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/powerpc/include/asm/vdso/clocksource.h | 7 ++ arch/powerpc/include/asm/vdso/gettimeofday.h | 160 +++++++++++++++++++++++++++ arch/powerpc/include/asm/vdso/processor.h | 38 +++++++ arch/powerpc/include/asm/vdso/timebase.h | 73 ++++++++++++ arch/powerpc/include/asm/vdso/vsyscall.h | 25 +++++ 5 files changed, 303 insertions(+) create mode 100644 arch/powerpc/include/asm/vdso/clocksource.h create mode 100644 arch/powerpc/include/asm/vdso/gettimeofday.h create mode 100644 arch/powerpc/include/asm/vdso/processor.h create mode 100644 arch/powerpc/include/asm/vdso/timebase.h create mode 100644 arch/powerpc/include/asm/vdso/vsyscall.h (limited to 'arch/powerpc/include/asm/vdso') diff --git a/arch/powerpc/include/asm/vdso/clocksource.h b/arch/powerpc/include/asm/vdso/clocksource.h new file mode 100644 index 000000000..c1ba56b82 --- /dev/null +++ b/arch/powerpc/include/asm/vdso/clocksource.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_VDSO_CLOCKSOURCE_H +#define _ASM_POWERPC_VDSO_CLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES VDSO_CLOCKMODE_ARCHTIMER + +#endif diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h new file mode 100644 index 000000000..f0a4cf01e --- /dev/null +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_VDSO_GETTIMEOFDAY_H +#define _ASM_POWERPC_VDSO_GETTIMEOFDAY_H + +#ifndef __ASSEMBLY__ + +#include +#include +#include +#include +#include + +#define VDSO_HAS_CLOCK_GETRES 1 + +#define VDSO_HAS_TIME 1 + +static __always_inline int do_syscall_2(const unsigned long _r0, const unsigned long _r3, + const unsigned long _r4) +{ + register long r0 asm("r0") = _r0; + register unsigned long r3 asm("r3") = _r3; + register unsigned long r4 asm("r4") = _r4; + register int ret asm ("r3"); + + asm volatile( + " sc\n" + " bns+ 1f\n" + " neg %0, %0\n" + "1:\n" + : "=r" (ret), "+r" (r4), "+r" (r0) + : "r" (r3) + : "memory", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "cr0", "ctr"); + + return ret; +} + +static __always_inline +int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz) +{ + return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); +} + +#ifdef __powerpc64__ + +static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); +} + +#else + +#define BUILD_VDSO32 1 + +static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); +} +#endif + +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_data *vd) +{ + return get_tb(); +} + +const struct vdso_data *__arch_get_vdso_data(void); + +#ifdef CONFIG_TIME_NS +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) +{ + return (void *)vd + PAGE_SIZE; +} +#endif + +static inline bool vdso_clocksource_ok(const struct vdso_data *vd) +{ + return true; +} +#define vdso_clocksource_ok vdso_clocksource_ok + +/* + * powerpc specific delta calculation. + * + * This variant removes the masking of the subtraction because the + * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX + * which would result in a pointless operation. The compiler cannot + * optimize it away as the mask comes from the vdso data and is not compile + * time constant. + */ +static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) +{ + return (cycles - last) * mult; +} +#define vdso_calc_delta vdso_calc_delta + +#ifndef __powerpc64__ +static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift) +{ + u32 hi = ns >> 32; + u32 lo = ns; + + lo >>= shift; + lo |= hi << (32 - shift); + hi >>= shift; + + if (likely(hi == 0)) + return lo; + + return ((u64)hi << 32) | lo; +} +#define vdso_shift_ns vdso_shift_ns +#endif + +#ifdef __powerpc64__ +int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, + const struct vdso_data *vd); +int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, + const struct vdso_data *vd); +#else +int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts, + const struct vdso_data *vd); +int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts, + const struct vdso_data *vd); +int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, + const struct vdso_data *vd); +#endif +int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, + const struct vdso_data *vd); +__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, + const struct vdso_data *vd); +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/powerpc/include/asm/vdso/processor.h b/arch/powerpc/include/asm/vdso/processor.h new file mode 100644 index 000000000..80d13207c --- /dev/null +++ b/arch/powerpc/include/asm/vdso/processor.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_VDSO_PROCESSOR_H +#define _ASM_POWERPC_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLY__ + +/* Macros for adjusting thread priority (hardware multi-threading) */ +#ifdef CONFIG_PPC64 +#define HMT_very_low() asm volatile("or 31, 31, 31 # very low priority") +#define HMT_low() asm volatile("or 1, 1, 1 # low priority") +#define HMT_medium_low() asm volatile("or 6, 6, 6 # medium low priority") +#define HMT_medium() asm volatile("or 2, 2, 2 # medium priority") +#define HMT_medium_high() asm volatile("or 5, 5, 5 # medium high priority") +#define HMT_high() asm volatile("or 3, 3, 3 # high priority") +#else +#define HMT_very_low() +#define HMT_low() +#define HMT_medium_low() +#define HMT_medium() +#define HMT_medium_high() +#define HMT_high() +#endif + +#ifdef CONFIG_PPC64 +#define cpu_relax() \ + asm volatile(ASM_FTR_IFCLR( \ + /* Pre-POWER10 uses low ; medium priority nops */ \ + "or 1,1,1 ; or 2,2,2", \ + /* POWER10 onward uses pause_short (wait 2,0) */ \ + PPC_WAIT(2, 0), \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") +#else +#define cpu_relax() barrier() +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_VDSO_PROCESSOR_H */ diff --git a/arch/powerpc/include/asm/vdso/timebase.h b/arch/powerpc/include/asm/vdso/timebase.h new file mode 100644 index 000000000..e9245f86a --- /dev/null +++ b/arch/powerpc/include/asm/vdso/timebase.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Common timebase prototypes and such for all ppc machines. + */ + +#ifndef _ASM_POWERPC_VDSO_TIMEBASE_H +#define _ASM_POWERPC_VDSO_TIMEBASE_H + +#include + +/* + * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit + * version below in the else case of the ifdef. + */ +#if defined(__powerpc64__) && (defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_E500)) +#define mftb() ({unsigned long rval; \ + asm volatile( \ + "90: mfspr %0, %2;\n" \ + ASM_FTR_IFSET( \ + "97: cmpwi %0,0;\n" \ + " beq- 90b;\n", "", %1) \ + : "=r" (rval) \ + : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ + rval;}) +#elif defined(CONFIG_PPC_8xx) +#define mftb() ({unsigned long rval; \ + asm volatile("mftbl %0" : "=r" (rval)); rval;}) +#else +#define mftb() ({unsigned long rval; \ + asm volatile("mfspr %0, %1" : \ + "=r" (rval) : "i" (SPRN_TBRL)); rval;}) +#endif /* !CONFIG_PPC_CELL */ + +#if defined(CONFIG_PPC_8xx) +#define mftbu() ({unsigned long rval; \ + asm volatile("mftbu %0" : "=r" (rval)); rval;}) +#else +#define mftbu() ({unsigned long rval; \ + asm volatile("mfspr %0, %1" : "=r" (rval) : \ + "i" (SPRN_TBRU)); rval;}) +#endif + +#define mttbl(v) asm volatile("mttbl %0":: "r"(v)) +#define mttbu(v) asm volatile("mttbu %0":: "r"(v)) + +static __always_inline u64 get_tb(void) +{ + unsigned int tbhi, tblo, tbhi2; + + /* + * We use __powerpc64__ here not CONFIG_PPC64 because we want the compat + * VDSO to use the 32-bit compatible version in the while loop below. + */ + if (__is_defined(__powerpc64__)) + return mftb(); + + do { + tbhi = mftbu(); + tblo = mftb(); + tbhi2 = mftbu(); + } while (tbhi != tbhi2); + + return ((u64)tbhi << 32) | tblo; +} + +static inline void set_tb(unsigned int upper, unsigned int lower) +{ + mtspr(SPRN_TBWL, 0); + mtspr(SPRN_TBWU, upper); + mtspr(SPRN_TBWL, lower); +} + +#endif /* _ASM_POWERPC_VDSO_TIMEBASE_H */ diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h new file mode 100644 index 000000000..48cf23f1e --- /dev/null +++ b/arch/powerpc/include/asm/vdso/vsyscall.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_VDSO_VSYSCALL_H +#define _ASM_POWERPC_VDSO_VSYSCALL_H + +#ifndef __ASSEMBLY__ + +#include +#include + +/* + * Update the vDSO data page to keep in sync with kernel timekeeping. + */ +static __always_inline +struct vdso_data *__arch_get_k_vdso_data(void) +{ + return vdso_data->data; +} +#define __arch_get_k_vdso_data __arch_get_k_vdso_data + +/* The asm-generic header needs to be included after the definitions above */ +#include + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_VDSO_VSYSCALL_H */ -- cgit v1.2.3