diff options
Diffstat (limited to 'drivers/xen')
| -rw-r--r-- | drivers/xen/Kconfig | 17 | ||||
| -rw-r--r-- | drivers/xen/Makefile | 2 | ||||
| -rw-r--r-- | drivers/xen/balloon.c | 23 | ||||
| -rw-r--r-- | drivers/xen/events/events_base.c | 18 | ||||
| -rw-r--r-- | drivers/xen/preempt.c | 44 | ||||
| -rw-r--r-- | drivers/xen/privcmd.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/conf_space.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/conf_space.h | 2 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/conf_space_header.c | 61 | ||||
| -rw-r--r-- | drivers/xen/xen-scsiback.c | 21 |
10 files changed, 158 insertions, 34 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index b812462..94d9680 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -55,6 +55,23 @@ config XEN_BALLOON_MEMORY_HOTPLUG In that case step 3 should be omitted. +config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT + int "Hotplugged memory limit (in GiB) for a PV guest" + default 512 if X86_64 + default 4 if X86_32 + range 0 64 if X86_32 + depends on XEN_HAVE_PVMMU + depends on XEN_BALLOON_MEMORY_HOTPLUG + help + Maxmium amount of memory (in GiB) that a PV guest can be + expanded to when using memory hotplug. + + A PV guest can have more memory than this limit if is + started with a larger maximum. + + This value is used to allocate enough space in internal + tables needed for physical memory administration. + config XEN_SCRUB_PAGES bool "Scrub pages before returning them to system" depends on XEN_BALLOON diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 2140398..2ccd359 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -2,7 +2,7 @@ ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),) obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o endif obj-$(CONFIG_X86) += fallback.o -obj-y += grant-table.o features.o balloon.o manage.o +obj-y += grant-table.o features.o balloon.o manage.o preempt.o obj-y += events/ obj-y += xenbus/ diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 0b52d92..fd93369 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -229,6 +229,29 @@ static enum bp_state reserve_additional_memory(long credit) balloon_hotplug = round_up(balloon_hotplug, PAGES_PER_SECTION); nid = memory_add_physaddr_to_nid(hotplug_start_paddr); +#ifdef CONFIG_XEN_HAVE_PVMMU + /* + * add_memory() will build page tables for the new memory so + * the p2m must contain invalid entries so the correct + * non-present PTEs will be written. + * + * If a failure occurs, the original (identity) p2m entries + * are not restored since this region is now known not to + * conflict with any devices. + */ + if (!xen_feature(XENFEAT_auto_translated_physmap)) { + unsigned long pfn, i; + + pfn = PFN_DOWN(hotplug_start_paddr); + for (i = 0; i < balloon_hotplug; i++) { + if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) { + pr_warn("set_phys_to_machine() failed, no memory added\n"); + return BP_ECANCELED; + } + } + } +#endif + rc = add_memory(nid, hotplug_start_paddr, balloon_hotplug << PAGE_SHIFT); if (rc) { diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index b4bca2d..70fba97 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -526,20 +526,26 @@ static unsigned int __startup_pirq(unsigned int irq) pirq_query_unmask(irq); rc = set_evtchn_to_irq(evtchn, irq); - if (rc != 0) { - pr_err("irq%d: Failed to set port to irq mapping (%d)\n", - irq, rc); - xen_evtchn_close(evtchn); - return 0; - } + if (rc) + goto err; + bind_evtchn_to_cpu(evtchn, 0); info->evtchn = evtchn; + rc = xen_evtchn_port_setup(info); + if (rc) + goto err; + out: unmask_evtchn(evtchn); eoi_pirq(irq_get_irq_data(irq)); return 0; + +err: + pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc); + xen_evtchn_close(evtchn); + return 0; } static unsigned int startup_pirq(struct irq_data *data) diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c new file mode 100644 index 0000000..a1800c1 --- /dev/null +++ b/drivers/xen/preempt.c @@ -0,0 +1,44 @@ +/* + * Preemptible hypercalls + * + * Copyright (C) 2014 Citrix Systems R&D ltd. + * + * This source code 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. + */ + +#include <linux/sched.h> +#include <xen/xen-ops.h> + +#ifndef CONFIG_PREEMPT + +/* + * Some hypercalls issued by the toolstack can take many 10s of + * seconds. Allow tasks running hypercalls via the privcmd driver to + * be voluntarily preempted even if full kernel preemption is + * disabled. + * + * Such preemptible hypercalls are bracketed by + * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end() + * calls. + */ + +DEFINE_PER_CPU(bool, xen_in_preemptible_hcall); +EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall); + +asmlinkage __visible void xen_maybe_preempt_hcall(void) +{ + if (unlikely(__this_cpu_read(xen_in_preemptible_hcall) + && should_resched())) { + /* + * Clear flag as we may be rescheduled on a different + * cpu. + */ + __this_cpu_write(xen_in_preemptible_hcall, false); + _cond_resched(); + __this_cpu_write(xen_in_preemptible_hcall, true); + } +} +#endif /* CONFIG_PREEMPT */ diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 569a13b..59ac71c 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -56,10 +56,12 @@ static long privcmd_ioctl_hypercall(void __user *udata) if (copy_from_user(&hypercall, udata, sizeof(hypercall))) return -EFAULT; + xen_preemptible_hcall_begin(); ret = privcmd_call(hypercall.op, hypercall.arg[0], hypercall.arg[1], hypercall.arg[2], hypercall.arg[3], hypercall.arg[4]); + xen_preemptible_hcall_end(); return ret; } diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 46ae0f9..75fe3d4 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -16,7 +16,7 @@ #include "conf_space.h" #include "conf_space_quirks.h" -static bool permissive; +bool permissive; module_param(permissive, bool, 0644); /* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word, diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h index e56c934..2e1d73d 100644 --- a/drivers/xen/xen-pciback/conf_space.h +++ b/drivers/xen/xen-pciback/conf_space.h @@ -64,6 +64,8 @@ struct config_field_entry { void *data; }; +extern bool permissive; + #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset) /* Add fields to a device - the add_fields macro expects to get a pointer to diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index c5ee825..2d73693 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -11,6 +11,10 @@ #include "pciback.h" #include "conf_space.h" +struct pci_cmd_info { + u16 val; +}; + struct pci_bar_info { u32 val; u32 len_val; @@ -20,22 +24,36 @@ struct pci_bar_info { #define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO)) #define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER) -static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +/* Bits guests are allowed to control in permissive mode. */ +#define PCI_COMMAND_GUEST (PCI_COMMAND_MASTER|PCI_COMMAND_SPECIAL| \ + PCI_COMMAND_INVALIDATE|PCI_COMMAND_VGA_PALETTE| \ + PCI_COMMAND_WAIT|PCI_COMMAND_FAST_BACK) + +static void *command_init(struct pci_dev *dev, int offset) { - int i; - int ret; - - ret = xen_pcibk_read_config_word(dev, offset, value, data); - if (!pci_is_enabled(dev)) - return ret; - - for (i = 0; i < PCI_ROM_RESOURCE; i++) { - if (dev->resource[i].flags & IORESOURCE_IO) - *value |= PCI_COMMAND_IO; - if (dev->resource[i].flags & IORESOURCE_MEM) - *value |= PCI_COMMAND_MEMORY; + struct pci_cmd_info *cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + int err; + + if (!cmd) + return ERR_PTR(-ENOMEM); + + err = pci_read_config_word(dev, PCI_COMMAND, &cmd->val); + if (err) { + kfree(cmd); + return ERR_PTR(err); } + return cmd; +} + +static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +{ + int ret = pci_read_config_word(dev, offset, value); + const struct pci_cmd_info *cmd = data; + + *value &= PCI_COMMAND_GUEST; + *value |= cmd->val & ~PCI_COMMAND_GUEST; + return ret; } @@ -43,6 +61,8 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) { struct xen_pcibk_dev_data *dev_data; int err; + u16 val; + struct pci_cmd_info *cmd = data; dev_data = pci_get_drvdata(dev); if (!pci_is_enabled(dev) && is_enable_cmd(value)) { @@ -83,6 +103,19 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) } } + cmd->val = value; + + if (!permissive && (!dev_data || !dev_data->permissive)) + return 0; + + /* Only allow the guest to control certain bits. */ + err = pci_read_config_word(dev, offset, &val); + if (err || val == value) + return err; + + value &= PCI_COMMAND_GUEST; + value |= val & ~PCI_COMMAND_GUEST; + return pci_write_config_word(dev, offset, value); } @@ -282,6 +315,8 @@ static const struct config_field header_common[] = { { .offset = PCI_COMMAND, .size = 2, + .init = command_init, + .release = bar_release, .u.w.read = command_read, .u.w.write = command_write, }, diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 61653a0..42bd55a 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -709,12 +709,11 @@ static int prepare_pending_reqs(struct vscsibk_info *info, static int scsiback_do_cmd_fn(struct vscsibk_info *info) { struct vscsiif_back_ring *ring = &info->ring; - struct vscsiif_request *ring_req; + struct vscsiif_request ring_req; struct vscsibk_pend *pending_req; RING_IDX rc, rp; int err, more_to_do; uint32_t result; - uint8_t act; rc = ring->req_cons; rp = ring->sring->req_prod; @@ -735,11 +734,10 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) if (!pending_req) return 1; - ring_req = RING_GET_REQUEST(ring, rc); + ring_req = *RING_GET_REQUEST(ring, rc); ring->req_cons = ++rc; - act = ring_req->act; - err = prepare_pending_reqs(info, ring_req, pending_req); + err = prepare_pending_reqs(info, &ring_req, pending_req); if (err) { switch (err) { case -ENODEV: @@ -755,9 +753,9 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) return 1; } - switch (act) { + switch (ring_req.act) { case VSCSIIF_ACT_SCSI_CDB: - if (scsiback_gnttab_data_map(ring_req, pending_req)) { + if (scsiback_gnttab_data_map(&ring_req, pending_req)) { scsiback_fast_flush_area(pending_req); scsiback_do_resp_with_sense(NULL, DRIVER_ERROR << 24, 0, pending_req); @@ -768,7 +766,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) break; case VSCSIIF_ACT_SCSI_ABORT: scsiback_device_action(pending_req, TMR_ABORT_TASK, - ring_req->ref_rqid); + ring_req.ref_rqid); break; case VSCSIIF_ACT_SCSI_RESET: scsiback_device_action(pending_req, TMR_LUN_RESET, 0); @@ -1661,11 +1659,8 @@ static int scsiback_make_nexus(struct scsiback_tpg *tpg, name); goto out; } - /* - * Now register the TCM pvscsi virtual I_T Nexus as active with the - * call to __transport_register_session() - */ - __transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, + /* Now register the TCM pvscsi virtual I_T Nexus as active. */ + transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, tv_nexus->tvn_se_sess, tv_nexus); tpg->tpg_nexus = tv_nexus; |
