diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-07 10:24:21 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-07 10:24:21 -0700 |
commit | 3ee31b89d9b12c01aa03dda7a923ef07a800eedd (patch) | |
tree | 3eff45b4147cb74a72c382414a15c5f91e2ec228 | |
parent | bac65d9d87b383471d8d29128319508d71b74180 (diff) | |
parent | d785d9ec7894d0e92f0d0eecc8add9c84131daa4 (diff) |
Merge tag 'for-linus-4.14b-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
Pull xen updates from Juergen Gross:
- the new pvcalls backend for routing socket calls from a guest to dom0
- some cleanups of Xen code
- a fix for wrong usage of {get,put}_cpu()
* tag 'for-linus-4.14b-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (27 commits)
xen/mmu: set MMU_NORMAL_PT_UPDATE in remap_area_mfn_pte_fn
xen: Don't try to call xen_alloc_p2m_entry() on autotranslating guests
xen/events: events_fifo: Don't use {get,put}_cpu() in xen_evtchn_fifo_init()
xen/pvcalls: use WARN_ON(1) instead of __WARN()
xen: remove not used trace functions
xen: remove unused function xen_set_domain_pte()
xen: remove tests for pvh mode in pure pv paths
xen-platform: constify pci_device_id.
xen: cleanup xen.h
xen: introduce a Kconfig option to enable the pvcalls backend
xen/pvcalls: implement write
xen/pvcalls: implement read
xen/pvcalls: implement the ioworker functions
xen/pvcalls: disconnect and module_exit
xen/pvcalls: implement release command
xen/pvcalls: implement poll command
xen/pvcalls: implement accept command
xen/pvcalls: implement listen command
xen/pvcalls: implement bind command
xen/pvcalls: implement connect command
...
-rw-r--r-- | arch/x86/include/asm/xen/page.h | 5 | ||||
-rw-r--r-- | arch/x86/xen/mmu.c | 2 | ||||
-rw-r--r-- | arch/x86/xen/mmu_pv.c | 20 | ||||
-rw-r--r-- | arch/x86/xen/p2m.c | 25 | ||||
-rw-r--r-- | arch/x86/xen/setup.c | 5 | ||||
-rw-r--r-- | drivers/xen/Kconfig | 12 | ||||
-rw-r--r-- | drivers/xen/Makefile | 1 | ||||
-rw-r--r-- | drivers/xen/balloon.c | 8 | ||||
-rw-r--r-- | drivers/xen/events/events_fifo.c | 7 | ||||
-rw-r--r-- | drivers/xen/platform-pci.c | 2 | ||||
-rw-r--r-- | drivers/xen/pvcalls-back.c | 1240 | ||||
-rw-r--r-- | include/trace/events/xen.h | 38 | ||||
-rw-r--r-- | include/xen/interface/io/pvcalls.h | 121 | ||||
-rw-r--r-- | include/xen/interface/io/ring.h | 2 | ||||
-rw-r--r-- | include/xen/xen.h | 20 |
15 files changed, 1397 insertions, 111 deletions
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 8417ef7c3885..07b6531813c4 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -158,9 +158,6 @@ static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn) unsigned long pfn; int ret; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return mfn; - if (unlikely(mfn >= machine_to_phys_nr)) return ~0; @@ -317,8 +314,6 @@ static inline pte_t __pte_ma(pteval_t x) #define p4d_val_ma(x) ((x).p4d) #endif -void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid); - xmaddr_t arbitrary_virt_to_machine(void *address); unsigned long arbitrary_virt_to_mfn(void *vaddr); void make_lowmem_page_readonly(void *vaddr); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3be06f3caf3c..3e15345abfe7 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -84,7 +84,7 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, else rmd->mfn++; - rmd->mmu_update->ptr = virt_to_machine(ptep).maddr; + rmd->mmu_update->ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE; rmd->mmu_update->val = pte_val_ma(pte); rmd->mmu_update++; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index e437714750f8..6b983b300666 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -162,26 +162,6 @@ static bool xen_page_pinned(void *ptr) return PagePinned(page); } -void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid) -{ - struct multicall_space mcs; - struct mmu_update *u; - - trace_xen_mmu_set_domain_pte(ptep, pteval, domid); - - mcs = xen_mc_entry(sizeof(*u)); - u = mcs.args; - - /* ptep might be kmapped when using 32-bit HIGHPTE */ - u->ptr = virt_to_machine(ptep).maddr; - u->val = pte_val_ma(pteval); - - MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, domid); - - xen_mc_issue(PARAVIRT_LAZY_MMU); -} -EXPORT_SYMBOL_GPL(xen_set_domain_pte); - static void xen_extend_mmu_update(const struct mmu_update *update) { struct multicall_space mcs; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 276da636dd39..6083ba462f35 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -212,8 +212,7 @@ void __ref xen_build_mfn_list_list(void) unsigned int level, topidx, mididx; unsigned long *mid_mfn_p; - if (xen_feature(XENFEAT_auto_translated_physmap) || - xen_start_info->flags & SIF_VIRT_P2M_4TOOLS) + if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS) return; /* Pre-initialize p2m_top_mfn to be completely missing */ @@ -269,9 +268,6 @@ void __ref xen_build_mfn_list_list(void) void xen_setup_mfn_list_list(void) { - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS) @@ -291,9 +287,6 @@ void __init xen_build_dynamic_phys_to_machine(void) { unsigned long pfn; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - xen_p2m_addr = (unsigned long *)xen_start_info->mfn_list; xen_p2m_size = ALIGN(xen_start_info->nr_pages, P2M_PER_PAGE); @@ -540,9 +533,6 @@ int xen_alloc_p2m_entry(unsigned long pfn) unsigned long addr = (unsigned long)(xen_p2m_addr + pfn); unsigned long p2m_pfn; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return 0; - ptep = lookup_address(addr, &level); BUG_ON(!ptep || level != PG_LEVEL_4K); pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1)); @@ -640,9 +630,6 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s, if (unlikely(pfn_s >= xen_p2m_size)) return 0; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) - return pfn_e - pfn_s; - if (pfn_s > pfn_e) return 0; @@ -660,10 +647,6 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) pte_t *ptep; unsigned int level; - /* don't track P2M changes in autotranslate guests */ - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) - return true; - if (unlikely(pfn >= xen_p2m_size)) { BUG_ON(mfn != INVALID_P2M_ENTRY); return true; @@ -711,9 +694,6 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, int i, ret = 0; pte_t *pte; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return 0; - if (kmap_ops) { ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, kmap_ops, count); @@ -756,9 +736,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, { int i, ret = 0; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return 0; - for (i = 0; i < count; i++) { unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index c81046323ebc..ac55c02f98e9 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -340,8 +340,6 @@ static void __init xen_do_set_identity_and_remap_chunk( WARN_ON(size == 0); - BUG_ON(xen_feature(XENFEAT_auto_translated_physmap)); - mfn_save = virt_to_mfn(buf); for (ident_pfn_iter = start_pfn, remap_pfn_iter = remap_pfn; @@ -1024,8 +1022,7 @@ void __init xen_pvmmu_arch_setup(void) void __init xen_arch_setup(void) { xen_panic_handler_init(); - if (!xen_feature(XENFEAT_auto_translated_physmap)) - xen_pvmmu_arch_setup(); + xen_pvmmu_arch_setup(); #ifdef CONFIG_ACPI if (!(xen_start_info->flags & SIF_INITDOMAIN)) { diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index f15bb3b789d5..4545561954ee 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -196,6 +196,18 @@ config XEN_PCIDEV_BACKEND If in doubt, say m. +config XEN_PVCALLS_BACKEND + bool "XEN PV Calls backend driver" + depends on INET && XEN && XEN_BACKEND + default n + help + Experimental backend for the Xen PV Calls protocol + (https://xenbits.xen.org/docs/unstable/misc/pvcalls.html). It + allows PV Calls frontends to send POSIX calls to the backend, + which implements them. + + If in doubt, say n. + config XEN_SCSI_BACKEND tristate "XEN SCSI backend driver" depends on XEN && XEN_BACKEND && TARGET_CORE diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 7f188b8d0c67..caaa15dc37bc 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o obj-$(CONFIG_XEN_EFI) += efi.o obj-$(CONFIG_XEN_SCSI_BACKEND) += xen-scsiback.o obj-$(CONFIG_XEN_AUTO_XLATE) += xlate_mmu.o +obj-$(CONFIG_XEN_PVCALLS_BACKEND) += pvcalls-back.o xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o xen-gntalloc-y := gntalloc.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index ab609255a0f3..f77e499afddd 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -664,9 +664,11 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages) */ BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE); - ret = xen_alloc_p2m_entry(page_to_pfn(page)); - if (ret < 0) - goto out_undo; + if (!xen_feature(XENFEAT_auto_translated_physmap)) { + ret = xen_alloc_p2m_entry(page_to_pfn(page)); + if (ret < 0) + goto out_undo; + } #endif } else { ret = add_ballooned_pages(nr_pages - pgno); diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 3c41470c7fc4..76b318e88382 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -432,12 +432,12 @@ static int xen_evtchn_cpu_dead(unsigned int cpu) int __init xen_evtchn_fifo_init(void) { - int cpu = get_cpu(); + int cpu = smp_processor_id(); int ret; ret = evtchn_fifo_alloc_control_block(cpu); if (ret < 0) - goto out; + return ret; pr_info("Using FIFO-based ABI\n"); @@ -446,7 +446,6 @@ int __init xen_evtchn_fifo_init(void) cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE, "xen/evtchn:prepare", xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead); -out: - put_cpu(); + return ret; } diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index 1275df83070f..5d7dcad0b0a0 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -175,7 +175,7 @@ pci_out: return ret; } -static struct pci_device_id platform_pci_tbl[] = { +static const struct pci_device_id platform_pci_tbl[] = { {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {0,} diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c new file mode 100644 index 000000000000..b209cd44bb8d --- /dev/null +++ b/drivers/xen/pvcalls-back.c @@ -0,0 +1,1240 @@ +/* + * (c) 2017 Stefano Stabellini <stefano@aporeto.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/inet.h> +#include <linux/kthread.h> +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/module.h> +#include <linux/semaphore.h> +#include <linux/wait.h> +#include <net/sock.h> +#include <net/inet_common.h> +#include <net/inet_connection_sock.h> +#include <net/request_sock.h> + +#include <xen/events.h> +#include <xen/grant_table.h> +#include <xen/xen.h> +#include <xen/xenbus.h> +#include <xen/interface/io/pvcalls.h> + +#define PVCALLS_VERSIONS "1" +#define MAX_RING_ORDER XENBUS_MAX_RING_GRANT_ORDER + +struct pvcalls_back_global { + struct list_head frontends; + struct semaphore frontends_lock; +} pvcalls_back_global; + +/* + * Per-frontend data structure. It contains pointers to the command + * ring, its event channel, a list of active sockets and a tree of + * passive sockets. + */ +struct pvcalls_fedata { + struct list_head list; + struct xenbus_device *dev; + struct xen_pvcalls_sring *sring; + struct xen_pvcalls_back_ring ring; + int irq; + struct list_head socket_mappings; + struct radix_tree_root socketpass_mappings; + struct semaphore socket_lock; +}; + +struct pvcalls_ioworker { + struct work_struct register_work; + struct workqueue_struct *wq; +}; + +struct sock_mapping { + struct list_head list; + struct pvcalls_fedata *fedata; + struct sockpass_mapping *sockpass; + struct socket *sock; + uint64_t id; + grant_ref_t ref; + struct pvcalls_data_intf *ring; + void *bytes; + struct pvcalls_data data; + uint32_t ring_order; + int irq; + atomic_t read; + atomic_t write; + atomic_t io; + atomic_t release; + void (*saved_data_ready)(struct sock *sk); + struct pvcalls_ioworker ioworker; +}; + +struct sockpass_mapping { + struct list_head list; + struct pvcalls_fedata *fedata; + struct socket *sock; + uint64_t id; + struct xen_pvcalls_request reqcopy; + spinlock_t copy_lock; + struct workqueue_struct *wq; + struct work_struct register_work; + void (*saved_data_ready)(struct sock *sk); +}; + +static irqreturn_t pvcalls_back_conn_event(int irq, void *sock_map); +static int pvcalls_back_release_active(struct xenbus_device *dev, + struct pvcalls_fedata *fedata, + struct sock_mapping *map); + +static void pvcalls_conn_back_read(void *opaque) +{ + struct sock_mapping *map = (struct sock_mapping *)opaque; + struct msghdr msg; + struct kvec vec[2]; + RING_IDX cons, prod, size, wanted, array_size, masked_prod, masked_cons; + int32_t error; + struct pvcalls_data_intf *intf = map->ring; + struct pvcalls_data *data = &map->data; + unsigned long flags; + int ret; + + array_size = XEN_FLEX_RING_SIZE(map->ring_order); + cons = intf->in_cons; + prod = intf->in_prod; + error = intf->in_error; + /* read the indexes first, then deal with the data */ + virt_mb(); + + if (error) + return; + + size = pvcalls_queued(prod, cons, array_size); + if (size >= array_size) + return; + spin_lock_irqsave(&map->sock->sk->sk_receive_queue.lock, flags); + if (skb_queue_empty(&map->sock->sk->sk_receive_queue)) { + atomic_set(&map->read, 0); + spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, + flags); + return; + } + spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, flags); + wanted = array_size - size; + masked_prod = pvcalls_mask(prod, array_size); + masked_cons = pvcalls_mask(cons, array_size); + + memset(&msg, 0, sizeof(msg)); + msg.msg_iter.type = ITER_KVEC|WRITE; + msg.msg_iter.count = wanted; + if (masked_prod < masked_cons) { + vec[0].iov_base = data->in + masked_prod; + vec[0].iov_len = wanted; + msg.msg_iter.kvec = vec; + msg.msg_iter.nr_segs = 1; + } else { + vec[0].iov_base = data->in + masked_prod; + vec[0].iov_len = array_size - masked_prod; + vec[1].iov_base = data->in; + vec[1].iov_len = wanted - vec[0].iov_len; + msg.msg_iter.kvec = vec; + msg.msg_iter.nr_segs = 2; + } + + atomic_set(&map->read, 0); + ret = inet_recvmsg(map->sock, &msg, wanted, MSG_DONTWAIT); + WARN_ON(ret > wanted); + if (ret == -EAGAIN) /* shouldn't happen */ + return; + if (!ret) + ret = -ENOTCONN; + spin_lock_irqsave(&map->sock->sk->sk_receive_queue.lock, flags); + if (ret > 0 && !skb_queue_empty(&map->sock->sk->sk_receive_queue)) + atomic_inc(&map->read); + spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, flags); + + /* write the data, then modify the indexes */ + virt_wmb(); + if (ret < 0) + intf->in_error = ret; + else + intf->in_prod = prod + ret; + /* update the indexes, then notify the other end */ + virt_wmb(); + notify_remote_via_irq(map->irq); + + return; +} + +static void pvcalls_conn_back_write(struct sock_mapping *map) +{ + struct pvcalls_data_intf *intf = map->ring; + struct pvcalls_data *data = &map->data; + struct msghdr msg; + struct kvec vec[2]; + RING_IDX cons, prod, size, array_size; + int ret; + + cons = intf->out_cons; + prod = intf->out_prod; + /* read the indexes before dealing with the data */ + virt_mb(); + + array_size = XEN_FLEX_RING_SIZE(map->ring_order); + size = pvcalls_queued(prod, cons, array_size); + if (size == 0) + return; + + memset(&msg, 0, sizeof(msg)); + msg.msg_flags |= MSG_DONTWAIT; + msg.msg_iter.type = ITER_KVEC|READ; + msg.msg_iter.count = size; + if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) { + vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); + vec[0].iov_len = size; + msg.msg_iter.kvec = vec; + msg.msg_iter.nr_segs = 1; + } else { + vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); + vec[0].iov_len = array_size - pvcalls_mask(cons, array_size); + vec[1].iov_base = data->out; + vec[1].iov_len = size - vec[0].iov_len; + msg.msg_iter.kvec = vec; + msg.msg_iter.nr_segs = 2; + } + + atomic_set(&map->write, 0); + ret = inet_sendmsg(map->sock, &msg, size); + if (ret == -EAGAIN || (ret >= 0 && ret < size)) { + atomic_inc(&map->write); + atomic_inc(&map->io); + } + if (ret == -EAGAIN) + return; + + /* write the data, then update the indexes */ + virt_wmb(); + if (ret < 0) { + intf->out_error = ret; + } else { + intf->out_error = 0; + intf->out_cons = cons + ret; + prod = intf->out_prod; + } + /* update the indexes, then notify the other end */ + virt_wmb(); + if (prod != cons + ret) + atomic_inc(&map->write); + notify_remote_via_irq(map->irq); +} + +static void pvcalls_back_ioworker(struct work_struct *work) +{ + struct pvcalls_ioworker *ioworker = container_of(work, + struct pvcalls_ioworker, register_work); + struct sock_mapping *map = container_of(ioworker, struct sock_mapping, + ioworker); + + while (atomic_read(&map->io) > 0) { + if (atomic_read(&map->release) > 0) { + atomic_set(&map->release, 0); + return; + } + + if (atomic_read(&map->read) > 0) + pvcalls_conn_back_read(map); + if (atomic_read(&map->write) > 0) + pvcalls_conn_back_write(map); + + atomic_dec(&map->io); + } +} + +static int pvcalls_back_socket(struct xenbus_device *dev, + struct xen_pvcalls_request *req) +{ + struct pvcalls_fedata *fedata; + int ret; + struct xen_pvcalls_response *rsp; + + fedata = dev_get_drvdata(&dev->dev); + + if (req->u.socket.domain != AF_INET || + req->u.socket.type != SOCK_STREAM || + (req->u.socket.protocol != IPPROTO_IP && + req->u.socket.protocol != AF_INET)) + ret = -EAFNOSUPPORT; + else + ret = 0; + + /* leave the actual socket allocation for later */ + + rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); + rsp->req_id = req->req_id; + rsp->cmd = req->cmd; + rsp->u.socket.id = req->u.socket.id; + rsp->ret = ret; + + return 0; +} + +static void pvcalls_sk_state_change(struct sock *sock) +{ + struct sock_mapping *map = sock->sk_user_data; + struct pvcalls_data_intf *intf; + + if (map == NULL) + return; + + intf = map->ring; + intf->in_error = -ENOTCONN; + notify_remote_via_irq(map->irq); +} + +static void pvcalls_sk_data_ready(struct sock *sock) +{ + struct sock_mapping *map = sock->sk_user_data; + struct pvcalls_ioworker *iow; + + if (map == NULL) + return; + + iow = &map->ioworker; + atomic_inc(&map->read); + atomic_inc(&map->io); + queue_work(iow->wq, &iow->register_work); +} + +static struct sock_mapping *pvcalls_new_active_socket( + struct pvcalls_fedata *fedata, + uint64_t id, + grant_ref_t ref, + uint32_t evtchn, + struct socket *sock) +{ + int ret; + struct sock_mapping *map; + void *page; + + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (map == NULL) + return NULL; + + map->fedata = fedata; + map->sock = sock; + map->id = id; + map->ref = ref; + + ret = xenbus_map_ring_valloc(fedata->dev, &ref, 1, &page); + if (ret < 0) + goto out; + map->ring = page; + map->ring_order = map->ring->ring_order; + /* first read the order, then map the data ring */ + virt_rmb(); + if (map->ring_order > MAX_RING_ORDER) { + pr_warn("%s frontend requested ring_order %u, which is > MAX (%u)\n", + __func__, map->ring_order, MAX_RING_ORDER); + goto out; + } + ret = xenbus_map_ring_valloc(fedata->dev, map->ring->ref, + (1 << map->ring_order), &page); + if (ret < 0) + goto out; + map->bytes = page; + + ret = bind_interdomain_evtchn_to_irqhandler(fedata->dev->otherend_id, + evtchn, + pvcalls_back_conn_event, + 0, + "pvcalls-backend", + map); + if (ret < 0) + goto out; + map->irq = ret; + + map->data.in = map->bytes; + map->data.out = map->bytes + XEN_FLEX_RING_SIZE(map->ring_order); + + map->ioworker.wq = alloc_workqueue("pvcalls_io", WQ_UNBOUND, 1); + if (!map->ioworker.wq) + goto out; + atomic_set(&map->io, 1); + INIT_WORK(&map->ioworker.register_work, pvcalls_back_ioworker); + + down(&fedata->socket_lock); + list_add_tail(&map->list, &fedata->socket_mappings); + up(&fedata->socket_lock); + + write_lock_bh(&map->sock->sk->sk_callback_lock); + map->saved_data_ready = map->sock->sk->sk_data_ready; + map->sock->sk->sk_user_data = map; + map->sock->sk->sk_data_ready = pvcalls_sk_data_ready; + map->sock->sk->sk_state_change = pvcalls_sk_state_change; + write_unlock_bh(&map->sock->sk->sk_callback_lock); + + return map; +out: + down(&fedata->socket_lock); + list_del(&map->list); + pvcalls_back_release_active(fedata->dev, fedata, map); + up(&fedata->socket_lock); + return NULL; +} + +static int pvcalls_back_connect(struct xenbus_device *dev, + struct xen_pvcalls_request *req) +{ + struct pvcalls_fedata *fedata; + int ret = -EINVAL; + struct socket *sock; + struct sock_mapping *map; + struct xen_pvcalls_response *rsp; + struct sockaddr *sa = (struct sockaddr *)&req->u.connect.addr; + + fedata = dev_get_drvdata(&dev->dev); + + if (req->u.connect.len < sizeof(sa->sa_family) || + req->u.connect.len > sizeof(req->u.connect.addr) || + sa->sa_family != AF_INET) + goto out; + + ret = sock_create(AF_INET, SOCK_STREAM, 0, &sock); + if (ret < 0) + goto out; + ret = inet_stream_connect(sock, sa, req->u.connect.len, 0); + if (ret < 0) { + sock_release(sock); + goto out; + } + + map = pvcalls_new_active_socket(fedata, + req->u.connect.id, + req->u.connect.ref, + req->u.connect.evtchn, + sock); + if (!map) { + ret = -EFAULT; + sock_release(map->sock); + } + +out: + rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); + rsp->req_id = req->req_id; + rsp->cmd = req->cmd; + rsp->u.connect.id = req->u.connect.id; + rsp->ret = ret; + + return 0; +} + +static int pvcalls_back_release_active(struct xenbus_device *dev, + struct pvcalls_fedata *fedata, + struct sock_mapping *map) +{ + disable_irq(map->irq); + if (map->sock->sk != NULL) { + write_lock_bh(&map->sock->sk->sk_callback_lock); + map->sock->sk->sk_user_data = NULL; + map->sock->sk->sk_data_ready = map->saved_data_ready; + write_unlock_bh(&map->sock->sk->sk_callback_lock); + } + + atomic_set(&map->release, 1); + flush_work(&map->ioworker.register_work); + + xenbus_unmap_ring_vfree(dev, map->bytes); + xenbus_unmap_ring_vfree(dev, (void *)map->ring); + unbind_from_irqhandler(map->irq, map); + + sock_release(map->sock); + kfree(map); + + return 0; +} + +static int pvcalls_back_release_passive(struct xenbus_device *dev, + struct pvcalls_fedata *fedata, + struct sockpass_mapping *mappass) +{ + if (mappass->sock->sk != NULL) { + write_lock_bh(&mappass->sock->sk->sk_callback_lock); + mappass->sock->sk->sk_user_data = NULL; + mappass->sock->sk->sk_data_ready = mappass->saved_data_ready; + write_unlock_bh(&mappass->sock->sk->sk_callback_lock); + } + sock_release(mappass->sock); + flush_workqueue(mappass->wq); + destroy_workqueue(mappass->wq); + kfree(mappass); + + return 0; +} + +static int pvcalls_back_release(struct xenbus_device *dev, + struct xen_pvcalls_request *req) +{ + struct pvcalls_fedata *fedata; + struct sock_mapping *map, *n; + struct sockpass_mapping *mappass; + int ret = 0; + struct xen_pvcalls_response *rsp; + + fedata = dev_get_drvdata(&dev->dev); + + down(&fedata->socket_lock); + list_for_each_entry_safe(map, n, &fedata->socket_mappings, list) { + if (map->id == req->u.release.id) { + list_del(&map->list); + up(&fedata->socket_lock); + ret = pvcalls_back_release_active(dev, fedata, map); + goto out; + } + } + mappass = radix_tree_lookup(&fedata->socketpass_mappings, + req->u.release.id); + if (mappass != NULL) { + radix_tree_delete(&fedata->socketpass_mappings, mappass->id); + up(&fedata->socket_lock); + ret = pvcalls_back_release_passive(dev, fedata, mappass); + } else + up(&fedata->socket_lock); + +out: + rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); + rsp->req_id = req->req_id; + rsp->u.release.id = req->u.release.id; + rsp->cmd = req->cmd; + rsp->ret = ret; + return 0; +} + +static void __pvcalls_back_accept(struct work_struct *work) +{ + struct sockpass_mapping *mappass = container_of( + work, struct sockpass_mapping, register_work); + struct sock_mapping *map; + struct pvcalls_ioworker *iow; + struct pvcalls_fedata *fedata; + struct socket *sock; + struct xen_pvcalls_response *rsp; + struct xen_pvcalls_request *req; + int notify; + int ret = -EINVAL; + unsigned long flags; + + fedata = mappass->fedata; + /* + * __pvcalls_back_accept can race against pvcalls_back_accept. + * We only need to check the value of "cmd" on read. It could be + * done atomically, but to simplify the code on the write side, we + * use a spinlock. + */ + spin_lock_irqsave(&mappass->copy_lock, flags); + req = &mappass->reqcopy; + if (req->cmd != PVCALLS_ACCEPT) { + spin_unlock_irqrestore(&mappass->copy_lock, flags); + return; + } + spin_unlock_irqrestore(&mappass->copy_lock, flags); + + sock = sock_alloc(); + if (sock == NULL) + goto out_error; + sock->type = mappass->sock->type; + sock->ops = mappass->sock->ops; + + ret = inet_accept(mappass->sock, sock, O_NONBLOCK, true); + if (ret == -EAGAIN) { + sock_release(sock); + goto out_error; + } + + map = pvcalls_new_active_socket(fedata, + req->u.accept.id_new, + req->u.accept.ref, + req->u.accept.evtchn, + sock); + if (!map) { + ret = -EFAULT; + sock_release(sock); + goto out_error; + } + + map->sockpass = mappass; + iow = &map->ioworker; + atomic_inc(&map->read); + atomic_inc(&map->io); + queue_work(iow->wq, &iow->register_work); + +out_error: + rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); + rsp->req_id = req->req_id; + rsp->cmd = req->cmd; + rsp->u.accept.id = req->u.accept.id; + rsp->ret = ret; + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&fedata->ring, notify); + if (notify) + notify_remote_via_irq(fedata->irq); + + mappass->reqcopy.cmd = 0; +} + +static void pvcalls_pass_sk_data_ready(struct sock *sock) +{ + struct sockpass_mapping *mappass = sock->sk_user_data; + struct pvcalls_fedata *fedata; + struct xen_pvcalls_response *rsp; + unsigned long flags; + int notify; + + if (mappass == NULL) + return; + + fedata = mappass->fedata; + spin_lock_irqsave(&mappass->copy_lock, flags); + if (mappass->reqcopy.cmd == PVCALLS_POLL) { + rsp = RING_GET_RESPONSE(&fedata->ring, + fedata->ring.rsp_prod_pvt++); + rsp->req_id = mappass->reqcopy.req_id; + rsp->u.poll.id = mappass->reqcopy.u.poll.id; + rsp->cmd = mappass->reqcopy.cmd; + rsp->ret = 0; + + mappass->reqcopy.cmd = 0; + spin_unlock_irqrestore(&mappass->copy_lock, flags); + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&fedata->ring, notify); + if (notify) + notify_remote_via_irq(mappass->fedata->irq); + } else { + spin_unlock_irqrestore(&mappass->copy_lock, flags); + queue_work(mappass->wq, &mappass->register_work); + } +} + +static int pvcalls_back_bind(struct xenbus_device *dev, + struct xen_pvcalls_request *req) +{ + struct pvcalls_fedata *fedata; + int ret; + struct sockpass_mapping *map; + struct xen_pvcalls_response *rsp; + + fedata = dev_get_drvdata(&dev->dev); + + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (map == NULL) { + ret = -ENOMEM; + goto out; + } + + INIT_WORK(&map->register_work, __pvcalls_back_accept); + spin_lock_init(&map->copy_lock); + map->wq = alloc_workqueue("pvcalls_wq", WQ_UNBOUND, 1); + if (!map->wq) { + ret = -ENOMEM; + goto out; + } + + ret = sock_create(AF_INET, SOCK_STREAM, 0, &map->sock); + if (ret < 0) + goto out; + + ret = inet_bind(map->sock, (struct sockaddr *)&req->u.bind.addr, + req->u.bind.len); + if (ret < 0) + goto out; + + map->fedata = fedata; + map->id = req->u.bind.id; + + down(&fedata->socket_lock); + ret = radix_tree_insert(&fedata->socketpass_mappings, map->id, + map); + up(&fedata->socket_lock); + if (ret) + goto out; + + write_lock_bh(&map->sock->sk->sk_callback_lock); + map->saved_data_ready = map->sock->sk->sk_data_ready; + map->sock->sk->sk_user_data = map; + map->sock->sk->sk_data_ready = pvcalls_pass_sk_data_ready; + write_unlock_bh(&map->sock->sk->sk_callback_lock); + +out: + if (ret) { + if (map && map->sock) + sock_release(map->sock); + if (map && map->wq) + destroy_workqueue(map->wq); + kfree(map); + } + rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); + rsp->req_id = req->req_id; + rsp->cmd = req->cmd; + rsp->u.bind.id = req->u.bind.id; + rsp->ret = ret; + return 0; +} + +static int pvcalls_back_listen(struct xenbus_device *dev, + struct xen_pvcalls_request *req) +{ + struct pvcalls_fedata *fedata; + int ret = -EINVAL; + struct sockpass_mapping *map; + struct xen_pvcalls_response *rsp; + + fedata = dev_get_drvdata(&dev->dev); + + down(&fedata->socket_lock); + map = radix_tree_lookup(&fedata->socketpass_mappings, req->u.listen.id); + up(&fedata->socket_lock); + if (map == NULL) + goto out; + + ret = inet_listen(map->sock, req->u.listen.backlog); + +out: + rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pv |