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/arm/mach-omap2/sleep44xx.S | 388 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 388 insertions(+) create mode 100644 arch/arm/mach-omap2/sleep44xx.S (limited to 'arch/arm/mach-omap2/sleep44xx.S') diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S new file mode 100644 index 000000000..f60f6a9ae --- /dev/null +++ b/arch/arm/mach-omap2/sleep44xx.S @@ -0,0 +1,388 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * OMAP44xx sleep code. + * + * Copyright (C) 2011 Texas Instruments, Inc. + * Santosh Shilimkar + */ + +#include +#include +#include +#include +#include + +#include "omap-secure.h" + +#include "common.h" +#include "omap44xx.h" +#include "omap4-sar-layout.h" + + .arch armv7-a + +#if defined(CONFIG_SMP) && defined(CONFIG_PM) + + .arch_extension sec +.macro DO_SMC + dsb + smc #0 + dsb +.endm + +#ifdef CONFIG_ARCH_OMAP4 + +/* + * ============================= + * == CPU suspend finisher == + * ============================= + * + * void omap4_finish_suspend(unsigned long cpu_state) + * + * This function code saves the CPU context and performs the CPU + * power down sequence. Calling WFI effectively changes the CPU + * power domains states to the desired target power state. + * + * @cpu_state : contains context save state (r0) + * 0 - No context lost + * 1 - CPUx L1 and logic lost: MPUSS CSWR + * 2 - CPUx L1 and logic lost + GIC lost: MPUSS OSWR + * 3 - CPUx L1 and logic lost + GIC + L2 lost: MPUSS OFF + * @return: This function never returns for CPU OFF and DORMANT power states. + * Post WFI, CPU transitions to DORMANT or OFF power state and on wake-up + * from this follows a full CPU reset path via ROM code to CPU restore code. + * The restore function pointer is stored at CPUx_WAKEUP_NS_PA_ADDR_OFFSET. + * It returns to the caller for CPU INACTIVE and ON power states or in case + * CPU failed to transition to targeted OFF/DORMANT state. + * + * omap4_finish_suspend() calls v7_flush_dcache_all() which doesn't save + * stack frame and it expects the caller to take care of it. Hence the entire + * stack frame is saved to avoid possible stack corruption. + */ +ENTRY(omap4_finish_suspend) + stmfd sp!, {r4-r12, lr} + cmp r0, #0x0 + beq do_WFI @ No lowpower state, jump to WFI + + /* + * Flush all data from the L1 data cache before disabling + * SCTLR.C bit. + */ + bl omap4_get_sar_ram_base + ldr r9, [r0, #OMAP_TYPE_OFFSET] + cmp r9, #0x1 @ Check for HS device + bne skip_secure_l1_clean + mov r0, #SCU_PM_NORMAL + mov r1, #0xFF @ clean seucre L1 + stmfd r13!, {r4-r12, r14} + ldr r12, =OMAP4_MON_SCU_PWR_INDEX + DO_SMC + ldmfd r13!, {r4-r12, r14} +skip_secure_l1_clean: + bl v7_flush_dcache_all + + /* + * Clear the SCTLR.C bit to prevent further data cache + * allocation. Clearing SCTLR.C would make all the data accesses + * strongly ordered and would not hit the cache. + */ + mrc p15, 0, r0, c1, c0, 0 + bic r0, r0, #(1 << 2) @ Disable the C bit + mcr p15, 0, r0, c1, c0, 0 + isb + + bl v7_invalidate_l1 + + /* + * Switch the CPU from Symmetric Multiprocessing (SMP) mode + * to AsymmetricMultiprocessing (AMP) mode by programming + * the SCU power status to DORMANT or OFF mode. + * This enables the CPU to be taken out of coherency by + * preventing the CPU from receiving cache, TLB, or BTB + * maintenance operations broadcast by other CPUs in the cluster. + */ + bl omap4_get_sar_ram_base + mov r8, r0 + ldr r9, [r8, #OMAP_TYPE_OFFSET] + cmp r9, #0x1 @ Check for HS device + bne scu_gp_set + mrc p15, 0, r0, c0, c0, 5 @ Read MPIDR + ands r0, r0, #0x0f + ldreq r0, [r8, #SCU_OFFSET0] + ldrne r0, [r8, #SCU_OFFSET1] + mov r1, #0x00 + stmfd r13!, {r4-r12, r14} + ldr r12, =OMAP4_MON_SCU_PWR_INDEX + DO_SMC + ldmfd r13!, {r4-r12, r14} + b skip_scu_gp_set +scu_gp_set: + mrc p15, 0, r0, c0, c0, 5 @ Read MPIDR + ands r0, r0, #0x0f + ldreq r1, [r8, #SCU_OFFSET0] + ldrne r1, [r8, #SCU_OFFSET1] + bl omap4_get_scu_base + bl scu_power_mode +skip_scu_gp_set: + mrc p15, 0, r0, c1, c1, 2 @ Read NSACR data + tst r0, #(1 << 18) + mrcne p15, 0, r0, c1, c0, 1 + bicne r0, r0, #(1 << 6) @ Disable SMP bit + mcrne p15, 0, r0, c1, c0, 1 + isb + dsb +#ifdef CONFIG_CACHE_L2X0 + /* + * Clean and invalidate the L2 cache. + * Common cache-l2x0.c functions can't be used here since it + * uses spinlocks. We are out of coherency here with data cache + * disabled. The spinlock implementation uses exclusive load/store + * instruction which can fail without data cache being enabled. + * OMAP4 hardware doesn't support exclusive monitor which can + * overcome exclusive access issue. Because of this, CPU can + * lead to deadlock. + */ + bl omap4_get_sar_ram_base + mov r8, r0 + mrc p15, 0, r5, c0, c0, 5 @ Read MPIDR + ands r5, r5, #0x0f + ldreq r0, [r8, #L2X0_SAVE_OFFSET0] @ Retrieve L2 state from SAR + ldrne r0, [r8, #L2X0_SAVE_OFFSET1] @ memory. + cmp r0, #3 + bne do_WFI +#ifdef CONFIG_PL310_ERRATA_727915 + mov r0, #0x03 + mov r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX + DO_SMC +#endif + bl omap4_get_l2cache_base + mov r2, r0 + ldr r0, =0xffff + str r0, [r2, #L2X0_CLEAN_INV_WAY] +wait: + ldr r0, [r2, #L2X0_CLEAN_INV_WAY] + ldr r1, =0xffff + ands r0, r0, r1 + bne wait +#ifdef CONFIG_PL310_ERRATA_727915 + mov r0, #0x00 + mov r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX + DO_SMC +#endif +l2x_sync: + bl omap4_get_l2cache_base + mov r2, r0 + mov r0, #0x0 + str r0, [r2, #L2X0_CACHE_SYNC] +sync: + ldr r0, [r2, #L2X0_CACHE_SYNC] + ands r0, r0, #0x1 + bne sync +#endif + +do_WFI: + bl omap_do_wfi + + /* + * CPU is here when it failed to enter OFF/DORMANT or + * no low power state was attempted. + */ + mrc p15, 0, r0, c1, c0, 0 + tst r0, #(1 << 2) @ Check C bit enabled? + orreq r0, r0, #(1 << 2) @ Enable the C bit + mcreq p15, 0, r0, c1, c0, 0 + isb + + /* + * Ensure the CPU power state is set to NORMAL in + * SCU power state so that CPU is back in coherency. + * In non-coherent mode CPU can lock-up and lead to + * system deadlock. + */ + mrc p15, 0, r0, c1, c0, 1 + tst r0, #(1 << 6) @ Check SMP bit enabled? + orreq r0, r0, #(1 << 6) + mcreq p15, 0, r0, c1, c0, 1 + isb + bl omap4_get_sar_ram_base + mov r8, r0 + ldr r9, [r8, #OMAP_TYPE_OFFSET] + cmp r9, #0x1 @ Check for HS device + bne scu_gp_clear + mov r0, #SCU_PM_NORMAL + mov r1, #0x00 + stmfd r13!, {r4-r12, r14} + ldr r12, =OMAP4_MON_SCU_PWR_INDEX + DO_SMC + ldmfd r13!, {r4-r12, r14} + b skip_scu_gp_clear +scu_gp_clear: + bl omap4_get_scu_base + mov r1, #SCU_PM_NORMAL + bl scu_power_mode +skip_scu_gp_clear: + isb + dsb + ldmfd sp!, {r4-r12, pc} +ENDPROC(omap4_finish_suspend) + +/* + * ============================ + * == CPU resume entry point == + * ============================ + * + * void omap4_cpu_resume(void) + * + * ROM code jumps to this function while waking up from CPU + * OFF or DORMANT state. Physical address of the function is + * stored in the SAR RAM while entering to OFF or DORMANT mode. + * The restore function pointer is stored at CPUx_WAKEUP_NS_PA_ADDR_OFFSET. + */ +ENTRY(omap4_cpu_resume) + /* + * Configure ACTRL and enable NS SMP bit access on CPU1 on HS device. + * OMAP44XX EMU/HS devices - CPU0 SMP bit access is enabled in PPA + * init and for CPU1, a secure PPA API provided. CPU0 must be ON + * while executing NS_SMP API on CPU1 and PPA version must be 1.4.0+. + * OMAP443X GP devices- SMP bit isn't accessible. + * OMAP446X GP devices - SMP bit access is enabled on both CPUs. + */ + ldr r8, =OMAP44XX_SAR_RAM_BASE + ldr r9, [r8, #OMAP_TYPE_OFFSET] + cmp r9, #0x1 @ Skip if GP device + bne skip_ns_smp_enable + mrc p15, 0, r0, c0, c0, 5 + ands r0, r0, #0x0f + beq skip_ns_smp_enable +ppa_actrl_retry: + mov r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX + adr r1, ppa_zero_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_zero_params + mov r1, #0x0 @ Process ID + mov r2, #0x4 @ Flag + mov r6, #0xff + mov r12, #0x00 @ Secure Service ID + DO_SMC + cmp r0, #0x0 @ API returns 0 on success. + beq enable_smp_bit + b ppa_actrl_retry +enable_smp_bit: + mrc p15, 0, r0, c1, c0, 1 + tst r0, #(1 << 6) @ Check SMP bit enabled? + orreq r0, r0, #(1 << 6) + mcreq p15, 0, r0, c1, c0, 1 + isb +skip_ns_smp_enable: +#ifdef CONFIG_CACHE_L2X0 + /* + * Restore the L2 AUXCTRL and enable the L2 cache. + * OMAP4_MON_L2X0_AUXCTRL_INDEX = Program the L2X0 AUXCTRL + * OMAP4_MON_L2X0_CTRL_INDEX = Enable the L2 using L2X0 CTRL + * register r0 contains value to be programmed. + * L2 cache is already invalidate by ROM code as part + * of MPUSS OFF wakeup path. + */ + ldr r2, =OMAP44XX_L2CACHE_BASE + ldr r0, [r2, #L2X0_CTRL] + and r0, #0x0f + cmp r0, #1 + beq skip_l2en @ Skip if already enabled + ldr r3, =OMAP44XX_SAR_RAM_BASE + ldr r1, [r3, #OMAP_TYPE_OFFSET] + cmp r1, #0x1 @ Check for HS device + bne set_gp_por + ldr r0, =OMAP4_PPA_L2_POR_INDEX + ldr r1, =OMAP44XX_SAR_RAM_BASE + ldr r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET] + adr r1, ppa_por_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_por_params + str r4, [r3, #0x04] + mov r1, #0x0 @ Process ID + mov r2, #0x4 @ Flag + mov r6, #0xff + mov r12, #0x00 @ Secure Service ID + DO_SMC + b set_aux_ctrl +set_gp_por: + ldr r1, =OMAP44XX_SAR_RAM_BASE + ldr r0, [r1, #L2X0_PREFETCH_CTRL_OFFSET] + ldr r12, =OMAP4_MON_L2X0_PREFETCH_INDEX @ Setup L2 PREFETCH + DO_SMC +set_aux_ctrl: + ldr r1, =OMAP44XX_SAR_RAM_BASE + ldr r0, [r1, #L2X0_AUXCTRL_OFFSET] + ldr r12, =OMAP4_MON_L2X0_AUXCTRL_INDEX @ Setup L2 AUXCTRL + DO_SMC + mov r0, #0x1 + ldr r12, =OMAP4_MON_L2X0_CTRL_INDEX @ Enable L2 cache + DO_SMC +skip_l2en: +#endif + + b cpu_resume @ Jump to generic resume +ppa_por_params_offset: + .long ppa_por_params - . +ENDPROC(omap4_cpu_resume) +#endif /* CONFIG_ARCH_OMAP4 */ + +#endif /* defined(CONFIG_SMP) && defined(CONFIG_PM) */ + +ENTRY(omap_do_wfi) + stmfd sp!, {lr} +#ifdef CONFIG_OMAP_INTERCONNECT_BARRIER + /* Drain interconnect write buffers. */ + bl omap_interconnect_sync +#endif + + /* + * Execute an ISB instruction to ensure that all of the + * CP15 register changes have been committed. + */ + isb + + /* + * Execute a barrier instruction to ensure that all cache, + * TLB and branch predictor maintenance operations issued + * by any CPU in the cluster have completed. + */ + dsb + dmb + + /* + * Execute a WFI instruction and wait until the + * STANDBYWFI output is asserted to indicate that the + * CPU is in idle and low power state. CPU can specualatively + * prefetch the instructions so add NOPs after WFI. Sixteen + * NOPs as per Cortex-A9 pipeline. + */ + wfi @ Wait For Interrupt + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + + ldmfd sp!, {pc} +ppa_zero_params_offset: + .long ppa_zero_params - . +ENDPROC(omap_do_wfi) + + .data + .align 2 +ppa_zero_params: + .word 0 + +ppa_por_params: + .word 1, 0 -- cgit v1.2.3