aboutsummaryrefslogtreecommitdiff
path: root/kernel/time/itimer.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /kernel/time/itimer.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
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(). ...
Diffstat (limited to '')
-rw-r--r--kernel/time/itimer.c403
1 files changed, 403 insertions, 0 deletions
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
new file mode 100644
index 000000000..00629e658
--- /dev/null
+++ b/kernel/time/itimer.c
@@ -0,0 +1,403 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 1992 Darren Senn
+ */
+
+/* These are all the functions necessary to implement itimers */
+
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/syscalls.h>
+#include <linux/time.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/cputime.h>
+#include <linux/posix-timers.h>
+#include <linux/hrtimer.h>
+#include <trace/events/timer.h>
+#include <linux/compat.h>
+
+#include <linux/uaccess.h>
+
+/**
+ * itimer_get_remtime - get remaining time for the timer
+ *
+ * @timer: the timer to read
+ *
+ * Returns the delta between the expiry time and now, which can be
+ * less than zero or 1usec for an pending expired timer
+ */
+static struct timespec64 itimer_get_remtime(struct hrtimer *timer)
+{
+ ktime_t rem = __hrtimer_get_remaining(timer, true);
+
+ /*
+ * Racy but safe: if the itimer expires after the above
+ * hrtimer_get_remtime() call but before this condition
+ * then we return 0 - which is correct.
+ */
+ if (hrtimer_active(timer)) {
+ if (rem <= 0)
+ rem = NSEC_PER_USEC;
+ } else
+ rem = 0;
+
+ return ktime_to_timespec64(rem);
+}
+
+static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+ struct itimerspec64 *const value)
+{
+ u64 val, interval;
+ struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+ spin_lock_irq(&tsk->sighand->siglock);
+
+ val = it->expires;
+ interval = it->incr;
+ if (val) {
+ u64 t, samples[CPUCLOCK_MAX];
+
+ thread_group_sample_cputime(tsk, samples);
+ t = samples[clock_id];
+
+ if (val < t)
+ /* about to fire */
+ val = TICK_NSEC;
+ else
+ val -= t;
+ }
+
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ value->it_value = ns_to_timespec64(val);
+ value->it_interval = ns_to_timespec64(interval);
+}
+
+static int do_getitimer(int which, struct itimerspec64 *value)
+{
+ struct task_struct *tsk = current;
+
+ switch (which) {
+ case ITIMER_REAL:
+ spin_lock_irq(&tsk->sighand->siglock);
+ value->it_value = itimer_get_remtime(&tsk->signal->real_timer);
+ value->it_interval =
+ ktime_to_timespec64(tsk->signal->it_real_incr);
+ spin_unlock_irq(&tsk->sighand->siglock);
+ break;
+ case ITIMER_VIRTUAL:
+ get_cpu_itimer(tsk, CPUCLOCK_VIRT, value);
+ break;
+ case ITIMER_PROF:
+ get_cpu_itimer(tsk, CPUCLOCK_PROF, value);
+ break;
+ default:
+ return(-EINVAL);
+ }
+ return 0;
+}
+
+static int put_itimerval(struct __kernel_old_itimerval __user *o,
+ const struct itimerspec64 *i)
+{
+ struct __kernel_old_itimerval v;
+
+ v.it_interval.tv_sec = i->it_interval.tv_sec;
+ v.it_interval.tv_usec = i->it_interval.tv_nsec / NSEC_PER_USEC;
+ v.it_value.tv_sec = i->it_value.tv_sec;
+ v.it_value.tv_usec = i->it_value.tv_nsec / NSEC_PER_USEC;
+ return copy_to_user(o, &v, sizeof(struct __kernel_old_itimerval)) ? -EFAULT : 0;
+}
+
+
+SYSCALL_DEFINE2(getitimer, int, which, struct __kernel_old_itimerval __user *, value)
+{
+ struct itimerspec64 get_buffer;
+ int error = do_getitimer(which, &get_buffer);
+
+ if (!error && put_itimerval(value, &get_buffer))
+ error = -EFAULT;
+ return error;
+}
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
+struct old_itimerval32 {
+ struct old_timeval32 it_interval;
+ struct old_timeval32 it_value;
+};
+
+static int put_old_itimerval32(struct old_itimerval32 __user *o,
+ const struct itimerspec64 *i)
+{
+ struct old_itimerval32 v32;
+
+ v32.it_interval.tv_sec = i->it_interval.tv_sec;
+ v32.it_interval.tv_usec = i->it_interval.tv_nsec / NSEC_PER_USEC;
+ v32.it_value.tv_sec = i->it_value.tv_sec;
+ v32.it_value.tv_usec = i->it_value.tv_nsec / NSEC_PER_USEC;
+ return copy_to_user(o, &v32, sizeof(struct old_itimerval32)) ? -EFAULT : 0;
+}
+
+COMPAT_SYSCALL_DEFINE2(getitimer, int, which,
+ struct old_itimerval32 __user *, value)
+{
+ struct itimerspec64 get_buffer;
+ int error = do_getitimer(which, &get_buffer);
+
+ if (!error && put_old_itimerval32(value, &get_buffer))
+ error = -EFAULT;
+ return error;
+}
+#endif
+
+/*
+ * The timer is automagically restarted, when interval != 0
+ */
+enum hrtimer_restart it_real_fn(struct hrtimer *timer)
+{
+ struct signal_struct *sig =
+ container_of(timer, struct signal_struct, real_timer);
+ struct pid *leader_pid = sig->pids[PIDTYPE_TGID];
+
+ trace_itimer_expire(ITIMER_REAL, leader_pid, 0);
+ kill_pid_info(SIGALRM, SEND_SIG_PRIV, leader_pid);
+
+ return HRTIMER_NORESTART;
+}
+
+static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+ const struct itimerspec64 *const value,
+ struct itimerspec64 *const ovalue)
+{
+ u64 oval, nval, ointerval, ninterval;
+ struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+ nval = timespec64_to_ns(&value->it_value);
+ ninterval = timespec64_to_ns(&value->it_interval);
+
+ spin_lock_irq(&tsk->sighand->siglock);
+
+ oval = it->expires;
+ ointerval = it->incr;
+ if (oval || nval) {
+ if (nval > 0)
+ nval += TICK_NSEC;
+ set_process_cpu_timer(tsk, clock_id, &nval, &oval);
+ }
+ it->expires = nval;
+ it->incr = ninterval;
+ trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
+ ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
+
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ if (ovalue) {
+ ovalue->it_value = ns_to_timespec64(oval);
+ ovalue->it_interval = ns_to_timespec64(ointerval);
+ }
+}
+
+/*
+ * Returns true if the timeval is in canonical form
+ */
+#define timeval_valid(t) \
+ (((t)->tv_sec >= 0) && (((unsigned long) (t)->tv_usec) < USEC_PER_SEC))
+
+static int do_setitimer(int which, struct itimerspec64 *value,
+ struct itimerspec64 *ovalue)
+{
+ struct task_struct *tsk = current;
+ struct hrtimer *timer;
+ ktime_t expires;
+
+ switch (which) {
+ case ITIMER_REAL:
+again:
+ spin_lock_irq(&tsk->sighand->siglock);
+ timer = &tsk->signal->real_timer;
+ if (ovalue) {
+ ovalue->it_value = itimer_get_remtime(timer);
+ ovalue->it_interval
+ = ktime_to_timespec64(tsk->signal->it_real_incr);
+ }
+ /* We are sharing ->siglock with it_real_fn() */
+ if (hrtimer_try_to_cancel(timer) < 0) {
+ spin_unlock_irq(&tsk->sighand->siglock);
+ hrtimer_cancel_wait_running(timer);
+ goto again;
+ }
+ expires = timespec64_to_ktime(value->it_value);
+ if (expires != 0) {
+ tsk->signal->it_real_incr =
+ timespec64_to_ktime(value->it_interval);
+ hrtimer_start(timer, expires, HRTIMER_MODE_REL);
+ } else
+ tsk->signal->it_real_incr = 0;
+
+ trace_itimer_state(ITIMER_REAL, value, 0);
+ spin_unlock_irq(&tsk->sighand->siglock);
+ break;
+ case ITIMER_VIRTUAL:
+ set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue);
+ break;
+ case ITIMER_PROF:
+ set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue);
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_SECURITY_SELINUX
+void clear_itimer(void)
+{
+ struct itimerspec64 v = {};
+ int i;
+
+ for (i = 0; i < 3; i++)
+ do_setitimer(i, &v, NULL);
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_ALARM
+
+/**
+ * alarm_setitimer - set alarm in seconds
+ *
+ * @seconds: number of seconds until alarm
+ * 0 disables the alarm
+ *
+ * Returns the remaining time in seconds of a pending timer or 0 when
+ * the timer is not active.
+ *
+ * On 32 bit machines the seconds value is limited to (INT_MAX/2) to avoid
+ * negative timeval settings which would cause immediate expiry.
+ */
+static unsigned int alarm_setitimer(unsigned int seconds)
+{
+ struct itimerspec64 it_new, it_old;
+
+#if BITS_PER_LONG < 64
+ if (seconds > INT_MAX)
+ seconds = INT_MAX;
+#endif
+ it_new.it_value.tv_sec = seconds;
+ it_new.it_value.tv_nsec = 0;
+ it_new.it_interval.tv_sec = it_new.it_interval.tv_nsec = 0;
+
+ do_setitimer(ITIMER_REAL, &it_new, &it_old);
+
+ /*
+ * We can't return 0 if we have an alarm pending ... And we'd
+ * better return too much than too little anyway
+ */
+ if ((!it_old.it_value.tv_sec && it_old.it_value.tv_nsec) ||
+ it_old.it_value.tv_nsec >= (NSEC_PER_SEC / 2))
+ it_old.it_value.tv_sec++;
+
+ return it_old.it_value.tv_sec;
+}
+
+/*
+ * For backwards compatibility? This can be done in libc so Alpha
+ * and all newer ports shouldn't need it.
+ */
+SYSCALL_DEFINE1(alarm, unsigned int, seconds)
+{
+ return alarm_setitimer(seconds);
+}
+
+#endif
+
+static int get_itimerval(struct itimerspec64 *o, const struct __kernel_old_itimerval __user *i)
+{
+ struct __kernel_old_itimerval v;
+
+ if (copy_from_user(&v, i, sizeof(struct __kernel_old_itimerval)))
+ return -EFAULT;
+
+ /* Validate the timevals in value. */
+ if (!timeval_valid(&v.it_value) ||
+ !timeval_valid(&v.it_interval))
+ return -EINVAL;
+
+ o->it_interval.tv_sec = v.it_interval.tv_sec;
+ o->it_interval.tv_nsec = v.it_interval.tv_usec * NSEC_PER_USEC;
+ o->it_value.tv_sec = v.it_value.tv_sec;
+ o->it_value.tv_nsec = v.it_value.tv_usec * NSEC_PER_USEC;
+ return 0;
+}
+
+SYSCALL_DEFINE3(setitimer, int, which, struct __kernel_old_itimerval __user *, value,
+ struct __kernel_old_itimerval __user *, ovalue)
+{
+ struct itimerspec64 set_buffer, get_buffer;
+ int error;
+
+ if (value) {
+ error = get_itimerval(&set_buffer, value);
+ if (error)
+ return error;
+ } else {
+ memset(&set_buffer, 0, sizeof(set_buffer));
+ printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+ " Misfeature support will be removed\n",
+ current->comm);
+ }
+
+ error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
+ if (error || !ovalue)
+ return error;
+
+ if (put_itimerval(ovalue, &get_buffer))
+ return -EFAULT;
+ return 0;
+}
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
+static int get_old_itimerval32(struct itimerspec64 *o, const struct old_itimerval32 __user *i)
+{
+ struct old_itimerval32 v32;
+
+ if (copy_from_user(&v32, i, sizeof(struct old_itimerval32)))
+ return -EFAULT;
+
+ /* Validate the timevals in value. */
+ if (!timeval_valid(&v32.it_value) ||
+ !timeval_valid(&v32.it_interval))
+ return -EINVAL;
+
+ o->it_interval.tv_sec = v32.it_interval.tv_sec;
+ o->it_interval.tv_nsec = v32.it_interval.tv_usec * NSEC_PER_USEC;
+ o->it_value.tv_sec = v32.it_value.tv_sec;
+ o->it_value.tv_nsec = v32.it_value.tv_usec * NSEC_PER_USEC;
+ return 0;
+}
+
+COMPAT_SYSCALL_DEFINE3(setitimer, int, which,
+ struct old_itimerval32 __user *, value,
+ struct old_itimerval32 __user *, ovalue)
+{
+ struct itimerspec64 set_buffer, get_buffer;
+ int error;
+
+ if (value) {
+ error = get_old_itimerval32(&set_buffer, value);
+ if (error)
+ return error;
+ } else {
+ memset(&set_buffer, 0, sizeof(set_buffer));
+ printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+ " Misfeature support will be removed\n",
+ current->comm);
+ }
+
+ error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
+ if (error || !ovalue)
+ return error;
+ if (put_old_itimerval32(ovalue, &get_buffer))
+ return -EFAULT;
+ return 0;
+}
+#endif