From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- drivers/xen/xen-acpi-processor.c | 604 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 604 insertions(+) create mode 100644 drivers/xen/xen-acpi-processor.c (limited to 'drivers/xen/xen-acpi-processor.c') diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c new file mode 100644 index 000000000..9cb61db67 --- /dev/null +++ b/drivers/xen/xen-acpi-processor.c @@ -0,0 +1,604 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2012 by Oracle Inc + * Author: Konrad Rzeszutek Wilk + * + * This code borrows ideas from + * https://lore.kernel.org/lkml/1322673664-14642-6-git-send-email-konrad.wilk@oracle.com + * so many thanks go to Kevin Tian + * and Yu Ke . + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +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 *acpi_id_present; +/* And if there is an _CST definition (or a PBLK) for the ACPI IDs */ +static unsigned long *acpi_id_cst_present; +/* Which ACPI P-State dependencies for a enumerated processor */ +static struct acpi_psd_package *acpi_psd; + +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->dpcnt = 0; + set_xen_guest_handle(dst_cx->dp, NULL); + } + if (!ok) { + pr_debug("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_platform_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 if ((ret != -EINVAL) && (ret != -ENOSYS)) + /* 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_err("(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("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_platform_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) && (ret != -ENOSYS)) + /* 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("(_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_platform_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_platform_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("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 +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; + } + if (invalid_phys_cpuid(acpi_get_phys_id(handle, + acpi_type == ACPI_TYPE_DEVICE, + acpi_id))) { + pr_debug("CPU with ACPI ID %u is unavailable\n", acpi_id); + 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("max acpi id %u, trying to set %u\n", + nr_acpi_bits - 1, acpi_id); + return AE_OK; + } + /* OK, There is a ACPI Processor object */ + __set_bit(acpi_id, acpi_id_present); + + pr_debug("ACPI CPU%u w/ PBLK:0x%lx\n", acpi_id, (unsigned long)pblk); + + /* It has P-state dependencies */ + if (!acpi_processor_get_psd(handle, &acpi_psd[acpi_id])) { + pr_debug("ACPI CPU%u w/ PST:coord_type = %llu domain = %llu\n", + acpi_id, acpi_psd[acpi_id].coord_type, + acpi_psd[acpi_id].domain); + } + + 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 check_acpi_ids(struct acpi_processor *pr_backup) +{ + + if (!pr_backup) + return -ENODEV; + + if (acpi_id_present && acpi_id_cst_present) + /* OK, done this once .. skip to uploading */ + goto upload; + + /* All online CPUs have been processed at this stage. Now verify + * whether in fact "online CPUs" == physical CPUs. + */ + acpi_id_present = bitmap_zalloc(nr_acpi_bits, GFP_KERNEL); + if (!acpi_id_present) + return -ENOMEM; + + acpi_id_cst_present = bitmap_zalloc(nr_acpi_bits, GFP_KERNEL); + if (!acpi_id_cst_present) { + bitmap_free(acpi_id_present); + return -ENOMEM; + } + + acpi_psd = kcalloc(nr_acpi_bits, sizeof(struct acpi_psd_package), + GFP_KERNEL); + if (!acpi_psd) { + bitmap_free(acpi_id_present); + bitmap_free(acpi_id_cst_present); + return -ENOMEM; + } + + acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, + read_acpi_id, NULL, NULL, NULL); + acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, read_acpi_id, NULL, NULL); + +upload: + 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); + /* num_entries is non-zero if we evaluated _PSD */ + if (acpi_psd[i].num_entries) { + memcpy(&pr_backup->performance->domain_info, + &acpi_psd[i], + sizeof(struct acpi_psd_package)); + } + (void)upload_pm_data(pr_backup); + } + } + + return 0; +} + +/* 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) +{ + 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 xen_upload_processor_pm_data(void) +{ + struct acpi_processor *pr_backup = NULL; + int i; + int rc = 0; + + pr_info("Uploading Xen processor PM info\n"); + + 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); + if (pr_backup) + memcpy(pr_backup, _pr, sizeof(struct acpi_processor)); + } + (void)upload_pm_data(_pr); + } + + rc = check_acpi_ids(pr_backup); + kfree(pr_backup); + + return rc; +} + +static void xen_acpi_processor_resume_worker(struct work_struct *dummy) +{ + int rc; + + bitmap_zero(acpi_ids_done, nr_acpi_bits); + + rc = xen_upload_processor_pm_data(); + if (rc != 0) + pr_info("ACPI data upload failed, error = %d\n", rc); +} + +static void xen_acpi_processor_resume(void) +{ + static DECLARE_WORK(wq, xen_acpi_processor_resume_worker); + + /* + * xen_upload_processor_pm_data() calls non-atomic code. + * However, the context for xen_acpi_processor_resume is syscore + * with only the boot CPU online and in an atomic context. + * + * So defer the upload for some point safer. + */ + schedule_work(&wq); +} + +static struct syscore_ops xap_syscore_ops = { + .resume = xen_acpi_processor_resume, +}; + +static int __init xen_acpi_processor_init(void) +{ + int i; + int rc; + + if (!xen_initial_domain()) + return -ENODEV; + + nr_acpi_bits = get_max_acpi_id() + 1; + acpi_ids_done = bitmap_zalloc(nr_acpi_bits, GFP_KERNEL); + if (!acpi_ids_done) + return -ENOMEM; + + acpi_perf_data = alloc_percpu(struct acpi_processor_performance); + if (!acpi_perf_data) { + pr_debug("Memory allocation error for acpi_perf_data\n"); + bitmap_free(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 *pr; + struct acpi_processor_performance *perf; + + pr = per_cpu(processors, i); + perf = per_cpu_ptr(acpi_perf_data, i); + if (!pr) + continue; + + pr->performance = perf; + rc = acpi_processor_get_performance_info(pr); + if (rc) + goto err_out; + } + + rc = xen_upload_processor_pm_data(); + if (rc) + goto err_unregister; + + register_syscore_ops(&xap_syscore_ops); + + return 0; +err_unregister: + for_each_possible_cpu(i) + acpi_processor_unregister_performance(i); + +err_out: + /* Freeing a NULL pointer is OK: alloc_percpu zeroes. */ + free_acpi_perf_data(); + bitmap_free(acpi_ids_done); + return rc; +} +static void __exit xen_acpi_processor_exit(void) +{ + int i; + + unregister_syscore_ops(&xap_syscore_ops); + bitmap_free(acpi_ids_done); + bitmap_free(acpi_id_present); + bitmap_free(acpi_id_cst_present); + kfree(acpi_psd); + for_each_possible_cpu(i) + acpi_processor_unregister_performance(i); + + free_acpi_perf_data(); +} + +MODULE_AUTHOR("Konrad Rzeszutek Wilk "); +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); -- cgit v1.2.3