aboutsummaryrefslogtreecommitdiff
path: root/arch/sparc/include/asm/processor_64.h
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/sparc/include/asm/processor_64.h
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/sparc/include/asm/processor_64.h')
-rw-r--r--arch/sparc/include/asm/processor_64.h250
1 files changed, 250 insertions, 0 deletions
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
new file mode 100644
index 000000000..2667f35d5
--- /dev/null
+++ b/arch/sparc/include/asm/processor_64.h
@@ -0,0 +1,250 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * include/asm/processor.h
+ *
+ * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
+ */
+
+#ifndef __ASM_SPARC64_PROCESSOR_H
+#define __ASM_SPARC64_PROCESSOR_H
+
+#include <asm/asi.h>
+#include <asm/pstate.h>
+#include <asm/ptrace.h>
+#include <asm/page.h>
+
+/*
+ * User lives in his very own context, and cannot reference us. Note
+ * that TASK_SIZE is a misnomer, it really gives maximum user virtual
+ * address that the kernel will allocate out.
+ *
+ * XXX No longer using virtual page tables, kill this upper limit...
+ */
+#define VA_BITS 44
+#ifndef __ASSEMBLY__
+#define VPTE_SIZE (1UL << (VA_BITS - PAGE_SHIFT + 3))
+#else
+#define VPTE_SIZE (1 << (VA_BITS - PAGE_SHIFT + 3))
+#endif
+
+#define TASK_SIZE_OF(tsk) \
+ (test_tsk_thread_flag(tsk,TIF_32BIT) ? \
+ (1UL << 32UL) : ((unsigned long)-VPTE_SIZE))
+#define TASK_SIZE \
+ (test_thread_flag(TIF_32BIT) ? \
+ (1UL << 32UL) : ((unsigned long)-VPTE_SIZE))
+#ifdef __KERNEL__
+
+#define STACK_TOP32 ((1UL << 32UL) - PAGE_SIZE)
+#define STACK_TOP64 (0x0000080000000000UL - (1UL << 32UL))
+
+#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \
+ STACK_TOP32 : STACK_TOP64)
+
+#define STACK_TOP_MAX STACK_TOP64
+
+#endif
+
+#ifndef __ASSEMBLY__
+
+/* The Sparc processor specific thread struct. */
+/* XXX This should die, everything can go into thread_info now. */
+struct thread_struct {
+#ifdef CONFIG_DEBUG_SPINLOCK
+ /* How many spinlocks held by this thread.
+ * Used with spin lock debugging to catch tasks
+ * sleeping illegally with locks held.
+ */
+ int smp_lock_count;
+ unsigned int smp_lock_pc;
+#else
+ int dummy; /* f'in gcc bug... */
+#endif
+};
+
+#endif /* !(__ASSEMBLY__) */
+
+#ifndef CONFIG_DEBUG_SPINLOCK
+#define INIT_THREAD { \
+ 0, \
+}
+#else /* CONFIG_DEBUG_SPINLOCK */
+#define INIT_THREAD { \
+/* smp_lock_count, smp_lock_pc, */ \
+ 0, 0, \
+}
+#endif /* !(CONFIG_DEBUG_SPINLOCK) */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/fpumacro.h>
+
+struct task_struct;
+
+/* On Uniprocessor, even in RMO processes see TSO semantics */
+#ifdef CONFIG_SMP
+#define TSTATE_INITIAL_MM TSTATE_TSO
+#else
+#define TSTATE_INITIAL_MM TSTATE_RMO
+#endif
+
+/* Do necessary setup to start up a newly executed thread. */
+#define start_thread(regs, pc, sp) \
+do { \
+ unsigned long __asi = ASI_PNF; \
+ regs->tstate = (regs->tstate & (TSTATE_CWP)) | (TSTATE_INITIAL_MM|TSTATE_IE) | (__asi << 24UL); \
+ regs->tpc = ((pc & (~3)) - 4); \
+ regs->tnpc = regs->tpc + 4; \
+ regs->y = 0; \
+ set_thread_wstate(1 << 3); \
+ if (current_thread_info()->utraps) { \
+ if (*(current_thread_info()->utraps) < 2) \
+ kfree(current_thread_info()->utraps); \
+ else \
+ (*(current_thread_info()->utraps))--; \
+ current_thread_info()->utraps = NULL; \
+ } \
+ __asm__ __volatile__( \
+ "stx %%g0, [%0 + %2 + 0x00]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x08]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x10]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x18]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x20]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x28]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x30]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x38]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x40]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x48]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x50]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x58]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x60]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x68]\n\t" \
+ "stx %1, [%0 + %2 + 0x70]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x78]\n\t" \
+ "wrpr %%g0, (1 << 3), %%wstate\n\t" \
+ : \
+ : "r" (regs), "r" (sp - sizeof(struct reg_window) - STACK_BIAS), \
+ "i" ((const unsigned long)(&((struct pt_regs *)0)->u_regs[0]))); \
+ fprs_write(0); \
+ current_thread_info()->xfsr[0] = 0; \
+ current_thread_info()->fpsaved[0] = 0; \
+ regs->tstate &= ~TSTATE_PEF; \
+} while (0)
+
+#define start_thread32(regs, pc, sp) \
+do { \
+ unsigned long __asi = ASI_PNF; \
+ pc &= 0x00000000ffffffffUL; \
+ sp &= 0x00000000ffffffffUL; \
+ regs->tstate = (regs->tstate & (TSTATE_CWP))|(TSTATE_INITIAL_MM|TSTATE_IE|TSTATE_AM) | (__asi << 24UL); \
+ regs->tpc = ((pc & (~3)) - 4); \
+ regs->tnpc = regs->tpc + 4; \
+ regs->y = 0; \
+ set_thread_wstate(2 << 3); \
+ if (current_thread_info()->utraps) { \
+ if (*(current_thread_info()->utraps) < 2) \
+ kfree(current_thread_info()->utraps); \
+ else \
+ (*(current_thread_info()->utraps))--; \
+ current_thread_info()->utraps = NULL; \
+ } \
+ __asm__ __volatile__( \
+ "stx %%g0, [%0 + %2 + 0x00]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x08]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x10]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x18]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x20]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x28]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x30]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x38]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x40]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x48]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x50]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x58]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x60]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x68]\n\t" \
+ "stx %1, [%0 + %2 + 0x70]\n\t" \
+ "stx %%g0, [%0 + %2 + 0x78]\n\t" \
+ "wrpr %%g0, (2 << 3), %%wstate\n\t" \
+ : \
+ : "r" (regs), "r" (sp - sizeof(struct reg_window32)), \
+ "i" ((const unsigned long)(&((struct pt_regs *)0)->u_regs[0]))); \
+ fprs_write(0); \
+ current_thread_info()->xfsr[0] = 0; \
+ current_thread_info()->fpsaved[0] = 0; \
+ regs->tstate &= ~TSTATE_PEF; \
+} while (0)
+
+unsigned long __get_wchan(struct task_struct *task);
+
+#define task_pt_regs(tsk) (task_thread_info(tsk)->kregs)
+#define KSTK_EIP(tsk) (task_pt_regs(tsk)->tpc)
+#define KSTK_ESP(tsk) (task_pt_regs(tsk)->u_regs[UREG_FP])
+
+/* Please see the commentary in asm/backoff.h for a description of
+ * what these instructions are doing and how they have been chosen.
+ * To make a long story short, we are trying to yield the current cpu
+ * strand during busy loops.
+ */
+#ifdef BUILD_VDSO
+#define cpu_relax() asm volatile("\n99:\n\t" \
+ "rd %%ccr, %%g0\n\t" \
+ "rd %%ccr, %%g0\n\t" \
+ "rd %%ccr, %%g0\n\t" \
+ ::: "memory")
+#else /* ! BUILD_VDSO */
+#define cpu_relax() asm volatile("\n99:\n\t" \
+ "rd %%ccr, %%g0\n\t" \
+ "rd %%ccr, %%g0\n\t" \
+ "rd %%ccr, %%g0\n\t" \
+ ".section .pause_3insn_patch,\"ax\"\n\t"\
+ ".word 99b\n\t" \
+ "wr %%g0, 128, %%asr27\n\t" \
+ "nop\n\t" \
+ "nop\n\t" \
+ ".previous" \
+ ::: "memory")
+#endif
+
+/* Prefetch support. This is tuned for UltraSPARC-III and later.
+ * UltraSPARC-I will treat these as nops, and UltraSPARC-II has
+ * a shallower prefetch queue than later chips.
+ */
+#define ARCH_HAS_PREFETCH
+#define ARCH_HAS_PREFETCHW
+#define ARCH_HAS_SPINLOCK_PREFETCH
+
+static inline void prefetch(const void *x)
+{
+ /* We do not use the read prefetch mnemonic because that
+ * prefetches into the prefetch-cache which only is accessible
+ * by floating point operations in UltraSPARC-III and later.
+ * By contrast, "#one_write" prefetches into the L2 cache
+ * in shared state.
+ */
+ __asm__ __volatile__("prefetch [%0], #one_write"
+ : /* no outputs */
+ : "r" (x));
+}
+
+static inline void prefetchw(const void *x)
+{
+ /* The most optimal prefetch to use for writes is
+ * "#n_writes". This brings the cacheline into the
+ * L2 cache in "owned" state.
+ */
+ __asm__ __volatile__("prefetch [%0], #n_writes"
+ : /* no outputs */
+ : "r" (x));
+}
+
+#define spin_lock_prefetch(x) prefetchw(x)
+
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
+int do_mathemu(struct pt_regs *regs, struct fpustate *f, bool illegal_insn_trap);
+
+#endif /* !(__ASSEMBLY__) */
+
+#endif /* !(__ASM_SPARC64_PROCESSOR_H) */