offset], len); - -out_free: - kfree(config_area); - kfree(ccw); -} - -static void virtio_ccw_set_config(struct virtio_device *vdev, - unsigned int offset, const void *buf, - unsigned len) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - struct ccw1 *ccw; - void *config_area; - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return; - - config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL); - if (!config_area) - goto out_free; - - memcpy(&vcdev->config[offset], buf, len); - /* Write the config area to the host. */ - memcpy(config_area, vcdev->config, sizeof(vcdev->config)); - ccw->cmd_code = CCW_CMD_WRITE_CONF; - ccw->flags = 0; - ccw->count = offset + len; - ccw->cda = (__u32)(unsigned long)config_area; - ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_CONFIG); - -out_free: - kfree(config_area); - kfree(ccw); -} - -static u8 virtio_ccw_get_status(struct virtio_device *vdev) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - - return *vcdev->status; -} - -static void virtio_ccw_set_status(struct virtio_device *vdev, u8 status) -{ - struct virtio_ccw_device *vcdev = to_vc_device(vdev); - u8 old_status = *vcdev->status; - struct ccw1 *ccw; - int ret; - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return; - - /* Write the status to the host. */ - *vcdev->status = status; - ccw->cmd_code = CCW_CMD_WRITE_STATUS; - ccw->flags = 0; - ccw->count = sizeof(status); - ccw->cda = (__u32)(unsigned long)vcdev->status; - ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_STATUS); - /* Write failed? We assume status is unchanged. */ - if (ret) - *vcdev->status = old_status; - kfree(ccw); -} - -static struct virtio_config_ops virtio_ccw_config_ops = { - .get_features = virtio_ccw_get_features, - .finalize_features = virtio_ccw_finalize_features, - .get = virtio_ccw_get_config, - .set = virtio_ccw_set_config, - .get_status = virtio_ccw_get_status, - .set_status = virtio_ccw_set_status, - .reset = virtio_ccw_reset, - .find_vqs = virtio_ccw_find_vqs, - .del_vqs = virtio_ccw_del_vqs, -}; - - -/* - * ccw bus driver related functions - */ - -static void virtio_ccw_release_dev(struct device *_d) -{ - struct virtio_device *dev = container_of(_d, struct virtio_device, - dev); - struct virtio_ccw_device *vcdev = to_vc_device(dev); - - kfree(vcdev->status); - kfree(vcdev->config_block); - kfree(vcdev); -} - -static int irb_is_error(struct irb *irb) -{ - if (scsw_cstat(&irb->scsw) != 0) - return 1; - if (scsw_dstat(&irb->scsw) & ~(DEV_STAT_CHN_END | DEV_STAT_DEV_END)) - return 1; - if (scsw_cc(&irb->scsw) != 0) - return 1; - return 0; -} - -static struct virtqueue *virtio_ccw_vq_by_ind(struct virtio_ccw_device *vcdev, - int index) -{ - struct virtio_ccw_vq_info *info; - unsigned long flags; - struct virtqueue *vq; - - vq = NULL; - spin_lock_irqsave(&vcdev->lock, flags); - list_for_each_entry(info, &vcdev->virtqueues, node) { - if (info->vq->index == index) { - vq = info->vq; - break; - } - } - spin_unlock_irqrestore(&vcdev->lock, flags); - return vq; -} - -static void virtio_ccw_int_handler(struct ccw_device *cdev, - unsigned long intparm, - struct irb *irb) -{ - __u32 activity = intparm & VIRTIO_CCW_INTPARM_MASK; - struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); - int i; - struct virtqueue *vq; - - if (!vcdev) - return; - /* Check if it's a notification from the host. */ - if ((intparm == 0) && - (scsw_stctl(&irb->scsw) == - (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND))) { - /* OK */ - } - if (irb_is_error(irb)) { - /* Command reject? */ - if ((scsw_dstat(&irb->scsw) & DEV_STAT_UNIT_CHECK) && - (irb->ecw[0] & SNS0_CMD_REJECT)) - vcdev->err = -EOPNOTSUPP; - else - /* Map everything else to -EIO. */ - vcdev->err = -EIO; - } - if (vcdev->curr_io & activity) { - switch (activity) { - case VIRTIO_CCW_DOING_READ_FEAT: - case VIRTIO_CCW_DOING_WRITE_FEAT: - case VIRTIO_CCW_DOING_READ_CONFIG: - case VIRTIO_CCW_DOING_WRITE_CONFIG: - case VIRTIO_CCW_DOING_WRITE_STATUS: - case VIRTIO_CCW_DOING_SET_VQ: - case VIRTIO_CCW_DOING_SET_IND: - case VIRTIO_CCW_DOING_SET_CONF_IND: - case VIRTIO_CCW_DOING_RESET: - case VIRTIO_CCW_DOING_READ_VQ_CONF: - case VIRTIO_CCW_DOING_SET_IND_ADAPTER: - case VIRTIO_CCW_DOING_SET_VIRTIO_REV: - vcdev->curr_io &= ~activity; - wake_up(&vcdev->wait_q); - break; - default: - /* don't know what to do... */ - dev_warn(&cdev->dev, "Suspicious activity '%08x'\n", - activity); - WARN_ON(1); - break; - } - } - for_each_set_bit(i, &vcdev->indicators, - sizeof(vcdev->indicators) * BITS_PER_BYTE) { - /* The bit clear must happen before the vring kick. */ - clear_bit(i, &vcdev->indicators); - barrier(); - vq = virtio_ccw_vq_by_ind(vcdev, i); - vring_interrupt(0, vq); - } - if (test_bit(0, &vcdev->indicators2)) { - virtio_config_changed(&vcdev->vdev); - clear_bit(0, &vcdev->indicators2); - } -} - -/* - * We usually want to autoonline all devices, but give the admin - * a way to exempt devices from this. - */ -#define __DEV_WORDS ((__MAX_SUBCHANNEL + (8*sizeof(long) - 1)) / \ - (8*sizeof(long))) -static unsigned long devs_no_auto[__MAX_SSID + 1][__DEV_WORDS]; - -static char *no_auto = ""; - -module_param(no_auto, charp, 0444); -MODULE_PARM_DESC(no_auto, "list of ccw bus id ranges not to be auto-onlined"); - -static int virtio_ccw_check_autoonline(struct ccw_device *cdev) -{ - struct ccw_dev_id id; - - ccw_device_get_id(cdev, &id); - if (test_bit(id.devno, devs_no_auto[id.ssid])) - return 0; - return 1; -} - -static void virtio_ccw_auto_online(void *data, async_cookie_t cookie) -{ - struct ccw_device *cdev = data; - int ret; - - ret = ccw_device_set_online(cdev); - if (ret) - dev_warn(&cdev->dev, "Failed to set online: %d\n", ret); -} - -static int virtio_ccw_probe(struct ccw_device *cdev) -{ - cdev->handler = virtio_ccw_int_handler; - - if (virtio_ccw_check_autoonline(cdev)) - async_schedule(virtio_ccw_auto_online, cdev); - return 0; -} - -static struct virtio_ccw_device *virtio_grab_drvdata(struct ccw_device *cdev) -{ - unsigned long flags; - struct virtio_ccw_device *vcdev; - - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); - vcdev = dev_get_drvdata(&cdev->dev); - if (!vcdev || vcdev->going_away) { - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); - return NULL; - } - vcdev->going_away = true; - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); - return vcdev; -} - -static void virtio_ccw_remove(struct ccw_device *cdev) -{ - unsigned long flags; - struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev); - - if (vcdev && cdev->online) { - if (vcdev->device_lost) - virtio_break_device(&vcdev->vdev); - unregister_virtio_device(&vcdev->vdev); - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); - dev_set_drvdata(&cdev->dev, NULL); - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); - } - cdev->handler = NULL; -} - -static int virtio_ccw_offline(struct ccw_device *cdev) -{ - unsigned long flags; - struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev); - - if (!vcdev) - return 0; - if (vcdev->device_lost) - virtio_break_device(&vcdev->vdev); - unregister_virtio_device(&vcdev->vdev); - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); - dev_set_drvdata(&cdev->dev, NULL); - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); - return 0; -} - -static int virtio_ccw_set_transport_rev(struct virtio_ccw_device *vcdev) -{ - struct virtio_rev_info *rev; - struct ccw1 *ccw; - int ret; - - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); - if (!ccw) - return -ENOMEM; - rev = kzalloc(sizeof(*rev), GFP_DMA | GFP_KERNEL); - if (!rev) { - kfree(ccw); - return -ENOMEM; - } - - /* Set transport revision */ - ccw->cmd_code = CCW_CMD_SET_VIRTIO_REV; - ccw->flags = 0; - ccw->count = sizeof(*rev); - ccw->cda = (__u32)(unsigned long)rev; - - vcdev->revision = VIRTIO_CCW_REV_MAX; - do { - rev->revision = vcdev->revision; - /* none of our supported revisions carry payload */ - rev->length = 0; - ret = ccw_io_helper(vcdev, ccw, - VIRTIO_CCW_DOING_SET_VIRTIO_REV); - if (ret == -EOPNOTSUPP) { - if (vcdev->revision == 0) - /* - * The host device does not support setting - * the revision: let's operate it in legacy - * mode. - */ - ret = 0; - else - vcdev->revision--; - } - } while (ret == -EOPNOTSUPP); - - kfree(ccw); - kfree(rev); - return ret; -} - -static int virtio_ccw_online(struct ccw_device *cdev) -{ - int ret; - struct virtio_ccw_device *vcdev; - unsigned long flags; - - vcdev = kzalloc(sizeof(*vcdev), GFP_KERNEL); - if (!vcdev) { - dev_warn(&cdev->dev, "Could not get memory for virtio\n"); - ret = -ENOMEM; - goto out_free; - } - vcdev->config_block = kzalloc(sizeof(*vcdev->config_block), - GFP_DMA | GFP_KERNEL); - if (!vcdev->config_block) { - ret = -ENOMEM; - goto out_free; - } - vcdev->status = kzalloc(sizeof(*vcdev->status), GFP_DMA | GFP_KERNEL); - if (!vcdev->status) { - ret = -ENOMEM; - goto out_free; - } - - vcdev->is_thinint = virtio_ccw_use_airq; /* at least try */ - - vcdev->vdev.dev.parent = &cdev->dev; - vcdev->vdev.dev.release = virtio_ccw_release_dev; - vcdev->vdev.config = &virtio_ccw_config_ops; - vcdev->cdev = cdev; - init_waitqueue_head(&vcdev->wait_q); - INIT_LIST_HEAD(&vcdev->virtqueues); - spin_lock_init(&vcdev->lock); - - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); - dev_set_drvdata(&cdev->dev, vcdev); - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); - vcdev->vdev.id.vendor = cdev->id.cu_type; - vcdev->vdev.id.device = cdev->id.cu_model; - - ret = virtio_ccw_set_transport_rev(vcdev); - if (ret) - goto out_free; - - ret = register_virtio_device(&vcdev->vdev); - if (ret) { - dev_warn(&cdev->dev, "Failed to register virtio device: %d\n", - ret); - goto out_put; - } - return 0; -out_put: - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); - dev_set_drvdata(&cdev->dev, NULL); - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); - put_device(&vcdev->vdev.dev); - return ret; -out_free: - if (vcdev) { - kfree(vcdev->status); - kfree(vcdev->config_block); - } - kfree(vcdev); - return ret; -} - -static int virtio_ccw_cio_notify(struct ccw_device *cdev, int event) -{ - int rc; - struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); - - /* - * Make sure vcdev is set - * i.e. set_offline/remove callback not already running - */ - if (!vcdev) - return NOTIFY_DONE; - - switch (event) { - case CIO_GONE: - vcdev->device_lost = true; - rc = NOTIFY_DONE; - break; - default: - rc = NOTIFY_DONE; - break; - } - return rc; -} - -static struct ccw_device_id virtio_ids[] = { - { CCW_DEVICE(0x3832, 0) }, - {}, -}; -MODULE_DEVICE_TABLE(ccw, virtio_ids); - -static struct ccw_driver virtio_ccw_driver = { - .driver = { - .owner = THIS_MODULE, - .name = "virtio_ccw", - }, - .ids = virtio_ids, - .probe = virtio_ccw_probe, - .remove = virtio_ccw_remove, - .set_offline = virtio_ccw_offline, - .set_online = virtio_ccw_online, - .notify = virtio_ccw_cio_notify, - .int_class = IRQIO_VIR, -}; - -static int __init pure_hex(char **cp, unsigned int *val, int min_digit, - int max_digit, int max_val) -{ - int diff; - - diff = 0; - *val = 0; - - while (diff <= max_digit) { - int value = hex_to_bin(**cp); - - if (value < 0) - break; - *val = *val * 16 + value; - (*cp)++; - diff++; - } - - if ((diff < min_digit) || (diff > max_digit) || (*val > max_val)) - return 1; - - return 0; -} - -static int __init parse_busid(char *str, unsigned int *cssid, - unsigned int *ssid, unsigned int *devno) -{ - char *str_work; - int rc, ret; - - rc = 1; - - if (*str == '\0') - goto out; - - str_work = str; - ret = pure_hex(&str_work, cssid, 1, 2, __MAX_CSSID); - if (ret || (str_work[0] != '.')) - goto out; - str_work++; - ret = pure_hex(&str_work, ssid, 1, 1, __MAX_SSID); - if (ret || (str_work[0] != '.')) - goto out; - str_work++; - ret = pure_hex(&str_work, devno, 4, 4, __MAX_SUBCHANNEL); - if (ret || (str_work[0] != '\0')) - goto out; - - rc = 0; -out: - return rc; -} - -static void __init no_auto_parse(void) -{ - unsigned int from_cssid, to_cssid, from_ssid, to_ssid, from, to; - char *parm, *str; - int rc; - - str = no_auto; - while ((parm = strsep(&str, ","))) { - rc = parse_busid(strsep(&parm, "-"), &from_cssid, - &from_ssid, &from); - if (rc) - continue; - if (parm != NULL) { - rc = parse_busid(parm, &to_cssid, - &to_ssid, &to); - if ((from_ssid > to_ssid) || - ((from_ssid == to_ssid) && (from > to))) - rc = -EINVAL; - } else { - to_cssid = from_cssid; - to_ssid = from_ssid; - to = from; - } - if (rc) - continue; - while ((from_ssid < to_ssid) || - ((from_ssid == to_ssid) && (from <= to))) { - set_bit(from, devs_no_auto[from_ssid]); - from++; - if (from > __MAX_SUBCHANNEL) { - from_ssid++; - from = 0; - } - } - } -} - -static int __init virtio_ccw_init(void) -{ - /* parse no_auto string before we do anything further */ - no_auto_parse(); - return ccw_driver_register(&virtio_ccw_driver); -} -module_init(virtio_ccw_init); - -static void __exit virtio_ccw_exit(void) -{ - int i; - - ccw_driver_unregister(&virtio_ccw_driver); - for (i = 0; i < MAX_AIRQ_AREAS; i++) - destroy_airq_info(airq_areas[i]); -} -module_exit(virtio_ccw_exit); diff --git a/drivers/s390/virtio/Makefile b/drivers/s390/virtio/Makefile new file mode 100644 index 0000000..241891a --- /dev/null +++ b/drivers/s390/virtio/Makefile @@ -0,0 +1,9 @@ +# Makefile for kvm guest drivers on s390 +# +# Copyright IBM Corp. 2008 +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License (version 2 only) +# as published by the Free Software Foundation. + +obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o diff --git a/drivers/s390/virtio/kvm_virtio.c b/drivers/s390/virtio/kvm_virtio.c new file mode 100644 index 0000000..dd65c8b --- /dev/null +++ b/drivers/s390/virtio/kvm_virtio.c @@ -0,0 +1,510 @@ +/* + * virtio for kvm on s390 + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Christian Borntraeger + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define VIRTIO_SUBCODE_64 0x0D00 + +/* + * The pointer to our (page) of device descriptions. + */ +static void *kvm_devices; +static struct work_struct hotplug_work; + +struct kvm_device { + struct virtio_device vdev; + struct kvm_device_desc *desc; +}; + +#define to_kvmdev(vd) container_of(vd, struct kvm_device, vdev) + +/* + * memory layout: + * - kvm_device_descriptor + * struct kvm_device_desc + * - configuration + * struct kvm_vqconfig + * - feature bits + * - config space + */ +static struct kvm_vqconfig *kvm_vq_config(const struct kvm_device_desc *desc) +{ + return (struct kvm_vqconfig *)(desc + 1); +} + +static u8 *kvm_vq_features(const struct kvm_device_desc *desc) +{ + return (u8 *)(kvm_vq_config(desc) + desc->num_vq); +} + +static u8 *kvm_vq_configspace(const struct kvm_device_desc *desc) +{ + return kvm_vq_features(desc) + desc->feature_len * 2; +} + +/* + * The total size of the config page used by this device (incl. desc) + */ +static unsigned desc_size(const struct kvm_device_desc *desc) +{ + return sizeof(*desc) + + desc->num_vq * sizeof(struct kvm_vqconfig) + + desc->feature_len * 2 + + desc->config_len; +} + +/* This gets the device's feature bits. */ +static u64 kvm_get_features(struct virtio_device *vdev) +{ + unsigned int i; + u32 features = 0; + struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; + u8 *in_features = kvm_vq_features(desc); + + for (i = 0; i < min(desc->feature_len * 8, 32); i++) + if (in_features[i / 8] & (1 << (i % 8))) + features |= (1 << i); + return features; +} + +static int kvm_finalize_features(struct virtio_device *vdev) +{ + unsigned int i, bits; + struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; + /* Second half of bitmap is features we accept. */ + u8 *out_features = kvm_vq_features(desc) + desc->feature_len; + + /* Give virtio_ring a chance to accept features. */ + vring_transport_features(vdev); + + /* Make sure we don't have any features > 32 bits! */ + BUG_ON((u32)vdev->features != vdev->features); + + memset(out_features, 0, desc->feature_len); + bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8; + for (i = 0; i < bits; i++) { + if (__virtio_test_bit(vdev, i)) + out_features[i / 8] |= (1 << (i % 8)); + } + + return 0; +} + +/* + * Reading and writing elements in config space + */ +static void kvm_get(struct virtio_device *vdev, unsigned int offset, + void *buf, unsigned len) +{ + struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; + + BUG_ON(offset + len > desc->config_len); + memcpy(buf, kvm_vq_configspace(desc) + offset, len); +} + +static void kvm_set(struct virtio_device *vdev, unsigned int offset, + const void *buf, unsigned len) +{ + struct kvm_device_desc *desc = to_kvmdev(vdev)->desc; + + BUG_ON(offset + len > desc->config_len); + memcpy(kvm_vq_configspace(desc) + offset, buf, len); +} + +/* + * The operations to get and set the status word just access + * the status field of the device descriptor. set_status will also + * make a hypercall to the host, to tell about status changes + */ +static u8 kvm_get_status(struct virtio_device *vdev) +{ + return to_kvmdev(vdev)->desc->status; +} + +static void kvm_set_status(struct virtio_device *vdev, u8 status) +{ + BUG_ON(!status); + to_kvmdev(vdev)->desc->status = status; + kvm_hypercall1(KVM_S390_VIRTIO_SET_STATUS, + (unsigned long) to_kvmdev(vdev)->desc); +} + +/* + * To reset the device, we use the KVM_VIRTIO_RESET hypercall, using the + * descriptor address. The Host will zero the status and all the + * features. + */ +static void kvm_reset(struct virtio_device *vdev) +{ + kvm_hypercall1(KVM_S390_VIRTIO_RESET, + (unsigned long) to_kvmdev(vdev)->desc); +} + +/* + * When the virtio_ring code wants to notify the Host, it calls us here and we + * make a hypercall. We hand the address of the virtqueue so the Host + * knows which virtqueue we're talking about. + */ +static bool kvm_notify(struct virtqueue *vq) +{ + long rc; + struct kvm_vqconfig *config = vq->priv; + + rc = kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address); + if (rc < 0) + return false; + return true; +} + +/* + * This routine finds the first virtqueue described in the configuration of + * this device and sets it up. + */ +static struct virtqueue *kvm_find_vq(struct virtio_device *vdev, + unsigned index, + void (*callback)(struct virtqueue *vq), + const char *name) +{ + struct kvm_device *kdev = to_kvmdev(vdev); + struct kvm_vqconfig *config; + struct virtqueue *vq; + int err; + + if (index >= kdev->desc->num_vq) + return ERR_PTR(-ENOENT); + + if (!name) + return NULL; + + config = kvm_vq_config(kdev->desc)+index; + + err = vmem_add_mapping(config->address, + vring_size(config->num, + KVM_S390_VIRTIO_RING_ALIGN)); + if (err) + goto out; + + vq = vring_new_virtqueue(index, config->num, KVM_S390_VIRTIO_RING_ALIGN, + vdev, true, (void *) config->address, + kvm_notify, callback, name); + if (!vq) { + err = -ENOMEM; + goto unmap; + } + + /* + * register a callback token + * The host will sent this via the external interrupt parameter + */ + config->token = (u64) vq; + + vq->priv = config; + return vq; +unmap: + vmem_remove_mapping(config->address, + vring_size(config->num, + KVM_S390_VIRTIO_RING_ALIGN)); +out: + return ERR_PTR(err); +} + +static void kvm_del_vq(struct virtqueue *vq) +{ + struct kvm_vqconfig *config = vq->priv; + + vring_del_virtqueue(vq); + vmem_remove_mapping(config->address, + vring_size(config->num, + KVM_S390_VIRTIO_RING_ALIGN)); +} + +static void kvm_del_vqs(struct virtio_device *vdev) +{ + struct virtqueue *vq, *n; + + list_for_each_entry_safe(vq, n, &vdev->vqs, list) + kvm_del_vq(vq); +} + +static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], + vq_callback_t *callbacks[], + const char *names[]) +{ + struct kvm_device *kdev = to_kvmdev(vdev); + int i; + + /* We must have this many virtqueues. */ + if (nvqs > kdev->desc->num_vq) + return -ENOENT; + + for (i = 0; i < nvqs; ++i) { + vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i]); + if (IS_ERR(vqs[i])) + goto error; + } + return 0; + +error: + kvm_del_vqs(vdev); + return PTR_ERR(vqs[i]); +} + +static const char *kvm_bus_name(struct virtio_device *vdev) +{ + return ""; +} + +/* + * The config ops structure as defined by virtio config + */ +static const struct virtio_config_ops kvm_vq_configspace_ops = { + .get_features = kvm_get_features, + .finalize_features = kvm_finalize_features, + .get = kvm_get, + .set = kvm_set, + .get_status = kvm_get_status, + .set_status = kvm_set_status, + .reset = kvm_reset, + .find_vqs = kvm_find_vqs, + .del_vqs = kvm_del_vqs, + .bus_name = kvm_bus_name, +}; + +/* + * The root device for the kvm virtio devices. + * This makes them appear as /sys/devices/kvm_s390/0,1,2 not /sys/devices/0,1,2. + */ +static struct device *kvm_root; + +/* + * adds a new device and register it with virtio + * appropriate drivers are loaded by the device model + */ +static void add_kvm_device(struct kvm_device_desc *d, unsigned int offset) +{ + struct kvm_device *kdev; + + kdev = kzalloc(sizeof(*kdev), GFP_KERNEL); + if (!kdev) { + printk(KERN_EMERG "Cannot allocate kvm dev %u type %u\n", + offset, d->type); + return; + } + + kdev->vdev.dev.parent = kvm_root; + kdev->vdev.id.device = d->type; + kdev->vdev.config = &kvm_vq_configspace_ops; + kdev->desc = d; + + if (register_virtio_device(&kdev->vdev) != 0) { + printk(KERN_ERR "Failed to register kvm device %u type %u\n", + offset, d->type); + kfree(kdev); + } +} + +/* + * scan_devices() simply iterates through the device page. + * The type 0 is reserved to mean "end of devices". + */ +static void scan_devices(void) +{ + unsigned int i; + struct kvm_device_desc *d; + + for (i = 0; i < PAGE_SIZE; i += desc_size(d)) { + d = kvm_devices + i; + + if (d->type == 0) + break; + + add_kvm_device(d, i); + } +} + +/* + * match for a kvm device with a specific desc pointer + */ +static int match_desc(struct device *dev, void *data) +{ + struct virtio_device *vdev = dev_to_virtio(dev); + struct kvm_device *kdev = to_kvmdev(vdev); + + return kdev->desc == data; +} + +/* + * hotplug_device tries to find changes in the device page. + */ +static void hotplug_devices(struct work_struct *dummy) +{ + unsigned int i; + struct kvm_device_desc *d; + struct device *dev; + + for (i = 0; i < PAGE_SIZE; i += desc_size(d)) { + d = kvm_devices + i; + + /* end of list */ + if (d->type == 0) + break; + + /* device already exists */ + dev = device_find_child(kvm_root, d, match_desc); + if (dev) { + /* XXX check for hotplug remove */ + put_device(dev); + continue; + } + + /* new device */ + printk(KERN_INFO "Adding new virtio device %p\n", d); + add_kvm_device(d, i); + } +} + +/* + * we emulate the request_irq behaviour on top of s390 extints + */ +static void kvm_extint_handler(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + struct virtqueue *vq; + u32 param; + + if ((ext_code.subcode & 0xff00) != VIRTIO_SUBCODE_64) + return; + inc_irq_stat(IRQEXT_VRT); + + /* The LSB might be overloaded, we have to mask it */ + vq = (struct virtqueue *)(param64 & ~1UL); + + /* We use ext_params to decide what this interrupt means */ + param = param32 & VIRTIO_PARAM_MASK; + + switch (param) { + case VIRTIO_PARAM_CONFIG_CHANGED: + virtio_config_changed(vq->vdev); + break; + case VIRTIO_PARAM_DEV_ADD: + schedule_work(&hotplug_work); + break; + case VIRTIO_PARAM_VRING_INTERRUPT: + default: + vring_interrupt(0, vq); + break; + } +} + +/* + * For s390-virtio, we expect a page above main storage containing + * the virtio configuration. Try to actually load from this area + * in order to figure out if the host provides this page. + */ +static int __init test_devices_support(unsigned long addr) +{ + int ret = -EIO; + + asm volatile( + "0: lura 0,%1\n" + "1: xgr %0,%0\n" + "2:\n" + EX_TABLE(0b,2b) + EX_TABLE(1b,2b) + : "+d" (ret) + : "a" (addr) + : "0", "cc"); + return ret; +} +/* + * Init function for virtio + * devices are in a single page above top of "normal" + standby mem + */ +static int __init kvm_devices_init(void) +{ + int rc; + unsigned long total_memory_size = sclp_get_rzm() * sclp_get_rnmax(); + + if (!MACHINE_IS_KVM) + return -ENODEV; + + if (test_devices_support(total_memory_size) < 0) + return -ENODEV; + + rc = vmem_add_mapping(total_memory_size, PAGE_SIZE); + if (rc) + return rc; + + kvm_devices = (void *) total_memory_size; + + kvm_root = root_device_register("kvm_s390"); + if (IS_ERR(kvm_root)) { + rc = PTR_ERR(kvm_root); + printk(KERN_ERR "Could not register kvm_s390 root device"); + vmem_remove_mapping(total_memory_size, PAGE_SIZE); + return rc; + } + + INIT_WORK(&hotplug_work, hotplug_devices); + + irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); + register_external_irq(EXT_IRQ_CP_SERVICE, kvm_extint_handler); + + scan_devices(); + return 0; +} + +/* code for early console output with virtio_console */ +static __init int early_put_chars(u32 vtermno, const char *buf, int count) +{ + char scratch[17]; + unsigned int len = count; + + if (len > sizeof(scratch) - 1) + len = sizeof(scratch) - 1; + scratch[len] = '\0'; + memcpy(scratch, buf, len); + kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, __pa(scratch)); + return len; +} + +static int __init s390_virtio_console_init(void) +{ + if (sclp_has_vt220() || sclp_has_linemode()) + return -ENODEV; + return virtio_cons_early_init(early_put_chars); +} +console_initcall(s390_virtio_console_init); + + +/* + * We do this after core stuff, but before the drivers. + */ +postcore_initcall(kvm_devices_init); diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c new file mode 100644 index 0000000..6f1fa17 --- /dev/null +++ b/drivers/s390/virtio/virtio_ccw.c @@ -0,0 +1,1380 @@ +/* + * ccw based virtio transport + * + * Copyright IBM Corp. 2012, 2014 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Cornelia Huck + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * virtio related functions + */ + +struct vq_config_block { + __u16 index; + __u16 num; +} __packed; + +#define VIRTIO_CCW_CONFIG_SIZE 0x100 +/* same as PCI config space size, should be enough for all drivers */ + +struct virtio_ccw_device { + struct virtio_device vdev; + __u8 *status; + __u8 config[VIRTIO_CCW_CONFIG_SIZE]; + struct ccw_device *cdev; + __u32 curr_io; + int err; + unsigned int revision; /* Transport revision */ + wait_queue_head_t wait_q; + spinlock_t lock; + struct list_head virtqueues; + unsigned long indicators; + unsigned long indicators2; + struct vq_config_block *config_block; + bool is_thinint; + bool going_away; + bool device_lost; + void *airq_info; +}; + +struct vq_info_block_legacy { + __u64 queue; + __u32 align; + __u16 index; + __u16 num; +} __packed; + +struct vq_info_block { + __u64 desc; + __u32 res0; + __u16 index; + __u16 num; + __u64 avail; + __u64 used; +} __packed; + +struct virtio_feature_desc { + __u32 features; + __u8 index; +} __packed; + +struct virtio_thinint_area { + unsigned long summary_indicator; + unsigned long indicator; + u64 bit_nr; + u8 isc; +} __packed; + +struct virtio_rev_info { + __u16 revision; + __u16 length; + __u8 data[]; +}; + +/* the highest virtio-ccw revision we support */ +#define VIRTIO_CCW_REV_MAX 1 + +struct virtio_ccw_vq_info { + struct virtqueue *vq; + int num; + void *queue; + union { + struct vq_info_block s; + struct vq_info_block_legacy l; + } *info_block; + int bit_nr; + struct list_head node; + long cookie; +}; + +#define VIRTIO_AIRQ_ISC IO_SCH_ISC /* inherit from subchannel */ + +#define VIRTIO_IV_BITS (L1_CACHE_BYTES * 8) +#define MAX_AIRQ_AREAS 20 + +static int virtio_ccw_use_airq = 1; + +struct airq_info { + rwlock_t lock; + u8 summary_indicator; + struct airq_struct airq; + struct airq_iv *aiv; +}; +static struct airq_info *airq_areas[MAX_AIRQ_AREAS]; + +#define CCW_CMD_SET_VQ 0x13 +#define CCW_CMD_VDEV_RESET 0x33 +#define CCW_CMD_SET_IND 0x43 +#define CCW_CMD_SET_CONF_IND 0x53 +#define CCW_CMD_READ_FEAT 0x12 +#define CCW_CMD_WRITE_FEAT 0x11 +#define CCW_CMD_READ_CONF 0x22 +#define CCW_CMD_WRITE_CONF 0x21 +#define CCW_CMD_WRITE_STATUS 0x31 +#define CCW_CMD_READ_VQ_CONF 0x32 +#define CCW_CMD_SET_IND_ADAPTER 0x73 +#define CCW_CMD_SET_VIRTIO_REV 0x83 + +#define VIRTIO_CCW_DOING_SET_VQ 0x00010000 +#define VIRTIO_CCW_DOING_RESET 0x00040000 +#define VIRTIO_CCW_DOING_READ_FEAT 0x00080000 +#define VIRTIO_CCW_DOING_WRITE_FEAT 0x00100000 +#define VIRTIO_CCW_DOING_READ_CONFIG 0x00200000 +#define VIRTIO_CCW_DOING_WRITE_CONFIG 0x00400000 +#define VIRTIO_CCW_DOING_WRITE_STATUS 0x00800000 +#define VIRTIO_CCW_DOING_SET_IND 0x01000000 +#define VIRTIO_CCW_DOING_READ_VQ_CONF 0x02000000 +#define VIRTIO_CCW_DOING_SET_CONF_IND 0x04000000 +#define VIRTIO_CCW_DOING_SET_IND_ADAPTER 0x08000000 +#define VIRTIO_CCW_DOING_SET_VIRTIO_REV 0x10000000 +#define VIRTIO_CCW_INTPARM_MASK 0xffff0000 + +static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev) +{ + return container_of(vdev, struct virtio_ccw_device, vdev); +} + +static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info) +{ + unsigned long i, flags; + + write_lock_irqsave(&info->lock, flags); + for (i = 0; i < airq_iv_end(info->aiv); i++) { + if (vq == (void *)airq_iv_get_ptr(info->aiv, i)) { + airq_iv_free_bit(info->aiv, i); + airq_iv_set_ptr(info->aiv, i, 0); + break; + } + } + write_unlock_irqrestore(&info->lock, flags); +} + +static void virtio_airq_handler(struct airq_struct *airq) +{ + struct airq_info *info = container_of(airq, struct airq_info, airq); + unsigned long ai; + + inc_irq_stat(IRQIO_VAI); + read_lock(&info->lock); + /* Walk through indicators field, summary indicator active. */ + for (ai = 0;;) { + ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv)); + if (ai == -1UL) + break; + vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai)); + } + info->summary_indicator = 0; + smp_wmb(); + /* Walk through indicators field, summary indicator not active. */ + for (ai = 0;;) { + ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv)); + if (ai == -1UL) + break; + vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai)); + } + read_unlock(&info->lock); +} + +static struct airq_info *new_airq_info(void) +{ + struct airq_info *info; + int rc; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return NULL; + rwlock_init(&info->lock); + info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR); + if (!info->aiv) { + kfree(info); + return NULL; + } + info->airq.handler = virtio_airq_handler; + info->airq.lsi_ptr = &info->summary_indicator; + info->airq.lsi_mask = 0xff; + info->airq.isc = VIRTIO_AIRQ_ISC; + rc = register_adapter_interrupt(&info->airq); + if (rc) { + airq_iv_release(info->aiv); + kfree(info); + return NULL; + } + return info; +} + +static void destroy_airq_info(struct airq_info *info) +{ + if (!info) + return; + + unregister_adapter_interrupt(&info->airq); + airq_iv_release(info->aiv); + kfree(info); +} + +static unsigned long get_airq_indicator(struct virtqueue *vqs[], int nvqs, + u64 *first, void **airq_info) +{ + int i, j; + struct airq_info *info; + unsigned long indicator_addr = 0; + unsigned long bit, flags; + + for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) { + if (!airq_areas[i]) + airq_areas[i] = new_airq_info(); + info = airq_areas[i]; + if (!info) + return 0; + write_lock_irqsave(&info->lock, flags); + bit = airq_iv_alloc(info->aiv, nvqs); + if (bit == -1UL) { + /* Not enough vacancies. */ + write_unlock_irqrestore(&info->lock, flags); + continue; + } + *first = bit; + *airq_info = info; + indicator_addr = (unsigned long)info->aiv->vector; + for (j = 0; j < nvqs; j++) { + airq_iv_set_ptr(info->aiv, bit + j, + (unsigned long)vqs[j]); + } + write_unlock_irqrestore(&info->lock, flags); + } + return indicator_addr; +} + +static void virtio_ccw_drop_indicators(struct virtio_ccw_device *vcdev) +{ + struct virtio_ccw_vq_info *info; + + list_for_each_entry(info, &vcdev->virtqueues, node) + drop_airq_indicator(info->vq, vcdev->airq_info); +} + +static int doing_io(struct virtio_ccw_device *vcdev, __u32 flag) +{ + unsigned long flags; + __u32 ret; + + spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags); + if (vcdev->err) + ret = 0; + else + ret = vcdev->curr_io & flag; + spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags); + return ret; +} + +static int ccw_io_helper(struct virtio_ccw_device *vcdev, + struct ccw1 *ccw, __u32 intparm) +{ + int ret; + unsigned long flags; + int flag = intparm & VIRTIO_CCW_INTPARM_MASK; + + do { + spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags); + ret = ccw_device_start(vcdev->cdev, ccw, intparm, 0, 0); + if (!ret) { + if (!vcdev->curr_io) + vcdev->err = 0; + vcdev->curr_io |= flag; + } + spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags); + cpu_relax(); + } while (ret == -EBUSY); + wait_event(vcdev->wait_q, doing_io(vcdev, flag) == 0); + return ret ? ret : vcdev->err; +} + +static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev, + struct ccw1 *ccw) +{ + int ret; + unsigned long *indicatorp = NULL; + struct virtio_thinint_area *thinint_area = NULL; + struct airq_info *airq_info = vcdev->airq_info; + + if (vcdev->is_thinint) { + thinint_area = kzalloc(sizeof(*thinint_area), + GFP_DMA | GFP_KERNEL); + if (!thinint_area) + return; + thinint_area->summary_indicator = + (unsigned long) &airq_info->summary_indicator; + thinint_area->isc = VIRTIO_AIRQ_ISC; + ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER; + ccw->count = sizeof(*thinint_area); + ccw->cda = (__u32)(unsigned long) thinint_area; + } else { + indicatorp = kmalloc(sizeof(&vcdev->indicators), + GFP_DMA | GFP_KERNEL); + if (!indicatorp) + return; + *indicatorp = 0; + ccw->cmd_code = CCW_CMD_SET_IND; + ccw->count = sizeof(vcdev->indicators); + ccw->cda = (__u32)(unsigned long) indicatorp; + } + /* Deregister indicators from host. */ + vcdev->indicators = 0; + ccw->flags = 0; + ret = ccw_io_helper(vcdev, ccw, + vcdev->is_thinint ? + VIRTIO_CCW_DOING_SET_IND_ADAPTER : + VIRTIO_CCW_DOING_SET_IND); + if (ret && (ret != -ENODEV)) + dev_info(&vcdev->cdev->dev, + "Failed to deregister indicators (%d)\n", ret); + else if (vcdev->is_thinint) + virtio_ccw_drop_indicators(vcdev); + kfree(indicatorp); + kfree(thinint_area); +} + +static inline long do_kvm_notify(struct subchannel_id schid, + unsigned long queue_index, + long cookie) +{ + register unsigned long __nr asm("1") = KVM_S390_VIRTIO_CCW_NOTIFY; + register struct subchannel_id __schid asm("2") = schid; + register unsigned long __index asm("3") = queue_index; + register long __rc asm("2"); + register long __cookie asm("4") = cookie; + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr), "d" (__schid), "d" (__index), + "d"(__cookie) + : "memory", "cc"); + return __rc; +} + +static bool virtio_ccw_kvm_notify(struct virtqueue *vq) +{ + struct virtio_ccw_vq_info *info = vq->priv; + struct virtio_ccw_device *vcdev; + struct subchannel_id schid; + + vcdev = to_vc_device(info->vq->vdev); + ccw_device_get_schid(vcdev->cdev, &schid); + info->cookie = do_kvm_notify(schid, vq->index, info->cookie); + if (info->cookie < 0) + return false; + return true; +} + +static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev, + struct ccw1 *ccw, int index) +{ + vcdev->config_block->index = index; + ccw->cmd_code = CCW_CMD_READ_VQ_CONF; + ccw->flags = 0; + ccw->count = sizeof(struct vq_config_block); + ccw->cda = (__u32)(unsigned long)(vcdev->config_block); + ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF); + return vcdev->config_block->num; +} + +static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vq->vdev); + struct virtio_ccw_vq_info *info = vq->priv; + unsigned long flags; + unsigned long size; + int ret; + unsigned int index = vq->index; + + /* Remove from our list. */ + spin_lock_irqsave(&vcdev->lock, flags); + list_del(&info->node); + spin_unlock_irqrestore(&vcdev->lock, flags); + + /* Release from host. */ + if (vcdev->revision == 0) { + info->info_block->l.queue = 0; + info->info_block->l.align = 0; + info->info_block->l.index = index; + info->info_block->l.num = 0; + ccw->count = sizeof(info->info_block->l); + } else { + info->info_block->s.desc = 0; + info->info_block->s.index = index; + info->info_block->s.num = 0; + info->info_block->s.avail = 0; + info->info_block->s.used = 0; + ccw->count = sizeof(info->info_block->s); + } + ccw->cmd_code = CCW_CMD_SET_VQ; + ccw->flags = 0; + ccw->cda = (__u32)(unsigned long)(info->info_block); + ret = ccw_io_helper(vcdev, ccw, + VIRTIO_CCW_DOING_SET_VQ | index); + /* + * -ENODEV isn't considered an error: The device is gone anyway. + * This may happen on device detach. + */ + if (ret && (ret != -ENODEV)) + dev_warn(&vq->vdev->dev, "Error %d while deleting queue %d", + ret, index); + + vring_del_virtqueue(vq); + size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN)); + free_pages_exact(info->queue, size); + kfree(info->info_block); + kfree(info); +} + +static void virtio_ccw_del_vqs(struct virtio_device *vdev) +{ + struct virtqueue *vq, *n; + struct ccw1 *ccw; + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return; + + virtio_ccw_drop_indicator(vcdev, ccw); + + list_for_each_entry_safe(vq, n, &vdev->vqs, list) + virtio_ccw_del_vq(vq, ccw); + + kfree(ccw); +} + +static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, + int i, vq_callback_t *callback, + const char *name, + struct ccw1 *ccw) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + int err; + struct virtqueue *vq = NULL; + struct virtio_ccw_vq_info *info; + unsigned long size = 0; /* silence the compiler */ + unsigned long flags; + + /* Allocate queue. */ + info = kzalloc(sizeof(struct virtio_ccw_vq_info), GFP_KERNEL); + if (!info) { + dev_warn(&vcdev->cdev->dev, "no info\n"); + err = -ENOMEM; + goto out_err; + } + info->info_block = kzalloc(sizeof(*info->info_block), + GFP_DMA | GFP_KERNEL); + if (!info->info_block) { + dev_warn(&vcdev->cdev->dev, "no info block\n"); + err = -ENOMEM; + goto out_err; + } + info->num = virtio_ccw_read_vq_conf(vcdev, ccw, i); + size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN)); + info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); + if (info->queue == NULL) { + dev_warn(&vcdev->cdev->dev, "no queue\n"); + err = -ENOMEM; + goto out_err; + } + + vq = vring_new_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev, + true, info->queue, virtio_ccw_kvm_notify, + callback, name); + if (!vq) { + /* For now, we fail if we can't get the requested size. */ + dev_warn(&vcdev->cdev->dev, "no vq\n"); + err = -ENOMEM; + goto out_err; + } + + /* Register it with the host. */ + if (vcdev->revision == 0) { + info->info_block->l.queue = (__u64)info->queue; + info->info_block->l.align = KVM_VIRTIO_CCW_RING_ALIGN; + info->info_block->l.index = i; + info->info_block->l.num = info->num; + ccw->count = sizeof(info->info_block->l); + } else { + info->info_block->s.desc = (__u64)info->queue; + info->info_block->s.index = i; + info->info_block->s.num = info->num; + info->info_block->s.avail = (__u64)virtqueue_get_avail(vq); + info->info_block->s.used = (__u64)virtqueue_get_used(vq); + ccw->count = sizeof(info->info_block->s); + } + ccw->cmd_code = CCW_CMD_SET_VQ; + ccw->flags = 0; + ccw->cda = (__u32)(unsigned long)(info->info_block); + err = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_VQ | i); + if (err) { + dev_warn(&vcdev->cdev->dev, "SET_VQ failed\n"); + goto out_err; + } + + info->vq = vq; + vq->priv = info; + + /* Save it to our list. */ + spin_lock_irqsave(&vcdev->lock, flags); + list_add(&info->node, &vcdev->virtqueues); + spin_unlock_irqrestore(&vcdev->lock, flags); + + return vq; + +out_err: + if (vq) + vring_del_virtqueue(vq); + if (info) { + if (info->queue) + free_pages_exact(info->queue, size); + kfree(info->info_block); + } + kfree(info); + return ERR_PTR(err); +} + +static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev, + struct virtqueue *vqs[], int nvqs, + struct ccw1 *ccw) +{ + int ret; + struct virtio_thinint_area *thinint_area = NULL; + struct airq_info *info; + + thinint_area = kzalloc(sizeof(*thinint_area), GFP_DMA | GFP_KERNEL); + if (!thinint_area) { + ret = -ENOMEM; + goto out; + } + /* Try to get an indicator. */ + thinint_area->indicator = get_airq_indicator(vqs, nvqs, + &thinint_area->bit_nr, + &vcdev->airq_info); + if (!thinint_area->indicator) { + ret = -ENOSPC; + goto out; + } + info = vcdev->airq_info; + thinint_area->summary_indicator = + (unsigned long) &info->summary_indicator; + thinint_area->isc = VIRTIO_AIRQ_ISC; + ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER; + ccw->flags = CCW_FLAG_SLI; + ccw->count = sizeof(*thinint_area); + ccw->cda = (__u32)(unsigned long)thinint_area; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND_ADAPTER); + if (ret) { + if (ret == -EOPNOTSUPP) { + /* + * The host does not support adapter interrupts + * for virtio-ccw, stop trying. + */ + virtio_ccw_use_airq = 0; + pr_info("Adapter interrupts unsupported on host\n"); + } else + dev_warn(&vcdev->cdev->dev, + "enabling adapter interrupts = %d\n", ret); + virtio_ccw_drop_indicators(vcdev); + } +out: + kfree(thinint_area); + return ret; +} + +static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], + vq_callback_t *callbacks[], + const char *names[]) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + unsigned long *indicatorp = NULL; + int ret, i; + struct ccw1 *ccw; + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return -ENOMEM; + + for (i = 0; i < nvqs; ++i) { + vqs[i] = virtio_ccw_setup_vq(vdev, i, callbacks[i], names[i], + ccw); + if (IS_ERR(vqs[i])) { + ret = PTR_ERR(vqs[i]); + vqs[i] = NULL; + goto out; + } + } + ret = -ENOMEM; + /* We need a data area under 2G to communicate. */ + indicatorp = kmalloc(sizeof(&vcdev->indicators), GFP_DMA | GFP_KERNEL); + if (!indicatorp) + goto out; + *indicatorp = (unsigned long) &vcdev->indicators; + if (vcdev->is_thinint) { + ret = virtio_ccw_register_adapter_ind(vcdev, vqs, nvqs, ccw); + if (ret) + /* no error, just fall back to legacy interrupts */ + vcdev->is_thinint = 0; + } + if (!vcdev->is_thinint) { + /* Register queue indicators with host. */ + vcdev->indicators = 0; + ccw->cmd_code = CCW_CMD_SET_IND; + ccw->flags = 0; + ccw->count = sizeof(vcdev->indicators); + ccw->cda = (__u32)(unsigned long) indicatorp; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND); + if (ret) + goto out; + } + /* Register indicators2 with host for config changes */ + *indicatorp = (unsigned long) &vcdev->indicators2; + vcdev->indicators2 = 0; + ccw->cmd_code = CCW_CMD_SET_CONF_IND; + ccw->flags = 0; + ccw->count = sizeof(vcdev->indicators2); + ccw->cda = (__u32)(unsigned long) indicatorp; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_CONF_IND); + if (ret) + goto out; + + kfree(indicatorp); + kfree(ccw); + return 0; +out: + kfree(indicatorp); + kfree(ccw); + virtio_ccw_del_vqs(vdev); + return ret; +} + +static void virtio_ccw_reset(struct virtio_device *vdev) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + struct ccw1 *ccw; + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return; + + /* Zero status bits. */ + *vcdev->status = 0; + + /* Send a reset ccw on device. */ + ccw->cmd_code = CCW_CMD_VDEV_RESET; + ccw->flags = 0; + ccw->count = 0; + ccw->cda = 0; + ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_RESET); + kfree(ccw); +} + +static u64 virtio_ccw_get_features(struct virtio_device *vdev) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + struct virtio_feature_desc *features; + int ret; + u64 rc; + struct ccw1 *ccw; + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return 0; + + features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL); + if (!features) { + rc = 0; + goto out_free; + } + /* Read the feature bits from the host. */ + features->index = 0; + ccw->cmd_code = CCW_CMD_READ_FEAT; + ccw->flags = 0; + ccw->count = sizeof(*features); + ccw->cda = (__u32)(unsigned long)features; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_FEAT); + if (ret) { + rc = 0; + goto out_free; + } + + rc = le32_to_cpu(features->features); + + if (vcdev->revision == 0) + goto out_free; + + /* Read second half of the feature bits from the host. */ + features->index = 1; + ccw->cmd_code = CCW_CMD_READ_FEAT; + ccw->flags = 0; + ccw->count = sizeof(*features); + ccw->cda = (__u32)(unsigned long)features; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_FEAT); + if (ret == 0) + rc |= (u64)le32_to_cpu(features->features) << 32; + +out_free: + kfree(features); + kfree(ccw); + return rc; +} + +static int virtio_ccw_finalize_features(struct virtio_device *vdev) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + struct virtio_feature_desc *features; + struct ccw1 *ccw; + int ret; + + if (vcdev->revision >= 1 && + !__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) { + dev_err(&vdev->dev, "virtio: device uses revision 1 " + "but does not have VIRTIO_F_VERSION_1\n"); + return -EINVAL; + } + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return -ENOMEM; + + features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL); + if (!features) { + ret = -ENOMEM; + goto out_free; + } + /* Give virtio_ring a chance to accept features. */ + vring_transport_features(vdev); + + features->index = 0; + features->features = cpu_to_le32((u32)vdev->features); + /* Write the first half of the feature bits to the host. */ + ccw->cmd_code = CCW_CMD_WRITE_FEAT; + ccw->flags = 0; + ccw->count = sizeof(*features); + ccw->cda = (__u32)(unsigned long)features; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT); + if (ret) + goto out_free; + + if (vcdev->revision == 0) + goto out_free; + + features->index = 1; + features->features = cpu_to_le32(vdev->features >> 32); + /* Write the second half of the feature bits to the host. */ + ccw->cmd_code = CCW_CMD_WRITE_FEAT; + ccw->flags = 0; + ccw->count = sizeof(*features); + ccw->cda = (__u32)(unsigned long)features; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT); + +out_free: + kfree(features); + kfree(ccw); + + return ret; +} + +static void virtio_ccw_get_config(struct virtio_device *vdev, + unsigned int offset, void *buf, unsigned len) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + int ret; + struct ccw1 *ccw; + void *config_area; + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return; + + config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL); + if (!config_area) + goto out_free; + + /* Read the config area from the host. */ + ccw->cmd_code = CCW_CMD_READ_CONF; + ccw->flags = 0; + ccw->count = offset + len; + ccw->cda = (__u32)(unsigned long)config_area; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_CONFIG); + if (ret) + goto out_free; + + memcpy(vcdev->config, config_area, sizeof(vcdev->config)); + memcpy(buf, &vcdev->config[offset], len); + +out_free: + kfree(config_area); + kfree(ccw); +} + +static void virtio_ccw_set_config(struct virtio_device *vdev, + unsigned int offset, const void *buf, + unsigned len) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + struct ccw1 *ccw; + void *config_area; + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return; + + config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL); + if (!config_area) + goto out_free; + + memcpy(&vcdev->config[offset], buf, len); + /* Write the config area to the host. */ + memcpy(config_area, vcdev->config, sizeof(vcdev->config)); + ccw->cmd_code = CCW_CMD_WRITE_CONF; + ccw->flags = 0; + ccw->count = offset + len; + ccw->cda = (__u32)(unsigned long)config_area; + ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_CONFIG); + +out_free: + kfree(config_area); + kfree(ccw); +} + +static u8 virtio_ccw_get_status(struct virtio_device *vdev) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + + return *vcdev->status; +} + +static void virtio_ccw_set_status(struct virtio_device *vdev, u8 status) +{ + struct virtio_ccw_device *vcdev = to_vc_device(vdev); + u8 old_status = *vcdev->status; + struct ccw1 *ccw; + int ret; + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return; + + /* Write the status to the host. */ + *vcdev->status = status; + ccw->cmd_code = CCW_CMD_WRITE_STATUS; + ccw->flags = 0; + ccw->count = sizeof(status); + ccw->cda = (__u32)(unsigned long)vcdev->status; + ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_STATUS); + /* Write failed? We assume status is unchanged. */ + if (ret) + *vcdev->status = old_status; + kfree(ccw); +} + +static struct virtio_config_ops virtio_ccw_config_ops = { + .get_features = virtio_ccw_get_features, + .finalize_features = virtio_ccw_finalize_features, + .get = virtio_ccw_get_config, + .set = virtio_ccw_set_config, + .get_status = virtio_ccw_get_status, + .set_status = virtio_ccw_set_status, + .reset = virtio_ccw_reset, + .find_vqs = virtio_ccw_find_vqs, + .del_vqs = virtio_ccw_del_vqs, +}; + + +/* + * ccw bus driver related functions + */ + +static void virtio_ccw_release_dev(struct device *_d) +{ + struct virtio_device *dev = container_of(_d, struct virtio_device, + dev); + struct virtio_ccw_device *vcdev = to_vc_device(dev); + + kfree(vcdev->status); + kfree(vcdev->config_block); + kfree(vcdev); +} + +static int irb_is_error(struct irb *irb) +{ + if (scsw_cstat(&irb->scsw) != 0) + return 1; + if (scsw_dstat(&irb->scsw) & ~(DEV_STAT_CHN_END | DEV_STAT_DEV_END)) + return 1; + if (scsw_cc(&irb->scsw) != 0) + return 1; + return 0; +} + +static struct virtqueue *virtio_ccw_vq_by_ind(struct virtio_ccw_device *vcdev, + int index) +{ + struct virtio_ccw_vq_info *info; + unsigned long flags; + struct virtqueue *vq; + + vq = NULL; + spin_lock_irqsave(&vcdev->lock, flags); + list_for_each_entry(info, &vcdev->virtqueues, node) { + if (info->vq->index == index) { + vq = info->vq; + break; + } + } + spin_unlock_irqrestore(&vcdev->lock, flags); + return vq; +} + +static void virtio_ccw_int_handler(struct ccw_device *cdev, + unsigned long intparm, + struct irb *irb) +{ + __u32 activity = intparm & VIRTIO_CCW_INTPARM_MASK; + struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); + int i; + struct virtqueue *vq; + + if (!vcdev) + return; + /* Check if it's a notification from the host. */ + if ((intparm == 0) && + (scsw_stctl(&irb->scsw) == + (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND))) { + /* OK */ + } + if (irb_is_error(irb)) { + /* Command reject? */ + if ((scsw_dstat(&irb->scsw) & DEV_STAT_UNIT_CHECK) && + (irb->ecw[0] & SNS0_CMD_REJECT)) + vcdev->err = -EOPNOTSUPP; + else + /* Map everything else to -EIO. */ + vcdev->err = -EIO; + } + if (vcdev->curr_io & activity) { + switch (activity) { + case VIRTIO_CCW_DOING_READ_FEAT: + case VIRTIO_CCW_DOING_WRITE_FEAT: + case VIRTIO_CCW_DOING_READ_CONFIG: + case VIRTIO_CCW_DOING_WRITE_CONFIG: + case VIRTIO_CCW_DOING_WRITE_STATUS: + case VIRTIO_CCW_DOING_SET_VQ: + case VIRTIO_CCW_DOING_SET_IND: + case VIRTIO_CCW_DOING_SET_CONF_IND: + case VIRTIO_CCW_DOING_RESET: + case VIRTIO_CCW_DOING_READ_VQ_CONF: + case VIRTIO_CCW_DOING_SET_IND_ADAPTER: + case VIRTIO_CCW_DOING_SET_VIRTIO_REV: + vcdev->curr_io &= ~activity; + wake_up(&vcdev->wait_q); + break; + default: + /* don't know what to do... */ + dev_warn(&cdev->dev, "Suspicious activity '%08x'\n", + activity); + WARN_ON(1); + break; + } + } + for_each_set_bit(i, &vcdev->indicators, + sizeof(vcdev->indicators) * BITS_PER_BYTE) { + /* The bit clear must happen before the vring kick. */ + clear_bit(i, &vcdev->indicators); + barrier(); + vq = virtio_ccw_vq_by_ind(vcdev, i); + vring_interrupt(0, vq); + } + if (test_bit(0, &vcdev->indicators2)) { + virtio_config_changed(&vcdev->vdev); + clear_bit(0, &vcdev->indicators2); + } +} + +/* + * We usually want to autoonline all devices, but give the admin + * a way to exempt devices from this. + */ +#define __DEV_WORDS ((__MAX_SUBCHANNEL + (8*sizeof(long) - 1)) / \ + (8*sizeof(long))) +static unsigned long devs_no_auto[__MAX_SSID + 1][__DEV_WORDS]; + +static char *no_auto = ""; + +module_param(no_auto, charp, 0444); +MODULE_PARM_DESC(no_auto, "list of ccw bus id ranges not to be auto-onlined"); + +static int virtio_ccw_check_autoonline(struct ccw_device *cdev) +{ + struct ccw_dev_id id; + + ccw_device_get_id(cdev, &id); + if (test_bit(id.devno, devs_no_auto[id.ssid])) + return 0; + return 1; +} + +static void virtio_ccw_auto_online(void *data, async_cookie_t cookie) +{ + struct ccw_device *cdev = data; + int ret; + + ret = ccw_device_set_online(cdev); + if (ret) + dev_warn(&cdev->dev, "Failed to set online: %d\n", ret); +} + +static int virtio_ccw_probe(struct ccw_device *cdev) +{ + cdev->handler = virtio_ccw_int_handler; + + if (virtio_ccw_check_autoonline(cdev)) + async_schedule(virtio_ccw_auto_online, cdev); + return 0; +} + +static struct virtio_ccw_device *virtio_grab_drvdata(struct ccw_device *cdev) +{ + unsigned long flags; + struct virtio_ccw_device *vcdev; + + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + vcdev = dev_get_drvdata(&cdev->dev); + if (!vcdev || vcdev->going_away) { + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + return NULL; + } + vcdev->going_away = true; + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + return vcdev; +} + +static void virtio_ccw_remove(struct ccw_device *cdev) +{ + unsigned long flags; + struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev); + + if (vcdev && cdev->online) { + if (vcdev->device_lost) + virtio_break_device(&vcdev->vdev); + unregister_virtio_device(&vcdev->vdev); + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + dev_set_drvdata(&cdev->dev, NULL); + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + } + cdev->handler = NULL; +} + +static int virtio_ccw_offline(struct ccw_device *cdev) +{ + unsigned long flags; + struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev); + + if (!vcdev) + return 0; + if (vcdev->device_lost) + virtio_break_device(&vcdev->vdev); + unregister_virtio_device(&vcdev->vdev); + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + dev_set_drvdata(&cdev->dev, NULL); + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + return 0; +} + +static int virtio_ccw_set_transport_rev(struct virtio_ccw_device *vcdev) +{ + struct virtio_rev_info *rev; + struct ccw1 *ccw; + int ret; + + ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + if (!ccw) + return -ENOMEM; + rev = kzalloc(sizeof(*rev), GFP_DMA | GFP_KERNEL); + if (!rev) { + kfree(ccw); + return -ENOMEM; + } + + /* Set transport revision */ + ccw->cmd_code = CCW_CMD_SET_VIRTIO_REV; + ccw->flags = 0; + ccw->count = sizeof(*rev); + ccw->cda = (__u32)(unsigned long)rev; + + vcdev->revision = VIRTIO_CCW_REV_MAX; + do { + rev->revision = vcdev->revision; + /* none of our supported revisions carry payload */ + rev->length = 0; + ret = ccw_io_helper(vcdev, ccw, + VIRTIO_CCW_DOING_SET_VIRTIO_REV); + if (ret == -EOPNOTSUPP) { + if (vcdev->revision == 0) + /* + * The host device does not support setting + * the revision: let's operate it in legacy + * mode. + */ + ret = 0; + else + vcdev->revision--; + } + } while (ret == -EOPNOTSUPP); + + kfree(ccw); + kfree(rev); + return ret; +} + +static int virtio_ccw_online(struct ccw_device *cdev) +{ + int ret; + struct virtio_ccw_device *vcdev; + unsigned long flags; + + vcdev = kzalloc(sizeof(*vcdev), GFP_KERNEL); + if (!vcdev) { + dev_warn(&cdev->dev, "Could not get memory for virtio\n"); + ret = -ENOMEM; + goto out_free; + } + vcdev->config_block = kzalloc(sizeof(*vcdev->config_block), + GFP_DMA | GFP_KERNEL); + if (!vcdev->config_block) { + ret = -ENOMEM; + goto out_free; + } + vcdev->status = kzalloc(sizeof(*vcdev->status), GFP_DMA | GFP_KERNEL); + if (!vcdev->status) { + ret = -ENOMEM; + goto out_free; + } + + vcdev->is_thinint = virtio_ccw_use_airq; /* at least try */ + + vcdev->vdev.dev.parent = &cdev->dev; + vcdev->vdev.dev.release = virtio_ccw_release_dev; + vcdev->vdev.config = &virtio_ccw_config_ops; + vcdev->cdev = cdev; + init_waitqueue_head(&vcdev->wait_q); + INIT_LIST_HEAD(&vcdev->virtqueues); + spin_lock_init(&vcdev->lock); + + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + dev_set_drvdata(&cdev->dev, vcdev); + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + vcdev->vdev.id.vendor = cdev->id.cu_type; + vcdev->vdev.id.device = cdev->id.cu_model; + + ret = virtio_ccw_set_transport_rev(vcdev); + if (ret) + goto out_free; + + ret = register_virtio_device(&vcdev->vdev); + if (ret) { + dev_warn(&cdev->dev, "Failed to register virtio device: %d\n", + ret); + goto out_put; + } + return 0; +out_put: + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + dev_set_drvdata(&cdev->dev, NULL); + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + put_device(&vcdev->vdev.dev); + return ret; +out_free: + if (vcdev) { + kfree(vcdev->status); + kfree(vcdev->config_block); + } + kfree(vcdev); + return ret; +} + +static int virtio_ccw_cio_notify(struct ccw_device *cdev, int event) +{ + int rc; + struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); + + /* + * Make sure vcdev is set + * i.e. set_offline/remove callback not already running + */ + if (!vcdev) + return NOTIFY_DONE; + + switch (event) { + case CIO_GONE: + vcdev->device_lost = true; + rc = NOTIFY_DONE; + break; + default: + rc = NOTIFY_DONE; + break; + } + return rc; +} + +static struct ccw_device_id virtio_ids[] = { + { CCW_DEVICE(0x3832, 0) }, + {}, +}; +MODULE_DEVICE_TABLE(ccw, virtio_ids); + +static struct ccw_driver virtio_ccw_driver = { + .driver = { + .owner = THIS_MODULE, + .name = "virtio_ccw", + }, + .ids = virtio_ids, + .probe = virtio_ccw_probe, + .remove = virtio_ccw_remove, + .set_offline = virtio_ccw_offline, + .set_online = virtio_ccw_online, + .notify = virtio_ccw_cio_notify, + .int_class = IRQIO_VIR, +}; + +static int __init pure_hex(char **cp, unsigned int *val, int min_digit, + int max_digit, int max_val) +{ + int diff; + + diff = 0; + *val = 0; + + while (diff <= max_digit) { + int value = hex_to_bin(**cp); + + if (value < 0) + break; + *val = *val * 16 + value; + (*cp)++; + diff++; + } + + if ((diff < min_digit) || (diff > max_digit) || (*val > max_val)) + return 1; + + return 0; +} + +static int __init parse_busid(char *str, unsigned int *cssid, + unsigned int *ssid, unsigned int *devno) +{ + char *str_work; + int rc, ret; + + rc = 1; + + if (*str == '\0') + goto out; + + str_work = str; + ret = pure_hex(&str_work, cssid, 1, 2, __MAX_CSSID); + if (ret || (str_work[0] != '.')) + goto out; + str_work++; + ret = pure_hex(&str_work, ssid, 1, 1, __MAX_SSID); + if (ret || (str_work[0] != '.')) + goto out; + str_work++; + ret = pure_hex(&str_work, devno, 4, 4, __MAX_SUBCHANNEL); + if (ret || (str_work[0] != '\0')) + goto out; + + rc = 0; +out: + return rc; +} + +static void __init no_auto_parse(void) +{ + unsigned int from_cssid, to_cssid, from_ssid, to_ssid, from, to; + char *parm, *str; + int rc; + + str = no_auto; + while ((parm = strsep(&str, ","))) { + rc = parse_busid(strsep(&parm, "-"), &from_cssid, + &from_ssid, &from); + if (rc) + continue; + if (parm != NULL) { + rc = parse_busid(parm, &to_cssid, + &to_ssid, &to); + if ((from_ssid > to_ssid) || + ((from_ssid == to_ssid) && (from > to))) + rc = -EINVAL; + } else { + to_cssid = from_cssid; + to_ssid = from_ssid; + to = from; + } + if (rc) + continue; + while ((from_ssid < to_ssid) || + ((from_ssid == to_ssid) && (from <= to))) { + set_bit(from, devs_no_auto[from_ssid]); + from++; + if (from > __MAX_SUBCHANNEL) { + from_ssid++; + from = 0; + } + } + } +} + +static int __init virtio_ccw_init(void) +{ + /* parse no_auto string before we do anything further */ + no_auto_parse(); + return ccw_driver_register(&virtio_ccw_driver); +} +module_init(virtio_ccw_init); + +static void __exit virtio_ccw_exit(void) +{ + int i; + + ccw_driver_unregister(&virtio_ccw_driver); + for (i = 0; i < MAX_AIRQ_AREAS; i++) + destroy_airq_info(airq_areas[i]); +} +module_exit(virtio_ccw_exit); -- cgit v0.10.2 From ea52bf8eda9832ad30e9f059c5ead8d44f882a53 Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Thu, 9 Jul 2015 14:58:26 +0200 Subject: 9p/trans_virtio: reset virtio device on remove On device shutdown/removal, virtio drivers need to trigger a reset on the device; if this is neglected, the virtio core will complain about non-zero device status. This patch resets the status when the 9p virtio driver is removed from the system by calling vdev->config->reset on the virtio_device to send a reset to the host virtio device. Signed-off-by: Pierre Morel Reviewed-by: Cornelia Huck Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 9dd49ca..6e70ddb 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -704,6 +704,7 @@ static void p9_virtio_remove(struct virtio_device *vdev) mutex_unlock(&virtio_9p_lock); + vdev->config->reset(vdev); vdev->config->del_vqs(vdev); sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); -- cgit v0.10.2 From 4de7255f7d2be5e51664c6ac6011ffd6e5463571 Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Wed, 1 Jul 2015 11:07:09 +0200 Subject: vhost: extend memory regions allocation to vmalloc with large number of memory regions we could end up with high order allocations and kmalloc could fail if host is under memory pressure. Considering that memory regions array is used on hot path try harder to allocate using kmalloc and if it fails resort to vmalloc. It's still better than just failing vhost_set_memory() and causing guest crash due to it when a new memory hotplugged to guest. I'll still look at QEMU side solution to reduce amount of memory regions it feeds to vhost to make things even better, but it doesn't hurt for kernel to behave smarter and don't crash older QEMU's which could use large amount of memory regions. Signed-off-by: Igor Mammedov Signed-off-by: Michael S. Tsirkin diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 71bb468..a4ac369 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -544,7 +545,7 @@ void vhost_dev_cleanup(struct vhost_dev *dev, bool locked) fput(dev->log_file); dev->log_file = NULL; /* No one will access memory at this point */ - kfree(dev->memory); + kvfree(dev->memory); dev->memory = NULL; WARN_ON(!list_empty(&dev->work_list)); if (dev->worker) { @@ -674,6 +675,18 @@ static int vhost_memory_reg_sort_cmp(const void *p1, const void *p2) return 0; } +static void *vhost_kvzalloc(unsigned long size) +{ + void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + + if (!n) { + n = vzalloc(size); + if (!n) + return ERR_PTR(-ENOMEM); + } + return n; +} + static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) { struct vhost_memory mem, *newmem, *oldmem; @@ -686,7 +699,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) return -EOPNOTSUPP; if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS) return -E2BIG; - newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL); + newmem = vhost_kvzalloc(size + mem.nregions * sizeof(*m->regions)); if (!newmem) return -ENOMEM; @@ -700,7 +713,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) vhost_memory_reg_sort_cmp, NULL); if (!memory_access_ok(d, newmem, 0)) { - kfree(newmem); + kvfree(newmem); return -EFAULT; } oldmem = d->memory; @@ -712,7 +725,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) d->vqs[i]->memory = newmem; mutex_unlock(&d->vqs[i]->mutex); } - kfree(oldmem); + kvfree(oldmem); return 0; } -- cgit v0.10.2 From c9ce42f72fd0ba180fd35539829e4139dca31494 Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Thu, 2 Jul 2015 15:08:11 +0200 Subject: vhost: add max_mem_regions module parameter it became possible to use a bigger amount of memory slots, which is used by memory hotplug for registering hotplugged memory. However QEMU crashes if it's used with more than ~60 pc-dimm devices and vhost-net enabled since host kernel in module vhost-net refuses to accept more than 64 memory regions. Allow to tweak limit via max_mem_regions module paramemter with default value set to 64 slots. Signed-off-by: Igor Mammedov Signed-off-by: Michael S. Tsirkin diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a4ac369..a9fe859 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -30,8 +30,12 @@ #include "vhost.h" +static ushort max_mem_regions = 64; +module_param(max_mem_regions, ushort, 0444); +MODULE_PARM_DESC(max_mem_regions, + "Maximum number of memory regions in memory map. (default: 64)"); + enum { - VHOST_MEMORY_MAX_NREGIONS = 64, VHOST_MEMORY_F_LOG = 0x1, }; @@ -697,7 +701,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) return -EFAULT; if (mem.padding) return -EOPNOTSUPP; - if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS) + if (mem.nregions > max_mem_regions) return -E2BIG; newmem = vhost_kvzalloc(size + mem.nregions * sizeof(*m->regions)); if (!newmem) -- cgit v0.10.2