aboutsummaryrefslogtreecommitdiff
path: root/arch/s390/kernel/machine_kexec.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/machine_kexec.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/machine_kexec.c')
-rw-r--r--arch/s390/kernel/machine_kexec.c297
1 files changed, 297 insertions, 0 deletions
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
new file mode 100644
index 000000000..2a8e73266
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2005, 2011
+ *
+ * Author(s): Rolf Adelsberger,
+ * Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <linux/device.h>
+#include <linux/mm.h>
+#include <linux/kexec.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/ftrace.h>
+#include <linux/debug_locks.h>
+#include <asm/cio.h>
+#include <asm/setup.h>
+#include <asm/smp.h>
+#include <asm/ipl.h>
+#include <asm/diag.h>
+#include <asm/elf.h>
+#include <asm/asm-offsets.h>
+#include <asm/cacheflush.h>
+#include <asm/abs_lowcore.h>
+#include <asm/os_info.h>
+#include <asm/set_memory.h>
+#include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+#include <asm/nmi.h>
+#include <asm/sclp.h>
+
+typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long,
+ unsigned long);
+
+extern const unsigned char relocate_kernel[];
+extern const unsigned long long relocate_kernel_len;
+
+#ifdef CONFIG_CRASH_DUMP
+
+/*
+ * Reset the system, copy boot CPU registers to absolute zero,
+ * and jump to the kdump image
+ */
+static void __do_machine_kdump(void *image)
+{
+ int (*start_kdump)(int);
+ unsigned long prefix;
+
+ /* store_status() saved the prefix register to lowcore */
+ prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
+
+ /* Now do the reset */
+ s390_reset_system();
+
+ /*
+ * Copy dump CPU store status info to absolute zero.
+ * This need to be done *after* s390_reset_system set the
+ * prefix register of this CPU to zero
+ */
+ memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA),
+ (void *)(prefix + __LC_FPREGS_SAVE_AREA), 512);
+
+ __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA);
+ start_kdump = (void *)((struct kimage *) image)->start;
+ start_kdump(1);
+
+ /* Die if start_kdump returns */
+ disabled_wait();
+}
+
+/*
+ * Start kdump: create a LGR log entry, store status of all CPUs and
+ * branch to __do_machine_kdump.
+ */
+static noinline void __machine_kdump(void *image)
+{
+ struct mcesa *mcesa;
+ union ctlreg2 cr2_old, cr2_new;
+ int this_cpu, cpu;
+
+ lgr_info_log();
+ /* Get status of the other CPUs */
+ this_cpu = smp_find_processor_id(stap());
+ for_each_online_cpu(cpu) {
+ if (cpu == this_cpu)
+ continue;
+ if (smp_store_status(cpu))
+ continue;
+ }
+ /* Store status of the boot CPU */
+ mcesa = __va(S390_lowcore.mcesad & MCESA_ORIGIN_MASK);
+ if (MACHINE_HAS_VX)
+ save_vx_regs((__vector128 *) mcesa->vector_save_area);
+ if (MACHINE_HAS_GS) {
+ __ctl_store(cr2_old.val, 2, 2);
+ cr2_new = cr2_old;
+ cr2_new.gse = 1;
+ __ctl_load(cr2_new.val, 2, 2);
+ save_gs_cb((struct gs_cb *) mcesa->guarded_storage_save_area);
+ __ctl_load(cr2_old.val, 2, 2);
+ }
+ /*
+ * To create a good backchain for this CPU in the dump store_status
+ * is passed the address of a function. The address is saved into
+ * the PSW save area of the boot CPU and the function is invoked as
+ * a tail call of store_status. The backchain in the dump will look
+ * like this:
+ * restart_int_handler -> __machine_kexec -> __do_machine_kdump
+ * The call to store_status() will not return.
+ */
+ store_status(__do_machine_kdump, image);
+}
+
+static unsigned long do_start_kdump(unsigned long addr)
+{
+ struct kimage *image = (struct kimage *) addr;
+ int (*start_kdump)(int) = (void *)image->start;
+ int rc;
+
+ __arch_local_irq_stnsm(0xfb); /* disable DAT */
+ rc = start_kdump(0);
+ __arch_local_irq_stosm(0x04); /* enable DAT */
+ return rc;
+}
+
+#endif /* CONFIG_CRASH_DUMP */
+
+/*
+ * Check if kdump checksums are valid: We call purgatory with parameter "0"
+ */
+static bool kdump_csum_valid(struct kimage *image)
+{
+#ifdef CONFIG_CRASH_DUMP
+ int rc;
+
+ preempt_disable();
+ rc = call_on_stack(1, S390_lowcore.nodat_stack, unsigned long, do_start_kdump,
+ unsigned long, (unsigned long)image);
+ preempt_enable();
+ return rc == 0;
+#else
+ return false;
+#endif
+}
+
+#ifdef CONFIG_CRASH_DUMP
+
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+ unsigned long addr, size;
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE)
+ free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
+ size = begin - crashk_res.start;
+ if (size)
+ os_info_crashkernel_add(crashk_res.start, size);
+ else
+ os_info_crashkernel_add(0, 0);
+}
+
+static void crash_protect_pages(int protect)
+{
+ unsigned long size;
+
+ if (!crashk_res.end)
+ return;
+ size = resource_size(&crashk_res);
+ if (protect)
+ set_memory_ro(crashk_res.start, size >> PAGE_SHIFT);
+ else
+ set_memory_rw(crashk_res.start, size >> PAGE_SHIFT);
+}
+
+void arch_kexec_protect_crashkres(void)
+{
+ crash_protect_pages(1);
+}
+
+void arch_kexec_unprotect_crashkres(void)
+{
+ crash_protect_pages(0);
+}
+
+#endif
+
+/*
+ * Give back memory to hypervisor before new kdump is loaded
+ */
+static int machine_kexec_prepare_kdump(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+ if (MACHINE_IS_VM)
+ diag10_range(PFN_DOWN(crashk_res.start),
+ PFN_DOWN(crashk_res.end - crashk_res.start + 1));
+ return 0;
+#else
+ return -EINVAL;
+#endif
+}
+
+int machine_kexec_prepare(struct kimage *image)
+{
+ void *reboot_code_buffer;
+
+ if (image->type == KEXEC_TYPE_CRASH)
+ return machine_kexec_prepare_kdump();
+
+ /* We don't support anything but the default image type for now. */
+ if (image->type != KEXEC_TYPE_DEFAULT)
+ return -EINVAL;
+
+ /* Get the destination where the assembler code should be copied to.*/
+ reboot_code_buffer = (void *) page_to_phys(image->control_code_page);
+
+ /* Then copy it */
+ memcpy(reboot_code_buffer, relocate_kernel, relocate_kernel_len);
+ return 0;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+}
+
+void arch_crash_save_vmcoreinfo(void)
+{
+ struct lowcore *abs_lc;
+
+ VMCOREINFO_SYMBOL(lowcore_ptr);
+ VMCOREINFO_SYMBOL(high_memory);
+ VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+ vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31);
+ vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31);
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+ abs_lc = get_abs_lowcore();
+ abs_lc->vmcore_info = paddr_vmcoreinfo_note();
+ put_abs_lowcore(abs_lc);
+}
+
+void machine_shutdown(void)
+{
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+ set_os_info_reipl_block();
+}
+
+/*
+ * Do normal kexec
+ */
+static void __do_machine_kexec(void *data)
+{
+ unsigned long diag308_subcode;
+ relocate_kernel_t data_mover;
+ struct kimage *image = data;
+
+ s390_reset_system();
+ data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page);
+
+ __arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */
+ /* Call the moving routine */
+ diag308_subcode = DIAG308_CLEAR_RESET;
+ if (sclp.has_iplcc)
+ diag308_subcode |= DIAG308_FLAG_EI;
+ (*data_mover)(&image->head, image->start, diag308_subcode);
+
+ /* Die if kexec returns */
+ disabled_wait();
+}
+
+/*
+ * Reset system and call either kdump or normal kexec
+ */
+static void __machine_kexec(void *data)
+{
+ pfault_fini();
+ tracing_off();
+ debug_locks_off();
+#ifdef CONFIG_CRASH_DUMP
+ if (((struct kimage *) data)->type == KEXEC_TYPE_CRASH)
+ __machine_kdump(data);
+#endif
+ __do_machine_kexec(data);
+}
+
+/*
+ * Do either kdump or normal kexec. In case of kdump we first ask
+ * purgatory, if kdump checksums are valid.
+ */
+void machine_kexec(struct kimage *image)
+{
+ if (image->type == KEXEC_TYPE_CRASH && !kdump_csum_valid(image))
+ return;
+ tracer_disable();
+ smp_send_stop();
+ smp_call_ipl_cpu(__machine_kexec, image);
+}