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/mm/proc-feroceon.S | 613 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 613 insertions(+) create mode 100644 arch/arm/mm/proc-feroceon.S (limited to 'arch/arm/mm/proc-feroceon.S') diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S new file mode 100644 index 000000000..61ce82aca --- /dev/null +++ b/arch/arm/mm/proc-feroceon.S @@ -0,0 +1,613 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * linux/arch/arm/mm/proc-feroceon.S: MMU functions for Feroceon + * + * Heavily based on proc-arm926.S + * Maintainer: Assaf Hoffman + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "proc-macros.S" + +/* + * This is the maximum size of an area which will be invalidated + * using the single invalidate entry instructions. Anything larger + * than this, and we go for the whole cache. + * + * This value should be chosen such that we choose the cheapest + * alternative. + */ +#define CACHE_DLIMIT 16384 + +/* + * the cache line size of the I and D cache + */ +#define CACHE_DLINESIZE 32 + + .bss + .align 3 +__cache_params_loc: + .space 8 + + .text +__cache_params: + .word __cache_params_loc + +/* + * cpu_feroceon_proc_init() + */ +ENTRY(cpu_feroceon_proc_init) + mrc p15, 0, r0, c0, c0, 1 @ read cache type register + ldr r1, __cache_params + mov r2, #(16 << 5) + tst r0, #(1 << 16) @ get way + mov r0, r0, lsr #18 @ get cache size order + movne r3, #((4 - 1) << 30) @ 4-way + and r0, r0, #0xf + moveq r3, #0 @ 1-way + mov r2, r2, lsl r0 @ actual cache size + movne r2, r2, lsr #2 @ turned into # of sets + sub r2, r2, #(1 << 5) + stmia r1, {r2, r3} + ret lr + +/* + * cpu_feroceon_proc_fin() + */ +ENTRY(cpu_feroceon_proc_fin) +#if defined(CONFIG_CACHE_FEROCEON_L2) && \ + !defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH) + mov r0, #0 + mcr p15, 1, r0, c15, c9, 0 @ clean L2 + mcr p15, 0, r0, c7, c10, 4 @ drain WB +#endif + + mrc p15, 0, r0, c1, c0, 0 @ ctrl register + bic r0, r0, #0x1000 @ ...i............ + bic r0, r0, #0x000e @ ............wca. + mcr p15, 0, r0, c1, c0, 0 @ disable caches + ret lr + +/* + * cpu_feroceon_reset(loc) + * + * Perform a soft reset of the system. Put the CPU into the + * same state as it would be if it had been reset, and branch + * to what would be the reset vector. + * + * loc: location to jump to for soft reset + */ + .align 5 + .pushsection .idmap.text, "ax" +ENTRY(cpu_feroceon_reset) + mov ip, #0 + mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches + mcr p15, 0, ip, c7, c10, 4 @ drain WB +#ifdef CONFIG_MMU + mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs +#endif + mrc p15, 0, ip, c1, c0, 0 @ ctrl register + bic ip, ip, #0x000f @ ............wcam + bic ip, ip, #0x1100 @ ...i...s........ + mcr p15, 0, ip, c1, c0, 0 @ ctrl register + ret r0 +ENDPROC(cpu_feroceon_reset) + .popsection + +/* + * cpu_feroceon_do_idle() + * + * Called with IRQs disabled + */ + .align 5 +ENTRY(cpu_feroceon_do_idle) + mov r0, #0 + mcr p15, 0, r0, c7, c10, 4 @ Drain write buffer + mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt + ret lr + +/* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(feroceon_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + ret lr +ENDPROC(feroceon_flush_icache_all) + +/* + * flush_user_cache_all() + * + * Clean and invalidate all cache entries in a particular + * address space. + */ + .align 5 +ENTRY(feroceon_flush_user_cache_all) + /* FALLTHROUGH */ + +/* + * flush_kern_cache_all() + * + * Clean and invalidate the entire cache. + */ +ENTRY(feroceon_flush_kern_cache_all) + mov r2, #VM_EXEC + +__flush_whole_cache: + ldr r1, __cache_params + ldmia r1, {r1, r3} +1: orr ip, r1, r3 +2: mcr p15, 0, ip, c7, c14, 2 @ clean + invalidate D set/way + subs ip, ip, #(1 << 30) @ next way + bcs 2b + subs r1, r1, #(1 << 5) @ next set + bcs 1b + + tst r2, #VM_EXEC + mov ip, #0 + mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache + mcrne p15, 0, ip, c7, c10, 4 @ drain WB + ret lr + +/* + * flush_user_cache_range(start, end, flags) + * + * Clean and invalidate a range of cache entries in the + * specified address range. + * + * - start - start address (inclusive) + * - end - end address (exclusive) + * - flags - vm_flags describing address space + */ + .align 5 +ENTRY(feroceon_flush_user_cache_range) + sub r3, r1, r0 @ calculate total size + cmp r3, #CACHE_DLIMIT + bgt __flush_whole_cache +1: tst r2, #VM_EXEC + mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D entry + mcrne p15, 0, r0, c7, c5, 1 @ invalidate I entry + add r0, r0, #CACHE_DLINESIZE + mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D entry + mcrne p15, 0, r0, c7, c5, 1 @ invalidate I entry + add r0, r0, #CACHE_DLINESIZE + cmp r0, r1 + blo 1b + tst r2, #VM_EXEC + mov ip, #0 + mcrne p15, 0, ip, c7, c10, 4 @ drain WB + ret lr + +/* + * coherent_kern_range(start, end) + * + * Ensure coherency between the Icache and the Dcache in the + * region described by start, end. If you have non-snooping + * Harvard caches, you need to implement this function. + * + * - start - virtual start address + * - end - virtual end address + */ + .align 5 +ENTRY(feroceon_coherent_kern_range) + /* FALLTHROUGH */ + +/* + * coherent_user_range(start, end) + * + * Ensure coherency between the Icache and the Dcache in the + * region described by start, end. If you have non-snooping + * Harvard caches, you need to implement this function. + * + * - start - virtual start address + * - end - virtual end address + */ +ENTRY(feroceon_coherent_user_range) + bic r0, r0, #CACHE_DLINESIZE - 1 +1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + mcr p15, 0, r0, c7, c5, 1 @ invalidate I entry + add r0, r0, #CACHE_DLINESIZE + cmp r0, r1 + blo 1b + mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 + ret lr + +/* + * flush_kern_dcache_area(void *addr, size_t size) + * + * Ensure no D cache aliasing occurs, either with itself or + * the I cache + * + * - addr - kernel address + * - size - region size + */ + .align 5 +ENTRY(feroceon_flush_kern_dcache_area) + add r1, r0, r1 +1: mcr p15, 0, r0, c7, c14, 1 @ clean+invalidate D entry + add r0, r0, #CACHE_DLINESIZE + cmp r0, r1 + blo 1b + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + + .align 5 +ENTRY(feroceon_range_flush_kern_dcache_area) + mrs r2, cpsr + add r1, r0, #PAGE_SZ - CACHE_DLINESIZE @ top addr is inclusive + orr r3, r2, #PSR_I_BIT + msr cpsr_c, r3 @ disable interrupts + mcr p15, 5, r0, c15, c15, 0 @ D clean/inv range start + mcr p15, 5, r1, c15, c15, 1 @ D clean/inv range top + msr cpsr_c, r2 @ restore interrupts + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + +/* + * dma_inv_range(start, end) + * + * Invalidate (discard) the specified virtual address range. + * May not write back any entries. If 'start' or 'end' + * are not cache line aligned, those lines must be written + * back. + * + * - start - virtual start address + * - end - virtual end address + * + * (same as v4wb) + */ + .align 5 +feroceon_dma_inv_range: + tst r0, #CACHE_DLINESIZE - 1 + bic r0, r0, #CACHE_DLINESIZE - 1 + mcrne p15, 0, r0, c7, c10, 1 @ clean D entry + tst r1, #CACHE_DLINESIZE - 1 + mcrne p15, 0, r1, c7, c10, 1 @ clean D entry +1: mcr p15, 0, r0, c7, c6, 1 @ invalidate D entry + add r0, r0, #CACHE_DLINESIZE + cmp r0, r1 + blo 1b + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + + .align 5 +feroceon_range_dma_inv_range: + mrs r2, cpsr + tst r0, #CACHE_DLINESIZE - 1 + mcrne p15, 0, r0, c7, c10, 1 @ clean D entry + tst r1, #CACHE_DLINESIZE - 1 + mcrne p15, 0, r1, c7, c10, 1 @ clean D entry + cmp r1, r0 + subne r1, r1, #1 @ top address is inclusive + orr r3, r2, #PSR_I_BIT + msr cpsr_c, r3 @ disable interrupts + mcr p15, 5, r0, c15, c14, 0 @ D inv range start + mcr p15, 5, r1, c15, c14, 1 @ D inv range top + msr cpsr_c, r2 @ restore interrupts + ret lr + +/* + * dma_clean_range(start, end) + * + * Clean the specified virtual address range. + * + * - start - virtual start address + * - end - virtual end address + * + * (same as v4wb) + */ + .align 5 +feroceon_dma_clean_range: + bic r0, r0, #CACHE_DLINESIZE - 1 +1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + add r0, r0, #CACHE_DLINESIZE + cmp r0, r1 + blo 1b + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + + .align 5 +feroceon_range_dma_clean_range: + mrs r2, cpsr + cmp r1, r0 + subne r1, r1, #1 @ top address is inclusive + orr r3, r2, #PSR_I_BIT + msr cpsr_c, r3 @ disable interrupts + mcr p15, 5, r0, c15, c13, 0 @ D clean range start + mcr p15, 5, r1, c15, c13, 1 @ D clean range top + msr cpsr_c, r2 @ restore interrupts + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + +/* + * dma_flush_range(start, end) + * + * Clean and invalidate the specified virtual address range. + * + * - start - virtual start address + * - end - virtual end address + */ + .align 5 +ENTRY(feroceon_dma_flush_range) + bic r0, r0, #CACHE_DLINESIZE - 1 +1: mcr p15, 0, r0, c7, c14, 1 @ clean+invalidate D entry + add r0, r0, #CACHE_DLINESIZE + cmp r0, r1 + blo 1b + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + + .align 5 +ENTRY(feroceon_range_dma_flush_range) + mrs r2, cpsr + cmp r1, r0 + subne r1, r1, #1 @ top address is inclusive + orr r3, r2, #PSR_I_BIT + msr cpsr_c, r3 @ disable interrupts + mcr p15, 5, r0, c15, c15, 0 @ D clean/inv range start + mcr p15, 5, r1, c15, c15, 1 @ D clean/inv range top + msr cpsr_c, r2 @ restore interrupts + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + +/* + * dma_map_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(feroceon_dma_map_area) + add r1, r1, r0 + cmp r2, #DMA_TO_DEVICE + beq feroceon_dma_clean_range + bcs feroceon_dma_inv_range + b feroceon_dma_flush_range +ENDPROC(feroceon_dma_map_area) + +/* + * dma_map_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(feroceon_range_dma_map_area) + add r1, r1, r0 + cmp r2, #DMA_TO_DEVICE + beq feroceon_range_dma_clean_range + bcs feroceon_range_dma_inv_range + b feroceon_range_dma_flush_range +ENDPROC(feroceon_range_dma_map_area) + +/* + * dma_unmap_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(feroceon_dma_unmap_area) + ret lr +ENDPROC(feroceon_dma_unmap_area) + + .globl feroceon_flush_kern_cache_louis + .equ feroceon_flush_kern_cache_louis, feroceon_flush_kern_cache_all + + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions feroceon + +.macro range_alias basename + .globl feroceon_range_\basename + .type feroceon_range_\basename , %function + .equ feroceon_range_\basename , feroceon_\basename +.endm + +/* + * Most of the cache functions are unchanged for this case. + * Export suitable alias symbols for the unchanged functions: + */ + range_alias flush_icache_all + range_alias flush_user_cache_all + range_alias flush_kern_cache_all + range_alias flush_kern_cache_louis + range_alias flush_user_cache_range + range_alias coherent_kern_range + range_alias coherent_user_range + range_alias dma_unmap_area + + define_cache_functions feroceon_range + + .align 5 +ENTRY(cpu_feroceon_dcache_clean_area) +#if defined(CONFIG_CACHE_FEROCEON_L2) && \ + !defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH) + mov r2, r0 + mov r3, r1 +#endif +1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + add r0, r0, #CACHE_DLINESIZE + subs r1, r1, #CACHE_DLINESIZE + bhi 1b +#if defined(CONFIG_CACHE_FEROCEON_L2) && \ + !defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH) +1: mcr p15, 1, r2, c15, c9, 1 @ clean L2 entry + add r2, r2, #CACHE_DLINESIZE + subs r3, r3, #CACHE_DLINESIZE + bhi 1b +#endif + mcr p15, 0, r0, c7, c10, 4 @ drain WB + ret lr + +/* =============================== PageTable ============================== */ + +/* + * cpu_feroceon_switch_mm(pgd) + * + * Set the translation base pointer to be as described by pgd. + * + * pgd: new page tables + */ + .align 5 +ENTRY(cpu_feroceon_switch_mm) +#ifdef CONFIG_MMU + /* + * Note: we wish to call __flush_whole_cache but we need to preserve + * lr to do so. The only way without touching main memory is to + * use r2 which is normally used to test the VM_EXEC flag, and + * compensate locally for the skipped ops if it is not set. + */ + mov r2, lr @ abuse r2 to preserve lr + bl __flush_whole_cache + @ if r2 contains the VM_EXEC bit then the next 2 ops are done already + tst r2, #VM_EXEC + mcreq p15, 0, ip, c7, c5, 0 @ invalidate I cache + mcreq p15, 0, ip, c7, c10, 4 @ drain WB + + mcr p15, 0, r0, c2, c0, 0 @ load page table pointer + mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs + ret r2 +#else + ret lr +#endif + +/* + * cpu_feroceon_set_pte_ext(ptep, pte, ext) + * + * Set a PTE and flush it out + */ + .align 5 +ENTRY(cpu_feroceon_set_pte_ext) +#ifdef CONFIG_MMU + armv3_set_pte_ext wc_disable=0 + mov r0, r0 + mcr p15, 0, r0, c7, c10, 1 @ clean D entry +#if defined(CONFIG_CACHE_FEROCEON_L2) && \ + !defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH) + mcr p15, 1, r0, c15, c9, 1 @ clean L2 entry +#endif + mcr p15, 0, r0, c7, c10, 4 @ drain WB +#endif + ret lr + +/* Suspend/resume support: taken from arch/arm/mm/proc-arm926.S */ +.globl cpu_feroceon_suspend_size +.equ cpu_feroceon_suspend_size, 4 * 3 +#ifdef CONFIG_ARM_CPU_SUSPEND +ENTRY(cpu_feroceon_do_suspend) + stmfd sp!, {r4 - r6, lr} + mrc p15, 0, r4, c13, c0, 0 @ PID + mrc p15, 0, r5, c3, c0, 0 @ Domain ID + mrc p15, 0, r6, c1, c0, 0 @ Control register + stmia r0, {r4 - r6} + ldmfd sp!, {r4 - r6, pc} +ENDPROC(cpu_feroceon_do_suspend) + +ENTRY(cpu_feroceon_do_resume) + mov ip, #0 + mcr p15, 0, ip, c8, c7, 0 @ invalidate I+D TLBs + mcr p15, 0, ip, c7, c7, 0 @ invalidate I+D caches + ldmia r0, {r4 - r6} + mcr p15, 0, r4, c13, c0, 0 @ PID + mcr p15, 0, r5, c3, c0, 0 @ Domain ID + mcr p15, 0, r1, c2, c0, 0 @ TTB address + mov r0, r6 @ control register + b cpu_resume_mmu +ENDPROC(cpu_feroceon_do_resume) +#endif + + .type __feroceon_setup, #function +__feroceon_setup: + mov r0, #0 + mcr p15, 0, r0, c7, c7 @ invalidate I,D caches on v4 + mcr p15, 0, r0, c7, c10, 4 @ drain write buffer on v4 +#ifdef CONFIG_MMU + mcr p15, 0, r0, c8, c7 @ invalidate I,D TLBs on v4 +#endif + + adr r5, feroceon_crval + ldmia r5, {r5, r6} + mrc p15, 0, r0, c1, c0 @ get control register v4 + bic r0, r0, r5 + orr r0, r0, r6 + ret lr + .size __feroceon_setup, . - __feroceon_setup + + /* + * B + * R P + * .RVI UFRS BLDP WCAM + * .011 .001 ..11 0101 + * + */ + .type feroceon_crval, #object +feroceon_crval: + crval clear=0x0000773f, mmuset=0x00003135, ucset=0x00001134 + + __INITDATA + + @ define struct processor (see and proc-macros.S) + define_processor_functions feroceon, dabort=v5t_early_abort, pabort=legacy_pabort + + .section ".rodata" + + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5" + string cpu_feroceon_name, "Feroceon" + string cpu_88fr531_name, "Feroceon 88FR531-vd" + string cpu_88fr571_name, "Feroceon 88FR571-vd" + string cpu_88fr131_name, "Feroceon 88FR131" + + .align + + .section ".proc.info.init", "a" + +.macro feroceon_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache:req + .type __\name\()_proc_info,#object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask + .long PMD_TYPE_SECT | \ + PMD_SECT_BUFFERABLE | \ + PMD_SECT_CACHEABLE | \ + PMD_BIT4 | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ + .long PMD_TYPE_SECT | \ + PMD_BIT4 | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ + initfn __feroceon_setup, __\name\()_proc_info + .long cpu_arch_name + .long cpu_elf_name + .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP + .long \cpu_name + .long feroceon_processor_functions + .long v4wbi_tlb_fns + .long feroceon_user_fns + .long \cache + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm + +#ifdef CONFIG_CPU_FEROCEON_OLD_ID + feroceon_proc_info feroceon_old_id, 0x41009260, 0xff00fff0, \ + cpu_name=cpu_feroceon_name, cache=feroceon_cache_fns +#endif + + feroceon_proc_info 88fr531, 0x56055310, 0xfffffff0, cpu_88fr531_name, \ + cache=feroceon_cache_fns + feroceon_proc_info 88fr571, 0x56155710, 0xfffffff0, cpu_88fr571_name, \ + cache=feroceon_range_cache_fns + feroceon_proc_info 88fr131, 0x56251310, 0xfffffff0, cpu_88fr131_name, \ + cache=feroceon_range_cache_fns -- cgit v1.2.3