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(). ... --- arch/x86/pci/pcbios.c | 429 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 429 insertions(+) create mode 100644 arch/x86/pci/pcbios.c (limited to 'arch/x86/pci/pcbios.c') diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c new file mode 100644 index 000000000..4f1528073 --- /dev/null +++ b/arch/x86/pci/pcbios.c @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * BIOS32 and PCI BIOS handling. + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* BIOS32 signature: "_32_" */ +#define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24)) + +/* PCI signature: "PCI " */ +#define PCI_SIGNATURE (('P' << 0) + ('C' << 8) + ('I' << 16) + (' ' << 24)) + +/* PCI service signature: "$PCI" */ +#define PCI_SERVICE (('$' << 0) + ('P' << 8) + ('C' << 16) + ('I' << 24)) + +/* PCI BIOS hardware mechanism flags */ +#define PCIBIOS_HW_TYPE1 0x01 +#define PCIBIOS_HW_TYPE2 0x02 +#define PCIBIOS_HW_TYPE1_SPEC 0x10 +#define PCIBIOS_HW_TYPE2_SPEC 0x20 + +int pcibios_enabled; + +/* According to the BIOS specification at: + * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could + * restrict the x zone to some pages and make it ro. But this may be + * broken on some bios, complex to handle with static_protections. + * We could make the 0xe0000-0x100000 range rox, but this can break + * some ISA mapping. + * + * So we let's an rw and x hole when pcibios is used. This shouldn't + * happen for modern system with mmconfig, and if you don't want it + * you could disable pcibios... + */ +static inline void set_bios_x(void) +{ + pcibios_enabled = 1; + set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT); + if (__supported_pte_mask & _PAGE_NX) + printk(KERN_INFO "PCI: PCI BIOS area is rw and x. Use pci=nobios if you want it NX.\n"); +} + +/* + * This is the standard structure used to identify the entry point + * to the BIOS32 Service Directory, as documented in + * Standard BIOS 32-bit Service Directory Proposal + * Revision 0.4 May 24, 1993 + * Phoenix Technologies Ltd. + * Norwood, MA + * and the PCI BIOS specification. + */ + +union bios32 { + struct { + unsigned long signature; /* _32_ */ + unsigned long entry; /* 32 bit physical address */ + unsigned char revision; /* Revision level, 0 */ + unsigned char length; /* Length in paragraphs should be 01 */ + unsigned char checksum; /* All bytes must add up to zero */ + unsigned char reserved[5]; /* Must be zero */ + } fields; + char chars[16]; +}; + +/* + * Physical address of the service directory. I don't know if we're + * allowed to have more than one of these or not, so just in case + * we'll make pcibios_present() take a memory start parameter and store + * the array there. + */ + +static struct { + unsigned long address; + unsigned short segment; +} bios32_indirect __initdata = { 0, __KERNEL_CS }; + +/* + * Returns the entry point for the given service, NULL on error + */ + +static unsigned long __init bios32_service(unsigned long service) +{ + unsigned char return_code; /* %al */ + unsigned long address; /* %ebx */ + unsigned long length; /* %ecx */ + unsigned long entry; /* %edx */ + unsigned long flags; + + local_irq_save(flags); + __asm__("lcall *(%%edi); cld" + : "=a" (return_code), + "=b" (address), + "=c" (length), + "=d" (entry) + : "0" (service), + "1" (0), + "D" (&bios32_indirect)); + local_irq_restore(flags); + + switch (return_code) { + case 0: + return address + entry; + case 0x80: /* Not present */ + printk(KERN_WARNING "bios32_service(0x%lx): not present\n", service); + return 0; + default: /* Shouldn't happen */ + printk(KERN_WARNING "bios32_service(0x%lx): returned 0x%x -- BIOS bug!\n", + service, return_code); + return 0; + } +} + +static struct { + unsigned long address; + unsigned short segment; +} pci_indirect __ro_after_init = { + .address = 0, + .segment = __KERNEL_CS, +}; + +static int pci_bios_present __ro_after_init; + +static int __init check_pcibios(void) +{ + u32 signature, eax, ebx, ecx; + u8 status, major_ver, minor_ver, hw_mech; + unsigned long flags, pcibios_entry; + + if ((pcibios_entry = bios32_service(PCI_SERVICE))) { + pci_indirect.address = pcibios_entry + PAGE_OFFSET; + + local_irq_save(flags); + __asm__( + "lcall *(%%edi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=d" (signature), + "=a" (eax), + "=b" (ebx), + "=c" (ecx) + : "1" (PCIBIOS_PCI_BIOS_PRESENT), + "D" (&pci_indirect) + : "memory"); + local_irq_restore(flags); + + status = (eax >> 8) & 0xff; + hw_mech = eax & 0xff; + major_ver = (ebx >> 8) & 0xff; + minor_ver = ebx & 0xff; + if (pcibios_last_bus < 0) + pcibios_last_bus = ecx & 0xff; + DBG("PCI: BIOS probe returned s=%02x hw=%02x ver=%02x.%02x l=%02x\n", + status, hw_mech, major_ver, minor_ver, pcibios_last_bus); + if (status || signature != PCI_SIGNATURE) { + printk (KERN_ERR "PCI: BIOS BUG #%x[%08x] found\n", + status, signature); + return 0; + } + printk(KERN_INFO "PCI: PCI BIOS revision %x.%02x entry at 0x%lx, last bus=%d\n", + major_ver, minor_ver, pcibios_entry, pcibios_last_bus); +#ifdef CONFIG_PCI_DIRECT + if (!(hw_mech & PCIBIOS_HW_TYPE1)) + pci_probe &= ~PCI_PROBE_CONF1; + if (!(hw_mech & PCIBIOS_HW_TYPE2)) + pci_probe &= ~PCI_PROBE_CONF2; +#endif + return 1; + } + return 0; +} + +static int pci_bios_read(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, u32 *value) +{ + unsigned long result = 0; + unsigned long flags; + unsigned long bx = (bus << 8) | devfn; + u16 number = 0, mask = 0; + + WARN_ON(seg); + if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) + return -EINVAL; + + raw_spin_lock_irqsave(&pci_config_lock, flags); + + switch (len) { + case 1: + number = PCIBIOS_READ_CONFIG_BYTE; + mask = 0xff; + break; + case 2: + number = PCIBIOS_READ_CONFIG_WORD; + mask = 0xffff; + break; + case 4: + number = PCIBIOS_READ_CONFIG_DWORD; + break; + } + + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=c" (*value), + "=a" (result) + : "1" (number), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 8 or 16 bits, do not trust the + * BIOS having done it: + */ + if (mask) + *value &= mask; + + raw_spin_unlock_irqrestore(&pci_config_lock, flags); + + return (int)((result & 0xff00) >> 8); +} + +static int pci_bios_write(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, u32 value) +{ + unsigned long result = 0; + unsigned long flags; + unsigned long bx = (bus << 8) | devfn; + u16 number = 0; + + WARN_ON(seg); + if ((bus > 255) || (devfn > 255) || (reg > 255)) + return -EINVAL; + + raw_spin_lock_irqsave(&pci_config_lock, flags); + + switch (len) { + case 1: + number = PCIBIOS_WRITE_CONFIG_BYTE; + break; + case 2: + number = PCIBIOS_WRITE_CONFIG_WORD; + break; + case 4: + number = PCIBIOS_WRITE_CONFIG_DWORD; + break; + } + + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=a" (result) + : "0" (number), + "c" (value), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + + raw_spin_unlock_irqrestore(&pci_config_lock, flags); + + return (int)((result & 0xff00) >> 8); +} + + +/* + * Function table for BIOS32 access + */ + +static const struct pci_raw_ops pci_bios_access = { + .read = pci_bios_read, + .write = pci_bios_write +}; + +/* + * Try to find PCI BIOS. + */ + +static const struct pci_raw_ops *__init pci_find_bios(void) +{ + union bios32 *check; + unsigned char sum; + int i, length; + + /* + * Follow the standard procedure for locating the BIOS32 Service + * directory by scanning the permissible address range from + * 0xe0000 through 0xfffff for a valid BIOS32 structure. + */ + + for (check = (union bios32 *) __va(0xe0000); + check <= (union bios32 *) __va(0xffff0); + ++check) { + long sig; + if (get_kernel_nofault(sig, &check->fields.signature)) + continue; + + if (check->fields.signature != BIOS32_SIGNATURE) + continue; + length = check->fields.length * 16; + if (!length) + continue; + sum = 0; + for (i = 0; i < length ; ++i) + sum += check->chars[i]; + if (sum != 0) + continue; + if (check->fields.revision != 0) { + printk("PCI: unsupported BIOS32 revision %d at 0x%p\n", + check->fields.revision, check); + continue; + } + DBG("PCI: BIOS32 Service Directory structure at 0x%p\n", check); + if (check->fields.entry >= 0x100000) { + printk("PCI: BIOS32 entry (0x%p) in high memory, " + "cannot use.\n", check); + return NULL; + } else { + unsigned long bios32_entry = check->fields.entry; + DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n", + bios32_entry); + bios32_indirect.address = bios32_entry + PAGE_OFFSET; + set_bios_x(); + if (check_pcibios()) + return &pci_bios_access; + } + break; /* Hopefully more than one BIOS32 cannot happen... */ + } + + return NULL; +} + +/* + * BIOS Functions for IRQ Routing + */ + +struct irq_routing_options { + u16 size; + struct irq_info *table; + u16 segment; +} __attribute__((packed)); + +struct irq_routing_table * pcibios_get_irq_routing_table(void) +{ + struct irq_routing_options opt; + struct irq_routing_table *rt = NULL; + int ret, map; + unsigned long page; + + if (!pci_bios_present) + return NULL; + page = __get_free_page(GFP_KERNEL); + if (!page) + return NULL; + opt.table = (struct irq_info *) page; + opt.size = PAGE_SIZE; + opt.segment = __KERNEL_DS; + + DBG("PCI: Fetching IRQ routing table... "); + __asm__("push %%es\n\t" + "push %%ds\n\t" + "pop %%es\n\t" + "lcall *(%%esi); cld\n\t" + "pop %%es\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=a" (ret), + "=b" (map), + "=m" (opt) + : "0" (PCIBIOS_GET_ROUTING_OPTIONS), + "1" (0), + "D" ((long) &opt), + "S" (&pci_indirect), + "m" (opt) + : "memory"); + DBG("OK ret=%d, size=%d, map=%x\n", ret, opt.size, map); + if (ret & 0xff00) + printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", (ret >> 8) & 0xff); + else if (opt.size) { + rt = kmalloc(sizeof(struct irq_routing_table) + opt.size, GFP_KERNEL); + if (rt) { + memset(rt, 0, sizeof(struct irq_routing_table)); + rt->size = opt.size + sizeof(struct irq_routing_table); + rt->exclusive_irqs = map; + memcpy(rt->slots, (void *) page, opt.size); + printk(KERN_INFO "PCI: Using BIOS Interrupt Routing Table\n"); + } + } + free_page(page); + return rt; +} +EXPORT_SYMBOL(pcibios_get_irq_routing_table); + +int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq) +{ + int ret; + + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=a" (ret) + : "0" (PCIBIOS_SET_PCI_HW_INT), + "b" ((dev->bus->number << 8) | dev->devfn), + "c" ((irq << 8) | (pin + 10)), + "S" (&pci_indirect)); + return !(ret & 0xff00); +} +EXPORT_SYMBOL(pcibios_set_irq_routing); + +void __init pci_pcbios_init(void) +{ + if ((pci_probe & PCI_PROBE_BIOS) + && ((raw_pci_ops = pci_find_bios()))) { + pci_bios_present = 1; + } +} + -- cgit v1.2.3