aboutsummaryrefslogtreecommitdiff
path: root/arch/s390/mm/init.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/mm/init.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/mm/init.c')
-rw-r--r--arch/s390/mm/init.c314
1 files changed, 314 insertions, 0 deletions
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
new file mode 100644
index 000000000..144447d5c
--- /dev/null
+++ b/arch/s390/mm/init.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * S390 version
+ * Copyright IBM Corp. 1999
+ * Author(s): Hartmut Penner (hp@de.ibm.com)
+ *
+ * Derived from "arch/i386/mm/init.c"
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/swiotlb.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/memblock.h>
+#include <linux/memory.h>
+#include <linux/pfn.h>
+#include <linux/poison.h>
+#include <linux/initrd.h>
+#include <linux/export.h>
+#include <linux/cma.h>
+#include <linux/gfp.h>
+#include <linux/dma-direct.h>
+#include <linux/percpu.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/kfence.h>
+#include <asm/ptdump.h>
+#include <asm/dma.h>
+#include <asm/abs_lowcore.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/ctl_reg.h>
+#include <asm/sclp.h>
+#include <asm/set_memory.h>
+#include <asm/kasan.h>
+#include <asm/dma-mapping.h>
+#include <asm/uv.h>
+#include <linux/virtio_anchor.h>
+#include <linux/virtio_config.h>
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
+pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir");
+
+unsigned long __bootdata_preserved(s390_invalid_asce);
+
+unsigned long empty_zero_page, zero_page_mask;
+EXPORT_SYMBOL(empty_zero_page);
+EXPORT_SYMBOL(zero_page_mask);
+
+static void __init setup_zero_pages(void)
+{
+ unsigned int order;
+ struct page *page;
+ int i;
+
+ /* Latest machines require a mapping granularity of 512KB */
+ order = 7;
+
+ /* Limit number of empty zero pages for small memory sizes */
+ while (order > 2 && (totalram_pages() >> 10) < (1UL << order))
+ order--;
+
+ empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
+ if (!empty_zero_page)
+ panic("Out of memory in setup_zero_pages");
+
+ page = virt_to_page((void *) empty_zero_page);
+ split_page(page, order);
+ for (i = 1 << order; i > 0; i--) {
+ mark_page_reserved(page);
+ page++;
+ }
+
+ zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
+}
+
+/*
+ * paging_init() sets up the page tables
+ */
+void __init paging_init(void)
+{
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+
+ vmem_map_init();
+ sparse_init();
+ zone_dma_bits = 31;
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+ max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
+ max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+ free_area_init(max_zone_pfns);
+}
+
+void mark_rodata_ro(void)
+{
+ unsigned long size = __end_ro_after_init - __start_ro_after_init;
+
+ set_memory_ro((unsigned long)__start_ro_after_init, size >> PAGE_SHIFT);
+ pr_info("Write protected read-only-after-init data: %luk\n", size >> 10);
+ debug_checkwx();
+}
+
+int set_memory_encrypted(unsigned long vaddr, int numpages)
+{
+ int i;
+
+ /* make specified pages unshared, (swiotlb, dma_free) */
+ for (i = 0; i < numpages; ++i) {
+ uv_remove_shared(virt_to_phys((void *)vaddr));
+ vaddr += PAGE_SIZE;
+ }
+ return 0;
+}
+
+int set_memory_decrypted(unsigned long vaddr, int numpages)
+{
+ int i;
+ /* make specified pages shared (swiotlb, dma_alloca) */
+ for (i = 0; i < numpages; ++i) {
+ uv_set_shared(virt_to_phys((void *)vaddr));
+ vaddr += PAGE_SIZE;
+ }
+ return 0;
+}
+
+/* are we a protected virtualization guest? */
+bool force_dma_unencrypted(struct device *dev)
+{
+ return is_prot_virt_guest();
+}
+
+/* protected virtualization */
+static void pv_init(void)
+{
+ if (!is_prot_virt_guest())
+ return;
+
+ virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
+
+ /* make sure bounce buffers are shared */
+ swiotlb_init(true, SWIOTLB_FORCE | SWIOTLB_VERBOSE);
+ swiotlb_update_mem_attributes();
+}
+
+void __init mem_init(void)
+{
+ cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
+ cpumask_set_cpu(0, mm_cpumask(&init_mm));
+
+ set_max_mapnr(max_low_pfn);
+ high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+
+ pv_init();
+ kfence_split_mapping();
+ /* Setup guest page hinting */
+ cmma_init();
+
+ /* this will put all low memory onto the freelists */
+ memblock_free_all();
+ setup_zero_pages(); /* Setup zeroed pages. */
+
+ cmma_init_nodat();
+}
+
+void free_initmem(void)
+{
+ __set_memory((unsigned long)_sinittext,
+ (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
+ SET_MEMORY_RW | SET_MEMORY_NX);
+ free_initmem_default(POISON_FREE_INITMEM);
+}
+
+unsigned long memory_block_size_bytes(void)
+{
+ /*
+ * Make sure the memory block size is always greater
+ * or equal than the memory increment size.
+ */
+ return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp.rzm);
+}
+
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+ return LOCAL_DISTANCE;
+}
+
+static int __init pcpu_cpu_to_node(int cpu)
+{
+ return 0;
+}
+
+void __init setup_per_cpu_areas(void)
+{
+ unsigned long delta;
+ unsigned int cpu;
+ int rc;
+
+ /*
+ * Always reserve area for module percpu variables. That's
+ * what the legacy allocator did.
+ */
+ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+ PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+ pcpu_cpu_distance,
+ pcpu_cpu_to_node);
+ if (rc < 0)
+ panic("Failed to initialize percpu areas.");
+
+ delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+ for_each_possible_cpu(cpu)
+ __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+
+#ifdef CONFIG_CMA
+
+/* Prevent memory blocks which contain cma regions from going offline */
+
+struct s390_cma_mem_data {
+ unsigned long start;
+ unsigned long end;
+};
+
+static int s390_cma_check_range(struct cma *cma, void *data)
+{
+ struct s390_cma_mem_data *mem_data;
+ unsigned long start, end;
+
+ mem_data = data;
+ start = cma_get_base(cma);
+ end = start + cma_get_size(cma);
+ if (end < mem_data->start)
+ return 0;
+ if (start >= mem_data->end)
+ return 0;
+ return -EBUSY;
+}
+
+static int s390_cma_mem_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct s390_cma_mem_data mem_data;
+ struct memory_notify *arg;
+ int rc = 0;
+
+ arg = data;
+ mem_data.start = arg->start_pfn << PAGE_SHIFT;
+ mem_data.end = mem_data.start + (arg->nr_pages << PAGE_SHIFT);
+ if (action == MEM_GOING_OFFLINE)
+ rc = cma_for_each_area(s390_cma_check_range, &mem_data);
+ return notifier_from_errno(rc);
+}
+
+static struct notifier_block s390_cma_mem_nb = {
+ .notifier_call = s390_cma_mem_notifier,
+};
+
+static int __init s390_cma_mem_init(void)
+{
+ return register_memory_notifier(&s390_cma_mem_nb);
+}
+device_initcall(s390_cma_mem_init);
+
+#endif /* CONFIG_CMA */
+
+int arch_add_memory(int nid, u64 start, u64 size,
+ struct mhp_params *params)
+{
+ unsigned long start_pfn = PFN_DOWN(start);
+ unsigned long size_pages = PFN_DOWN(size);
+ int rc;
+
+ if (WARN_ON_ONCE(params->altmap))
+ return -EINVAL;
+
+ if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot))
+ return -EINVAL;
+
+ VM_BUG_ON(!mhp_range_allowed(start, size, true));
+ rc = vmem_add_mapping(start, size);
+ if (rc)
+ return rc;
+
+ rc = __add_pages(nid, start_pfn, size_pages, params);
+ if (rc)
+ vmem_remove_mapping(start, size);
+ return rc;
+}
+
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+{
+ unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+
+ __remove_pages(start_pfn, nr_pages, altmap);
+ vmem_remove_mapping(start, size);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */