diff options
64 files changed, 2181 insertions, 1684 deletions
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 11fe51c036b..194c8f35132 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1134,13 +1134,6 @@ check the amount of free space (value is in seconds). Default settings are: 4, resume it if we have a value of 3 or more percent; consider information about the amount of free space valid for 30 seconds -audit_argv_kb -------------- - -The file contains a single value denoting the limit on the argv array size -for execve (in KiB). This limit is only applied when system call auditing for -execve is enabled, otherwise the value is ignored. - ctrl-alt-del ------------ diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index 50be56c9e9e..a24fb790090 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -140,7 +140,7 @@ FEXPORT(__kernel_entry) j kernel_entry #endif - __INIT_REFOK + __REF NESTED(kernel_entry, 16, sp) # kernel entry point diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile index 32fd5db9577..c6f832e0f41 100644 --- a/arch/mips/mm/Makefile +++ b/arch/mips/mm/Makefile @@ -3,7 +3,8 @@ # obj-y += cache.o dma-default.o extable.o fault.o \ - init.o pgtable.o tlbex.o tlbex-fault.o + init.o pgtable.o tlbex.o tlbex-fault.o \ + uasm.o obj-$(CONFIG_32BIT) += ioremap.o pgtable-32.o obj-$(CONFIG_64BIT) += pgtable-64.o diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index d026302e0ec..218a6cc415e 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -5,7 +5,7 @@ * * Synthesize TLB refill handlers at runtime. * - * Copyright (C) 2004,2005,2006 by Thiemo Seufer + * Copyright (C) 2004, 2005, 2006, 2008 Thiemo Seufer * Copyright (C) 2005, 2007 Maciej W. Rozycki * Copyright (C) 2006 Ralf Baechle (ralf@linux-mips.org) * @@ -24,12 +24,11 @@ #include <linux/string.h> #include <linux/init.h> -#include <asm/bugs.h> #include <asm/mmu_context.h> -#include <asm/inst.h> -#include <asm/elf.h> #include <asm/war.h> +#include "uasm.h" + static inline int r45k_bvahwbug(void) { /* XXX: We should probe for the presence of this bug, but we don't. */ @@ -67,371 +66,9 @@ static int __init m4kc_tlbp_war(void) (PRID_COMP_MIPS | PRID_IMP_4KC); } -/* - * A little micro-assembler, intended for TLB refill handler - * synthesizing. It is intentionally kept simple, does only support - * a subset of instructions, and does not try to hide pipeline effects - * like branch delay slots. - */ - -enum fields -{ - RS = 0x001, - RT = 0x002, - RD = 0x004, - RE = 0x008, - SIMM = 0x010, - UIMM = 0x020, - BIMM = 0x040, - JIMM = 0x080, - FUNC = 0x100, - SET = 0x200 -}; - -#define OP_MASK 0x3f -#define OP_SH 26 -#define RS_MASK 0x1f -#define RS_SH 21 -#define RT_MASK 0x1f -#define RT_SH 16 -#define RD_MASK 0x1f -#define RD_SH 11 -#define RE_MASK 0x1f -#define RE_SH 6 -#define IMM_MASK 0xffff -#define IMM_SH 0 -#define JIMM_MASK 0x3ffffff -#define JIMM_SH 0 -#define FUNC_MASK 0x3f -#define FUNC_SH 0 -#define SET_MASK 0x7 -#define SET_SH 0 - -enum opcode { - insn_invalid, - insn_addu, insn_addiu, insn_and, insn_andi, insn_beq, - insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl, - insn_bne, insn_daddu, insn_daddiu, insn_dmfc0, insn_dmtc0, - insn_dsll, insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, - insn_dsubu, insn_eret, insn_j, insn_jal, insn_jr, insn_ld, - insn_ll, insn_lld, insn_lui, insn_lw, insn_mfc0, insn_mtc0, - insn_ori, insn_rfe, insn_sc, insn_scd, insn_sd, insn_sll, - insn_sra, insn_srl, insn_subu, insn_sw, insn_tlbp, insn_tlbwi, - insn_tlbwr, insn_xor, insn_xori -}; - -struct insn { - enum opcode opcode; - u32 match; - enum fields fields; -}; - -/* This macro sets the non-variable bits of an instruction. */ -#define M(a, b, c, d, e, f) \ - ((a) << OP_SH \ - | (b) << RS_SH \ - | (c) << RT_SH \ - | (d) << RD_SH \ - | (e) << RE_SH \ - | (f) << FUNC_SH) - -static struct insn insn_table[] __initdata = { - { insn_addiu, M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_addu, M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD }, - { insn_and, M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD }, - { insn_andi, M(andi_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_beq, M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_beql, M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_bgez, M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM }, - { insn_bgezl, M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM }, - { insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM }, - { insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM }, - { insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD }, - { insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_dmtc0, M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_dsll, M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE }, - { insn_dsll32, M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE }, - { insn_dsra, M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE }, - { insn_dsrl, M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE }, - { insn_dsrl32, M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE }, - { insn_dsubu, M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD }, - { insn_eret, M(cop0_op, cop_op, 0, 0, 0, eret_op), 0 }, - { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jal, M(jal_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jr, M(spec_op, 0, 0, 0, 0, jr_op), RS }, - { insn_ld, M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_ll, M(ll_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_lld, M(lld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_lui, M(lui_op, 0, 0, 0, 0, 0), RT | SIMM }, - { insn_lw, M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_mfc0, M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mtc0, M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_ori, M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_rfe, M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0 }, - { insn_sc, M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_scd, M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sd, M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sll, M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE }, - { insn_sra, M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE }, - { insn_srl, M(spec_op, 0, 0, 0, 0, srl_op), RT | RD | RE }, - { insn_subu, M(spec_op, 0, 0, 0, 0, subu_op), RS | RT | RD }, - { insn_sw, M(sw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_tlbp, M(cop0_op, cop_op, 0, 0, 0, tlbp_op), 0 }, - { insn_tlbwi, M(cop0_op, cop_op, 0, 0, 0, tlbwi_op), 0 }, - { insn_tlbwr, M(cop0_op, cop_op, 0, 0, 0, tlbwr_op), 0 }, - { insn_xor, M(spec_op, 0, 0, 0, 0, xor_op), RS | RT | RD }, - { insn_xori, M(xori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_invalid, 0, 0 } -}; - -#undef M - -static u32 __init build_rs(u32 arg) -{ - if (arg & ~RS_MASK) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return (arg & RS_MASK) << RS_SH; -} - -static u32 __init build_rt(u32 arg) -{ - if (arg & ~RT_MASK) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return (arg & RT_MASK) << RT_SH; -} - -static u32 __init build_rd(u32 arg) -{ - if (arg & ~RD_MASK) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return (arg & RD_MASK) << RD_SH; -} - -static u32 __init build_re(u32 arg) -{ - if (arg & ~RE_MASK) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return (arg & RE_MASK) << RE_SH; -} - -static u32 __init build_simm(s32 arg) -{ - if (arg > 0x7fff || arg < -0x8000) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return arg & 0xffff; -} - -static u32 __init build_uimm(u32 arg) -{ - if (arg & ~IMM_MASK) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return arg & IMM_MASK; -} - -static u32 __init build_bimm(s32 arg) -{ - if (arg > 0x1ffff || arg < -0x20000) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - if (arg & 0x3) - printk(KERN_WARNING "Invalid TLB synthesizer branch target\n"); - - return ((arg < 0) ? (1 << 15) : 0) | ((arg >> 2) & 0x7fff); -} - -static u32 __init build_jimm(u32 arg) -{ - if (arg & ~((JIMM_MASK) << 2)) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return (arg >> 2) & JIMM_MASK; -} - -static u32 __init build_func(u32 arg) -{ - if (arg & ~FUNC_MASK) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return arg & FUNC_MASK; -} - -static u32 __init build_set(u32 arg) -{ - if (arg & ~SET_MASK) - printk(KERN_WARNING "TLB synthesizer field overflow\n"); - - return arg & SET_MASK; -} - -/* - * The order of opcode arguments is implicitly left to right, - * starting with RS and ending with FUNC or IMM. - */ -static void __init build_insn(u32 **buf, enum opcode opc, ...) -{ - struct insn *ip = NULL; - unsigned int i; - va_list ap; - u32 op; - - for (i = 0; insn_table[i].opcode != insn_invalid; i++) - if (insn_table[i].opcode == opc) { - ip = &insn_table[i]; - break; - } - - if (!ip || (opc == insn_daddiu && r4k_daddiu_bug())) - panic("Unsupported TLB synthesizer instruction %d", opc); - - op = ip->match; - va_start(ap, opc); - if (ip->fields & RS) op |= build_rs(va_arg(ap, u32)); - if (ip->fields & RT) op |= build_rt(va_arg(ap, u32)); - if (ip->fields & RD) op |= build_rd(va_arg(ap, u32)); - if (ip->fields & RE) op |= build_re(va_arg(ap, u32)); - if (ip->fields & SIMM) op |= build_simm(va_arg(ap, s32)); - if (ip->fields & UIMM) op |= build_uimm(va_arg(ap, u32)); - if (ip->fields & BIMM) op |= build_bimm(va_arg(ap, s32)); - if (ip->fields & JIMM) op |= build_jimm(va_arg(ap, u32)); - if (ip->fields & FUNC) op |= build_func(va_arg(ap, u32)); - if (ip->fields & SET) op |= build_set(va_arg(ap, u32)); - va_end(ap); - - **buf = op; - (*buf)++; -} - -#define I_u1u2u3(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - unsigned int b, unsigned int c) \ - { \ - build_insn(buf, insn##op, a, b, c); \ - } - -#define I_u2u1u3(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - unsigned int b, unsigned int c) \ - { \ - build_insn(buf, insn##op, b, a, c); \ - } - -#define I_u3u1u2(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - unsigned int b, unsigned int c) \ - { \ - build_insn(buf, insn##op, b, c, a); \ - } - -#define I_u1u2s3(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - unsigned int b, signed int c) \ - { \ - build_insn(buf, insn##op, a, b, c); \ - } - -#define I_u2s3u1(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - signed int b, unsigned int c) \ - { \ - build_insn(buf, insn##op, c, a, b); \ - } - -#define I_u2u1s3(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - unsigned int b, signed int c) \ - { \ - build_insn(buf, insn##op, b, a, c); \ - } - -#define I_u1u2(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - unsigned int b) \ - { \ - build_insn(buf, insn##op, a, b); \ - } - -#define I_u1s2(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a, \ - signed int b) \ - { \ - build_insn(buf, insn##op, a, b); \ - } - -#define I_u1(op) \ - static void __init __maybe_unused i##op(u32 **buf, unsigned int a) \ - { \ - build_insn(buf, insn##op, a); \ - } - -#define I_0(op) \ - static void __init __maybe_unused i##op(u32 **buf) \ - { \ - build_insn(buf, insn##op); \ - } - -I_u2u1s3(_addiu); -I_u3u1u2(_addu); -I_u2u1u3(_andi); -I_u3u1u2(_and); -I_u1u2s3(_beq); -I_u1u2s3(_beql); -I_u1s2(_bgez); -I_u1s2(_bgezl); -I_u1s2(_bltz); -I_u1s2(_bltzl); -I_u1u2s3(_bne); -I_u1u2u3(_dmfc0); -I_u1u2u3(_dmtc0); -I_u2u1s3(_daddiu); -I_u3u1u2(_daddu); -I_u2u1u3(_dsll); -I_u2u1u3(_dsll32); -I_u2u1u3(_dsra); -I_u2u1u3(_dsrl); -I_u2u1u3(_dsrl32); -I_u3u1u2(_dsubu); -I_0(_eret); -I_u1(_j); -I_u1(_jal); -I_u1(_jr); -I_u2s3u1(_ld); -I_u2s3u1(_ll); -I_u2s3u1(_lld); -I_u1s2(_lui); -I_u2s3u1(_lw); -I_u1u2u3(_mfc0); -I_u1u2u3(_mtc0); -I_u2u1u3(_ori); -I_0(_rfe); -I_u2s3u1(_sc); -I_u2s3u1(_scd); -I_u2s3u1(_sd); -I_u2u1u3(_sll); -I_u2u1u3(_sra); -I_u2u1u3(_srl); -I_u3u1u2(_subu); -I_u2s3u1(_sw); -I_0(_tlbp); -I_0(_tlbwi); -I_0(_tlbwr); -I_u3u1u2(_xor) -I_u2u1u3(_xori); - -/* - * handling labels - */ - +/* Handle labels (which must be positive integers). */ enum label_id { - label_invalid, - label_second_part, + label_second_part = 1, label_leave, #ifdef MODULE_START label_module_alloc, @@ -447,278 +84,20 @@ enum label_id { label_r3000_write_probe_fail, }; -struct label { - u32 *addr; - enum label_id lab; -}; - -static void __init build_label(struct label **lab, u32 *addr, - enum label_id l) -{ - (*lab)->addr = addr; - (*lab)->lab = l; - (*lab)++; -} - -#define L_LA(lb) \ - static inline void __init l##lb(struct label **lab, u32 *addr) \ - { \ - build_label(lab, addr, label##lb); \ - } - -L_LA(_second_part) -L_LA(_leave) +UASM_L_LA(_second_part) +UASM_L_LA(_leave) #ifdef MODULE_START -L_LA(_module_alloc) -#endif -L_LA(_vmalloc) -L_LA(_vmalloc_done) -L_LA(_tlbw_hazard) -L_LA(_split) -L_LA(_nopage_tlbl) -L_LA(_nopage_tlbs) -L_LA(_nopage_tlbm) -L_LA(_smp_pgtable_change) -L_LA(_r3000_write_probe_fail) - -/* convenience macros for instructions */ -#ifdef CONFIG_64BIT -# define i_LW(buf, rs, rt, off) i_ld(buf, rs, rt, off) -# define i_SW(buf, rs, rt, off) i_sd(buf, rs, rt, off) -# define i_SLL(buf, rs, rt, sh) i_dsll(buf, rs, rt, sh) -# define i_SRA(buf, rs, rt, sh) i_dsra(buf, rs, rt, sh) -# define i_SRL(buf, rs, rt, sh) i_dsrl(buf, rs, rt, sh) -# define i_MFC0(buf, rt, rd...) i_dmfc0(buf, rt, rd) -# define i_MTC0(buf, rt, rd...) i_dmtc0(buf, rt, rd) -# define i_ADDIU(buf, rs, rt, val) i_daddiu(buf, rs, rt, val) -# define i_ADDU(buf, rs, rt, rd) i_daddu(buf, rs, rt, rd) -# define i_SUBU(buf, rs, rt, rd) i_dsubu(buf, rs, rt, rd) -# define i_LL(buf, rs, rt, off) i_lld(buf, rs, rt, off) -# define i_SC(buf, rs, rt, off) i_scd(buf, rs, rt, off) -#else -# define i_LW(buf, rs, rt, off) i_lw(buf, rs, rt, off) -# define i_SW(buf, rs, rt, off) i_sw(buf, rs, rt, off) -# define i_SLL(buf, rs, rt, sh) i_sll(buf, rs, rt, sh) -# define i_SRA(buf, rs, rt, sh) i_sra(buf, rs, rt, sh) -# define i_SRL(buf, rs, rt, sh) i_srl(buf, rs, rt, sh) -# define i_MFC0(buf, rt, rd...) i_mfc0(buf, rt, rd) -# define i_MTC0(buf, rt, rd...) i_mtc0(buf, rt, rd) -# define i_ADDIU(buf, rs, rt, val) i_addiu(buf, rs, rt, val) -# define i_ADDU(buf, rs, rt, rd) i_addu(buf, rs, rt, rd) -# define i_SUBU(buf, rs, rt, rd) i_subu(buf, rs, rt, rd) -# define i_LL(buf, rs, rt, off) i_ll(buf, rs, rt, off) -# define i_SC(buf, rs, rt, off) i_sc(buf, rs, rt, off) -#endif - -#define i_b(buf, off) i_beq(buf, 0, 0, off) -#define i_beqz(buf, rs, off) i_beq(buf, rs, 0, off) -#define i_beqzl(buf, rs, off) i_beql(buf, rs, 0, off) -#define i_bnez(buf, rs, off) i_bne(buf, rs, 0, off) -#define i_bnezl(buf, rs, off) i_bnel(buf, rs, 0, off) -#define i_move(buf, a, b) i_ADDU(buf, a, 0, b) -#define i_nop(buf) i_sll(buf, 0, 0, 0) -#define i_ssnop(buf) i_sll(buf, 0, 0, 1) -#define i_ehb(buf) i_sll(buf, 0, 0, 3) - -static int __init __maybe_unused in_compat_space_p(long addr) -{ - /* Is this address in 32bit compat space? */ -#ifdef CONFIG_64BIT - return (((addr) & 0xffffffff00000000L) == 0xffffffff00000000L); -#else - return 1; +UASM_L_LA(_module_alloc) #endif -} - -static int __init __maybe_unused rel_highest(long val) -{ -#ifdef CONFIG_64BIT - return ((((val + 0x800080008000L) >> 48) & 0xffff) ^ 0x8000) - 0x8000; -#else - return 0; -#endif -} - -static int __init __maybe_unused rel_higher(long val) -{ -#ifdef CONFIG_64BIT - return ((((val + 0x80008000L) >> 32) & 0xffff) ^ 0x8000) - 0x8000; -#else - return 0; -#endif -} - -static int __init rel_hi(long val) -{ - return ((((val + 0x8000L) >> 16) & 0xffff) ^ 0x8000) - 0x8000; -} - -static int __init rel_lo(long val) -{ - return ((val & 0xffff) ^ 0x8000) - 0x8000; -} - -static void __init i_LA_mostly(u32 **buf, unsigned int rs, long addr) -{ - if (!in_compat_space_p(addr)) { - i_lui(buf, rs, rel_highest(addr)); - if (rel_higher(addr)) - i_daddiu(buf, rs, rs, rel_higher(addr)); - if (rel_hi(addr)) { - i_dsll(buf, rs, rs, 16); - i_daddiu(buf, rs, rs, rel_hi(addr)); - i_dsll(buf, rs, rs, 16); - } else - i_dsll32(buf, rs, rs, 0); - } else - i_lui(buf, rs, rel_hi(addr)); -} - -static void __init __maybe_unused i_LA(u32 **buf, unsigned int rs, long addr) -{ - i_LA_mostly(buf, rs, addr); - if (rel_lo(addr)) { - if (!in_compat_space_p(addr)) - i_daddiu(buf, rs, rs, rel_lo(addr)); - else - i_addiu(buf, rs, rs, rel_lo(addr)); - } -} - -/* - * handle relocations - */ - -struct reloc { - u32 *addr; - unsigned int type; - enum label_id lab; -}; - -static void __init r_mips_pc16(struct reloc **rel, u32 *addr, - enum label_id l) -{ - (*rel)->addr = addr; - (*rel)->type = R_MIPS_PC16; - (*rel)->lab = l; - (*rel)++; -} - -static inline void __resolve_relocs(struct reloc *rel, struct label *lab) -{ - long laddr = (long)lab->addr; - long raddr = (long)rel->addr; - - switch (rel->type) { - case R_MIPS_PC16: - *rel->addr |= build_bimm(laddr - (raddr + 4)); - break; - - default: - panic("Unsupported TLB synthesizer relocation %d", - rel->type); - } -} - -static void __init resolve_relocs(struct reloc *rel, struct label *lab) -{ - struct label *l; - - for (; rel->lab != label_invalid; rel++) - for (l = lab; l->lab != label_invalid; l++) - if (rel->lab == l->lab) - __resolve_relocs(rel, l); -} - -static void __init move_relocs(struct reloc *rel, u32 *first, u32 *end, - long off) -{ - for (; rel->lab != label_invalid; rel++) - if (rel->addr >= first && rel->addr < end) - rel->addr += off; -} - -static void __init move_labels(struct label *lab, u32 *first, u32 *end, - long off) -{ - for (; lab->lab != label_invalid; lab++) - if (lab->addr >= first && lab->addr < end) - lab->addr += off; -} - -static void __init copy_handler(struct reloc *rel, struct label *lab, - u32 *first, u32 *end, u32 *target) -{ - long off = (long)(target - first); - - memcpy(target, first, (end - first) * sizeof(u32)); - - move_relocs(rel, first, end, off); - move_labels(lab, first, end, off); -} - -static int __init __maybe_unused insn_has_bdelay(struct reloc *rel, - u32 *addr) -{ - for (; rel->lab != label_invalid; rel++) { - if (rel->addr == addr - && (rel->type == R_MIPS_PC16 - || rel->type == R_MIPS_26)) - return 1; - } - - return 0; -} - -/* convenience functions for labeled branches */ -static void __init __maybe_unused - il_bltz(u32 **p, struct reloc **r, unsigned int reg, enum label_id l) -{ - r_mips_pc16(r, *p, l); - i_bltz(p, reg, 0); -} - -static void __init __maybe_unused il_b(u32 **p, struct reloc **r, - enum label_id l) -{ - r_mips_pc16(r, *p, l); - i_b(p, 0); -} - -static void __init il_beqz(u32 **p, struct reloc **r, unsigned int reg, - enum label_id l) -{ - r_mips_pc16(r, *p, l); - i_beqz(p, reg, 0); -} - -static void __init __maybe_unused -il_beqzl(u32 **p, struct reloc **r, unsigned int reg, enum label_id l) -{ - r_mips_pc16(r, *p, l); - i_beqzl(p, reg, 0); -} - -static void __init il_bnez(u32 **p, struct reloc **r, unsigned int reg, - enum label_id l) -{ - r_mips_pc16(r, *p, l); - i_bnez(p, reg, 0); -} - -static void __init il_bgezl(u32 **p, struct reloc **r, unsigned int reg, - enum label_id l) -{ - r_mips_pc16(r, *p, l); - i_bgezl(p, reg, 0); -} - -static void __init __maybe_unused -il_bgez(u32 **p, struct reloc **r, unsigned int reg, enum label_id l) -{ - r_mips_pc16(r, *p, l); - i_bgez(p, reg, 0); -} +UASM_L_LA(_vmalloc) +UASM_L_LA(_vmalloc_done) +UASM_L_LA(_tlbw_hazard) +UASM_L_LA(_split) +UASM_L_LA(_nopage_tlbl) +UASM_L_LA(_nopage_tlbs) +UASM_L_LA(_nopage_tlbm) +UASM_L_LA(_smp_pgtable_change) +UASM_L_LA(_r3000_write_probe_fail) /* * For debug purposes. @@ -752,9 +131,9 @@ static inline void dump_handler(const u32 *handler, int count) #define C0_XCONTEXT 20, 0 #ifdef CONFIG_64BIT -# define GET_CONTEXT(buf, reg) i_MFC0(buf, reg, C0_XCONTEXT) +# define GET_CONTEXT(buf, reg) UASM_i_MFC0(buf, reg, C0_XCONTEXT) #else -# define GET_CONTEXT(buf, reg) i_MFC0(buf, reg, C0_CONTEXT) +# define GET_CONTEXT(buf, reg) UASM_i_MFC0(buf, reg, C0_CONTEXT) #endif /* The worst case length of the handler is around 18 instructions for @@ -768,8 +147,8 @@ static inline void dump_handler(const u32 *handler, int count) static u32 tlb_handler[128] __initdata; /* simply assume worst case size for labels and relocs */ -static struct label labels[128] __initdata; -static struct reloc relocs[128] __initdata; +static struct uasm_label labels[128] __initdata; +static struct uasm_reloc relocs[128] __initdata; /* * The R3000 TLB handler is simple. @@ -782,29 +161,29 @@ static void __init build_r3000_tlb_refill_handler(void) memset(tlb_handler, 0, sizeof(tlb_handler)); p = tlb_handler; - i_mfc0(&p, K0, C0_BADVADDR); - i_lui(&p, K1, rel_hi(pgdc)); /* cp0 delay */ - i_lw(&p, K1, rel_lo(pgdc), K1); - i_srl(&p, K0, K0, 22); /* load delay */ - i_sll(&p, K0, K0, 2); - i_addu(&p, K1, K1, K0); - i_mfc0(&p, K0, C0_CONTEXT); - i_lw(&p, K1, 0, K1); /* cp0 delay */ - i_andi(&p, K0, K0, 0xffc); /* load delay */ - i_addu(&p, K1, K1, K0); - i_lw(&p, K0, 0, K1); - i_nop(&p); /* load delay */ - i_mtc0(&p, K0, C0_ENTRYLO0); - i_mfc0(&p, K1, C0_EPC); /* cp0 delay */ - i_tlbwr(&p); /* cp0 delay */ - i_jr(&p, K1); - i_rfe(&p); /* branch delay */ + uasm_i_mfc0(&p, K0, C0_BADVADDR); + uasm_i_lui(&p, K1, uasm_rel_hi(pgdc)); /* cp0 delay */ + uasm_i_lw(&p, K1, uasm_rel_lo(pgdc), K1); + uasm_i_srl(&p, K0, K0, 22); /* load delay */ + uasm_i_sll(&p, K0, K0, 2); + uasm_i_addu(&p, K1, K1, K0); + uasm_i_mfc0(&p, K0, C0_CONTEXT); + uasm_i_lw(&p, K1, 0, K1); /* cp0 delay */ + uasm_i_andi(&p, K0, K0, 0xffc); /* load delay */ + uasm_i_addu(&p, K1, K1, K0); + uasm_i_lw(&p, K0, 0, K1); + uasm_i_nop(&p); /* load delay */ + uasm_i_mtc0(&p, K0, C0_ENTRYLO0); + uasm_i_mfc0(&p, K1, C0_EPC); /* cp0 delay */ + uasm_i_tlbwr(&p); /* cp0 delay */ + uasm_i_jr(&p, K1); + uasm_i_rfe(&p); /* branch delay */ if (p > tlb_handler + 32) panic("TLB refill handler space exceeded"); - pr_info("Synthesized TLB refill handler (%u instructions).\n", - (unsigned int)(p - tlb_handler)); + pr_debug("Wrote TLB refill handler (%u instructions).\n", + (unsigned int)(p - tlb_handler)); memcpy((void *)ebase, tlb_handler, 0x80); @@ -850,12 +229,12 @@ static void __init __maybe_unused build_tlb_probe_entry(u32 **p) case CPU_R5000: case CPU_R5000A: case CPU_NEVADA: - i_nop(p); - i_tlbp(p); + uasm_i_nop(p); + uasm_i_tlbp(p); break; default: - i_tlbp(p); + uasm_i_tlbp(p); break; } } @@ -866,19 +245,19 @@ static void __init __maybe_unused build_tlb_probe_entry(u32 **p) */ enum tlb_write_entry { tlb_random, tlb_indexed }; -static void __init build_tlb_write_entry(u32 **p, struct label **l, - struct reloc **r, +static void __init build_tlb_write_entry(u32 **p, struct uasm_label **l, + struct uasm_reloc **r, enum tlb_write_entry wmode) { void(*tlbw)(u32 **) = NULL; switch (wmode) { - case tlb_random: tlbw = i_tlbwr; break; - case tlb_indexed: tlbw = i_tlbwi; break; + case tlb_random: tlbw = uasm_i_tlbwr; break; + case tlb_indexed: tlbw = uasm_i_tlbwi; break; } if (cpu_has_mips_r2) { - i_ehb(p); + uasm_i_ehb(p); tlbw(p); return; } @@ -894,19 +273,19 @@ static void __init build_tlb_write_entry(u32 **p, struct label **l, * This branch uses up a mtc0 hazard nop slot and saves * two nops after the tlbw instruction. */ - il_bgezl(p, r, 0, label_tlbw_hazard); + uasm_il_bgezl(p, r, 0, label_tlbw_hazard); tlbw(p); - l_tlbw_hazard(l, *p); - i_nop(p); + uasm_l_tlbw_hazard(l, *p); + uasm_i_nop(p); break; case CPU_R4600: case CPU_R4700: case CPU_R5000: case CPU_R5000A: - i_nop(p); + uasm_i_nop(p); tlbw(p); - i_nop(p); + uasm_i_nop(p); break; case CPU_R4300: @@ -920,7 +299,7 @@ static void __init build_tlb_write_entry(u32 **p, struct label **l, case CPU_AU1210: case CPU_AU1250: case CPU_PR4450: - i_nop(p); + uasm_i_nop(p); tlbw(p); break; @@ -937,26 +316,26 @@ static void __init build_tlb_write_entry(u32 **p, struct label **l, case CPU_BCM4710: case CPU_LOONGSON2: if (m4kc_tlbp_war()) - i_nop(p); + uasm_i_nop(p); tlbw(p); break; case CPU_NEVADA: - i_nop(p); /* QED specifies 2 nops hazard */ + uasm_i_nop(p); /* QED specifies 2 nops hazard */ /* * This branch uses up a mtc0 hazard nop slot and saves * a nop after the tlbw instruction. */ - il_bgezl(p, r, 0, label_tlbw_hazard); + uasm_il_bgezl(p, r, 0, label_tlbw_hazard); tlbw(p); - l_tlbw_hazard(l, *p); + uasm_l_tlbw_hazard(l, *p); break; case CPU_RM7000: - i_nop(p); - i_nop(p); - i_nop(p); - i_nop(p); + uasm_i_nop(p); + uasm_i_nop(p); + uasm_i_nop(p); + uasm_i_nop(p); tlbw(p); break; @@ -967,15 +346,15 @@ static void __init build_tlb_write_entry(u32 **p, struct label **l, * cpu cycles and use for data translations should not occur * for 3 cpu cycles. */ - i_ssnop(p); - i_ssnop(p); - i_ssnop(p); - i_ssnop(p); + uasm_i_ssnop(p); + uasm_i_ssnop(p); + uasm_i_ssnop(p); + uasm_i_ssnop(p); tlbw(p); - i_ssnop(p); - i_ssnop(p); - i_ssnop(p); - i_ssnop(p); + uasm_i_ssnop(p); + uasm_i_ssnop(p); + uasm_i_ssnop(p); + uasm_i_ssnop(p); break; case CPU_VR4111: @@ -983,18 +362,18 @@ static void __init build_tlb_write_entry(u32 **p, struct label **l, case CPU_VR4122: case CPU_VR4181: case CPU_VR4181A: - i_nop(p); - i_nop(p); + uasm_i_nop(p); + uasm_i_nop(p); tlbw(p); - i_nop(p); - i_nop(p); + uasm_i_nop(p); + uasm_i_nop(p); break; case CPU_VR4131: case CPU_VR4133: case CPU_R5432: - i_nop(p); - i_nop(p); + uasm_i_nop(p); + uasm_i_nop(p); tlbw(p); break; @@ -1011,7 +390,7 @@ static void __init build_tlb_write_entry(u32 **p, struct label **l, * TMP will be clobbered, PTR will hold the pmd entry. */ static void __init -build_get_pmde64(u32 **p, struct label **l, struct reloc **r, +build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, unsigned int tmp, unsigned int ptr) { long pgdc = (long)pgd_current; @@ -1019,52 +398,52 @@ build_get_pmde64(u32 **p, struct label **l, struct reloc **r, /* * The vmalloc handling is not in the hotpath. */ - i_dmfc0(p, tmp, C0_BADVADDR); + uasm_i_dmfc0(p, tmp, C0_BADVADDR); #ifdef MODULE_START - il_bltz(p, r, tmp, label_module_alloc); + uasm_il_bltz(p, r, tmp, label_module_alloc); #else - il_bltz(p, r, tmp, label_vmalloc); + uasm_il_bltz(p, r, tmp, label_vmalloc); #endif - /* No i_nop needed here, since the next insn doesn't touch TMP. */ + /* No uasm_i_nop needed here, since the next insn doesn't touch TMP. */ #ifdef CONFIG_SMP # ifdef CONFIG_MIPS_MT_SMTC /* * SMTC uses TCBind value as "CPU" index */ - i_mfc0(p, ptr, C0_TCBIND); - i_dsrl(p, ptr, ptr, 19); + uasm_i_mfc0(p, ptr, C0_TCBIND); + uasm_i_dsrl(p, ptr, ptr, 19); # else /* * 64 bit SMP running in XKPHYS has smp_processor_id() << 3 * stored in CONTEXT. */ - i_dmfc0(p, ptr, C0_CONTEXT); - i_dsrl(p, ptr, ptr, 23); + uasm_i_dmfc0(p, ptr, C0_CONTEXT); + uasm_i_dsrl(p, ptr, ptr, 23); #endif - i_LA_mostly(p, tmp, pgdc); - i_daddu(p, ptr, ptr, tmp); - i_dmfc0(p, tmp, C0_BADVADDR); - i_ld(p, ptr, rel_lo(pgdc), ptr); + UASM_i_LA_mostly(p, tmp, pgdc); + uasm_i_daddu(p, ptr, ptr, tmp); + uasm_i_dmfc0(p, tmp, C0_BADVADDR); + uasm_i_ld(p, ptr, uasm_rel_lo(pgdc), ptr); #else - i_LA_mostly(p, ptr, pgdc); - i_ld(p, ptr, rel_lo(pgdc), ptr); + UASM_i_LA_mostly(p, ptr, pgdc); + uasm_i_ld(p, ptr, uasm_rel_lo(pgdc), ptr); #endif - l_vmalloc_done(l, *p); + uasm_l_vmalloc_done(l, *p); if (PGDIR_SHIFT - 3 < 32) /* get pgd offset in bytes */ - i_dsrl(p, tmp, tmp, PGDIR_SHIFT-3); + uasm_i_dsrl(p, tmp, tmp, PGDIR_SHIFT-3); else - i_dsrl32(p, tmp, tmp, PGDIR_SHIFT - 3 - 32); - - i_andi(p, tmp, tmp, (PTRS_PER_PGD - 1)<<3); - i_daddu(p, ptr, ptr, tmp); /* add in pgd offset */ - i_dmfc0(p, tmp, C0_BADVADDR); /* get faulting address */ - i_ld(p, ptr, 0, ptr); /* get pmd pointer */ - i_dsrl(p, tmp, tmp, PMD_SHIFT-3); /* get pmd offset in bytes */ - i_andi(p, tmp, tmp, (PTRS_PER_PMD - 1)<<3); - i_daddu(p, ptr, ptr, tmp); /* add in pmd offset */ + uasm_i_dsrl32(p, tmp, tmp, PGDIR_SHIFT - 3 - 32); + + uasm_i_andi(p, tmp, tmp, (PTRS_PER_PGD - 1)<<3); + uasm_i_daddu(p, ptr, ptr, tmp); /* add in pgd offset */ + uasm_i_dmfc0(p, tmp, C0_BADVADDR); /* get faulting address */ + uasm_i_ld(p, ptr, 0, ptr); /* get pmd pointer */ + uasm_i_dsrl(p, tmp, tmp, PMD_SHIFT-3); /* get pmd offset in bytes */ + uasm_i_andi(p, tmp, tmp, (PTRS_PER_PMD - 1)<<3); + uasm_i_daddu(p, ptr, ptr, tmp); /* add in pmd offset */ } /* @@ -1072,7 +451,7 @@ build_get_pmde64(u32 **p, struct label **l, struct reloc **r, * PTR will hold the pgd for vmalloc. */ static void __init -build_get_pgd_vmalloc64(u32 **p, struct label **l, struct reloc **r, +build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, unsigned int bvaddr, unsigned int ptr) { long swpd = (long)swapper_pg_dir; @@ -1080,58 +459,60 @@ build_get_pgd_vmalloc64(u32 **p, struct label **l, struct reloc **r, #ifdef MODULE_START long modd = (long)module_pg_dir; - l_module_alloc(l, *p); + uasm_l_module_alloc(l, *p); /* * Assumption: * VMALLOC_START >= 0xc000000000000000UL * MODULE_START >= 0xe000000000000000UL */ - i_SLL(p, ptr, bvaddr, 2); - il_bgez(p, r, ptr, label_vmalloc); + UASM_i_SLL(p, ptr, bvaddr, 2); + uasm_il_bgez(p, r, ptr, label_vmalloc); - if (in_compat_space_p(MODULE_START) && !rel_lo(MODULE_START)) { - i_lui(p, ptr, rel_hi(MODULE_START)); /* delay slot */ + if (uasm_in_compat_space_p(MODULE_START) && + !uasm_rel_lo(MODULE_START)) { + uasm_i_lui(p, ptr, uasm_rel_hi(MODULE_START)); /* delay slot */ } else { /* unlikely configuration */ - i_nop(p); /* delay slot */ - i_LA(p, ptr, MODULE_START); + uasm_i_nop(p); /* delay slot */ + UASM_i_LA(p, ptr, MODULE_START); } - i_dsubu(p, bvaddr, bvaddr, ptr); + uasm_i_dsubu(p, bvaddr, bvaddr, ptr); - if (in_compat_space_p(modd) && !rel_lo(modd)) { - il_b(p, r, label_vmalloc_done); - i_lui(p, ptr, rel_hi(modd)); + if (uasm_in_compat_space_p(modd) && !uasm_rel_lo(modd)) { + uasm_il_b(p, r, label_vmalloc_done); + uasm_i_lui(p, ptr, uasm_rel_hi(modd)); } else { - i_LA_mostly(p, ptr, modd); - il_b(p, r, label_vmalloc_done); - if (in_compat_space_p(modd)) - i_addiu(p, ptr, ptr, rel_lo(modd)); + UASM_i_LA_mostly(p, ptr, modd); + uasm_il_b(p, r, label_vmalloc_done); + if (uasm_in_compat_space_p(modd)) + uasm_i_addiu(p, ptr, ptr, uasm_rel_lo(modd)); else - i_daddiu(p, ptr, ptr, rel_lo(modd)); + uasm_i_daddiu(p, ptr, ptr, uasm_rel_lo(modd)); } - l_vmalloc(l, *p); - if (in_compat_space_p(MODULE_START) && !rel_lo(MODULE_START) && + uasm_l_vmalloc(l, *p); + if (uasm_in_compat_space_p(MODULE_START) && + !uasm_rel_lo(MODULE_START) && MODULE_START << 32 == VMALLOC_START) - i_dsll32(p, ptr, ptr, 0); /* typical case */ + uasm_i_dsll32(p, ptr, ptr, 0); /* typical case */ else - i_LA(p, ptr, VMALLOC_START); + UASM_i_LA(p, ptr, VMALLOC_START); #else - l_vmalloc(l, *p); - i_LA(p, ptr, VMALLOC_START); + uasm_l_vmalloc(l, *p); + UASM_i_LA(p, ptr, VMALLOC_START); #endif - i_dsubu(p, bvaddr, bvaddr, ptr); + uasm_i_dsubu(p, bvaddr, bvaddr, ptr); - if (in_compat_space_p(swpd) && !rel_lo(swpd)) { - il_b(p, r, label_vmalloc_done); - i_lui(p, ptr, rel_hi(swpd)); + if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) { + uasm_il_b(p, r, label_vmalloc_done); + uasm_i_lui(p, ptr, uasm_rel_hi(swpd)); } else { - i_LA_mostly(p, ptr, swpd); - il_b(p, r, label_vmalloc_done); - if (in_compat_space_p(swpd)) - i_addiu(p, ptr, ptr, rel_lo(swpd)); + UASM_i_LA_mostly(p, ptr, swpd); + uasm_il_b(p, r, label_vmalloc_done); + if (uasm_in_compat_space_p(swpd)) + uasm_i_addiu(p, ptr, ptr, uasm_rel_lo(swpd)); else - i_daddiu(p, ptr, ptr, rel_lo(swpd)); + uasm_i_daddiu(p, ptr, ptr, uasm_rel_lo(swpd)); } } @@ -1152,26 +533,26 @@ build_get_pgde32(u32 **p, unsigned int tmp, unsigned int ptr) /* * SMTC uses TCBind value as "CPU" index */ - i_mfc0(p, ptr, C0_TCBIND); - i_LA_mostly(p, tmp, pgdc); - i_srl(p, ptr, ptr, 19); + uasm_i_mfc0(p, ptr, C0_TCBIND); + UASM_i_LA_mostly(p, tmp, pgdc); + uasm_i_srl(p, ptr, ptr, 19); #else /* * smp_processor_id() << 3 is stored in CONTEXT. */ - i_mfc0(p, ptr, C0_CONTEXT); - i_LA_mostly(p, tmp, pgdc); - i_srl(p, ptr, ptr, 23); + uasm_i_mfc0(p, ptr, C0_CONTEXT); + UASM_i_LA_mostly(p, tmp, pgdc); + uasm_i_srl(p, ptr, ptr, 23); #endif - i_addu(p, ptr, tmp, ptr); + uasm_i_addu(p, ptr, tmp, ptr); #else - i_LA_mostly(p, ptr, pgdc); + UASM_i_LA_mostly(p, ptr, pgdc); #endif - i_mfc0(p, tmp, C0_BADVADDR); /* get faulting address */ - i_lw(p, ptr, rel_lo(pgdc), ptr); - i_srl(p, tmp, tmp, PGDIR_SHIFT); /* get pgd only bits */ - i_sll(p, tmp, tmp, PGD_T_LOG2); - i_addu(p, ptr, ptr, tmp); /* add in pgd offset */ + uasm_i_mfc0(p, tmp, C0_BADVADDR); /* get faulting address */ + uasm_i_lw(p, ptr, uasm_rel_lo(pgdc), ptr); + uasm_i_srl(p, tmp, tmp, PGDIR_SHIFT); /* get pgd only bits */ + uasm_i_sll(p, tmp, tmp, PGD_T_LOG2); + uasm_i_addu(p, ptr, ptr, tmp); /* add in pgd offset */ } #endif /* !CONFIG_64BIT */ @@ -1198,8 +579,8 @@ static void __init build_adjust_context(u32 **p, unsigned int ctx) } if (shift) - i_SRL(p, ctx, ctx, shift); - i_andi(p, ctx, ctx, mask); + UASM_i_SRL(p, ctx, ctx, shift); + uasm_i_andi(p, ctx, ctx, mask); } static void __init build_get_ptep(u32 **p, unsigned int tmp, unsigned int ptr) @@ -1213,18 +594,18 @@ static void __init build_get_ptep(u32 **p, unsigned int tmp, unsigned int ptr) */ switch (current_cpu_type()) { case CPU_NEVADA: - i_LW(p, ptr, 0, ptr); + UASM_i_LW(p, ptr, 0, ptr); GET_CONTEXT(p, tmp); /* get context reg */ break; default: GET_CONTEXT(p, tmp); /* get context reg */ - i_LW(p, ptr, 0, ptr); + UASM_i_LW(p, ptr, 0, ptr); break; } build_adjust_context(p, tmp); - i_ADDU(p, ptr, ptr, tmp); /* add in offset */ + UASM_i_ADDU(p, ptr, ptr, tmp); /* add in offset */ } static void __init build_update_entries(u32 **p, unsigned int tmp, @@ -1236,45 +617,45 @@ static void __init build_update_entries(u32 **p, unsigned int tmp, */ #ifdef CONFIG_64BIT_PHYS_ADDR if (cpu_has_64bits) { - i_ld(p, tmp, 0, ptep); /* get even pte */ - i_ld(p, ptep, sizeof(pte_t), ptep); /* get odd pte */ - i_dsrl(p, tmp, tmp, 6); /* convert to entrylo0 */ - i_mtc0(p, tmp, C0_ENTRYLO0); /* load it */ - i_dsrl(p, ptep, ptep, 6); /* convert to entrylo1 */ - i_mtc0(p, ptep, C0_ENTRYLO1); /* load it */ + uasm_i_ld(p, tmp, 0, ptep); /* get even pte */ + uasm_i_ld(p, ptep, sizeof(pte_t), ptep); /* get odd pte */ + uasm_i_dsrl(p, tmp, tmp, 6); /* convert to entrylo0 */ + uasm_i_mtc0(p, tmp, C0_ENTRYLO0); /* load it */ + uasm_i_dsrl(p, ptep, ptep, 6); /* convert to entrylo1 */ + uasm_i_mtc0(p, ptep, C0_ENTRYLO1); /* load it */ } else { int pte_off_even = sizeof(pte_t) / 2; int pte_off_odd = pte_off_even + sizeof(pte_t); /* The pte entries are pre-shifted */ - i_lw(p, tmp, pte_off_even, ptep); /* get even pte */ - i_mtc0(p, tmp, C0_ENTRYLO0); /* load it */ - i_lw(p, ptep, pte_off_odd, ptep); /* get odd pte */ - i_mtc0(p, ptep, C0_ENTRYLO1); /* load it */ + uasm_i_lw(p, tmp, pte_off_even, ptep); /* get even pte */ + uasm_i_mtc0(p, tmp, C0_ENTRYLO0); /* load it */ + uasm_i_lw(p, ptep, pte_off_odd, ptep); /* get odd pte */ + uasm_i_mtc0(p, ptep, C0_ENTRYLO1); /* load it */ } #else - i_LW(p, tmp, 0, ptep); /* get even pte */ - i_LW(p, ptep, sizeof(pte_t), ptep); /* get odd pte */ + UASM_i_LW(p, tmp, 0, ptep); /* get even pte */ + UASM_i_LW(p, ptep, sizeof(pte_t), ptep); /* get odd pte */ if (r45k_bvahwbug()) build_tlb_probe_entry(p); - i_SRL(p, tmp, tmp, 6); /* convert to entrylo0 */ + UASM_i_SRL(p, tmp, tmp, 6); /* convert to entrylo0 */ if (r4k_250MHZhwbug()) - i_mtc0(p, 0, C0_ENTRYLO0); - i_mtc0(p, tmp, C0_ENTRYLO0); /* load it */ - i_SRL(p, ptep, ptep, 6); /* convert to entrylo1 */ + uasm_i_mtc0(p, 0, C0_ENTRYLO0); + uasm_i_mtc0(p, tmp, C0_ENTRYLO0); /* load it */ + UASM_i_SRL(p, ptep, ptep, 6); /* convert to entrylo1 */ if (r45k_bvahwbug()) - i_mfc0(p, tmp, C0_INDEX); + uasm_i_mfc0(p, tmp, C0_INDEX); if (r4k_250MHZhwbug()) - i_mtc0(p, 0, C0_ENTRYLO1); - i_mtc0(p, ptep, C0_ENTRYLO1); /* load it */ + uasm_i_mtc0(p, 0, C0_ENTRYLO1); + uasm_i_mtc0(p, ptep, C0_ENTRYLO1); /* load it */ #endif } static void __init build_r4000_tlb_refill_handler(void) { u32 *p = tlb_handler; - struct label *l = labels; - struct reloc *r = relocs; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; u32 *f; unsigned int final_len; @@ -1287,12 +668,12 @@ static void __init build_r4000_tlb_refill_handler(void) * create the plain linear handler */ if (bcm1250_m3_war()) { - i_MFC0(&p, K0, C0_BADVADDR); - i_MFC0(&p, K1, C0_ENTRYHI); - i_xor(&p, K0, K0, K1); - i_SRL(&p, K0, K0, PAGE_SHIFT + 1); - il_bnez(&p, &r, K0, label_leave); - /* No need for i_nop */ + UASM_i_MFC0(&p, K0, C0_BADVADDR); + UASM_i_MFC0(&p, K1, C0_ENTRYHI); + uasm_i_xor(&p, K0, K0, K1); + UASM_i_SRL(&p, K0, K0, PAGE_SHIFT + 1); + uasm_il_bnez(&p, &r, K0, label_leave); + /* No need for uasm_i_nop */ } #ifdef CONFIG_64BIT @@ -1304,8 +685,8 @@ static void __init build_r4000_tlb_refill_handler(void) build_get_ptep(&p, K0, K1); build_update_entries(&p, K0, K1); build_tlb_write_entry(&p, &l, &r, tlb_random); - l_leave(&l, p); - i_eret(&p); /* return from trap */ + uasm_l_leave(&l, p); + uasm_i_eret(&p); /* return from trap */ #ifdef CONFIG_64BIT build_get_pgd_vmalloc64(&p, &l, &r, K0, K1); @@ -1325,7 +706,7 @@ static void __init build_r4000_tlb_refill_handler(void) #else if (((p - tlb_handler) > 63) || (((p - tlb_handler) > 61) - && insn_has_bdelay(relocs, tlb_handler + 29))) + && uasm_insn_has_bdelay(relocs, tlb_handler + 29))) panic("TLB refill handler space exceeded"); #endif @@ -1335,13 +716,13 @@ static void __init build_r4000_tlb_refill_handler(void) #if defined(CONFIG_32BIT) || defined(CONFIG_CPU_LOONGSON2) f = final_handler; /* Simplest case, just copy the handler. */ - copy_handler(relocs, labels, tlb_handler, p, f); + uasm_copy_handler(relocs, labels, tlb_handler, p, f); final_len = p - tlb_handler; #else /* CONFIG_64BIT */ f = final_handler + 32; if ((p - tlb_handler) <= 32) { /* Just copy the handler. */ - copy_handler(relocs, labels, tlb_handler, p, f); + uasm_copy_handler(relocs, labels, tlb_handler, p, f); final_len = p - tlb_handler; } else { u32 *split = tlb_handler + 30; @@ -1349,34 +730,34 @@ static void __init build_r4000_tlb_refill_handler(void) /* * Find the split point. */ - if (insn_has_bdelay(relocs, split - 1)) + if (uasm_insn_has_bdelay(relocs, split - 1)) split--; /* Copy first part of the handler. */ - copy_handler(relocs, labels, tlb_handler, split, f); + uasm_copy_handler(relocs, labels, tlb_handler, split, f); f += split - tlb_handler; /* Insert branch. */ - l_split(&l, final_handler); - il_b(&f, &r, label_split); - if (insn_has_bdelay(relocs, split)) - i_nop(&f); + uasm_l_split(&l, final_handler); + uasm_il_b(&f, &r, label_split); + if (uasm_insn_has_bdelay(relocs, split)) + uasm_i_nop(&f); else { - copy_handler(relocs, labels, split, split + 1, f); - move_labels(labels, f, f + 1, -1); + uasm_copy_handler(relocs, labels, split, split + 1, f); + uasm_move_labels(labels, f, f + 1, -1); f++; split++; } /* Copy the rest of the handler. */ - copy_handler(relocs, labels, split, p, final_handler); + uasm_copy_handler(relocs, labels, split, p, final_handler); final_len = (f - (final_handler + 32)) + (p - split); } #endif /* CONFIG_64BIT */ - resolve_relocs(relocs, labels); - pr_info("Synthesized TLB refill handler (%u instructions).\n", - final_len); + uasm_resolve_relocs(relocs, labels); + pr_debug("Wrote TLB refill handler (%u instructions).\n", + final_len); memcpy((void *)ebase, final_handler, 0x100); @@ -1403,75 +784,75 @@ u32 handle_tlbs[FASTPATH_SIZE] __cacheline_aligned; u32 handle_tlbm[FASTPATH_SIZE] __cacheline_aligned; static void __init -iPTE_LW(u32 **p, struct label **l, unsigned int pte, unsigned int ptr) +iPTE_LW(u32 **p, struct uasm_label **l, unsigned int pte, unsigned int ptr) { #ifdef CONFIG_SMP # ifdef CONFIG_64BIT_PHYS_ADDR if (cpu_has_64bits) - i_lld(p, pte, 0, ptr); + uasm_i_lld(p, pte, 0, ptr); else # endif - i_LL(p, pte, 0, ptr); + UASM_i_LL(p, pte, 0, ptr); #else # ifdef CONFIG_64BIT_PHYS_ADDR if (cpu_has_64bits) - i_ld(p, pte, 0, ptr); + uasm_i_ld(p, pte, 0, ptr); else # endif - i_LW(p, pte, 0, ptr); + UASM_i_LW(p, pte, 0, ptr); #endif } static void __init -iPTE_SW(u32 **p, struct reloc **r, unsigned int pte, unsigned int ptr, +iPTE_SW(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr, unsigned int mode) { #ifdef CONFIG_64BIT_PHYS_ADDR unsigned int hwmode = mode & (_PAGE_VALID | _PAGE_DIRTY); #endif - i_ori(p, pte, pte, mode); + uasm_i_ori(p, pte, pte, mode); #ifdef CONFIG_SMP # ifdef CONFIG_64BIT_PHYS_ADDR if (cpu_has_64bits) - i_scd(p, pte, 0, ptr); + uasm_i_scd(p, pte, 0, ptr); else # endif - i_SC(p, pte, 0, ptr); + UASM_i_SC(p, pte, 0, ptr); if (r10000_llsc_war()) - il_beqzl(p, r, pte, label_smp_pgtable_change); + uasm_il_beqzl(p, r, pte, label_smp_pgtable_change); else - il_beqz(p, r, pte, label_smp_pgtable_change); + uasm_il_beqz(p, r, pte, label_smp_pgtable_change); # ifdef CONFIG_64BIT_PHYS_ADDR if (!cpu_has_64bits) { - /* no i_nop needed */ - i_ll(p, pte, sizeof(pte_t) / 2, ptr); - i_ori(p, pte, pte, hwmode); - i_sc(p, pte, sizeof(pte_t) / 2, ptr); - il_beqz(p, r, pte, label_smp_pgtable_change); - /* no i_nop needed */ - i_lw(p, pte, 0, ptr); + /* no uasm_i_nop needed */ + uasm_i_ll(p, pte, sizeof(pte_t) / 2, ptr); + uasm_i_ori(p, pte, pte, hwmode); + uasm_i_sc(p, pte, sizeof(pte_t) / 2, ptr); + uasm_il_beqz(p, r, pte, label_smp_pgtable_change); + /* no uasm_i_nop needed */ + uasm_i_lw(p, pte, 0, ptr); } else - i_nop(p); + uasm_i_nop(p); # else - i_nop(p); + uasm_i_nop(p); # endif #else # ifdef CONFIG_64BIT_PHYS_ADDR if (cpu_has_64bits) - i_sd(p, pte, 0, ptr); + uasm_i_sd(p, pte, 0, ptr); else # endif - i_SW(p, pte, 0, ptr); + UASM_i_SW(p, pte, 0, ptr); # ifdef CONFIG_64BIT_PHYS_ADDR if (!cpu_has_64bits) { - i_lw(p, pte, sizeof(pte_t) / 2, ptr); - i_ori(p, pte, pte, hwmode); - i_sw(p, pte, sizeof(pte_t) / 2, ptr); - i_lw(p, pte, 0, ptr); + uasm_i_lw(p, pte, sizeof(pte_t) / 2, ptr); + uasm_i_ori(p, pte, pte, hwmode); + uasm_i_sw(p, pte, sizeof(pte_t) / 2, ptr); + uasm_i_lw(p, pte, 0, ptr); } # endif #endif @@ -1483,18 +864,18 @@ iPTE_SW(u32 **p, struct reloc **r, unsigned int pte, unsigned int ptr, * with it's original value. */ static void __init -build_pte_present(u32 **p, struct label **l, struct reloc **r, +build_pte_present(u32 **p, struct uasm_label **l, struct uasm_reloc **r, unsigned int pte, unsigned int ptr, enum label_id lid) { - i_andi(p, pte, pte, _PAGE_PRESENT | _PAGE_READ); - i_xori(p, pte, pte, _PAGE_PRESENT | _PAGE_READ); - il_bnez(p, r, pte, lid); + uasm_i_andi(p, pte, pte, _PAGE_PRESENT | _PAGE_READ); + uasm_i_xori(p, pte, pte, _PAGE_PRESENT | _PAGE_READ); + uasm_il_bnez(p, r, pte, lid); iPTE_LW(p, l, pte, ptr); } /* Make PTE valid, store result in PTR. */ static void __init -build_make_valid(u32 **p, struct reloc **r, unsigned int pte, +build_make_valid(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr) { unsigned int mode = _PAGE_VALID | _PAGE_ACCESSED; @@ -1507,12 +888,12 @@ build_make_valid(u32 **p, struct reloc **r, unsigned int pte, * restore PTE with value from PTR when done. */ static void __init -build_pte_writable(u32 **p, struct label **l, struct reloc **r, +build_pte_writable(u32 **p, struct uasm_label **l, struct uasm_reloc **r, unsigned int pte, unsigned int ptr, enum label_id lid) { - i_andi(p, pte, pte, _PAGE_PRESENT | _PAGE_WRITE); - i_xori(p, pte, pte, _PAGE_PRESENT | _PAGE_WRITE); - il_bnez(p, r, pte, lid); + uasm_i_andi(p, pte, pte, _PAGE_PRESENT | _PAGE_WRITE); + uasm_i_xori(p, pte, pte, _PAGE_PRESENT | _PAGE_WRITE); + uasm_il_bnez(p, r, pte, lid); iPTE_LW(p, l, pte, ptr); } @@ -1520,7 +901,7 @@ build_pte_writable(u32 **p, struct label **l, struct reloc **r, * at PTR. */ static void __init -build_make_write(u32 **p, struct reloc **r, unsigned int pte, +build_make_write(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr) { unsigned int mode = (_PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID @@ -1534,11 +915,11 @@ build_make_write(u32 **p, struct reloc **r, unsigned int pte, * restore PTE with value from PTR when done. */ static void __init -build_pte_modifiable(u32 **p, struct label **l, struct reloc **r, +build_pte_modifiable(u32 **p, struct uasm_label **l, struct uasm_reloc **r, unsigned int pte, unsigned int ptr, enum label_id lid) { - i_andi(p, pte, pte, _PAGE_WRITE); - il_beqz(p, r, pte, lid); + uasm_i_andi(p, pte, pte, _PAGE_WRITE); + uasm_il_beqz(p, r, pte, lid); iPTE_LW(p, l, pte, ptr); } @@ -1553,11 +934,11 @@ build_pte_modifiable(u32 **p, struct label **l, struct reloc **r, static void __init build_r3000_pte_reload_tlbwi(u32 **p, unsigned int pte, unsigned int tmp) { - i_mtc0(p, pte, C0_ENTRYLO0); /* cp0 delay */ - i_mfc0(p, tmp, C0_EPC); /* cp0 delay */ - i_tlbwi(p); - i_jr(p, tmp); - i_rfe(p); /* branch delay */ + uasm_i_mtc0(p, pte, C0_ENTRYLO0); /* cp0 delay */ + uasm_i_mfc0(p, tmp, C0_EPC); /* cp0 delay */ + uasm_i_tlbwi(p); + uasm_i_jr(p, tmp); + uasm_i_rfe(p); /* branch delay */ } /* @@ -1567,20 +948,21 @@ build_r3000_pte_reload_tlbwi(u32 **p, unsigned int pte, unsigned int tmp) * kseg2 access, i.e. without refill. Then it returns. */ static void __init -build_r3000_tlb_reload_write(u32 **p, struct label **l, struct reloc **r, - unsigned int pte, unsigned int tmp) -{ - i_mfc0(p, tmp, C0_INDEX); - i_mtc0(p, pte, C0_ENTRYLO0); /* cp0 delay */ - il_bltz(p, r, tmp, label_r3000_write_probe_fail); /* cp0 delay */ - i_mfc0(p, tmp, C0_EPC); /* branch delay */ - i_tlbwi(p); /* cp0 delay */ - i_jr(p, tmp); - i_rfe(p); /* branch delay */ - l_r3000_write_probe_fail(l, *p); - i_tlbwr(p); /* cp0 delay */ - i_jr(p, tmp); - i_rfe(p); /* branch delay */ +build_r3000_tlb_reload_write(u32 **p, struct uasm_label **l, + struct uasm_reloc **r, unsigned int pte, + unsigned int tmp) +{ + uasm_i_mfc0(p, tmp, C0_INDEX); + uasm_i_mtc0(p, pte, C0_ENTRYLO0); /* cp0 delay */ + uasm_il_bltz(p, r, tmp, label_r3000_write_probe_fail); /* cp0 delay */ + uasm_i_mfc0(p, tmp, C0_EPC); /* branch delay */ + uasm_i_tlbwi(p); /* cp0 delay */ + uasm_i_jr(p, tmp); + uasm_i_rfe(p); /* branch delay */ + uasm_l_r3000_write_probe_fail(l, *p); + uasm_i_tlbwr(p); /* cp0 delay */ + uasm_i_jr(p, tmp); + uasm_i_rfe(p); /* branch delay */ } static void __init @@ -1589,25 +971,25 @@ build_r3000_tlbchange_handler_head(u32 **p, unsigned int pte, { long pgdc = (long)pgd_current; - i_mfc0(p, pte, C0_BADVADDR); - i_lui(p, ptr, rel_hi(pgdc)); /* cp0 delay */ - i_lw(p, ptr, rel_lo(pgdc), ptr); - i_srl(p, pte, pte, 22); /* load delay */ - i_sll(p, pte, pte, 2); - i_addu(p, ptr, ptr, pte); - i_mfc0(p, pte, C0_CONTEXT); - i_lw(p, ptr, 0, ptr); /* cp0 delay */ - i_andi(p, pte, pte, 0xffc); /* load delay */ - i_addu(p, ptr, ptr, pte); - i_lw(p, pte, 0, ptr); - i_tlbp(p); /* load delay */ + uasm_i_mfc0(p, pte, C0_BADVADDR); + uasm_i_lui(p, ptr, uasm_rel_hi(pgdc)); /* cp0 delay */ + uasm_i_lw(p, ptr, uasm_rel_lo(pgdc), ptr); + uasm_i_srl(p, pte, pte, 22); /* load delay */ + uasm_i_sll(p, pte, pte, 2); + uasm_i_addu(p, ptr, ptr, pte); + uasm_i_mfc0(p, pte, C0_CONTEXT); + uasm_i_lw(p, ptr, 0, ptr); /* cp0 delay */ + uasm_i_andi(p, pte, pte, 0xffc); /* load delay */ + uasm_i_addu(p, ptr, ptr, pte); + uasm_i_lw(p, pte, 0, ptr); + uasm_i_tlbp(p); /* load delay */ } static void __init build_r3000_tlb_load_handler(void) { u32 *p = handle_tlbl; - struct label *l = labels; - struct reloc *r = relocs; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; memset(handle_tlbl, 0, sizeof(handle_tlbl)); memset(labels, 0, sizeof(labels)); @@ -1615,20 +997,20 @@ static void __init build_r3000_tlb_load_handler(void) build_r3000_tlbchange_handler_head(&p, K0, K1); build_pte_present(&p, &l, &r, K0, K1, label_nopage_tlbl); - i_nop(&p); /* load delay */ + uasm_i_nop(&p); /* load delay */ build_make_valid(&p, &r, K0, K1); build_r3000_tlb_reload_write(&p, &l, &r, K0, K1); - l_nopage_tlbl(&l, p); - i_j(&p, (unsigned long)tlb_do_page_fault_0 & 0x0fffffff); - i_nop(&p); + uasm_l_nopage_tlbl(&l, p); + uasm_i_j(&p, (unsigned long)tlb_do_page_fault_0 & 0x0fffffff); + uasm_i_nop(&p); if ((p - handle_tlbl) > FASTPATH_SIZE) panic("TLB load handler fastpath space exceeded"); - resolve_relocs(relocs, labels); - pr_info("Synthesized TLB load handler fastpath (%u instructions).\n", - (unsigned int)(p - handle_tlbl)); + uasm_resolve_relocs(relocs, labels); + pr_debug("Wrote TLB load handler fastpath (%u instructions).\n", + (unsigned int)(p - handle_tlbl)); dump_handler(handle_tlbl, ARRAY_SIZE(handle_tlbl)); } @@ -1636,8 +1018,8 @@ static void __init build_r3000_tlb_load_handler(void) static void __init build_r3000_tlb_store_handler(void) { u32 *p = handle_tlbs; - struct label *l = labels; - struct reloc *r = relocs; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; memset(handle_tlbs, 0, sizeof(handle_tlbs)); memset(labels, 0, sizeof(labels)); @@ -1645,20 +1027,20 @@ static void __init build_r3000_tlb_store_handler(void) build_r3000_tlbchange_handler_head(&p, K0, K1); build_pte_writable(&p, &l, &r, K0, K1, label_nopage_tlbs); - i_nop(&p); /* load delay */ + uasm_i_nop(&p); /* load delay */ build_make_write(&p, &r, K0, K1); build_r3000_tlb_reload_write(&p, &l, &r, K0, K1); - l_nopage_tlbs(&l, p); - i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); - i_nop(&p); + uasm_l_nopage_tlbs(&l, p); + uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); + uasm_i_nop(&p); if ((p - handle_tlbs) > FASTPATH_SIZE) panic("TLB store handler fastpath space exceeded"); - resolve_relocs(relocs, labels); - pr_info("Synthesized TLB store handler fastpath (%u instructions).\n", - (unsigned int)(p - handle_tlbs)); + uasm_resolve_relocs(relocs, labels); + pr_debug("Wrote TLB store handler fastpath (%u instructions).\n", + (unsigned int)(p - handle_tlbs)); dump_handler(handle_tlbs, ARRAY_SIZE(handle_tlbs)); } @@ -1666,8 +1048,8 @@ static void __init build_r3000_tlb_store_handler(void) static void __init build_r3000_tlb_modify_handler(void) { u32 *p = handle_tlbm; - struct label *l = labels; - struct reloc *r = relocs; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; memset(handle_tlbm, 0, sizeof(handle_tlbm)); memset(labels, 0, sizeof(labels)); @@ -1675,20 +1057,20 @@ static void __init build_r3000_tlb_modify_handler(void) build_r3000_tlbchange_handler_head(&p, K0, K1); build_pte_modifiable(&p, &l, &r, K0, K1, label_nopage_tlbm); - i_nop(&p); /* load delay */ + uasm_i_nop(&p); /* load delay */ build_make_write(&p, &r, K0, K1); build_r3000_pte_reload_tlbwi(&p, K0, K1); - l_nopage_tlbm(&l, p); - i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); - i_nop(&p); + uasm_l_nopage_tlbm(&l, p); + uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); + uasm_i_nop(&p); if ((p - handle_tlbm) > FASTPATH_SIZE) panic("TLB modify handler fastpath space exceeded"); - resolve_relocs(relocs, labels); - pr_info("Synthesized TLB modify handler fastpath (%u instructions).\n", - (unsigned int)(p - handle_tlbm)); + uasm_resolve_relocs(relocs, labels); + pr_debug("Wrote TLB modify handler fastpath (%u instructions).\n", + (unsigned int)(p - handle_tlbm)); dump_handler(handle_tlbm, ARRAY_SIZE(handle_tlbm)); } @@ -1697,8 +1079,8 @@ static void __init build_r3000_tlb_modify_handler(void) * R4000 style TLB load/store/modify handlers. */ static void __init -build_r4000_tlbchange_handler_head(u32 **p, struct label **l, - struct reloc **r, unsigned int pte, +build_r4000_tlbchange_handler_head(u32 **p, struct uasm_label **l, + struct uasm_reloc **r, unsigned int pte, unsigned int ptr) { #ifdef CONFIG_64BIT @@ -1707,31 +1089,31 @@ build_r4000_tlbchange_handler_head(u32 **p, struct label **l, build_get_pgde32(p, pte, ptr); /* get pgd in ptr */ #endif - i_MFC0(p, pte, C0_BADVADDR); - i_LW(p, ptr, 0, ptr); - i_SRL(p, pte, pte, PAGE_SHIFT + PTE_ORDER - PTE_T_LOG2); - i_andi(p, pte, pte, (PTRS_PER_PTE - 1) << PTE_T_LOG2); - i_ADDU(p, ptr, ptr, pte); + UASM_i_MFC0(p, pte, C0_BADVADDR); + UASM_i_LW(p, ptr, 0, ptr); + UASM_i_SRL(p, pte, pte, PAGE_SHIFT + PTE_ORDER - PTE_T_LOG2); + uasm_i_andi(p, pte, pte, (PTRS_PER_PTE - 1) << PTE_T_LOG2); + UASM_i_ADDU(p, ptr, ptr, pte); #ifdef CONFIG_SMP - l_smp_pgtable_change(l, *p); -# endif + uasm_l_smp_pgtable_change(l, *p); +#endif iPTE_LW(p, l, pte, ptr); /* get even pte */ if (!m4kc_tlbp_war()) build_tlb_probe_entry(p); } static void __init -build_r4000_tlbchange_handler_tail(u32 **p, struct label **l, - struct reloc **r, unsigned int tmp, +build_r4000_tlbchange_handler_tail(u32 **p, struct uasm_label **l, + struct uasm_reloc **r, unsigned int tmp, unsigned int ptr) { - i_ori(p, ptr, ptr, sizeof(pte_t)); - i_xori(p, ptr, ptr, sizeof(pte_t)); + uasm_i_ori(p, ptr, ptr, sizeof(pte_t)); + uasm_i_xori(p, ptr, ptr, sizeof(pte_t)); build_update_entries(p, tmp, ptr); build_tlb_write_entry(p, l, r, tlb_indexed); - l_leave(l, *p); - i_eret(p); /* return from trap */ + uasm_l_leave(l, *p); + uasm_i_eret(p); /* return from trap */ #ifdef CONFIG_64BIT build_get_pgd_vmalloc64(p, l, r, tmp, ptr); @@ -1741,20 +1123,20 @@ build_r4000_tlbchange_handler_tail(u32 **p, struct label **l, static void __init build_r4000_tlb_load_handler(void) { u32 *p = handle_tlbl; - struct label *l = labels; - struct reloc *r = relocs; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; memset(handle_tlbl, 0, sizeof(handle_tlbl)); memset(labels, 0, sizeof(labels)); memset(relocs, 0, sizeof(relocs)); if (bcm1250_m3_war()) { - i_MFC0(&p, K0, C0_BADVADDR); - i_MFC0(&p, K1, C0_ENTRYHI); - i_xor(&p, K0, K0, K1); - i_SRL(&p, K0, K0, PAGE_SHIFT + 1); - il_bnez(&p, &r, K0, label_leave); - /* No need for i_nop */ + UASM_i_MFC0(&p, K0, C0_BADVADDR); + UASM_i_MFC0(&p, K1, C0_ENTRYHI); + uasm_i_xor(&p, K0, K0, K1); + UASM_i_SRL(&p, K0, K0, PAGE_SHIFT + 1); + uasm_il_bnez(&p, &r, K0, label_leave); + /* No need for uasm_i_nop */ } build_r4000_tlbchange_handler_head(&p, &l, &r, K0, K1); @@ -1764,16 +1146,16 @@ static void __init build_r4000_tlb_load_handler(void) build_make_valid(&p, &r, K0, K1); build_r4000_tlbchange_handler_tail(&p, &l, &r, K0, K1); - l_nopage_tlbl(&l, p); - i_j(&p, (unsigned long)tlb_do_page_fault_0 & 0x0fffffff); - i_nop(&p); + uasm_l_nopage_tlbl(&l, p); + uasm_i_j(&p, (unsigned long)tlb_do_page_fault_0 & 0x0fffffff); + uasm_i_nop(&p); if ((p - handle_tlbl) > FASTPATH_SIZE) panic("TLB load handler fastpath space exceeded"); - resolve_relocs(relocs, labels); - pr_info("Synthesized TLB load handler fastpath (%u instructions).\n", - (unsigned int)(p - handle_tlbl)); + uasm_resolve_relocs(relocs, labels); + pr_debug("Wrote TLB load handler fastpath (%u instructions).\n", + (unsigned int)(p - handle_tlbl)); dump_handler(handle_tlbl, ARRAY_SIZE(handle_tlbl)); } @@ -1781,8 +1163,8 @@ static void __init build_r4000_tlb_load_handler(void) static void __init build_r4000_tlb_store_handler(void) { u32 *p = handle_tlbs; - struct label *l = labels; - struct reloc *r = relocs; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; memset(handle_tlbs, 0, sizeof(handle_tlbs)); memset(labels, 0, sizeof(labels)); @@ -1795,16 +1177,16 @@ static void __init build_r4000_tlb_store_handler(void) build_make_write(&p, &r, K0, K1); build_r4000_tlbchange_handler_tail(&p, &l, &r, K0, K1); - l_nopage_tlbs(&l, p); - i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); - i_nop(&p); + uasm_l_nopage_tlbs(&l, p); + uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); + uasm_i_nop(&p); if ((p - handle_tlbs) > FASTPATH_SIZE) panic("TLB store handler fastpath space exceeded"); - resolve_relocs(relocs, labels); - pr_info("Synthesized TLB store handler fastpath (%u instructions).\n", - (unsigned int)(p - handle_tlbs)); + uasm_resolve_relocs(relocs, labels); + pr_debug("Wrote TLB store handler fastpath (%u instructions).\n", + (unsigned int)(p - handle_tlbs)); dump_handler(handle_tlbs, ARRAY_SIZE(handle_tlbs)); } @@ -1812,8 +1194,8 @@ static void __init build_r4000_tlb_store_handler(void) static void __init build_r4000_tlb_modify_handler(void) { u32 *p = handle_tlbm; - struct label *l = labels; - struct reloc *r = relocs; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; memset(handle_tlbm, 0, sizeof(handle_tlbm)); memset(labels, 0, sizeof(labels)); @@ -1827,16 +1209,16 @@ static void __init build_r4000_tlb_modify_handler(void) build_make_write(&p, &r, K0, K1); build_r4000_tlbchange_handler_tail(&p, &l, &r, K0, K1); - l_nopage_tlbm(&l, p); - i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); - i_nop(&p); + uasm_l_nopage_tlbm(&l, p); + uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff); + uasm_i_nop(&p); if ((p - handle_tlbm) > FASTPATH_SIZE) panic("TLB modify handler fastpath space exceeded"); - resolve_relocs(relocs, labels); - pr_info("Synthesized TLB modify handler fastpath (%u instructions).\n", - (unsigned int)(p - handle_tlbm)); + uasm_resolve_relocs(relocs, labels); + pr_debug("Wrote TLB modify handler fastpath (%u instructions).\n", + (unsigned int)(p - handle_tlbm)); dump_handler(handle_tlbm, ARRAY_SIZE(handle_tlbm)); } diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c new file mode 100644 index 00000000000..e3f74ed5f70 --- /dev/null +++ b/arch/mips/mm/uasm.c @@ -0,0 +1,576 @@ +/* + * 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. + * + * A small micro-assembler. It is intentionally kept simple, does only + * support a subset of instructions, and does not try to hide pipeline + * effects like branch delay slots. + * + * Copyright (C) 2004, 2005, 2006, 2008 Thiemo Seufer + * Copyright (C) 2005, 2007 Maciej W. Rozycki + * Copyright (C) 2006 Ralf Baechle (ralf@linux-mips.org) + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/init.h> + +#include <asm/inst.h> +#include <asm/elf.h> +#include <asm/bugs.h> + +#include "uasm.h" + +enum fields { + RS = 0x001, + RT = 0x002, + RD = 0x004, + RE = 0x008, + SIMM = 0x010, + UIMM = 0x020, + BIMM = 0x040, + JIMM = 0x080, + FUNC = 0x100, + SET = 0x200 +}; + +#define OP_MASK 0x3f +#define OP_SH 26 +#define RS_MASK 0x1f +#define RS_SH 21 +#define RT_MASK 0x1f +#define RT_SH 16 +#define RD_MASK 0x1f +#define RD_SH 11 +#define RE_MASK 0x1f +#define RE_SH 6 +#define IMM_MASK 0xffff +#define IMM_SH 0 +#define JIMM_MASK 0x3ffffff +#define JIMM_SH 0 +#define FUNC_MASK 0x3f +#define FUNC_SH 0 +#define SET_MASK 0x7 +#define SET_SH 0 + +enum opcode { + insn_invalid, + insn_addu, insn_addiu, insn_and, insn_andi, insn_beq, + insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl, + insn_bne, insn_daddu, insn_daddiu, insn_dmfc0, insn_dmtc0, + insn_dsll, insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, + insn_dsubu, insn_eret, insn_j, insn_jal, insn_jr, insn_ld, + insn_ll, insn_lld, insn_lui, insn_lw, insn_mfc0, insn_mtc0, + insn_ori, insn_rfe, insn_sc, insn_scd, insn_sd, insn_sll, + insn_sra, insn_srl, insn_subu, insn_sw, insn_tlbp, insn_tlbwi, + insn_tlbwr, insn_xor, insn_xori +}; + +struct insn { + enum opcode opcode; + u32 match; + enum fields fields; +}; + +/* This macro sets the non-variable bits of an instruction. */ +#define M(a, b, c, d, e, f) \ + ((a) << OP_SH \ + | (b) << RS_SH \ + | (c) << RT_SH \ + | (d) << RD_SH \ + | (e) << RE_SH \ + | (f) << FUNC_SH) + +static struct insn insn_table[] __initdata = { + { insn_addiu, M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_addu, M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD }, + { insn_and, M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD }, + { insn_andi, M(andi_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, + { insn_beq, M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, + { insn_beql, M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, + { insn_bgez, M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM }, + { insn_bgezl, M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM }, + { insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM }, + { insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM }, + { insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, + { insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD }, + { insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, + { insn_dmtc0, M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, + { insn_dsll, M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE }, + { insn_dsll32, M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE }, + { insn_dsra, M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE }, + { insn_dsrl, M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE }, + { insn_dsrl32, M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE }, + { insn_dsubu, M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD }, + { insn_eret, M(cop0_op, cop_op, 0, 0, 0, eret_op), 0 }, + { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, + { insn_jal, M(jal_op, 0, 0, 0, 0, 0), JIMM }, + { insn_jr, M(spec_op, 0, 0, 0, 0, jr_op), RS }, + { insn_ld, M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_ll, M(ll_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_lld, M(lld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_lui, M(lui_op, 0, 0, 0, 0, 0), RT | SIMM }, + { insn_lw, M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_mfc0, M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, + { insn_mtc0, M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, + { insn_ori, M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, + { insn_rfe, M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0 }, + { insn_sc, M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_scd, M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_sd, M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_sll, M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE }, + { insn_sra, M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE }, + { insn_srl, M(spec_op, 0, 0, 0, 0, srl_op), RT | RD | RE }, + { insn_subu, M(spec_op, 0, 0, 0, 0, subu_op), RS | RT | RD }, + { insn_sw, M(sw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_tlbp, M(cop0_op, cop_op, 0, 0, 0, tlbp_op), 0 }, + { insn_tlbwi, M(cop0_op, cop_op, 0, 0, 0, tlbwi_op), 0 }, + { insn_tlbwr, M(cop0_op, cop_op, 0, 0, 0, tlbwr_op), 0 }, + { insn_xor, M(spec_op, 0, 0, 0, 0, xor_op), RS | RT | RD }, + { insn_xori, M(xori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, + { insn_invalid, 0, 0 } +}; + +#undef M + +static inline __init u32 build_rs(u32 arg) +{ + if (arg & ~RS_MASK) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return (arg & RS_MASK) << RS_SH; +} + +static inline __init u32 build_rt(u32 arg) +{ + if (arg & ~RT_MASK) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return (arg & RT_MASK) << RT_SH; +} + +static inline __init u32 build_rd(u32 arg) +{ + if (arg & ~RD_MASK) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return (arg & RD_MASK) << RD_SH; +} + +static inline __init u32 build_re(u32 arg) +{ + if (arg & ~RE_MASK) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return (arg & RE_MASK) << RE_SH; +} + +static inline __init u32 build_simm(s32 arg) +{ + if (arg > 0x7fff || arg < -0x8000) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return arg & 0xffff; +} + +static inline __init u32 build_uimm(u32 arg) +{ + if (arg & ~IMM_MASK) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return arg & IMM_MASK; +} + +static inline __init u32 build_bimm(s32 arg) +{ + if (arg > 0x1ffff || arg < -0x20000) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + if (arg & 0x3) + printk(KERN_WARNING "Invalid micro-assembler branch target\n"); + + return ((arg < 0) ? (1 << 15) : 0) | ((arg >> 2) & 0x7fff); +} + +static inline __init u32 build_jimm(u32 arg) +{ + if (arg & ~((JIMM_MASK) << 2)) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return (arg >> 2) & JIMM_MASK; +} + +static inline __init u32 build_func(u32 arg) +{ + if (arg & ~FUNC_MASK) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return arg & FUNC_MASK; +} + +static inline __init u32 build_set(u32 arg) +{ + if (arg & ~SET_MASK) + printk(KERN_WARNING "Micro-assembler field overflow\n"); + + return arg & SET_MASK; +} + +/* + * The order of opcode arguments is implicitly left to right, + * starting with RS and ending with FUNC or IMM. + */ +static void __init build_insn(u32 **buf, enum opcode opc, ...) +{ + struct insn *ip = NULL; + unsigned int i; + va_list ap; + u32 op; + + for (i = 0; insn_table[i].opcode != insn_invalid; i++) + if (insn_table[i].opcode == opc) { + ip = &insn_table[i]; + break; + } + + if (!ip || (opc == insn_daddiu && r4k_daddiu_bug())) + panic("Unsupported Micro-assembler instruction %d", opc); + + op = ip->match; + va_start(ap, opc); + if (ip->fields & RS) + op |= build_rs(va_arg(ap, u32)); + if (ip->fields & RT) + op |= build_rt(va_arg(ap, u32)); + if (ip->fields & RD) + op |= build_rd(va_arg(ap, u32)); + if (ip->fields & RE) + op |= build_re(va_arg(ap, u32)); + if (ip->fields & SIMM) + op |= build_simm(va_arg(ap, s32)); + if (ip->fields & UIMM) + op |= build_uimm(va_arg(ap, u32)); + if (ip->fields & BIMM) + op |= build_bimm(va_arg(ap, s32)); + if (ip->fields & JIMM) + op |= build_jimm(va_arg(ap, u32)); + if (ip->fields & FUNC) + op |= build_func(va_arg(ap, u32)); + if (ip->fields & SET) + op |= build_set(va_arg(ap, u32)); + va_end(ap); + + **buf = op; + (*buf)++; +} + +#define I_u1u2u3(op) \ +Ip_u1u2u3(op) \ +{ \ + build_insn(buf, insn##op, a, b, c); \ +} + +#define I_u2u1u3(op) \ +Ip_u2u1u3(op) \ +{ \ + build_insn(buf, insn##op, b, a, c); \ +} + +#define I_u3u1u2(op) \ +Ip_u3u1u2(op) \ +{ \ + build_insn(buf, insn##op, b, c, a); \ +} + +#define I_u1u2s3(op) \ +Ip_u1u2s3(op) \ +{ \ + build_insn(buf, insn##op, a, b, c); \ +} + +#define I_u2s3u1(op) \ +Ip_u2s3u1(op) \ +{ \ + build_insn(buf, insn##op, c, a, b); \ +} + +#define I_u2u1s3(op) \ +Ip_u2u1s3(op) \ +{ \ + build_insn(buf, insn##op, b, a, c); \ +} + +#define I_u1u2(op) \ +Ip_u1u2(op) \ +{ \ + build_insn(buf, insn##op, a, b); \ +} + +#define I_u1s2(op) \ +Ip_u1s2(op) \ +{ \ + build_insn(buf, insn##op, a, b); \ +} + +#define I_u1(op) \ +Ip_u1(op) \ +{ \ + build_insn(buf, insn##op, a); \ +} + +#define I_0(op) \ +Ip_0(op) \ +{ \ + build_insn(buf, insn##op); \ +} + +I_u2u1s3(_addiu) +I_u3u1u2(_addu) +I_u2u1u3(_andi) +I_u3u1u2(_and) +I_u1u2s3(_beq) +I_u1u2s3(_beql) +I_u1s2(_bgez) +I_u1s2(_bgezl) +I_u1s2(_bltz) +I_u1s2(_bltzl) +I_u1u2s3(_bne) +I_u1u2u3(_dmfc0) +I_u1u2u3(_dmtc0) +I_u2u1s3(_daddiu) +I_u3u1u2(_daddu) +I_u2u1u3(_dsll) +I_u2u1u3(_dsll32) +I_u2u1u3(_dsra) +I_u2u1u3(_dsrl) +I_u2u1u3(_dsrl32) +I_u3u1u2(_dsubu) +I_0(_eret) +I_u1(_j) +I_u1(_jal) +I_u1(_jr) +I_u2s3u1(_ld) +I_u2s3u1(_ll) +I_u2s3u1(_lld) +I_u1s2(_lui) +I_u2s3u1(_lw) +I_u1u2u3(_mfc0) +I_u1u2u3(_mtc0) +I_u2u1u3(_ori) +I_0(_rfe) +I_u2s3u1(_sc) +I_u2s3u1(_scd) +I_u2s3u1(_sd) +I_u2u1u3(_sll) +I_u2u1u3(_sra) +I_u2u1u3(_srl) +I_u3u1u2(_subu) +I_u2s3u1(_sw) +I_0(_tlbp) +I_0(_tlbwi) +I_0(_tlbwr) +I_u3u1u2(_xor) +I_u2u1u3(_xori) + +/* Handle labels. */ +void __init uasm_build_label(struct uasm_label **lab, u32 *addr, int lid) +{ + (*lab)->addr = addr; + (*lab)->lab = lid; + (*lab)++; +} + +int __init uasm_in_compat_space_p(long addr) +{ + /* Is this address in 32bit compat space? */ +#ifdef CONFIG_64BIT + return (((addr) & 0xffffffff00000000L) == 0xffffffff00000000L); +#else + return 1; +#endif +} + +int __init uasm_rel_highest(long val) +{ +#ifdef CONFIG_64BIT + return ((((val + 0x800080008000L) >> 48) & 0xffff) ^ 0x8000) - 0x8000; +#else + return 0; +#endif +} + +int __init uasm_rel_higher(long val) +{ +#ifdef CONFIG_64BIT + return ((((val + 0x80008000L) >> 32) & 0xffff) ^ 0x8000) - 0x8000; +#else + return 0; +#endif +} + +int __init uasm_rel_hi(long val) +{ + return ((((val + 0x8000L) >> 16) & 0xffff) ^ 0x8000) - 0x8000; +} + +int __init uasm_rel_lo(long val) +{ + return ((val & 0xffff) ^ 0x8000) - 0x8000; +} + +void __init UASM_i_LA_mostly(u32 **buf, unsigned int rs, long addr) +{ + if (!uasm_in_compat_space_p(addr)) { + uasm_i_lui(buf, rs, uasm_rel_highest(addr)); + if (uasm_rel_higher(addr)) + uasm_i_daddiu(buf, rs, rs, uasm_rel_higher(addr)); + if (uasm_rel_hi(addr)) { + uasm_i_dsll(buf, rs, rs, 16); + uasm_i_daddiu(buf, rs, rs, uasm_rel_hi(addr)); + uasm_i_dsll(buf, rs, rs, 16); + } else + uasm_i_dsll32(buf, rs, rs, 0); + } else + uasm_i_lui(buf, rs, uasm_rel_hi(addr)); +} + +void __init UASM_i_LA(u32 **buf, unsigned int rs, long addr) +{ + UASM_i_LA_mostly(buf, rs, addr); + if (uasm_rel_lo(addr)) { + if (!uasm_in_compat_space_p(addr)) + uasm_i_daddiu(buf, rs, rs, uasm_rel_lo(addr)); + else + uasm_i_addiu(buf, rs, rs, uasm_rel_lo(addr)); + } +} + +/* Handle relocations. */ +void __init +uasm_r_mips_pc16(struct uasm_reloc **rel, u32 *addr, int lid) +{ + (*rel)->addr = addr; + (*rel)->type = R_MIPS_PC16; + (*rel)->lab = lid; + (*rel)++; +} + +static inline void __init +__resolve_relocs(struct uasm_reloc *rel, struct uasm_label *lab) +{ + long laddr = (long)lab->addr; + long raddr = (long)rel->addr; + + switch (rel->type) { + case R_MIPS_PC16: + *rel->addr |= build_bimm(laddr - (raddr + 4)); + break; + + default: + panic("Unsupported Micro-assembler relocation %d", + rel->type); + } +} + +void __init +uasm_resolve_relocs(struct uasm_reloc *rel, struct uasm_label *lab) +{ + struct uasm_label *l; + + for (; rel->lab != UASM_LABEL_INVALID; rel++) + for (l = lab; l->lab != UASM_LABEL_INVALID; l++) + if (rel->lab == l->lab) + __resolve_relocs(rel, l); +} + +void __init +uasm_move_relocs(struct uasm_reloc *rel, u32 *first, u32 *end, long off) +{ + for (; rel->lab != UASM_LABEL_INVALID; rel++) + if (rel->addr >= first && rel->addr < end) + rel->addr += off; +} + +void __init +uasm_move_labels(struct uasm_label *lab, u32 *first, u32 *end, long off) +{ + for (; lab->lab != UASM_LABEL_INVALID; lab++) + if (lab->addr >= first && lab->addr < end) + lab->addr += off; +} + +void __init +uasm_copy_handler(struct uasm_reloc *rel, struct uasm_label *lab, u32 *first, + u32 *end, u32 *target) +{ + long off = (long)(target - first); + + memcpy(target, first, (end - first) * sizeof(u32)); + + uasm_move_relocs(rel, first, end, off); + uasm_move_labels(lab, first, end, off); +} + +int __init uasm_insn_has_bdelay(struct uasm_reloc *rel, u32 *addr) +{ + for (; rel->lab != UASM_LABEL_INVALID; rel++) { + if (rel->addr == addr + && (rel->type == R_MIPS_PC16 + || rel->type == R_MIPS_26)) + return 1; + } + + return 0; +} + +/* Convenience functions for labeled branches. */ +void __init +uasm_il_bltz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + uasm_i_bltz(p, reg, 0); +} + +void __init +uasm_il_b(u32 **p, struct uasm_reloc **r, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + uasm_i_b(p, 0); +} + +void __init +uasm_il_beqz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + uasm_i_beqz(p, reg, 0); +} + +void __init +uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + uasm_i_beqzl(p, reg, 0); +} + +void __init +uasm_il_bnez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + uasm_i_bnez(p, reg, 0); +} + +void __init +uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + uasm_i_bgezl(p, reg, 0); +} + +void __init +uasm_il_bgez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + uasm_i_bgez(p, reg, 0); +} diff --git a/arch/mips/mm/uasm.h b/arch/mips/mm/uasm.h new file mode 100644 index 00000000000..a10fc1135c7 --- /dev/null +++ b/arch/mips/mm/uasm.h @@ -0,0 +1,192 @@ +/* + * 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) 2004, 2005, 2006, 2008 Thiemo Seufer + * Copyright (C) 2005 Maciej W. Rozycki + * Copyright (C) 2006 Ralf Baechle (ralf@linux-mips.org) + */ + +#include <linux/types.h> + +#define Ip_u1u2u3(op) \ +void __init \ +uasm_i##op(u32 **buf, unsigned int a, unsigned int b, unsigned int c) + +#define Ip_u2u1u3(op) \ +void __init \ +uasm_i##op(u32 **buf, unsigned int a, unsigned int b, unsigned int c) + +#define Ip_u3u1u2(op) \ +void __init \ +uasm_i##op(u32 **buf, unsigned int a, unsigned int b, unsigned int c) + +#define Ip_u1u2s3(op) \ +void __init \ +uasm_i##op(u32 **buf, unsigned int a, unsigned int b, signed int c) + +#define Ip_u2s3u1(op) \ +void __init \ +uasm_i##op(u32 **buf, unsigned int a, signed int b, unsigned int c) + +#define Ip_u2u1s3(op) \ +void __init \ +uasm_i##op(u32 **buf, unsigned int a, unsigned int b, signed int c) + +#define Ip_u1u2(op) \ +void __init uasm_i##op(u32 **buf, unsigned int a, unsigned int b) + +#define Ip_u1s2(op) \ +void __init uasm_i##op(u32 **buf, unsigned int a, signed int b) + +#define Ip_u1(op) void __init uasm_i##op(u32 **buf, unsigned int a) + +#define Ip_0(op) void __init uasm_i##op(u32 **buf) + +Ip_u2u1s3(_addiu); +Ip_u3u1u2(_addu); +Ip_u2u1u3(_andi); +Ip_u3u1u2(_and); +Ip_u1u2s3(_beq); +Ip_u1u2s3(_beql); +Ip_u1s2(_bgez); +Ip_u1s2(_bgezl); +Ip_u1s2(_bltz); +Ip_u1s2(_bltzl); +Ip_u1u2s3(_bne); +Ip_u1u2u3(_dmfc0); +Ip_u1u2u3(_dmtc0); +Ip_u2u1s3(_daddiu); +Ip_u3u1u2(_daddu); +Ip_u2u1u3(_dsll); +Ip_u2u1u3(_dsll32); +Ip_u2u1u3(_dsra); +Ip_u2u1u3(_dsrl); +Ip_u2u1u3(_dsrl32); +Ip_u3u1u2(_dsubu); +Ip_0(_eret); +Ip_u1(_j); +Ip_u1(_jal); +Ip_u1(_jr); +Ip_u2s3u1(_ld); +Ip_u2s3u1(_ll); +Ip_u2s3u1(_lld); +Ip_u1s2(_lui); +Ip_u2s3u1(_lw); +Ip_u1u2u3(_mfc0); +Ip_u1u2u3(_mtc0); +Ip_u2u1u3(_ori); +Ip_0(_rfe); +Ip_u2s3u1(_sc); +Ip_u2s3u1(_scd); +Ip_u2s3u1(_sd); +Ip_u2u1u3(_sll); +Ip_u2u1u3(_sra); +Ip_u2u1u3(_srl); +Ip_u3u1u2(_subu); +Ip_u2s3u1(_sw); +Ip_0(_tlbp); +Ip_0(_tlbwi); +Ip_0(_tlbwr); +Ip_u3u1u2(_xor); +Ip_u2u1u3(_xori); + +/* Handle labels. */ +struct uasm_label { + u32 *addr; + int lab; +}; + +void __init uasm_build_label(struct uasm_label **lab, u32 *addr, int lid); +#ifdef CONFIG_64BIT +int __init uasm_in_compat_space_p(long addr); +int __init uasm_rel_highest(long val); +int __init uasm_rel_higher(long val); +#endif +int __init uasm_rel_hi(long val); +int __init uasm_rel_lo(long val); +void __init UASM_i_LA_mostly(u32 **buf, unsigned int rs, long addr); +void __init UASM_i_LA(u32 **buf, unsigned int rs, long addr); + +#define UASM_L_LA(lb) \ +static inline void __init uasm_l##lb(struct uasm_label **lab, u32 *addr) \ +{ \ + uasm_build_label(lab, addr, label##lb); \ +} + +/* convenience macros for instructions */ +#ifdef CONFIG_64BIT +# define UASM_i_LW(buf, rs, rt, off) uasm_i_ld(buf, rs, rt, off) +# define UASM_i_SW(buf, rs, rt, off) uasm_i_sd(buf, rs, rt, off) +# define UASM_i_SLL(buf, rs, rt, sh) uasm_i_dsll(buf, rs, rt, sh) +# define UASM_i_SRA(buf, rs, rt, sh) uasm_i_dsra(buf, rs, rt, sh) +# define UASM_i_SRL(buf, rs, rt, sh) uasm_i_dsrl(buf, rs, rt, sh) +# define UASM_i_MFC0(buf, rt, rd...) uasm_i_dmfc0(buf, rt, rd) +# define UASM_i_MTC0(buf, rt, rd...) uasm_i_dmtc0(buf, rt, rd) +# define UASM_i_ADDIU(buf, rs, rt, val) uasm_i_daddiu(buf, rs, rt, val) +# define UASM_i_ADDU(buf, rs, rt, rd) uasm_i_daddu(buf, rs, rt, rd) +# define UASM_i_SUBU(buf, rs, rt, rd) uasm_i_dsubu(buf, rs, rt, rd) +# define UASM_i_LL(buf, rs, rt, off) uasm_i_lld(buf, rs, rt, off) +# define UASM_i_SC(buf, rs, rt, off) uasm_i_scd(buf, rs, rt, off) +#else +# define UASM_i_LW(buf, rs, rt, off) uasm_i_lw(buf, rs, rt, off) +# define UASM_i_SW(buf, rs, rt, off) uasm_i_sw(buf, rs, rt, off) +# define UASM_i_SLL(buf, rs, rt, sh) uasm_i_sll(buf, rs, rt, sh) +# define UASM_i_SRA(buf, rs, rt, sh) uasm_i_sra(buf, rs, rt, sh) +# define UASM_i_SRL(buf, rs, rt, sh) uasm_i_srl(buf, rs, rt, sh) +# define UASM_i_MFC0(buf, rt, rd...) uasm_i_mfc0(buf, rt, rd) +# define UASM_i_MTC0(buf, rt, rd...) uasm_i_mtc0(buf, rt, rd) +# define UASM_i_ADDIU(buf, rs, rt, val) uasm_i_addiu(buf, rs, rt, val) +# define UASM_i_ADDU(buf, rs, rt, rd) uasm_i_addu(buf, rs, rt, rd) +# define UASM_i_SUBU(buf, rs, rt, rd) uasm_i_subu(buf, rs, rt, rd) +# define UASM_i_LL(buf, rs, rt, off) uasm_i_ll(buf, rs, rt, off) +# define UASM_i_SC(buf, rs, rt, off) uasm_i_sc(buf, rs, rt, off) +#endif + +#define uasm_i_b(buf, off) uasm_i_beq(buf, 0, 0, off) +#define uasm_i_beqz(buf, rs, off) uasm_i_beq(buf, rs, 0, off) +#define uasm_i_beqzl(buf, rs, off) uasm_i_beql(buf, rs, 0, off) +#define uasm_i_bnez(buf, rs, off) uasm_i_bne(buf, rs, 0, off) +#define uasm_i_bnezl(buf, rs, off) uasm_i_bnel(buf, rs, 0, off) +#define uasm_i_move(buf, a, b) UASM_i_ADDU(buf, a, 0, b) +#define uasm_i_nop(buf) uasm_i_sll(buf, 0, 0, 0) +#define uasm_i_ssnop(buf) uasm_i_sll(buf, 0, 0, 1) +#define uasm_i_ehb(buf) uasm_i_sll(buf, 0, 0, 3) + +/* Handle relocations. */ +struct uasm_reloc { + u32 *addr; + unsigned int type; + int lab; +}; + +/* This is zero so we can use zeroed label arrays. */ +#define UASM_LABEL_INVALID 0 + +void __init uasm_r_mips_pc16(struct uasm_reloc **rel, u32 *addr, int lid); +void __init +uasm_resolve_relocs(struct uasm_reloc *rel, struct uasm_label *lab); +void __init +uasm_move_relocs(struct uasm_reloc *rel, u32 *first, u32 *end, long off); +void __init +uasm_move_labels(struct uasm_label *lab, u32 *first, u32 *end, long off); +void __init +uasm_copy_handler(struct uasm_reloc *rel, struct uasm_label *lab, u32 *first, + u32 *end, u32 *target); +int __init uasm_insn_has_bdelay(struct uasm_reloc *rel, u32 *addr); + +/* Convenience functions for labeled branches. */ +void __init +uasm_il_bltz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); +void __init uasm_il_b(u32 **p, struct uasm_reloc **r, int lid); +void __init +uasm_il_beqz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); +void __init +uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); +void __init +uasm_il_bnez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); +void __init +uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); +void __init +uasm_il_bgez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 65b449134cf..93e66678e15 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -44,6 +44,9 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y +config HAVE_LATENCYTOP_SUPPORT + def_bool y + config SEMAPHORE_SLEEPERS def_bool y diff --git a/arch/x86/boot/compressed/vmlinux_64.lds b/arch/x86/boot/compressed/vmlinux_64.lds index f6e5b445f45..7e5c7209f6c 100644 --- a/arch/x86/boot/compressed/vmlinux_64.lds +++ b/arch/x86/boot/compressed/vmlinux_64.lds @@ -3,7 +3,7 @@ OUTPUT_ARCH(i386:x86-64) ENTRY(startup_64) SECTIONS { - /* Be careful parts of head_64.S assume startup_64 is at + /* Be careful parts of head_64.S assume startup_32 is at * address 0. */ . = 0; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 0ca27c7b0e8..d2a58431a07 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -496,7 +496,8 @@ EXPORT_SYMBOL(acpi_register_gsi); * ACPI based hotplug support for CPU */ #ifdef CONFIG_ACPI_HOTPLUG_CPU -int acpi_map_lsapic(acpi_handle handle, int *pcpu) + +static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; @@ -551,6 +552,11 @@ int acpi_map_lsapic(acpi_handle handle, int *pcpu) return 0; } +/* wrapper to silence section mismatch warning */ +int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu) +{ + return _acpi_map_lsapic(handle, pcpu); +} EXPORT_SYMBOL(acpi_map_lsapic); int acpi_unmap_lsapic(int cpu) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d608c9ebbfe..b7b2142b58e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -258,10 +258,10 @@ static int __cpuinit have_cpuid_p(void) void __init cpu_detect(struct cpuinfo_x86 *c) { /* Get vendor name */ - cpuid(0x00000000, &c->cpuid_level, - (int *)&c->x86_vendor_id[0], - (int *)&c->x86_vendor_id[8], - (int *)&c->x86_vendor_id[4]); + cpuid(0x00000000, (unsigned int *)&c->cpuid_level, + (unsigned int *)&c->x86_vendor_id[0], + (unsigned int *)&c->x86_vendor_id[8], + (unsigned int *)&c->x86_vendor_id[4]); c->x86 = 4; if (c->cpuid_level >= 0x00000001) { @@ -283,7 +283,7 @@ void __init cpu_detect(struct cpuinfo_x86 *c) static void __cpuinit early_get_cap(struct cpuinfo_x86 *c) { u32 tfms, xlvl; - int ebx; + unsigned int ebx; memset(&c->x86_capability, 0, sizeof c->x86_capability); if (have_cpuid_p()) { @@ -343,14 +343,14 @@ static void __init early_cpu_detect(void) static void __cpuinit generic_identify(struct cpuinfo_x86 * c) { u32 tfms, xlvl; - int ebx; + unsigned int ebx; if (have_cpuid_p()) { /* Get vendor name */ - cpuid(0x00000000, &c->cpuid_level, - (int *)&c->x86_vendor_id[0], - (int *)&c->x86_vendor_id[8], - (int *)&c->x86_vendor_id[4]); + cpuid(0x00000000, (unsigned int *)&c->cpuid_level, + (unsigned int *)&c->x86_vendor_id[0], + (unsigned int *)&c->x86_vendor_id[8], + (unsigned int *)&c->x86_vendor_id[4]); get_cpu_vendor(c, 0); /* Initialize the standard set of capabilities */ diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index dec66e45281..a63432d800f 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -170,7 +170,7 @@ static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb, return err ? NOTIFY_BAD : NOTIFY_OK; } -static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier = +static struct notifier_block __refdata cpuid_class_cpu_notifier = { .notifier_call = cpuid_class_cpu_callback, }; diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c index c617174e896..9f65b4cc323 100644 --- a/arch/x86/kernel/e820_64.c +++ b/arch/x86/kernel/e820_64.c @@ -54,30 +54,33 @@ static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT; struct early_res { unsigned long start, end; + char name[16]; }; static struct early_res early_res[MAX_EARLY_RES] __initdata = { - { 0, PAGE_SIZE }, /* BIOS data page */ + { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */ #ifdef CONFIG_SMP - { SMP_TRAMPOLINE_BASE, SMP_TRAMPOLINE_BASE + 2*PAGE_SIZE }, + { SMP_TRAMPOLINE_BASE, SMP_TRAMPOLINE_BASE + 2*PAGE_SIZE, "SMP_TRAMPOLINE" }, #endif {} }; -void __init reserve_early(unsigned long start, unsigned long end) +void __init reserve_early(unsigned long start, unsigned long end, char *name) { int i; struct early_res *r; for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { r = &early_res[i]; if (end > r->start && start < r->end) - panic("Overlapping early reservations %lx-%lx to %lx-%lx\n", - start, end, r->start, r->end); + panic("Overlapping early reservations %lx-%lx %s to %lx-%lx %s\n", + start, end - 1, name?name:"", r->start, r->end - 1, r->name); } if (i >= MAX_EARLY_RES) panic("Too many early reservations"); r = &early_res[i]; r->start = start; r->end = end; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); } void __init early_res_to_bootmem(void) @@ -85,6 +88,8 @@ void __init early_res_to_bootmem(void) int i; for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { struct early_res *r = &early_res[i]; + printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i, + r->start, r->end - 1, r->name); reserve_bootmem_generic(r->start, r->end - r->start); } } @@ -166,12 +171,13 @@ int __init e820_all_mapped(unsigned long start, unsigned long end, } /* - * Find a free area in a specific range. + * Find a free area with specified alignment in a specific range. */ unsigned long __init find_e820_area(unsigned long start, unsigned long end, - unsigned size) + unsigned size, unsigned long align) { int i; + unsigned long mask = ~(align - 1); for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; @@ -185,7 +191,8 @@ unsigned long __init find_e820_area(unsigned long start, unsigned long end, continue; while (bad_addr(&addr, size) && addr+size <= ei->addr+ei->size) ; - last = PAGE_ALIGN(addr) + size; + addr = (addr + align - 1) & mask; + last = addr + size; if (last > ei->addr + ei->size) continue; if (last > end) diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index b7d6c23f287..cff84cd9987 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -193,7 +193,7 @@ static struct console simnow_console = { }; /* Direct interface for emergencies */ -struct console *early_console = &early_vga_console; +static struct console *early_console = &early_vga_console; static int early_console_initialized = 0; void early_printk(const char *fmt, ...) diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index 4b73992c1e1..674f2379480 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -44,7 +44,7 @@ static void __init early_mapping_set_exec(unsigned long start, int executable) { pte_t *kpte; - int level; + unsigned int level; while (start < end) { kpte = lookup_address((unsigned long)__va(start), &level); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index a317336cdea..24dbf56928d 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -75,7 +75,7 @@ static __init void reserve_ebda(void) if (ebda_size > 64*1024) ebda_size = 64*1024; - reserve_early(ebda_addr, ebda_addr + ebda_size); + reserve_early(ebda_addr, ebda_addr + ebda_size, "EBDA"); } void __init x86_64_start_kernel(char * real_mode_data) @@ -105,14 +105,14 @@ void __init x86_64_start_kernel(char * real_mode_data) pda_init(0); copy_bootdata(__va(real_mode_data)); - reserve_early(__pa_symbol(&_text), __pa_symbol(&_end)); + reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS"); /* Reserve INITRD */ if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; unsigned long ramdisk_end = ramdisk_image + ramdisk_size; - reserve_early(ramdisk_image, ramdisk_end); + reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } reserve_ebda(); diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c index 6ff447f9fda..f2702d01b8a 100644 --- a/arch/x86/kernel/microcode.c +++ b/arch/x86/kernel/microcode.c @@ -797,7 +797,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) return NOTIFY_OK; } -static struct notifier_block __cpuinitdata mc_cpu_notifier = { +static struct notifier_block __refdata mc_cpu_notifier = { .notifier_call = mc_cpu_callback, }; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 21f6e3c0be1..bd82850e651 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -168,7 +168,7 @@ static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb, return err ? NOTIFY_BAD : NOTIFY_OK; } -static struct notifier_block __cpuinitdata msr_class_cpu_notifier = { +static struct notifier_block __refdata msr_class_cpu_notifier = { .notifier_call = msr_class_cpu_callback, }; diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 21f34db2c03..1fe7f043ebd 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1006,7 +1006,7 @@ static void __init calgary_set_split_completion_timeout(void __iomem *bbar, readq(target); /* flush */ } -static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev) +static void __init calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev) { unsigned char busnum = dev->bus->number; void __iomem *bbar = tbl->bbar; @@ -1022,7 +1022,7 @@ static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev) writel(cpu_to_be32(val), target); } -static void calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev) +static void __init calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev) { unsigned char busnum = dev->bus->number; diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index 77fb87bf6e5..18df70c534b 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -182,7 +182,8 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn) unsigned long bootmap_size, bootmap; bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT; - bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size); + bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size, + PAGE_SIZE); if (bootmap == -1L) panic("Cannot find bootmem map of size %ld\n", bootmap_size); bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn); diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c index cc64b8085c2..d53bd6fcb42 100644 --- a/arch/x86/kernel/smpboot_64.c +++ b/arch/x86/kernel/smpboot_64.c @@ -1019,7 +1019,7 @@ static void remove_siblinginfo(int cpu) cpu_clear(cpu, cpu_sibling_setup_map); } -void remove_cpu_from_maps(void) +static void __ref remove_cpu_from_maps(void) { int cpu = smp_processor_id(); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 78cbb655aa7..e6757aaa202 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -57,11 +57,10 @@ void arch_unregister_cpu(int num) } EXPORT_SYMBOL(arch_unregister_cpu); #else -int arch_register_cpu(int num) +static int __init arch_register_cpu(int num) { return register_cpu(&per_cpu(cpu_devices, num).cpu, num); } -EXPORT_SYMBOL(arch_register_cpu); #endif /*CONFIG_HOTPLUG_CPU*/ static int __init topology_init(void) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e28cc5277b1..e4440d0abf8 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -382,7 +382,7 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, #ifdef CONFIG_X86_PAE if (error_code & PF_INSTR) { - int level; + unsigned int level; pte_t *pte = lookup_address(address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index cc50a13ce8d..eabcaed76c2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -354,17 +354,10 @@ static void __init find_early_table_space(unsigned long end) * need roughly 0.5KB per GB. */ start = 0x8000; - table_start = find_e820_area(start, end, tables); + table_start = find_e820_area(start, end, tables, PAGE_SIZE); if (table_start == -1UL) panic("Cannot find space for the kernel page tables"); - /* - * When you have a lot of RAM like 256GB, early_table will not fit - * into 0x8000 range, find_e820_area() will find area after kernel - * bss but the table_start is not page aligned, so need to round it - * up to avoid overlap with bss: - */ - table_start = round_up(table_start, PAGE_SIZE); table_start >>= PAGE_SHIFT; table_end = table_start; @@ -420,7 +413,9 @@ void __init_refok init_memory_mapping(unsigned long start, unsigned long end) mmu_cr4_features = read_cr4(); __flush_tlb_all(); - reserve_early(table_start << PAGE_SHIFT, table_end << PAGE_SHIFT); + if (!after_bootmem) + reserve_early(table_start << PAGE_SHIFT, + table_end << PAGE_SHIFT, "PGTABLE"); } #ifndef CONFIG_NUMA diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index a177d76e1c5..c004d94608f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -75,7 +75,8 @@ static int ioremap_change_attr(unsigned long paddr, unsigned long size, { unsigned long vaddr = (unsigned long)__va(paddr); unsigned long nrpages = size >> PAGE_SHIFT; - int err, level; + unsigned int level; + int err; /* No change for pages after the last mapping */ if ((paddr + size - 1) >= (max_pfn_mapped << PAGE_SHIFT)) diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index dc3b1f7e145..a920d09b919 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -84,26 +84,24 @@ static int __init populate_memnodemap(const struct bootnode *nodes, static int __init allocate_cachealigned_memnodemap(void) { - unsigned long pad, pad_addr; + unsigned long addr; memnodemap = memnode.embedded_map; if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map)) return 0; - pad = L1_CACHE_BYTES - 1; - pad_addr = 0x8000; - nodemap_size = pad + sizeof(s16) * memnodemapsize; - nodemap_addr = find_e820_area(pad_addr, end_pfn<<PAGE_SHIFT, - nodemap_size); + addr = 0x8000; + nodemap_size = round_up(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES); + nodemap_addr = find_e820_area(addr, end_pfn<<PAGE_SHIFT, + nodemap_size, L1_CACHE_BYTES); if (nodemap_addr == -1UL) { printk(KERN_ERR "NUMA: Unable to allocate Memory to Node hash map\n"); nodemap_addr = nodemap_size = 0; return -1; } - pad_addr = (nodemap_addr + pad) & ~pad; - memnodemap = phys_to_virt(pad_addr); - reserve_early(nodemap_addr, nodemap_addr + nodemap_size); + memnodemap = phys_to_virt(nodemap_addr); + reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP"); printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n", nodemap_addr, nodemap_addr + nodemap_size); @@ -164,15 +162,16 @@ int early_pfn_to_nid(unsigned long pfn) } static void * __init early_node_mem(int nodeid, unsigned long start, - unsigned long end, unsigned long size) + unsigned long end, unsigned long size, + unsigned long align) { - unsigned long mem = find_e820_area(start, end, size); + unsigned long mem = find_e820_area(start, end, size, align); void *ptr; if (mem != -1L) return __va(mem); - ptr = __alloc_bootmem_nopanic(size, - SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)); + + ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS)); if (ptr == NULL) { printk(KERN_ERR "Cannot find %lu bytes in node %d\n", size, nodeid); @@ -198,7 +197,8 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, start_pfn = start >> PAGE_SHIFT; end_pfn = end >> PAGE_SHIFT; - node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size); + node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size, + SMP_CACHE_BYTES); if (node_data[nodeid] == NULL) return; nodedata_phys = __pa(node_data[nodeid]); @@ -211,8 +211,12 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, /* Find a place for the bootmem map */ bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE); + /* + * SMP_CAHCE_BYTES could be enough, but init_bootmem_node like + * to use that to align to PAGE_SIZE + */ bootmap = early_node_mem(nodeid, bootmap_start, end, - bootmap_pages<<PAGE_SHIFT); + bootmap_pages<<PAGE_SHIFT, PAGE_SIZE); if (bootmap == NULL) { if (nodedata_phys < start || nodedata_phys >= end) free_bootmem((unsigned long)node_data[nodeid], diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 06353d43f72..7573e786d2f 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -42,7 +42,7 @@ static __init int print_split(struct split_state *s) s->max_exec = 0; for (i = 0; i < max_pfn_mapped; ) { unsigned long addr = (unsigned long)__va(i << PAGE_SHIFT); - int level; + unsigned int level; pte_t *pte; pte = lookup_address(addr, &level); @@ -106,7 +106,7 @@ static __init int exercise_pageattr(void) unsigned long *bm; pte_t *pte, pte0; int failed = 0; - int level; + unsigned int level; int i, k; int err; diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index ae19c9b30d1..ba8f7f4dfa1 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -69,7 +69,7 @@ config ATA_PIIX config SATA_MV tristate "Marvell SATA support (HIGHLY EXPERIMENTAL)" - depends on PCI && EXPERIMENTAL + depends on EXPERIMENTAL help This option enables support for the Marvell Serial ATA family. Currently supports 88SX[56]0[48][01] chips. diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 6f089b899a1..27c8d56111c 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -475,6 +475,8 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x294e), board_ahci }, /* ICH9M */ { PCI_VDEVICE(INTEL, 0x502a), board_ahci }, /* Tolapai */ { PCI_VDEVICE(INTEL, 0x502b), board_ahci }, /* Tolapai */ + { PCI_VDEVICE(INTEL, 0x3a05), board_ahci }, /* ICH10 */ + { PCI_VDEVICE(INTEL, 0x3a25), board_ahci }, /* ICH10 */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index a65c8ae5c46..47892e6f5de 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -267,6 +267,14 @@ static const struct pci_device_id piix_pci_tbl[] = { { 0x8086, 0x292e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_ahci }, /* SATA Controller IDE (Tolapai) */ { 0x8086, 0x5028, PCI_ANY_ID, PCI_ANY_ID, 0, 0, tolapai_sata_ahci }, + /* SATA Controller IDE (ICH10) */ + { 0x8086, 0x3a00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_ahci }, + /* SATA Controller IDE (ICH10) */ + { 0x8086, 0x3a06, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, + /* SATA Controller IDE (ICH10) */ + { 0x8086, 0x3a20, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_ahci }, + /* SATA Controller IDE (ICH10) */ + { 0x8086, 0x3a26, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, { } /* terminate list */ }; @@ -1068,7 +1076,7 @@ static void piix_sidpr_write(struct ata_device *dev, unsigned int reg, u32 val) iowrite32(val, hpriv->sidpr + PIIX_SIDPR_DATA); } -u32 piix_merge_scr(u32 val0, u32 val1, const int * const *merge_tbl) +static u32 piix_merge_scr(u32 val0, u32 val1, const int * const *merge_tbl) { u32 val = 0; int i, mi; diff --git a/drivers/ata/pata_bf54x.c b/drivers/ata/pata_bf54x.c index a32e3c44a60..7f87f105c2f 100644 --- a/drivers/ata/pata_bf54x.c +++ b/drivers/ata/pata_bf54x.c @@ -299,7 +299,7 @@ static void bfin_set_piomode(struct ata_port *ap, struct ata_device *adev) */ n6 = num_clocks_min(t6min, fsclk); if (mode >= 0 && mode <= 4 && n6 >= 1) { - pr_debug("set piomode: mode=%d, fsclk=%ud\n", mode, fsclk); + dev_dbg(adev->link->ap->dev, "set piomode: mode=%d, fsclk=%ud\n", mode, fsclk); /* calculate the timing values for register transfers. */ while (mode > 0 && pio_fsclk[mode] > fsclk) mode--; @@ -376,7 +376,7 @@ static void bfin_set_dmamode(struct ata_port *ap, struct ata_device *adev) mode = adev->dma_mode - XFER_UDMA_0; if (mode >= 0 && mode <= 5) { - pr_debug("set udmamode: mode=%d\n", mode); + dev_dbg(adev->link->ap->dev, "set udmamode: mode=%d\n", mode); /* the most restrictive timing value is t6 and tc, * the DIOW - data hold. If one SCLK pulse is longer * than this minimum value then register @@ -433,7 +433,7 @@ static void bfin_set_dmamode(struct ata_port *ap, struct ata_device *adev) mode = adev->dma_mode - XFER_MW_DMA_0; if (mode >= 0 && mode <= 2) { - pr_debug("set mdmamode: mode=%d\n", mode); + dev_dbg(adev->link->ap->dev, "set mdmamode: mode=%d\n", mode); /* the most restrictive timing value is tf, the DMACK to * read data released. If one SCLK pulse is longer than * this maximum value then the MDMA mode @@ -697,7 +697,7 @@ static void bfin_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) write_atapi_register(base, ATA_REG_LBAL, tf->hob_lbal); write_atapi_register(base, ATA_REG_LBAM, tf->hob_lbam); write_atapi_register(base, ATA_REG_LBAH, tf->hob_lbah); - pr_debug("hob: feat 0x%X nsect 0x%X, lba 0x%X " + dev_dbg(ap->dev, "hob: feat 0x%X nsect 0x%X, lba 0x%X " "0x%X 0x%X\n", tf->hob_feature, tf->hob_nsect, @@ -711,7 +711,7 @@ static void bfin_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) write_atapi_register(base, ATA_REG_LBAL, tf->lbal); write_atapi_register(base, ATA_REG_LBAM, tf->lbam); write_atapi_register(base, ATA_REG_LBAH, tf->lbah); - pr_debug("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n", + dev_dbg(ap->dev, "feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n", tf->feature, tf->nsect, tf->lbal, @@ -721,7 +721,7 @@ static void bfin_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) if (tf->flags & ATA_TFLAG_DEVICE) { write_atapi_register(base, ATA_REG_DEVICE, tf->device); - pr_debug("device 0x%X\n", tf->device); + dev_dbg(ap->dev, "device 0x%X\n", tf->device); } ata_wait_idle(ap); @@ -782,7 +782,7 @@ static void bfin_exec_command(struct ata_port *ap, const struct ata_taskfile *tf) { void __iomem *base = (void __iomem *)ap->ioaddr.ctl_addr; - pr_debug("ata%u: cmd 0x%X\n", ap->print_id, tf->command); + dev_dbg(ap->dev, "ata%u: cmd 0x%X\n", ap->print_id, tf->command); write_atapi_register(base, ATA_REG_CMD, tf->command); ata_pause(ap); @@ -834,7 +834,7 @@ static void bfin_bmdma_setup(struct ata_queued_cmd *qc) struct scatterlist *sg; unsigned int si; - pr_debug("in atapi dma setup\n"); + dev_dbg(qc->ap->dev, "in atapi dma setup\n"); /* Program the ATA_CTRL register with dir */ if (qc->tf.flags & ATA_TFLAG_WRITE) { /* fill the ATAPI DMA controller */ @@ -870,7 +870,7 @@ static void bfin_bmdma_start(struct ata_queued_cmd *qc) struct scatterlist *sg; unsigned int si; - pr_debug("in atapi dma start\n"); + dev_dbg(qc->ap->dev, "in atapi dma start\n"); if (!(ap->udma_mask || ap->mwdma_mask)) return; @@ -888,7 +888,7 @@ static void bfin_bmdma_start(struct ata_queued_cmd *qc) sg_dma_address(sg) + sg_dma_len(sg)); } enable_dma(CH_ATAPI_TX); - pr_debug("enable udma write\n"); + dev_dbg(qc->ap->dev, "enable udma write\n"); /* Send ATA DMA write command */ bfin_exec_command(ap, &qc->tf); @@ -898,7 +898,7 @@ static void bfin_bmdma_start(struct ata_queued_cmd *qc) | XFER_DIR)); } else { enable_dma(CH_ATAPI_RX); - pr_debug("enable udma read\n"); + dev_dbg(qc->ap->dev, "enable udma read\n"); /* Send ATA DMA read command */ bfin_exec_command(ap, &qc->tf); @@ -936,7 +936,7 @@ static void bfin_bmdma_stop(struct ata_queued_cmd *qc) struct scatterlist *sg; unsigned int si; - pr_debug("in atapi dma stop\n"); + dev_dbg(qc->ap->dev, "in atapi dma stop\n"); if (!(ap->udma_mask || ap->mwdma_mask)) return; @@ -1147,15 +1147,15 @@ static unsigned char bfin_bmdma_status(struct ata_port *ap) void __iomem *base = (void __iomem *)ap->ioaddr.ctl_addr; unsigned short int_status = ATAPI_GET_INT_STATUS(base); - if (ATAPI_GET_STATUS(base) & (MULTI_XFER_ON|ULTRA_XFER_ON)) { + if (ATAPI_GET_STATUS(base) & (MULTI_XFER_ON|ULTRA_XFER_ON)) host_stat |= ATA_DMA_ACTIVE; - } - if (int_status & (MULTI_DONE_INT|UDMAIN_DONE_INT|UDMAOUT_DONE_INT)) { + if (int_status & (MULTI_DONE_INT|UDMAIN_DONE_INT|UDMAOUT_DONE_INT| + ATAPI_DEV_INT)) host_stat |= ATA_DMA_INTR; - } - if (int_status & (MULTI_TERM_INT|UDMAIN_TERM_INT|UDMAOUT_TERM_INT)) { - host_stat |= ATA_DMA_ERR; - } + if (int_status & (MULTI_TERM_INT|UDMAIN_TERM_INT|UDMAOUT_TERM_INT)) + host_stat |= ATA_DMA_ERR|ATA_DMA_INTR; + + dev_dbg(ap->dev, "ATAPI: host_stat=0x%x\n", host_stat); return host_stat; } @@ -1213,8 +1213,7 @@ static void bfin_irq_clear(struct ata_port *ap) { void __iomem *base = (void __iomem *)ap->ioaddr.ctl_addr; - pr_debug("in atapi irq clear\n"); - + dev_dbg(ap->dev, "in atapi irq clear\n"); ATAPI_SET_INT_STATUS(base, ATAPI_GET_INT_STATUS(base)|ATAPI_DEV_INT | MULTI_DONE_INT | UDMAIN_DONE_INT | UDMAOUT_DONE_INT | MULTI_TERM_INT | UDMAIN_TERM_INT | UDMAOUT_TERM_INT); @@ -1232,7 +1231,7 @@ static unsigned char bfin_irq_on(struct ata_port *ap) void __iomem *base = (void __iomem *)ap->ioaddr.ctl_addr; u8 tmp; - pr_debug("in atapi irq on\n"); + dev_dbg(ap->dev, "in atapi irq on\n"); ap->ctl &= ~ATA_NIEN; ap->last_ctl = ap->ctl; @@ -1255,7 +1254,7 @@ static void bfin_bmdma_freeze(struct ata_port *ap) { void __iomem *base = (void __iomem *)ap->ioaddr.ctl_addr; - pr_debug("in atapi dma freeze\n"); + dev_dbg(ap->dev, "in atapi dma freeze\n"); ap->ctl |= ATA_NIEN; ap->last_ctl = ap->ctl; @@ -1328,7 +1327,7 @@ static void bfin_error_handler(struct ata_port *ap) static void bfin_port_stop(struct ata_port *ap) { - pr_debug("in atapi port stop\n"); + dev_dbg(ap->dev, "in atapi port stop\n"); if (ap->udma_mask != 0 || ap->mwdma_mask != 0) { free_dma(CH_ATAPI_RX); free_dma(CH_ATAPI_TX); @@ -1337,7 +1336,7 @@ static void bfin_port_stop(struct ata_port *ap) static int bfin_port_start(struct ata_port *ap) { - pr_debug("in atapi port start\n"); + dev_dbg(ap->dev, "in atapi port start\n"); if (!(ap->udma_mask || ap->mwdma_mask)) return 0; @@ -1373,10 +1372,6 @@ static struct scsi_host_template bfin_sht = { .slave_configure = ata_scsi_slave_config, .slave_destroy = ata_scsi_slave_destroy, .bios_param = ata_std_bios_param, -#ifdef CONFIG_PM - .resume = ata_scsi_device_resume, - .suspend = ata_scsi_device_suspend, -#endif }; static const struct ata_port_operations bfin_pata_ops = { diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c index 1388cef52c0..81ef207f826 100644 --- a/drivers/ata/pata_sl82c105.c +++ b/drivers/ata/pata_sl82c105.c @@ -26,7 +26,7 @@ #include <linux/libata.h> #define DRV_NAME "pata_sl82c105" -#define DRV_VERSION "0.3.2" +#define DRV_VERSION "0.3.3" enum { /* @@ -206,6 +206,34 @@ static void sl82c105_bmdma_stop(struct ata_queued_cmd *qc) sl82c105_set_piomode(ap, qc->dev); } +/** + * sl82c105_qc_defer - implement serialization + * @qc: command + * + * We must issue one command per host not per channel because + * of the reset bug. + * + * Q: is the scsi host lock sufficient ? + */ + +static int sl82c105_qc_defer(struct ata_queued_cmd *qc) +{ + struct ata_host *host = qc->ap->host; + struct ata_port *alt = host->ports[1 ^ qc->ap->port_no]; + int rc; + + /* First apply the usual rules */ + rc = ata_std_qc_defer(qc); + if (rc != 0) + return rc; + + /* Now apply serialization rules. Only allow a command if the + other channel state machine is idle */ + if (alt && alt->qc_active) + return ATA_DEFER_PORT; + return 0; +} + static struct scsi_host_template sl82c105_sht = { .module = THIS_MODULE, .name = DRV_NAME, @@ -245,6 +273,7 @@ static struct ata_port_operations sl82c105_port_ops = { .bmdma_stop = sl82c105_bmdma_stop, .bmdma_status = ata_bmdma_status, + .qc_defer = sl82c105_qc_defer, .qc_prep = ata_qc_prep, .qc_issue = ata_qc_issue_prot, @@ -312,7 +341,7 @@ static int sl82c105_init_one(struct pci_dev *dev, const struct pci_device_id *id }; /* for now use only the first port */ const struct ata_port_info *ppi[] = { &info_early, - &ata_dummy_port_info }; + NULL }; u32 val; int rev; diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 7e72463a90e..3c1b5c9027d 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -29,7 +29,13 @@ I distinctly remember a couple workarounds (one related to PCI-X) are still needed. - 4) Add NCQ support (easy to intermediate, once new-EH support appears) + 2) Improve/fix IRQ and error handling sequences. + + 3) ATAPI support (Marvell claims the 60xx/70xx chips can do it). + + 4) Think about TCQ support here, and for libata in general + with controllers that suppport it via host-queuing hardware + (a software-only implementation could be a nightmare). 5) Investigate problems with PCI Message Signalled Interrupts (MSI). @@ -53,8 +59,6 @@ Target mode, for those without docs, is the ability to directly connect two SATA controllers. - 13) Verify that 7042 is fully supported. I only have a 6042. - */ @@ -73,7 +77,7 @@ #include <linux/libata.h> #define DRV_NAME "sata_mv" -#define DRV_VERSION "1.01" +#define DRV_VERSION "1.20" enum { /* BAR's are enumerated in terms of pci_resource_start() terms */ @@ -107,14 +111,12 @@ enum { /* CRQB needs alignment on a 1KB boundary. Size == 1KB * CRPB needs alignment on a 256B boundary. Size == 256B - * SG count of 176 leads to MV_PORT_PRIV_DMA_SZ == 4KB * ePRD (SG) entries need alignment on a 16B boundary. Size == 16B */ MV_CRQB_Q_SZ = (32 * MV_MAX_Q_DEPTH), MV_CRPB_Q_SZ = (8 * MV_MAX_Q_DEPTH), - MV_MAX_SG_CT = 176, + MV_MAX_SG_CT = 256, MV_SG_TBL_SZ = (16 * MV_MAX_SG_CT), - MV_PORT_PRIV_DMA_SZ = (MV_CRQB_Q_SZ + MV_CRPB_Q_SZ + MV_SG_TBL_SZ), MV_PORTS_PER_HC = 4, /* == (port / MV_PORTS_PER_HC) to determine HC from 0-7 port */ @@ -125,6 +127,9 @@ enum { /* Host Flags */ MV_FLAG_DUAL_HC = (1 << 30), /* two SATA Host Controllers */ MV_FLAG_IRQ_COALESCE = (1 << 29), /* IRQ coalescing capability */ + /* SoC integrated controllers, no PCI interface */ + MV_FLAG_SOC = (1 << 28), + MV_COMMON_FLAGS = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_MMIO | ATA_FLAG_NO_ATAPI | ATA_FLAG_PIO_POLLING, @@ -170,7 +175,7 @@ enum { PCIE_IRQ_CAUSE_OFS = 0x1900, PCIE_IRQ_MASK_OFS = 0x1910, - PCIE_UNMASK_ALL_IRQS = 0x70a, /* assorted bits */ + PCIE_UNMASK_ALL_IRQS = 0x40a, /* assorted bits */ HC_MAIN_IRQ_CAUSE_OFS = 0x1d60, HC_MAIN_IRQ_MASK_OFS = 0x1d64, @@ -210,6 +215,7 @@ enum { /* SATA registers */ SATA_STATUS_OFS = 0x300, /* ctrl, err regs follow status */ SATA_ACTIVE_OFS = 0x350, + SATA_FIS_IRQ_CAUSE_OFS = 0x364, PHY_MODE3 = 0x310, PHY_MODE4 = 0x314, PHY_MODE2 = 0x330, @@ -222,11 +228,11 @@ enum { /* Port registers */ EDMA_CFG_OFS = 0, - EDMA_CFG_Q_DEPTH = 0, /* queueing disabled */ - EDMA_CFG_NCQ = (1 << 5), - EDMA_CFG_NCQ_GO_ON_ERR = (1 << 14), /* continue on error */ - EDMA_CFG_RD_BRST_EXT = (1 << 11), /* read burst 512B */ - EDMA_CFG_WR_BUFF_LEN = (1 << 13), /* write buffer 512B */ + EDMA_CFG_Q_DEPTH = 0x1f, /* max device queue depth */ + EDMA_CFG_NCQ = (1 << 5), /* for R/W FPDMA queued */ + EDMA_CFG_NCQ_GO_ON_ERR = (1 << 14), /* continue on error */ + EDMA_CFG_RD_BRST_EXT = (1 << 11), /* read burst 512B */ + EDMA_CFG_WR_BUFF_LEN = (1 << 13), /* write buffer 512B */ EDMA_ERR_IRQ_CAUSE_OFS = 0x8, EDMA_ERR_IRQ_MASK_OFS = 0xc, @@ -244,14 +250,33 @@ enum { EDMA_ERR_CRPB_PAR = (1 << 10), /* CRPB parity error */ EDMA_ERR_INTRL_PAR = (1 << 11), /* internal parity error */ EDMA_ERR_IORDY = (1 << 12), /* IORdy timeout */ + EDMA_ERR_LNK_CTRL_RX = (0xf << 13), /* link ctrl rx error */ - EDMA_ERR_LNK_CTRL_RX_2 = (1 << 15), + EDMA_ERR_LNK_CTRL_RX_0 = (1 << 13), /* transient: CRC err */ + EDMA_ERR_LNK_CTRL_RX_1 = (1 << 14), /* transient: FIFO err */ + EDMA_ERR_LNK_CTRL_RX_2 = (1 << 15), /* fatal: caught SYNC */ + EDMA_ERR_LNK_CTRL_RX_3 = (1 << 16), /* transient: FIS rx err */ + EDMA_ERR_LNK_DATA_RX = (0xf << 17), /* link data rx error */ + EDMA_ERR_LNK_CTRL_TX = (0x1f << 21), /* link ctrl tx error */ + EDMA_ERR_LNK_CTRL_TX_0 = (1 << 21), /* transient: CRC err */ + EDMA_ERR_LNK_CTRL_TX_1 = (1 << 22), /* transient: FIFO err */ + EDMA_ERR_LNK_CTRL_TX_2 = (1 << 23), /* transient: caught SYNC */ + EDMA_ERR_LNK_CTRL_TX_3 = (1 << 24), /* transient: caught DMAT */ + EDMA_ERR_LNK_CTRL_TX_4 = (1 << 25), /* transient: FIS collision */ + EDMA_ERR_LNK_DATA_TX = (0x1f << 26), /* link data tx error */ + EDMA_ERR_TRANS_PROTO = (1 << 31), /* transport protocol error */ EDMA_ERR_OVERRUN_5 = (1 << 5), EDMA_ERR_UNDERRUN_5 = (1 << 6), + + EDMA_ERR_IRQ_TRANSIENT = EDMA_ERR_LNK_CTRL_RX_0 | + EDMA_ERR_LNK_CTRL_RX_1 | + EDMA_ERR_LNK_CTRL_RX_3 | + EDMA_ERR_LNK_CTRL_TX, + EDMA_EH_FREEZE = EDMA_ERR_D_PAR | EDMA_ERR_PRD_PAR | EDMA_ERR_DEV_DCON | @@ -311,12 +336,14 @@ enum { /* Port private flags (pp_flags) */ MV_PP_FLAG_EDMA_EN = (1 << 0), /* is EDMA engine enabled? */ + MV_PP_FLAG_NCQ_EN = (1 << 1), /* is EDMA set up for NCQ? */ MV_PP_FLAG_HAD_A_RESET = (1 << 2), /* 1st hard reset complete? */ }; #define IS_GEN_I(hpriv) ((hpriv)->hp_flags & MV_HP_GEN_I) #define IS_GEN_II(hpriv) ((hpriv)->hp_flags & MV_HP_GEN_II) #define IS_GEN_IIE(hpriv) ((hpriv)->hp_flags & MV_HP_GEN_IIE) +#define HAS_PCI(host) (!((host)->ports[0]->flags & MV_FLAG_SOC)) enum { /* DMA boundary 0xffff is required by the s/g splitting @@ -379,8 +406,8 @@ struct mv_port_priv { dma_addr_t crqb_dma; struct mv_crpb *crpb; dma_addr_t crpb_dma; - struct mv_sg *sg_tbl; - dma_addr_t sg_tbl_dma; + struct mv_sg *sg_tbl[MV_MAX_Q_DEPTH]; + dma_addr_t sg_tbl_dma[MV_MAX_Q_DEPTH]; unsigned int req_idx; unsigned int resp_idx; @@ -400,6 +427,14 @@ struct mv_host_priv { u32 irq_cause_ofs; u32 irq_mask_ofs; u32 unmask_all_irqs; + /* + * These consistent DMA memory pools give us guaranteed + * alignment for hardware-accessed data structures, + * and less memory waste in accomplishing the alignment. + */ + struct dma_pool *crqb_pool; + struct dma_pool *crpb_pool; + struct dma_pool *sg_tbl_pool; }; struct mv_hw_ops { @@ -411,7 +446,7 @@ struct mv_hw_ops { int (*reset_hc)(struct mv_host_priv *hpriv, void __iomem *mmio, unsigned int n_hc); void (*reset_flash)(struct mv_host_priv *hpriv, void __iomem *mmio); - void (*reset_bus)(struct pci_dev *pdev, void __iomem *mmio); + void (*reset_bus)(struct ata_host *host, void __iomem *mmio); }; static void mv_irq_clear(struct ata_port *ap); @@ -425,10 +460,9 @@ static void mv_qc_prep(struct ata_queued_cmd *qc); static void mv_qc_prep_iie(struct ata_queued_cmd *qc); static unsigned int mv_qc_issue(struct ata_queued_cmd *qc); static void mv_error_handler(struct ata_port *ap); -static void mv_post_int_cmd(struct ata_queued_cmd *qc); static void mv_eh_freeze(struct ata_port *ap); static void mv_eh_thaw(struct ata_port *ap); -static int mv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); +static void mv6_dev_config(struct ata_device *dev); static void mv5_phy_errata(struct mv_host_priv *hpriv, void __iomem *mmio, unsigned int port); @@ -438,7 +472,7 @@ static void mv5_read_preamp(struct mv_host_priv *hpriv, int idx, static int mv5_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, unsigned int n_hc); static void mv5_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio); -static void mv5_reset_bus(struct pci_dev *pdev, void __iomem *mmio); +static void mv5_reset_bus(struct ata_host *host, void __iomem *mmio); static void mv6_phy_errata(struct mv_host_priv *hpriv, void __iomem *mmio, unsigned int port); @@ -448,10 +482,17 @@ static void mv6_read_preamp(struct mv_host_priv *hpriv, int idx, static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, unsigned int n_hc); static void mv6_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio); -static void mv_reset_pci_bus(struct pci_dev *pdev, void __iomem *mmio); +static void mv_reset_pci_bus(struct ata_host *host, void __iomem *mmio); static void mv_channel_reset(struct mv_host_priv *hpriv, void __iomem *mmio, unsigned int port_no); +static void mv_edma_cfg(struct mv_port_priv *pp, struct mv_host_priv *hpriv, + void __iomem *port_mmio, int want_ncq); +static int __mv_stop_dma(struct ata_port *ap); +/* .sg_tablesize is (MV_MAX_SG_CT / 2) in the structures below + * because we have to allow room for worst case splitting of + * PRDs for 64K boundaries in mv_fill_sg(). + */ static struct scsi_host_template mv5_sht = { .module = THIS_MODULE, .name = DRV_NAME, @@ -475,7 +516,8 @@ static struct scsi_host_template mv6_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .can_queue = ATA_DEF_QUEUE, + .change_queue_depth = ata_scsi_change_queue_depth, + .can_queue = MV_MAX_Q_DEPTH - 1, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = MV_MAX_SG_CT / 2, .cmd_per_lun = ATA_SHT_CMD_PER_LUN, @@ -505,7 +547,6 @@ static const struct ata_port_operations mv5_ops = { .irq_on = ata_irq_on, .error_handler = mv_error_handler, - .post_internal_cmd = mv_post_int_cmd, .freeze = mv_eh_freeze, .thaw = mv_eh_thaw, @@ -517,6 +558,7 @@ static const struct ata_port_operations mv5_ops = { }; static const struct ata_port_operations mv6_ops = { + .dev_config = mv6_dev_config, .tf_load = ata_tf_load, .tf_read = ata_tf_read, .check_status = ata_check_status, @@ -533,9 +575,9 @@ static const struct ata_port_operations mv6_ops = { .irq_on = ata_irq_on, .error_handler = mv_error_handler, - .post_internal_cmd = mv_post_int_cmd, .freeze = mv_eh_freeze, .thaw = mv_eh_thaw, + .qc_defer = ata_std_qc_defer, .scr_read = mv_scr_read, .scr_write = mv_scr_write, @@ -561,9 +603,9 @@ static const struct ata_port_operations mv_iie_ops = { .irq_on = ata_irq_on, .error_handler = mv_error_handler, - .post_internal_cmd = mv_post_int_cmd, .freeze = mv_eh_freeze, .thaw = mv_eh_thaw, + .qc_defer = ata_std_qc_defer, .scr_read = mv_scr_read, .scr_write = mv_scr_write, @@ -592,26 +634,29 @@ static const struct ata_port_info mv_port_info[] = { .port_ops = &mv5_ops, }, { /* chip_604x */ - .flags = MV_COMMON_FLAGS | MV_6XXX_FLAGS, + .flags = MV_COMMON_FLAGS | MV_6XXX_FLAGS | + ATA_FLAG_NCQ, .pio_mask = 0x1f, /* pio0-4 */ .udma_mask = ATA_UDMA6, .port_ops = &mv6_ops, }, { /* chip_608x */ .flags = MV_COMMON_FLAGS | MV_6XXX_FLAGS | - MV_FLAG_DUAL_HC, + ATA_FLAG_NCQ | MV_FLAG_DUAL_HC, .pio_mask = 0x1f, /* pio0-4 */ .udma_mask = ATA_UDMA6, .port_ops = &mv6_ops, }, { /* chip_6042 */ - .flags = MV_COMMON_FLAGS | MV_6XXX_FLAGS, + .flags = MV_COMMON_FLAGS | MV_6XXX_FLAGS | + ATA_FLAG_NCQ, .pio_mask = 0x1f, /* pio0-4 */ .udma_mask = ATA_UDMA6, .port_ops = &mv_iie_ops, }, { /* chip_7042 */ - .flags = MV_COMMON_FLAGS | MV_6XXX_FLAGS, + .flags = MV_COMMON_FLAGS | MV_6XXX_FLAGS | + ATA_FLAG_NCQ, .pio_mask = 0x1f, /* pio0-4 */ .udma_mask = ATA_UDMA6, .port_ops = &mv_iie_ops, @@ -648,13 +693,6 @@ static const struct pci_device_id mv_pci_tbl[] = { { } /* terminate list */ }; -static struct pci_driver mv_pci_driver = { - .name = DRV_NAME, - .id_table = mv_pci_tbl, - .probe = mv_init_one, - .remove = ata_pci_remove_one, -}; - static const struct mv_hw_ops mv5xxx_ops = { .phy_errata = mv5_phy_errata, .enable_leds = mv5_enable_leds, @@ -674,45 +712,6 @@ static const struct mv_hw_ops mv6xxx_ops = { }; /* - * module options - */ -static int msi; /* Use PCI msi; either zero (off, default) or non-zero */ - - -/* move to PCI layer or libata core? */ -static int pci_go_64(struct pci_dev *pdev) -{ - int rc; - - if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) { - rc = pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK); - if (rc) { - rc = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK); - if (rc) { - dev_printk(KERN_ERR, &pdev->dev, - "64-bit DMA enable failed\n"); - return rc; - } - } - } else { - rc = pci_set_dma_mask(pdev, DMA_32BIT_MASK); - if (rc) { - dev_printk(KERN_ERR, &pdev->dev, - "32-bit DMA enable failed\n"); - return rc; - } - rc = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK); - if (rc) { - dev_printk(KERN_ERR, &pdev->dev, - "32-bit consistent DMA enable failed\n"); - return rc; - } - } - - return rc; -} - -/* * Functions */ @@ -815,19 +814,46 @@ static void mv_set_edma_ptrs(void __iomem *port_mmio, * LOCKING: * Inherited from caller. */ -static void mv_start_dma(void __iomem *base, struct mv_host_priv *hpriv, - struct mv_port_priv *pp) +static void mv_start_dma(struct ata_port *ap, void __iomem *port_mmio, + struct mv_port_priv *pp, u8 protocol) { + int want_ncq = (protocol == ATA_PROT_NCQ); + + if (pp->pp_flags & MV_PP_FLAG_EDMA_EN) { + int using_ncq = ((pp->pp_flags & MV_PP_FLAG_NCQ_EN) != 0); + if (want_ncq != using_ncq) + __mv_stop_dma(ap); + } if (!(pp->pp_flags & MV_PP_FLAG_EDMA_EN)) { + struct mv_host_priv *hpriv = ap->host->private_data; + int hard_port = mv_hardport_from_port(ap->port_no); + void __iomem *hc_mmio = mv_hc_base_from_port( + ap->host->iomap[MV_PRIMARY_BAR], hard_port); + u32 hc_irq_cause, ipending; + /* clear EDMA event indicators, if any */ - writelfl(0, base + EDMA_ERR_IRQ_CAUSE_OFS); + writelfl(0, port_mmio + EDMA_ERR_IRQ_CAUSE_OFS); + + /* clear EDMA interrupt indicator, if any */ + hc_irq_cause = readl(hc_mmio + HC_IRQ_CAUSE_OFS); + ipending = (DEV_IRQ << hard_port) | + (CRPB_DMA_DONE << hard_port); + if (hc_irq_cause & ipending) { + writelfl(hc_irq_cause & ~ipending, + hc_mmio + HC_IRQ_CAUSE_OFS); + } + + mv_edma_cfg(pp, hpriv, port_mmio, want_ncq); + + /* clear FIS IRQ Cause */ + writelfl(0, port_mmio + SATA_FIS_IRQ_CAUSE_OFS); - mv_set_edma_ptrs(base, hpriv, pp); + mv_set_edma_ptrs(port_mmio, hpriv, pp); - writelfl(EDMA_EN, base + EDMA_CMD_OFS); + writelfl(EDMA_EN, port_mmio + EDMA_CMD_OFS); pp->pp_flags |= MV_PP_FLAG_EDMA_EN; } - WARN_ON(!(EDMA_EN & readl(base + EDMA_CMD_OFS))); + WARN_ON(!(EDMA_EN & readl(port_mmio + EDMA_CMD_OFS))); } /** @@ -1003,38 +1029,76 @@ static int mv_scr_write(struct ata_port *ap, unsigned int sc_reg_in, u32 val) return -EINVAL; } -static void mv_edma_cfg(struct ata_port *ap, struct mv_host_priv *hpriv, - void __iomem *port_mmio) +static void mv6_dev_config(struct ata_device *adev) { - u32 cfg = readl(port_mmio + EDMA_CFG_OFS); + /* + * We don't have hob_nsect when doing NCQ commands on Gen-II. + * See mv_qc_prep() for more info. + */ + if (adev->flags & ATA_DFLAG_NCQ) + if (adev->max_sectors > ATA_MAX_SECTORS) + adev->max_sectors = ATA_MAX_SECTORS; +} + +static void mv_edma_cfg(struct mv_port_priv *pp, struct mv_host_priv *hpriv, + void __iomem *port_mmio, int want_ncq) +{ + u32 cfg; /* set up non-NCQ EDMA configuration */ - cfg &= ~(1 << 9); /* disable eQue */ + cfg = EDMA_CFG_Q_DEPTH; /* always 0x1f for *all* chips */ - if (IS_GEN_I(hpriv)) { - cfg &= ~0x1f; /* clear queue depth */ + if (IS_GEN_I(hpriv)) cfg |= (1 << 8); /* enab config burst size mask */ - } - else if (IS_GEN_II(hpriv)) { - cfg &= ~0x1f; /* clear queue depth */ + else if (IS_GEN_II(hpriv)) cfg |= EDMA_CFG_RD_BRST_EXT | EDMA_CFG_WR_BUFF_LEN; - cfg &= ~(EDMA_CFG_NCQ | EDMA_CFG_NCQ_GO_ON_ERR); /* clear NCQ */ - } else if (IS_GEN_IIE(hpriv)) { cfg |= (1 << 23); /* do not mask PM field in rx'd FIS */ cfg |= (1 << 22); /* enab 4-entry host queue cache */ - cfg &= ~(1 << 19); /* dis 128-entry queue (for now?) */ cfg |= (1 << 18); /* enab early completion */ cfg |= (1 << 17); /* enab cut-through (dis stor&forwrd) */ - cfg &= ~(1 << 16); /* dis FIS-based switching (for now) */ - cfg &= ~(EDMA_CFG_NCQ); /* clear NCQ */ } + if (want_ncq) { + cfg |= EDMA_CFG_NCQ; + pp->pp_flags |= MV_PP_FLAG_NCQ_EN; + } else + pp->pp_flags &= ~MV_PP_FLAG_NCQ_EN; + writelfl(cfg, port_mmio + EDMA_CFG_OFS); } +static void mv_port_free_dma_mem(struct ata_port *ap) +{ + struct mv_host_priv *hpriv = ap->host->private_data; + struct mv_port_priv *pp = ap->private_data; + int tag; + + if (pp->crqb) { + dma_pool_free(hpriv->crqb_pool, pp->crqb, pp->crqb_dma); + pp->crqb = NULL; + } + if (pp->crpb) { + dma_pool_free(hpriv->crpb_pool, pp->crpb, pp->crpb_dma); + pp->crpb = NULL; + } + /* + * For GEN_I, there's no NCQ, so we have only a single sg_tbl. + * For later hardware, we have one unique sg_tbl per NCQ tag. + */ + for (tag = 0; tag < MV_MAX_Q_DEPTH; ++tag) { + if (pp->sg_tbl[tag]) { + if (tag == 0 || !IS_GEN_I(hpriv)) + dma_pool_free(hpriv->sg_tbl_pool, + pp->sg_tbl[tag], + pp->sg_tbl_dma[tag]); + pp->sg_tbl[tag] = NULL; + } + } +} + /** * mv_port_start - Port specific init/start routine. * @ap: ATA channel to manipulate @@ -1051,51 +1115,47 @@ static int mv_port_start(struct ata_port *ap) struct mv_host_priv *hpriv = ap->host->private_data; struct mv_port_priv *pp; void __iomem *port_mmio = mv_ap_base(ap); - void *mem; - dma_addr_t mem_dma; unsigned long flags; - int rc; + int tag, rc; pp = devm_kzalloc(dev, sizeof(*pp), GFP_KERNEL); if (!pp) return -ENOMEM; - - mem = dmam_alloc_coherent(dev, MV_PORT_PRIV_DMA_SZ, &mem_dma, - GFP_KERNEL); - if (!mem) - return -ENOMEM; - memset(mem, 0, MV_PORT_PRIV_DMA_SZ); + ap->private_data = pp; rc = ata_pad_alloc(ap, dev); if (rc) return rc; - /* First item in chunk of DMA memory: - * 32-slot command request table (CRQB), 32 bytes each in size - */ - pp->crqb = mem; - pp->crqb_dma = mem_dma; - mem += MV_CRQB_Q_SZ; - mem_dma += MV_CRQB_Q_SZ; + pp->crqb = dma_pool_alloc(hpriv->crqb_pool, GFP_KERNEL, &pp->crqb_dma); + if (!pp->crqb) + return -ENOMEM; + memset(pp->crqb, 0, MV_CRQB_Q_SZ); - /* Second item: - * 32-slot command response table (CRPB), 8 bytes each in size - */ - pp->crpb = mem; - pp->crpb_dma = mem_dma; - mem += MV_CRPB_Q_SZ; - mem_dma += MV_CRPB_Q_SZ; + pp->crpb = dma_pool_alloc(hpriv->crpb_pool, GFP_KERNEL, &pp->crpb_dma); + if (!pp->crpb) + goto out_port_free_dma_mem; + memset(pp->crpb, 0, MV_CRPB_Q_SZ); - /* Third item: - * Table of scatter-gather descriptors (ePRD), 16 bytes each + /* + * For GEN_I, there's no NCQ, so we only allocate a single sg_tbl. + * For later hardware, we need one unique sg_tbl per NCQ tag. */ - pp->sg_tbl = mem; - pp->sg_tbl_dma = mem_dma; + for (tag = 0; tag < MV_MAX_Q_DEPTH; ++tag) { + if (tag == 0 || !IS_GEN_I(hpriv)) { + pp->sg_tbl[tag] = dma_pool_alloc(hpriv->sg_tbl_pool, + GFP_KERNEL, &pp->sg_tbl_dma[tag]); + if (!pp->sg_tbl[tag]) + goto out_port_free_dma_mem; + } else { + pp->sg_tbl[tag] = pp->sg_tbl[0]; + pp->sg_tbl_dma[tag] = pp->sg_tbl_dma[0]; + } + } spin_lock_irqsave(&ap->host->lock, flags); - mv_edma_cfg(ap, hpriv, port_mmio); - + mv_edma_cfg(pp, hpriv, port_mmio, 0); mv_set_edma_ptrs(port_mmio, hpriv, pp); spin_unlock_irqrestore(&ap->host->lock, flags); @@ -1104,8 +1164,11 @@ static int mv_port_start(struct ata_port *ap) * we'll be unable to send non-data, PIO, etc due to restricted access * to shadow regs. */ - ap->private_data = pp; return 0; + +out_port_free_dma_mem: + mv_port_free_dma_mem(ap); + return -ENOMEM; } /** @@ -1120,6 +1183,7 @@ static int mv_port_start(struct ata_port *ap) static void mv_port_stop(struct ata_port *ap) { mv_stop_dma(ap); + mv_port_free_dma_mem(ap); } /** @@ -1138,7 +1202,7 @@ static void mv_fill_sg(struct ata_queued_cmd *qc) struct mv_sg *mv_sg, *last_sg = NULL; unsigned int si; - mv_sg = pp->sg_tbl; + mv_sg = pp->sg_tbl[qc->tag]; for_each_sg(qc->sg, sg, qc->n_elem, si) { dma_addr_t addr = sg_dma_address(sg); u32 sg_len = sg_dma_len(sg); @@ -1194,7 +1258,8 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) u16 flags = 0; unsigned in_index; - if (qc->tf.protocol != ATA_PROT_DMA) + if ((qc->tf.protocol != ATA_PROT_DMA) && + (qc->tf.protocol != ATA_PROT_NCQ)) return; /* Fill in command request block @@ -1203,15 +1268,14 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) flags |= CRQB_FLAG_READ; WARN_ON(MV_MAX_Q_DEPTH <= qc->tag); flags |= qc->tag << CRQB_TAG_SHIFT; - flags |= qc->tag << CRQB_IOID_SHIFT; /* 50xx appears to ignore this*/ /* get current queue index from software */ in_index = pp->req_idx & MV_MAX_Q_DEPTH_MASK; pp->crqb[in_index].sg_addr = - cpu_to_le32(pp->sg_tbl_dma & 0xffffffff); + cpu_to_le32(pp->sg_tbl_dma[qc->tag] & 0xffffffff); pp->crqb[in_index].sg_addr_hi = - cpu_to_le32((pp->sg_tbl_dma >> 16) >> 16); + cpu_to_le32((pp->sg_tbl_dma[qc->tag] >> 16) >> 16); pp->crqb[in_index].ctrl_flags = cpu_to_le16(flags); cw = &pp->crqb[in_index].ata_cmd[0]; @@ -1231,13 +1295,11 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) case ATA_CMD_WRITE_FUA_EXT: mv_crqb_pack_cmd(cw++, tf->hob_nsect, ATA_REG_NSECT, 0); break; -#ifdef LIBATA_NCQ /* FIXME: remove this line when NCQ added */ case ATA_CMD_FPDMA_READ: case ATA_CMD_FPDMA_WRITE: mv_crqb_pack_cmd(cw++, tf->hob_feature, ATA_REG_FEATURE, 0); mv_crqb_pack_cmd(cw++, tf->feature, ATA_REG_FEATURE, 0); break; -#endif /* FIXME: remove this line when NCQ added */ default: /* The only other commands EDMA supports in non-queued and * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none @@ -1286,7 +1348,8 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) unsigned in_index; u32 flags = 0; - if (qc->tf.protocol != ATA_PROT_DMA) + if ((qc->tf.protocol != ATA_PROT_DMA) && + (qc->tf.protocol != ATA_PROT_NCQ)) return; /* Fill in Gen IIE command request block @@ -1296,15 +1359,14 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) WARN_ON(MV_MAX_Q_DEPTH <= qc->tag); flags |= qc->tag << CRQB_TAG_SHIFT; - flags |= qc->tag << CRQB_IOID_SHIFT; /* "I/O Id" is -really- - what we use as our tag */ + flags |= qc->tag << CRQB_HOSTQ_SHIFT; /* get current queue index from software */ in_index = pp->req_idx & MV_MAX_Q_DEPTH_MASK; crqb = (struct mv_crqb_iie *) &pp->crqb[in_index]; - crqb->addr = cpu_to_le32(pp->sg_tbl_dma & 0xffffffff); - crqb->addr_hi = cpu_to_le32((pp->sg_tbl_dma >> 16) >> 16); + crqb->addr = cpu_to_le32(pp->sg_tbl_dma[qc->tag] & 0xffffffff); + crqb->addr_hi = cpu_to_le32((pp->sg_tbl_dma[qc->tag] >> 16) >> 16); crqb->flags = cpu_to_le32(flags); tf = &qc->tf; @@ -1351,10 +1413,10 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; void __iomem *port_mmio = mv_ap_base(ap); struct mv_port_priv *pp = ap->private_data; - struct mv_host_priv *hpriv = ap->host->private_data; u32 in_index; - if (qc->tf.protocol != ATA_PROT_DMA) { + if ((qc->tf.protocol != ATA_PROT_DMA) && + (qc->tf.protocol != ATA_PROT_NCQ)) { /* We're about to send a non-EDMA capable command to the * port. Turn off EDMA so there won't be problems accessing * shadow block, etc registers. @@ -1363,13 +1425,7 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc) return ata_qc_issue_prot(qc); } - mv_start_dma(port_mmio, hpriv, pp); - - in_index = pp->req_idx & MV_MAX_Q_DEPTH_MASK; - - /* until we do queuing, the queue should be empty at this point */ - WARN_ON(in_index != ((readl(port_mmio + EDMA_REQ_Q_OUT_PTR_OFS) - >> EDMA_REQ_Q_PTR_SHIFT) & MV_MAX_Q_DEPTH_MASK)); + mv_start_dma(ap, port_mmio, pp, qc->tf.protocol); pp->req_idx++; @@ -1437,6 +1493,7 @@ static void mv_err_intr(struct ata_port *ap, struct ata_queued_cmd *qc) ata_ehi_hotplugged(ehi); ata_ehi_push_desc(ehi, edma_err_cause & EDMA_ERR_DEV_DCON ? "dev disconnect" : "dev connect"); + action |= ATA_EH_HARDRESET; } if (IS_GEN_I(hpriv)) { @@ -1465,7 +1522,7 @@ static void mv_err_intr(struct ata_port *ap, struct ata_queued_cmd *qc) } /* Clear EDMA now that SERR cleanup done */ - writelfl(0, port_mmio + EDMA_ERR_IRQ_CAUSE_OFS); + writelfl(~edma_err_cause, port_mmio + EDMA_ERR_IRQ_CAUSE_OFS); if (!err_mask) { err_mask = AC_ERR_OTHER; @@ -1538,23 +1595,17 @@ static void mv_intr_edma(struct ata_port *ap) * support for queueing. this works transparently for * queued and non-queued modes. */ - else if (IS_GEN_II(hpriv)) - tag = (le16_to_cpu(pp->crpb[out_index].id) - >> CRPB_IOID_SHIFT_6) & 0x3f; - - else /* IS_GEN_IIE */ - tag = (le16_to_cpu(pp->crpb[out_index].id) - >> CRPB_IOID_SHIFT_7) & 0x3f; + else + tag = le16_to_cpu(pp->crpb[out_index].id) & 0x1f; qc = ata_qc_from_tag(ap, tag); - /* lower 8 bits of status are EDMA_ERR_IRQ_CAUSE_OFS - * bits (WARNING: might not necessarily be associated - * with this command), which -should- be clear - * if all is well + /* For non-NCQ mode, the lower 8 bits of status + * are from EDMA_ERR_IRQ_CAUSE_OFS, + * which should be zero if all went well. */ status = le16_to_cpu(pp->crpb[out_index].flags); - if (unlikely(status & 0xff)) { + if ((status & 0xff) && !(pp->pp_flags & MV_PP_FLAG_NCQ_EN)) { mv_err_intr(ap, qc); return; } @@ -1715,20 +1766,21 @@ static irqreturn_t mv_interrupt(int irq, void *dev_instance) struct ata_host *host = dev_instance; unsigned int hc, handled = 0, n_hcs; void __iomem *mmio = host->iomap[MV_PRIMARY_BAR]; - u32 irq_stat; + u32 irq_stat, irq_mask; + spin_lock(&host->lock); irq_stat = readl(mmio + HC_MAIN_IRQ_CAUSE_OFS); + irq_mask = readl(mmio + HC_MAIN_IRQ_MASK_OFS); /* check the cases where we either have nothing pending or have read * a bogus register value which can indicate HW removal or PCI fault */ - if (!irq_stat || (0xffffffffU == irq_stat)) - return IRQ_NONE; + if (!(irq_stat & irq_mask) || (0xffffffffU == irq_stat)) + goto out_unlock; n_hcs = mv_get_hc_count(host->ports[0]->flags); - spin_lock(&host->lock); - if (unlikely(irq_stat & PCI_ERR)) { + if (unlikely((irq_stat & PCI_ERR) && HAS_PCI(host))) { mv_pci_error(host, mmio); handled = 1; goto out_unlock; /* skip all other HC irq handling */ @@ -1799,8 +1851,9 @@ static int mv5_scr_write(struct ata_port *ap, unsigned int sc_reg_in, u32 val) return -EINVAL; } -static void mv5_reset_bus(struct pci_dev *pdev, void __iomem *mmio) +static void mv5_reset_bus(struct ata_host *host, void __iomem *mmio) { + struct pci_dev *pdev = to_pci_dev(host->dev); int early_5080; early_5080 = (pdev->device == 0x5080) && (pdev->revision == 0); @@ -1811,7 +1864,7 @@ static void mv5_reset_bus(struct pci_dev *pdev, void __iomem *mmio) writel(tmp, mmio + MV_PCI_EXP_ROM_BAR_CTL); } - mv_reset_pci_bus(pdev, mmio); + mv_reset_pci_bus(host, mmio); } static void mv5_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio) @@ -1935,9 +1988,8 @@ static int mv5_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, #undef ZERO #define ZERO(reg) writel(0, mmio + (reg)) -static void mv_reset_pci_bus(struct pci_dev *pdev, void __iomem *mmio) +static void mv_reset_pci_bus(struct ata_host *host, void __iomem *mmio) { - struct ata_host *host = dev_get_drvdata(&pdev->dev); struct mv_host_priv *hpriv = host->private_data; u32 tmp; @@ -2329,11 +2381,6 @@ static void mv_error_handler(struct ata_port *ap) mv_hardreset, mv_postreset); } -static void mv_post_int_cmd(struct ata_queued_cmd *qc) -{ - mv_stop_dma(qc->ap); -} - static void mv_eh_freeze(struct ata_port *ap) { void __iomem *mmio = ap->host->iomap[MV_PRIMARY_BAR]; @@ -2427,8 +2474,8 @@ static void mv_port_init(struct ata_ioports *port, void __iomem *port_mmio) writelfl(readl(port_mmio + serr_ofs), port_mmio + serr_ofs); writelfl(0, port_mmio + EDMA_ERR_IRQ_CAUSE_OFS); - /* unmask all EDMA error interrupts */ - writelfl(~0, port_mmio + EDMA_ERR_IRQ_MASK_OFS); + /* unmask all non-transient EDMA error interrupts */ + writelfl(~EDMA_ERR_IRQ_TRANSIENT, port_mmio + EDMA_ERR_IRQ_MASK_OFS); VPRINTK("EDMA cfg=0x%08x EDMA IRQ err cause/mask=0x%08x/0x%08x\n", readl(port_mmio + EDMA_CFG_OFS), @@ -2586,7 +2633,6 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx) static int mv_init_host(struct ata_host *host, unsigned int board_idx) { int rc = 0, n_hc, port, hc; - struct pci_dev *pdev = to_pci_dev(host->dev); void __iomem *mmio = host->iomap[MV_PRIMARY_BAR]; struct mv_host_priv *hpriv = host->private_data; @@ -2607,7 +2653,7 @@ static int mv_init_host(struct ata_host *host, unsigned int board_idx) goto done; hpriv->ops->reset_flash(hpriv, mmio); - hpriv->ops->reset_bus(pdev, mmio); + hpriv->ops->reset_bus(host, mmio); hpriv->ops->enable_leds(hpriv, mmio); for (port = 0; port < host->n_ports; port++) { @@ -2630,8 +2676,10 @@ static int mv_init_host(struct ata_host *host, unsigned int board_idx) mv_port_init(&ap->ioaddr, port_mmio); +#ifdef CONFIG_PCI ata_port_pbar_desc(ap, MV_PRIMARY_BAR, -1, "mmio"); ata_port_pbar_desc(ap, MV_PRIMARY_BAR, offset, "port"); +#endif } for (hc = 0; hc < n_hc; hc++) { @@ -2668,6 +2716,55 @@ done: return rc; } +#ifdef CONFIG_PCI +static int mv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); + +static struct pci_driver mv_pci_driver = { + .name = DRV_NAME, + .id_table = mv_pci_tbl, + .probe = mv_init_one, + .remove = ata_pci_remove_one, +}; + +/* + * module options + */ +static int msi; /* Use PCI msi; either zero (off, default) or non-zero */ + + +/* move to PCI layer or libata core? */ +static int pci_go_64(struct pci_dev *pdev) +{ + int rc; + + if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) { + rc = pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK); + if (rc) { + rc = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK); + if (rc) { + dev_printk(KERN_ERR, &pdev->dev, + "64-bit DMA enable failed\n"); + return rc; + } + } + } else { + rc = pci_set_dma_mask(pdev, DMA_32BIT_MASK); + if (rc) { + dev_printk(KERN_ERR, &pdev->dev, + "32-bit DMA enable failed\n"); + return rc; + } + rc = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK); + if (rc) { + dev_printk(KERN_ERR, &pdev->dev, + "32-bit consistent DMA enable failed\n"); + return rc; + } + } + + return rc; +} + /** * mv_print_info - Dump key info to kernel log for perusal. * @host: ATA host to print info about @@ -2710,6 +2807,26 @@ static void mv_print_info(struct ata_host *host) scc_s, (MV_HP_FLAG_MSI & hpriv->hp_flags) ? "MSI" : "INTx"); } +static int mv_create_dma_pools(struct mv_host_priv *hpriv, struct device *dev) +{ + hpriv->crqb_pool = dmam_pool_create("crqb_q", dev, MV_CRQB_Q_SZ, + MV_CRQB_Q_SZ, 0); + if (!hpriv->crqb_pool) + return -ENOMEM; + + hpriv->crpb_pool = dmam_pool_create("crpb_q", dev, MV_CRPB_Q_SZ, + MV_CRPB_Q_SZ, 0); + if (!hpriv->crpb_pool) + return -ENOMEM; + + hpriv->sg_tbl_pool = dmam_pool_create("sg_tbl", dev, MV_SG_TBL_SZ, + MV_SG_TBL_SZ, 0); + if (!hpriv->sg_tbl_pool) + return -ENOMEM; + + return 0; +} + /** * mv_init_one - handle a positive probe of a Marvell host * @pdev: PCI device found @@ -2755,6 +2872,10 @@ static int mv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc; + rc = mv_create_dma_pools(hpriv, &pdev->dev); + if (rc) + return rc; + /* initialize adapter */ rc = mv_init_host(host, board_idx); if (rc) @@ -2772,15 +2893,22 @@ static int mv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return ata_host_activate(host, pdev->irq, mv_interrupt, IRQF_SHARED, IS_GEN_I(hpriv) ? &mv5_sht : &mv6_sht); } +#endif static int __init mv_init(void) { - return pci_register_driver(&mv_pci_driver); + int rc = -ENODEV; +#ifdef CONFIG_PCI + rc = pci_register_driver(&mv_pci_driver); +#endif + return rc; } static void __exit mv_exit(void) { +#ifdef CONFIG_PCI pci_unregister_driver(&mv_pci_driver); +#endif } MODULE_AUTHOR("Brett Russ"); @@ -2789,8 +2917,10 @@ MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(pci, mv_pci_tbl); MODULE_VERSION(DRV_VERSION); +#ifdef CONFIG_PCI module_param(msi, int, 0444); MODULE_PARM_DESC(msi, "Enable use of PCI MSI (0=off, 1=on)"); +#endif module_init(mv_init); module_exit(mv_exit); diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index a0f98fdab7a..bfe92a43cf8 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -1011,14 +1011,20 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance) } if (status & (NV_ADMA_STAT_DONE | - NV_ADMA_STAT_CPBERR)) { - u32 check_commands; + NV_ADMA_STAT_CPBERR | + NV_ADMA_STAT_CMD_COMPLETE)) { + u32 check_commands = notifier_clears[i]; int pos, error = 0; - if (ata_tag_valid(ap->link.active_tag)) - check_commands = 1 << ap->link.active_tag; - else - check_commands = ap->link.sactive; + if (status & NV_ADMA_STAT_CPBERR) { + /* Check all active commands */ + if (ata_tag_valid(ap->link.active_tag)) + check_commands = 1 << + ap->link.active_tag; + else + check_commands = ap-> + link.sactive; + } /** Check CPBs for completed commands */ while ((pos = ffs(check_commands)) && !error) { diff --git a/drivers/char/tty_audit.c b/drivers/char/tty_audit.c index d222012c1b0..bacded0eefa 100644 --- a/drivers/char/tty_audit.c +++ b/drivers/char/tty_audit.c @@ -73,6 +73,7 @@ static void tty_audit_buf_put(struct tty_audit_buf *buf) * @tsk with @loginuid. @buf->mutex must be locked. */ static void tty_audit_buf_push(struct task_struct *tsk, uid_t loginuid, + unsigned int sessionid, struct tty_audit_buf *buf) { struct audit_buffer *ab; @@ -85,9 +86,9 @@ static void tty_audit_buf_push(struct task_struct *tsk, uid_t loginuid, if (ab) { char name[sizeof(tsk->comm)]; - audit_log_format(ab, "tty pid=%u uid=%u auid=%u major=%d " - "minor=%d comm=", tsk->pid, tsk->uid, - loginuid, buf->major, buf->minor); + audit_log_format(ab, "tty pid=%u uid=%u auid=%u ses=%u " + "major=%d minor=%d comm=", tsk->pid, tsk->uid, + loginuid, sessionid, buf->major, buf->minor); get_task_comm(name, tsk); audit_log_untrustedstring(ab, name); audit_log_format(ab, " data="); @@ -105,8 +106,9 @@ static void tty_audit_buf_push(struct task_struct *tsk, uid_t loginuid, */ static void tty_audit_buf_push_current(struct tty_audit_buf *buf) { - tty_audit_buf_push(current, audit_get_loginuid(current->audit_context), - buf); + uid_t auid = audit_get_loginuid(current); + unsigned int sessionid = audit_get_sessionid(current); + tty_audit_buf_push(current, auid, sessionid, buf); } /** @@ -152,6 +154,11 @@ void tty_audit_fork(struct signal_struct *sig) void tty_audit_push_task(struct task_struct *tsk, uid_t loginuid) { struct tty_audit_buf *buf; + /* FIXME I think this is correct. Check against netlink once that is + * I really need to read this code more closely. But that's for + * another patch. + */ + unsigned int sessionid = audit_get_sessionid(tsk); spin_lock_irq(&tsk->sighand->siglock); buf = tsk->signal->tty_audit_buf; @@ -162,7 +169,7 @@ void tty_audit_push_task(struct task_struct *tsk, uid_t loginuid) return; mutex_lock(&buf->mutex); - tty_audit_buf_push(tsk, loginuid, buf); + tty_audit_buf_push(tsk, loginuid, sessionid, buf); mutex_unlock(&buf->mutex); tty_audit_buf_put(buf); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 71d561fda0a..7d4ce906d20 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -823,7 +823,8 @@ int pcim_enable_device(struct pci_dev *pdev) dr = get_pci_dr(pdev); if (unlikely(!dr)) return -ENOMEM; - WARN_ON(!!dr->enabled); + if (dr->enabled) + return 0; rc = pci_enable_device(pdev); if (!rc) { diff --git a/fs/proc/base.c b/fs/proc/base.c index 9fa9708cc71..33537487f5a 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -984,7 +984,7 @@ static ssize_t proc_loginuid_read(struct file * file, char __user * buf, if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", - audit_get_loginuid(task->audit_context)); + audit_get_loginuid(task)); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } diff --git a/include/asm-x86/cpu.h b/include/asm-x86/cpu.h index 85ece5f10e9..73f2ea84fd7 100644 --- a/include/asm-x86/cpu.h +++ b/include/asm-x86/cpu.h @@ -10,8 +10,9 @@ struct x86_cpu { struct cpu cpu; }; -extern int arch_register_cpu(int num); + #ifdef CONFIG_HOTPLUG_CPU +extern int arch_register_cpu(int num); extern void arch_unregister_cpu(int); #endif diff --git a/include/asm-x86/e820_64.h b/include/asm-x86/e820_64.h index 51e4170f9ca..a560c4f5d50 100644 --- a/include/asm-x86/e820_64.h +++ b/include/asm-x86/e820_64.h @@ -15,7 +15,7 @@ #ifndef __ASSEMBLY__ extern unsigned long find_e820_area(unsigned long start, unsigned long end, - unsigned size); + unsigned size, unsigned long align); extern void add_memory_region(unsigned long start, unsigned long size, int type); extern void setup_memory_region(void); @@ -41,7 +41,7 @@ extern void finish_e820_parsing(void); extern struct e820map e820; extern void update_e820(void); -extern void reserve_early(unsigned long start, unsigned long end); +extern void reserve_early(unsigned long start, unsigned long end, char *name); extern void early_res_to_bootmem(void); #endif/*!__ASSEMBLY__*/ diff --git a/include/asm-x86/futex.h b/include/asm-x86/futex.h index 62828d63f1b..9d919264923 100644 --- a/include/asm-x86/futex.h +++ b/include/asm-x86/futex.h @@ -30,7 +30,7 @@ "1: movl %2, %0\n \ movl %0, %3\n" \ insn "\n" \ -"2: " LOCK_PREFIX "cmpxchgl %3, %2\n \ +"2: lock; cmpxchgl %3, %2\n \ jnz 1b\n \ 3: .section .fixup,\"ax\"\n \ 4: mov %5, %1\n \ @@ -72,7 +72,7 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr) __futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval, + __futex_atomic_op1("lock; xaddl %0, %2", ret, oldval, uaddr, oparg); break; case FUTEX_OP_OR: @@ -111,8 +111,8 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) return -EFAULT; __asm__ __volatile__( - "1: " LOCK_PREFIX "cmpxchgl %3, %1 \n" + "1: lock; cmpxchgl %3, %1 \n" "2: .section .fixup, \"ax\" \n" "3: mov %2, %0 \n" " jmp 2b \n" diff --git a/include/linux/audit.h b/include/linux/audit.h index bdd6f5de5fc..97153027207 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -98,6 +98,7 @@ #define AUDIT_FD_PAIR 1317 /* audit record for pipe/socketpair */ #define AUDIT_OBJ_PID 1318 /* ptrace target */ #define AUDIT_TTY 1319 /* Input on an administrative TTY */ +#define AUDIT_EOE 1320 /* End of multi-record event */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ @@ -409,7 +410,8 @@ extern unsigned int audit_serial(void); extern void auditsc_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial); extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); -extern uid_t audit_get_loginuid(struct audit_context *ctx); +#define audit_get_loginuid(t) ((t)->loginuid) +#define audit_get_sessionid(t) ((t)->sessionid) extern void audit_log_task_context(struct audit_buffer *ab); extern int __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); @@ -488,7 +490,8 @@ extern int audit_signals; #define audit_inode_child(d,i,p) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) #define auditsc_get_stamp(c,t,s) do { BUG(); } while (0) -#define audit_get_loginuid(c) ({ -1; }) +#define audit_get_loginuid(t) (-1) +#define audit_get_sessionid(t) (-1) #define audit_log_task_context(b) do { ; } while (0) #define audit_ipc_obj(i) ({ 0; }) #define audit_ipc_set_perm(q,u,g,m) ({ 0; }) @@ -522,9 +525,11 @@ extern void audit_log_end(struct audit_buffer *ab); extern void audit_log_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); -extern const char * audit_log_untrustedstring(struct audit_buffer *ab, +extern int audit_string_contains_control(const char *string, + size_t len); +extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); -extern const char * audit_log_n_untrustedstring(struct audit_buffer *ab, +extern void audit_log_n_untrustedstring(struct audit_buffer *ab, size_t n, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, diff --git a/include/linux/futex.h b/include/linux/futex.h index 1a15f8e237a..90048fb28a3 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -21,6 +21,8 @@ union ktime; #define FUTEX_LOCK_PI 6 #define FUTEX_UNLOCK_PI 7 #define FUTEX_TRYLOCK_PI 8 +#define FUTEX_WAIT_BITSET 9 +#define FUTEX_WAKE_BITSET 10 #define FUTEX_PRIVATE_FLAG 128 #define FUTEX_CMD_MASK ~FUTEX_PRIVATE_FLAG @@ -33,6 +35,8 @@ union ktime; #define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG) +#define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG) +#define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG) /* * Support for robust futexes: the kernel cleans up held futexes at @@ -111,6 +115,12 @@ struct robust_list_head { */ #define ROBUST_LIST_LIMIT 2048 +/* + * bitset with all bits set for the FUTEX_xxx_BITSET OPs to request a + * match of any bit. + */ +#define FUTEX_BITSET_MATCH_ANY 0xffffffff + #ifdef __KERNEL__ long do_futex(u32 __user *uaddr, int op, u32 val, union ktime *timeout, u32 __user *uaddr2, u32 val2, u32 val3); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index e6b3f708067..f42663eaf65 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -114,6 +114,13 @@ extern struct group_info init_groups; .pid = &init_struct_pid, \ } +#ifdef CONFIG_AUDITSYSCALL +#define INIT_IDS \ + .loginuid = -1, \ + .sessionid = -1, +#else +#define INIT_IDS +#endif /* * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) @@ -173,6 +180,7 @@ extern struct group_info init_groups; [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \ }, \ .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \ + INIT_IDS \ INIT_TRACE_IRQFLAGS \ INIT_LOCKDEP \ } diff --git a/include/linux/sched.h b/include/linux/sched.h index 6c333579d9d..af6947e69b4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1139,6 +1139,10 @@ struct task_struct { void *security; #endif struct audit_context *audit_context; +#ifdef CONFIG_AUDITSYSCALL + uid_t loginuid; + unsigned int sessionid; +#endif seccomp_t seccomp; /* Thread group tracking */ diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index dfbdfb9836f..421323e5a2d 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -23,6 +23,7 @@ struct restart_block { u32 *uaddr; u32 val; u32 flags; + u32 bitset; u64 time; } futex; }; diff --git a/include/linux/tick.h b/include/linux/tick.h index 0fadf95debe..a881c652f7e 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -39,6 +39,8 @@ enum tick_nohz_mode { * @idle_calls: Total number of idle calls * @idle_sleeps: Number of idle calls, where the sched tick was stopped * @idle_entrytime: Time when the idle call was entered + * @idle_waketime: Time when the idle was interrupted + * @idle_exittime: Time when the idle state was left * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped * @sleep_length: Duration of the current idle sleep */ @@ -53,6 +55,8 @@ struct tick_sched { unsigned long idle_sleeps; int idle_active; ktime_t idle_entrytime; + ktime_t idle_waketime; + ktime_t idle_exittime; ktime_t idle_sleeptime; ktime_t idle_lastupdate; ktime_t sleep_length; diff --git a/include/linux/time.h b/include/linux/time.h index b04136d60a2..ceaab9fff15 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -122,6 +122,7 @@ extern void monotonic_to_bootbased(struct timespec *ts); extern struct timespec timespec_trunc(struct timespec t, unsigned gran); extern int timekeeping_is_continuous(void); extern void update_wall_time(void); +extern void update_xtime_cache(u64 nsec); /** * timespec_to_ns - Convert timespec to nanoseconds diff --git a/kernel/audit.c b/kernel/audit.c index 801c946dd24..c8555b18021 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -66,10 +66,11 @@ * (Initialization happens after skb_init is called.) */ static int audit_initialized; -/* 0 - no auditing - * 1 - auditing enabled - * 2 - auditing enabled and configuration is locked/unchangeable. */ +#define AUDIT_OFF 0 +#define AUDIT_ON 1 +#define AUDIT_LOCKED 2 int audit_enabled; +int audit_ever_enabled; /* Default state when kernel boots without any parameters. */ static int audit_default; @@ -152,8 +153,10 @@ struct audit_buffer { static void audit_set_pid(struct audit_buffer *ab, pid_t pid) { - struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); - nlh->nlmsg_pid = pid; + if (ab) { + struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); + nlh->nlmsg_pid = pid; + } } void audit_panic(const char *message) @@ -163,7 +166,8 @@ void audit_panic(const char *message) case AUDIT_FAIL_SILENT: break; case AUDIT_FAIL_PRINTK: - printk(KERN_ERR "audit: %s\n", message); + if (printk_ratelimit()) + printk(KERN_ERR "audit: %s\n", message); break; case AUDIT_FAIL_PANIC: panic("audit: %s\n", message); @@ -231,161 +235,107 @@ void audit_log_lost(const char *message) } if (print) { - printk(KERN_WARNING - "audit: audit_lost=%d audit_rate_limit=%d audit_backlog_limit=%d\n", - atomic_read(&audit_lost), - audit_rate_limit, - audit_backlog_limit); + if (printk_ratelimit()) + printk(KERN_WARNING + "audit: audit_lost=%d audit_rate_limit=%d " + "audit_backlog_limit=%d\n", + atomic_read(&audit_lost), + audit_rate_limit, + audit_backlog_limit); audit_panic(message); } } -static int audit_set_rate_limit(int limit, uid_t loginuid, u32 sid) +static int audit_log_config_change(char *function_name, int new, int old, + uid_t loginuid, u32 sid, int allow_changes) { - int res, rc = 0, old = audit_rate_limit; - - /* check if we are locked */ - if (audit_enabled == 2) - res = 0; - else - res = 1; + struct audit_buffer *ab; + int rc = 0; + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + audit_log_format(ab, "%s=%d old=%d by auid=%u", function_name, new, + old, loginuid); if (sid) { char *ctx = NULL; u32 len; - if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) { - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_rate_limit=%d old=%d by auid=%u" - " subj=%s res=%d", - limit, old, loginuid, ctx, res); + + rc = selinux_sid_to_string(sid, &ctx, &len); + if (rc) { + audit_log_format(ab, " sid=%u", sid); + allow_changes = 0; /* Something weird, deny request */ + } else { + audit_log_format(ab, " subj=%s", ctx); kfree(ctx); - } else - res = 0; /* Something weird, deny request */ + } } - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_rate_limit=%d old=%d by auid=%u res=%d", - limit, old, loginuid, res); - - /* If we are allowed, make the change */ - if (res == 1) - audit_rate_limit = limit; - /* Not allowed, update reason */ - else if (rc == 0) - rc = -EPERM; + audit_log_format(ab, " res=%d", allow_changes); + audit_log_end(ab); return rc; } -static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sid) +static int audit_do_config_change(char *function_name, int *to_change, + int new, uid_t loginuid, u32 sid) { - int res, rc = 0, old = audit_backlog_limit; + int allow_changes, rc = 0, old = *to_change; /* check if we are locked */ - if (audit_enabled == 2) - res = 0; + if (audit_enabled == AUDIT_LOCKED) + allow_changes = 0; else - res = 1; + allow_changes = 1; - if (sid) { - char *ctx = NULL; - u32 len; - if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) { - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_backlog_limit=%d old=%d by auid=%u" - " subj=%s res=%d", - limit, old, loginuid, ctx, res); - kfree(ctx); - } else - res = 0; /* Something weird, deny request */ + if (audit_enabled != AUDIT_OFF) { + rc = audit_log_config_change(function_name, new, old, + loginuid, sid, allow_changes); + if (rc) + allow_changes = 0; } - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_backlog_limit=%d old=%d by auid=%u res=%d", - limit, old, loginuid, res); /* If we are allowed, make the change */ - if (res == 1) - audit_backlog_limit = limit; + if (allow_changes == 1) + *to_change = new; /* Not allowed, update reason */ else if (rc == 0) rc = -EPERM; return rc; } -static int audit_set_enabled(int state, uid_t loginuid, u32 sid) +static int audit_set_rate_limit(int limit, uid_t loginuid, u32 sid) +{ + return audit_do_config_change("audit_rate_limit", &audit_rate_limit, + limit, loginuid, sid); +} + +static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sid) { - int res, rc = 0, old = audit_enabled; + return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, + limit, loginuid, sid); +} - if (state < 0 || state > 2) +static int audit_set_enabled(int state, uid_t loginuid, u32 sid) +{ + int rc; + if (state < AUDIT_OFF || state > AUDIT_LOCKED) return -EINVAL; - /* check if we are locked */ - if (audit_enabled == 2) - res = 0; - else - res = 1; + rc = audit_do_config_change("audit_enabled", &audit_enabled, state, + loginuid, sid); - if (sid) { - char *ctx = NULL; - u32 len; - if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) { - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_enabled=%d old=%d by auid=%u" - " subj=%s res=%d", - state, old, loginuid, ctx, res); - kfree(ctx); - } else - res = 0; /* Something weird, deny request */ - } - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_enabled=%d old=%d by auid=%u res=%d", - state, old, loginuid, res); + if (!rc) + audit_ever_enabled |= !!state; - /* If we are allowed, make the change */ - if (res == 1) - audit_enabled = state; - /* Not allowed, update reason */ - else if (rc == 0) - rc = -EPERM; return rc; } static int audit_set_failure(int state, uid_t loginuid, u32 sid) { - int res, rc = 0, old = audit_failure; - if (state != AUDIT_FAIL_SILENT && state != AUDIT_FAIL_PRINTK && state != AUDIT_FAIL_PANIC) return -EINVAL; - /* check if we are locked */ - if (audit_enabled == 2) - res = 0; - else - res = 1; - - if (sid) { - char *ctx = NULL; - u32 len; - if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) { - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_failure=%d old=%d by auid=%u" - " subj=%s res=%d", - state, old, loginuid, ctx, res); - kfree(ctx); - } else - res = 0; /* Something weird, deny request */ - } - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_failure=%d old=%d by auid=%u res=%d", - state, old, loginuid, res); - - /* If we are allowed, make the change */ - if (res == 1) - audit_failure = state; - /* Not allowed, update reason */ - else if (rc == 0) - rc = -EPERM; - return rc; + return audit_do_config_change("audit_failure", &audit_failure, state, + loginuid, sid); } static int kauditd_thread(void *dummy) @@ -405,7 +355,11 @@ static int kauditd_thread(void *dummy) audit_pid = 0; } } else { - printk(KERN_NOTICE "%s\n", skb->data + NLMSG_SPACE(0)); + if (printk_ratelimit()) + printk(KERN_NOTICE "%s\n", skb->data + + NLMSG_SPACE(0)); + else + audit_log_lost("printk limit exceeded\n"); kfree_skb(skb); } } else { @@ -573,6 +527,33 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) return err; } +static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type, + u32 pid, u32 uid, uid_t auid, u32 sid) +{ + int rc = 0; + char *ctx = NULL; + u32 len; + + if (!audit_enabled) { + *ab = NULL; + return rc; + } + + *ab = audit_log_start(NULL, GFP_KERNEL, msg_type); + audit_log_format(*ab, "user pid=%d uid=%u auid=%u", + pid, uid, auid); + if (sid) { + rc = selinux_sid_to_string(sid, &ctx, &len); + if (rc) + audit_log_format(*ab, " ssid=%u", sid); + else + audit_log_format(*ab, " subj=%s", ctx); + kfree(ctx); + } + + return rc; +} + static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 uid, pid, seq, sid; @@ -583,7 +564,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) u16 msg_type = nlh->nlmsg_type; uid_t loginuid; /* loginuid of sender */ struct audit_sig_info *sig_data; - char *ctx; + char *ctx = NULL; u32 len; err = audit_netlink_ok(skb, msg_type); @@ -634,23 +615,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) return err; } if (status_get->mask & AUDIT_STATUS_PID) { - int old = audit_pid; - if (sid) { - if ((err = selinux_sid_to_string( - sid, &ctx, &len))) - return err; - else - audit_log(NULL, GFP_KERNEL, - AUDIT_CONFIG_CHANGE, - "audit_pid=%d old=%d by auid=%u subj=%s", - status_get->pid, old, - loginuid, ctx); - kfree(ctx); - } else - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "audit_pid=%d old=%d by auid=%u", - status_get->pid, old, loginuid); - audit_pid = status_get->pid; + int new_pid = status_get->pid; + + if (audit_enabled != AUDIT_OFF) + audit_log_config_change("audit_pid", new_pid, + audit_pid, loginuid, + sid, 1); + + audit_pid = new_pid; } if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) err = audit_set_rate_limit(status_get->rate_limit, @@ -673,64 +645,35 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (err) break; } - ab = audit_log_start(NULL, GFP_KERNEL, msg_type); - if (ab) { - audit_log_format(ab, - "user pid=%d uid=%u auid=%u", - pid, uid, loginuid); - if (sid) { - if (selinux_sid_to_string( - sid, &ctx, &len)) { - audit_log_format(ab, - " ssid=%u", sid); - /* Maybe call audit_panic? */ - } else - audit_log_format(ab, - " subj=%s", ctx); - kfree(ctx); - } - if (msg_type != AUDIT_USER_TTY) - audit_log_format(ab, " msg='%.1024s'", - (char *)data); - else { - int size; - - audit_log_format(ab, " msg="); - size = nlmsg_len(nlh); - audit_log_n_untrustedstring(ab, size, - data); - } - audit_set_pid(ab, pid); - audit_log_end(ab); + audit_log_common_recv_msg(&ab, msg_type, pid, uid, + loginuid, sid); + + if (msg_type != AUDIT_USER_TTY) + audit_log_format(ab, " msg='%.1024s'", + (char *)data); + else { + int size; + + audit_log_format(ab, " msg="); + size = nlmsg_len(nlh); + audit_log_n_untrustedstring(ab, size, + data); } + audit_set_pid(ab, pid); + audit_log_end(ab); } break; case AUDIT_ADD: case AUDIT_DEL: if (nlmsg_len(nlh) < sizeof(struct audit_rule)) return -EINVAL; - if (audit_enabled == 2) { - ab = audit_log_start(NULL, GFP_KERNEL, - AUDIT_CONFIG_CHANGE); - if (ab) { - audit_log_format(ab, - "pid=%d uid=%u auid=%u", - pid, uid, loginuid); - if (sid) { - if (selinux_sid_to_string( - sid, &ctx, &len)) { - audit_log_format(ab, - " ssid=%u", sid); - /* Maybe call audit_panic? */ - } else - audit_log_format(ab, - " subj=%s", ctx); - kfree(ctx); - } - audit_log_format(ab, " audit_enabled=%d res=0", - audit_enabled); - audit_log_end(ab); - } + if (audit_enabled == AUDIT_LOCKED) { + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, + uid, loginuid, sid); + + audit_log_format(ab, " audit_enabled=%d res=0", + audit_enabled); + audit_log_end(ab); return -EPERM; } /* fallthrough */ @@ -743,28 +686,13 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_DEL_RULE: if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) return -EINVAL; - if (audit_enabled == 2) { - ab = audit_log_start(NULL, GFP_KERNEL, - AUDIT_CONFIG_CHANGE); - if (ab) { - audit_log_format(ab, - "pid=%d uid=%u auid=%u", - pid, uid, loginuid); - if (sid) { - if (selinux_sid_to_string( - sid, &ctx, &len)) { - audit_log_format(ab, - " ssid=%u", sid); - /* Maybe call audit_panic? */ - } else - audit_log_format(ab, - " subj=%s", ctx); - kfree(ctx); - } - audit_log_format(ab, " audit_enabled=%d res=0", - audit_enabled); - audit_log_end(ab); - } + if (audit_enabled == AUDIT_LOCKED) { + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, + uid, loginuid, sid); + + audit_log_format(ab, " audit_enabled=%d res=0", + audit_enabled); + audit_log_end(ab); return -EPERM; } /* fallthrough */ @@ -775,19 +703,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; case AUDIT_TRIM: audit_trim_trees(); - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); - if (!ab) - break; - audit_log_format(ab, "auid=%u", loginuid); - if (sid) { - u32 len; - ctx = NULL; - if (selinux_sid_to_string(sid, &ctx, &len)) - audit_log_format(ab, " ssid=%u", sid); - else - audit_log_format(ab, " subj=%s", ctx); - kfree(ctx); - } + + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, + uid, loginuid, sid); + audit_log_format(ab, " op=trim res=1"); audit_log_end(ab); break; @@ -817,22 +736,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) /* OK, here comes... */ err = audit_tag_tree(old, new); - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); - if (!ab) { - kfree(old); - kfree(new); - break; - } - audit_log_format(ab, "auid=%u", loginuid); - if (sid) { - u32 len; - ctx = NULL; - if (selinux_sid_to_string(sid, &ctx, &len)) - audit_log_format(ab, " ssid=%u", sid); - else - audit_log_format(ab, " subj=%s", ctx); - kfree(ctx); - } + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, + uid, loginuid, sid); + audit_log_format(ab, " op=make_equiv old="); audit_log_untrustedstring(ab, old); audit_log_format(ab, " new="); @@ -965,6 +871,7 @@ static int __init audit_init(void) skb_queue_head_init(&audit_skb_queue); audit_initialized = 1; audit_enabled = audit_default; + audit_ever_enabled |= !!audit_default; /* Register the callback with selinux. This callback will be invoked * when a new policy is loaded. */ @@ -992,8 +899,10 @@ static int __init audit_enable(char *str) printk(KERN_INFO "audit: %s%s\n", audit_default ? "enabled" : "disabled", audit_initialized ? "" : " (after initialization)"); - if (audit_initialized) + if (audit_initialized) { audit_enabled = audit_default; + audit_ever_enabled |= !!audit_default; + } return 1; } @@ -1130,7 +1039,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, { struct audit_buffer *ab = NULL; struct timespec t; - unsigned int serial; + unsigned int uninitialized_var(serial); int reserve; unsigned long timeout_start = jiffies; @@ -1164,7 +1073,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, remove_wait_queue(&audit_backlog_wait, &wait); continue; } - if (audit_rate_check()) + if (audit_rate_check() && printk_ratelimit()) printk(KERN_WARNING "audit: audit_backlog=%d > " "audit_backlog_limit=%d\n", @@ -1249,6 +1158,7 @@ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, goto out; len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); } + va_end(args2); if (len > 0) skb_put(skb, len); out: @@ -1350,6 +1260,21 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen, } /** + * audit_string_contains_control - does a string need to be logged in hex + * @string - string to be checked + * @len - max length of the string to check + */ +int audit_string_contains_control(const char *string, size_t len) +{ + const unsigned char *p; + for (p = string; p < (const unsigned char *)string + len && *p; p++) { + if (*p == '"' || *p < 0x21 || *p > 0x7f) + return 1; + } + return 0; +} + +/** * audit_log_n_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @len: lenth of string (not including trailing null) @@ -1363,19 +1288,13 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen, * The caller specifies the number of characters in the string to log, which may * or may not be the entire string. */ -const char *audit_log_n_untrustedstring(struct audit_buffer *ab, size_t len, - const char *string) +void audit_log_n_untrustedstring(struct audit_buffer *ab, size_t len, + const char *string) { - const unsigned char *p; - - for (p = string; p < (const unsigned char *)string + len && *p; p++) { - if (*p == '"' || *p < 0x21 || *p > 0x7f) { - audit_log_hex(ab, string, len); - return string + len + 1; - } - } - audit_log_n_string(ab, len, string); - return p + 1; + if (audit_string_contains_control(string, len)) + audit_log_hex(ab, string, len); + else + audit_log_n_string(ab, len, string); } /** @@ -1386,9 +1305,9 @@ const char *audit_log_n_untrustedstring(struct audit_buffer *ab, size_t len, * Same as audit_log_n_untrustedstring(), except that strlen is used to * determine string length. */ -const char *audit_log_untrustedstring(struct audit_buffer *ab, const char *string) +void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { - return audit_log_n_untrustedstring(ab, strlen(string), string); + audit_log_n_untrustedstring(ab, strlen(string), string); } /* This is a helper-function to print the escaped d_path */ @@ -1437,8 +1356,11 @@ void audit_log_end(struct audit_buffer *ab) skb_queue_tail(&audit_skb_queue, ab->skb); ab->skb = NULL; wake_up_interruptible(&kauditd_wait); + } else if (printk_ratelimit()) { + struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); + printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, ab->skb->data + NLMSG_SPACE(0)); } else { - printk(KERN_NOTICE "%s\n", ab->skb->data + NLMSG_SPACE(0)); + audit_log_lost("printk limit exceeded\n"); } } audit_buffer_free(ab); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 5d96f2cc7be..6f19fd477aa 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -95,6 +95,8 @@ extern struct inotify_handle *audit_ih; /* Inotify events we care about. */ #define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF +extern int audit_enabled; + void audit_free_parent(struct inotify_watch *i_watch) { struct audit_parent *parent; @@ -974,7 +976,6 @@ static void audit_update_watch(struct audit_parent *parent, struct audit_watch *owatch, *nwatch, *nextw; struct audit_krule *r, *nextr; struct audit_entry *oentry, *nentry; - struct audit_buffer *ab; mutex_lock(&audit_filter_mutex); list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) { @@ -1014,13 +1015,18 @@ static void audit_update_watch(struct audit_parent *parent, call_rcu(&oentry->rcu, audit_free_rule_rcu); } - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); - audit_log_format(ab, "op=updated rules specifying path="); - audit_log_untrustedstring(ab, owatch->path); - audit_log_format(ab, " with dev=%u ino=%lu\n", dev, ino); - audit_log_format(ab, " list=%d res=1", r->listnr); - audit_log_end(ab); - + if (audit_enabled) { + struct audit_buffer *ab; + ab = audit_log_start(NULL, GFP_KERNEL, + AUDIT_CONFIG_CHANGE); + audit_log_format(ab, + "op=updated rules specifying path="); + audit_log_untrustedstring(ab, owatch->path); + audit_log_format(ab, " with dev=%u ino=%lu\n", + dev, ino); + audit_log_format(ab, " list=%d res=1", r->listnr); + audit_log_end(ab); + } audit_remove_watch(owatch); goto add_watch_to_parent; /* event applies to a single watch */ } @@ -1039,25 +1045,28 @@ static void audit_remove_parent_watches(struct audit_parent *parent) struct audit_watch *w, *nextw; struct audit_krule *r, *nextr; struct audit_entry *e; - struct audit_buffer *ab; mutex_lock(&audit_filter_mutex); parent->flags |= AUDIT_PARENT_INVALID; list_for_each_entry_safe(w, nextw, &parent->watches, wlist) { list_for_each_entry_safe(r, nextr, &w->rules, rlist) { e = container_of(r, struct audit_entry, rule); - - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); - audit_log_format(ab, "op=remove rule path="); - audit_log_untrustedstring(ab, w->path); - if (r->filterkey) { - audit_log_format(ab, " key="); - audit_log_untrustedstring(ab, r->filterkey); - } else - audit_log_format(ab, " key=(null)"); - audit_log_format(ab, " list=%d res=1", r->listnr); - audit_log_end(ab); - + if (audit_enabled) { + struct audit_buffer *ab; + ab = audit_log_start(NULL, GFP_KERNEL, + AUDIT_CONFIG_CHANGE); + audit_log_format(ab, "op=remove rule path="); + audit_log_untrustedstring(ab, w->path); + if (r->filterkey) { + audit_log_format(ab, " key="); + audit_log_untrustedstring(ab, + r->filterkey); + } else + audit_log_format(ab, " key=(null)"); + audit_log_format(ab, " list=%d res=1", + r->listnr); + audit_log_end(ab); + } list_del(&r->rlist); list_del_rcu(&e->list); call_rcu(&e->rcu, audit_free_rule_rcu); @@ -1495,6 +1504,9 @@ static void audit_log_rule_change(uid_t loginuid, u32 sid, char *action, { struct audit_buffer *ab; + if (!audit_enabled) + return; + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index bce9ecdb771..1c06ecf38d7 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -70,6 +70,7 @@ #include "audit.h" extern struct list_head audit_filter_list[]; +extern int audit_ever_enabled; /* AUDIT_NAMES is the number of slots we reserve in the audit_context * for saving names from getname(). */ @@ -78,6 +79,9 @@ extern struct list_head audit_filter_list[]; /* Indicates that audit should log the full pathname. */ #define AUDIT_NAME_FULL -1 +/* no execve audit message should be longer than this (userspace limits) */ +#define MAX_EXECVE_AUDIT_LEN 7500 + /* number of audit rules */ int audit_n_rules; @@ -176,7 +180,11 @@ struct audit_aux_data_fd_pair { struct audit_aux_data_pids { struct audit_aux_data d; pid_t target_pid[AUDIT_AUX_PIDS]; + uid_t target_auid[AUDIT_AUX_PIDS]; + uid_t target_uid[AUDIT_AUX_PIDS]; + unsigned int target_sessionid[AUDIT_AUX_PIDS]; u32 target_sid[AUDIT_AUX_PIDS]; + char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN]; int pid_count; }; @@ -192,7 +200,6 @@ struct audit_context { enum audit_state state; unsigned int serial; /* serial number for record */ struct timespec ctime; /* time of syscall entry */ - uid_t loginuid; /* login uid (identity) */ int major; /* syscall number */ unsigned long argv[4]; /* syscall arguments */ int return_valid; /* return code is valid */ @@ -215,7 +222,11 @@ struct audit_context { int arch; pid_t target_pid; + uid_t target_auid; + uid_t target_uid; + unsigned int target_sessionid; u32 target_sid; + char target_comm[TASK_COMM_LEN]; struct audit_tree_refs *trees, *first_trees; int tree_count; @@ -506,7 +517,7 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_LOGINUID: result = 0; if (ctx) - result = audit_comparator(ctx->loginuid, f->op, f->val); + result = audit_comparator(tsk->loginuid, f->op, f->val); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: @@ -702,7 +713,24 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk, if (likely(!context)) return NULL; context->return_valid = return_valid; - context->return_code = return_code; + + /* + * we need to fix up the return code in the audit logs if the actual + * return codes are later going to be fixed up by the arch specific + * signal handlers + * + * This is actually a test for: + * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) || + * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK) + * + * but is faster than a bunch of || + */ + if (unlikely(return_code <= -ERESTARTSYS) && + (return_code >= -ERESTART_RESTARTBLOCK) && + (return_code != -ENOIOCTLCMD)) + context->return_code = -EINTR; + else + context->return_code = return_code; if (context->in_syscall && !context->dummy && !context->auditable) { enum audit_state state; @@ -783,11 +811,8 @@ static inline void audit_free_aux(struct audit_context *context) static inline void audit_zero_context(struct audit_context *context, enum audit_state state) { - uid_t loginuid = context->loginuid; - memset(context, 0, sizeof(*context)); context->state = state; - context->loginuid = loginuid; } static inline struct audit_context *audit_alloc_context(enum audit_state state) @@ -814,7 +839,7 @@ int audit_alloc(struct task_struct *tsk) struct audit_context *context; enum audit_state state; - if (likely(!audit_enabled)) + if (likely(!audit_ever_enabled)) return 0; /* Return if not auditing. */ state = audit_filter_task(tsk); @@ -826,11 +851,6 @@ int audit_alloc(struct task_struct *tsk) return -ENOMEM; } - /* Preserve login uid */ - context->loginuid = -1; - if (current->audit_context) - context->loginuid = current->audit_context->loginuid; - tsk->audit_context = context; set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); return 0; @@ -922,7 +942,8 @@ static void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk } static int audit_log_pid_context(struct audit_context *context, pid_t pid, - u32 sid) + uid_t auid, uid_t uid, unsigned int sessionid, + u32 sid, char *comm) { struct audit_buffer *ab; char *s = NULL; @@ -931,68 +952,204 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid, ab = audit_log_start(context, GFP_KERNEL, AUDIT_OBJ_PID); if (!ab) - return 1; + return rc; + audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, auid, + uid, sessionid); if (selinux_sid_to_string(sid, &s, &len)) { - audit_log_format(ab, "opid=%d obj=(none)", pid); + audit_log_format(ab, " obj=(none)"); rc = 1; } else - audit_log_format(ab, "opid=%d obj=%s", pid, s); + audit_log_format(ab, " obj=%s", s); + audit_log_format(ab, " ocomm="); + audit_log_untrustedstring(ab, comm); audit_log_end(ab); kfree(s); return rc; } -static void audit_log_execve_info(struct audit_buffer *ab, - struct audit_aux_data_execve *axi) +/* + * to_send and len_sent accounting are very loose estimates. We aren't + * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being + * within about 500 bytes (next page boundry) + * + * why snprintf? an int is up to 12 digits long. if we just assumed when + * logging that a[%d]= was going to be 16 characters long we would be wasting + * space in every audit message. In one 7500 byte message we can log up to + * about 1000 min size arguments. That comes down to about 50% waste of space + * if we didn't do the snprintf to find out how long arg_num_len was. + */ +static int audit_log_single_execve_arg(struct audit_context *context, + struct audit_buffer **ab, + int arg_num, + size_t *len_sent, + const char __user *p, + char *buf) { - int i; - long len, ret; - const char __user *p; - char *buf; + char arg_num_len_buf[12]; + const char __user *tmp_p = p; + /* how many digits are in arg_num? 3 is the length of a=\n */ + size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 3; + size_t len, len_left, to_send; + size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN; + unsigned int i, has_cntl = 0, too_long = 0; + int ret; + + /* strnlen_user includes the null we don't want to send */ + len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1; - if (axi->mm != current->mm) - return; /* execve failed, no additional info */ - - p = (const char __user *)axi->mm->arg_start; + /* + * We just created this mm, if we can't find the strings + * we just copied into it something is _very_ wrong. Similar + * for strings that are too long, we should not have created + * any. + */ + if (unlikely((len = -1) || len > MAX_ARG_STRLEN - 1)) { + WARN_ON(1); + send_sig(SIGKILL, current, 0); + } - for (i = 0; i < axi->argc; i++, p += len) { - len = strnlen_user(p, MAX_ARG_STRLEN); + /* walk the whole argument looking for non-ascii chars */ + do { + if (len_left > MAX_EXECVE_AUDIT_LEN) + to_send = MAX_EXECVE_AUDIT_LEN; + else + to_send = len_left; + ret = copy_from_user(buf, tmp_p, to_send); /* - * We just created this mm, if we can't find the strings - * we just copied into it something is _very_ wrong. Similar - * for strings that are too long, we should not have created - * any. + * There is no reason for this copy to be short. We just + * copied them here, and the mm hasn't been exposed to user- + * space yet. */ - if (!len || len > MAX_ARG_STRLEN) { + if (ret) { WARN_ON(1); send_sig(SIGKILL, current, 0); } - - buf = kmalloc(len, GFP_KERNEL); - if (!buf) { - audit_panic("out of memory for argv string\n"); + buf[to_send] = '\0'; + has_cntl = audit_string_contains_control(buf, to_send); + if (has_cntl) { + /* + * hex messages get logged as 2 bytes, so we can only + * send half as much in each message + */ + max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2; break; } + len_left -= to_send; + tmp_p += to_send; + } while (len_left > 0); + + len_left = len; + + if (len > max_execve_audit_len) + too_long = 1; + + /* rewalk the argument actually logging the message */ + for (i = 0; len_left > 0; i++) { + int room_left; + + if (len_left > max_execve_audit_len) + to_send = max_execve_audit_len; + else + to_send = len_left; + + /* do we have space left to send this argument in this ab? */ + room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent; + if (has_cntl) + room_left -= (to_send * 2); + else + room_left -= to_send; + if (room_left < 0) { + *len_sent = 0; + audit_log_end(*ab); + *ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE); + if (!*ab) + return 0; + } - ret = copy_from_user(buf, p, len); /* - * There is no reason for this copy to be short. We just - * copied them here, and the mm hasn't been exposed to user- - * space yet. + * first record needs to say how long the original string was + * so we can be sure nothing was lost. + */ + if ((i == 0) && (too_long)) + audit_log_format(*ab, "a%d_len=%ld ", arg_num, + has_cntl ? 2*len : len); + + /* + * normally arguments are small enough to fit and we already + * filled buf above when we checked for control characters + * so don't bother with another copy_from_user */ + if (len >= max_execve_audit_len) + ret = copy_from_user(buf, p, to_send); + else + ret = 0; if (ret) { WARN_ON(1); send_sig(SIGKILL, current, 0); } + buf[to_send] = '\0'; + + /* actually log it */ + audit_log_format(*ab, "a%d", arg_num); + if (too_long) + audit_log_format(*ab, "[%d]", i); + audit_log_format(*ab, "="); + if (has_cntl) + audit_log_hex(*ab, buf, to_send); + else + audit_log_format(*ab, "\"%s\"", buf); + audit_log_format(*ab, "\n"); + + p += to_send; + len_left -= to_send; + *len_sent += arg_num_len; + if (has_cntl) + *len_sent += to_send * 2; + else + *len_sent += to_send; + } + /* include the null we didn't log */ + return len + 1; +} - audit_log_format(ab, "a%d=", i); - audit_log_untrustedstring(ab, buf); - audit_log_format(ab, "\n"); +static void audit_log_execve_info(struct audit_context *context, + struct audit_buffer **ab, + struct audit_aux_data_execve *axi) +{ + int i; + size_t len, len_sent = 0; + const char __user *p; + char *buf; + + if (axi->mm != current->mm) + return; /* execve failed, no additional info */ + + p = (const char __user *)axi->mm->arg_start; + + audit_log_format(*ab, "argc=%d ", axi->argc); + + /* + * we need some kernel buffer to hold the userspace args. Just + * allocate one big one rather than allocating one of the right size + * for every single argument inside audit_log_single_execve_arg() + * should be <8k allocation so should be pretty safe. + */ + buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL); + if (!buf) { + audit_panic("out of memory for argv string\n"); + return; + } - kfree(buf); + for (i = 0; i < axi->argc; i++) { + len = audit_log_single_execve_arg(context, ab, i, + &len_sent, p, buf); + if (len <= 0) + break; + p += len; } + kfree(buf); } static void audit_log_exit(struct audit_context *context, struct task_struct *tsk) @@ -1039,7 +1196,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts " a0=%lx a1=%lx a2=%lx a3=%lx items=%d" " ppid=%d pid=%d auid=%u uid=%u gid=%u" " euid=%u suid=%u fsuid=%u" - " egid=%u sgid=%u fsgid=%u tty=%s", + " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", context->argv[0], context->argv[1], context->argv[2], @@ -1047,11 +1204,12 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts context->name_count, context->ppid, context->pid, - context->loginuid, + tsk->loginuid, context->uid, context->gid, context->euid, context->suid, context->fsuid, - context->egid, context->sgid, context->fsgid, tty); + context->egid, context->sgid, context->fsgid, tty, + tsk->sessionid); mutex_unlock(&tty_mutex); @@ -1135,7 +1293,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts case AUDIT_EXECVE: { struct audit_aux_data_execve *axi = (void *)aux; - audit_log_execve_info(ab, axi); + audit_log_execve_info(context, &ab, axi); break; } case AUDIT_SOCKETCALL: { @@ -1168,13 +1326,19 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts for (i = 0; i < axs->pid_count; i++) if (audit_log_pid_context(context, axs->target_pid[i], - axs->target_sid[i])) + axs->target_auid[i], + axs->target_uid[i], + axs->target_sessionid[i], + axs->target_sid[i], + axs->target_comm[i])) call_panic = 1; } if (context->target_pid && audit_log_pid_context(context, context->target_pid, - context->target_sid)) + context->target_auid, context->target_uid, + context->target_sessionid, + context->target_sid, context->target_comm)) call_panic = 1; if (context->pwd && context->pwdmnt) { @@ -1242,6 +1406,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts audit_log_end(ab); } + + /* Send end of event record to help user space know we are finished */ + ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE); + if (ab) + audit_log_end(ab); if (call_panic) audit_panic("error converting sid to string"); } @@ -1766,6 +1935,9 @@ void auditsc_get_stamp(struct audit_context *ctx, ctx->auditable = 1; } +/* global counter which is incremented every time something logs in */ +static atomic_t session_id = ATOMIC_INIT(0); + /** * audit_set_loginuid - set a task's audit_context loginuid * @task: task whose audit context is being modified @@ -1777,41 +1949,29 @@ void auditsc_get_stamp(struct audit_context *ctx, */ int audit_set_loginuid(struct task_struct *task, uid_t loginuid) { + unsigned int sessionid = atomic_inc_return(&session_id); struct audit_context *context = task->audit_context; - if (context) { - /* Only log if audit is enabled */ - if (context->in_syscall) { - struct audit_buffer *ab; - - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); - if (ab) { - audit_log_format(ab, "login pid=%d uid=%u " - "old auid=%u new auid=%u", - task->pid, task->uid, - context->loginuid, loginuid); - audit_log_end(ab); - } + if (context && context->in_syscall) { + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); + if (ab) { + audit_log_format(ab, "login pid=%d uid=%u " + "old auid=%u new auid=%u" + " old ses=%u new ses=%u", + task->pid, task->uid, + task->loginuid, loginuid, + task->sessionid, sessionid); + audit_log_end(ab); } - context->loginuid = loginuid; } + task->sessionid = sessionid; + task->loginuid = loginuid; return 0; } /** - * audit_get_loginuid - get the loginuid for an audit_context - * @ctx: the audit_context - * - * Returns the context's loginuid or -1 if @ctx is NULL. - */ -uid_t audit_get_loginuid(struct audit_context *ctx) -{ - return ctx ? ctx->loginuid : -1; -} - -EXPORT_SYMBOL(audit_get_loginuid); - -/** * __audit_mq_open - record audit data for a POSIX MQ open * @oflag: open flag * @mode: mode bits @@ -2070,8 +2230,6 @@ int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode return 0; } -int audit_argv_kb = 32; - int audit_bprm(struct linux_binprm *bprm) { struct audit_aux_data_execve *ax; @@ -2080,14 +2238,6 @@ int audit_bprm(struct linux_binprm *bprm) if (likely(!audit_enabled || !context || context->dummy)) return 0; - /* - * Even though the stack code doesn't limit the arg+env size any more, - * the audit code requires that _all_ arguments be logged in a single - * netlink skb. Hence cap it :-( - */ - if (bprm->argv_len > (audit_argv_kb << 10)) - return -E2BIG; - ax = kmalloc(sizeof(*ax), GFP_KERNEL); if (!ax) return -ENOMEM; @@ -2193,7 +2343,11 @@ void __audit_ptrace(struct task_struct *t) struct audit_context *context = current->audit_context; context->target_pid = t->pid; + context->target_auid = audit_get_loginuid(t); + context->target_uid = t->uid; + context->target_sessionid = audit_get_sessionid(t); selinux_get_task_sid(t, &context->target_sid); + memcpy(context->target_comm, t->comm, TASK_COMM_LEN); } /** @@ -2216,8 +2370,8 @@ int __audit_signal_info(int sig, struct task_struct *t) if (audit_pid && t->tgid == audit_pid) { if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1) { audit_sig_pid = tsk->pid; - if (ctx) - audit_sig_uid = ctx->loginuid; + if (tsk->loginuid != -1) + audit_sig_uid = tsk->loginuid; else audit_sig_uid = tsk->uid; selinux_get_task_sid(tsk, &audit_sig_sid); @@ -2230,7 +2384,11 @@ int __audit_signal_info(int sig, struct task_struct *t) * in audit_context */ if (!ctx->target_pid) { ctx->target_pid = t->tgid; + ctx->target_auid = audit_get_loginuid(t); + ctx->target_uid = t->uid; + ctx->target_sessionid = audit_get_sessionid(t); selinux_get_task_sid(t, &ctx->target_sid); + memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); return 0; } @@ -2247,7 +2405,11 @@ int __audit_signal_info(int sig, struct task_struct *t) BUG_ON(axp->pid_count >= AUDIT_AUX_PIDS); axp->target_pid[axp->pid_count] = t->tgid; + axp->target_auid[axp->pid_count] = audit_get_loginuid(t); + axp->target_uid[axp->pid_count] = t->uid; + axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); selinux_get_task_sid(t, &axp->target_sid[axp->pid_count]); + memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); axp->pid_count++; return 0; @@ -2264,6 +2426,8 @@ void audit_core_dumps(long signr) { struct audit_buffer *ab; u32 sid; + uid_t auid = audit_get_loginuid(current); + unsigned int sessionid = audit_get_sessionid(current); if (!audit_enabled) return; @@ -2272,9 +2436,8 @@ void audit_core_dumps(long signr) return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); - audit_log_format(ab, "auid=%u uid=%u gid=%u", - audit_get_loginuid(current->audit_context), - current->uid, current->gid); + audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", + auid, current->uid, current->gid, sessionid); selinux_get_task_sid(current, &sid); if (sid) { char *ctx = NULL; diff --git a/kernel/futex.c b/kernel/futex.c index db9824de8bf..a6baaec44b8 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -109,6 +109,9 @@ struct futex_q { /* Optional priority inheritance state: */ struct futex_pi_state *pi_state; struct task_struct *task; + + /* Bitset for the optional bitmasked wakeup */ + u32 bitset; }; /* @@ -722,7 +725,7 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) * to this virtual address: */ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, - int nr_wake) + int nr_wake, u32 bitset) { struct futex_hash_bucket *hb; struct futex_q *this, *next; @@ -730,6 +733,9 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, union futex_key key; int ret; + if (!bitset) + return -EINVAL; + futex_lock_mm(fshared); ret = get_futex_key(uaddr, fshared, &key); @@ -746,6 +752,11 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, ret = -EINVAL; break; } + + /* Check if one of the bits is set in both bitsets */ + if (!(this->bitset & bitset)) + continue; + wake_futex(this); if (++ret >= nr_wake) break; @@ -1156,7 +1167,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, static long futex_wait_restart(struct restart_block *restart); static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, - u32 val, ktime_t *abs_time) + u32 val, ktime_t *abs_time, u32 bitset) { struct task_struct *curr = current; DECLARE_WAITQUEUE(wait, curr); @@ -1167,7 +1178,11 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, struct hrtimer_sleeper t; int rem = 0; + if (!bitset) + return -EINVAL; + q.pi_state = NULL; + q.bitset = bitset; retry: futex_lock_mm(fshared); @@ -1252,6 +1267,8 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, t.timer.expires = *abs_time; hrtimer_start(&t.timer, t.timer.expires, HRTIMER_MODE_ABS); + if (!hrtimer_active(&t.timer)) + t.task = NULL; /* * the timer could have already expired, in which @@ -1293,6 +1310,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, restart->futex.uaddr = (u32 *)uaddr; restart->futex.val = val; restart->futex.time = abs_time->tv64; + restart->futex.bitset = bitset; restart->futex.flags = 0; if (fshared) @@ -1319,7 +1337,8 @@ static long futex_wait_restart(struct restart_block *restart) restart->fn = do_no_restart_syscall; if (restart->futex.flags & FLAGS_SHARED) fshared = ¤t->mm->mmap_sem; - return (long)futex_wait(uaddr, fshared, restart->futex.val, &t); + return (long)futex_wait(uaddr, fshared, restart->futex.val, &t, + restart->futex.bitset); } @@ -1535,9 +1554,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, owner = rt_mutex_owner(&q.pi_state->pi_mutex); res = fixup_pi_state_owner(uaddr, &q, owner); - WARN_ON(rt_mutex_owner(&q.pi_state->pi_mutex) != - owner); - /* propagate -EFAULT, if the fixup failed */ if (res) ret = res; @@ -1943,7 +1959,8 @@ retry: * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, &curr->mm->mmap_sem, 1); + futex_wake(uaddr, &curr->mm->mmap_sem, 1, + FUTEX_BITSET_MATCH_ANY); } return 0; } @@ -2043,10 +2060,14 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, switch (cmd) { case FUTEX_WAIT: - ret = futex_wait(uaddr, fshared, val, timeout); + val3 = FUTEX_BITSET_MATCH_ANY; + case FUTEX_WAIT_BITSET: + ret = futex_wait(uaddr, fshared, val, timeout, val3); break; case FUTEX_WAKE: - ret = futex_wake(uaddr, fshared, val); + val3 = FUTEX_BITSET_MATCH_ANY; + case FUTEX_WAKE_BITSET: + ret = futex_wake(uaddr, fshared, val, val3); break; case FUTEX_FD: /* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */ @@ -2086,7 +2107,8 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, u32 val2 = 0; int cmd = op & FUTEX_CMD_MASK; - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI)) { + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET)) { if (copy_from_user(&ts, utime, sizeof(ts)) != 0) return -EFAULT; if (!timespec_valid(&ts)) diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 0a43def6fee..133d558db45 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -167,7 +167,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, int val2 = 0; int cmd = op & FUTEX_CMD_MASK; - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI)) { + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET)) { if (get_compat_timespec(&ts, utime)) return -EFAULT; if (!timespec_valid(&ts)) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index bd5d6b5060b..1069998fe25 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1315,6 +1315,8 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod } while (t->task && !signal_pending(current)); + __set_current_state(TASK_RUNNING); + return t->task == NULL; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 357b68ba23e..7cb1ac3e6ff 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -81,7 +81,6 @@ extern int percpu_pagelist_fraction; extern int compat_log; extern int maps_protect; extern int sysctl_stat_interval; -extern int audit_argv_kb; extern int latencytop_enabled; /* Constants used for minimum and maximum */ @@ -390,16 +389,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, -#ifdef CONFIG_AUDITSYSCALL - { - .ctl_name = CTL_UNNUMBERED, - .procname = "audit_argv_kb", - .data = &audit_argv_kb, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, -#endif { .ctl_name = KERN_CORE_PATTERN, .procname = "core_pattern", diff --git a/kernel/time.c b/kernel/time.c index 09d3c45c4da..4064c0566e7 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -129,6 +129,7 @@ static inline void warp_clock(void) write_seqlock_irq(&xtime_lock); wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60; xtime.tv_sec += sys_tz.tz_minuteswest * 60; + update_xtime_cache(0); write_sequnlock_irq(&xtime_lock); clock_was_set(); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 63f24b55069..88267f0a847 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -137,6 +137,7 @@ void tick_nohz_update_jiffies(void) cpu_clear(cpu, nohz_cpu_mask); now = ktime_get(); + ts->idle_waketime = now; local_irq_save(flags); tick_do_update_jiffies64(now); @@ -400,6 +401,7 @@ void tick_nohz_restart_sched_tick(void) * Cancel the scheduled timer and restore the tick */ ts->tick_stopped = 0; + ts->idle_exittime = now; hrtimer_cancel(&ts->sched_timer); ts->sched_timer.expires = ts->idle_tick; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 092a2366b5a..cd5dbc4579c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -47,7 +47,7 @@ struct timespec wall_to_monotonic __attribute__ ((aligned (16))); static unsigned long total_sleep_time; /* seconds */ static struct timespec xtime_cache __attribute__ ((aligned (16))); -static inline void update_xtime_cache(u64 nsec) +void update_xtime_cache(u64 nsec) { xtime_cache = xtime; timespec_add_ns(&xtime_cache, nsec); @@ -145,6 +145,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); + update_xtime_cache(0); clock->error = 0; ntp_clear(); @@ -252,8 +253,8 @@ void __init timekeeping_init(void) xtime.tv_nsec = 0; set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec); + update_xtime_cache(0); total_sleep_time = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); } @@ -290,6 +291,7 @@ static int timekeeping_resume(struct sys_device *dev) } /* Make sure that we have the correct xtime reference */ timespec_add_ns(&xtime, timekeeping_suspend_nsecs); + update_xtime_cache(0); /* re-base the last cycle value */ clock->cycle_last = clocksource_read(clock); clock->error = 0; diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 12c5f4cb6b8..d3d94c1a0fd 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -166,6 +166,8 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) P(idle_calls); P(idle_sleeps); P_ns(idle_entrytime); + P_ns(idle_waketime); + P_ns(idle_exittime); P_ns(idle_sleeptime); P(last_jiffies); P(next_jiffies); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 89f4035b526..0d8a5a4a789 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -581,7 +581,7 @@ config LATENCYTOP select STACKTRACE select SCHEDSTATS select SCHED_DEBUG - depends on X86 || X86_64 + depends on HAVE_LATENCYTOP_SUPPORT help Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. diff --git a/net/core/dev.c b/net/core/dev.c index edaff2720e1..9549417250b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2752,12 +2752,15 @@ static void __dev_set_promiscuity(struct net_device *dev, int inc) printk(KERN_INFO "device %s %s promiscuous mode\n", dev->name, (dev->flags & IFF_PROMISC) ? "entered" : "left"); - audit_log(current->audit_context, GFP_ATOMIC, - AUDIT_ANOM_PROMISCUOUS, - "dev=%s prom=%d old_prom=%d auid=%u", - dev->name, (dev->flags & IFF_PROMISC), - (old_flags & IFF_PROMISC), - audit_get_loginuid(current->audit_context)); + if (audit_enabled) + audit_log(current->audit_context, GFP_ATOMIC, + AUDIT_ANOM_PROMISCUOUS, + "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", + dev->name, (dev->flags & IFF_PROMISC), + (old_flags & IFF_PROMISC), + audit_get_loginuid(current), + current->uid, current->gid, + audit_get_sessionid(current)); if (dev->change_rx_flags) dev->change_rx_flags(dev, IFF_PROMISC); diff --git a/net/key/af_key.c b/net/key/af_key.c index 16b72b5570c..45c3c27d279 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1466,7 +1466,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, err = xfrm_state_update(x); xfrm_audit_state_add(x, err ? 0 : 1, - audit_get_loginuid(current->audit_context), 0); + audit_get_loginuid(current), 0); if (err < 0) { x->km.state = XFRM_STATE_DEAD; @@ -1520,7 +1520,7 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h km_state_notify(x, &c); out: xfrm_audit_state_delete(x, err ? 0 : 1, - audit_get_loginuid(current->audit_context), 0); + audit_get_loginuid(current), 0); xfrm_state_put(x); return err; @@ -1695,7 +1695,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hd if (proto == 0) return -EINVAL; - audit_info.loginuid = audit_get_loginuid(current->audit_context); + audit_info.loginuid = audit_get_loginuid(current); audit_info.secid = 0; err = xfrm_state_flush(proto, &audit_info); if (err) @@ -2273,7 +2273,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h hdr->sadb_msg_type != SADB_X_SPDUPDATE); xfrm_audit_policy_add(xp, err ? 0 : 1, - audit_get_loginuid(current->audit_context), 0); + audit_get_loginuid(current), 0); if (err) goto out; @@ -2356,7 +2356,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg return -ENOENT; xfrm_audit_policy_delete(xp, err ? 0 : 1, - audit_get_loginuid(current->audit_context), 0); + audit_get_loginuid(current), 0); if (err) goto out; @@ -2617,7 +2617,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h if (delete) { xfrm_audit_policy_delete(xp, err ? 0 : 1, - audit_get_loginuid(current->audit_context), 0); + audit_get_loginuid(current), 0); if (err) goto out; @@ -2694,7 +2694,7 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg struct xfrm_audit audit_info; int err; - audit_info.loginuid = audit_get_loginuid(current->audit_context); + audit_info.loginuid = audit_get_loginuid(current); audit_info.secid = 0; err = xfrm_policy_flush(XFRM_POLICY_TYPE_MAIN, &audit_info); if (err) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index ff9fb6ba0c5..1ab0da2632e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1238,7 +1238,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, NETLINK_CB(skb).pid = nlk->pid; NETLINK_CB(skb).dst_group = dst_group; - NETLINK_CB(skb).loginuid = audit_get_loginuid(current->audit_context); + NETLINK_CB(skb).loginuid = audit_get_loginuid(current); selinux_get_task_sid(current, &(NETLINK_CB(skb).sid)); memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 3ff76e84d54..7ba65e82941 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -493,7 +493,7 @@ expired: km_state_expired(x, 1, 0); xfrm_audit_state_delete(x, err ? 0 : 1, - audit_get_loginuid(current->audit_context), 0); + audit_get_loginuid(current), 0); out: spin_unlock(&x->lock); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index a85740530af..0341567665b 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -172,9 +172,10 @@ static ssize_t sel_write_enforce(struct file * file, const char __user * buf, if (length) goto out; audit_log(current->audit_context, GFP_KERNEL, AUDIT_MAC_STATUS, - "enforcing=%d old_enforcing=%d auid=%u", new_value, - selinux_enforcing, - audit_get_loginuid(current->audit_context)); + "enforcing=%d old_enforcing=%d auid=%u ses=%u", + new_value, selinux_enforcing, + audit_get_loginuid(current), + audit_get_sessionid(current)); selinux_enforcing = new_value; if (selinux_enforcing) avc_ss_reset(0); @@ -243,8 +244,9 @@ static ssize_t sel_write_disable(struct file * file, const char __user * buf, if (length < 0) goto out; audit_log(current->audit_context, GFP_KERNEL, AUDIT_MAC_STATUS, - "selinux=0 auid=%u", - audit_get_loginuid(current->audit_context)); + "selinux=0 auid=%u ses=%u", + audit_get_loginuid(current), + audit_get_sessionid(current)); } length = count; @@ -356,8 +358,9 @@ out1: (security_get_allow_unknown() ? "allow" : "deny"))); audit_log(current->audit_context, GFP_KERNEL, AUDIT_MAC_POLICY_LOAD, - "policy loaded auid=%u", - audit_get_loginuid(current->audit_context)); + "policy loaded auid=%u ses=%u", + audit_get_loginuid(current), + audit_get_sessionid(current)); out: mutex_unlock(&sel_mutex); vfree(data); diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 880d455aa65..fced6bccee7 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -1905,11 +1905,12 @@ int security_set_bools(int len, int *values) if (!!values[i] != policydb.bool_val_to_struct[i]->state) { audit_log(current->audit_context, GFP_ATOMIC, AUDIT_MAC_CONFIG_CHANGE, - "bool=%s val=%d old_val=%d auid=%u", + "bool=%s val=%d old_val=%d auid=%u ses=%u", policydb.p_bool_val_to_name[i], !!values[i], policydb.bool_val_to_struct[i]->state, - audit_get_loginuid(current->audit_context)); + audit_get_loginuid(current), + audit_get_sessionid(current)); } if (values[i]) { policydb.bool_val_to_struct[i]->state = 1; |