From: Stephen Rothwell Date: Thu, 9 Apr 2015 05:13:12 +0000 (+1000) Subject: Merge remote-tracking branch 'tip/auto-latest' X-Git-Tag: KARO-TXA5-2015-06-26~56 X-Git-Url: https://git.karo-electronics.de/?p=karo-tx-linux.git;a=commitdiff_plain;h=5cd181c125b603fdca603e00d9a859abc50dc40a Merge remote-tracking branch 'tip/auto-latest' Conflicts: include/linux/bpf.h include/uapi/linux/bpf.h samples/bpf/Makefile --- 5cd181c125b603fdca603e00d9a859abc50dc40a diff --cc arch/arm/kernel/vdso.c index 0d31d3ccab81,000000000000..efe17dd9b921 mode 100644,000000..100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@@ -1,337 -1,0 +1,337 @@@ +/* + * Adapted from arm64 version. + * + * Copyright (C) 2012 ARM Limited + * Copyright (C) 2015 Mentor Graphics Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MAX_SYMNAME 64 + +static struct page **vdso_text_pagelist; + +/* Total number of pages needed for the data and text portions of the VDSO. */ +unsigned int vdso_total_pages __read_mostly; + +/* + * The VDSO data page. + */ +static union vdso_data_store vdso_data_store __page_aligned_data; +static struct vdso_data *vdso_data = &vdso_data_store.data; + +static struct page *vdso_data_page; +static struct vm_special_mapping vdso_data_mapping = { + .name = "[vvar]", + .pages = &vdso_data_page, +}; + +static struct vm_special_mapping vdso_text_mapping = { + .name = "[vdso]", +}; + +struct elfinfo { + Elf32_Ehdr *hdr; /* ptr to ELF */ + Elf32_Sym *dynsym; /* ptr to .dynsym section */ + unsigned long dynsymsize; /* size of .dynsym section */ + char *dynstr; /* ptr to .dynstr section */ +}; + +/* Cached result of boot-time check for whether the arch timer exists, + * and if so, whether the virtual counter is useable. + */ +static bool cntvct_ok __read_mostly; + +static bool __init cntvct_functional(void) +{ + struct device_node *np; + bool ret = false; + + if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) + goto out; + + /* The arm_arch_timer core should export + * arch_timer_use_virtual or similar so we don't have to do + * this. + */ + np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); + if (!np) + goto out_put; + + if (of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) + goto out_put; + + ret = true; + +out_put: + of_node_put(np); +out: + return ret; +} + +static void * __init find_section(Elf32_Ehdr *ehdr, const char *name, + unsigned long *size) +{ + Elf32_Shdr *sechdrs; + unsigned int i; + char *secnames; + + /* Grab section headers and strings so we can tell who is who */ + sechdrs = (void *)ehdr + ehdr->e_shoff; + secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; + + /* Find the section they want */ + for (i = 1; i < ehdr->e_shnum; i++) { + if (strcmp(secnames + sechdrs[i].sh_name, name) == 0) { + if (size) + *size = sechdrs[i].sh_size; + return (void *)ehdr + sechdrs[i].sh_offset; + } + } + + if (size) + *size = 0; + return NULL; +} + +static Elf32_Sym * __init find_symbol(struct elfinfo *lib, const char *symname) +{ + unsigned int i; + + for (i = 0; i < (lib->dynsymsize / sizeof(Elf32_Sym)); i++) { + char name[MAX_SYMNAME], *c; + + if (lib->dynsym[i].st_name == 0) + continue; + strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, + MAX_SYMNAME); + c = strchr(name, '@'); + if (c) + *c = 0; + if (strcmp(symname, name) == 0) + return &lib->dynsym[i]; + } + return NULL; +} + +static void __init vdso_nullpatch_one(struct elfinfo *lib, const char *symname) +{ + Elf32_Sym *sym; + + sym = find_symbol(lib, symname); + if (!sym) + return; + + sym->st_name = 0; +} + +static void __init patch_vdso(void *ehdr) +{ + struct elfinfo einfo; + + einfo = (struct elfinfo) { + .hdr = ehdr, + }; + + einfo.dynsym = find_section(einfo.hdr, ".dynsym", &einfo.dynsymsize); + einfo.dynstr = find_section(einfo.hdr, ".dynstr", NULL); + + /* If the virtual counter is absent or non-functional we don't + * want programs to incur the slight additional overhead of + * dispatching through the VDSO only to fall back to syscalls. + */ + if (!cntvct_ok) { + vdso_nullpatch_one(&einfo, "__vdso_gettimeofday"); + vdso_nullpatch_one(&einfo, "__vdso_clock_gettime"); + } +} + +static int __init vdso_init(void) +{ + unsigned int text_pages; + int i; + + if (memcmp(&vdso_start, "\177ELF", 4)) { + pr_err("VDSO is not a valid ELF object!\n"); + return -ENOEXEC; + } + + text_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT; + pr_debug("vdso: %i text pages at base %p\n", text_pages, &vdso_start); + + /* Allocate the VDSO text pagelist */ + vdso_text_pagelist = kcalloc(text_pages, sizeof(struct page *), + GFP_KERNEL); + if (vdso_text_pagelist == NULL) + return -ENOMEM; + + /* Grab the VDSO data page. */ + vdso_data_page = virt_to_page(vdso_data); + + /* Grab the VDSO text pages. */ + for (i = 0; i < text_pages; i++) { + struct page *page; + + page = virt_to_page(&vdso_start + i * PAGE_SIZE); + vdso_text_pagelist[i] = page; + } + + vdso_text_mapping.pages = vdso_text_pagelist; + + vdso_total_pages = 1; /* for the data/vvar page */ + vdso_total_pages += text_pages; + + cntvct_ok = cntvct_functional(); + + patch_vdso(&vdso_start); + + return 0; +} +arch_initcall(vdso_init); + +static int install_vvar(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + + vma = _install_special_mapping(mm, addr, PAGE_SIZE, + VM_READ | VM_MAYREAD, + &vdso_data_mapping); + + return IS_ERR(vma) ? PTR_ERR(vma) : 0; +} + +/* assumes mmap_sem is write-locked */ +void arm_install_vdso(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + unsigned long len; + + mm->context.vdso = 0; + + if (vdso_text_pagelist == NULL) + return; + + if (install_vvar(mm, addr)) + return; + + /* Account for vvar page. */ + addr += PAGE_SIZE; + len = (vdso_total_pages - 1) << PAGE_SHIFT; + + vma = _install_special_mapping(mm, addr, len, + VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, + &vdso_text_mapping); + + if (!IS_ERR(vma)) + mm->context.vdso = addr; +} + +static void vdso_write_begin(struct vdso_data *vdata) +{ + ++vdso_data->seq_count; + smp_wmb(); /* Pairs with smp_rmb in vdso_read_retry */ +} + +static void vdso_write_end(struct vdso_data *vdata) +{ + smp_wmb(); /* Pairs with smp_rmb in vdso_read_begin */ + ++vdso_data->seq_count; +} + +static bool tk_is_cntvct(const struct timekeeper *tk) +{ + if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) + return false; + - if (strcmp(tk->tkr.clock->name, "arch_sys_counter") != 0) ++ if (strcmp(tk->tkr_mono.clock->name, "arch_sys_counter") != 0) + return false; + + return true; +} + +/** + * update_vsyscall - update the vdso data page + * + * Increment the sequence counter, making it odd, indicating to + * userspace that an update is in progress. Update the fields used + * for coarse clocks and, if the architected system timer is in use, + * the fields used for high precision clocks. Increment the sequence + * counter again, making it even, indicating to userspace that the + * update is finished. + * + * Userspace is expected to sample seq_count before reading any other + * fields from the data page. If seq_count is odd, userspace is + * expected to wait until it becomes even. After copying data from + * the page, userspace must sample seq_count again; if it has changed + * from its previous value, userspace must retry the whole sequence. + * + * Calls to update_vsyscall are serialized by the timekeeping core. + */ +void update_vsyscall(struct timekeeper *tk) +{ + struct timespec xtime_coarse; + struct timespec64 *wtm = &tk->wall_to_monotonic; + + if (!cntvct_ok) { + /* The entry points have been zeroed, so there is no + * point in updating the data page. + */ + return; + } + + vdso_write_begin(vdso_data); + + xtime_coarse = __current_kernel_time(); + vdso_data->tk_is_cntvct = tk_is_cntvct(tk); + vdso_data->xtime_coarse_sec = xtime_coarse.tv_sec; + vdso_data->xtime_coarse_nsec = xtime_coarse.tv_nsec; + vdso_data->wtm_clock_sec = wtm->tv_sec; + vdso_data->wtm_clock_nsec = wtm->tv_nsec; + + if (vdso_data->tk_is_cntvct) { - vdso_data->cs_cycle_last = tk->tkr.cycle_last; ++ vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last; + vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_snsec = tk->tkr.xtime_nsec; - vdso_data->cs_mult = tk->tkr.mult; - vdso_data->cs_shift = tk->tkr.shift; - vdso_data->cs_mask = tk->tkr.mask; ++ vdso_data->xtime_clock_snsec = tk->tkr_mono.xtime_nsec; ++ vdso_data->cs_mult = tk->tkr_mono.mult; ++ vdso_data->cs_shift = tk->tkr_mono.shift; ++ vdso_data->cs_mask = tk->tkr_mono.mask; + } + + vdso_write_end(vdso_data); + + flush_dcache_page(virt_to_page(vdso_data)); +} + +void update_vsyscall_tz(void) +{ + vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; + vdso_data->tz_dsttime = sys_tz.tz_dsttime; + flush_dcache_page(virt_to_page(vdso_data)); +} diff --cc arch/arm/mach-omap2/cpuidle44xx.c index 7622dbb05083,57d429830e09..4b8e9f4d59ea --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@@ -14,9 -14,10 +14,9 @@@ #include #include #include - #include + #include #include -#include #include "common.h" #include "pm.h" diff --cc include/uapi/linux/bpf.h index 23df3e7f8e7d,cc47ef41076a..3df89a908ad6 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@@ -118,12 -118,9 +118,13 @@@ enum bpf_map_type enum bpf_prog_type { BPF_PROG_TYPE_UNSPEC, BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_KPROBE, }; +#define BPF_PSEUDO_MAP_FD 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ @@@ -166,45 -164,9 +168,48 @@@ enum bpf_func_id BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */ BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */ BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ + BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ + BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ + + /** + * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet + * @skb: pointer to skb + * @offset: offset within packet from skb->data + * @from: pointer where to copy bytes from + * @len: number of bytes to store into packet + * @flags: bit 0 - if true, recompute skb->csum + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_skb_store_bytes, + + /** + * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum + * @skb: pointer to skb + * @offset: offset within packet where IP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_l3_csum_replace, + + /** + * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum + * @skb: pointer to skb + * @offset: offset within packet where TCP/UDP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * bit 4 - is pseudo header + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_l4_csum_replace, + BPF_FUNC_probe_read, /* int bpf_probe_read(void *dst, int size, void *src) */ + BPF_FUNC_ktime_get_ns, /* u64 bpf_ktime_get_ns(void) */ + BPF_FUNC_trace_printk, /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */ __BPF_FUNC_MAX_ID, }; diff --cc kernel/bpf/syscall.c index ea75c654af1b,504c10b990ef..3bae6c591914 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@@ -467,10 -466,9 +468,10 @@@ struct bpf_prog *bpf_prog_get(u32 ufd fdput(f); return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_get); /* last field in 'union bpf_attr' used by this command */ - #define BPF_PROG_LOAD_LAST_FIELD log_buf + #define BPF_PROG_LOAD_LAST_FIELD kern_version static int bpf_prog_load(union bpf_attr *attr) { diff --cc kernel/events/core.c index 2fabc0627165,06917d537302..81aa3a4ece9f --- a/kernel/events/core.c +++ b/kernel/events/core.c @@@ -6449,6 -6711,49 +6711,49 @@@ static void perf_event_free_filter(stru ftrace_profile_free_filter(event); } + static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) + { + struct bpf_prog *prog; + + if (event->attr.type != PERF_TYPE_TRACEPOINT) + return -EINVAL; + + if (event->tp_event->prog) + return -EEXIST; + + if (!(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) + /* bpf programs can only be attached to kprobes */ + return -EINVAL; + + prog = bpf_prog_get(prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + - if (prog->aux->prog_type != BPF_PROG_TYPE_KPROBE) { ++ if (prog->type != BPF_PROG_TYPE_KPROBE) { + /* valid fd, but invalid bpf program type */ + bpf_prog_put(prog); + return -EINVAL; + } + + event->tp_event->prog = prog; + + return 0; + } + + static void perf_event_free_bpf_prog(struct perf_event *event) + { + struct bpf_prog *prog; + + if (!event->tp_event) + return; + + prog = event->tp_event->prog; + if (prog) { + event->tp_event->prog = NULL; + bpf_prog_put(prog); + } + } + #else static inline void perf_tp_register(void) diff --cc samples/bpf/Makefile index d24f51bca465,fe98fb226e6e..cd0a93ffdd96 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@@ -17,7 -25,10 +25,11 @@@ tracex4-objs := bpf_load.o libbpf.o tra always := $(hostprogs-y) always += sockex1_kern.o always += sockex2_kern.o +always += tcbpf1_kern.o + always += tracex1_kern.o + always += tracex2_kern.o + always += tracex3_kern.o + always += tracex4_kern.o HOSTCFLAGS += -I$(objtree)/usr/include diff --cc samples/bpf/test_verifier.c index 75d561f9fd6a,740ce97cda5e..9ab645698ffb --- a/samples/bpf/test_verifier.c +++ b/samples/bpf/test_verifier.c @@@ -767,9 -687,9 +767,9 @@@ static int test(void } printf("#%d %s ", i, tests[i].descr); - prog_fd = bpf_prog_load(BPF_PROG_TYPE_UNSPEC, prog, + prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len * sizeof(struct bpf_insn), - "GPL"); + "GPL", 0); if (tests[i].result == ACCEPT) { if (prog_fd < 0) {