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(). ... --- kernel/power/suspend.c | 629 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 629 insertions(+) create mode 100644 kernel/power/suspend.c (limited to 'kernel/power/suspend.c') diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c new file mode 100644 index 000000000..fa3bf161d --- /dev/null +++ b/kernel/power/suspend.c @@ -0,0 +1,629 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kernel/power/suspend.c - Suspend to RAM and standby functionality. + * + * Copyright (c) 2003 Patrick Mochel + * Copyright (c) 2003 Open Source Development Lab + * Copyright (c) 2009 Rafael J. Wysocki , Novell Inc. + */ + +#define pr_fmt(fmt) "PM: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "power.h" + +const char * const pm_labels[] = { + [PM_SUSPEND_TO_IDLE] = "freeze", + [PM_SUSPEND_STANDBY] = "standby", + [PM_SUSPEND_MEM] = "mem", +}; +const char *pm_states[PM_SUSPEND_MAX]; +static const char * const mem_sleep_labels[] = { + [PM_SUSPEND_TO_IDLE] = "s2idle", + [PM_SUSPEND_STANDBY] = "shallow", + [PM_SUSPEND_MEM] = "deep", +}; +const char *mem_sleep_states[PM_SUSPEND_MAX]; + +suspend_state_t mem_sleep_current = PM_SUSPEND_TO_IDLE; +suspend_state_t mem_sleep_default = PM_SUSPEND_MAX; +suspend_state_t pm_suspend_target_state; +EXPORT_SYMBOL_GPL(pm_suspend_target_state); + +unsigned int pm_suspend_global_flags; +EXPORT_SYMBOL_GPL(pm_suspend_global_flags); + +static const struct platform_suspend_ops *suspend_ops; +static const struct platform_s2idle_ops *s2idle_ops; +static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head); + +enum s2idle_states __read_mostly s2idle_state; +static DEFINE_RAW_SPINLOCK(s2idle_lock); + +/** + * pm_suspend_default_s2idle - Check if suspend-to-idle is the default suspend. + * + * Return 'true' if suspend-to-idle has been selected as the default system + * suspend method. + */ +bool pm_suspend_default_s2idle(void) +{ + return mem_sleep_current == PM_SUSPEND_TO_IDLE; +} +EXPORT_SYMBOL_GPL(pm_suspend_default_s2idle); + +void s2idle_set_ops(const struct platform_s2idle_ops *ops) +{ + unsigned int sleep_flags; + + sleep_flags = lock_system_sleep(); + s2idle_ops = ops; + unlock_system_sleep(sleep_flags); +} + +static void s2idle_begin(void) +{ + s2idle_state = S2IDLE_STATE_NONE; +} + +static void s2idle_enter(void) +{ + trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, true); + + raw_spin_lock_irq(&s2idle_lock); + if (pm_wakeup_pending()) + goto out; + + s2idle_state = S2IDLE_STATE_ENTER; + raw_spin_unlock_irq(&s2idle_lock); + + cpus_read_lock(); + + /* Push all the CPUs into the idle loop. */ + wake_up_all_idle_cpus(); + /* Make the current CPU wait so it can enter the idle loop too. */ + swait_event_exclusive(s2idle_wait_head, + s2idle_state == S2IDLE_STATE_WAKE); + + cpus_read_unlock(); + + raw_spin_lock_irq(&s2idle_lock); + + out: + s2idle_state = S2IDLE_STATE_NONE; + raw_spin_unlock_irq(&s2idle_lock); + + trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, false); +} + +static void s2idle_loop(void) +{ + pm_pr_dbg("suspend-to-idle\n"); + + /* + * Suspend-to-idle equals: + * frozen processes + suspended devices + idle processors. + * Thus s2idle_enter() should be called right after all devices have + * been suspended. + * + * Wakeups during the noirq suspend of devices may be spurious, so try + * to avoid them upfront. + */ + for (;;) { + if (s2idle_ops && s2idle_ops->wake) { + if (s2idle_ops->wake()) + break; + } else if (pm_wakeup_pending()) { + break; + } + + if (s2idle_ops && s2idle_ops->check) + s2idle_ops->check(); + + s2idle_enter(); + } + + pm_pr_dbg("resume from suspend-to-idle\n"); +} + +void s2idle_wake(void) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&s2idle_lock, flags); + if (s2idle_state > S2IDLE_STATE_NONE) { + s2idle_state = S2IDLE_STATE_WAKE; + swake_up_one(&s2idle_wait_head); + } + raw_spin_unlock_irqrestore(&s2idle_lock, flags); +} +EXPORT_SYMBOL_GPL(s2idle_wake); + +static bool valid_state(suspend_state_t state) +{ + /* + * The PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states require low-level + * support and need to be valid to the low-level implementation. + * + * No ->valid() or ->enter() callback implies that none are valid. + */ + return suspend_ops && suspend_ops->valid && suspend_ops->valid(state) && + suspend_ops->enter; +} + +void __init pm_states_init(void) +{ + /* "mem" and "freeze" are always present in /sys/power/state. */ + pm_states[PM_SUSPEND_MEM] = pm_labels[PM_SUSPEND_MEM]; + pm_states[PM_SUSPEND_TO_IDLE] = pm_labels[PM_SUSPEND_TO_IDLE]; + /* + * Suspend-to-idle should be supported even without any suspend_ops, + * initialize mem_sleep_states[] accordingly here. + */ + mem_sleep_states[PM_SUSPEND_TO_IDLE] = mem_sleep_labels[PM_SUSPEND_TO_IDLE]; +} + +static int __init mem_sleep_default_setup(char *str) +{ + suspend_state_t state; + + for (state = PM_SUSPEND_TO_IDLE; state <= PM_SUSPEND_MEM; state++) + if (mem_sleep_labels[state] && + !strcmp(str, mem_sleep_labels[state])) { + mem_sleep_default = state; + break; + } + + return 1; +} +__setup("mem_sleep_default=", mem_sleep_default_setup); + +/** + * suspend_set_ops - Set the global suspend method table. + * @ops: Suspend operations to use. + */ +void suspend_set_ops(const struct platform_suspend_ops *ops) +{ + unsigned int sleep_flags; + + sleep_flags = lock_system_sleep(); + + suspend_ops = ops; + + if (valid_state(PM_SUSPEND_STANDBY)) { + mem_sleep_states[PM_SUSPEND_STANDBY] = mem_sleep_labels[PM_SUSPEND_STANDBY]; + pm_states[PM_SUSPEND_STANDBY] = pm_labels[PM_SUSPEND_STANDBY]; + if (mem_sleep_default == PM_SUSPEND_STANDBY) + mem_sleep_current = PM_SUSPEND_STANDBY; + } + if (valid_state(PM_SUSPEND_MEM)) { + mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM]; + if (mem_sleep_default >= PM_SUSPEND_MEM) + mem_sleep_current = PM_SUSPEND_MEM; + } + + unlock_system_sleep(sleep_flags); +} +EXPORT_SYMBOL_GPL(suspend_set_ops); + +/** + * suspend_valid_only_mem - Generic memory-only valid callback. + * @state: Target system sleep state. + * + * Platform drivers that implement mem suspend only and only need to check for + * that in their .valid() callback can use this instead of rolling their own + * .valid() callback. + */ +int suspend_valid_only_mem(suspend_state_t state) +{ + return state == PM_SUSPEND_MEM; +} +EXPORT_SYMBOL_GPL(suspend_valid_only_mem); + +static bool sleep_state_supported(suspend_state_t state) +{ + return state == PM_SUSPEND_TO_IDLE || + (valid_state(state) && !cxl_mem_active()); +} + +static int platform_suspend_prepare(suspend_state_t state) +{ + return state != PM_SUSPEND_TO_IDLE && suspend_ops->prepare ? + suspend_ops->prepare() : 0; +} + +static int platform_suspend_prepare_late(suspend_state_t state) +{ + return state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->prepare ? + s2idle_ops->prepare() : 0; +} + +static int platform_suspend_prepare_noirq(suspend_state_t state) +{ + if (state == PM_SUSPEND_TO_IDLE) + return s2idle_ops && s2idle_ops->prepare_late ? + s2idle_ops->prepare_late() : 0; + + return suspend_ops->prepare_late ? suspend_ops->prepare_late() : 0; +} + +static void platform_resume_noirq(suspend_state_t state) +{ + if (state == PM_SUSPEND_TO_IDLE) { + if (s2idle_ops && s2idle_ops->restore_early) + s2idle_ops->restore_early(); + } else if (suspend_ops->wake) { + suspend_ops->wake(); + } +} + +static void platform_resume_early(suspend_state_t state) +{ + if (state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->restore) + s2idle_ops->restore(); +} + +static void platform_resume_finish(suspend_state_t state) +{ + if (state != PM_SUSPEND_TO_IDLE && suspend_ops->finish) + suspend_ops->finish(); +} + +static int platform_suspend_begin(suspend_state_t state) +{ + if (state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->begin) + return s2idle_ops->begin(); + else if (suspend_ops && suspend_ops->begin) + return suspend_ops->begin(state); + else + return 0; +} + +static void platform_resume_end(suspend_state_t state) +{ + if (state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->end) + s2idle_ops->end(); + else if (suspend_ops && suspend_ops->end) + suspend_ops->end(); +} + +static void platform_recover(suspend_state_t state) +{ + if (state != PM_SUSPEND_TO_IDLE && suspend_ops->recover) + suspend_ops->recover(); +} + +static bool platform_suspend_again(suspend_state_t state) +{ + return state != PM_SUSPEND_TO_IDLE && suspend_ops->suspend_again ? + suspend_ops->suspend_again() : false; +} + +#ifdef CONFIG_PM_DEBUG +static unsigned int pm_test_delay = 5; +module_param(pm_test_delay, uint, 0644); +MODULE_PARM_DESC(pm_test_delay, + "Number of seconds to wait before resuming from suspend test"); +#endif + +static int suspend_test(int level) +{ +#ifdef CONFIG_PM_DEBUG + if (pm_test_level == level) { + pr_info("suspend debug: Waiting for %d second(s).\n", + pm_test_delay); + mdelay(pm_test_delay * 1000); + return 1; + } +#endif /* !CONFIG_PM_DEBUG */ + return 0; +} + +/** + * suspend_prepare - Prepare for entering system sleep state. + * @state: Target system sleep state. + * + * Common code run for every system sleep state that can be entered (except for + * hibernation). Run suspend notifiers, allocate the "suspend" console and + * freeze processes. + */ +static int suspend_prepare(suspend_state_t state) +{ + int error; + + if (!sleep_state_supported(state)) + return -EPERM; + + pm_prepare_console(); + + error = pm_notifier_call_chain_robust(PM_SUSPEND_PREPARE, PM_POST_SUSPEND); + if (error) + goto Restore; + + trace_suspend_resume(TPS("freeze_processes"), 0, true); + error = suspend_freeze_processes(); + trace_suspend_resume(TPS("freeze_processes"), 0, false); + if (!error) + return 0; + + suspend_stats.failed_freeze++; + dpm_save_failed_step(SUSPEND_FREEZE); + pm_notifier_call_chain(PM_POST_SUSPEND); + Restore: + pm_restore_console(); + return error; +} + +/* default implementation */ +void __weak arch_suspend_disable_irqs(void) +{ + local_irq_disable(); +} + +/* default implementation */ +void __weak arch_suspend_enable_irqs(void) +{ + local_irq_enable(); +} + +/** + * suspend_enter - Make the system enter the given sleep state. + * @state: System sleep state to enter. + * @wakeup: Returns information that the sleep state should not be re-entered. + * + * This function should be called after devices have been suspended. + */ +static int suspend_enter(suspend_state_t state, bool *wakeup) +{ + int error; + + error = platform_suspend_prepare(state); + if (error) + goto Platform_finish; + + error = dpm_suspend_late(PMSG_SUSPEND); + if (error) { + pr_err("late suspend of devices failed\n"); + goto Platform_finish; + } + error = platform_suspend_prepare_late(state); + if (error) + goto Devices_early_resume; + + error = dpm_suspend_noirq(PMSG_SUSPEND); + if (error) { + pr_err("noirq suspend of devices failed\n"); + goto Platform_early_resume; + } + error = platform_suspend_prepare_noirq(state); + if (error) + goto Platform_wake; + + if (suspend_test(TEST_PLATFORM)) + goto Platform_wake; + + if (state == PM_SUSPEND_TO_IDLE) { + s2idle_loop(); + goto Platform_wake; + } + + error = pm_sleep_disable_secondary_cpus(); + if (error || suspend_test(TEST_CPUS)) + goto Enable_cpus; + + arch_suspend_disable_irqs(); + BUG_ON(!irqs_disabled()); + + system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (!error) { + *wakeup = pm_wakeup_pending(); + if (!(suspend_test(TEST_CORE) || *wakeup)) { + trace_suspend_resume(TPS("machine_suspend"), + state, true); + error = suspend_ops->enter(state); + trace_suspend_resume(TPS("machine_suspend"), + state, false); + } else if (*wakeup) { + error = -EBUSY; + } + syscore_resume(); + } + + system_state = SYSTEM_RUNNING; + + arch_suspend_enable_irqs(); + BUG_ON(irqs_disabled()); + + Enable_cpus: + pm_sleep_enable_secondary_cpus(); + + Platform_wake: + platform_resume_noirq(state); + dpm_resume_noirq(PMSG_RESUME); + + Platform_early_resume: + platform_resume_early(state); + + Devices_early_resume: + dpm_resume_early(PMSG_RESUME); + + Platform_finish: + platform_resume_finish(state); + return error; +} + +/** + * suspend_devices_and_enter - Suspend devices and enter system sleep state. + * @state: System sleep state to enter. + */ +int suspend_devices_and_enter(suspend_state_t state) +{ + int error; + bool wakeup = false; + + if (!sleep_state_supported(state)) + return -ENOSYS; + + pm_suspend_target_state = state; + + if (state == PM_SUSPEND_TO_IDLE) + pm_set_suspend_no_platform(); + + error = platform_suspend_begin(state); + if (error) + goto Close; + + suspend_console(); + suspend_test_start(); + error = dpm_suspend_start(PMSG_SUSPEND); + if (error) { + pr_err("Some devices failed to suspend, or early wake event detected\n"); + goto Recover_platform; + } + suspend_test_finish("suspend devices"); + if (suspend_test(TEST_DEVICES)) + goto Recover_platform; + + do { + error = suspend_enter(state, &wakeup); + } while (!error && !wakeup && platform_suspend_again(state)); + + Resume_devices: + suspend_test_start(); + dpm_resume_end(PMSG_RESUME); + suspend_test_finish("resume devices"); + trace_suspend_resume(TPS("resume_console"), state, true); + resume_console(); + trace_suspend_resume(TPS("resume_console"), state, false); + + Close: + platform_resume_end(state); + pm_suspend_target_state = PM_SUSPEND_ON; + return error; + + Recover_platform: + platform_recover(state); + goto Resume_devices; +} + +/** + * suspend_finish - Clean up before finishing the suspend sequence. + * + * Call platform code to clean up, restart processes, and free the console that + * we've allocated. This routine is not called for hibernation. + */ +static void suspend_finish(void) +{ + suspend_thaw_processes(); + pm_notifier_call_chain(PM_POST_SUSPEND); + pm_restore_console(); +} + +/** + * enter_state - Do common work needed to enter system sleep state. + * @state: System sleep state to enter. + * + * Make sure that no one else is trying to put the system into a sleep state. + * Fail if that's not the case. Otherwise, prepare for system suspend, make the + * system enter the given sleep state and clean up after wakeup. + */ +static int enter_state(suspend_state_t state) +{ + int error; + + trace_suspend_resume(TPS("suspend_enter"), state, true); + if (state == PM_SUSPEND_TO_IDLE) { +#ifdef CONFIG_PM_DEBUG + if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { + pr_warn("Unsupported test mode for suspend to idle, please choose none/freezer/devices/platform.\n"); + return -EAGAIN; + } +#endif + } else if (!valid_state(state)) { + return -EINVAL; + } + if (!mutex_trylock(&system_transition_mutex)) + return -EBUSY; + + if (state == PM_SUSPEND_TO_IDLE) + s2idle_begin(); + + if (sync_on_suspend_enabled) { + trace_suspend_resume(TPS("sync_filesystems"), 0, true); + ksys_sync_helper(); + trace_suspend_resume(TPS("sync_filesystems"), 0, false); + } + + pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]); + pm_suspend_clear_flags(); + error = suspend_prepare(state); + if (error) + goto Unlock; + + if (suspend_test(TEST_FREEZER)) + goto Finish; + + trace_suspend_resume(TPS("suspend_enter"), state, false); + pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]); + pm_restrict_gfp_mask(); + error = suspend_devices_and_enter(state); + pm_restore_gfp_mask(); + + Finish: + events_check_enabled = false; + pm_pr_dbg("Finishing wakeup.\n"); + suspend_finish(); + Unlock: + mutex_unlock(&system_transition_mutex); + return error; +} + +/** + * pm_suspend - Externally visible function for suspending the system. + * @state: System sleep state to enter. + * + * Check if the value of @state represents one of the supported states, + * execute enter_state() and update system suspend statistics. + */ +int pm_suspend(suspend_state_t state) +{ + int error; + + if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) + return -EINVAL; + + pr_info("suspend entry (%s)\n", mem_sleep_labels[state]); + error = enter_state(state); + if (error) { + suspend_stats.fail++; + dpm_save_failed_errno(error); + } else { + suspend_stats.success++; + } + pr_info("suspend exit\n"); + return error; +} +EXPORT_SYMBOL(pm_suspend); -- cgit v1.2.3