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/mips/mm/init.c | 570 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 570 insertions(+) create mode 100644 arch/mips/mm/init.c (limited to 'arch/mips/mm/init.c') diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c new file mode 100644 index 000000000..5a8002839 --- /dev/null +++ b/arch/mips/mm/init.c @@ -0,0 +1,570 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1994 - 2000 Ralf Baechle + * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com + * Copyright (C) 2000 MIPS Technologies, Inc. All rights reserved. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * We have up to 8 empty zeroed pages so we can map one of the right colour + * when needed. This is necessary only on R4000 / R4400 SC and MC versions + * where we have to avoid VCED / VECI exceptions for good performance at + * any price. Since page is never written to after the initialization we + * don't have to care about aliases on other CPUs. + */ +unsigned long empty_zero_page, zero_page_mask; +EXPORT_SYMBOL_GPL(empty_zero_page); +EXPORT_SYMBOL(zero_page_mask); + +/* + * Not static inline because used by IP27 special magic initialization code + */ +void setup_zero_pages(void) +{ + unsigned int order, i; + struct page *page; + + if (cpu_has_vce) + order = 3; + else + order = 0; + + empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); + if (!empty_zero_page) + panic("Oh boy, that early out of memory?"); + + page = virt_to_page((void *)empty_zero_page); + split_page(page, order); + for (i = 0; i < (1 << order); i++, page++) + mark_page_reserved(page); + + zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK; +} + +static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot) +{ + enum fixed_addresses idx; + unsigned int old_mmid; + unsigned long vaddr, flags, entrylo; + unsigned long old_ctx; + pte_t pte; + int tlbidx; + + BUG_ON(Page_dcache_dirty(page)); + + preempt_disable(); + pagefault_disable(); + idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1); + idx += in_interrupt() ? FIX_N_COLOURS : 0; + vaddr = __fix_to_virt(FIX_CMAP_END - idx); + pte = mk_pte(page, prot); +#if defined(CONFIG_XPA) + entrylo = pte_to_entrylo(pte.pte_high); +#elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) + entrylo = pte.pte_high; +#else + entrylo = pte_to_entrylo(pte_val(pte)); +#endif + + local_irq_save(flags); + old_ctx = read_c0_entryhi(); + write_c0_entryhi(vaddr & (PAGE_MASK << 1)); + write_c0_entrylo0(entrylo); + write_c0_entrylo1(entrylo); + if (cpu_has_mmid) { + old_mmid = read_c0_memorymapid(); + write_c0_memorymapid(MMID_KERNEL_WIRED); + } +#ifdef CONFIG_XPA + if (cpu_has_xpa) { + entrylo = (pte.pte_low & _PFNX_MASK); + writex_c0_entrylo0(entrylo); + writex_c0_entrylo1(entrylo); + } +#endif + tlbidx = num_wired_entries(); + write_c0_wired(tlbidx + 1); + write_c0_index(tlbidx); + mtc0_tlbw_hazard(); + tlb_write_indexed(); + tlbw_use_hazard(); + write_c0_entryhi(old_ctx); + if (cpu_has_mmid) + write_c0_memorymapid(old_mmid); + local_irq_restore(flags); + + return (void*) vaddr; +} + +void *kmap_coherent(struct page *page, unsigned long addr) +{ + return __kmap_pgprot(page, addr, PAGE_KERNEL); +} + +void *kmap_noncoherent(struct page *page, unsigned long addr) +{ + return __kmap_pgprot(page, addr, PAGE_KERNEL_NC); +} + +void kunmap_coherent(void) +{ + unsigned int wired; + unsigned long flags, old_ctx; + + local_irq_save(flags); + old_ctx = read_c0_entryhi(); + wired = num_wired_entries() - 1; + write_c0_wired(wired); + write_c0_index(wired); + write_c0_entryhi(UNIQUE_ENTRYHI(wired)); + write_c0_entrylo0(0); + write_c0_entrylo1(0); + mtc0_tlbw_hazard(); + tlb_write_indexed(); + tlbw_use_hazard(); + write_c0_entryhi(old_ctx); + local_irq_restore(flags); + pagefault_enable(); + preempt_enable(); +} + +void copy_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + void *vfrom, *vto; + + vto = kmap_atomic(to); + if (cpu_has_dc_aliases && + page_mapcount(from) && !Page_dcache_dirty(from)) { + vfrom = kmap_coherent(from, vaddr); + copy_page(vto, vfrom); + kunmap_coherent(); + } else { + vfrom = kmap_atomic(from); + copy_page(vto, vfrom); + kunmap_atomic(vfrom); + } + if ((!cpu_has_ic_fills_f_dc) || + pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK)) + flush_data_cache_page((unsigned long)vto); + kunmap_atomic(vto); + /* Make sure this page is cleared on other CPU's too before using it */ + smp_wmb(); +} + +void copy_to_user_page(struct vm_area_struct *vma, + struct page *page, unsigned long vaddr, void *dst, const void *src, + unsigned long len) +{ + if (cpu_has_dc_aliases && + page_mapcount(page) && !Page_dcache_dirty(page)) { + void *vto = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); + memcpy(vto, src, len); + kunmap_coherent(); + } else { + memcpy(dst, src, len); + if (cpu_has_dc_aliases) + SetPageDcacheDirty(page); + } + if (vma->vm_flags & VM_EXEC) + flush_cache_page(vma, vaddr, page_to_pfn(page)); +} + +void copy_from_user_page(struct vm_area_struct *vma, + struct page *page, unsigned long vaddr, void *dst, const void *src, + unsigned long len) +{ + if (cpu_has_dc_aliases && + page_mapcount(page) && !Page_dcache_dirty(page)) { + void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); + memcpy(dst, vfrom, len); + kunmap_coherent(); + } else { + memcpy(dst, src, len); + if (cpu_has_dc_aliases) + SetPageDcacheDirty(page); + } +} +EXPORT_SYMBOL_GPL(copy_from_user_page); + +void __init fixrange_init(unsigned long start, unsigned long end, + pgd_t *pgd_base) +{ +#ifdef CONFIG_HIGHMEM + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int i, j, k; + unsigned long vaddr; + + vaddr = start; + i = pgd_index(vaddr); + j = pud_index(vaddr); + k = pmd_index(vaddr); + pgd = pgd_base + i; + + for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) { + pud = (pud_t *)pgd; + for ( ; (j < PTRS_PER_PUD) && (vaddr < end); pud++, j++) { + pmd = (pmd_t *)pud; + for (; (k < PTRS_PER_PMD) && (vaddr < end); pmd++, k++) { + if (pmd_none(*pmd)) { + pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, + PAGE_SIZE); + if (!pte) + panic("%s: Failed to allocate %lu bytes align=%lx\n", + __func__, PAGE_SIZE, + PAGE_SIZE); + + set_pmd(pmd, __pmd((unsigned long)pte)); + BUG_ON(pte != pte_offset_kernel(pmd, 0)); + } + vaddr += PMD_SIZE; + } + k = 0; + } + j = 0; + } +#endif +} + +struct maar_walk_info { + struct maar_config cfg[16]; + unsigned int num_cfg; +}; + +static int maar_res_walk(unsigned long start_pfn, unsigned long nr_pages, + void *data) +{ + struct maar_walk_info *wi = data; + struct maar_config *cfg = &wi->cfg[wi->num_cfg]; + unsigned int maar_align; + + /* MAAR registers hold physical addresses right shifted by 4 bits */ + maar_align = BIT(MIPS_MAAR_ADDR_SHIFT + 4); + + /* Fill in the MAAR config entry */ + cfg->lower = ALIGN(PFN_PHYS(start_pfn), maar_align); + cfg->upper = ALIGN_DOWN(PFN_PHYS(start_pfn + nr_pages), maar_align) - 1; + cfg->attrs = MIPS_MAAR_S; + + /* Ensure we don't overflow the cfg array */ + if (!WARN_ON(wi->num_cfg >= ARRAY_SIZE(wi->cfg))) + wi->num_cfg++; + + return 0; +} + + +unsigned __weak platform_maar_init(unsigned num_pairs) +{ + unsigned int num_configured; + struct maar_walk_info wi; + + wi.num_cfg = 0; + walk_system_ram_range(0, max_pfn, &wi, maar_res_walk); + + num_configured = maar_config(wi.cfg, wi.num_cfg, num_pairs); + if (num_configured < wi.num_cfg) + pr_warn("Not enough MAAR pairs (%u) for all memory regions (%u)\n", + num_pairs, wi.num_cfg); + + return num_configured; +} + +void maar_init(void) +{ + unsigned num_maars, used, i; + phys_addr_t lower, upper, attr; + static struct { + struct maar_config cfgs[3]; + unsigned used; + } recorded = { { { 0 } }, 0 }; + + if (!cpu_has_maar) + return; + + /* Detect the number of MAARs */ + write_c0_maari(~0); + back_to_back_c0_hazard(); + num_maars = read_c0_maari() + 1; + + /* MAARs should be in pairs */ + WARN_ON(num_maars % 2); + + /* Set MAARs using values we recorded already */ + if (recorded.used) { + used = maar_config(recorded.cfgs, recorded.used, num_maars / 2); + BUG_ON(used != recorded.used); + } else { + /* Configure the required MAARs */ + used = platform_maar_init(num_maars / 2); + } + + /* Disable any further MAARs */ + for (i = (used * 2); i < num_maars; i++) { + write_c0_maari(i); + back_to_back_c0_hazard(); + write_c0_maar(0); + back_to_back_c0_hazard(); + } + + if (recorded.used) + return; + + pr_info("MAAR configuration:\n"); + for (i = 0; i < num_maars; i += 2) { + write_c0_maari(i); + back_to_back_c0_hazard(); + upper = read_c0_maar(); +#ifdef CONFIG_XPA + upper |= (phys_addr_t)readx_c0_maar() << MIPS_MAARX_ADDR_SHIFT; +#endif + + write_c0_maari(i + 1); + back_to_back_c0_hazard(); + lower = read_c0_maar(); +#ifdef CONFIG_XPA + lower |= (phys_addr_t)readx_c0_maar() << MIPS_MAARX_ADDR_SHIFT; +#endif + + attr = lower & upper; + lower = (lower & MIPS_MAAR_ADDR) << 4; + upper = ((upper & MIPS_MAAR_ADDR) << 4) | 0xffff; + + pr_info(" [%d]: ", i / 2); + if ((attr & MIPS_MAAR_V) != MIPS_MAAR_V) { + pr_cont("disabled\n"); + continue; + } + + pr_cont("%pa-%pa", &lower, &upper); + + if (attr & MIPS_MAAR_S) + pr_cont(" speculate"); + + pr_cont("\n"); + + /* Record the setup for use on secondary CPUs */ + if (used <= ARRAY_SIZE(recorded.cfgs)) { + recorded.cfgs[recorded.used].lower = lower; + recorded.cfgs[recorded.used].upper = upper; + recorded.cfgs[recorded.used].attrs = attr; + recorded.used++; + } + } +} + +#ifndef CONFIG_NUMA +void __init paging_init(void) +{ + unsigned long max_zone_pfns[MAX_NR_ZONES]; + + pagetable_init(); + +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; +#endif +#ifdef CONFIG_ZONE_DMA32 + max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; +#endif + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; +#ifdef CONFIG_HIGHMEM + max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; + + if (cpu_has_dc_aliases && max_low_pfn != highend_pfn) { + printk(KERN_WARNING "This processor doesn't support highmem." + " %ldk highmem ignored\n", + (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10)); + max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn; + } +#endif + + free_area_init(max_zone_pfns); +} + +#ifdef CONFIG_64BIT +static struct kcore_list kcore_kseg0; +#endif + +static inline void __init mem_init_free_highmem(void) +{ +#ifdef CONFIG_HIGHMEM + unsigned long tmp; + + if (cpu_has_dc_aliases) + return; + + for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { + struct page *page = pfn_to_page(tmp); + + if (!memblock_is_memory(PFN_PHYS(tmp))) + SetPageReserved(page); + else + free_highmem_page(page); + } +#endif +} + +void __init mem_init(void) +{ + /* + * When _PFN_SHIFT is greater than PAGE_SHIFT we won't have enough PTE + * bits to hold a full 32b physical address on MIPS32 systems. + */ + BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (_PFN_SHIFT > PAGE_SHIFT)); + +#ifdef CONFIG_HIGHMEM + max_mapnr = highend_pfn ? highend_pfn : max_low_pfn; +#else + max_mapnr = max_low_pfn; +#endif + high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); + + maar_init(); + memblock_free_all(); + setup_zero_pages(); /* Setup zeroed pages. */ + mem_init_free_highmem(); + +#ifdef CONFIG_64BIT + if ((unsigned long) &_text > (unsigned long) CKSEG0) + /* The -4 is a hack so that user tools don't have to handle + the overflow. */ + kclist_add(&kcore_kseg0, (void *) CKSEG0, + 0x80000000 - 4, KCORE_TEXT); +#endif +} +#endif /* !CONFIG_NUMA */ + +void free_init_pages(const char *what, unsigned long begin, unsigned long end) +{ + unsigned long pfn; + + for (pfn = PFN_UP(begin); pfn < PFN_DOWN(end); pfn++) { + struct page *page = pfn_to_page(pfn); + void *addr = phys_to_virt(PFN_PHYS(pfn)); + + memset(addr, POISON_FREE_INITMEM, PAGE_SIZE); + free_reserved_page(page); + } + printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10); +} + +void (*free_init_pages_eva)(void *begin, void *end) = NULL; + +void __weak __init prom_free_prom_memory(void) +{ + /* nothing to do */ +} + +void __ref free_initmem(void) +{ + prom_free_prom_memory(); + /* + * Let the platform define a specific function to free the + * init section since EVA may have used any possible mapping + * between virtual and physical addresses. + */ + if (free_init_pages_eva) + free_init_pages_eva((void *)&__init_begin, (void *)&__init_end); + else + free_initmem_default(POISON_FREE_INITMEM); +} + +#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); + +static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) +{ + return node_distance(cpu_to_node(from), cpu_to_node(to)); +} + +static int __init pcpu_cpu_to_node(int cpu) +{ + return cpu_to_node(cpu); +} + +void __init setup_per_cpu_areas(void) +{ + unsigned long delta; + unsigned int cpu; + int rc; + + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, + pcpu_cpu_distance, + pcpu_cpu_to_node); + if (rc < 0) + panic("Failed to initialize percpu areas."); + + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) + __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; +} +#endif + +#ifndef CONFIG_MIPS_PGD_C0_CONTEXT +unsigned long pgd_current[NR_CPUS]; +#endif + +/* + * Align swapper_pg_dir in to 64K, allows its address to be loaded + * with a single LUI instruction in the TLB handlers. If we used + * __aligned(64K), its size would get rounded up to the alignment + * size, and waste space. So we place it in its own section and align + * it in the linker script. + */ +pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir"); +#ifndef __PAGETABLE_PUD_FOLDED +pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss; +#endif +#ifndef __PAGETABLE_PMD_FOLDED +pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned_bss; +EXPORT_SYMBOL_GPL(invalid_pmd_table); +#endif +pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss; +EXPORT_SYMBOL(invalid_pte_table); -- cgit v1.2.3