diff options
Diffstat (limited to 'drivers/xen')
-rw-r--r-- | drivers/xen/Kconfig | 16 | ||||
-rw-r--r-- | drivers/xen/Makefile | 2 | ||||
-rw-r--r-- | drivers/xen/cpu_hotplug.c | 3 | ||||
-rw-r--r-- | drivers/xen/events.c | 26 | ||||
-rw-r--r-- | drivers/xen/grant-table.c | 7 | ||||
-rw-r--r-- | drivers/xen/manage.c | 6 | ||||
-rw-r--r-- | drivers/xen/platform-pci.c | 5 | ||||
-rw-r--r-- | drivers/xen/sys-hypervisor.c | 6 | ||||
-rw-r--r-- | drivers/xen/tmem.c | 31 | ||||
-rw-r--r-- | drivers/xen/xen-acpi-processor.c | 562 | ||||
-rw-r--r-- | drivers/xen/xen-balloon.c | 2 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pci_stub.c | 49 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pciback.h | 1 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/xenbus.c | 5 | ||||
-rw-r--r-- | drivers/xen/xen-selfballoon.c | 2 | ||||
-rw-r--r-- | drivers/xen/xenbus/xenbus_client.c | 6 | ||||
-rw-r--r-- | drivers/xen/xenbus/xenbus_dev_frontend.c | 4 | ||||
-rw-r--r-- | drivers/xen/xenbus/xenbus_probe.c | 3 | ||||
-rw-r--r-- | drivers/xen/xenbus/xenbus_probe_frontend.c | 6 |
19 files changed, 691 insertions, 51 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index a1ced52..9424313 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -178,4 +178,20 @@ config XEN_PRIVCMD depends on XEN default m +config XEN_ACPI_PROCESSOR + tristate "Xen ACPI processor" + depends on XEN && X86 && ACPI_PROCESSOR && CPU_FREQ + default m + help + This ACPI processor uploads Power Management information to the Xen hypervisor. + + To do that the driver parses the Power Management data and uploads said + information to the Xen hypervisor. Then the Xen hypervisor can select the + proper Cx and Pxx states. It also registers itslef as the SMM so that + other drivers (such as ACPI cpufreq scaling driver) will not load. + + To compile this driver as a module, choose M here: the + module will be called xen_acpi_processor If you do not know what to choose, + select M here. If the CPUFREQ drivers are built in, select Y here. + endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index aa31337..9adc5be 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -20,7 +20,7 @@ obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o obj-$(CONFIG_XEN_DOM0) += pci.o obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/ obj-$(CONFIG_XEN_PRIVCMD) += xen-privcmd.o - +obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o xen-gntalloc-y := gntalloc.o diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index 14e2d99..4dcfced 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -30,7 +30,8 @@ static int vcpu_online(unsigned int cpu) sprintf(dir, "cpu/%u", cpu); err = xenbus_scanf(XBT_NIL, dir, "availability", "%s", state); if (err != 1) { - printk(KERN_ERR "XENBUS: Unable to read cpu state\n"); + if (!xen_initial_domain()) + printk(KERN_ERR "XENBUS: Unable to read cpu state\n"); return err; } diff --git a/drivers/xen/events.c b/drivers/xen/events.c index e5e5812..4b33acd 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -37,6 +37,7 @@ #include <asm/idle.h> #include <asm/io_apic.h> #include <asm/sync_bitops.h> +#include <asm/xen/page.h> #include <asm/xen/pci.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -109,6 +110,8 @@ struct irq_info { #define PIRQ_SHAREABLE (1 << 1) static int *evtchn_to_irq; +static unsigned long *pirq_eoi_map; +static bool (*pirq_needs_eoi)(unsigned irq); static DEFINE_PER_CPU(unsigned long [NR_EVENT_CHANNELS/BITS_PER_LONG], cpu_evtchn_mask); @@ -269,10 +272,14 @@ static unsigned int cpu_from_evtchn(unsigned int evtchn) return ret; } -static bool pirq_needs_eoi(unsigned irq) +static bool pirq_check_eoi_map(unsigned irq) { - struct irq_info *info = info_for_irq(irq); + return test_bit(irq, pirq_eoi_map); +} +static bool pirq_needs_eoi_flag(unsigned irq) +{ + struct irq_info *info = info_for_irq(irq); BUG_ON(info->type != IRQT_PIRQ); return info->u.pirq.flags & PIRQ_NEEDS_EOI; @@ -1768,7 +1775,7 @@ void xen_callback_vector(void) {} void __init xen_init_IRQ(void) { - int i; + int i, rc; evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq), GFP_KERNEL); @@ -1782,6 +1789,8 @@ void __init xen_init_IRQ(void) for (i = 0; i < NR_EVENT_CHANNELS; i++) mask_evtchn(i); + pirq_needs_eoi = pirq_needs_eoi_flag; + if (xen_hvm_domain()) { xen_callback_vector(); native_init_IRQ(); @@ -1789,8 +1798,19 @@ void __init xen_init_IRQ(void) * __acpi_register_gsi can point at the right function */ pci_xen_hvm_init(); } else { + struct physdev_pirq_eoi_gmfn eoi_gmfn; + irq_ctx_init(smp_processor_id()); if (xen_initial_domain()) pci_xen_initial_domain(); + + pirq_eoi_map = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO); + eoi_gmfn.gmfn = virt_to_mfn(pirq_eoi_map); + rc = HYPERVISOR_physdev_op(PHYSDEVOP_pirq_eoi_gmfn_v2, &eoi_gmfn); + if (rc != 0) { + free_page((unsigned long) pirq_eoi_map); + pirq_eoi_map = NULL; + } else + pirq_needs_eoi = pirq_check_eoi_map; } } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 1cd94da..b4d4eac 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -948,9 +948,12 @@ static void gnttab_request_version(void) int rc; struct gnttab_set_version gsv; - gsv.version = 2; + if (xen_hvm_domain()) + gsv.version = 1; + else + gsv.version = 2; rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1); - if (rc == 0) { + if (rc == 0 && gsv.version == 2) { grant_table_version = 2; gnttab_interface = &gnttab_v2_ops; } else if (grant_table_version == 2) { diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index ce4fa08..9e14ae6 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -129,9 +129,9 @@ static void do_suspend(void) printk(KERN_DEBUG "suspending xenstore...\n"); xs_suspend(); - err = dpm_suspend_noirq(PMSG_FREEZE); + err = dpm_suspend_end(PMSG_FREEZE); if (err) { - printk(KERN_ERR "dpm_suspend_noirq failed: %d\n", err); + printk(KERN_ERR "dpm_suspend_end failed: %d\n", err); goto out_resume; } @@ -149,7 +149,7 @@ static void do_suspend(void) err = stop_machine(xen_suspend, &si, cpumask_of(0)); - dpm_resume_noirq(si.cancelled ? PMSG_THAW : PMSG_RESTORE); + dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE); if (err) { printk(KERN_ERR "failed to start xen_suspend: %d\n", err); diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index 319dd0a..2389e58 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -186,11 +186,6 @@ static struct pci_driver platform_driver = { static int __init platform_pci_module_init(void) { - /* no unplug has been done, IGNORE hasn't been specified: just - * return now */ - if (!xen_platform_pci_unplug) - return -ENODEV; - return pci_register_driver(&platform_driver); } diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c index 1e0fe01..fdb6d22 100644 --- a/drivers/xen/sys-hypervisor.c +++ b/drivers/xen/sys-hypervisor.c @@ -97,7 +97,7 @@ static struct attribute *version_attrs[] = { NULL }; -static struct attribute_group version_group = { +static const struct attribute_group version_group = { .name = "version", .attrs = version_attrs, }; @@ -210,7 +210,7 @@ static struct attribute *xen_compile_attrs[] = { NULL }; -static struct attribute_group xen_compilation_group = { +static const struct attribute_group xen_compilation_group = { .name = "compilation", .attrs = xen_compile_attrs, }; @@ -340,7 +340,7 @@ static struct attribute *xen_properties_attrs[] = { NULL }; -static struct attribute_group xen_properties_group = { +static const struct attribute_group xen_properties_group = { .name = "properties", .attrs = xen_properties_attrs, }; diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index d369965..dcb79521 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -9,7 +9,6 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/pagemap.h> -#include <linux/module.h> #include <linux/cleancache.h> /* temporary ifdef until include/linux/frontswap.h is upstream */ @@ -128,15 +127,13 @@ static int xen_tmem_flush_object(u32 pool_id, struct tmem_oid oid) return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, oid, 0, 0, 0, 0, 0); } -int tmem_enabled __read_mostly; -EXPORT_SYMBOL(tmem_enabled); +bool __read_mostly tmem_enabled = false; static int __init enable_tmem(char *s) { - tmem_enabled = 1; + tmem_enabled = true; return 1; } - __setup("tmem", enable_tmem); #ifdef CONFIG_CLEANCACHE @@ -229,22 +226,21 @@ static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize) return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize); } -static int use_cleancache = 1; +static bool __initdata use_cleancache = true; static int __init no_cleancache(char *s) { - use_cleancache = 0; + use_cleancache = false; return 1; } - __setup("nocleancache", no_cleancache); -static struct cleancache_ops tmem_cleancache_ops = { +static struct cleancache_ops __initdata tmem_cleancache_ops = { .put_page = tmem_cleancache_put_page, .get_page = tmem_cleancache_get_page, - .flush_page = tmem_cleancache_flush_page, - .flush_inode = tmem_cleancache_flush_inode, - .flush_fs = tmem_cleancache_flush_fs, + .invalidate_page = tmem_cleancache_flush_page, + .invalidate_inode = tmem_cleancache_flush_inode, + .invalidate_fs = tmem_cleancache_flush_fs, .init_shared_fs = tmem_cleancache_init_shared_fs, .init_fs = tmem_cleancache_init_fs }; @@ -356,21 +352,20 @@ static void tmem_frontswap_init(unsigned ignored) xen_tmem_new_pool(private, TMEM_POOL_PERSIST, PAGE_SIZE); } -static int __initdata use_frontswap = 1; +static bool __initdata use_frontswap = true; static int __init no_frontswap(char *s) { - use_frontswap = 0; + use_frontswap = false; return 1; } - __setup("nofrontswap", no_frontswap); -static struct frontswap_ops tmem_frontswap_ops = { +static struct frontswap_ops __initdata tmem_frontswap_ops = { .put_page = tmem_frontswap_put_page, .get_page = tmem_frontswap_get_page, - .flush_page = tmem_frontswap_flush_page, - .flush_area = tmem_frontswap_flush_area, + .invalidate_page = tmem_frontswap_flush_page, + .invalidate_area = tmem_frontswap_flush_area, .init = tmem_frontswap_init }; #endif diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c new file mode 100644 index 0000000..174b565 --- /dev/null +++ b/drivers/xen/xen-acpi-processor.c @@ -0,0 +1,562 @@ +/* + * Copyright 2012 by Oracle Inc + * Author: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> + * + * This code borrows ideas from https://lkml.org/lkml/2011/11/30/249 + * so many thanks go to Kevin Tian <kevin.tian@intel.com> + * and Yu Ke <ke.yu@intel.com>. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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/cpumask.h> +#include <linux/cpufreq.h> +#include <linux/freezer.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/types.h> +#include <acpi/acpi_bus.h> +#include <acpi/acpi_drivers.h> +#include <acpi/processor.h> + +#include <xen/interface/platform.h> +#include <asm/xen/hypercall.h> + +#define DRV_NAME "xen-acpi-processor: " + +static int no_hypercall; +MODULE_PARM_DESC(off, "Inhibit the hypercall."); +module_param_named(off, no_hypercall, int, 0400); + +/* + * Note: Do not convert the acpi_id* below to cpumask_var_t or use cpumask_bit + * - as those shrink to nr_cpu_bits (which is dependent on possible_cpu), which + * can be less than what we want to put in. Instead use the 'nr_acpi_bits' + * which is dynamically computed based on the MADT or x2APIC table. + */ +static unsigned int nr_acpi_bits; +/* Mutex to protect the acpi_ids_done - for CPU hotplug use. */ +static DEFINE_MUTEX(acpi_ids_mutex); +/* Which ACPI ID we have processed from 'struct acpi_processor'. */ +static unsigned long *acpi_ids_done; +/* Which ACPI ID exist in the SSDT/DSDT processor definitions. */ +static unsigned long __initdata *acpi_id_present; +/* And if there is an _CST definition (or a PBLK) for the ACPI IDs */ +static unsigned long __initdata *acpi_id_cst_present; + +static int push_cxx_to_hypervisor(struct acpi_processor *_pr) +{ + struct xen_platform_op op = { + .cmd = XENPF_set_processor_pminfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.set_pminfo.id = _pr->acpi_id, + .u.set_pminfo.type = XEN_PM_CX, + }; + struct xen_processor_cx *dst_cx, *dst_cx_states = NULL; + struct acpi_processor_cx *cx; + unsigned int i, ok; + int ret = 0; + + dst_cx_states = kcalloc(_pr->power.count, + sizeof(struct xen_processor_cx), GFP_KERNEL); + if (!dst_cx_states) + return -ENOMEM; + + for (ok = 0, i = 1; i <= _pr->power.count; i++) { + cx = &_pr->power.states[i]; + if (!cx->valid) + continue; + + dst_cx = &(dst_cx_states[ok++]); + + dst_cx->reg.space_id = ACPI_ADR_SPACE_SYSTEM_IO; + if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) { + dst_cx->reg.bit_width = 8; + dst_cx->reg.bit_offset = 0; + dst_cx->reg.access_size = 1; + } else { + dst_cx->reg.space_id = ACPI_ADR_SPACE_FIXED_HARDWARE; + if (cx->entry_method == ACPI_CSTATE_FFH) { + /* NATIVE_CSTATE_BEYOND_HALT */ + dst_cx->reg.bit_offset = 2; + dst_cx->reg.bit_width = 1; /* VENDOR_INTEL */ + } + dst_cx->reg.access_size = 0; + } + dst_cx->reg.address = cx->address; + + dst_cx->type = cx->type; + dst_cx->latency = cx->latency; + dst_cx->power = cx->power; + + dst_cx->dpcnt = 0; + set_xen_guest_handle(dst_cx->dp, NULL); + } + if (!ok) { + pr_debug(DRV_NAME "No _Cx for ACPI CPU %u\n", _pr->acpi_id); + kfree(dst_cx_states); + return -EINVAL; + } + op.u.set_pminfo.power.count = ok; + op.u.set_pminfo.power.flags.bm_control = _pr->flags.bm_control; + op.u.set_pminfo.power.flags.bm_check = _pr->flags.bm_check; + op.u.set_pminfo.power.flags.has_cst = _pr->flags.has_cst; + op.u.set_pminfo.power.flags.power_setup_done = + _pr->flags.power_setup_done; + + set_xen_guest_handle(op.u.set_pminfo.power.states, dst_cx_states); + + if (!no_hypercall) + ret = HYPERVISOR_dom0_op(&op); + + if (!ret) { + pr_debug("ACPI CPU%u - C-states uploaded.\n", _pr->acpi_id); + for (i = 1; i <= _pr->power.count; i++) { + cx = &_pr->power.states[i]; + if (!cx->valid) + continue; + pr_debug(" C%d: %s %d uS\n", + cx->type, cx->desc, (u32)cx->latency); + } + } else + pr_err(DRV_NAME "(CX): Hypervisor error (%d) for ACPI CPU%u\n", + ret, _pr->acpi_id); + + kfree(dst_cx_states); + + return ret; +} +static struct xen_processor_px * +xen_copy_pss_data(struct acpi_processor *_pr, + struct xen_processor_performance *dst_perf) +{ + struct xen_processor_px *dst_states = NULL; + unsigned int i; + + BUILD_BUG_ON(sizeof(struct xen_processor_px) != + sizeof(struct acpi_processor_px)); + + dst_states = kcalloc(_pr->performance->state_count, + sizeof(struct xen_processor_px), GFP_KERNEL); + if (!dst_states) + return ERR_PTR(-ENOMEM); + + dst_perf->state_count = _pr->performance->state_count; + for (i = 0; i < _pr->performance->state_count; i++) { + /* Fortunatly for us, they are both the same size */ + memcpy(&(dst_states[i]), &(_pr->performance->states[i]), + sizeof(struct acpi_processor_px)); + } + return dst_states; +} +static int xen_copy_psd_data(struct acpi_processor *_pr, + struct xen_processor_performance *dst) +{ + struct acpi_psd_package *pdomain; + + BUILD_BUG_ON(sizeof(struct xen_psd_package) != + sizeof(struct acpi_psd_package)); + + /* This information is enumerated only if acpi_processor_preregister_performance + * has been called. + */ + dst->shared_type = _pr->performance->shared_type; + + pdomain = &(_pr->performance->domain_info); + + /* 'acpi_processor_preregister_performance' does not parse if the + * num_processors <= 1, but Xen still requires it. Do it manually here. + */ + if (pdomain->num_processors <= 1) { + if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL) + dst->shared_type = CPUFREQ_SHARED_TYPE_ALL; + else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL) + dst->shared_type = CPUFREQ_SHARED_TYPE_HW; + else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY) + dst->shared_type = CPUFREQ_SHARED_TYPE_ANY; + + } + memcpy(&(dst->domain_info), pdomain, sizeof(struct acpi_psd_package)); + return 0; +} +static int xen_copy_pct_data(struct acpi_pct_register *pct, + struct xen_pct_register *dst_pct) +{ + /* It would be nice if you could just do 'memcpy(pct, dst_pct') but + * sadly the Xen structure did not have the proper padding so the + * descriptor field takes two (dst_pct) bytes instead of one (pct). + */ + dst_pct->descriptor = pct->descriptor; + dst_pct->length = pct->length; + dst_pct->space_id = pct->space_id; + dst_pct->bit_width = pct->bit_width; + dst_pct->bit_offset = pct->bit_offset; + dst_pct->reserved = pct->reserved; + dst_pct->address = pct->address; + return 0; +} +static int push_pxx_to_hypervisor(struct acpi_processor *_pr) +{ + int ret = 0; + struct xen_platform_op op = { + .cmd = XENPF_set_processor_pminfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.set_pminfo.id = _pr->acpi_id, + .u.set_pminfo.type = XEN_PM_PX, + }; + struct xen_processor_performance *dst_perf; + struct xen_processor_px *dst_states = NULL; + + dst_perf = &op.u.set_pminfo.perf; + + dst_perf->platform_limit = _pr->performance_platform_limit; + dst_perf->flags |= XEN_PX_PPC; + xen_copy_pct_data(&(_pr->performance->control_register), + &dst_perf->control_register); + xen_copy_pct_data(&(_pr->performance->status_register), + &dst_perf->status_register); + dst_perf->flags |= XEN_PX_PCT; + dst_states = xen_copy_pss_data(_pr, dst_perf); + if (!IS_ERR_OR_NULL(dst_states)) { + set_xen_guest_handle(dst_perf->states, dst_states); + dst_perf->flags |= XEN_PX_PSS; + } + if (!xen_copy_psd_data(_pr, dst_perf)) + dst_perf->flags |= XEN_PX_PSD; + + if (dst_perf->flags != (XEN_PX_PSD | XEN_PX_PSS | XEN_PX_PCT | XEN_PX_PPC)) { + pr_warn(DRV_NAME "ACPI CPU%u missing some P-state data (%x), skipping.\n", + _pr->acpi_id, dst_perf->flags); + ret = -ENODEV; + goto err_free; + } + + if (!no_hypercall) + ret = HYPERVISOR_dom0_op(&op); + + if (!ret) { + struct acpi_processor_performance *perf; + unsigned int i; + + perf = _pr->performance; + pr_debug("ACPI CPU%u - P-states uploaded.\n", _pr->acpi_id); + for (i = 0; i < perf->state_count; i++) { + pr_debug(" %cP%d: %d MHz, %d mW, %d uS\n", + (i == perf->state ? '*' : ' '), i, + (u32) perf->states[i].core_frequency, + (u32) perf->states[i].power, + (u32) perf->states[i].transition_latency); + } + } else if (ret != -EINVAL) + /* EINVAL means the ACPI ID is incorrect - meaning the ACPI + * table is referencing a non-existing CPU - which can happen + * with broken ACPI tables. */ + pr_warn(DRV_NAME "(_PXX): Hypervisor error (%d) for ACPI CPU%u\n", + ret, _pr->acpi_id); +err_free: + if (!IS_ERR_OR_NULL(dst_states)) + kfree(dst_states); + + return ret; +} +static int upload_pm_data(struct acpi_processor *_pr) +{ + int err = 0; + + mutex_lock(&acpi_ids_mutex); + if (__test_and_set_bit(_pr->acpi_id, acpi_ids_done)) { + mutex_unlock(&acpi_ids_mutex); + return -EBUSY; + } + if (_pr->flags.power) + err = push_cxx_to_hypervisor(_pr); + + if (_pr->performance && _pr->performance->states) + err |= push_pxx_to_hypervisor(_pr); + + mutex_unlock(&acpi_ids_mutex); + return err; +} +static unsigned int __init get_max_acpi_id(void) +{ + struct xenpf_pcpuinfo *info; + struct xen_platform_op op = { + .cmd = XENPF_get_cpuinfo, + .interface_version = XENPF_INTERFACE_VERSION, + }; + int ret = 0; + unsigned int i, last_cpu, max_acpi_id = 0; + + info = &op.u.pcpu_info; + info->xen_cpuid = 0; + + ret = HYPERVISOR_dom0_op(&op); + if (ret) + return NR_CPUS; + + /* The max_present is the same irregardless of the xen_cpuid */ + last_cpu = op.u.pcpu_info.max_present; + for (i = 0; i <= last_cpu; i++) { + info->xen_cpuid = i; + ret = HYPERVISOR_dom0_op(&op); + if (ret) + continue; + max_acpi_id = max(info->acpi_id, max_acpi_id); + } + max_acpi_id *= 2; /* Slack for CPU hotplug support. */ + pr_debug(DRV_NAME "Max ACPI ID: %u\n", max_acpi_id); + return max_acpi_id; +} +/* + * The read_acpi_id and check_acpi_ids are there to support the Xen + * oddity of virtual CPUs != physical CPUs in the initial domain. + * The user can supply 'xen_max_vcpus=X' on the Xen hypervisor line + * which will band the amount of CPUs the initial domain can see. + * In general that is OK, except it plays havoc with any of the + * for_each_[present|online]_cpu macros which are banded to the virtual + * CPU amount. + */ +static acpi_status __init +read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv) +{ + u32 acpi_id; + acpi_status status; + acpi_object_type acpi_type; + unsigned long long tmp; + union acpi_object object = { 0 }; + struct acpi_buffer buffer = { sizeof(union acpi_object), &object }; + acpi_io_address pblk = 0; + + status = acpi_get_type(handle, &acpi_type); + if (ACPI_FAILURE(status)) + return AE_OK; + + switch (acpi_type) { + case ACPI_TYPE_PROCESSOR: + status = acpi_evaluate_object(handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) + return AE_OK; + acpi_id = object.processor.proc_id; + pblk = object.processor.pblk_address; + break; + case ACPI_TYPE_DEVICE: + status = acpi_evaluate_integer(handle, "_UID", NULL, &tmp); + if (ACPI_FAILURE(status)) + return AE_OK; + acpi_id = tmp; + break; + default: + return AE_OK; + } + /* There are more ACPI Processor objects than in x2APIC or MADT. + * This can happen with incorrect ACPI SSDT declerations. */ + if (acpi_id > nr_acpi_bits) { + pr_debug(DRV_NAME "We only have %u, trying to set %u\n", + nr_acpi_bits, acpi_id); + return AE_OK; + } + /* OK, There is a ACPI Processor object */ + __set_bit(acpi_id, acpi_id_present); + + pr_debug(DRV_NAME "ACPI CPU%u w/ PBLK:0x%lx\n", acpi_id, + (unsigned long)pblk); + + status = acpi_evaluate_object(handle, "_CST", NULL, &buffer); + if (ACPI_FAILURE(status)) { + if (!pblk) + return AE_OK; + } + /* .. and it has a C-state */ + __set_bit(acpi_id, acpi_id_cst_present); + + return AE_OK; +} +static int __init check_acpi_ids(struct acpi_processor *pr_backup) +{ + + if (!pr_backup) + return -ENODEV; + + /* All online CPUs have been processed at this stage. Now verify + * whether in fact "online CPUs" == physical CPUs. + */ + acpi_id_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); + if (!acpi_id_present) + return -ENOMEM; + + acpi_id_cst_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); + if (!acpi_id_cst_present) { + kfree(acpi_id_present); + return -ENOMEM; + } + + acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, + read_acpi_id, NULL, NULL, NULL); + acpi_get_devices("ACPI0007", read_acpi_id, NULL, NULL); + + if (!bitmap_equal(acpi_id_present, acpi_ids_done, nr_acpi_bits)) { + unsigned int i; + for_each_set_bit(i, acpi_id_present, nr_acpi_bits) { + pr_backup->acpi_id = i; + /* Mask out C-states if there are no _CST or PBLK */ + pr_backup->flags.power = test_bit(i, acpi_id_cst_present); + (void)upload_pm_data(pr_backup); + } + } + kfree(acpi_id_present); + acpi_id_present = NULL; + kfree(acpi_id_cst_present); + acpi_id_cst_present = NULL; + return 0; +} +static int __init check_prereq(void) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + + if (!xen_initial_domain()) + return -ENODEV; + + if (!acpi_gbl_FADT.smi_command) + return -ENODEV; + + if (c->x86_vendor == X86_VENDOR_INTEL) { + if (!cpu_has(c, X86_FEATURE_EST)) + return -ENODEV; + + return 0; + } + if (c->x86_vendor == X86_VENDOR_AMD) { + /* Copied from powernow-k8.h, can't include ../cpufreq/powernow + * as we get compile warnings for the static functions. + */ +#define CPUID_FREQ_VOLT_CAPABILITIES 0x80000007 +#define USE_HW_PSTATE 0x00000080 + u32 eax, ebx, ecx, edx; + cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx); + if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE) + return -ENODEV; + return 0; + } + return -ENODEV; +} +/* acpi_perf_data is a pointer to percpu data. */ +static struct acpi_processor_performance __percpu *acpi_perf_data; + +static void free_acpi_perf_data(void) +{ + unsigned int i; + + /* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */ + for_each_possible_cpu(i) + free_cpumask_var(per_cpu_ptr(acpi_perf_data, i) + ->shared_cpu_map); + free_percpu(acpi_perf_data); +} + +static int __init xen_acpi_processor_init(void) +{ + struct acpi_processor *pr_backup = NULL; + unsigned int i; + int rc = check_prereq(); + + if (rc) + return rc; + + nr_acpi_bits = get_max_acpi_id() + 1; + acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); + if (!acpi_ids_done) + return -ENOMEM; + + acpi_perf_data = alloc_percpu(struct acpi_processor_performance); + if (!acpi_perf_data) { + pr_debug(DRV_NAME "Memory allocation error for acpi_perf_data.\n"); + kfree(acpi_ids_done); + return -ENOMEM; + } + for_each_possible_cpu(i) { + if (!zalloc_cpumask_var_node( + &per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map, + GFP_KERNEL, cpu_to_node(i))) { + rc = -ENOMEM; + goto err_out; + } + } + + /* Do initialization in ACPI core. It is OK to fail here. */ + (void)acpi_processor_preregister_performance(acpi_perf_data); + + for_each_possible_cpu(i) { + struct acpi_processor_performance *perf; + + perf = per_cpu_ptr(acpi_perf_data, i); + rc = acpi_processor_register_performance(perf, i); + if (rc) + goto err_out; + } + rc = acpi_processor_notify_smm(THIS_MODULE); + if (rc) + goto err_unregister; + + for_each_possible_cpu(i) { + struct acpi_processor *_pr; + _pr = per_cpu(processors, i /* APIC ID */); + if (!_pr) + continue; + + if (!pr_backup) { + pr_backup = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL); + memcpy(pr_backup, _pr, sizeof(struct acpi_processor)); + } + (void)upload_pm_data(_pr); + } + rc = check_acpi_ids(pr_backup); + if (rc) + goto err_unregister; + + kfree(pr_backup); + + return 0; +err_unregister: + for_each_possible_cpu(i) { + struct acpi_processor_performance *perf; + perf = per_cpu_ptr(acpi_perf_data, i); + acpi_processor_unregister_performance(perf, i); + } +err_out: + /* Freeing a NULL pointer is OK: alloc_percpu zeroes. */ + free_acpi_perf_data(); + kfree(acpi_ids_done); + return rc; +} +static void __exit xen_acpi_processor_exit(void) +{ + int i; + + kfree(acpi_ids_done); + for_each_possible_cpu(i) { + struct acpi_processor_performance *perf; + perf = per_cpu_ptr(acpi_perf_data, i); + acpi_processor_unregister_performance(perf, i); + } + free_acpi_perf_data(); +} + +MODULE_AUTHOR("Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>"); +MODULE_DESCRIPTION("Xen ACPI Processor P-states (and Cx) driver which uploads PM data to Xen hypervisor"); +MODULE_LICENSE("GPL"); + +/* We want to be loaded before the CPU freq scaling drivers are loaded. + * They are loaded in late_initcall. */ +device_initcall(xen_acpi_processor_init); +module_exit(xen_acpi_processor_exit); diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index 596e6a7..8f37e23 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -207,7 +207,7 @@ static struct attribute *balloon_info_attrs[] = { NULL }; -static struct attribute_group balloon_info_group = { +static const struct attribute_group balloon_info_group = { .name = "info", .attrs = balloon_info_attrs }; diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 7944a17..097e536 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -85,19 +85,34 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev) static void pcistub_device_release(struct kref *kref) { struct pcistub_device *psdev; + struct xen_pcibk_dev_data *dev_data; psdev = container_of(kref, struct pcistub_device, kref); + dev_data = pci_get_drvdata(psdev->dev); dev_dbg(&psdev->dev->dev, "pcistub_device_release\n"); xen_unregister_device_domain_owner(psdev->dev); - /* Clean-up the device */ + /* Call the reset function which does not take lock as this + * is called from "unbind" which takes a device_lock mutex. + */ + __pci_reset_function_locked(psdev->dev); + if (pci_load_and_free_saved_state(psdev->dev, + &dev_data->pci_saved_state)) { + dev_dbg(&psdev->dev->dev, "Could not reload PCI state\n"); + } else + pci_restore_state(psdev->dev); + + /* Disable the device */ xen_pcibk_reset_device(psdev->dev); + + kfree(dev_data); + pci_set_drvdata(psdev->dev, NULL); + + /* Clean-up the device */ xen_pcibk_config_free_dyn_fields(psdev->dev); xen_pcibk_config_free_dev(psdev->dev); - kfree(pci_get_drvdata(psdev->dev)); - pci_set_drvdata(psdev->dev, NULL); psdev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED; pci_dev_put(psdev->dev); @@ -231,7 +246,17 @@ void pcistub_put_pci_dev(struct pci_dev *dev) /* Cleanup our device * (so it's ready for the next domain) */ + + /* This is OK - we are running from workqueue context + * and want to inhibit the user from fiddling with 'reset' + */ + pci_reset_function(dev); + pci_restore_state(psdev->dev); + + /* This disables the device. */ xen_pcibk_reset_device(found_psdev->dev); + + /* And cleanup up our emulated fields. */ xen_pcibk_config_free_dyn_fields(found_psdev->dev); xen_pcibk_config_reset_dev(found_psdev->dev); @@ -328,6 +353,16 @@ static int __devinit pcistub_init_device(struct pci_dev *dev) if (err) goto config_release; + dev_dbg(&dev->dev, "reseting (FLR, D3, etc) the device\n"); + __pci_reset_function_locked(dev); + + /* We need the device active to save the state. */ + dev_dbg(&dev->dev, "save state of device\n"); + pci_save_state(dev); + dev_data->pci_saved_state = pci_store_saved_state(dev); + if (!dev_data->pci_saved_state) + dev_err(&dev->dev, "Could not store PCI conf saved state!\n"); + /* Now disable the device (this also ensures some private device * data is setup before we export) */ @@ -884,7 +919,7 @@ static inline int str_to_quirk(const char *buf, int *domain, int *bus, int int err; err = - sscanf(buf, " %04x:%02x:%02x.%1x-%08x:%1x:%08x", domain, bus, slot, + sscanf(buf, " %04x:%02x:%02x.%d-%08x:%1x:%08x", domain, bus, slot, func, reg, size, mask); if (err == 7) return 0; @@ -904,7 +939,7 @@ static int pcistub_device_id_add(int domain, int bus, int slot, int func) pci_dev_id->bus = bus; pci_dev_id->devfn = PCI_DEVFN(slot, func); - pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%01x\n", + pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%d\n", domain, bus, slot, func); spin_lock_irqsave(&device_ids_lock, flags); @@ -934,7 +969,7 @@ static int pcistub_device_id_remove(int domain, int bus, int slot, int func) err = 0; - pr_debug(DRV_NAME ": removed %04x:%02x:%02x.%01x from " + pr_debug(DRV_NAME ": removed %04x:%02x:%02x.%d from " "seize list\n", domain, bus, slot, func); } } @@ -1029,7 +1064,7 @@ static ssize_t pcistub_slot_show(struct device_driver *drv, char *buf) break; count += scnprintf(buf + count, PAGE_SIZE - count, - "%04x:%02x:%02x.%01x\n", + "%04x:%02x:%02x.%d\n", pci_dev_id->domain, pci_dev_id->bus, PCI_SLOT(pci_dev_id->devfn), PCI_FUNC(pci_dev_id->devfn)); diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index e9b4011..a7def01 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -41,6 +41,7 @@ struct xen_pcibk_device { struct xen_pcibk_dev_data { struct list_head config_fields; + struct pci_saved_state *pci_saved_state; unsigned int permissive:1; unsigned int warned_on_write:1; unsigned int enable_intx:1; diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index d5dcf8d..64b11f9 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -206,6 +206,7 @@ static int xen_pcibk_publish_pci_dev(struct xen_pcibk_device *pdev, goto out; } + /* Note: The PV protocol uses %02x, don't change it */ err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, str, "%04x:%02x:%02x.%02x", domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); @@ -229,7 +230,7 @@ static int xen_pcibk_export_device(struct xen_pcibk_device *pdev, err = -EINVAL; xenbus_dev_fatal(pdev->xdev, err, "Couldn't locate PCI device " - "(%04x:%02x:%02x.%01x)! " + "(%04x:%02x:%02x.%d)! " "perhaps already in-use?", domain, bus, slot, func); goto out; @@ -274,7 +275,7 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev, if (!dev) { err = -EINVAL; dev_dbg(&pdev->xdev->dev, "Couldn't locate PCI device " - "(%04x:%02x:%02x.%01x)! not owned by this domain\n", + "(%04x:%02x:%02x.%d)! not owned by this domain\n", domain, bus, slot, func); goto out; } diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 767ff65..146c948 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -488,7 +488,7 @@ static struct attribute *selfballoon_attrs[] = { NULL }; -static struct attribute_group selfballoon_group = { +static const struct attribute_group selfballoon_group = { .name = "selfballoon", .attrs = selfballoon_attrs }; diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 566d2ad..b3e146e 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -569,7 +569,7 @@ int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref, { struct gnttab_map_grant_ref op; - gnttab_set_map_op(&op, (phys_addr_t)vaddr, GNTMAP_host_map, gnt_ref, + gnttab_set_map_op(&op, (unsigned long)vaddr, GNTMAP_host_map, gnt_ref, dev->otherend_id); if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1)) @@ -662,7 +662,7 @@ static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr) goto found; } } - node = NULL; + node = addr = NULL; found: spin_unlock(&xenbus_valloc_lock); @@ -698,7 +698,7 @@ int xenbus_unmap_ring(struct xenbus_device *dev, { struct gnttab_unmap_grant_ref op; - gnttab_set_unmap_op(&op, (phys_addr_t)vaddr, GNTMAP_host_map, handle); + gnttab_set_unmap_op(&op, (unsigned long)vaddr, GNTMAP_host_map, handle); if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1)) BUG(); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 527dc2a..89f7625 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -369,6 +369,10 @@ static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u) goto out; } token++; + if (memchr(token, 0, u->u.msg.len - (token - path)) == NULL) { + rc = -EILSEQ; + goto out; + } if (msg_type == XS_WATCH) { watch = alloc_watch_adapter(path, token); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 3864967..b793723 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -257,11 +257,12 @@ int xenbus_dev_remove(struct device *_dev) DPRINTK("%s", dev->nodename); free_otherend_watch(dev); - free_otherend_details(dev); if (drv->remove) drv->remove(dev); + free_otherend_details(dev); + xenbus_switch_state(dev, XenbusStateClosed); return 0; } diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index 9c57819..f20c5f1 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -53,6 +53,12 @@ static int xenbus_probe_frontend(struct xen_bus_type *bus, const char *type, char *nodename; int err; + /* ignore console/0 */ + if (!strncmp(type, "console", 7) && !strncmp(name, "0", 1)) { + DPRINTK("Ignoring buggy device entry console/0"); + return 0; + } + nodename = kasprintf(GFP_KERNEL, "%s/%s/%s", bus->root, type, name); if (!nodename) return -ENOMEM; |