aboutsummaryrefslogtreecommitdiff
path: root/arch/s390/kernel/processor.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 /arch/s390/kernel/processor.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 'arch/s390/kernel/processor.c')
-rw-r--r--arch/s390/kernel/processor.c384
1 files changed, 384 insertions, 0 deletions
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
new file mode 100644
index 000000000..a194611ba
--- /dev/null
+++ b/arch/s390/kernel/processor.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2008
+ * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ */
+
+#define KMSG_COMPONENT "cpu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/stop_machine.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/random.h>
+#include <linux/sched/mm.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/mm_types.h>
+#include <linux/delay.h>
+#include <linux/cpu.h>
+
+#include <asm/diag.h>
+#include <asm/facility.h>
+#include <asm/elf.h>
+#include <asm/lowcore.h>
+#include <asm/param.h>
+#include <asm/sclp.h>
+#include <asm/smp.h>
+
+unsigned long __read_mostly elf_hwcap;
+char elf_platform[ELF_PLATFORM_SIZE];
+
+struct cpu_info {
+ unsigned int cpu_mhz_dynamic;
+ unsigned int cpu_mhz_static;
+ struct cpuid cpu_id;
+};
+
+static DEFINE_PER_CPU(struct cpu_info, cpu_info);
+static DEFINE_PER_CPU(int, cpu_relax_retry);
+
+static bool machine_has_cpu_mhz;
+
+void __init cpu_detect_mhz_feature(void)
+{
+ if (test_facility(34) && __ecag(ECAG_CPU_ATTRIBUTE, 0) != -1UL)
+ machine_has_cpu_mhz = true;
+}
+
+static void update_cpu_mhz(void *arg)
+{
+ unsigned long mhz;
+ struct cpu_info *c;
+
+ mhz = __ecag(ECAG_CPU_ATTRIBUTE, 0);
+ c = this_cpu_ptr(&cpu_info);
+ c->cpu_mhz_dynamic = mhz >> 32;
+ c->cpu_mhz_static = mhz & 0xffffffff;
+}
+
+void s390_update_cpu_mhz(void)
+{
+ s390_adjust_jiffies();
+ if (machine_has_cpu_mhz)
+ on_each_cpu(update_cpu_mhz, NULL, 0);
+}
+
+void notrace stop_machine_yield(const struct cpumask *cpumask)
+{
+ int cpu, this_cpu;
+
+ this_cpu = smp_processor_id();
+ if (__this_cpu_inc_return(cpu_relax_retry) >= spin_retry) {
+ __this_cpu_write(cpu_relax_retry, 0);
+ cpu = cpumask_next_wrap(this_cpu, cpumask, this_cpu, false);
+ if (cpu >= nr_cpu_ids)
+ return;
+ if (arch_vcpu_is_preempted(cpu))
+ smp_yield_cpu(cpu);
+ }
+}
+
+/*
+ * cpu_init - initializes state that is per-CPU.
+ */
+void cpu_init(void)
+{
+ struct cpuid *id = this_cpu_ptr(&cpu_info.cpu_id);
+
+ get_cpu_id(id);
+ if (machine_has_cpu_mhz)
+ update_cpu_mhz(NULL);
+ mmgrab(&init_mm);
+ current->active_mm = &init_mm;
+ BUG_ON(current->mm);
+ enter_lazy_tlb(&init_mm, current);
+}
+
+static void show_facilities(struct seq_file *m)
+{
+ unsigned int bit;
+
+ seq_puts(m, "facilities :");
+ for_each_set_bit_inv(bit, (long *)&stfle_fac_list, MAX_FACILITY_BIT)
+ seq_printf(m, " %d", bit);
+ seq_putc(m, '\n');
+}
+
+static void show_cpu_summary(struct seq_file *m, void *v)
+{
+ static const char *hwcap_str[] = {
+ [HWCAP_NR_ESAN3] = "esan3",
+ [HWCAP_NR_ZARCH] = "zarch",
+ [HWCAP_NR_STFLE] = "stfle",
+ [HWCAP_NR_MSA] = "msa",
+ [HWCAP_NR_LDISP] = "ldisp",
+ [HWCAP_NR_EIMM] = "eimm",
+ [HWCAP_NR_DFP] = "dfp",
+ [HWCAP_NR_HPAGE] = "edat",
+ [HWCAP_NR_ETF3EH] = "etf3eh",
+ [HWCAP_NR_HIGH_GPRS] = "highgprs",
+ [HWCAP_NR_TE] = "te",
+ [HWCAP_NR_VXRS] = "vx",
+ [HWCAP_NR_VXRS_BCD] = "vxd",
+ [HWCAP_NR_VXRS_EXT] = "vxe",
+ [HWCAP_NR_GS] = "gs",
+ [HWCAP_NR_VXRS_EXT2] = "vxe2",
+ [HWCAP_NR_VXRS_PDE] = "vxp",
+ [HWCAP_NR_SORT] = "sort",
+ [HWCAP_NR_DFLT] = "dflt",
+ [HWCAP_NR_VXRS_PDE2] = "vxp2",
+ [HWCAP_NR_NNPA] = "nnpa",
+ [HWCAP_NR_PCI_MIO] = "pcimio",
+ [HWCAP_NR_SIE] = "sie",
+ };
+ int i, cpu;
+
+ BUILD_BUG_ON(ARRAY_SIZE(hwcap_str) != HWCAP_NR_MAX);
+ seq_printf(m, "vendor_id : IBM/S390\n"
+ "# processors : %i\n"
+ "bogomips per cpu: %lu.%02lu\n",
+ num_online_cpus(), loops_per_jiffy/(500000/HZ),
+ (loops_per_jiffy/(5000/HZ))%100);
+ seq_printf(m, "max thread id : %d\n", smp_cpu_mtid);
+ seq_puts(m, "features\t: ");
+ for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
+ if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
+ seq_printf(m, "%s ", hwcap_str[i]);
+ seq_puts(m, "\n");
+ show_facilities(m);
+ show_cacheinfo(m);
+ for_each_online_cpu(cpu) {
+ struct cpuid *id = &per_cpu(cpu_info.cpu_id, cpu);
+
+ seq_printf(m, "processor %d: "
+ "version = %02X, "
+ "identification = %06X, "
+ "machine = %04X\n",
+ cpu, id->version, id->ident, id->machine);
+ }
+}
+
+static int __init setup_hwcaps(void)
+{
+ /* instructions named N3, "backported" to esa-mode */
+ elf_hwcap |= HWCAP_ESAN3;
+
+ /* z/Architecture mode active */
+ elf_hwcap |= HWCAP_ZARCH;
+
+ /* store-facility-list-extended */
+ if (test_facility(7))
+ elf_hwcap |= HWCAP_STFLE;
+
+ /* message-security assist */
+ if (test_facility(17))
+ elf_hwcap |= HWCAP_MSA;
+
+ /* long-displacement */
+ if (test_facility(19))
+ elf_hwcap |= HWCAP_LDISP;
+
+ /* extended-immediate */
+ elf_hwcap |= HWCAP_EIMM;
+
+ /* extended-translation facility 3 enhancement */
+ if (test_facility(22) && test_facility(30))
+ elf_hwcap |= HWCAP_ETF3EH;
+
+ /* decimal floating point & perform floating point operation */
+ if (test_facility(42) && test_facility(44))
+ elf_hwcap |= HWCAP_DFP;
+
+ /* huge page support */
+ if (MACHINE_HAS_EDAT1)
+ elf_hwcap |= HWCAP_HPAGE;
+
+ /* 64-bit register support for 31-bit processes */
+ elf_hwcap |= HWCAP_HIGH_GPRS;
+
+ /* transactional execution */
+ if (MACHINE_HAS_TE)
+ elf_hwcap |= HWCAP_TE;
+
+ /*
+ * Vector extension can be disabled with the "novx" parameter.
+ * Use MACHINE_HAS_VX instead of facility bit 129.
+ */
+ if (MACHINE_HAS_VX) {
+ elf_hwcap |= HWCAP_VXRS;
+ if (test_facility(134))
+ elf_hwcap |= HWCAP_VXRS_BCD;
+ if (test_facility(135))
+ elf_hwcap |= HWCAP_VXRS_EXT;
+ if (test_facility(148))
+ elf_hwcap |= HWCAP_VXRS_EXT2;
+ if (test_facility(152))
+ elf_hwcap |= HWCAP_VXRS_PDE;
+ if (test_facility(192))
+ elf_hwcap |= HWCAP_VXRS_PDE2;
+ }
+
+ if (test_facility(150))
+ elf_hwcap |= HWCAP_SORT;
+
+ if (test_facility(151))
+ elf_hwcap |= HWCAP_DFLT;
+
+ if (test_facility(165))
+ elf_hwcap |= HWCAP_NNPA;
+
+ /* guarded storage */
+ if (MACHINE_HAS_GS)
+ elf_hwcap |= HWCAP_GS;
+
+ if (MACHINE_HAS_PCI_MIO)
+ elf_hwcap |= HWCAP_PCI_MIO;
+
+ /* virtualization support */
+ if (sclp.has_sief2)
+ elf_hwcap |= HWCAP_SIE;
+
+ return 0;
+}
+arch_initcall(setup_hwcaps);
+
+static int __init setup_elf_platform(void)
+{
+ struct cpuid cpu_id;
+
+ get_cpu_id(&cpu_id);
+ add_device_randomness(&cpu_id, sizeof(cpu_id));
+ switch (cpu_id.machine) {
+ default: /* Use "z10" as default. */
+ strcpy(elf_platform, "z10");
+ break;
+ case 0x2817:
+ case 0x2818:
+ strcpy(elf_platform, "z196");
+ break;
+ case 0x2827:
+ case 0x2828:
+ strcpy(elf_platform, "zEC12");
+ break;
+ case 0x2964:
+ case 0x2965:
+ strcpy(elf_platform, "z13");
+ break;
+ case 0x3906:
+ case 0x3907:
+ strcpy(elf_platform, "z14");
+ break;
+ case 0x8561:
+ case 0x8562:
+ strcpy(elf_platform, "z15");
+ break;
+ case 0x3931:
+ case 0x3932:
+ strcpy(elf_platform, "z16");
+ break;
+ }
+ return 0;
+}
+arch_initcall(setup_elf_platform);
+
+static void show_cpu_topology(struct seq_file *m, unsigned long n)
+{
+#ifdef CONFIG_SCHED_TOPOLOGY
+ seq_printf(m, "physical id : %d\n", topology_physical_package_id(n));
+ seq_printf(m, "core id : %d\n", topology_core_id(n));
+ seq_printf(m, "book id : %d\n", topology_book_id(n));
+ seq_printf(m, "drawer id : %d\n", topology_drawer_id(n));
+ seq_printf(m, "dedicated : %d\n", topology_cpu_dedicated(n));
+ seq_printf(m, "address : %d\n", smp_cpu_get_cpu_address(n));
+ seq_printf(m, "siblings : %d\n", cpumask_weight(topology_core_cpumask(n)));
+ seq_printf(m, "cpu cores : %d\n", topology_booted_cores(n));
+#endif /* CONFIG_SCHED_TOPOLOGY */
+}
+
+static void show_cpu_ids(struct seq_file *m, unsigned long n)
+{
+ struct cpuid *id = &per_cpu(cpu_info.cpu_id, n);
+
+ seq_printf(m, "version : %02X\n", id->version);
+ seq_printf(m, "identification : %06X\n", id->ident);
+ seq_printf(m, "machine : %04X\n", id->machine);
+}
+
+static void show_cpu_mhz(struct seq_file *m, unsigned long n)
+{
+ struct cpu_info *c = per_cpu_ptr(&cpu_info, n);
+
+ if (!machine_has_cpu_mhz)
+ return;
+ seq_printf(m, "cpu MHz dynamic : %d\n", c->cpu_mhz_dynamic);
+ seq_printf(m, "cpu MHz static : %d\n", c->cpu_mhz_static);
+}
+
+/*
+ * show_cpuinfo - Get information on one CPU for use by procfs.
+ */
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+ unsigned long n = (unsigned long) v - 1;
+ unsigned long first = cpumask_first(cpu_online_mask);
+
+ if (n == first)
+ show_cpu_summary(m, v);
+ seq_printf(m, "\ncpu number : %ld\n", n);
+ show_cpu_topology(m, n);
+ show_cpu_ids(m, n);
+ show_cpu_mhz(m, n);
+ return 0;
+}
+
+static inline void *c_update(loff_t *pos)
+{
+ if (*pos)
+ *pos = cpumask_next(*pos - 1, cpu_online_mask);
+ else
+ *pos = cpumask_first(cpu_online_mask);
+ return *pos < nr_cpu_ids ? (void *)*pos + 1 : NULL;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ cpus_read_lock();
+ return c_update(pos);
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ ++*pos;
+ return c_update(pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+ cpus_read_unlock();
+}
+
+const struct seq_operations cpuinfo_op = {
+ .start = c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = show_cpuinfo,
+};
+
+int s390_isolate_bp(void)
+{
+ if (!test_facility(82))
+ return -EOPNOTSUPP;
+ set_thread_flag(TIF_ISOLATE_BP);
+ return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp);
+
+int s390_isolate_bp_guest(void)
+{
+ if (!test_facility(82))
+ return -EOPNOTSUPP;
+ set_thread_flag(TIF_ISOLATE_BP_GUEST);
+ return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp_guest);