From 00ce5c8a66fb2241d4fed9645b12a1cbce97b798 Mon Sep 17 00:00:00 2001 From: Deepak S Date: Thu, 29 Oct 2015 10:22:01 -0700 Subject: drm/i915/kbl: Kabylake uses the same GMS values as Skylake Reviewed-by: Damien Lespiau Signed-off-by: Deepak S Signed-off-by: Damien Lespiau Signed-off-by: Rodrigo Vivi Link: http://patchwork.freedesktop.org/patch/msgid/1446139321-2818-2-git-send-email-rodrigo.vivi@intel.com Signed-off-by: Jani Nikula --- arch/x86/kernel/early-quirks.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 9f9cc682e561..5b85bf0e23fe 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -547,6 +547,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_CHV_IDS(&chv_stolen_funcs), INTEL_SKL_IDS(&gen9_stolen_funcs), INTEL_BXT_IDS(&gen9_stolen_funcs), + INTEL_KBL_IDS(&gen9_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) -- cgit v1.2.3 From b05086c77a162dd8ef79606cb4723f1fc1448bb1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 25 Nov 2015 14:13:11 -0500 Subject: ftrace: Add variable ftrace_expected for archs to show expected code When an anomaly is found while modifying function code, ftrace_bug() is called which disables the function tracing infrastructure and reports information about what failed. If the code that is to be replaced does not match what is expected, then actual code is shown. Currently there is no arch generic way to show what was expected. Add a new variable pointer calld ftrace_expected that the arch code can set to point to what it expected so that ftrace_bug() can report the actual text as well as the text that was expected to be there. Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 9 +++++++++ include/linux/ftrace.h | 6 ++++++ kernel/trace/ftrace.c | 9 +++++++-- 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 311bcf338f07..909da012406d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -105,6 +105,8 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, { unsigned char replaced[MCOUNT_INSN_SIZE]; + ftrace_expected = old_code; + /* * Note: Due to modules and __init, code can * disappear and change, we need to protect against faulting @@ -154,6 +156,8 @@ int ftrace_make_nop(struct module *mod, if (addr == MCOUNT_ADDR) return ftrace_modify_code_direct(rec->ip, old, new); + ftrace_expected = NULL; + /* Normal cases use add_brk_on_nop */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; @@ -220,6 +224,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); + ftrace_expected = NULL; return -EINVAL; } @@ -314,6 +319,8 @@ static int add_break(unsigned long ip, const char *old) if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; + ftrace_expected = old; + /* Make sure it is what we expect it to be */ if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) return -EINVAL; @@ -413,6 +420,8 @@ static int remove_breakpoint(struct dyn_ftrace *rec) ftrace_addr = ftrace_get_addr_curr(rec); nop = ftrace_call_replace(ip, ftrace_addr); + ftrace_expected = nop; + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 870c8eea38cd..134f8d45b35b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -305,6 +305,12 @@ enum ftrace_bug_type { }; extern enum ftrace_bug_type ftrace_bug_type; +/* + * Archs can set this to point to a variable that holds the value that was + * expected at the call site before calling ftrace_bug(). + */ +extern const void *ftrace_expected; + void ftrace_bug(int err, struct dyn_ftrace *rec); struct seq_file; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b95efcac9dfe..7870c03b4c4d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1940,7 +1940,7 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash); } -static void print_ip_ins(const char *fmt, unsigned char *p) +static void print_ip_ins(const char *fmt, const unsigned char *p) { int i; @@ -1954,6 +1954,7 @@ static struct ftrace_ops * ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); enum ftrace_bug_type ftrace_bug_type; +const void *ftrace_expected; static void print_bug_type(void) { @@ -2001,8 +2002,12 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec) FTRACE_WARN_ON_ONCE(1); pr_info("ftrace failed to modify "); print_ip_sym(ip); - print_ip_ins(" actual: ", (unsigned char *)ip); + print_ip_ins(" actual: ", (unsigned char *)ip); pr_cont("\n"); + if (ftrace_expected) { + print_ip_ins(" expected: ", ftrace_expected); + pr_cont("\n"); + } break; case -EPERM: FTRACE_WARN_ON_ONCE(1); -- cgit v1.2.3 From 7523e4dc5057e157212b4741abd6256e03404cf1 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 26 Nov 2015 09:44:08 +1030 Subject: module: use a structure to encapsulate layout. Makes it easier to handle init vs core cleanly, though the change is fairly invasive across random architectures. It simplifies the rbtree code immediately, however, while keeping the core data together in the same cachline (now iff the rbtree code is enabled). Acked-by: Peter Zijlstra Reviewed-by: Josh Poimboeuf Signed-off-by: Rusty Russell Signed-off-by: Jiri Kosina --- arch/alpha/kernel/module.c | 2 +- arch/arc/kernel/unwind.c | 4 +- arch/arm/kernel/module-plts.c | 2 +- arch/avr32/kernel/module.c | 12 +-- arch/ia64/kernel/module.c | 14 +-- arch/metag/kernel/module.c | 4 +- arch/mips/kernel/vpe.c | 6 +- arch/parisc/kernel/module.c | 32 +++---- arch/powerpc/kernel/module_32.c | 6 +- arch/s390/kernel/module.c | 22 ++--- arch/x86/kernel/livepatch.c | 6 +- include/linux/module.h | 64 ++++++------- kernel/debug/kdb/kdb_main.c | 4 +- kernel/module.c | 199 +++++++++++++++++++--------------------- 14 files changed, 178 insertions(+), 199 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index 2fd00b7077e4..936bc8f89a67 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -160,7 +160,7 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, /* The small sections were sorted to the end of the segment. The following should definitely cover them. */ - gp = (u64)me->module_core + me->core_size - 0x8000; + gp = (u64)me->core_layout.base + me->core_layout.size - 0x8000; got = sechdrs[me->arch.gotsecindex].sh_addr; for (i = 0; i < n; i++) { diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 93c6ea52b671..e0034a6656ef 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -372,8 +372,8 @@ void *unwind_add_table(struct module *module, const void *table_start, return NULL; init_unwind_table(table, module->name, - module->module_core, module->core_size, - module->module_init, module->init_size, + module->core_layout.base, module->core_layout.size, + module->init_layout.base, module->init_layout.size, table_start, table_size, NULL, 0); diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index 097e2e201b9f..0c7efc3446c0 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -32,7 +32,7 @@ struct plt_entries { static bool in_init(const struct module *mod, u32 addr) { - return addr - (u32)mod->module_init < mod->init_size; + return addr - (u32)mod->init_layout.base < mod->init_layout.size; } u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 164efa009e5b..2b4c54c04cb6 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -118,9 +118,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, * Increase core size to make room for GOT and set start * offset for GOT. */ - module->core_size = ALIGN(module->core_size, 4); - module->arch.got_offset = module->core_size; - module->core_size += module->arch.got_size; + module->core_layout.size = ALIGN(module->core_layout.size, 4); + module->arch.got_offset = module->core_layout.size; + module->core_layout.size += module->arch.got_size; return 0; @@ -177,7 +177,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, if (!info->got_initialized) { Elf32_Addr *gotent; - gotent = (module->module_core + gotent = (module->core_layout.base + module->arch.got_offset + info->got_offset); *gotent = relocation; @@ -255,8 +255,8 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, */ pr_debug("GOTPC: PC=0x%x, got_offset=0x%lx, core=0x%p\n", relocation, module->arch.got_offset, - module->module_core); - relocation -= ((unsigned long)module->module_core + module->core_layout.base); + relocation -= ((unsigned long)module->core_layout.base + module->arch.got_offset); *location = relocation; break; diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index b15933c31b2f..6ab0ae7d6535 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -486,13 +486,13 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, static inline int in_init (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_init < mod->init_size; + return addr - (uint64_t) mod->init_layout.base < mod->init_layout.size; } static inline int in_core (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_core < mod->core_size; + return addr - (uint64_t) mod->core_layout.base < mod->core_layout.size; } static inline int @@ -675,7 +675,7 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend, break; case RV_BDREL: - val -= (uint64_t) (in_init(mod, val) ? mod->module_init : mod->module_core); + val -= (uint64_t) (in_init(mod, val) ? mod->init_layout.base : mod->core_layout.base); break; case RV_LTV: @@ -810,15 +810,15 @@ apply_relocate_add (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symind * addresses have been selected... */ uint64_t gp; - if (mod->core_size > MAX_LTOFF) + if (mod->core_layout.size > MAX_LTOFF) /* * This takes advantage of fact that SHF_ARCH_SMALL gets allocated * at the end of the module. */ - gp = mod->core_size - MAX_LTOFF / 2; + gp = mod->core_layout.size - MAX_LTOFF / 2; else - gp = mod->core_size / 2; - gp = (uint64_t) mod->module_core + ((gp + 7) & -8); + gp = mod->core_layout.size / 2; + gp = (uint64_t) mod->core_layout.base + ((gp + 7) & -8); mod->arch.gp = gp; DEBUGP("%s: placing gp at 0x%lx\n", __func__, gp); } diff --git a/arch/metag/kernel/module.c b/arch/metag/kernel/module.c index 986331cd0a52..bb8dfba9a763 100644 --- a/arch/metag/kernel/module.c +++ b/arch/metag/kernel/module.c @@ -176,8 +176,8 @@ static uint32_t do_plt_call(void *location, Elf32_Addr val, tramp[1] = 0xac000001 | ((val & 0x0000ffff) << 3); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 9067b651c7a2..544ea21bfef9 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -205,11 +205,11 @@ static void layout_sections(struct module *mod, const Elf_Ehdr *hdr, || s->sh_entsize != ~0UL) continue; s->sh_entsize = - get_offset((unsigned long *)&mod->core_size, s); + get_offset((unsigned long *)&mod->core_layout.size, s); } if (m == 0) - mod->core_text_size = mod->core_size; + mod->core_layout.text_size = mod->core_layout.size; } } @@ -641,7 +641,7 @@ static int vpe_elfload(struct vpe *v) layout_sections(&mod, hdr, sechdrs, secstrings); } - v->load_addr = alloc_progmem(mod.core_size); + v->load_addr = alloc_progmem(mod.core_layout.size); if (!v->load_addr) return -ENOMEM; diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 3c63a820fcda..b9d75d9fa9ac 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -42,9 +42,9 @@ * We are not doing SEGREL32 handling correctly. According to the ABI, we * should do a value offset, like this: * if (in_init(me, (void *)val)) - * val -= (uint32_t)me->module_init; + * val -= (uint32_t)me->init_layout.base; * else - * val -= (uint32_t)me->module_core; + * val -= (uint32_t)me->core_layout.base; * However, SEGREL32 is used only for PARISC unwind entries, and we want * those entries to have an absolute address, and not just an offset. * @@ -100,14 +100,14 @@ * or init pieces the location is */ static inline int in_init(struct module *me, void *loc) { - return (loc >= me->module_init && - loc <= (me->module_init + me->init_size)); + return (loc >= me->init_layout.base && + loc <= (me->init_layout.base + me->init_layout.size)); } static inline int in_core(struct module *me, void *loc) { - return (loc >= me->module_core && - loc <= (me->module_core + me->core_size)); + return (loc >= me->core_layout.base && + loc <= (me->core_layout.base + me->core_layout.size)); } static inline int in_local(struct module *me, void *loc) @@ -367,13 +367,13 @@ int module_frob_arch_sections(CONST Elf_Ehdr *hdr, } /* align things a bit */ - me->core_size = ALIGN(me->core_size, 16); - me->arch.got_offset = me->core_size; - me->core_size += gots * sizeof(struct got_entry); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += gots * sizeof(struct got_entry); - me->core_size = ALIGN(me->core_size, 16); - me->arch.fdesc_offset = me->core_size; - me->core_size += fdescs * sizeof(Elf_Fdesc); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.fdesc_offset = me->core_layout.size; + me->core_layout.size += fdescs * sizeof(Elf_Fdesc); me->arch.got_max = gots; me->arch.fdesc_max = fdescs; @@ -391,7 +391,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) BUG_ON(value == 0); - got = me->module_core + me->arch.got_offset; + got = me->core_layout.base + me->arch.got_offset; for (i = 0; got[i].addr; i++) if (got[i].addr == value) goto out; @@ -409,7 +409,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) #ifdef CONFIG_64BIT static Elf_Addr get_fdesc(struct module *me, unsigned long value) { - Elf_Fdesc *fdesc = me->module_core + me->arch.fdesc_offset; + Elf_Fdesc *fdesc = me->core_layout.base + me->arch.fdesc_offset; if (!value) { printk(KERN_ERR "%s: zero OPD requested!\n", me->name); @@ -427,7 +427,7 @@ static Elf_Addr get_fdesc(struct module *me, unsigned long value) /* Create new one */ fdesc->addr = value; - fdesc->gp = (Elf_Addr)me->module_core + me->arch.got_offset; + fdesc->gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; return (Elf_Addr)fdesc; } #endif /* CONFIG_64BIT */ @@ -839,7 +839,7 @@ register_unwind_table(struct module *me, table = (unsigned char *)sechdrs[me->arch.unwind_section].sh_addr; end = table + sechdrs[me->arch.unwind_section].sh_size; - gp = (Elf_Addr)me->module_core + me->arch.got_offset; + gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; DEBUGP("register_unwind_table(), sect = %d at 0x%p - 0x%p (gp=0x%lx)\n", me->arch.unwind_section, table, end, gp); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index c94d2e018d84..2c01665eb410 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -188,8 +188,8 @@ static uint32_t do_plt_call(void *location, pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; @@ -296,7 +296,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, } #ifdef CONFIG_DYNAMIC_FTRACE module->arch.tramp = - do_plt_call(module->module_core, + do_plt_call(module->core_layout.base, (unsigned long)ftrace_caller, sechdrs, module); #endif diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 0c1a679314dd..7873e171457c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -159,11 +159,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, /* Increase core size by size of got & plt and set start offsets for got and plt. */ - me->core_size = ALIGN(me->core_size, 4); - me->arch.got_offset = me->core_size; - me->core_size += me->arch.got_size; - me->arch.plt_offset = me->core_size; - me->core_size += me->arch.plt_size; + me->core_layout.size = ALIGN(me->core_layout.size, 4); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += me->arch.got_size; + me->arch.plt_offset = me->core_layout.size; + me->core_layout.size += me->arch.plt_size; return 0; } @@ -279,7 +279,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, if (info->got_initialized == 0) { Elf_Addr *gotent; - gotent = me->module_core + me->arch.got_offset + + gotent = me->core_layout.base + me->arch.got_offset + info->got_offset; *gotent = val; info->got_initialized = 1; @@ -302,7 +302,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, rc = apply_rela_bits(loc, val, 0, 64, 0); else if (r_type == R_390_GOTENT || r_type == R_390_GOTPLTENT) { - val += (Elf_Addr) me->module_core - loc; + val += (Elf_Addr) me->core_layout.base - loc; rc = apply_rela_bits(loc, val, 1, 32, 1); } break; @@ -315,7 +315,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { unsigned int *ip; - ip = me->module_core + me->arch.plt_offset + + ip = me->core_layout.base + me->arch.plt_offset + info->plt_offset; ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ ip[1] = 0x100a0004; @@ -334,7 +334,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val - loc + 0xffffUL < 0x1ffffeUL) || (r_type == R_390_PLT32DBL && val - loc + 0xffffffffULL < 0x1fffffffeULL))) - val = (Elf_Addr) me->module_core + + val = (Elf_Addr) me->core_layout.base + me->arch.plt_offset + info->plt_offset; val += rela->r_addend - loc; @@ -356,7 +356,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_GOTOFF32: /* 32 bit offset to GOT. */ case R_390_GOTOFF64: /* 64 bit offset to GOT. */ val = val + rela->r_addend - - ((Elf_Addr) me->module_core + me->arch.got_offset); + ((Elf_Addr) me->core_layout.base + me->arch.got_offset); if (r_type == R_390_GOTOFF16) rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_GOTOFF32) @@ -366,7 +366,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, break; case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ - val = (Elf_Addr) me->module_core + me->arch.got_offset + + val = (Elf_Addr) me->core_layout.base + me->arch.got_offset + rela->r_addend - loc; if (r_type == R_390_GOTPC) rc = apply_rela_bits(loc, val, 1, 32, 0); diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c index d1d35ccffed3..bcc06e82a593 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -41,8 +41,8 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, int ret, numpages, size = 4; bool readonly; unsigned long val; - unsigned long core = (unsigned long)mod->module_core; - unsigned long core_size = mod->core_size; + unsigned long core = (unsigned long)mod->core_layout.base; + unsigned long core_size = mod->core_layout.size; switch (type) { case R_X86_64_NONE: @@ -72,7 +72,7 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, readonly = false; #ifdef CONFIG_DEBUG_SET_MODULE_RONX - if (loc < core + mod->core_ro_size) + if (loc < core + mod->core_layout.ro_size) readonly = true; #endif diff --git a/include/linux/module.h b/include/linux/module.h index 3a19c79918e0..6e68e8cf4d0d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -302,6 +302,28 @@ struct mod_tree_node { struct latch_tree_node node; }; +struct module_layout { + /* The actual code + data. */ + void *base; + /* Total size. */ + unsigned int size; + /* The size of the executable code. */ + unsigned int text_size; + /* Size of RO section of the module (text+rodata) */ + unsigned int ro_size; + +#ifdef CONFIG_MODULES_TREE_LOOKUP + struct mod_tree_node mtn; +#endif +}; + +#ifdef CONFIG_MODULES_TREE_LOOKUP +/* Only touch one cacheline for common rbtree-for-core-layout case. */ +#define __module_layout_align ____cacheline_aligned +#else +#define __module_layout_align +#endif + struct module { enum module_state state; @@ -366,37 +388,9 @@ struct module { /* Startup function. */ int (*init)(void); - /* - * If this is non-NULL, vfree() after init() returns. - * - * Cacheline align here, such that: - * module_init, module_core, init_size, core_size, - * init_text_size, core_text_size and mtn_core::{mod,node[0]} - * are on the same cacheline. - */ - void *module_init ____cacheline_aligned; - - /* Here is the actual code + data, vfree'd on unload. */ - void *module_core; - - /* Here are the sizes of the init and core sections */ - unsigned int init_size, core_size; - - /* The size of the executable code in each section. */ - unsigned int init_text_size, core_text_size; - -#ifdef CONFIG_MODULES_TREE_LOOKUP - /* - * We want mtn_core::{mod,node[0]} to be in the same cacheline as the - * above entries such that a regular lookup will only touch one - * cacheline. - */ - struct mod_tree_node mtn_core; - struct mod_tree_node mtn_init; -#endif - - /* Size of RO sections of the module (text+rodata) */ - unsigned int init_ro_size, core_ro_size; + /* Core layout: rbtree is accessed frequently, so keep together. */ + struct module_layout core_layout __module_layout_align; + struct module_layout init_layout; /* Arch-specific module values */ struct mod_arch_specific arch; @@ -505,15 +499,15 @@ bool is_module_text_address(unsigned long addr); static inline bool within_module_core(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->module_core <= addr && - addr < (unsigned long)mod->module_core + mod->core_size; + return (unsigned long)mod->core_layout.base <= addr && + addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->module_init <= addr && - addr < (unsigned long)mod->module_init + mod->init_size; + return (unsigned long)mod->init_layout.base <= addr && + addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; } static inline bool within_module(unsigned long addr, const struct module *mod) diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 4121345498e0..2a20c0dfdafc 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2021,7 +2021,7 @@ static int kdb_lsmod(int argc, const char **argv) continue; kdb_printf("%-20s%8u 0x%p ", mod->name, - mod->core_size, (void *)mod); + mod->core_layout.size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD kdb_printf("%4d ", module_refcount(mod)); #endif @@ -2031,7 +2031,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); - kdb_printf(" 0x%p", mod->module_core); + kdb_printf(" 0x%p", mod->core_layout.base); #ifdef CONFIG_MODULE_UNLOAD { diff --git a/kernel/module.c b/kernel/module.c index 14b224967e7b..a0a3d6d9d5e8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -108,13 +108,6 @@ static LIST_HEAD(modules); * Use a latched RB-tree for __module_address(); this allows us to use * RCU-sched lookups of the address from any context. * - * Because modules have two address ranges: init and core, we need two - * latch_tree_nodes entries. Therefore we need the back-pointer from - * mod_tree_node. - * - * Because init ranges are short lived we mark them unlikely and have placed - * them outside the critical cacheline in struct module. - * * This is conditional on PERF_EVENTS || TRACING because those can really hit * __module_address() hard by doing a lot of stack unwinding; potentially from * NMI context. @@ -122,24 +115,16 @@ static LIST_HEAD(modules); static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->module_init; - - return (unsigned long)mod->module_core; + return (unsigned long)layout->base; } static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; - - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->init_size; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - return (unsigned long)mod->core_size; + return (unsigned long)layout->size; } static __always_inline bool @@ -197,23 +182,23 @@ static void __mod_tree_remove(struct mod_tree_node *node) */ static void mod_tree_insert(struct module *mod) { - mod->mtn_core.mod = mod; - mod->mtn_init.mod = mod; + mod->core_layout.mtn.mod = mod; + mod->init_layout.mtn.mod = mod; - __mod_tree_insert(&mod->mtn_core); - if (mod->init_size) - __mod_tree_insert(&mod->mtn_init); + __mod_tree_insert(&mod->core_layout.mtn); + if (mod->init_layout.size) + __mod_tree_insert(&mod->init_layout.mtn); } static void mod_tree_remove_init(struct module *mod) { - if (mod->init_size) - __mod_tree_remove(&mod->mtn_init); + if (mod->init_layout.size) + __mod_tree_remove(&mod->init_layout.mtn); } static void mod_tree_remove(struct module *mod) { - __mod_tree_remove(&mod->mtn_core); + __mod_tree_remove(&mod->core_layout.mtn); mod_tree_remove_init(mod); } @@ -267,9 +252,9 @@ static void __mod_update_bounds(void *base, unsigned int size) static void mod_update_bounds(struct module *mod) { - __mod_update_bounds(mod->module_core, mod->core_size); - if (mod->init_size) - __mod_update_bounds(mod->module_init, mod->init_size); + __mod_update_bounds(mod->core_layout.base, mod->core_layout.size); + if (mod->init_layout.size) + __mod_update_bounds(mod->init_layout.base, mod->init_layout.size); } #ifdef CONFIG_KGDB_KDB @@ -1214,7 +1199,7 @@ struct module_attribute module_uevent = static ssize_t show_coresize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->core_size); + return sprintf(buffer, "%u\n", mk->mod->core_layout.size); } static struct module_attribute modinfo_coresize = @@ -1223,7 +1208,7 @@ static struct module_attribute modinfo_coresize = static ssize_t show_initsize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->init_size); + return sprintf(buffer, "%u\n", mk->mod->init_layout.size); } static struct module_attribute modinfo_initsize = @@ -1917,29 +1902,29 @@ static void set_section_ro_nx(void *base, static void set_module_core_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_core, mod->core_text_size, - mod->core_ro_size, mod->core_size, + set_section_ro_nx(mod->core_layout.base, mod->core_layout.text_size, + mod->core_layout.ro_size, mod->core_layout.size, set_memory_ro, set_memory_nx); } static void unset_module_core_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_core, mod->core_text_size, - mod->core_ro_size, mod->core_size, + set_section_ro_nx(mod->core_layout.base, mod->core_layout.text_size, + mod->core_layout.ro_size, mod->core_layout.size, set_memory_rw, set_memory_x); } static void set_module_init_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_init, mod->init_text_size, - mod->init_ro_size, mod->init_size, + set_section_ro_nx(mod->init_layout.base, mod->init_layout.text_size, + mod->init_layout.ro_size, mod->init_layout.size, set_memory_ro, set_memory_nx); } static void unset_module_init_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_init, mod->init_text_size, - mod->init_ro_size, mod->init_size, + set_section_ro_nx(mod->init_layout.base, mod->init_layout.text_size, + mod->init_layout.ro_size, mod->init_layout.size, set_memory_rw, set_memory_x); } @@ -1952,14 +1937,14 @@ void set_all_modules_text_rw(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, + if ((mod->core_layout.base) && (mod->core_layout.text_size)) { + set_page_attributes(mod->core_layout.base, + mod->core_layout.base + mod->core_layout.text_size, set_memory_rw); } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, + if ((mod->init_layout.base) && (mod->init_layout.text_size)) { + set_page_attributes(mod->init_layout.base, + mod->init_layout.base + mod->init_layout.text_size, set_memory_rw); } } @@ -1975,14 +1960,14 @@ void set_all_modules_text_ro(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, + if ((mod->core_layout.base) && (mod->core_layout.text_size)) { + set_page_attributes(mod->core_layout.base, + mod->core_layout.base + mod->core_layout.text_size, set_memory_ro); } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, + if ((mod->init_layout.base) && (mod->init_layout.text_size)) { + set_page_attributes(mod->init_layout.base, + mod->init_layout.base + mod->init_layout.text_size, set_memory_ro); } } @@ -2047,16 +2032,16 @@ static void free_module(struct module *mod) /* This may be NULL, but that's OK */ unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - module_memfree(mod->module_init); + module_memfree(mod->init_layout.base); kfree(mod->args); percpu_modfree(mod); /* Free lock-classes; relies on the preceding sync_rcu(). */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); /* Finally, free the core (containing the module structure) */ unset_module_core_ro_nx(mod); - module_memfree(mod->module_core); + module_memfree(mod->core_layout.base); #ifdef CONFIG_MPU update_protections(current->mm); @@ -2259,20 +2244,20 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || strstarts(sname, ".init")) continue; - s->sh_entsize = get_offset(mod, &mod->core_size, s, i); + s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->core_size = debug_align(mod->core_size); - mod->core_text_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.text_size = mod->core_layout.size; break; case 1: /* RO: text and ro-data */ - mod->core_size = debug_align(mod->core_size); - mod->core_ro_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.ro_size = mod->core_layout.size; break; case 3: /* whole core */ - mod->core_size = debug_align(mod->core_size); + mod->core_layout.size = debug_align(mod->core_layout.size); break; } } @@ -2288,21 +2273,21 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || !strstarts(sname, ".init")) continue; - s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) + s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i) | INIT_OFFSET_MASK); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->init_size = debug_align(mod->init_size); - mod->init_text_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.text_size = mod->init_layout.size; break; case 1: /* RO: text and ro-data */ - mod->init_size = debug_align(mod->init_size); - mod->init_ro_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.ro_size = mod->init_layout.size; break; case 3: /* whole init */ - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); break; } } @@ -2477,7 +2462,7 @@ static void layout_symtab(struct module *mod, struct load_info *info) /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; - symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, + symsect->sh_entsize = get_offset(mod, &mod->init_layout.size, symsect, info->index.sym) | INIT_OFFSET_MASK; pr_debug("\t%s\n", info->secstrings + symsect->sh_name); @@ -2494,16 +2479,16 @@ static void layout_symtab(struct module *mod, struct load_info *info) } /* Append room for core symbols at end of core part. */ - info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); - info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); - mod->core_size += strtab_size; - mod->core_size = debug_align(mod->core_size); + info->symoffs = ALIGN(mod->core_layout.size, symsect->sh_addralign ?: 1); + info->stroffs = mod->core_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); + mod->core_layout.size += strtab_size; + mod->core_layout.size = debug_align(mod->core_layout.size); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; - strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, + strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect, info->index.str) | INIT_OFFSET_MASK; - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); } @@ -2524,8 +2509,8 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) for (i = 0; i < mod->num_symtab; i++) mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - mod->core_symtab = dst = mod->module_core + info->symoffs; - mod->core_strtab = s = mod->module_core + info->stroffs; + mod->core_symtab = dst = mod->core_layout.base + info->symoffs; + mod->core_strtab = s = mod->core_layout.base + info->stroffs; src = mod->symtab; for (ndst = i = 0; i < mod->num_symtab; i++) { if (i == 0 || @@ -2975,7 +2960,7 @@ static int move_module(struct module *mod, struct load_info *info) void *ptr; /* Do the allocs. */ - ptr = module_alloc(mod->core_size); + ptr = module_alloc(mod->core_layout.size); /* * The pointer to this block is stored in the module structure * which is inside the block. Just mark it as not being a @@ -2985,11 +2970,11 @@ static int move_module(struct module *mod, struct load_info *info) if (!ptr) return -ENOMEM; - memset(ptr, 0, mod->core_size); - mod->module_core = ptr; + memset(ptr, 0, mod->core_layout.size); + mod->core_layout.base = ptr; - if (mod->init_size) { - ptr = module_alloc(mod->init_size); + if (mod->init_layout.size) { + ptr = module_alloc(mod->init_layout.size); /* * The pointer to this block is stored in the module structure * which is inside the block. This block doesn't need to be @@ -2998,13 +2983,13 @@ static int move_module(struct module *mod, struct load_info *info) */ kmemleak_ignore(ptr); if (!ptr) { - module_memfree(mod->module_core); + module_memfree(mod->core_layout.base); return -ENOMEM; } - memset(ptr, 0, mod->init_size); - mod->module_init = ptr; + memset(ptr, 0, mod->init_layout.size); + mod->init_layout.base = ptr; } else - mod->module_init = NULL; + mod->init_layout.base = NULL; /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); @@ -3016,10 +3001,10 @@ static int move_module(struct module *mod, struct load_info *info) continue; if (shdr->sh_entsize & INIT_OFFSET_MASK) - dest = mod->module_init + dest = mod->init_layout.base + (shdr->sh_entsize & ~INIT_OFFSET_MASK); else - dest = mod->module_core + shdr->sh_entsize; + dest = mod->core_layout.base + shdr->sh_entsize; if (shdr->sh_type != SHT_NOBITS) memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); @@ -3081,12 +3066,12 @@ static void flush_module_icache(const struct module *mod) * Do it before processing of module parameters, so the module * can provide parameter accessor functions of its own. */ - if (mod->module_init) - flush_icache_range((unsigned long)mod->module_init, - (unsigned long)mod->module_init - + mod->init_size); - flush_icache_range((unsigned long)mod->module_core, - (unsigned long)mod->module_core + mod->core_size); + if (mod->init_layout.base) + flush_icache_range((unsigned long)mod->init_layout.base, + (unsigned long)mod->init_layout.base + + mod->init_layout.size); + flush_icache_range((unsigned long)mod->core_layout.base, + (unsigned long)mod->core_layout.base + mod->core_layout.size); set_fs(old_fs); } @@ -3144,8 +3129,8 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); - module_memfree(mod->module_init); - module_memfree(mod->module_core); + module_memfree(mod->init_layout.base); + module_memfree(mod->core_layout.base); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -3232,7 +3217,7 @@ static noinline int do_init_module(struct module *mod) ret = -ENOMEM; goto fail; } - freeinit->module_init = mod->module_init; + freeinit->module_init = mod->init_layout.base; /* * We want to find out whether @mod uses async during init. Clear @@ -3292,10 +3277,10 @@ static noinline int do_init_module(struct module *mod) mod_tree_remove_init(mod); unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - mod->module_init = NULL; - mod->init_size = 0; - mod->init_ro_size = 0; - mod->init_text_size = 0; + mod->init_layout.base = NULL; + mod->init_layout.size = 0; + mod->init_layout.ro_size = 0; + mod->init_layout.text_size = 0; /* * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we @@ -3575,7 +3560,7 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_unlock(&module_mutex); free_module: /* Free lock-classes; relies on the preceding sync_rcu() */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); module_deallocate(mod, info); free_copy: @@ -3653,9 +3638,9 @@ static const char *get_ksymbol(struct module *mod, /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) - nextval = (unsigned long)mod->module_init+mod->init_text_size; + nextval = (unsigned long)mod->init_layout.base+mod->init_layout.text_size; else - nextval = (unsigned long)mod->module_core+mod->core_text_size; + nextval = (unsigned long)mod->core_layout.base+mod->core_layout.text_size; /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ @@ -3902,7 +3887,7 @@ static int m_show(struct seq_file *m, void *p) return 0; seq_printf(m, "%s %u", - mod->name, mod->init_size + mod->core_size); + mod->name, mod->init_layout.size + mod->core_layout.size); print_unload_info(m, mod); /* Informative for users. */ @@ -3911,7 +3896,7 @@ static int m_show(struct seq_file *m, void *p) mod->state == MODULE_STATE_COMING ? "Loading" : "Live"); /* Used by oprofile and other similar tools. */ - seq_printf(m, " 0x%pK", mod->module_core); + seq_printf(m, " 0x%pK", mod->core_layout.base); /* Taints info */ if (mod->taints) @@ -4054,8 +4039,8 @@ struct module *__module_text_address(unsigned long addr) struct module *mod = __module_address(addr); if (mod) { /* Make sure it's within the text section. */ - if (!within(addr, mod->module_init, mod->init_text_size) - && !within(addr, mod->module_core, mod->core_text_size)) + if (!within(addr, mod->init_layout.base, mod->init_layout.text_size) + && !within(addr, mod->core_layout.base, mod->core_layout.text_size)) mod = NULL; } return mod; -- cgit v1.2.3 From b56b36ee6751abe7fb3890681e86fc8de2122953 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 3 Dec 2015 16:33:26 -0600 Subject: livepatch: Cleanup module page permission changes Calling set_memory_rw() and set_memory_ro() for every iteration of the loop in klp_write_object_relocations() is messy, inefficient, and error-prone. Change all the read-only pages to read-write before the loop and convert them back to read-only again afterwards. Suggested-by: Miroslav Benes Signed-off-by: Josh Poimboeuf Reviewed-by: Petr Mladek Signed-off-by: Jiri Kosina --- arch/x86/kernel/livepatch.c | 25 ++----------------------- kernel/livepatch/core.c | 16 +++++++++++----- 2 files changed, 13 insertions(+), 28 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c index bcc06e82a593..92fc1a51f994 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -20,8 +20,6 @@ #include #include -#include -#include #include #include @@ -38,8 +36,7 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, unsigned long loc, unsigned long value) { - int ret, numpages, size = 4; - bool readonly; + size_t size = 4; unsigned long val; unsigned long core = (unsigned long)mod->core_layout.base; unsigned long core_size = mod->core_layout.size; @@ -69,23 +66,5 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, /* loc does not point to any symbol inside the module */ return -EINVAL; - readonly = false; - -#ifdef CONFIG_DEBUG_SET_MODULE_RONX - if (loc < core + mod->core_layout.ro_size) - readonly = true; -#endif - - /* determine if the relocation spans a page boundary */ - numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2; - - if (readonly) - set_memory_rw(loc & PAGE_MASK, numpages); - - ret = probe_kernel_write((void *)loc, &val, size); - - if (readonly) - set_memory_ro(loc & PAGE_MASK, numpages); - - return ret; + return probe_kernel_write((void *)loc, &val, size); } diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 94893e844e44..bc2c85c064c1 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -28,6 +28,7 @@ #include #include #include +#include /** * struct klp_ops - structure for tracking registered ftrace ops structs @@ -232,7 +233,7 @@ static int klp_find_external_symbol(struct module *pmod, const char *name, static int klp_write_object_relocations(struct module *pmod, struct klp_object *obj) { - int ret; + int ret = 0; unsigned long val; struct klp_reloc *reloc; @@ -242,13 +243,16 @@ static int klp_write_object_relocations(struct module *pmod, if (WARN_ON(!obj->relocs)) return -EINVAL; + module_disable_ro(pmod); + for (reloc = obj->relocs; reloc->name; reloc++) { /* discover the address of the referenced symbol */ if (reloc->external) { if (reloc->sympos > 0) { pr_err("non-zero sympos for external reloc symbol '%s' is not supported\n", reloc->name); - return -EINVAL; + ret = -EINVAL; + goto out; } ret = klp_find_external_symbol(pmod, reloc->name, &val); } else @@ -257,18 +261,20 @@ static int klp_write_object_relocations(struct module *pmod, reloc->sympos, &val); if (ret) - return ret; + goto out; ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc, val + reloc->addend); if (ret) { pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n", reloc->name, val, ret); - return ret; + goto out; } } - return 0; +out: + module_enable_ro(pmod); + return ret; } static void notrace klp_ftrace_handler(unsigned long ip, -- cgit v1.2.3 From b25472f9b96159cc0b9b7ed449448805973cd789 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 5 Dec 2015 22:04:48 -0500 Subject: new helpers: no_seek_end_llseek{,_size}() Signed-off-by: Al Viro --- arch/sparc/kernel/mdesc.c | 20 ++-------------- arch/x86/kernel/cpuid.c | 24 +------------------- arch/x86/kernel/msr.c | 24 +------------------- drivers/char/nwflash.c | 31 +------------------------ drivers/net/wireless/ti/wlcore/debugfs.c | 17 +------------- drivers/s390/char/vmur.c | 15 +----------- drivers/s390/char/zcore.c | 13 +---------- drivers/usb/core/devices.c | 26 +-------------------- drivers/usb/core/devio.c | 26 +-------------------- drivers/usb/host/uhci-debug.c | 23 ++----------------- drivers/usb/misc/sisusbvga/sisusb.c | 16 +------------ fs/read_write.c | 39 ++++++++++++++++++++++++++++++++ include/linux/fs.h | 2 ++ 13 files changed, 54 insertions(+), 222 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 6f80936e0eea..11228861d9b4 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -1033,25 +1033,9 @@ static ssize_t mdesc_read(struct file *file, char __user *buf, static loff_t mdesc_llseek(struct file *file, loff_t offset, int whence) { - struct mdesc_handle *hp; - - switch (whence) { - case SEEK_CUR: - offset += file->f_pos; - break; - case SEEK_SET: - break; - default: - return -EINVAL; - } - - hp = file->private_data; - if (offset > hp->handle_size) - return -EINVAL; - else - file->f_pos = offset; + struct mdesc_handle *hp = file->private_data; - return offset; + return no_seek_end_llseek_size(file, offset, whence, hp->handle_size); } /* mdesc_close() - /dev/mdesc is being closed, release the reference to diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index bd3507da39f0..2836de390f95 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -58,28 +58,6 @@ static void cpuid_smp_cpuid(void *cmd_block) &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx); } -static loff_t cpuid_seek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - struct inode *inode = file->f_mapping->host; - - mutex_lock(&inode->i_mutex); - switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t cpuid_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -132,7 +110,7 @@ static int cpuid_open(struct inode *inode, struct file *file) */ static const struct file_operations cpuid_fops = { .owner = THIS_MODULE, - .llseek = cpuid_seek, + .llseek = no_seek_end_llseek, .read = cpuid_read, .open = cpuid_open, }; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 113e70784854..64f9616f93f1 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -45,28 +45,6 @@ static struct class *msr_class; -static loff_t msr_seek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - struct inode *inode = file_inode(file); - - mutex_lock(&inode->i_mutex); - switch (orig) { - case SEEK_SET: - file->f_pos = offset; - ret = file->f_pos; - break; - case SEEK_CUR: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t msr_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -194,7 +172,7 @@ static int msr_open(struct inode *inode, struct file *file) */ static const struct file_operations msr_fops = { .owner = THIS_MODULE, - .llseek = msr_seek, + .llseek = no_seek_end_llseek, .read = msr_read, .write = msr_write, .open = msr_open, diff --git a/drivers/char/nwflash.c b/drivers/char/nwflash.c index e371480d3639..dbe598de9b74 100644 --- a/drivers/char/nwflash.c +++ b/drivers/char/nwflash.c @@ -277,36 +277,7 @@ static loff_t flash_llseek(struct file *file, loff_t offset, int orig) printk(KERN_DEBUG "flash_llseek: offset=0x%X, orig=0x%X.\n", (unsigned int) offset, orig); - switch (orig) { - case 0: - if (offset < 0) { - ret = -EINVAL; - break; - } - - if ((unsigned int) offset > gbFlashSize) { - ret = -EINVAL; - break; - } - - file->f_pos = (unsigned int) offset; - ret = file->f_pos; - break; - case 1: - if ((file->f_pos + offset) > gbFlashSize) { - ret = -EINVAL; - break; - } - if ((file->f_pos + offset) < 0) { - ret = -EINVAL; - break; - } - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } + ret = no_seek_end_llseek_size(file, offset, orig, gbFlashSize); mutex_unlock(&flash_mutex); return ret; } diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c index eb43f94a1597..be72306f8c69 100644 --- a/drivers/net/wireless/ti/wlcore/debugfs.c +++ b/drivers/net/wireless/ti/wlcore/debugfs.c @@ -1205,26 +1205,11 @@ err_out: static loff_t dev_mem_seek(struct file *file, loff_t offset, int orig) { - loff_t ret; - /* only requests of dword-aligned size and offset are supported */ if (offset % 4) return -EINVAL; - switch (orig) { - case SEEK_SET: - file->f_pos = offset; - ret = file->f_pos; - break; - case SEEK_CUR: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - - return ret; + return no_seek_end_llseek(file, offset, orig); } static const struct file_operations dev_mem_ops = { diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index 0efb27f6f199..6c30e93ab8fa 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -782,24 +782,11 @@ static int ur_release(struct inode *inode, struct file *file) static loff_t ur_llseek(struct file *file, loff_t offset, int whence) { - loff_t newpos; - if ((file->f_flags & O_ACCMODE) != O_RDONLY) return -ESPIPE; /* seek allowed only for reader */ if (offset % PAGE_SIZE) return -ESPIPE; /* only multiples of 4K allowed */ - switch (whence) { - case 0: /* SEEK_SET */ - newpos = offset; - break; - case 1: /* SEEK_CUR */ - newpos = file->f_pos + offset; - break; - default: - return -EINVAL; - } - file->f_pos = newpos; - return newpos; + return no_seek_end_llseek(file, offset, whence); } static const struct file_operations ur_fops = { diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index 823f41fc4bbd..3339b862ec17 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -385,18 +385,7 @@ static loff_t zcore_lseek(struct file *file, loff_t offset, int orig) loff_t rc; mutex_lock(&zcore_mutex); - switch (orig) { - case 0: - file->f_pos = offset; - rc = file->f_pos; - break; - case 1: - file->f_pos += offset; - rc = file->f_pos; - break; - default: - rc = -EINVAL; - } + rc = no_seek_end_llseek(file, offset, orig); mutex_unlock(&zcore_mutex); return rc; } diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c index 2a3bbdf7eb94..cffa0a0d7de2 100644 --- a/drivers/usb/core/devices.c +++ b/drivers/usb/core/devices.c @@ -661,32 +661,8 @@ static unsigned int usb_device_poll(struct file *file, return 0; } -static loff_t usb_device_lseek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - - mutex_lock(&file_inode(file)->i_mutex); - - switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - break; - case 2: - default: - ret = -EINVAL; - } - - mutex_unlock(&file_inode(file)->i_mutex); - return ret; -} - const struct file_operations usbfs_devices_fops = { - .llseek = usb_device_lseek, + .llseek = no_seek_end_llseek, .read = usb_device_read, .poll = usb_device_poll, }; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 38ae877c46e3..dbc3e143453a 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -157,30 +157,6 @@ static int connected(struct usb_dev_state *ps) ps->dev->state != USB_STATE_NOTATTACHED); } -static loff_t usbdev_lseek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - - mutex_lock(&file_inode(file)->i_mutex); - - switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - break; - case 2: - default: - ret = -EINVAL; - } - - mutex_unlock(&file_inode(file)->i_mutex); - return ret; -} - static ssize_t usbdev_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { @@ -2366,7 +2342,7 @@ static unsigned int usbdev_poll(struct file *file, const struct file_operations usbdev_file_operations = { .owner = THIS_MODULE, - .llseek = usbdev_lseek, + .llseek = no_seek_end_llseek, .read = usbdev_read, .poll = usbdev_poll, .unlocked_ioctl = usbdev_ioctl, diff --git a/drivers/usb/host/uhci-debug.c b/drivers/usb/host/uhci-debug.c index 1b28a000d5c6..9c6635d43db0 100644 --- a/drivers/usb/host/uhci-debug.c +++ b/drivers/usb/host/uhci-debug.c @@ -584,27 +584,8 @@ static int uhci_debug_open(struct inode *inode, struct file *file) static loff_t uhci_debug_lseek(struct file *file, loff_t off, int whence) { - struct uhci_debug *up; - loff_t new = -1; - - up = file->private_data; - - /* - * XXX: atomic 64bit seek access, but that needs to be fixed in the VFS - */ - switch (whence) { - case 0: - new = off; - break; - case 1: - new = file->f_pos + off; - break; - } - - if (new < 0 || new > up->size) - return -EINVAL; - - return (file->f_pos = new); + struct uhci_debug *up = file->private_data; + return no_seek_end_llseek_size(file, off, whence, up->size); } static ssize_t uhci_debug_read(struct file *file, char __user *buf, diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c index 306d6852ebc7..8efbabacc84e 100644 --- a/drivers/usb/misc/sisusbvga/sisusb.c +++ b/drivers/usb/misc/sisusbvga/sisusb.c @@ -2825,21 +2825,7 @@ sisusb_lseek(struct file *file, loff_t offset, int orig) return -ENODEV; } - switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - /* never negative, no force_successful_syscall needed */ - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - /* never negative, no force_successful_syscall needed */ - break; - default: - /* seeking relative to "end of file" is not supported */ - ret = -EINVAL; - } + ret = no_seek_end_llseek(file, offset, orig); mutex_unlock(&sisusb->lock); return ret; diff --git a/fs/read_write.c b/fs/read_write.c index 819ef3faf1bb..acb171331278 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -170,6 +170,45 @@ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t si } EXPORT_SYMBOL(fixed_size_llseek); +/** + * no_seek_end_llseek - llseek implementation for fixed-sized devices + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * + */ +loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) +{ + switch (whence) { + case SEEK_SET: case SEEK_CUR: + return generic_file_llseek_size(file, offset, whence, + ~0ULL, 0); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL(no_seek_end_llseek); + +/** + * no_seek_end_llseek_size - llseek implementation for fixed-sized devices + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * @size: maximal offset allowed + * + */ +loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) +{ + switch (whence) { + case SEEK_SET: case SEEK_CUR: + return generic_file_llseek_size(file, offset, whence, + size, 0); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL(no_seek_end_llseek_size); + /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on diff --git a/include/linux/fs.h b/include/linux/fs.h index bd1447661e3c..fb0fa224d8e8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2660,6 +2660,8 @@ extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); +extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); +extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); -- cgit v1.2.3 From c5d641f92c9633f568740332989c067a0ba7d4dc Mon Sep 17 00:00:00 2001 From: Li Bin Date: Sun, 6 Dec 2015 10:02:58 +0800 Subject: x86: ftrace: Fix the comments for ftrace_modify_code_direct() There is no need to worry about module and __init text disappearing case, because that ftrace has a module notifier that is called when a module is being unloaded and before the text goes away and this code grabs the ftrace_lock mutex and removes the module functions from the ftrace list, such that it will no longer do any modifications to that module's text, the update to make functions be traced or not is done under the ftrace_lock mutex as well. And by now, __init section codes should not been modified by ftrace, because it is black listed in recordmcount.c and ignored by ftrace. Link: http://lkml.kernel.org/r/1449367378-29430-6-git-send-email-huawei.libin@huawei.com Reviewed-by: Thomas Gleixner Suggested-by: Steven Rostedt Signed-off-by: Li Bin Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 909da012406d..29408d6d6626 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -108,13 +108,11 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, ftrace_expected = old_code; /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. We do this by using the - * probe_kernel_* functions. - * - * No real locking needed, this code is run through - * kstop_machine, or before SMP starts. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ -- cgit v1.2.3 From 2f0c0b2d96b1205efb14347009748d786c2d9ba5 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 18 Dec 2015 20:24:06 +0100 Subject: x86/reboot/quirks: Add iMac10,1 to pci_reboot_dmi_table[] Without the reboot=pci method, the iMac 10,1 simply hangs after printing "Restarting system" at the point when it should reboot. This fixes it. Signed-off-by: Mario Kleiner Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Jones Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1450466646-26663-1-git-send-email-mario.kleiner.de@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/reboot.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index d64889aa2d46..ab0adc0fa5db 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ -- cgit v1.2.3 From 7030a7e9321166eef44c811fe4af4d460360d424 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 13 Jan 2016 15:39:40 +0300 Subject: x86/cpu/amd: Remove an unneeded condition in srat_detect_node() Originally we calculated ht_nodeid as "ht_nodeid = apicid - boot_cpu_id;" so presumably it could be negative. But after commit: 01aaea1afbcd ('x86: introduce initial apicid') we use c->initial_apicid which is an unsigned short and thus always >= 0. It causes a static checker warning to test for impossible conditions so let's remove it. Signed-off-by: Dan Carpenter Cc: Andy Lutomirski Cc: Aravind Gopalakrishnan Cc: Borislav Petkov Cc: Hector Marco-Gisbert Cc: Huang Rui Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yinghai Lu Link: http://lkml.kernel.org/r/20160113123940.GE19993@mwanda Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/amd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e678ddeed030..a07956a08936 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -434,8 +434,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) */ int ht_nodeid = c->initial_apicid; - if (ht_nodeid >= 0 && - __apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) node = __apicid_to_node[ht_nodeid]; /* Pick a nearby node */ if (!node_online(node)) -- cgit v1.2.3 From 78ddc53473419073ffb2e91178001e87bc513524 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:52:42 -0800 Subject: thp: rename split_huge_page_pmd() to split_huge_pmd() We are going to decouple splitting THP PMD from splitting underlying compound page. This patch renames split_huge_page_pmd*() functions to split_huge_pmd*() to reflect the fact that it doesn't imply page splitting, only PMD. Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin Tested-by: Aneesh Kumar K.V Acked-by: Jerome Marchand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Naoya Horiguchi Cc: Steve Capper Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/mm/subpage-prot.c | 2 +- arch/x86/kernel/vm86_32.c | 6 +++++- include/linux/huge_mm.h | 8 ++------ mm/gup.c | 2 +- mm/huge_memory.c | 32 +++++++++++--------------------- mm/memory.c | 2 +- mm/mempolicy.c | 2 +- mm/mprotect.c | 2 +- mm/mremap.c | 2 +- mm/pagewalk.c | 2 +- 10 files changed, 25 insertions(+), 35 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index fa9fb5b4c66c..d5543514c1df 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -135,7 +135,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); return 0; } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 483231ebbb0b..e574b8546518 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -175,7 +175,11 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd_mm(mm, 0xA0000, pmd); + + if (pmd_trans_huge(*pmd)) { + struct vm_area_struct *vma = find_vma(mm, 0xA0000); + split_huge_pmd(vma, pmd, 0xA0000); + } if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ecb080d6ff42..805c7ae42280 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -102,7 +102,7 @@ static inline int split_huge_page(struct page *page) } extern void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd); -#define split_huge_page_pmd(__vma, __address, __pmd) \ +#define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (unlikely(pmd_trans_huge(*____pmd))) \ @@ -117,8 +117,6 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma, BUG_ON(pmd_trans_splitting(*____pmd) || \ pmd_trans_huge(*____pmd)); \ } while (0) -extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, - pmd_t *pmd); #if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif @@ -183,11 +181,9 @@ static inline int split_huge_page(struct page *page) { return 0; } -#define split_huge_page_pmd(__vma, __address, __pmd) \ - do { } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) -#define split_huge_page_pmd_mm(__mm, __address, __pmd) \ +#define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) diff --git a/mm/gup.c b/mm/gup.c index 20fa606b4e76..1c50b506888d 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -254,7 +254,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (is_huge_zero_page(page)) { spin_unlock(ptl); ret = 0; - split_huge_page_pmd(vma, address, pmd); + split_huge_pmd(vma, pmd, address); } else { get_page(page); spin_unlock(ptl); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f4da89cef2cd..0d70ec056ecc 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1233,13 +1233,13 @@ alloc: if (unlikely(!new_page)) { if (!page) { - split_huge_page_pmd(vma, address, pmd); + split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; } else { ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); if (ret & VM_FAULT_OOM) { - split_huge_page(page); + split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; } put_user_huge_page(page); @@ -1252,10 +1252,10 @@ alloc: true))) { put_page(new_page); if (page) { - split_huge_page(page); + split_huge_pmd(vma, pmd, address); put_user_huge_page(page); } else - split_huge_page_pmd(vma, address, pmd); + split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); goto out; @@ -3131,17 +3131,7 @@ again: goto again; } -void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, - pmd_t *pmd) -{ - struct vm_area_struct *vma; - - vma = find_vma(mm, address); - BUG_ON(vma == NULL); - split_huge_page_pmd(vma, address, pmd); -} - -static void split_huge_page_address(struct mm_struct *mm, +static void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address) { pgd_t *pgd; @@ -3150,7 +3140,7 @@ static void split_huge_page_address(struct mm_struct *mm, VM_BUG_ON(!(address & ~HPAGE_PMD_MASK)); - pgd = pgd_offset(mm, address); + pgd = pgd_offset(vma->vm_mm, address); if (!pgd_present(*pgd)) return; @@ -3159,13 +3149,13 @@ static void split_huge_page_address(struct mm_struct *mm, return; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) + if (!pmd_present(*pmd) || !pmd_trans_huge(*pmd)) return; /* * Caller holds the mmap_sem write mode, so a huge pmd cannot * materialize from under us. */ - split_huge_page_pmd_mm(mm, address, pmd); + __split_huge_page_pmd(vma, address, pmd); } void vma_adjust_trans_huge(struct vm_area_struct *vma, @@ -3181,7 +3171,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, if (start & ~HPAGE_PMD_MASK && (start & HPAGE_PMD_MASK) >= vma->vm_start && (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) - split_huge_page_address(vma->vm_mm, start); + split_huge_pmd_address(vma, start); /* * If the new end address isn't hpage aligned and it could @@ -3191,7 +3181,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, if (end & ~HPAGE_PMD_MASK && (end & HPAGE_PMD_MASK) >= vma->vm_start && (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) - split_huge_page_address(vma->vm_mm, end); + split_huge_pmd_address(vma, end); /* * If we're also updating the vma->vm_next->vm_start, if the new @@ -3205,6 +3195,6 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, if (nstart & ~HPAGE_PMD_MASK && (nstart & HPAGE_PMD_MASK) >= next->vm_start && (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end) - split_huge_page_address(next->vm_mm, nstart); + split_huge_pmd_address(next, nstart); } } diff --git a/mm/memory.c b/mm/memory.c index eecdd05e9923..561b7ad7f27a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1193,7 +1193,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, BUG(); } #endif - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d8caff071a30..5f7f9dace354 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -493,7 +493,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, pte_t *pte; spinlock_t *ptl; - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); if (pmd_trans_unstable(pmd)) return 0; diff --git a/mm/mprotect.c b/mm/mprotect.c index c764402c464f..6047707085c1 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -160,7 +160,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, if (pmd_trans_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); else { int nr_ptes = change_huge_pmd(vma, pmd, addr, newprot, prot_numa); diff --git a/mm/mremap.c b/mm/mremap.c index e55b157865d5..5969b5093850 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -209,7 +209,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, need_flush = true; continue; } else if (!err) { - split_huge_page_pmd(vma, old_addr, old_pmd); + split_huge_pmd(vma, old_pmd, old_addr); } VM_BUG_ON(pmd_trans_huge(*old_pmd)); } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 29f2f8b853ae..207244489a68 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -58,7 +58,7 @@ again: if (!walk->pte_entry) continue; - split_huge_page_pmd_mm(walk->mm, addr, pmd); + split_huge_pmd(walk->vma, pmd, addr); if (pmd_trans_unstable(pmd)) goto again; err = walk_pte_range(pmd, addr, next, walk); -- cgit v1.2.3 From 978e30c9b46161c792ecdad0091fd017b21b8ca5 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 20 Jan 2016 15:00:36 -0800 Subject: kexec: move some memembers and definitions within the scope of CONFIG_KEXEC_FILE Move the stuff currently only used by the kexec file code within CONFIG_KEXEC_FILE (and CONFIG_KEXEC_VERIFY_SIG). Also move internal "struct kexec_sha_region" and "struct kexec_buf" into "kexec_internal.h". Signed-off-by: Xunlei Pang Cc: "Eric W. Biederman" Cc: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/machine_kexec_64.c | 2 ++ include/linux/kexec.h | 62 +++++++++++++++----------------------- kernel/kexec_file.c | 2 ++ kernel/kexec_internal.h | 21 +++++++++++++ 4 files changed, 50 insertions(+), 37 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 819ab3f9c9c7..ba7fbba9831b 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -385,6 +385,7 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) return image->fops->cleanup(image->image_loader_data); } +#ifdef CONFIG_KEXEC_VERIFY_SIG int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel, unsigned long kernel_len) { @@ -395,6 +396,7 @@ int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel, return image->fops->verify_sig(kernel, kernel_len); } +#endif /* * Apply purgatory relocations. diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 7b68d2788a56..2cc643c6e870 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -109,11 +109,7 @@ struct compat_kexec_segment { }; #endif -struct kexec_sha_region { - unsigned long start; - unsigned long len; -}; - +#ifdef CONFIG_KEXEC_FILE struct purgatory_info { /* Pointer to elf header of read only purgatory */ Elf_Ehdr *ehdr; @@ -130,6 +126,28 @@ struct purgatory_info { unsigned long purgatory_load_addr; }; +typedef int (kexec_probe_t)(const char *kernel_buf, unsigned long kernel_size); +typedef void *(kexec_load_t)(struct kimage *image, char *kernel_buf, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len); +typedef int (kexec_cleanup_t)(void *loader_data); + +#ifdef CONFIG_KEXEC_VERIFY_SIG +typedef int (kexec_verify_sig_t)(const char *kernel_buf, + unsigned long kernel_len); +#endif + +struct kexec_file_ops { + kexec_probe_t *probe; + kexec_load_t *load; + kexec_cleanup_t *cleanup; +#ifdef CONFIG_KEXEC_VERIFY_SIG + kexec_verify_sig_t *verify_sig; +#endif +}; +#endif + struct kimage { kimage_entry_t head; kimage_entry_t *entry; @@ -161,6 +179,7 @@ struct kimage { struct kimage_arch arch; #endif +#ifdef CONFIG_KEXEC_FILE /* Additional fields for file based kexec syscall */ void *kernel_buf; unsigned long kernel_buf_len; @@ -179,38 +198,7 @@ struct kimage { /* Information for loading purgatory */ struct purgatory_info purgatory_info; -}; - -/* - * Keeps track of buffer parameters as provided by caller for requesting - * memory placement of buffer. - */ -struct kexec_buf { - struct kimage *image; - char *buffer; - unsigned long bufsz; - unsigned long mem; - unsigned long memsz; - unsigned long buf_align; - unsigned long buf_min; - unsigned long buf_max; - bool top_down; /* allocate from top of memory hole */ -}; - -typedef int (kexec_probe_t)(const char *kernel_buf, unsigned long kernel_size); -typedef void *(kexec_load_t)(struct kimage *image, char *kernel_buf, - unsigned long kernel_len, char *initrd, - unsigned long initrd_len, char *cmdline, - unsigned long cmdline_len); -typedef int (kexec_cleanup_t)(void *loader_data); -typedef int (kexec_verify_sig_t)(const char *kernel_buf, - unsigned long kernel_len); - -struct kexec_file_ops { - kexec_probe_t *probe; - kexec_load_t *load; - kexec_cleanup_t *cleanup; - kexec_verify_sig_t *verify_sig; +#endif }; /* kexec interface functions */ diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b70ada0028d2..007b791f676d 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -109,11 +109,13 @@ int __weak arch_kimage_file_post_load_cleanup(struct kimage *image) return -EINVAL; } +#ifdef CONFIG_KEXEC_VERIFY_SIG int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, unsigned long buf_len) { return -EKEYREJECTED; } +#endif /* Apply relocations of type RELA */ int __weak diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index e4392a698ad4..0a52315d9c62 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -15,6 +15,27 @@ int kimage_is_destination_range(struct kimage *image, extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE +struct kexec_sha_region { + unsigned long start; + unsigned long len; +}; + +/* + * Keeps track of buffer parameters as provided by caller for requesting + * memory placement of buffer. + */ +struct kexec_buf { + struct kimage *image; + char *buffer; + unsigned long bufsz; + unsigned long mem; + unsigned long memsz; + unsigned long buf_align; + unsigned long buf_min; + unsigned long buf_max; + bool top_down; /* allocate from top of memory hole */ +}; + void kimage_file_post_load_cleanup(struct kimage *image); #else /* CONFIG_KEXEC_FILE */ static inline void kimage_file_post_load_cleanup(struct kimage *image) { } -- cgit v1.2.3